id	sid	tid	token	lemma	pos
cana-3838	1	1	communications	communication	NOUN
cana-3838	1	2	on	on	ADP
cana-3838	1	3	applied	apply	VERB
cana-3838	1	4	nonlinear	nonlinear	ADJ
cana-3838	1	5	analysis	analysis	NOUN
cana-3838	1	6	issn	issn	NOUN
cana-3838	1	7	:	:	PUNCT
cana-3838	1	8	1074	1074	NUM
cana-3838	1	9	-	-	PUNCT
cana-3838	1	10	133x	133x	NUM
cana-3838	1	11	vol	vol	NOUN
cana-3838	1	12	32	32	NUM
cana-3838	1	13	no	no	NOUN
cana-3838	1	14	.	.	PUNCT
cana-3838	2	1	9s	9s	NUM
cana-3838	2	2	(	(	PUNCT
cana-3838	2	3	2025	2025	NUM
cana-3838	2	4	)	)	PUNCT
cana-3838	2	5	63	63	NUM
cana-3838	2	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-3838	2	7	a	a	DET
cana-3838	2	8	hybrid	hybrid	ADJ
cana-3838	2	9	model	model	NOUN
cana-3838	2	10	for	for	ADP
cana-3838	2	11	brain	brain	NOUN
cana-3838	2	12	tumor	tumor	NOUN
cana-3838	2	13	segmentation	segmentation	NOUN
cana-3838	2	14	using	use	VERB
cana-3838	2	15	vgg16	vgg16	PROPN
cana-3838	2	16	and	and	CCONJ
cana-3838	2	17	resnet50	resnet50	VERB
cana-3838	2	18	1dr.v.r	1dr.v.r	NOUN
cana-3838	2	19	.	.	PUNCT
cana-3838	3	1	elangovan	elangovan	PROPN
cana-3838	3	2	,	,	PUNCT
cana-3838	3	3	2	2	NUM
cana-3838	3	4	dr.d.helen	dr.d.helen	PROPN
cana-3838	3	5	*	*	PROPN
cana-3838	3	6	,	,	PUNCT
cana-3838	3	7	3dr.s.gokila	3dr.s.gokila	NUM
cana-3838	3	8	,	,	PUNCT
cana-3838	3	9	4dr.s.rajeswari	4dr.s.rajeswari	NUM
cana-3838	3	10	,	,	PUNCT
cana-3838	3	11	5dr.m.ganesh	5dr.m.ganesh	PROPN
cana-3838	3	12	raja	raja	PROPN
cana-3838	3	13	1assistant	1assistant	NUM
cana-3838	3	14	professor	professor	NOUN
cana-3838	3	15	,	,	PUNCT
cana-3838	3	16	department	department	NOUN
cana-3838	3	17	of	of	ADP
cana-3838	3	18	computer	computer	NOUN
cana-3838	3	19	applications	application	NOUN
cana-3838	3	20	,	,	PUNCT
cana-3838	3	21	faculty	faculty	NOUN
cana-3838	3	22	of	of	ADP
cana-3838	3	23	science	science	NOUN
cana-3838	3	24	and	and	CCONJ
cana-3838	3	25	humanities	humanity	NOUN
cana-3838	3	26	,	,	PUNCT
cana-3838	3	27	srm	srm	PROPN
cana-3838	3	28	institute	institute	PROPN
cana-3838	3	29	of	of	ADP
cana-3838	3	30	science	science	NOUN
cana-3838	3	31	and	and	CCONJ
cana-3838	3	32	technology	technology	NOUN
cana-3838	3	33	,	,	PUNCT
cana-3838	3	34	kattankulathur	kattankulathur	PROPN
cana-3838	3	35	,	,	PUNCT
cana-3838	3	36	chennai	chennai	PROPN
cana-3838	3	37	.	.	PUNCT
cana-3838	4	1	elangotesting@gmail.com,elangovv1@srmist.edu.in	elangotesting@gmail.com,elangovv1@srmist.edu.in	PROPN
cana-3838	4	2	2*assistant	2*assistant	PROPN
cana-3838	4	3	professor	professor	NOUN
cana-3838	4	4	,	,	PUNCT
cana-3838	4	5	department	department	NOUN
cana-3838	4	6	of	of	ADP
cana-3838	4	7	computer	computer	NOUN
cana-3838	4	8	applications	application	NOUN
cana-3838	4	9	,	,	PUNCT
cana-3838	4	10	faculty	faculty	NOUN
cana-3838	4	11	of	of	ADP
cana-3838	4	12	science	science	NOUN
cana-3838	4	13	and	and	CCONJ
cana-3838	4	14	humanities	humanity	NOUN
cana-3838	4	15	,	,	PUNCT
cana-3838	4	16	srm	srm	PROPN
cana-3838	4	17	institute	institute	PROPN
cana-3838	4	18	of	of	ADP
cana-3838	4	19	science	science	NOUN
cana-3838	4	20	and	and	CCONJ
cana-3838	4	21	technology	technology	NOUN
cana-3838	4	22	,	,	PUNCT
cana-3838	4	23	kattankulathur	kattankulathur	PROPN
cana-3838	4	24	,	,	PUNCT
cana-3838	4	25	chennai	chennai	PROPN
cana-3838	4	26	.	.	PUNCT
cana-3838	5	1	helensaran15@gmail.com	helensaran15@gmail.com	X
cana-3838	5	2	3professor	3professor	NUM
cana-3838	5	3	,	,	PUNCT
cana-3838	5	4	department	department	NOUN
cana-3838	5	5	of	of	ADP
cana-3838	5	6	computer	computer	NOUN
cana-3838	5	7	applications	application	NOUN
cana-3838	5	8	,	,	PUNCT
cana-3838	5	9	hindustan	hindustan	PROPN
cana-3838	5	10	institute	institute	PROPN
cana-3838	5	11	of	of	ADP
cana-3838	5	12	technology	technology	PROPN
cana-3838	5	13	and	and	CCONJ
cana-3838	5	14	science	science	NOUN
cana-3838	5	15	,	,	PUNCT
cana-3838	5	16	chennai	chennai	PROPN
cana-3838	5	17	,	,	PUNCT
cana-3838	5	18	sgokilas@gmail.com	sgokilas@gmail.com	PROPN
cana-3838	6	1	4assistant	4assistant	NUM
cana-3838	6	2	professor	professor	NOUN
cana-3838	6	3	,	,	PUNCT
cana-3838	6	4	pg	pg	PROPN
cana-3838	6	5	department	department	PROPN
cana-3838	6	6	of	of	ADP
cana-3838	6	7	computer	computer	NOUN
cana-3838	6	8	science	science	NOUN
cana-3838	6	9	,	,	PUNCT
cana-3838	6	10	shrimathi	shrimathi	PROPN
cana-3838	6	11	devkunvar	devkunvar	PROPN
cana-3838	6	12	nanalal	nanalal	PROPN
cana-3838	6	13	bhatt	bhatt	PROPN
cana-3838	6	14	vaishnav	vaishnav	PROPN
cana-3838	6	15	college	college	PROPN
cana-3838	6	16	for	for	ADP
cana-3838	6	17	women	woman	NOUN
cana-3838	6	18	,	,	PUNCT
cana-3838	6	19	chennai	chennai	PROPN
cana-3838	6	20	.	.	PUNCT
cana-3838	6	21	vrajee2008@gmail.com	vrajee2008@gmail.com	X
cana-3838	7	1	5assistant	5assistant	NUM
cana-3838	7	2	professor	professor	NOUN
cana-3838	7	3	,	,	PUNCT
cana-3838	7	4	department	department	NOUN
cana-3838	7	5	of	of	ADP
cana-3838	7	6	computer	computer	NOUN
cana-3838	7	7	science	science	PROPN
cana-3838	7	8	dhanraj	dhanraj	PROPN
cana-3838	7	9	baid	baid	PROPN
cana-3838	7	10	jain	jain	PROPN
cana-3838	7	11	college	college	PROPN
cana-3838	7	12	,	,	PUNCT
cana-3838	7	13	chennai	chennai	PROPN
cana-3838	7	14	,	,	PUNCT
cana-3838	7	15	ganeshraja888@gmail.com	ganeshraja888@gmail.com	X
cana-3838	7	16	corresponding	correspond	VERB
cana-3838	7	17	author:dr.d.helen,helensaran15@gmail.com	author:dr.d.helen,helensaran15@gmail.com	PROPN
cana-3838	7	18	article	article	NOUN
cana-3838	7	19	history	history	NOUN
cana-3838	7	20	:	:	PUNCT
cana-3838	7	21	received	receive	VERB
cana-3838	7	22	:	:	PUNCT
cana-3838	7	23	12	12	NUM
cana-3838	7	24	-	-	SYM
cana-3838	7	25	11	11	NUM
cana-3838	7	26	-	-	PUNCT
cana-3838	7	27	2024	2024	NUM
cana-3838	7	28	revised:24	revised:24	X
cana-3838	7	29	-	-	PUNCT
cana-3838	7	30	12	12	NUM
cana-3838	7	31	-	-	PUNCT
cana-3838	7	32	2024	2024	NUM
cana-3838	7	33	accepted:09	accepted:09	NOUN
cana-3838	7	34	-	-	PUNCT
cana-3838	7	35	01	01	NUM
cana-3838	7	36	-	-	PUNCT
cana-3838	7	37	2025	2025	NUM
cana-3838	7	38	abstract	abstract	NOUN
cana-3838	7	39	:	:	PUNCT
cana-3838	7	40	cancers	cancer	NOUN
cana-3838	7	41	of	of	ADP
cana-3838	7	42	the	the	DET
cana-3838	7	43	brain	brain	NOUN
cana-3838	7	44	are	be	AUX
cana-3838	7	45	among	among	ADP
cana-3838	7	46	the	the	DET
cana-3838	7	47	worst	bad	ADJ
cana-3838	7	48	illnesses	illness	NOUN
cana-3838	7	49	a	a	DET
cana-3838	7	50	person	person	NOUN
cana-3838	7	51	may	may	AUX
cana-3838	7	52	get	get	VERB
cana-3838	7	53	.	.	PUNCT
cana-3838	8	1	the	the	DET
cana-3838	8	2	course	course	NOUN
cana-3838	8	3	of	of	ADP
cana-3838	8	4	medical	medical	ADJ
cana-3838	8	5	therapy	therapy	NOUN
cana-3838	8	6	is	be	AUX
cana-3838	8	7	mostly	mostly	ADV
cana-3838	8	8	determined	determine	VERB
cana-3838	8	9	by	by	ADP
cana-3838	8	10	the	the	DET
cana-3838	8	11	tumor	tumor	NOUN
cana-3838	8	12	's	's	PART
cana-3838	8	13	location	location	NOUN
cana-3838	8	14	and	and	CCONJ
cana-3838	8	15	kind	kind	ADJ
cana-3838	8	16	.	.	PUNCT
cana-3838	9	1	neuro	neuro	PROPN
cana-3838	9	2	specialists	specialist	NOUN
cana-3838	9	3	and	and	CCONJ
cana-3838	9	4	radiologists	radiologist	NOUN
cana-3838	9	5	must	must	AUX
cana-3838	9	6	carefully	carefully	ADV
cana-3838	9	7	review	review	VERB
cana-3838	9	8	magnetic	magnetic	ADJ
cana-3838	9	9	resonance	resonance	NOUN
cana-3838	9	10	imaging	imaging	NOUN
cana-3838	9	11	(	(	PUNCT
cana-3838	9	12	mri	mri	NOUN
cana-3838	9	13	)	)	PUNCT
cana-3838	9	14	pictures	picture	NOUN
cana-3838	9	15	in	in	ADP
cana-3838	9	16	order	order	NOUN
cana-3838	9	17	to	to	PART
cana-3838	9	18	arrive	arrive	VERB
cana-3838	9	19	at	at	ADP
cana-3838	9	20	a	a	DET
cana-3838	9	21	definitive	definitive	ADJ
cana-3838	9	22	diagnosis	diagnosis	NOUN
cana-3838	9	23	of	of	ADP
cana-3838	9	24	a	a	DET
cana-3838	9	25	malignancy	malignancy	NOUN
cana-3838	9	26	.	.	PUNCT
cana-3838	10	1	treatment	treatment	NOUN
cana-3838	10	2	option	option	NOUN
cana-3838	10	3	mapping	mapping	NOUN
cana-3838	10	4	,	,	PUNCT
cana-3838	10	5	disease	disease	NOUN
cana-3838	10	6	progression	progression	NOUN
cana-3838	10	7	monitoring	monitoring	NOUN
cana-3838	10	8	,	,	PUNCT
cana-3838	10	9	and	and	CCONJ
cana-3838	10	10	image	image	NOUN
cana-3838	10	11	-	-	PUNCT
cana-3838	10	12	based	base	VERB
cana-3838	10	13	tumor	tumor	NOUN
cana-3838	10	14	segmentation	segmentation	NOUN
cana-3838	10	15	are	be	AUX
cana-3838	10	16	of	of	ADP
cana-3838	10	17	utmost	utmost	ADJ
cana-3838	10	18	importance	importance	NOUN
cana-3838	10	19	in	in	ADP
cana-3838	10	20	medical	medical	ADJ
cana-3838	10	21	imaging	imaging	NOUN
cana-3838	10	22	because	because	SCONJ
cana-3838	10	23	they	they	PRON
cana-3838	10	24	provide	provide	VERB
cana-3838	10	25	information	information	NOUN
cana-3838	10	26	vital	vital	ADJ
cana-3838	10	27	for	for	ADP
cana-3838	10	28	cancer	cancer	NOUN
cana-3838	10	29	analysis	analysis	NOUN
cana-3838	10	30	and	and	CCONJ
cana-3838	10	31	diagnosis	diagnosis	NOUN
cana-3838	10	32	.	.	PUNCT
cana-3838	11	1	some	some	PRON
cana-3838	11	2	have	have	AUX
cana-3838	11	3	speculated	speculate	VERB
cana-3838	11	4	that	that	SCONJ
cana-3838	11	5	deep	deep	ADJ
cana-3838	11	6	learning	learning	NOUN
cana-3838	11	7	might	might	AUX
cana-3838	11	8	be	be	AUX
cana-3838	11	9	the	the	DET
cana-3838	11	10	key	key	NOUN
cana-3838	11	11	to	to	ADP
cana-3838	11	12	better	well	ADJ
cana-3838	11	13	brain	brain	NOUN
cana-3838	11	14	cancer	cancer	NOUN
cana-3838	11	15	diagnosis	diagnosis	NOUN
cana-3838	11	16	and	and	CCONJ
cana-3838	11	17	treatment	treatment	NOUN
cana-3838	11	18	.	.	PUNCT
cana-3838	12	1	with	with	ADP
cana-3838	12	2	its	its	PRON
cana-3838	12	3	state	state	NOUN
cana-3838	12	4	-	-	PUNCT
cana-3838	12	5	of	of	ADP
cana-3838	12	6	-	-	PUNCT
cana-3838	12	7	the	the	DET
cana-3838	12	8	-	-	PUNCT
cana-3838	12	9	art	art	NOUN
cana-3838	12	10	segmentation	segmentation	NOUN
cana-3838	12	11	and	and	CCONJ
cana-3838	12	12	detection	detection	NOUN
cana-3838	12	13	capabilities	capability	NOUN
cana-3838	12	14	,	,	PUNCT
cana-3838	12	15	the	the	DET
cana-3838	12	16	segmentation	segmentation	NOUN
cana-3838	12	17	strategy	strategy	NOUN
cana-3838	12	18	has	have	AUX
cana-3838	12	19	significantly	significantly	ADV
cana-3838	12	20	improved	improve	VERB
cana-3838	12	21	the	the	DET
cana-3838	12	22	removal	removal	NOUN
cana-3838	12	23	of	of	ADP
cana-3838	12	24	abnormal	abnormal	ADJ
cana-3838	12	25	tumor	tumor	NOUN
cana-3838	12	26	regions	region	NOUN
cana-3838	12	27	from	from	ADP
cana-3838	12	28	the	the	DET
cana-3838	12	29	brain	brain	NOUN
cana-3838	12	30	.	.	PUNCT
cana-3838	13	1	in	in	ADP
cana-3838	13	2	this	this	DET
cana-3838	13	3	study	study	NOUN
cana-3838	13	4	,	,	PUNCT
cana-3838	13	5	we	we	PRON
cana-3838	13	6	published	publish	VERB
cana-3838	13	7	a	a	DET
cana-3838	13	8	vgg16	vgg16	NOUN
cana-3838	13	9	and	and	CCONJ
cana-3838	13	10	resnet50	resnet50	VERB
cana-3838	13	11	hybrid	hybrid	ADJ
cana-3838	13	12	model	model	NOUN
cana-3838	13	13	for	for	ADP
cana-3838	13	14	mri	mri	NOUN
cana-3838	13	15	brain	brain	NOUN
cana-3838	13	16	tumor	tumor	NOUN
cana-3838	13	17	segmentation	segmentation	NOUN
cana-3838	13	18	.	.	PUNCT
cana-3838	14	1	with	with	ADP
cana-3838	14	2	the	the	DET
cana-3838	14	3	use	use	NOUN
cana-3838	14	4	of	of	ADP
cana-3838	14	5	the	the	DET
cana-3838	14	6	resnet50	resnet50	NOUN
cana-3838	14	7	algorithm	algorithm	NOUN
cana-3838	14	8	and	and	CCONJ
cana-3838	14	9	the	the	DET
cana-3838	14	10	vgg16	vgg16	NOUN
cana-3838	14	11	,	,	PUNCT
cana-3838	14	12	a	a	DET
cana-3838	14	13	transfer	transfer	NOUN
cana-3838	14	14	learning	learning	NOUN
cana-3838	14	15	method	method	NOUN
cana-3838	14	16	,	,	PUNCT
cana-3838	14	17	brain	brain	NOUN
cana-3838	14	18	tumors	tumor	NOUN
cana-3838	14	19	may	may	AUX
cana-3838	14	20	be	be	AUX
cana-3838	14	21	detected	detect	VERB
cana-3838	14	22	in	in	ADP
cana-3838	14	23	segmented	segment	VERB
cana-3838	14	24	pictures	picture	NOUN
cana-3838	14	25	.	.	PUNCT
cana-3838	15	1	the	the	DET
cana-3838	15	2	findings	finding	NOUN
cana-3838	15	3	show	show	VERB
cana-3838	15	4	that	that	SCONJ
cana-3838	15	5	our	our	PRON
cana-3838	15	6	suggested	suggest	VERB
cana-3838	15	7	approach	approach	NOUN
cana-3838	15	8	is	be	AUX
cana-3838	15	9	more	more	ADV
cana-3838	15	10	accurate	accurate	ADJ
cana-3838	15	11	and	and	CCONJ
cana-3838	15	12	performs	perform	VERB
cana-3838	15	13	better	well	ADJ
cana-3838	15	14	than	than	ADP
cana-3838	15	15	other	other	ADJ
cana-3838	15	16	models	model	NOUN
cana-3838	15	17	when	when	SCONJ
cana-3838	15	18	compared	compare	VERB
cana-3838	15	19	side	side	NOUN
cana-3838	15	20	by	by	ADP
cana-3838	15	21	side	side	NOUN
cana-3838	15	22	.	.	PUNCT
cana-3838	16	1	keyword	keyword	NOUN
cana-3838	16	2	:	:	PUNCT
cana-3838	16	3	image	image	NOUN
cana-3838	16	4	segmentation	segmentation	NOUN
cana-3838	16	5	,	,	PUNCT
cana-3838	16	6	cnn	cnn	PROPN
cana-3838	16	7	,	,	PUNCT
cana-3838	16	8	transfer	transfer	NOUN
cana-3838	16	9	learning	learning	NOUN
cana-3838	16	10	,	,	PUNCT
cana-3838	16	11	vgg16	vgg16	PROPN
cana-3838	16	12	,	,	PUNCT
cana-3838	16	13	resnet50	resnet50	NOUN
cana-3838	16	14	1	1	NUM
cana-3838	16	15	.	.	PUNCT
cana-3838	17	1	introduction	introduction	NOUN
cana-3838	17	2	tumors	tumor	NOUN
cana-3838	17	3	in	in	ADP
cana-3838	17	4	the	the	DET
cana-3838	17	5	brain	brain	NOUN
cana-3838	17	6	develop	develop	VERB
cana-3838	17	7	when	when	SCONJ
cana-3838	17	8	the	the	DET
cana-3838	17	9	brain	brain	NOUN
cana-3838	17	10	's	's	PART
cana-3838	17	11	cell	cell	NOUN
cana-3838	17	12	development	development	NOUN
cana-3838	17	13	is	be	AUX
cana-3838	17	14	abnormal	abnormal	ADJ
cana-3838	17	15	and	and	CCONJ
cana-3838	17	16	uncontrolled	uncontrolled	ADJ
cana-3838	17	17	.	.	PUNCT
cana-3838	18	1	since	since	SCONJ
cana-3838	18	2	the	the	DET
cana-3838	18	3	human	human	ADJ
cana-3838	18	4	skull	skull	NOUN
cana-3838	18	5	is	be	AUX
cana-3838	18	6	inflexible	inflexible	ADJ
cana-3838	18	7	and	and	CCONJ
cana-3838	18	8	has	have	VERB
cana-3838	18	9	limited	limited	ADJ
cana-3838	18	10	space	space	NOUN
cana-3838	18	11	,	,	PUNCT
cana-3838	18	12	any	any	DET
cana-3838	18	13	sudden	sudden	ADJ
cana-3838	18	14	alteration	alteration	NOUN
cana-3838	18	15	would	would	AUX
cana-3838	18	16	have	have	VERB
cana-3838	18	17	an	an	DET
cana-3838	18	18	effect	effect	NOUN
cana-3838	18	19	on	on	ADP
cana-3838	18	20	human	human	ADJ
cana-3838	18	21	function	function	NOUN
cana-3838	18	22	according	accord	VERB
cana-3838	18	23	to	to	ADP
cana-3838	18	24	the	the	DET
cana-3838	18	25	region	region	NOUN
cana-3838	18	26	of	of	ADP
cana-3838	18	27	the	the	DET
cana-3838	18	28	brain	brain	NOUN
cana-3838	18	29	impacted	impact	VERB
cana-3838	18	30	,	,	PUNCT
cana-3838	18	31	and	and	CCONJ
cana-3838	18	32	the	the	DET
cana-3838	18	33	cancer	cancer	NOUN
cana-3838	18	34	might	might	AUX
cana-3838	18	35	spread	spread	VERB
cana-3838	18	36	to	to	ADP
cana-3838	18	37	other	other	ADJ
cana-3838	18	38	organs	organ	NOUN
cana-3838	18	39	.	.	PUNCT
cana-3838	19	1	as	as	ADP
cana-3838	19	2	to	to	ADP
cana-3838	19	3	the	the	DET
cana-3838	19	4	world	world	PROPN
cana-3838	19	5	health	health	PROPN
cana-3838	19	6	organization	organization	PROPN
cana-3838	19	7	’s	’s	PART
cana-3838	19	8	world	world	NOUN
cana-3838	19	9	cancer	cancer	NOUN
cana-3838	19	10	report	report	NOUN
cana-3838	19	11	,	,	PUNCT
cana-3838	19	12	fewer	few	ADJ
cana-3838	19	13	than	than	ADP
cana-3838	19	14	2	2	NUM
cana-3838	19	15	%	%	NOUN
cana-3838	19	16	of	of	ADP
cana-3838	19	17	all	all	DET
cana-3838	19	18	human	human	ADJ
cana-3838	19	19	malignant	malignant	ADJ
cana-3838	19	20	growths	growth	NOUN
cana-3838	19	21	are	be	AUX
cana-3838	19	22	cerebral	cerebral	ADJ
cana-3838	19	23	illnesses	illness	NOUN
cana-3838	19	24	.	.	PUNCT
cana-3838	20	1	whatever	whatever	PRON
cana-3838	20	2	the	the	DET
cana-3838	20	3	case	case	NOUN
cana-3838	20	4	may	may	AUX
cana-3838	20	5	be	be	AUX
cana-3838	20	6	,	,	PUNCT
cana-3838	21	1	it	it	PRON
cana-3838	21	2	mailto:sgokilas@gmail.com	mailto:sgokilas@gmail.com	VERB
cana-3838	21	3	mailto:ganeshraja888@gmail.com	mailto:ganeshraja888@gmail.com	X
cana-3838	22	1	communications	communication	NOUN
cana-3838	22	2	on	on	ADP
cana-3838	22	3	applied	apply	VERB
cana-3838	22	4	nonlinear	nonlinear	ADJ
cana-3838	22	5	analysis	analysis	NOUN
cana-3838	22	6	issn	issn	NOUN
cana-3838	22	7	:	:	PUNCT
cana-3838	22	8	1074	1074	NUM
cana-3838	22	9	-	-	PUNCT
cana-3838	22	10	133x	133x	NUM
cana-3838	22	11	vol	vol	NOUN
cana-3838	22	12	32	32	NUM
cana-3838	22	13	no	no	NOUN
cana-3838	22	14	.	.	PUNCT
cana-3838	23	1	9s	9s	NUM
cana-3838	23	2	(	(	PUNCT
cana-3838	23	3	2025	2025	NUM
cana-3838	23	4	)	)	PUNCT
cana-3838	23	5	64	64	NUM
cana-3838	23	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-3838	23	7	leads	lead	VERB
cana-3838	23	8	to	to	ADP
cana-3838	23	9	major	major	ADJ
cana-3838	23	10	problems	problem	NOUN
cana-3838	23	11	and	and	CCONJ
cana-3838	23	12	harm	harm	NOUN
cana-3838	23	13	.	.	PUNCT
cana-3838	24	1	worldwide	worldwide	ADV
cana-3838	24	2	,	,	PUNCT
cana-3838	24	3	some	some	DET
cana-3838	24	4	5,250	5,250	NUM
cana-3838	24	5	people	people	NOUN
cana-3838	24	6	lose	lose	VERB
cana-3838	24	7	their	their	PRON
cana-3838	24	8	lives	life	NOUN
cana-3838	24	9	each	each	DET
cana-3838	24	10	year	year	NOUN
cana-3838	24	11	to	to	ADP
cana-3838	24	12	malignancies	malignancy	NOUN
cana-3838	24	13	of	of	ADP
cana-3838	24	14	the	the	DET
cana-3838	24	15	brain	brain	NOUN
cana-3838	24	16	,	,	PUNCT
cana-3838	24	17	cns	cns	NOUN
cana-3838	24	18	,	,	PUNCT
cana-3838	24	19	and	and	CCONJ
cana-3838	24	20	other	other	ADJ
cana-3838	24	21	parts	part	NOUN
cana-3838	24	22	of	of	ADP
cana-3838	24	23	the	the	DET
cana-3838	24	24	brain	brain	NOUN
cana-3838	24	25	and	and	CCONJ
cana-3838	24	26	spinal	spinal	ADJ
cana-3838	24	27	cord	cord	NOUN
cana-3838	25	1	[	[	X
cana-3838	25	2	1	1	NUM
cana-3838	25	3	]	]	PUNCT
cana-3838	25	4	.	.	PUNCT
cana-3838	26	1	cancer	cancer	NOUN
cana-3838	26	2	has	have	AUX
cana-3838	26	3	risen	rise	VERB
cana-3838	26	4	sharply	sharply	ADV
cana-3838	26	5	in	in	ADP
cana-3838	26	6	recent	recent	ADJ
cana-3838	26	7	years	year	NOUN
cana-3838	26	8	to	to	PART
cana-3838	26	9	become	become	VERB
cana-3838	26	10	the	the	DET
cana-3838	26	11	leading	lead	VERB
cana-3838	26	12	global	global	ADJ
cana-3838	26	13	health	health	NOUN
cana-3838	26	14	concern	concern	NOUN
cana-3838	26	15	.	.	PUNCT
cana-3838	27	1	according	accord	VERB
cana-3838	27	2	to	to	ADP
cana-3838	27	3	data	datum	NOUN
cana-3838	27	4	collected	collect	VERB
cana-3838	27	5	from	from	ADP
cana-3838	27	6	the	the	DET
cana-3838	27	7	country	country	NOUN
cana-3838	27	8	's	's	PART
cana-3838	27	9	population	population	NOUN
cana-3838	27	10	registry	registry	NOUN
cana-3838	27	11	,	,	PUNCT
cana-3838	27	12	cancer	cancer	NOUN
cana-3838	27	13	claims	claim	VERB
cana-3838	27	14	the	the	DET
cana-3838	27	15	lives	life	NOUN
cana-3838	27	16	of	of	ADP
cana-3838	27	17	around	around	ADP
cana-3838	27	18	8	8	NUM
cana-3838	27	19	lacs	lac	NOUN
cana-3838	27	20	people	people	NOUN
cana-3838	27	21	year	year	NOUN
cana-3838	27	22	,	,	PUNCT
cana-3838	27	23	making	make	VERB
cana-3838	27	24	it	it	PRON
cana-3838	27	25	the	the	DET
cana-3838	27	26	second	second	ADV
cana-3838	27	27	-	-	PUNCT
cana-3838	27	28	leading	lead	VERB
cana-3838	27	29	chronic	chronic	ADJ
cana-3838	27	30	killer	killer	NOUN
cana-3838	27	31	in	in	ADP
cana-3838	27	32	india	india	PROPN
cana-3838	27	33	.	.	PUNCT
cana-3838	28	1	the	the	DET
cana-3838	28	2	indian	indian	PROPN
cana-3838	28	3	council	council	PROPN
cana-3838	28	4	of	of	ADP
cana-3838	28	5	medical	medical	ADJ
cana-3838	28	6	research	research	NOUN
cana-3838	28	7	(	(	PUNCT
cana-3838	28	8	icmr	icmr	PROPN
cana-3838	28	9	)	)	PUNCT
cana-3838	28	10	estimated	estimate	VERB
cana-3838	28	11	in	in	ADP
cana-3838	28	12	2016	2016	NUM
cana-3838	28	13	that	that	PRON
cana-3838	28	14	the	the	DET
cana-3838	28	15	indian	indian	ADJ
cana-3838	28	16	territory	territory	NOUN
cana-3838	28	17	had	have	VERB
cana-3838	28	18	around	around	ADV
cana-3838	28	19	14	14	NUM
cana-3838	28	20	lacs	lac	NOUN
cana-3838	28	21	recorded	record	VERB
cana-3838	28	22	cases	case	NOUN
cana-3838	28	23	of	of	ADP
cana-3838	28	24	cancer	cancer	NOUN
cana-3838	28	25	,	,	PUNCT
cana-3838	28	26	however	however	ADV
cana-3838	28	27	the	the	DET
cana-3838	28	28	true	true	ADJ
cana-3838	28	29	number	number	NOUN
cana-3838	28	30	of	of	ADP
cana-3838	28	31	cases	case	NOUN
cana-3838	28	32	was	be	AUX
cana-3838	28	33	probably	probably	ADV
cana-3838	28	34	far	far	ADV
cana-3838	28	35	higher	high	ADJ
cana-3838	28	36	.	.	PUNCT
cana-3838	29	1	additionally	additionally	ADV
cana-3838	29	2	,	,	PUNCT
cana-3838	29	3	a	a	DET
cana-3838	29	4	number	number	NOUN
cana-3838	29	5	of	of	ADP
cana-3838	29	6	occurrences	occurrence	NOUN
cana-3838	29	7	that	that	PRON
cana-3838	29	8	were	be	AUX
cana-3838	29	9	unrecorded	unrecorde	VERB
cana-3838	29	10	by	by	ADP
cana-3838	29	11	healthcare	healthcare	NOUN
cana-3838	29	12	institutions	institution	NOUN
cana-3838	29	13	were	be	AUX
cana-3838	29	14	considered	consider	VERB
cana-3838	29	15	.	.	PUNCT
cana-3838	30	1	furthermore	furthermore	ADV
cana-3838	30	2	,	,	PUNCT
cana-3838	30	3	the	the	DET
cana-3838	30	4	icmr	icmr	NOUN
cana-3838	30	5	observed	observe	VERB
cana-3838	30	6	that	that	SCONJ
cana-3838	30	7	the	the	DET
cana-3838	30	8	cancer	cancer	NOUN
cana-3838	30	9	diagnosis	diagnosis	NOUN
cana-3838	30	10	rate	rate	NOUN
cana-3838	30	11	was	be	AUX
cana-3838	30	12	at	at	ADP
cana-3838	30	13	25.8	25.8	NUM
cana-3838	30	14	per	per	ADP
cana-3838	30	15	lac	lac	X
cana-3838	30	16	population	population	NOUN
cana-3838	30	17	up	up	ADP
cana-3838	30	18	to	to	ADP
cana-3838	30	19	2019	2019	NUM
cana-3838	30	20	,	,	PUNCT
cana-3838	30	21	and	and	CCONJ
cana-3838	30	22	it	it	PRON
cana-3838	30	23	is	be	AUX
cana-3838	30	24	anticipated	anticipate	VERB
cana-3838	30	25	to	to	PART
cana-3838	30	26	reach	reach	VERB
cana-3838	30	27	35	35	NUM
cana-3838	30	28	per	per	ADP
cana-3838	30	29	year	year	NOUN
cana-3838	30	30	by	by	ADP
cana-3838	30	31	2029	2029	NUM
cana-3838	30	32	.	.	PUNCT
cana-3838	31	1	the	the	DET
cana-3838	31	2	cancer	cancer	NOUN
cana-3838	31	3	diagnosis	diagnosis	NOUN
cana-3838	31	4	rate	rate	NOUN
cana-3838	31	5	in	in	ADP
cana-3838	31	6	india	india	PROPN
cana-3838	31	7	is	be	AUX
cana-3838	31	8	third	third	ADV
cana-3838	31	9	highest	high	ADJ
cana-3838	31	10	in	in	ADP
cana-3838	31	11	the	the	DET
cana-3838	31	12	world	world	NOUN
cana-3838	31	13	,	,	PUNCT
cana-3838	31	14	behind	behind	ADP
cana-3838	31	15	only	only	ADV
cana-3838	31	16	china	china	PROPN
cana-3838	31	17	and	and	CCONJ
cana-3838	31	18	the	the	DET
cana-3838	31	19	us	us	PROPN
cana-3838	31	20	.	.	PUNCT
cana-3838	32	1	more	more	ADJ
cana-3838	32	2	than	than	ADP
cana-3838	32	3	2,000	2,000	NUM
cana-3838	32	4	cases	case	NOUN
cana-3838	32	5	of	of	ADP
cana-3838	32	6	brain	brain	NOUN
cana-3838	32	7	tumors	tumor	NOUN
cana-3838	32	8	are	be	AUX
cana-3838	32	9	reported	report	VERB
cana-3838	32	10	every	every	DET
cana-3838	32	11	day	day	NOUN
cana-3838	32	12	in	in	ADP
cana-3838	32	13	three	three	NUM
cana-3838	32	14	important	important	ADJ
cana-3838	32	15	indian	indian	ADJ
cana-3838	32	16	states	state	NOUN
cana-3838	32	17	:	:	PUNCT
cana-3838	32	18	kerala	kerala	PROPN
cana-3838	32	19	,	,	PUNCT
cana-3838	32	20	tamil	tamil	PROPN
cana-3838	32	21	nadu	nadu	NOUN
cana-3838	32	22	,	,	PUNCT
cana-3838	32	23	and	and	CCONJ
cana-3838	32	24	delhi	delhi	PROPN
cana-3838	32	25	.	.	PUNCT
cana-3838	33	1	the	the	DET
cana-3838	33	2	survival	survival	NOUN
cana-3838	33	3	rate	rate	NOUN
cana-3838	33	4	is	be	AUX
cana-3838	33	5	four	four	NUM
cana-3838	33	6	to	to	PART
cana-3838	33	7	seventeen	seventeen	NUM
cana-3838	33	8	times	time	NOUN
cana-3838	33	9	lower	low	ADJ
cana-3838	33	10	since	since	SCONJ
cana-3838	33	11	around	around	ADP
cana-3838	33	12	1200	1200	NUM
cana-3838	33	13	of	of	ADP
cana-3838	33	14	these	these	DET
cana-3838	33	15	individuals	individual	NOUN
cana-3838	33	16	are	be	AUX
cana-3838	33	17	in	in	ADP
cana-3838	33	18	the	the	DET
cana-3838	33	19	advanced	advanced	ADJ
cana-3838	33	20	or	or	CCONJ
cana-3838	33	21	late	late	ADJ
cana-3838	33	22	stages	stage	NOUN
cana-3838	33	23	.	.	PUNCT
cana-3838	34	1	among	among	ADP
cana-3838	34	2	female	female	ADJ
cana-3838	34	3	cancer	cancer	NOUN
cana-3838	34	4	patients	patient	NOUN
cana-3838	34	5	,	,	PUNCT
cana-3838	34	6	brain	brain	NOUN
cana-3838	34	7	tumors	tumor	NOUN
cana-3838	34	8	rank	rank	VERB
cana-3838	34	9	second	second	ADV
cana-3838	34	10	in	in	ADP
cana-3838	34	11	incidence	incidence	NOUN
cana-3838	34	12	and	and	CCONJ
cana-3838	34	13	second	second	ADJ
cana-3838	34	14	in	in	ADP
cana-3838	34	15	fatality	fatality	NOUN
cana-3838	34	16	rates	rate	NOUN
cana-3838	34	17	,	,	PUNCT
cana-3838	34	18	behind	behind	ADP
cana-3838	34	19	only	only	ADJ
cana-3838	34	20	lung	lung	NOUN
cana-3838	34	21	cancer	cancer	NOUN
cana-3838	34	22	.	.	PUNCT
cana-3838	35	1	a	a	DET
cana-3838	35	2	recent	recent	ADJ
cana-3838	35	3	study	study	NOUN
cana-3838	35	4	found	find	VERB
cana-3838	35	5	that	that	SCONJ
cana-3838	35	6	brain	brain	NOUN
cana-3838	35	7	tumors	tumor	NOUN
cana-3838	35	8	were	be	AUX
cana-3838	35	9	the	the	DET
cana-3838	35	10	cause	cause	NOUN
cana-3838	35	11	of	of	ADP
cana-3838	35	12	death	death	NOUN
cana-3838	35	13	for	for	ADP
cana-3838	35	14	about	about	ADV
cana-3838	35	15	5	5	NUM
cana-3838	35	16	lacs	lac	NOUN
cana-3838	35	17	of	of	ADP
cana-3838	35	18	women	woman	NOUN
cana-3838	35	19	in	in	ADP
cana-3838	35	20	2015	2015	NUM
cana-3838	35	21	.	.	PUNCT
cana-3838	36	1	the	the	DET
cana-3838	36	2	world	world	PROPN
cana-3838	36	3	health	health	PROPN
cana-3838	36	4	organization	organization	NOUN
cana-3838	36	5	estimates	estimate	VERB
cana-3838	36	6	that	that	SCONJ
cana-3838	36	7	1.5	1.5	NUM
cana-3838	36	8	million	million	NUM
cana-3838	36	9	more	more	ADJ
cana-3838	36	10	women	woman	NOUN
cana-3838	36	11	will	will	AUX
cana-3838	36	12	lose	lose	VERB
cana-3838	36	13	their	their	PRON
cana-3838	36	14	lives	life	NOUN
cana-3838	36	15	to	to	ADP
cana-3838	36	16	brain	brain	NOUN
cana-3838	36	17	tumors	tumor	NOUN
cana-3838	36	18	in	in	ADP
cana-3838	36	19	the	the	DET
cana-3838	36	20	next	next	ADJ
cana-3838	36	21	year	year	NOUN
cana-3838	36	22	.	.	PUNCT
cana-3838	37	1	even	even	ADV
cana-3838	37	2	though	though	SCONJ
cana-3838	37	3	it	it	PRON
cana-3838	37	4	has	have	VERB
cana-3838	37	5	one	one	NUM
cana-3838	37	6	of	of	ADP
cana-3838	37	7	the	the	DET
cana-3838	37	8	best	good	ADJ
cana-3838	37	9	healthcare	healthcare	NOUN
cana-3838	37	10	systems	system	NOUN
cana-3838	37	11	in	in	ADP
cana-3838	37	12	the	the	DET
cana-3838	37	13	world	world	NOUN
cana-3838	37	14	,	,	PUNCT
cana-3838	37	15	the	the	DET
cana-3838	37	16	united	united	PROPN
cana-3838	37	17	states	states	PROPN
cana-3838	37	18	had	have	VERB
cana-3838	37	19	about	about	ADP
cana-3838	37	20	2.5	2.5	NUM
cana-3838	37	21	million	million	NUM
cana-3838	37	22	cases	case	NOUN
cana-3838	37	23	of	of	ADP
cana-3838	37	24	brain	brain	NOUN
cana-3838	37	25	tumors	tumor	NOUN
cana-3838	37	26	and	and	CCONJ
cana-3838	37	27	40,000	40,000	NUM
cana-3838	37	28	deaths	death	NOUN
cana-3838	37	29	from	from	ADP
cana-3838	37	30	them	they	PRON
cana-3838	37	31	in	in	ADP
cana-3838	37	32	2017	2017	NUM
cana-3838	38	1	[	[	X
cana-3838	38	2	2	2	NUM
cana-3838	38	3	]	]	PUNCT
cana-3838	38	4	.	.	PUNCT
cana-3838	39	1	there	there	PRON
cana-3838	39	2	is	be	VERB
cana-3838	39	3	a	a	DET
cana-3838	39	4	dramatic	dramatic	ADJ
cana-3838	39	5	decrease	decrease	NOUN
cana-3838	39	6	in	in	ADP
cana-3838	39	7	survival	survival	NOUN
cana-3838	39	8	rate	rate	NOUN
cana-3838	39	9	(	(	PUNCT
cana-3838	39	10	4	4	NUM
cana-3838	39	11	-	-	SYM
cana-3838	39	12	17	17	NUM
cana-3838	39	13	times	time	NOUN
cana-3838	39	14	)	)	PUNCT
cana-3838	39	15	as	as	SCONJ
cana-3838	39	16	over	over	ADP
cana-3838	39	17	1200	1200	NUM
cana-3838	39	18	of	of	ADP
cana-3838	39	19	these	these	DET
cana-3838	39	20	patients	patient	NOUN
cana-3838	39	21	are	be	AUX
cana-3838	39	22	in	in	ADP
cana-3838	39	23	advanced	advanced	ADJ
cana-3838	39	24	or	or	CCONJ
cana-3838	39	25	later	later	ADJ
cana-3838	39	26	stages	stage	NOUN
cana-3838	39	27	.	.	PUNCT
cana-3838	40	1	in	in	ADP
cana-3838	40	2	terms	term	NOUN
cana-3838	40	3	of	of	ADP
cana-3838	40	4	cancer	cancer	NOUN
cana-3838	40	5	incidence	incidence	NOUN
cana-3838	40	6	and	and	CCONJ
cana-3838	40	7	fatality	fatality	NOUN
cana-3838	40	8	rates	rate	NOUN
cana-3838	40	9	in	in	ADP
cana-3838	40	10	females	female	NOUN
cana-3838	40	11	,	,	PUNCT
cana-3838	40	12	brain	brain	NOUN
cana-3838	40	13	tumors	tumor	NOUN
cana-3838	40	14	rank	rank	VERB
cana-3838	40	15	second	second	ADV
cana-3838	40	16	,	,	PUNCT
cana-3838	40	17	after	after	ADP
cana-3838	40	18	lung	lung	NOUN
cana-3838	40	19	cancer	cancer	NOUN
cana-3838	40	20	.	.	PUNCT
cana-3838	41	1	in	in	ADP
cana-3838	41	2	2015	2015	NUM
cana-3838	41	3	,	,	PUNCT
cana-3838	41	4	brain	brain	NOUN
cana-3838	41	5	tumors	tumor	NOUN
cana-3838	41	6	claimed	claim	VERB
cana-3838	41	7	the	the	DET
cana-3838	41	8	lives	life	NOUN
cana-3838	41	9	of	of	ADP
cana-3838	41	10	about	about	ADV
cana-3838	41	11	5	5	NUM
cana-3838	41	12	lacs	lac	NOUN
cana-3838	41	13	of	of	ADP
cana-3838	41	14	women	woman	NOUN
cana-3838	41	15	,	,	PUNCT
cana-3838	41	16	as	as	SCONJ
cana-3838	41	17	revealed	reveal	VERB
cana-3838	41	18	by	by	ADP
cana-3838	41	19	new	new	ADJ
cana-3838	41	20	study	study	NOUN
cana-3838	41	21	.	.	PUNCT
cana-3838	42	1	brain	brain	NOUN
cana-3838	42	2	tumors	tumor	NOUN
cana-3838	42	3	may	may	AUX
cana-3838	42	4	kill	kill	VERB
cana-3838	42	5	1.5	1.5	NUM
cana-3838	42	6	million	million	NUM
cana-3838	42	7	more	more	ADJ
cana-3838	42	8	women	woman	NOUN
cana-3838	42	9	,	,	PUNCT
cana-3838	42	10	says	say	VERB
cana-3838	42	11	the	the	DET
cana-3838	42	12	world	world	PROPN
cana-3838	42	13	health	health	NOUN
cana-3838	42	14	organization	organization	NOUN
cana-3838	42	15	(	(	PUNCT
cana-3838	42	16	who	who	PRON
cana-3838	42	17	)	)	PUNCT
cana-3838	42	18	.	.	PUNCT
cana-3838	43	1	despite	despite	SCONJ
cana-3838	43	2	being	be	AUX
cana-3838	43	3	one	one	NUM
cana-3838	43	4	of	of	ADP
cana-3838	43	5	the	the	DET
cana-3838	43	6	most	most	ADV
cana-3838	43	7	industrialized	industrialize	VERB
cana-3838	43	8	nations	nation	NOUN
cana-3838	43	9	with	with	ADP
cana-3838	43	10	the	the	DET
cana-3838	43	11	finest	fine	ADJ
cana-3838	43	12	healthcare	healthcare	NOUN
cana-3838	43	13	infrastructure	infrastructure	NOUN
cana-3838	43	14	,	,	PUNCT
cana-3838	43	15	the	the	DET
cana-3838	43	16	united	united	PROPN
cana-3838	43	17	states	states	PROPN
cana-3838	43	18	reported	report	VERB
cana-3838	43	19	about	about	ADP
cana-3838	43	20	2.5	2.5	NUM
cana-3838	43	21	lacs	lac	NOUN
cana-3838	43	22	of	of	ADP
cana-3838	43	23	brain	brain	NOUN
cana-3838	43	24	tumor	tumor	NOUN
cana-3838	43	25	patients	patient	NOUN
cana-3838	43	26	and	and	CCONJ
cana-3838	43	27	forty	forty	NUM
cana-3838	43	28	thousand	thousand	NUM
cana-3838	43	29	deaths	death	NOUN
cana-3838	43	30	in	in	ADP
cana-3838	43	31	2017	2017	NUM
cana-3838	43	32	[	[	X
cana-3838	43	33	2	2	NUM
cana-3838	43	34	]	]	PUNCT
cana-3838	43	35	.	.	PUNCT
cana-3838	44	1	this	this	DET
cana-3838	44	2	remarkable	remarkable	ADJ
cana-3838	44	3	soft	soft	ADJ
cana-3838	44	4	tissue	tissue	NOUN
cana-3838	44	5	delineation	delineation	NOUN
cana-3838	44	6	becomes	become	VERB
cana-3838	44	7	very	very	ADV
cana-3838	44	8	important	important	ADJ
cana-3838	44	9	when	when	SCONJ
cana-3838	44	10	attempting	attempt	VERB
cana-3838	44	11	to	to	PART
cana-3838	44	12	distinguish	distinguish	VERB
cana-3838	44	13	between	between	ADP
cana-3838	44	14	healthy	healthy	ADJ
cana-3838	44	15	tissues	tissue	NOUN
cana-3838	44	16	and	and	CCONJ
cana-3838	44	17	infectious	infectious	ADJ
cana-3838	44	18	organisms	organism	NOUN
cana-3838	44	19	[	[	X
cana-3838	44	20	3	3	NUM
cana-3838	44	21	]	]	PUNCT
cana-3838	44	22	.	.	PUNCT
cana-3838	45	1	medical	medical	ADJ
cana-3838	45	2	image	image	NOUN
cana-3838	45	3	analysis	analysis	NOUN
cana-3838	45	4	often	often	ADV
cana-3838	45	5	use	use	VERB
cana-3838	45	6	a	a	DET
cana-3838	45	7	number	number	NOUN
cana-3838	45	8	of	of	ADP
cana-3838	45	9	techniques	technique	NOUN
cana-3838	45	10	to	to	PART
cana-3838	45	11	generate	generate	VERB
cana-3838	45	12	pictures	picture	NOUN
cana-3838	45	13	of	of	ADP
cana-3838	45	14	the	the	DET
cana-3838	45	15	human	human	ADJ
cana-3838	45	16	body	body	NOUN
cana-3838	45	17	's	's	PART
cana-3838	45	18	soft	soft	ADJ
cana-3838	45	19	tissues	tissue	NOUN
cana-3838	45	20	.	.	PUNCT
cana-3838	46	1	magnetic	magnetic	ADJ
cana-3838	46	2	resonance	resonance	NOUN
cana-3838	46	3	imaging	imaging	NOUN
cana-3838	46	4	(	(	PUNCT
cana-3838	46	5	mri	mri	NOUN
cana-3838	46	6	)	)	PUNCT
cana-3838	46	7	is	be	AUX
cana-3838	46	8	one	one	NUM
cana-3838	46	9	of	of	ADP
cana-3838	46	10	these	these	DET
cana-3838	46	11	tools	tool	NOUN
cana-3838	46	12	that	that	PRON
cana-3838	46	13	clinicians	clinician	NOUN
cana-3838	46	14	use	use	VERB
cana-3838	46	15	often	often	ADV
cana-3838	46	16	.	.	PUNCT
cana-3838	47	1	in	in	ADP
cana-3838	47	2	order	order	NOUN
cana-3838	47	3	to	to	PART
cana-3838	47	4	aid	aid	VERB
cana-3838	47	5	physicians	physician	NOUN
cana-3838	47	6	in	in	ADP
cana-3838	47	7	determining	determine	VERB
cana-3838	47	8	the	the	DET
cana-3838	47	9	patient	patient	NOUN
cana-3838	47	10	's	's	PART
cana-3838	47	11	health	health	NOUN
cana-3838	47	12	,	,	PUNCT
cana-3838	47	13	this	this	DET
cana-3838	47	14	approach	approach	NOUN
cana-3838	47	15	correctly	correctly	ADV
cana-3838	47	16	interprets	interpret	VERB
cana-3838	47	17	imaging	imaging	NOUN
cana-3838	47	18	data	datum	NOUN
cana-3838	47	19	of	of	ADP
cana-3838	47	20	human	human	ADJ
cana-3838	47	21	brain	brain	NOUN
cana-3838	47	22	tumors	tumor	NOUN
cana-3838	47	23	without	without	ADP
cana-3838	47	24	invasive	invasive	ADJ
cana-3838	47	25	procedures	procedure	NOUN
cana-3838	47	26	.	.	PUNCT
cana-3838	48	1	thanks	thank	NOUN
cana-3838	48	2	to	to	ADP
cana-3838	48	3	its	its	PRON
cana-3838	48	4	high	high	ADJ
cana-3838	48	5	-	-	PUNCT
cana-3838	48	6	resolution	resolution	NOUN
cana-3838	48	7	pictures	picture	NOUN
cana-3838	48	8	and	and	CCONJ
cana-3838	48	9	tissue	tissue	NOUN
cana-3838	48	10	contrast	contrast	NOUN
cana-3838	48	11	normalization	normalization	NOUN
cana-3838	48	12	,	,	PUNCT
cana-3838	48	13	it	it	PRON
cana-3838	48	14	is	be	AUX
cana-3838	48	15	a	a	DET
cana-3838	48	16	great	great	ADJ
cana-3838	48	17	tool	tool	NOUN
cana-3838	48	18	.	.	PUNCT
cana-3838	49	1	imaging	imaging	NOUN
cana-3838	49	2	studies	study	NOUN
cana-3838	49	3	using	use	VERB
cana-3838	49	4	magnetic	magnetic	ADJ
cana-3838	49	5	resonance	resonance	NOUN
cana-3838	49	6	imaging	imaging	NOUN
cana-3838	49	7	(	(	PUNCT
cana-3838	49	8	mri	mri	NOUN
cana-3838	49	9	)	)	PUNCT
cana-3838	49	10	may	may	AUX
cana-3838	49	11	provide	provide	VERB
cana-3838	49	12	light	light	NOUN
cana-3838	49	13	on	on	ADP
cana-3838	49	14	the	the	DET
cana-3838	49	15	genetics	genetic	NOUN
cana-3838	49	16	,	,	PUNCT
cana-3838	49	17	chemistry	chemistry	NOUN
cana-3838	49	18	,	,	PUNCT
cana-3838	49	19	physiology	physiology	NOUN
cana-3838	49	20	,	,	PUNCT
cana-3838	49	21	and	and	CCONJ
cana-3838	49	22	biology	biology	NOUN
cana-3838	49	23	of	of	ADP
cana-3838	49	24	brain	brain	NOUN
cana-3838	49	25	problems	problem	NOUN
cana-3838	49	26	.	.	PUNCT
cana-3838	50	1	there	there	PRON
cana-3838	50	2	are	be	VERB
cana-3838	50	3	several	several	ADJ
cana-3838	50	4	types	type	NOUN
cana-3838	50	5	of	of	ADP
cana-3838	50	6	tumors	tumor	NOUN
cana-3838	50	7	that	that	PRON
cana-3838	50	8	are	be	AUX
cana-3838	50	9	defined	define	VERB
cana-3838	50	10	by	by	ADP
cana-3838	50	11	their	their	PRON
cana-3838	50	12	origin	origin	NOUN
cana-3838	50	13	and	and	CCONJ
cana-3838	50	14	cell	cell	NOUN
cana-3838	50	15	type	type	NOUN
cana-3838	50	16	.	.	PUNCT
cana-3838	51	1	it	it	PRON
cana-3838	51	2	's	be	AUX
cana-3838	51	3	important	important	ADJ
cana-3838	51	4	to	to	PART
cana-3838	51	5	remember	remember	VERB
cana-3838	51	6	that	that	PRON
cana-3838	51	7	primary	primary	ADJ
cana-3838	51	8	brain	brain	NOUN
cana-3838	51	9	tumors	tumor	NOUN
cana-3838	51	10	originate	originate	VERB
cana-3838	51	11	in	in	ADP
cana-3838	51	12	different	different	ADJ
cana-3838	51	13	human	human	ADJ
cana-3838	51	14	organs	organ	NOUN
cana-3838	51	15	and	and	CCONJ
cana-3838	51	16	spread	spread	VERB
cana-3838	51	17	to	to	ADP
cana-3838	51	18	the	the	DET
cana-3838	51	19	brain	brain	NOUN
cana-3838	51	20	,	,	PUNCT
cana-3838	51	21	while	while	SCONJ
cana-3838	51	22	vertebrate	vertebrate	ADJ
cana-3838	51	23	cerebrum	cerebrum	NOUN
cana-3838	51	24	malignancies	malignancy	NOUN
cana-3838	51	25	often	often	ADV
cana-3838	51	26	show	show	VERB
cana-3838	51	27	up	up	ADP
cana-3838	51	28	in	in	ADP
cana-3838	51	29	the	the	DET
cana-3838	51	30	area	area	NOUN
cana-3838	51	31	of	of	ADP
cana-3838	51	32	the	the	DET
cana-3838	51	33	brain	brain	NOUN
cana-3838	51	34	's	's	PART
cana-3838	51	35	central	central	ADJ
cana-3838	51	36	hemispheres	hemisphere	NOUN
cana-3838	51	37	.	.	PUNCT
cana-3838	52	1	gliomas	glioma	NOUN
cana-3838	52	2	,	,	PUNCT
cana-3838	52	3	meningiomas	meningioma	NOUN
cana-3838	52	4	,	,	PUNCT
cana-3838	52	5	and	and	CCONJ
cana-3838	52	6	pituitary	pituitary	ADJ
cana-3838	52	7	tumors	tumor	NOUN
cana-3838	52	8	are	be	AUX
cana-3838	52	9	the	the	DET
cana-3838	52	10	three	three	NUM
cana-3838	52	11	main	main	ADJ
cana-3838	52	12	forms	form	NOUN
cana-3838	52	13	of	of	ADP
cana-3838	52	14	primary	primary	ADJ
cana-3838	52	15	brain	brain	NOUN
cana-3838	52	16	tumors	tumor	NOUN
cana-3838	52	17	,	,	PUNCT
cana-3838	52	18	as	as	SCONJ
cana-3838	52	19	seen	see	VERB
cana-3838	52	20	in	in	ADP
cana-3838	52	21	figure1[4	figure1[4	PROPN
cana-3838	52	22	]	]	PUNCT
cana-3838	52	23	.	.	PUNCT
cana-3838	53	1	communications	communication	NOUN
cana-3838	53	2	on	on	ADP
cana-3838	53	3	applied	apply	VERB
cana-3838	53	4	nonlinear	nonlinear	ADJ
cana-3838	53	5	analysis	analysis	NOUN
cana-3838	53	6	issn	issn	NOUN
cana-3838	53	7	:	:	PUNCT
cana-3838	53	8	1074	1074	NUM
cana-3838	53	9	-	-	PUNCT
cana-3838	53	10	133x	133x	NUM
cana-3838	53	11	vol	vol	NOUN
cana-3838	53	12	32	32	NUM
cana-3838	53	13	no	no	NOUN
cana-3838	53	14	.	.	PUNCT
cana-3838	54	1	9s	9s	NUM
cana-3838	54	2	(	(	PUNCT
cana-3838	54	3	2025	2025	NUM
cana-3838	54	4	)	)	PUNCT
cana-3838	54	5	65	65	NUM
cana-3838	54	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-3838	54	7	(	(	PUNCT
cana-3838	54	8	a	a	NOUN
cana-3838	54	9	)	)	PUNCT
cana-3838	54	10	(	(	PUNCT
cana-3838	54	11	b	b	X
cana-3838	54	12	)	)	PUNCT
cana-3838	54	13	(	(	PUNCT
cana-3838	54	14	c	c	X
cana-3838	54	15	)	)	PUNCT
cana-3838	54	16	figure	figure	NOUN
cana-3838	54	17	1	1	NUM
cana-3838	54	18	:	:	PUNCT
cana-3838	54	19	typical	typical	ADJ
cana-3838	54	20	brain	brain	NOUN
cana-3838	54	21	tumor	tumor	NOUN
cana-3838	54	22	types	type	NOUN
cana-3838	54	23	.	.	PUNCT
cana-3838	55	1	the	the	DET
cana-3838	55	2	abnormal	abnormal	ADJ
cana-3838	55	3	and	and	CCONJ
cana-3838	55	4	uncontrolled	uncontrolled	ADJ
cana-3838	55	5	growth	growth	NOUN
cana-3838	55	6	of	of	ADP
cana-3838	55	7	cells	cell	NOUN
cana-3838	55	8	all	all	ADV
cana-3838	55	9	across	across	ADP
cana-3838	55	10	the	the	DET
cana-3838	55	11	body	body	NOUN
cana-3838	55	12	is	be	AUX
cana-3838	55	13	what	what	PRON
cana-3838	55	14	defines	define	VERB
cana-3838	55	15	cancer	cancer	NOUN
cana-3838	55	16	.	.	PUNCT
cana-3838	56	1	when	when	SCONJ
cana-3838	56	2	these	these	DET
cana-3838	56	3	aberrant	aberrant	ADJ
cana-3838	56	4	cell	cell	NOUN
cana-3838	56	5	divisions	division	NOUN
cana-3838	56	6	proliferate	proliferate	VERB
cana-3838	56	7	in	in	ADP
cana-3838	56	8	the	the	DET
cana-3838	56	9	brain	brain	NOUN
cana-3838	56	10	at	at	ADP
cana-3838	56	11	an	an	DET
cana-3838	56	12	abnormal	abnormal	ADJ
cana-3838	56	13	rate	rate	NOUN
cana-3838	56	14	,	,	PUNCT
cana-3838	56	15	the	the	DET
cana-3838	56	16	result	result	NOUN
cana-3838	56	17	is	be	AUX
cana-3838	56	18	a	a	DET
cana-3838	56	19	tumor	tumor	NOUN
cana-3838	56	20	.	.	PUNCT
cana-3838	57	1	despite	despite	SCONJ
cana-3838	57	2	their	their	PRON
cana-3838	57	3	rarity	rarity	NOUN
cana-3838	57	4	,	,	PUNCT
cana-3838	57	5	brain	brain	NOUN
cana-3838	57	6	tumors	tumor	NOUN
cana-3838	57	7	are	be	AUX
cana-3838	57	8	on	on	ADP
cana-3838	57	9	the	the	DET
cana-3838	57	10	list	list	NOUN
cana-3838	57	11	of	of	ADP
cana-3838	57	12	the	the	DET
cana-3838	57	13	most	most	ADV
cana-3838	57	14	lethal	lethal	ADJ
cana-3838	57	15	malignancies	malignancy	NOUN
cana-3838	57	16	.	.	PUNCT
cana-3838	58	1	although	although	SCONJ
cana-3838	58	2	they	they	PRON
cana-3838	58	3	originate	originate	VERB
cana-3838	58	4	from	from	ADP
cana-3838	58	5	different	different	ADJ
cana-3838	58	6	places	place	NOUN
cana-3838	58	7	,	,	PUNCT
cana-3838	58	8	the	the	DET
cana-3838	58	9	same	same	ADJ
cana-3838	58	10	kind	kind	NOUN
cana-3838	58	11	of	of	ADP
cana-3838	58	12	brain	brain	NOUN
cana-3838	58	13	tumor	tumor	NOUN
cana-3838	58	14	is	be	AUX
cana-3838	58	15	known	know	VERB
cana-3838	58	16	as	as	ADP
cana-3838	58	17	a	a	DET
cana-3838	58	18	primary	primary	ADJ
cana-3838	58	19	brain	brain	NOUN
cana-3838	58	20	tumor	tumor	NOUN
cana-3838	58	21	or	or	CCONJ
cana-3838	58	22	a	a	DET
cana-3838	58	23	metastatic	metastatic	ADJ
cana-3838	58	24	brain	brain	NOUN
cana-3838	58	25	tumor	tumor	NOUN
cana-3838	58	26	.	.	PUNCT
cana-3838	59	1	although	although	SCONJ
cana-3838	59	2	both	both	CCONJ
cana-3838	59	3	primary	primary	ADJ
cana-3838	59	4	and	and	CCONJ
cana-3838	59	5	metastatic	metastatic	ADJ
cana-3838	59	6	brain	brain	NOUN
cana-3838	59	7	tumors	tumor	NOUN
cana-3838	59	8	originate	originate	VERB
cana-3838	59	9	in	in	ADP
cana-3838	59	10	cells	cell	NOUN
cana-3838	59	11	of	of	ADP
cana-3838	59	12	brain	brain	NOUN
cana-3838	59	13	tissue	tissue	NOUN
cana-3838	59	14	,	,	PUNCT
cana-3838	59	15	the	the	DET
cana-3838	59	16	former	former	ADJ
cana-3838	59	17	originates	originate	NOUN
cana-3838	59	18	in	in	ADP
cana-3838	59	19	another	another	DET
cana-3838	59	20	part	part	NOUN
cana-3838	59	21	of	of	ADP
cana-3838	59	22	the	the	DET
cana-3838	59	23	body	body	NOUN
cana-3838	59	24	and	and	CCONJ
cana-3838	59	25	the	the	DET
cana-3838	59	26	latter	latter	ADJ
cana-3838	59	27	spreads	spread	NOUN
cana-3838	59	28	to	to	ADP
cana-3838	59	29	it	it	PRON
cana-3838	59	30	.	.	PUNCT
cana-3838	60	1	unregulated	unregulated	ADJ
cana-3838	60	2	and	and	CCONJ
cana-3838	60	3	abnormal	abnormal	ADJ
cana-3838	60	4	cell	cell	NOUN
cana-3838	60	5	growth	growth	NOUN
cana-3838	60	6	throughout	throughout	ADP
cana-3838	60	7	the	the	DET
cana-3838	60	8	body	body	NOUN
cana-3838	60	9	is	be	AUX
cana-3838	60	10	a	a	DET
cana-3838	60	11	hallmark	hallmark	NOUN
cana-3838	60	12	of	of	ADP
cana-3838	60	13	cancer	cancer	NOUN
cana-3838	60	14	.	.	PUNCT
cana-3838	61	1	the	the	DET
cana-3838	61	2	accumulation	accumulation	NOUN
cana-3838	61	3	of	of	ADP
cana-3838	61	4	these	these	DET
cana-3838	61	5	aberrant	aberrant	ADJ
cana-3838	61	6	cell	cell	NOUN
cana-3838	61	7	divisions	division	NOUN
cana-3838	61	8	in	in	ADP
cana-3838	61	9	brain	brain	NOUN
cana-3838	61	10	tissue	tissue	NOUN
cana-3838	61	11	is	be	AUX
cana-3838	61	12	known	know	VERB
cana-3838	61	13	as	as	ADP
cana-3838	61	14	a	a	DET
cana-3838	61	15	brain	brain	NOUN
cana-3838	61	16	tumor	tumor	NOUN
cana-3838	61	17	.	.	PUNCT
cana-3838	62	1	despite	despite	SCONJ
cana-3838	62	2	their	their	PRON
cana-3838	62	3	rarity	rarity	NOUN
cana-3838	62	4	,	,	PUNCT
cana-3838	62	5	brain	brain	NOUN
cana-3838	62	6	tumors	tumor	NOUN
cana-3838	62	7	are	be	AUX
cana-3838	62	8	among	among	ADP
cana-3838	62	9	the	the	DET
cana-3838	62	10	most	most	ADV
cana-3838	62	11	lethal	lethal	ADJ
cana-3838	62	12	forms	form	NOUN
cana-3838	62	13	of	of	ADP
cana-3838	62	14	cancer	cancer	NOUN
cana-3838	62	15	.	.	PUNCT
cana-3838	63	1	metastatic	metastatic	ADJ
cana-3838	63	2	brain	brain	NOUN
cana-3838	63	3	tumors	tumor	NOUN
cana-3838	63	4	and	and	CCONJ
cana-3838	63	5	primary	primary	ADJ
cana-3838	63	6	brain	brain	NOUN
cana-3838	63	7	tumors	tumor	NOUN
cana-3838	63	8	both	both	PRON
cana-3838	63	9	refer	refer	VERB
cana-3838	63	10	to	to	ADP
cana-3838	63	11	the	the	DET
cana-3838	63	12	same	same	ADJ
cana-3838	63	13	kind	kind	NOUN
cana-3838	63	14	of	of	ADP
cana-3838	63	15	tumor	tumor	NOUN
cana-3838	63	16	,	,	PUNCT
cana-3838	63	17	although	although	SCONJ
cana-3838	63	18	they	they	PRON
cana-3838	63	19	originate	originate	VERB
cana-3838	63	20	from	from	ADP
cana-3838	63	21	distinct	distinct	ADJ
cana-3838	63	22	places	place	NOUN
cana-3838	63	23	in	in	ADP
cana-3838	63	24	the	the	DET
cana-3838	63	25	brain	brain	NOUN
cana-3838	63	26	.	.	PUNCT
cana-3838	64	1	while	while	SCONJ
cana-3838	64	2	primary	primary	ADJ
cana-3838	64	3	tumors	tumor	NOUN
cana-3838	64	4	begin	begin	VERB
cana-3838	64	5	in	in	ADP
cana-3838	64	6	the	the	DET
cana-3838	64	7	cells	cell	NOUN
cana-3838	64	8	of	of	ADP
cana-3838	64	9	brain	brain	NOUN
cana-3838	64	10	tissue	tissue	NOUN
cana-3838	64	11	,	,	PUNCT
cana-3838	64	12	metastatic	metastatic	ADJ
cana-3838	64	13	malignancies	malignancy	NOUN
cana-3838	64	14	travel	travel	VERB
cana-3838	64	15	from	from	ADP
cana-3838	64	16	another	another	DET
cana-3838	64	17	part	part	NOUN
cana-3838	64	18	of	of	ADP
cana-3838	64	19	the	the	DET
cana-3838	64	20	body	body	NOUN
cana-3838	64	21	to	to	ADP
cana-3838	64	22	the	the	DET
cana-3838	64	23	brain	brain	NOUN
cana-3838	64	24	.	.	PUNCT
cana-3838	65	1	the	the	DET
cana-3838	65	2	future	future	NOUN
cana-3838	65	3	of	of	ADP
cana-3838	65	4	image	image	NOUN
cana-3838	65	5	processing	processing	NOUN
cana-3838	65	6	is	be	AUX
cana-3838	65	7	highly	highly	ADV
cana-3838	65	8	dependent	dependent	ADJ
cana-3838	65	9	on	on	ADP
cana-3838	65	10	image	image	NOUN
cana-3838	65	11	segmentation	segmentation	NOUN
cana-3838	65	12	,	,	PUNCT
cana-3838	65	13	a	a	DET
cana-3838	65	14	fundamental	fundamental	ADJ
cana-3838	65	15	and	and	CCONJ
cana-3838	65	16	important	important	ADJ
cana-3838	65	17	phase	phase	NOUN
cana-3838	65	18	in	in	ADP
cana-3838	65	19	the	the	DET
cana-3838	65	20	process	process	NOUN
cana-3838	65	21	.	.	PUNCT
cana-3838	66	1	brain	brain	NOUN
cana-3838	66	2	tumor	tumor	NOUN
cana-3838	66	3	segmentation	segmentation	NOUN
cana-3838	66	4	from	from	ADP
cana-3838	66	5	mri	mri	NOUN
cana-3838	66	6	scans	scan	NOUN
cana-3838	66	7	has	have	AUX
cana-3838	66	8	been	be	AUX
cana-3838	66	9	our	our	PRON
cana-3838	66	10	primary	primary	ADJ
cana-3838	66	11	emphasis	emphasis	NOUN
cana-3838	66	12	here	here	ADV
cana-3838	66	13	.	.	PUNCT
cana-3838	67	1	it	it	PRON
cana-3838	67	2	helps	help	VERB
cana-3838	67	3	doctors	doctor	NOUN
cana-3838	67	4	get	get	VERB
cana-3838	67	5	a	a	DET
cana-3838	67	6	precise	precise	ADJ
cana-3838	67	7	location	location	NOUN
cana-3838	67	8	of	of	ADP
cana-3838	67	9	the	the	DET
cana-3838	67	10	tumor	tumor	NOUN
cana-3838	67	11	in	in	ADP
cana-3838	67	12	the	the	DET
cana-3838	67	13	brain	brain	NOUN
cana-3838	67	14	.	.	PUNCT
cana-3838	68	1	when	when	SCONJ
cana-3838	68	2	we	we	PRON
cana-3838	68	3	talk	talk	VERB
cana-3838	68	4	about	about	ADP
cana-3838	68	5	"	"	PUNCT
cana-3838	68	6	medical	medical	ADJ
cana-3838	68	7	image	image	NOUN
cana-3838	68	8	processing	processing	NOUN
cana-3838	68	9	,	,	PUNCT
cana-3838	68	10	"	"	PUNCT
cana-3838	68	11	we	we	PRON
cana-3838	68	12	're	be	AUX
cana-3838	68	13	referring	refer	VERB
cana-3838	68	14	to	to	ADP
cana-3838	68	15	the	the	DET
cana-3838	68	16	steps	step	NOUN
cana-3838	68	17	used	use	VERB
cana-3838	68	18	to	to	ADP
cana-3838	68	19	decipher	decipher	NOUN
cana-3838	68	20	and	and	CCONJ
cana-3838	68	21	make	make	VERB
cana-3838	68	22	sense	sense	NOUN
cana-3838	68	23	of	of	ADP
cana-3838	68	24	massive	massive	ADJ
cana-3838	68	25	databases	database	NOUN
cana-3838	68	26	of	of	ADP
cana-3838	68	27	three	three	NUM
cana-3838	68	28	-	-	PUNCT
cana-3838	68	29	dimensional	dimensional	ADJ
cana-3838	68	30	(	(	PUNCT
cana-3838	68	31	3d	3d	NOUN
cana-3838	68	32	)	)	PUNCT
cana-3838	68	33	medical	medical	ADJ
cana-3838	68	34	pictures	picture	NOUN
cana-3838	68	35	,	,	PUNCT
cana-3838	68	36	often	often	ADV
cana-3838	68	37	captured	capture	VERB
cana-3838	68	38	by	by	ADP
cana-3838	68	39	mri	mri	NOUN
cana-3838	68	40	or	or	CCONJ
cana-3838	68	41	ct	ct	NUM
cana-3838	68	42	scanners	scanner	NOUN
cana-3838	68	43	,	,	PUNCT
cana-3838	68	44	for	for	ADP
cana-3838	68	45	the	the	DET
cana-3838	68	46	benefit	benefit	NOUN
cana-3838	68	47	of	of	ADP
cana-3838	68	48	research	research	NOUN
cana-3838	68	49	,	,	PUNCT
cana-3838	68	50	diagnosis	diagnosis	NOUN
cana-3838	68	51	,	,	PUNCT
cana-3838	68	52	or	or	CCONJ
cana-3838	68	53	treatment	treatment	NOUN
cana-3838	68	54	planning	planning	NOUN
cana-3838	68	55	.	.	PUNCT
cana-3838	69	1	medical	medical	ADJ
cana-3838	69	2	professionals	professional	NOUN
cana-3838	69	3	,	,	PUNCT
cana-3838	69	4	engineers	engineer	NOUN
cana-3838	69	5	,	,	PUNCT
cana-3838	69	6	and	and	CCONJ
cana-3838	69	7	radiologists	radiologist	NOUN
cana-3838	69	8	may	may	AUX
cana-3838	69	9	learn	learn	VERB
cana-3838	69	10	a	a	DET
cana-3838	69	11	great	great	ADJ
cana-3838	69	12	deal	deal	NOUN
cana-3838	69	13	about	about	ADP
cana-3838	69	14	the	the	DET
cana-3838	69	15	anatomy	anatomy	NOUN
cana-3838	69	16	of	of	ADP
cana-3838	69	17	individuals	individual	NOUN
cana-3838	69	18	and	and	CCONJ
cana-3838	69	19	whole	whole	ADJ
cana-3838	69	20	populations	population	NOUN
cana-3838	69	21	via	via	ADP
cana-3838	69	22	medical	medical	ADJ
cana-3838	69	23	image	image	NOUN
cana-3838	69	24	processing	processing	NOUN
cana-3838	69	25	.	.	PUNCT
cana-3838	70	1	statistical	statistical	ADJ
cana-3838	70	2	analysis	analysis	NOUN
cana-3838	70	3	,	,	PUNCT
cana-3838	70	4	measurement	measurement	NOUN
cana-3838	70	5	,	,	PUNCT
cana-3838	70	6	and	and	CCONJ
cana-3838	70	7	the	the	DET
cana-3838	70	8	development	development	NOUN
cana-3838	70	9	of	of	ADP
cana-3838	70	10	simulation	simulation	NOUN
cana-3838	70	11	models	model	NOUN
cana-3838	70	12	that	that	PRON
cana-3838	70	13	include	include	VERB
cana-3838	70	14	actual	actual	ADJ
cana-3838	70	15	anatomical	anatomical	ADJ
cana-3838	70	16	geometries	geometry	NOUN
cana-3838	70	17	all	all	PRON
cana-3838	70	18	provide	provide	VERB
cana-3838	70	19	the	the	DET
cana-3838	70	20	possibility	possibility	NOUN
cana-3838	70	21	of	of	ADP
cana-3838	70	22	a	a	DET
cana-3838	70	23	more	more	ADV
cana-3838	70	24	comprehensive	comprehensive	ADJ
cana-3838	70	25	knowledge	knowledge	NOUN
cana-3838	70	26	of	of	ADP
cana-3838	70	27	the	the	DET
cana-3838	70	28	interplay	interplay	NOUN
cana-3838	70	29	between	between	ADP
cana-3838	70	30	medical	medical	ADJ
cana-3838	70	31	equipment	equipment	NOUN
cana-3838	70	32	and	and	CCONJ
cana-3838	70	33	human	human	ADJ
cana-3838	70	34	anatomy	anatomy	NOUN
cana-3838	70	35	,	,	PUNCT
cana-3838	70	36	for	for	ADP
cana-3838	70	37	instance	instance	NOUN
cana-3838	70	38	[	[	X
cana-3838	70	39	6	6	NUM
cana-3838	70	40	]	]	PUNCT
cana-3838	70	41	.	.	PUNCT
cana-3838	71	1	incorrect	incorrect	ADJ
cana-3838	71	2	results	result	NOUN
cana-3838	71	3	are	be	AUX
cana-3838	71	4	produced	produce	VERB
cana-3838	71	5	by	by	ADP
cana-3838	71	6	several	several	ADJ
cana-3838	71	7	ml	ml	NOUN
cana-3838	71	8	algorithms	algorithm	NOUN
cana-3838	71	9	when	when	SCONJ
cana-3838	71	10	pixel	pixel	PROPN
cana-3838	71	11	classification	classification	NOUN
cana-3838	71	12	occurs	occur	VERB
cana-3838	71	13	because	because	SCONJ
cana-3838	71	14	these	these	DET
cana-3838	71	15	algorithms	algorithm	NOUN
cana-3838	71	16	do	do	AUX
cana-3838	71	17	not	not	PART
cana-3838	71	18	take	take	VERB
cana-3838	71	19	into	into	ADP
cana-3838	71	20	account	account	NOUN
cana-3838	71	21	the	the	DET
cana-3838	71	22	local	local	ADJ
cana-3838	71	23	dependencies	dependency	NOUN
cana-3838	71	24	of	of	ADP
cana-3838	71	25	labels	label	NOUN
cana-3838	71	26	.	.	PUNCT
cana-3838	72	1	in	in	ADP
cana-3838	72	2	other	other	ADJ
cana-3838	72	3	words	word	NOUN
cana-3838	72	4	,	,	PUNCT
cana-3838	72	5	segmentation	segmentation	NOUN
cana-3838	72	6	labels	label	NOUN
cana-3838	72	7	are	be	AUX
cana-3838	72	8	conditionally	conditionally	ADV
cana-3838	72	9	independent	independent	ADJ
cana-3838	72	10	given	give	VERB
cana-3838	72	11	the	the	DET
cana-3838	72	12	input	input	NOUN
cana-3838	72	13	picture	picture	NOUN
cana-3838	72	14	.	.	PUNCT
cana-3838	73	1	conditional	conditional	ADJ
cana-3838	73	2	random	random	ADJ
cana-3838	73	3	fields	field	NOUN
cana-3838	73	4	(	(	PUNCT
cana-3838	73	5	crfs	crfs	PROPN
cana-3838	73	6	)	)	PUNCT
cana-3838	73	7	and	and	CCONJ
cana-3838	73	8	other	other	ADJ
cana-3838	73	9	computationally	computationally	ADV
cana-3838	73	10	expensive	expensive	ADJ
cana-3838	73	11	inference	inference	NOUN
cana-3838	73	12	methods	method	NOUN
cana-3838	73	13	with	with	ADP
cana-3838	73	14	structured	structured	ADJ
cana-3838	73	15	outputs	output	NOUN
cana-3838	73	16	may	may	AUX
cana-3838	73	17	help	help	VERB
cana-3838	73	18	with	with	ADP
cana-3838	73	19	this	this	PRON
cana-3838	73	20	.	.	PUNCT
cana-3838	74	1	another	another	DET
cana-3838	74	2	option	option	NOUN
cana-3838	74	3	is	be	AUX
cana-3838	74	4	to	to	PART
cana-3838	74	5	utilize	utilize	VERB
cana-3838	74	6	a	a	DET
cana-3838	74	7	cascaded	cascade	VERB
cana-3838	74	8	architecture	architecture	NOUN
cana-3838	74	9	,	,	PUNCT
cana-3838	74	10	which	which	PRON
cana-3838	74	11	involves	involve	VERB
cana-3838	74	12	passing	pass	VERB
cana-3838	74	13	the	the	DET
cana-3838	74	14	pixel	pixel	ADJ
cana-3838	74	15	-	-	ADJ
cana-3838	74	16	wise	wise	ADJ
cana-3838	74	17	probability	probability	NOUN
cana-3838	74	18	estimates	estimate	NOUN
cana-3838	74	19	from	from	ADP
cana-3838	74	20	one	one	NUM
cana-3838	74	21	cnn	cnn	NOUN
cana-3838	74	22	into	into	ADP
cana-3838	74	23	specified	specified	ADJ
cana-3838	74	24	layers	layer	NOUN
cana-3838	74	25	of	of	ADP
cana-3838	74	26	another	another	DET
cana-3838	74	27	communications	communication	NOUN
cana-3838	74	28	on	on	ADP
cana-3838	74	29	applied	apply	VERB
cana-3838	74	30	nonlinear	nonlinear	ADJ
cana-3838	74	31	analysis	analysis	NOUN
cana-3838	74	32	issn	issn	NOUN
cana-3838	74	33	:	:	PUNCT
cana-3838	74	34	1074	1074	NUM
cana-3838	74	35	-	-	PUNCT
cana-3838	74	36	133x	133x	NUM
cana-3838	74	37	vol	vol	NOUN
cana-3838	74	38	32	32	NUM
cana-3838	74	39	no	no	NOUN
cana-3838	74	40	.	.	PUNCT
cana-3838	75	1	9s	9s	NUM
cana-3838	75	2	(	(	PUNCT
cana-3838	75	3	2025	2025	NUM
cana-3838	75	4	)	)	PUNCT
cana-3838	75	5	66	66	NUM
cana-3838	75	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-3838	75	7	dnn	dnn	PROPN
cana-3838	75	8	,	,	PUNCT
cana-3838	75	9	to	to	PART
cana-3838	75	10	explain	explain	VERB
cana-3838	75	11	label	label	NOUN
cana-3838	75	12	relationships	relationship	NOUN
cana-3838	75	13	.	.	PUNCT
cana-3838	76	1	the	the	DET
cana-3838	76	2	effectiveness	effectiveness	NOUN
cana-3838	76	3	of	of	ADP
cana-3838	76	4	convolutions	convolution	NOUN
cana-3838	76	5	suggests	suggest	VERB
cana-3838	76	6	that	that	SCONJ
cana-3838	76	7	this	this	DET
cana-3838	76	8	technique	technique	NOUN
cana-3838	76	9	might	might	AUX
cana-3838	76	10	be	be	AUX
cana-3838	76	11	much	much	ADV
cana-3838	76	12	faster	fast	ADJ
cana-3838	76	13	than	than	ADP
cana-3838	76	14	building	build	VERB
cana-3838	76	15	a	a	DET
cana-3838	76	16	crf	crf	NOUN
cana-3838	77	1	[	[	X
cana-3838	77	2	7	7	NUM
cana-3838	77	3	]	]	PUNCT
cana-3838	77	4	.	.	PUNCT
cana-3838	78	1	subfield	subfield	NOUN
cana-3838	78	2	of	of	ADP
cana-3838	78	3	machine	machine	NOUN
cana-3838	78	4	learning	learning	NOUN
cana-3838	78	5	known	know	VERB
cana-3838	78	6	as	as	ADP
cana-3838	78	7	"	"	PUNCT
cana-3838	78	8	deep	deep	ADJ
cana-3838	78	9	learning	learning	NOUN
cana-3838	78	10	"	"	PUNCT
cana-3838	78	11	allows	allow	VERB
cana-3838	78	12	computers	computer	NOUN
cana-3838	78	13	to	to	PART
cana-3838	78	14	learn	learn	VERB
cana-3838	78	15	data	data	NOUN
cana-3838	78	16	representations	representation	NOUN
cana-3838	78	17	,	,	PUNCT
cana-3838	78	18	which	which	PRON
cana-3838	78	19	in	in	ADP
cana-3838	78	20	turn	turn	NOUN
cana-3838	78	21	allows	allow	VERB
cana-3838	78	22	them	they	PRON
cana-3838	78	23	to	to	PART
cana-3838	78	24	draw	draw	VERB
cana-3838	78	25	inferences	inference	NOUN
cana-3838	78	26	and	and	CCONJ
cana-3838	78	27	make	make	VERB
cana-3838	78	28	predictions	prediction	NOUN
cana-3838	78	29	based	base	VERB
cana-3838	78	30	on	on	ADP
cana-3838	78	31	data	datum	NOUN
cana-3838	78	32	.	.	PUNCT
cana-3838	79	1	these	these	DET
cana-3838	79	2	methods	method	NOUN
cana-3838	79	3	constitute	constitute	VERB
cana-3838	79	4	a	a	DET
cana-3838	79	5	significant	significant	ADJ
cana-3838	79	6	computational	computational	ADJ
cana-3838	79	7	intelligence	intelligence	NOUN
cana-3838	79	8	approach	approach	NOUN
cana-3838	79	9	and	and	CCONJ
cana-3838	79	10	find	find	VERB
cana-3838	79	11	widespread	widespread	ADJ
cana-3838	79	12	use	use	NOUN
cana-3838	79	13	in	in	ADP
cana-3838	79	14	medical	medical	ADJ
cana-3838	79	15	imaging	imaging	NOUN
cana-3838	79	16	categorization	categorization	NOUN
cana-3838	79	17	.	.	PUNCT
cana-3838	80	1	deep	deep	ADJ
cana-3838	80	2	learning	learning	NOUN
cana-3838	80	3	has	have	AUX
cana-3838	80	4	been	be	AUX
cana-3838	80	5	very	very	ADV
cana-3838	80	6	successful	successful	ADJ
cana-3838	80	7	in	in	ADP
cana-3838	80	8	many	many	ADJ
cana-3838	80	9	various	various	ADJ
cana-3838	80	10	domains	domain	NOUN
cana-3838	80	11	and	and	CCONJ
cana-3838	80	12	applications	application	NOUN
cana-3838	80	13	,	,	PUNCT
cana-3838	80	14	but	but	CCONJ
cana-3838	80	15	it	it	PRON
cana-3838	80	16	is	be	AUX
cana-3838	80	17	a	a	DET
cana-3838	80	18	data	data	NOUN
cana-3838	80	19	thirsty	thirsty	ADJ
cana-3838	80	20	method	method	NOUN
cana-3838	80	21	that	that	PRON
cana-3838	80	22	requires	require	VERB
cana-3838	80	23	at	at	ADV
cana-3838	80	24	least	least	ADV
cana-3838	80	25	10	10	NUM
cana-3838	80	26	times	time	NOUN
cana-3838	80	27	as	as	ADV
cana-3838	80	28	many	many	ADJ
cana-3838	80	29	samples	sample	NOUN
cana-3838	80	30	with	with	ADP
cana-3838	80	31	degrees	degree	NOUN
cana-3838	80	32	of	of	ADP
cana-3838	80	33	freedom	freedom	NOUN
cana-3838	80	34	.	.	PUNCT
cana-3838	81	1	if	if	SCONJ
cana-3838	81	2	we	we	PRON
cana-3838	81	3	use	use	VERB
cana-3838	81	4	transfer	transfer	NOUN
cana-3838	81	5	learning	learn	VERB
cana-3838	81	6	to	to	PART
cana-3838	81	7	improve	improve	VERB
cana-3838	81	8	storing	store	VERB
cana-3838	81	9	knowledge	knowledge	NOUN
cana-3838	81	10	we	we	PRON
cana-3838	81	11	've	have	AUX
cana-3838	81	12	already	already	ADV
cana-3838	81	13	learned	learn	VERB
cana-3838	81	14	on	on	ADP
cana-3838	81	15	similar	similar	ADJ
cana-3838	81	16	situations	situation	NOUN
cana-3838	81	17	,	,	PUNCT
cana-3838	81	18	we	we	PRON
cana-3838	81	19	may	may	AUX
cana-3838	81	20	potentially	potentially	ADV
cana-3838	81	21	solve	solve	VERB
cana-3838	81	22	the	the	DET
cana-3838	81	23	difficulty	difficulty	NOUN
cana-3838	81	24	of	of	ADP
cana-3838	81	25	tiny	tiny	ADJ
cana-3838	81	26	training	training	NOUN
cana-3838	81	27	samples	sample	NOUN
cana-3838	81	28	.	.	PUNCT
cana-3838	82	1	in	in	ADP
cana-3838	82	2	transfer	transfer	NOUN
cana-3838	82	3	learning	learning	NOUN
cana-3838	82	4	,	,	PUNCT
cana-3838	82	5	a	a	DET
cana-3838	82	6	large	large	ADJ
cana-3838	82	7	dataset	dataset	NOUN
cana-3838	82	8	(	(	PUNCT
cana-3838	82	9	the	the	DET
cana-3838	82	10	base	base	NOUN
cana-3838	82	11	dataset	dataset	NOUN
cana-3838	82	12	)	)	PUNCT
cana-3838	82	13	is	be	AUX
cana-3838	82	14	used	use	VERB
cana-3838	82	15	to	to	PART
cana-3838	82	16	train	train	VERB
cana-3838	82	17	the	the	DET
cana-3838	82	18	network	network	NOUN
cana-3838	82	19	,	,	PUNCT
cana-3838	82	20	and	and	CCONJ
cana-3838	82	21	then	then	ADV
cana-3838	82	22	its	its	PRON
cana-3838	82	23	knowledge	knowledge	NOUN
cana-3838	82	24	is	be	AUX
cana-3838	82	25	applied	apply	VERB
cana-3838	82	26	to	to	ADP
cana-3838	82	27	a	a	DET
cana-3838	82	28	smaller	small	ADJ
cana-3838	82	29	dataset	dataset	NOUN
cana-3838	82	30	(	(	PUNCT
cana-3838	82	31	the	the	DET
cana-3838	82	32	target	target	NOUN
cana-3838	82	33	dataset	dataset	NOUN
cana-3838	82	34	)	)	PUNCT
cana-3838	83	1	[	[	X
cana-3838	83	2	8	8	NUM
cana-3838	83	3	]	]	PUNCT
cana-3838	83	4	.	.	PUNCT
cana-3838	84	1	this	this	PRON
cana-3838	84	2	is	be	AUX
cana-3838	84	3	one	one	NUM
cana-3838	84	4	way	way	NOUN
cana-3838	84	5	of	of	ADP
cana-3838	84	6	deep	deep	ADJ
cana-3838	84	7	learning	learning	NOUN
cana-3838	84	8	.	.	PUNCT
cana-3838	85	1	in	in	ADP
cana-3838	85	2	this	this	DET
cana-3838	85	3	study	study	NOUN
cana-3838	85	4	,	,	PUNCT
cana-3838	85	5	we	we	PRON
cana-3838	85	6	use	use	VERB
cana-3838	85	7	residual	residual	ADJ
cana-3838	85	8	networks	network	NOUN
cana-3838	85	9	(	(	PUNCT
cana-3838	85	10	resnets	resnet	NOUN
cana-3838	85	11	)	)	PUNCT
cana-3838	85	12	to	to	PART
cana-3838	85	13	improve	improve	VERB
cana-3838	85	14	computation	computation	NOUN
cana-3838	85	15	time	time	NOUN
cana-3838	85	16	and	and	CCONJ
cana-3838	85	17	get	get	VERB
cana-3838	85	18	around	around	ADP
cana-3838	85	19	the	the	DET
cana-3838	85	20	problems	problem	NOUN
cana-3838	85	21	with	with	ADP
cana-3838	85	22	convolutional	convolutional	ADJ
cana-3838	85	23	neural	neural	ADJ
cana-3838	85	24	networks	network	NOUN
cana-3838	85	25	(	(	PUNCT
cana-3838	85	26	cnns	cnns	PROPN
cana-3838	85	27	)	)	PUNCT
cana-3838	85	28	and	and	CCONJ
cana-3838	85	29	fcns	fcns	NOUN
cana-3838	85	30	.	.	PUNCT
cana-3838	86	1	the	the	DET
cana-3838	86	2	idea	idea	NOUN
cana-3838	86	3	behind	behind	ADP
cana-3838	86	4	resnets	resnet	NOUN
cana-3838	86	5	is	be	AUX
cana-3838	86	6	to	to	PART
cana-3838	86	7	add	add	VERB
cana-3838	86	8	the	the	DET
cana-3838	86	9	layer	layer	NOUN
cana-3838	86	10	's	's	PART
cana-3838	86	11	output	output	NOUN
cana-3838	86	12	to	to	ADP
cana-3838	86	13	its	its	PRON
cana-3838	86	14	input	input	NOUN
cana-3838	86	15	.	.	PUNCT
cana-3838	87	1	since	since	SCONJ
cana-3838	87	2	deep	deep	ADJ
cana-3838	87	3	networks	network	NOUN
cana-3838	87	4	already	already	ADV
cana-3838	87	5	include	include	VERB
cana-3838	87	6	shortcut	shortcut	NOUN
cana-3838	87	7	connections	connection	NOUN
cana-3838	87	8	running	run	VERB
cana-3838	87	9	parallel	parallel	NOUN
cana-3838	87	10	to	to	ADP
cana-3838	87	11	their	their	PRON
cana-3838	87	12	regular	regular	ADJ
cana-3838	87	13	convolutional	convolutional	ADJ
cana-3838	87	14	layers	layer	NOUN
cana-3838	87	15	,	,	PUNCT
cana-3838	87	16	this	this	DET
cana-3838	87	17	little	little	ADJ
cana-3838	87	18	tweak	tweak	NOUN
cana-3838	87	19	makes	make	VERB
cana-3838	87	20	training	train	VERB
cana-3838	87	21	them	they	PRON
cana-3838	87	22	much	much	ADV
cana-3838	87	23	easier	easy	ADJ
cana-3838	87	24	.	.	PUNCT
cana-3838	88	1	training	training	NOUN
cana-3838	88	2	goes	go	VERB
cana-3838	88	3	more	more	ADV
cana-3838	88	4	quickly	quickly	ADV
cana-3838	88	5	and	and	CCONJ
cana-3838	88	6	accurately	accurately	ADV
cana-3838	88	7	because	because	SCONJ
cana-3838	88	8	to	to	ADP
cana-3838	88	9	these	these	DET
cana-3838	88	10	live	live	ADJ
cana-3838	88	11	shortcuts	shortcut	NOUN
cana-3838	88	12	,	,	PUNCT
cana-3838	88	13	and	and	CCONJ
cana-3838	88	14	gradients	gradient	NOUN
cana-3838	88	15	propagate	propagate	VERB
cana-3838	88	16	readily	readily	ADV
cana-3838	88	17	across	across	ADP
cana-3838	88	18	them	they	PRON
cana-3838	88	19	,	,	PUNCT
cana-3838	88	20	thanks	thank	NOUN
cana-3838	88	21	to	to	ADP
cana-3838	88	22	the	the	DET
cana-3838	88	23	much	much	ADV
cana-3838	88	24	enhanced	enhance	VERB
cana-3838	88	25	depth.one	depth.one	X
cana-3838	88	26	deep	deep	ADJ
cana-3838	88	27	cnn	cnn	NOUN
cana-3838	88	28	architecture	architecture	NOUN
cana-3838	88	29	is	be	AUX
cana-3838	88	30	vggnet	vggnet	ADJ
cana-3838	88	31	.	.	PUNCT
cana-3838	89	1	in	in	ADP
cana-3838	89	2	2014	2014	NUM
cana-3838	89	3	,	,	PUNCT
cana-3838	89	4	it	it	PRON
cana-3838	89	5	came	come	VERB
cana-3838	89	6	in	in	ADP
cana-3838	89	7	second	second	ADJ
cana-3838	89	8	place	place	NOUN
cana-3838	89	9	in	in	ADP
cana-3838	89	10	the	the	DET
cana-3838	89	11	ilsvrc	ilsvrc	ADJ
cana-3838	89	12	competition	competition	NOUN
cana-3838	89	13	[	[	X
cana-3838	89	14	10	10	NUM
cana-3838	89	15	]	]	PUNCT
cana-3838	89	16	.	.	PUNCT
cana-3838	90	1	here	here	ADV
cana-3838	90	2	,	,	PUNCT
cana-3838	90	3	we	we	PRON
cana-3838	90	4	provide	provide	VERB
cana-3838	90	5	a	a	DET
cana-3838	90	6	vgg16+resnet50	vgg16+resnet50	NOUN
cana-3838	90	7	hybrid	hybrid	ADJ
cana-3838	90	8	model	model	NOUN
cana-3838	90	9	for	for	ADP
cana-3838	90	10	mri	mri	NOUN
cana-3838	90	11	-	-	PUNCT
cana-3838	90	12	based	base	VERB
cana-3838	90	13	brain	brain	NOUN
cana-3838	90	14	tumor	tumor	NOUN
cana-3838	90	15	segmentation	segmentation	NOUN
cana-3838	90	16	.	.	PUNCT
cana-3838	91	1	ii.related	ii.relate	VERB
cana-3838	91	2	work	work	VERB
cana-3838	91	3	the	the	DET
cana-3838	91	4	visual	visual	ADJ
cana-3838	91	5	characteristics	characteristic	NOUN
cana-3838	91	6	of	of	ADP
cana-3838	91	7	the	the	DET
cana-3838	91	8	tumor	tumor	NOUN
cana-3838	91	9	region	region	NOUN
cana-3838	91	10	significantly	significantly	ADV
cana-3838	91	11	influence	influence	VERB
cana-3838	91	12	the	the	DET
cana-3838	91	13	accuracy	accuracy	NOUN
cana-3838	91	14	of	of	ADP
cana-3838	91	15	brain	brain	NOUN
cana-3838	91	16	tumor	tumor	NOUN
cana-3838	91	17	identification	identification	NOUN
cana-3838	91	18	and	and	CCONJ
cana-3838	91	19	segmentation	segmentation	NOUN
cana-3838	91	20	.	.	PUNCT
cana-3838	92	1	it	it	PRON
cana-3838	92	2	is	be	AUX
cana-3838	92	3	possible	possible	ADJ
cana-3838	92	4	for	for	SCONJ
cana-3838	92	5	similar	similar	ADJ
cana-3838	92	6	scans	scan	NOUN
cana-3838	92	7	to	to	PART
cana-3838	92	8	show	show	VERB
cana-3838	92	9	different	different	ADJ
cana-3838	92	10	tumor	tumor	NOUN
cana-3838	92	11	areas	area	NOUN
cana-3838	92	12	in	in	ADP
cana-3838	92	13	terms	term	NOUN
cana-3838	92	14	of	of	ADP
cana-3838	92	15	intensity	intensity	NOUN
cana-3838	92	16	,	,	PUNCT
cana-3838	92	17	shape	shape	NOUN
cana-3838	92	18	,	,	PUNCT
cana-3838	92	19	location	location	NOUN
cana-3838	92	20	,	,	PUNCT
cana-3838	92	21	and	and	CCONJ
cana-3838	92	22	size	size	NOUN
cana-3838	92	23	.	.	PUNCT
cana-3838	93	1	in	in	ADP
cana-3838	93	2	this	this	DET
cana-3838	93	3	article	article	NOUN
cana-3838	93	4	,	,	PUNCT
cana-3838	93	5	we	we	PRON
cana-3838	93	6	review	review	VERB
cana-3838	93	7	the	the	DET
cana-3838	93	8	research	research	NOUN
cana-3838	93	9	on	on	ADP
cana-3838	93	10	methods	method	NOUN
cana-3838	93	11	for	for	ADP
cana-3838	93	12	segmenting	segment	VERB
cana-3838	93	13	and	and	CCONJ
cana-3838	93	14	detecting	detect	VERB
cana-3838	93	15	brain	brain	NOUN
cana-3838	93	16	tumors	tumor	NOUN
cana-3838	93	17	in	in	ADP
cana-3838	93	18	images	image	NOUN
cana-3838	93	19	.	.	PUNCT
cana-3838	94	1	with	with	ADP
cana-3838	94	2	the	the	DET
cana-3838	94	3	addition	addition	NOUN
cana-3838	94	4	of	of	ADP
cana-3838	94	5	volumetric	volumetric	ADJ
cana-3838	94	6	input	input	NOUN
cana-3838	94	7	patches	patch	NOUN
cana-3838	94	8	,	,	PUNCT
cana-3838	94	9	jonas	jonas	PROPN
cana-3838	94	10	wacker	wacker	PROPN
cana-3838	94	11	et	et	PROPN
cana-3838	94	12	al	al	PROPN
cana-3838	94	13	.	.	PUNCT
cana-3838	95	1	[	[	X
cana-3838	95	2	11	11	NUM
cana-3838	95	3	]	]	PUNCT
cana-3838	95	4	shown	show	VERB
cana-3838	95	5	that	that	SCONJ
cana-3838	95	6	albunet3d	albunet3d	ADJ
cana-3838	95	7	outperforms	outperform	VERB
cana-3838	95	8	albunet2d	albunet2d	PROPN
cana-3838	95	9	even	even	ADV
cana-3838	95	10	more	more	ADJ
cana-3838	95	11	.	.	PUNCT
cana-3838	96	1	a	a	DET
cana-3838	96	2	more	more	ADV
cana-3838	96	3	robust	robust	ADJ
cana-3838	96	4	training	training	NOUN
cana-3838	96	5	method	method	NOUN
cana-3838	96	6	and	and	CCONJ
cana-3838	96	7	better	well	ADJ
cana-3838	96	8	segmentation	segmentation	NOUN
cana-3838	96	9	outcomes	outcome	NOUN
cana-3838	96	10	using	use	VERB
cana-3838	96	11	u	u	NOUN
cana-3838	96	12	-	-	ADJ
cana-3838	96	13	net	net	ADJ
cana-3838	96	14	based	base	VERB
cana-3838	96	15	architectures	architecture	NOUN
cana-3838	96	16	for	for	ADP
cana-3838	96	17	the	the	DET
cana-3838	96	18	problem	problem	NOUN
cana-3838	96	19	of	of	ADP
cana-3838	96	20	brain	brain	NOUN
cana-3838	96	21	tumor	tumor	NOUN
cana-3838	96	22	segmentation	segmentation	NOUN
cana-3838	96	23	are	be	AUX
cana-3838	96	24	shown	show	VERB
cana-3838	96	25	by	by	ADP
cana-3838	96	26	using	use	VERB
cana-3838	96	27	encoders	encoder	NOUN
cana-3838	96	28	pretrained	pretraine	VERB
cana-3838	96	29	on	on	ADP
cana-3838	96	30	imagenet	imagenet	NOUN
cana-3838	96	31	.	.	PUNCT
cana-3838	97	1	regrettably	regrettably	ADV
cana-3838	97	2	,	,	PUNCT
cana-3838	97	3	this	this	PRON
cana-3838	97	4	is	be	AUX
cana-3838	97	5	not	not	PART
cana-3838	97	6	applicable	applicable	ADJ
cana-3838	97	7	to	to	ADP
cana-3838	97	8	their	their	PRON
cana-3838	97	9	privately	privately	ADV
cana-3838	97	10	obtained	obtain	VERB
cana-3838	97	11	clinical	clinical	ADJ
cana-3838	97	12	dataset	dataset	NOUN
cana-3838	97	13	,	,	PUNCT
cana-3838	97	14	which	which	PRON
cana-3838	97	15	necessitates	necessitate	VERB
cana-3838	97	16	further	further	ADJ
cana-3838	97	17	robustness	robustness	NOUN
cana-3838	97	18	via	via	ADP
cana-3838	97	19	future	future	ADJ
cana-3838	97	20	study	study	NOUN
cana-3838	97	21	.	.	PUNCT
cana-3838	98	1	compared	compare	VERB
cana-3838	98	2	to	to	ADP
cana-3838	98	3	the	the	DET
cana-3838	98	4	brats	brat	NOUN
cana-3838	98	5	benchmark	benchmark	NOUN
cana-3838	98	6	,	,	PUNCT
cana-3838	98	7	the	the	DET
cana-3838	98	8	mri	mri	NOUN
cana-3838	98	9	data	datum	NOUN
cana-3838	98	10	that	that	PRON
cana-3838	98	11	is	be	AUX
cana-3838	98	12	accessible	accessible	ADJ
cana-3838	98	13	in	in	ADP
cana-3838	98	14	a	a	DET
cana-3838	98	15	real	real	ADJ
cana-3838	98	16	-	-	PUNCT
cana-3838	98	17	world	world	NOUN
cana-3838	98	18	clinical	clinical	ADJ
cana-3838	98	19	setting	setting	NOUN
cana-3838	98	20	is	be	AUX
cana-3838	98	21	far	far	ADV
cana-3838	98	22	more	more	ADV
cana-3838	98	23	diverse	diverse	ADJ
cana-3838	98	24	.	.	PUNCT
cana-3838	99	1	in	in	ADP
cana-3838	99	2	order	order	NOUN
cana-3838	99	3	to	to	PART
cana-3838	99	4	automatically	automatically	ADV
cana-3838	99	5	detect	detect	VERB
cana-3838	99	6	brain	brain	NOUN
cana-3838	99	7	cancers	cancer	NOUN
cana-3838	99	8	from	from	ADP
cana-3838	99	9	mri	mri	NOUN
cana-3838	99	10	data	datum	NOUN
cana-3838	99	11	,	,	PUNCT
cana-3838	99	12	ayesha	ayesha	PROPN
cana-3838	99	13	younis	younis	PROPN
cana-3838	99	14	et	et	VERB
cana-3838	99	15	al	al	PROPN
cana-3838	99	16	.	.	PUNCT
cana-3838	100	1	[	[	X
cana-3838	100	2	12	12	NUM
cana-3838	100	3	]	]	PUNCT
cana-3838	100	4	constructed	construct	VERB
cana-3838	100	5	a	a	DET
cana-3838	100	6	convolutional	convolutional	ADJ
cana-3838	100	7	neural	neural	ADJ
cana-3838	100	8	network	network	NOUN
cana-3838	100	9	(	(	PUNCT
cana-3838	100	10	cnn	cnn	PROPN
cana-3838	100	11	)	)	PUNCT
cana-3838	100	12	.	.	PUNCT
cana-3838	101	1	it	it	PRON
cana-3838	101	2	would	would	AUX
cana-3838	101	3	be	be	AUX
cana-3838	101	4	easier	easy	ADJ
cana-3838	101	5	and	and	CCONJ
cana-3838	101	6	faster	fast	ADV
cana-3838	101	7	to	to	PART
cana-3838	101	8	train	train	VERB
cana-3838	101	9	the	the	DET
cana-3838	101	10	network	network	NOUN
cana-3838	101	11	using	use	VERB
cana-3838	101	12	a	a	DET
cana-3838	101	13	pre	pre	ADJ
cana-3838	101	14	-	-	ADJ
cana-3838	101	15	trained	train	VERB
cana-3838	101	16	vgg	vgg	ADJ
cana-3838	101	17	16	16	NUM
cana-3838	101	18	model	model	NOUN
cana-3838	101	19	.	.	PUNCT
cana-3838	102	1	when	when	SCONJ
cana-3838	102	2	choosing	choose	VERB
cana-3838	102	3	a	a	DET
cana-3838	102	4	commercial	commercial	ADJ
cana-3838	102	5	model	model	NOUN
cana-3838	102	6	,	,	PUNCT
cana-3838	102	7	it	it	PRON
cana-3838	102	8	is	be	AUX
cana-3838	102	9	vital	vital	ADJ
cana-3838	102	10	to	to	PART
cana-3838	102	11	examine	examine	VERB
cana-3838	102	12	vgg	vgg	PROPN
cana-3838	102	13	16	16	NUM
cana-3838	102	14	,	,	PUNCT
cana-3838	102	15	a	a	DET
cana-3838	102	16	cnn	cnn	PROPN
cana-3838	102	17	model	model	NOUN
cana-3838	102	18	with	with	ADP
cana-3838	102	19	sixteen	sixteen	NUM
cana-3838	102	20	layers	layer	NOUN
cana-3838	102	21	.	.	PUNCT
cana-3838	103	1	their	their	PRON
cana-3838	103	2	paper	paper	NOUN
cana-3838	103	3	's	's	PART
cana-3838	103	4	stated	state	VERB
cana-3838	103	5	goal	goal	NOUN
cana-3838	103	6	was	be	AUX
cana-3838	103	7	to	to	PART
cana-3838	103	8	find	find	VERB
cana-3838	103	9	a	a	DET
cana-3838	103	10	brain	brain	NOUN
cana-3838	103	11	tumor	tumor	NOUN
cana-3838	103	12	using	use	VERB
cana-3838	103	13	vgg	vgg	PROPN
cana-3838	103	14	16	16	NUM
cana-3838	103	15	,	,	PUNCT
cana-3838	103	16	cnn	cnn	PROPN
cana-3838	103	17	model	model	NOUN
cana-3838	103	18	architecture	architecture	NOUN
cana-3838	103	19	,	,	PUNCT
cana-3838	103	20	and	and	CCONJ
cana-3838	103	21	weights	weight	NOUN
cana-3838	103	22	to	to	ADP
cana-3838	103	23	training	training	NOUN
cana-3838	103	24	data	datum	NOUN
cana-3838	103	25	.	.	PUNCT
cana-3838	104	1	the	the	DET
cana-3838	104	2	precision	precision	NOUN
cana-3838	104	3	of	of	ADP
cana-3838	104	4	the	the	DET
cana-3838	104	5	outcome	outcome	NOUN
cana-3838	104	6	was	be	AUX
cana-3838	104	7	verified	verify	VERB
cana-3838	104	8	.	.	PUNCT
cana-3838	105	1	they	they	PRON
cana-3838	105	2	planned	plan	VERB
cana-3838	105	3	to	to	PART
cana-3838	105	4	use	use	VERB
cana-3838	105	5	magnetic	magnetic	ADJ
cana-3838	105	6	resonance	resonance	NOUN
cana-3838	105	7	imaging	imaging	NOUN
cana-3838	105	8	(	(	PUNCT
cana-3838	105	9	mri	mri	NOUN
cana-3838	105	10	)	)	PUNCT
cana-3838	105	11	scans	scan	NOUN
cana-3838	105	12	of	of	ADP
cana-3838	105	13	the	the	DET
cana-3838	105	14	brain	brain	NOUN
cana-3838	105	15	to	to	PART
cana-3838	105	16	look	look	VERB
cana-3838	105	17	for	for	ADP
cana-3838	105	18	tumors	tumor	NOUN
cana-3838	105	19	.	.	PUNCT
cana-3838	106	1	the	the	DET
cana-3838	106	2	findings	finding	NOUN
cana-3838	106	3	showed	show	VERB
cana-3838	106	4	that	that	SCONJ
cana-3838	106	5	the	the	DET
cana-3838	106	6	proposed	propose	VERB
cana-3838	106	7	network	network	NOUN
cana-3838	106	8	design	design	NOUN
cana-3838	106	9	communications	communication	NOUN
cana-3838	106	10	on	on	ADP
cana-3838	106	11	applied	apply	VERB
cana-3838	106	12	nonlinear	nonlinear	ADJ
cana-3838	106	13	analysis	analysis	NOUN
cana-3838	106	14	issn	issn	NOUN
cana-3838	106	15	:	:	PUNCT
cana-3838	106	16	1074	1074	NUM
cana-3838	106	17	-	-	PUNCT
cana-3838	106	18	133x	133x	NUM
cana-3838	106	19	vol	vol	NOUN
cana-3838	106	20	32	32	NUM
cana-3838	106	21	no	no	NOUN
cana-3838	106	22	.	.	PUNCT
cana-3838	107	1	9s	9s	NUM
cana-3838	107	2	(	(	PUNCT
cana-3838	107	3	2025	2025	NUM
cana-3838	107	4	)	)	PUNCT
cana-3838	107	5	67	67	NUM
cana-3838	108	1	https://internationalpubls.com	https://internationalpubls.com	X
cana-3838	108	2	was	be	AUX
cana-3838	108	3	both	both	PRON
cana-3838	108	4	aesthetically	aesthetically	ADV
cana-3838	108	5	pleasing	pleasing	ADJ
cana-3838	108	6	and	and	CCONJ
cana-3838	108	7	much	much	ADV
cana-3838	108	8	more	more	ADV
cana-3838	108	9	effective	effective	ADJ
cana-3838	108	10	than	than	ADP
cana-3838	108	11	conventional	conventional	ADJ
cana-3838	108	12	approaches	approach	NOUN
cana-3838	108	13	in	in	ADP
cana-3838	108	14	tumor	tumor	NOUN
cana-3838	108	15	identification	identification	NOUN
cana-3838	108	16	.	.	PUNCT
cana-3838	109	1	several	several	ADJ
cana-3838	109	2	processing	processing	NOUN
cana-3838	109	3	techniques	technique	NOUN
cana-3838	109	4	were	be	AUX
cana-3838	109	5	also	also	ADV
cana-3838	109	6	carried	carry	VERB
cana-3838	109	7	out	out	ADP
cana-3838	109	8	to	to	PART
cana-3838	109	9	enhance	enhance	VERB
cana-3838	109	10	the	the	DET
cana-3838	109	11	model	model	NOUN
cana-3838	109	12	's	's	PART
cana-3838	109	13	performance	performance	NOUN
cana-3838	109	14	even	even	ADV
cana-3838	109	15	more	more	ADV
cana-3838	109	16	.	.	PUNCT
cana-3838	110	1	biomedical	biomedical	ADJ
cana-3838	110	2	image	image	NOUN
cana-3838	110	3	segmentation	segmentation	NOUN
cana-3838	110	4	is	be	AUX
cana-3838	110	5	a	a	DET
cana-3838	110	6	common	common	ADJ
cana-3838	110	7	goal	goal	NOUN
cana-3838	110	8	for	for	ADP
cana-3838	110	9	both	both	PRON
cana-3838	110	10	of	of	ADP
cana-3838	110	11	the	the	DET
cana-3838	110	12	networks	network	NOUN
cana-3838	110	13	described	describe	VERB
cana-3838	110	14	by	by	ADP
cana-3838	110	15	mahnoor	mahnoor	PROPN
cana-3838	110	16	ali	ali	PROPN
cana-3838	110	17	et	et	PROPN
cana-3838	110	18	al	al	PROPN
cana-3838	110	19	.	.	PUNCT
cana-3838	111	1	[	[	X
cana-3838	111	2	13	13	NUM
cana-3838	111	3	]	]	PUNCT
cana-3838	111	4	,	,	PUNCT
cana-3838	111	5	which	which	PRON
cana-3838	111	6	form	form	VERB
cana-3838	111	7	an	an	DET
cana-3838	111	8	ensemble	ensemble	NOUN
cana-3838	111	9	.	.	PUNCT
cana-3838	112	1	when	when	SCONJ
cana-3838	112	2	presented	present	VERB
cana-3838	112	3	with	with	ADP
cana-3838	112	4	the	the	DET
cana-3838	112	5	multimodal	multimodal	NOUN
cana-3838	112	6	mri	mri	NOUN
cana-3838	112	7	images	image	NOUN
cana-3838	112	8	from	from	ADP
cana-3838	112	9	the	the	DET
cana-3838	112	10	brats	brat	NOUN
cana-3838	112	11	2019	2019	NUM
cana-3838	112	12	challenge	challenge	NOUN
cana-3838	112	13	,	,	PUNCT
cana-3838	112	14	the	the	DET
cana-3838	112	15	ensemble	ensemble	ADJ
cana-3838	112	16	is	be	AUX
cana-3838	112	17	able	able	ADJ
cana-3838	112	18	to	to	PART
cana-3838	112	19	provide	provide	VERB
cana-3838	112	20	very	very	ADV
cana-3838	112	21	accurate	accurate	ADJ
cana-3838	112	22	tumor	tumor	NOUN
cana-3838	112	23	segmentation	segmentation	NOUN
cana-3838	112	24	,	,	PUNCT
cana-3838	112	25	which	which	PRON
cana-3838	112	26	compares	compare	VERB
cana-3838	112	27	well	well	ADV
cana-3838	112	28	with	with	ADP
cana-3838	112	29	predictions	prediction	NOUN
cana-3838	112	30	made	make	VERB
cana-3838	112	31	by	by	ADP
cana-3838	112	32	other	other	ADJ
cana-3838	112	33	state	state	NOUN
cana-3838	112	34	-	-	PUNCT
cana-3838	112	35	ofart	ofart	NOUN
cana-3838	112	36	models	model	NOUN
cana-3838	112	37	.	.	PUNCT
cana-3838	113	1	they	they	PRON
cana-3838	113	2	blend	blend	VERB
cana-3838	113	3	the	the	DET
cana-3838	113	4	individual	individual	ADJ
cana-3838	113	5	model	model	NOUN
cana-3838	113	6	outputs	output	NOUN
cana-3838	113	7	using	use	VERB
cana-3838	113	8	a	a	DET
cana-3838	113	9	variable	variable	NOUN
cana-3838	113	10	ensembling	ensemble	VERB
cana-3838	113	11	strategy	strategy	NOUN
cana-3838	113	12	to	to	PART
cana-3838	113	13	get	get	VERB
cana-3838	113	14	the	the	DET
cana-3838	113	15	best	good	ADJ
cana-3838	113	16	ratings	rating	NOUN
cana-3838	113	17	.	.	PUNCT
cana-3838	114	1	to	to	PART
cana-3838	114	2	help	help	VERB
cana-3838	114	3	with	with	ADP
cana-3838	114	4	disease	disease	NOUN
cana-3838	114	5	planning	planning	NOUN
cana-3838	114	6	and	and	CCONJ
cana-3838	114	7	patient	patient	ADJ
cana-3838	114	8	care	care	NOUN
cana-3838	114	9	in	in	ADP
cana-3838	114	10	the	the	DET
cana-3838	114	11	clinic	clinic	NOUN
cana-3838	114	12	,	,	PUNCT
cana-3838	114	13	the	the	DET
cana-3838	114	14	suggested	suggest	VERB
cana-3838	114	15	ensemble	ensemble	NOUN
cana-3838	114	16	provides	provide	VERB
cana-3838	114	17	an	an	DET
cana-3838	114	18	objective	objective	NOUN
cana-3838	114	19	and	and	CCONJ
cana-3838	114	20	automated	automated	ADJ
cana-3838	114	21	way	way	NOUN
cana-3838	114	22	to	to	PART
cana-3838	114	23	generate	generate	VERB
cana-3838	114	24	brain	brain	NOUN
cana-3838	114	25	tumor	tumor	NOUN
cana-3838	114	26	segmentation	segmentation	NOUN
cana-3838	114	27	.	.	PUNCT
cana-3838	115	1	in	in	ADP
cana-3838	115	2	their	their	PRON
cana-3838	115	3	study	study	NOUN
cana-3838	115	4	,	,	PUNCT
cana-3838	115	5	yakubbhanothu	yakubbhanothu	PROPN
cana-3838	115	6	et	et	PROPN
cana-3838	115	7	al	al	PROPN
cana-3838	115	8	.	.	PUNCT
cana-3838	116	1	[	[	X
cana-3838	116	2	14	14	NUM
cana-3838	116	3	]	]	PUNCT
cana-3838	116	4	discussed	discuss	VERB
cana-3838	116	5	the	the	DET
cana-3838	116	6	use	use	NOUN
cana-3838	116	7	of	of	ADP
cana-3838	116	8	a	a	DET
cana-3838	116	9	deep	deep	ADJ
cana-3838	116	10	learning	learning	NOUN
cana-3838	116	11	system	system	NOUN
cana-3838	116	12	for	for	ADP
cana-3838	116	13	the	the	DET
cana-3838	116	14	automatic	automatic	ADJ
cana-3838	116	15	detection	detection	NOUN
cana-3838	116	16	and	and	CCONJ
cana-3838	116	17	categorization	categorization	NOUN
cana-3838	116	18	of	of	ADP
cana-3838	116	19	brain	brain	NOUN
cana-3838	116	20	cancers	cancer	NOUN
cana-3838	116	21	from	from	ADP
cana-3838	116	22	mri	mri	NOUN
cana-3838	116	23	images	image	NOUN
cana-3838	116	24	.	.	PUNCT
cana-3838	117	1	the	the	DET
cana-3838	117	2	faster	fast	ADJ
cana-3838	117	3	r	r	NOUN
cana-3838	117	4	-	-	PUNCT
cana-3838	117	5	cnn	cnn	PROPN
cana-3838	117	6	approach	approach	NOUN
cana-3838	117	7	was	be	AUX
cana-3838	117	8	used	use	VERB
cana-3838	117	9	to	to	PART
cana-3838	117	10	detect	detect	VERB
cana-3838	117	11	tumor	tumor	NOUN
cana-3838	117	12	areas	area	NOUN
cana-3838	117	13	and	and	CCONJ
cana-3838	117	14	classify	classify	VERB
cana-3838	117	15	them	they	PRON
cana-3838	117	16	as	as	ADP
cana-3838	117	17	glioma	glioma	NOUN
cana-3838	117	18	,	,	PUNCT
cana-3838	117	19	meningioma	meningioma	NOUN
cana-3838	117	20	,	,	PUNCT
cana-3838	117	21	or	or	CCONJ
cana-3838	117	22	pituitary	pituitary	ADJ
cana-3838	117	23	tumor	tumor	NOUN
cana-3838	117	24	.	.	PUNCT
cana-3838	118	1	the	the	DET
cana-3838	118	2	faster	fast	ADJ
cana-3838	118	3	r	r	NOUN
cana-3838	118	4	-	-	PUNCT
cana-3838	118	5	cnn	cnn	PROPN
cana-3838	118	6	approach	approach	NOUN
cana-3838	118	7	was	be	AUX
cana-3838	118	8	built	build	VERB
cana-3838	118	9	on	on	ADP
cana-3838	118	10	top	top	NOUN
cana-3838	118	11	of	of	ADP
cana-3838	118	12	a	a	DET
cana-3838	118	13	vgg-16	vgg-16	NOUN
cana-3838	118	14	deep	deep	ADJ
cana-3838	118	15	convolutional	convolutional	ADJ
cana-3838	118	16	network	network	NOUN
cana-3838	118	17	.	.	PUNCT
cana-3838	119	1	the	the	DET
cana-3838	119	2	proposed	propose	VERB
cana-3838	119	3	approach	approach	NOUN
cana-3838	119	4	employs	employ	VERB
cana-3838	119	5	rpn	rpn	NOUN
cana-3838	119	6	to	to	PART
cana-3838	119	7	ascertain	ascertain	VERB
cana-3838	119	8	the	the	DET
cana-3838	119	9	optimal	optimal	ADJ
cana-3838	119	10	bounding	bounding	NOUN
cana-3838	119	11	box	box	NOUN
cana-3838	119	12	for	for	ADP
cana-3838	119	13	the	the	DET
cana-3838	119	14	successful	successful	ADJ
cana-3838	119	15	localization	localization	NOUN
cana-3838	119	16	of	of	ADP
cana-3838	119	17	brain	brain	NOUN
cana-3838	119	18	tumors	tumor	NOUN
cana-3838	119	19	.	.	PUNCT
cana-3838	120	1	we	we	PRON
cana-3838	120	2	enhanced	enhance	VERB
cana-3838	120	3	the	the	DET
cana-3838	120	4	map	map	NOUN
cana-3838	120	5	for	for	ADP
cana-3838	120	6	detecting	detect	VERB
cana-3838	120	7	brain	brain	NOUN
cana-3838	120	8	tumors	tumor	NOUN
cana-3838	120	9	using	use	VERB
cana-3838	120	10	the	the	DET
cana-3838	120	11	test	test	NOUN
cana-3838	120	12	dataset	dataset	NOUN
cana-3838	120	13	.	.	PUNCT
cana-3838	121	1	they	they	PRON
cana-3838	121	2	should	should	AUX
cana-3838	121	3	broaden	broaden	VERB
cana-3838	121	4	their	their	PRON
cana-3838	121	5	research	research	NOUN
cana-3838	121	6	to	to	PART
cana-3838	121	7	find	find	VERB
cana-3838	121	8	the	the	DET
cana-3838	121	9	tumor	tumor	NOUN
cana-3838	121	10	's	's	PART
cana-3838	121	11	percentage	percentage	NOUN
cana-3838	121	12	area	area	NOUN
cana-3838	121	13	in	in	ADP
cana-3838	121	14	relation	relation	NOUN
cana-3838	121	15	to	to	ADP
cana-3838	121	16	the	the	DET
cana-3838	121	17	brain	brain	NOUN
cana-3838	121	18	area	area	NOUN
cana-3838	121	19	as	as	ADV
cana-3838	121	20	well	well	ADV
cana-3838	121	21	.	.	PUNCT
cana-3838	122	1	their	their	PRON
cana-3838	122	2	approach	approach	NOUN
cana-3838	122	3	may	may	AUX
cana-3838	122	4	also	also	ADV
cana-3838	122	5	be	be	AUX
cana-3838	122	6	useful	useful	ADJ
cana-3838	122	7	for	for	ADP
cana-3838	122	8	the	the	DET
cana-3838	122	9	categorization	categorization	NOUN
cana-3838	122	10	and	and	CCONJ
cana-3838	122	11	segmentation	segmentation	NOUN
cana-3838	122	12	of	of	ADP
cana-3838	122	13	skin	skin	NOUN
cana-3838	122	14	lesions	lesion	NOUN
cana-3838	122	15	,	,	PUNCT
cana-3838	122	16	two	two	NUM
cana-3838	122	17	additional	additional	ADJ
cana-3838	122	18	medicinal	medicinal	ADJ
cana-3838	122	19	applications	application	NOUN
cana-3838	122	20	.	.	PUNCT
cana-3838	123	1	fahad	fahad	PROPN
cana-3838	123	2	ahmed	ahmed	PROPN
cana-3838	123	3	et	et	PROPN
cana-3838	123	4	al	al	PROPN
cana-3838	123	5	.	.	PUNCT
cana-3838	124	1	[	[	X
cana-3838	124	2	15	15	NUM
cana-3838	124	3	]	]	PUNCT
cana-3838	124	4	created	create	VERB
cana-3838	124	5	a	a	DET
cana-3838	124	6	vgg16	vgg16	NOUN
cana-3838	124	7	model	model	NOUN
cana-3838	124	8	that	that	PRON
cana-3838	124	9	trained	train	VERB
cana-3838	124	10	with	with	ADP
cana-3838	124	11	a	a	DET
cana-3838	124	12	precision	precision	NOUN
cana-3838	124	13	of	of	ADP
cana-3838	124	14	99.88	99.88	NUM
cana-3838	124	15	%	%	NOUN
cana-3838	124	16	and	and	CCONJ
cana-3838	124	17	a	a	DET
cana-3838	124	18	testing	testing	NOUN
cana-3838	124	19	accuracy	accuracy	NOUN
cana-3838	124	20	of	of	ADP
cana-3838	124	21	97.33	97.33	NUM
cana-3838	124	22	%	%	NOUN
cana-3838	124	23	using	use	VERB
cana-3838	124	24	a	a	DET
cana-3838	124	25	dataset	dataset	NOUN
cana-3838	124	26	of	of	ADP
cana-3838	124	27	brain	brain	NOUN
cana-3838	124	28	pictures	picture	NOUN
cana-3838	124	29	that	that	PRON
cana-3838	124	30	included	include	VERB
cana-3838	124	31	both	both	CCONJ
cana-3838	124	32	normal	normal	ADJ
cana-3838	124	33	and	and	CCONJ
cana-3838	124	34	tumor	tumor	NOUN
cana-3838	124	35	images	image	NOUN
cana-3838	124	36	.	.	PUNCT
cana-3838	125	1	the	the	DET
cana-3838	125	2	model	model	NOUN
cana-3838	125	3	successfully	successfully	ADV
cana-3838	125	4	identified	identify	VERB
cana-3838	125	5	and	and	CCONJ
cana-3838	125	6	predicted	predict	VERB
cana-3838	125	7	brain	brain	NOUN
cana-3838	125	8	images	image	NOUN
cana-3838	125	9	.	.	PUNCT
cana-3838	126	1	applying	apply	VERB
cana-3838	126	2	layer	layer	NOUN
cana-3838	126	3	wise	wise	ADJ
cana-3838	126	4	relevance	relevance	NOUN
cana-3838	126	5	propagation	propagation	NOUN
cana-3838	126	6	(	(	PUNCT
cana-3838	126	7	lrp	lrp	PROPN
cana-3838	126	8	)	)	PUNCT
cana-3838	126	9	helped	help	VERB
cana-3838	126	10	shed	shed	VERB
cana-3838	126	11	light	light	NOUN
cana-3838	126	12	on	on	ADP
cana-3838	126	13	how	how	SCONJ
cana-3838	126	14	the	the	DET
cana-3838	126	15	model	model	NOUN
cana-3838	126	16	arrived	arrive	VERB
cana-3838	126	17	at	at	ADP
cana-3838	126	18	its	its	PRON
cana-3838	126	19	decisions	decision	NOUN
cana-3838	126	20	.	.	PUNCT
cana-3838	127	1	the	the	DET
cana-3838	127	2	combination	combination	NOUN
cana-3838	127	3	of	of	ADP
cana-3838	127	4	the	the	DET
cana-3838	127	5	vgg16	vgg16	NOUN
cana-3838	127	6	model	model	NOUN
cana-3838	127	7	with	with	ADP
cana-3838	127	8	lrp	lrp	PROPN
cana-3838	127	9	offers	offer	VERB
cana-3838	127	10	a	a	DET
cana-3838	127	11	promising	promising	ADJ
cana-3838	127	12	strategy	strategy	NOUN
cana-3838	127	13	for	for	ADP
cana-3838	127	14	the	the	DET
cana-3838	127	15	identification	identification	NOUN
cana-3838	127	16	and	and	CCONJ
cana-3838	127	17	understanding	understanding	NOUN
cana-3838	127	18	of	of	ADP
cana-3838	127	19	brain	brain	NOUN
cana-3838	127	20	tumors	tumor	NOUN
cana-3838	127	21	.	.	PUNCT
cana-3838	128	1	using	use	VERB
cana-3838	128	2	multi	multi	ADJ
cana-3838	128	3	-	-	ADJ
cana-3838	128	4	modal	modal	ADJ
cana-3838	128	5	images	image	NOUN
cana-3838	128	6	,	,	PUNCT
cana-3838	128	7	sajid	sajid	PROPN
cana-3838	128	8	iqbal	iqbal	PROPN
cana-3838	128	9	et	et	PROPN
cana-3838	128	10	al	al	PROPN
cana-3838	128	11	.	.	PUNCT
cana-3838	129	1	[	[	X
cana-3838	129	2	16	16	NUM
cana-3838	129	3	]	]	PUNCT
cana-3838	129	4	demonstrated	demonstrate	VERB
cana-3838	129	5	a	a	DET
cana-3838	129	6	similar	similar	ADJ
cana-3838	129	7	network	network	NOUN
cana-3838	129	8	design	design	NOUN
cana-3838	129	9	for	for	ADP
cana-3838	129	10	segmenting	segment	VERB
cana-3838	129	11	brain	brain	NOUN
cana-3838	129	12	tumors	tumor	NOUN
cana-3838	129	13	.	.	PUNCT
cana-3838	130	1	there	there	PRON
cana-3838	130	2	were	be	VERB
cana-3838	130	3	three	three	NUM
cana-3838	130	4	models	model	NOUN
cana-3838	130	5	offered	offer	VERB
cana-3838	130	6	,	,	PUNCT
cana-3838	130	7	each	each	PRON
cana-3838	130	8	with	with	ADP
cana-3838	130	9	an	an	DET
cana-3838	130	10	escalating	escalate	VERB
cana-3838	130	11	performance	performance	NOUN
cana-3838	130	12	level	level	NOUN
cana-3838	130	13	.	.	PUNCT
cana-3838	131	1	the	the	DET
cana-3838	131	2	findings	finding	NOUN
cana-3838	131	3	show	show	VERB
cana-3838	131	4	that	that	SCONJ
cana-3838	131	5	interpolation	interpolation	NOUN
cana-3838	131	6	methods	method	NOUN
cana-3838	131	7	and	and	CCONJ
cana-3838	131	8	intermediate	intermediate	ADJ
cana-3838	131	9	convolutional	convolutional	ADJ
cana-3838	131	10	maps	map	NOUN
cana-3838	131	11	are	be	AUX
cana-3838	131	12	viable	viable	ADJ
cana-3838	131	13	options	option	NOUN
cana-3838	131	14	with	with	ADP
cana-3838	131	15	good	good	ADJ
cana-3838	131	16	potential	potential	NOUN
cana-3838	131	17	.	.	PUNCT
cana-3838	132	1	the	the	DET
cana-3838	132	2	vast	vast	ADJ
cana-3838	132	3	majority	majority	NOUN
cana-3838	132	4	of	of	ADP
cana-3838	132	5	the	the	DET
cana-3838	132	6	networks	network	NOUN
cana-3838	132	7	published	publish	VERB
cana-3838	132	8	so	so	ADV
cana-3838	132	9	far	far	ADV
cana-3838	132	10	are	be	AUX
cana-3838	132	11	deep	deep	ADJ
cana-3838	132	12	networks	network	NOUN
cana-3838	132	13	,	,	PUNCT
cana-3838	132	14	which	which	PRON
cana-3838	132	15	need	need	VERB
cana-3838	132	16	extensive	extensive	ADJ
cana-3838	132	17	training	training	NOUN
cana-3838	132	18	before	before	SCONJ
cana-3838	132	19	they	they	PRON
cana-3838	132	20	can	can	AUX
cana-3838	132	21	converge	converge	VERB
cana-3838	132	22	.	.	PUNCT
cana-3838	133	1	nevertheless	nevertheless	ADV
cana-3838	133	2	,	,	PUNCT
cana-3838	133	3	the	the	DET
cana-3838	133	4	suggested	suggest	VERB
cana-3838	133	5	network	network	NOUN
cana-3838	133	6	architecture	architecture	NOUN
cana-3838	133	7	is	be	AUX
cana-3838	133	8	compact	compact	ADJ
cana-3838	133	9	,	,	PUNCT
cana-3838	133	10	quick	quick	ADJ
cana-3838	133	11	,	,	PUNCT
cana-3838	133	12	and	and	CCONJ
cana-3838	133	13	requires	require	VERB
cana-3838	133	14	less	less	ADJ
cana-3838	133	15	memory	memory	NOUN
cana-3838	133	16	.	.	PUNCT
cana-3838	134	1	their	their	PRON
cana-3838	134	2	plans	plan	NOUN
cana-3838	134	3	for	for	ADP
cana-3838	134	4	the	the	DET
cana-3838	134	5	future	future	NOUN
cana-3838	134	6	include	include	VERB
cana-3838	134	7	investigating	investigate	VERB
cana-3838	134	8	se	se	PROPN
cana-3838	134	9	blocks	block	NOUN
cana-3838	134	10	'	'	PART
cana-3838	134	11	potential	potential	ADJ
cana-3838	134	12	application	application	NOUN
cana-3838	134	13	at	at	ADP
cana-3838	134	14	various	various	ADJ
cana-3838	134	15	levels	level	NOUN
cana-3838	134	16	.	.	PUNCT
cana-3838	135	1	investigations	investigation	NOUN
cana-3838	135	2	into	into	ADP
cana-3838	135	3	the	the	DET
cana-3838	135	4	relative	relative	ADJ
cana-3838	135	5	merits	merit	NOUN
cana-3838	135	6	of	of	ADP
cana-3838	135	7	different	different	ADJ
cana-3838	135	8	weighting	weighting	NOUN
cana-3838	135	9	strategies	strategy	NOUN
cana-3838	135	10	and	and	CCONJ
cana-3838	135	11	the	the	DET
cana-3838	135	12	potential	potential	ADJ
cana-3838	135	13	benefits	benefit	NOUN
cana-3838	135	14	of	of	ADP
cana-3838	135	15	various	various	ADJ
cana-3838	135	16	combinations	combination	NOUN
cana-3838	135	17	thereof	thereof	ADV
cana-3838	135	18	are	be	AUX
cana-3838	135	19	equally	equally	ADV
cana-3838	135	20	intriguing	intriguing	ADJ
cana-3838	135	21	.	.	PUNCT
cana-3838	136	1	an	an	DET
cana-3838	136	2	mri	mri	NOUN
cana-3838	136	3	model	model	NOUN
cana-3838	136	4	for	for	ADP
cana-3838	136	5	brain	brain	NOUN
cana-3838	136	6	cancers	cancer	NOUN
cana-3838	136	7	was	be	AUX
cana-3838	136	8	proposed	propose	VERB
cana-3838	136	9	by	by	ADP
cana-3838	136	10	abdullah	abdullah	PROPN
cana-3838	136	11	a.	a.	PROPN
cana-3838	136	12	asiri	asiri	PROPN
cana-3838	136	13	et	et	PROPN
cana-3838	136	14	al	al	PROPN
cana-3838	136	15	.	.	PUNCT
cana-3838	137	1	[	[	X
cana-3838	137	2	17	17	NUM
cana-3838	137	3	]	]	PUNCT
cana-3838	137	4	using	use	VERB
cana-3838	137	5	a	a	DET
cana-3838	137	6	convolutional	convolutional	ADJ
cana-3838	137	7	neural	neural	ADJ
cana-3838	137	8	network	network	NOUN
cana-3838	137	9	(	(	PUNCT
cana-3838	137	10	cnn	cnn	PROPN
cana-3838	137	11	)	)	PUNCT
cana-3838	137	12	that	that	PRON
cana-3838	137	13	incorporates	incorporate	VERB
cana-3838	137	14	fine	fine	ADV
cana-3838	137	15	-	-	PUNCT
cana-3838	137	16	tuned	tune	VERB
cana-3838	137	17	resnet50	resnet50	NOUN
cana-3838	137	18	and	and	CCONJ
cana-3838	137	19	u	u	NOUN
cana-3838	137	20	-	-	NOUN
cana-3838	137	21	net	net	NOUN
cana-3838	137	22	.	.	PUNCT
cana-3838	138	1	their	their	PRON
cana-3838	138	2	approach	approach	NOUN
cana-3838	138	3	is	be	AUX
cana-3838	138	4	superior	superior	ADJ
cana-3838	138	5	in	in	ADP
cana-3838	138	6	both	both	DET
cana-3838	138	7	tasks	task	NOUN
cana-3838	138	8	because	because	SCONJ
cana-3838	138	9	it	it	PRON
cana-3838	138	10	combines	combine	VERB
cana-3838	138	11	the	the	DET
cana-3838	138	12	greatest	great	ADJ
cana-3838	138	13	aspects	aspect	NOUN
cana-3838	138	14	of	of	ADP
cana-3838	138	15	two	two	NUM
cana-3838	138	16	different	different	ADJ
cana-3838	138	17	designs	design	NOUN
cana-3838	138	18	.	.	PUNCT
cana-3838	139	1	the	the	DET
cana-3838	139	2	fine	fine	ADV
cana-3838	139	3	-	-	PUNCT
cana-3838	139	4	tuned	tune	VERB
cana-3838	139	5	resnet50	resnet50	NOUN
cana-3838	139	6	configuration	configuration	NOUN
cana-3838	139	7	is	be	AUX
cana-3838	139	8	used	use	VERB
cana-3838	139	9	for	for	ADP
cana-3838	139	10	brain	brain	NOUN
cana-3838	139	11	tumor	tumor	NOUN
cana-3838	139	12	detection	detection	NOUN
cana-3838	139	13	,	,	PUNCT
cana-3838	139	14	which	which	PRON
cana-3838	139	15	comprises	comprise	VERB
cana-3838	139	16	detecting	detect	VERB
cana-3838	139	17	tumors	tumor	NOUN
cana-3838	139	18	in	in	ADP
cana-3838	139	19	mris	mris	PROPN
cana-3838	139	20	.	.	PUNCT
cana-3838	140	1	the	the	DET
cana-3838	140	2	u	u	ADJ
cana-3838	140	3	-	-	ADJ
cana-3838	140	4	net	net	ADJ
cana-3838	140	5	design	design	NOUN
cana-3838	140	6	may	may	AUX
cana-3838	140	7	be	be	AUX
cana-3838	140	8	used	use	VERB
cana-3838	140	9	to	to	ADP
cana-3838	140	10	the	the	DET
cana-3838	140	11	task	task	NOUN
cana-3838	140	12	of	of	ADP
cana-3838	140	13	brain	brain	NOUN
cana-3838	140	14	tumor	tumor	NOUN
cana-3838	140	15	segmentation	segmentation	NOUN
cana-3838	140	16	,	,	PUNCT
cana-3838	140	17	which	which	PRON
cana-3838	140	18	comprises	comprise	VERB
cana-3838	140	19	the	the	DET
cana-3838	140	20	exact	exact	ADJ
cana-3838	140	21	separation	separation	NOUN
cana-3838	140	22	of	of	ADP
cana-3838	140	23	the	the	DET
cana-3838	140	24	tumor	tumor	NOUN
cana-3838	140	25	from	from	ADP
cana-3838	140	26	the	the	DET
cana-3838	140	27	surrounding	surround	VERB
cana-3838	140	28	healthy	healthy	ADJ
cana-3838	140	29	communications	communication	NOUN
cana-3838	140	30	on	on	ADP
cana-3838	140	31	applied	apply	VERB
cana-3838	140	32	nonlinear	nonlinear	ADJ
cana-3838	140	33	analysis	analysis	NOUN
cana-3838	140	34	issn	issn	NOUN
cana-3838	140	35	:	:	PUNCT
cana-3838	140	36	1074	1074	NUM
cana-3838	140	37	-	-	PUNCT
cana-3838	140	38	133x	133x	NUM
cana-3838	140	39	vol	vol	NOUN
cana-3838	140	40	32	32	NUM
cana-3838	140	41	no	no	NOUN
cana-3838	140	42	.	.	PUNCT
cana-3838	141	1	9s	9s	NUM
cana-3838	141	2	(	(	PUNCT
cana-3838	141	3	2025	2025	NUM
cana-3838	141	4	)	)	PUNCT
cana-3838	141	5	68	68	NUM
cana-3838	141	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-3838	141	7	tissue	tissue	NOUN
cana-3838	141	8	.	.	PUNCT
cana-3838	142	1	the	the	DET
cana-3838	142	2	study	study	NOUN
cana-3838	142	3	compared	compare	VERB
cana-3838	142	4	cnn	cnn	PROPN
cana-3838	142	5	with	with	ADP
cana-3838	142	6	fine	fine	ADV
cana-3838	142	7	-	-	PUNCT
cana-3838	142	8	tuned	tune	VERB
cana-3838	142	9	resnet50	resnet50	NOUN
cana-3838	142	10	,	,	PUNCT
cana-3838	142	11	two	two	NUM
cana-3838	142	12	models	model	NOUN
cana-3838	142	13	developed	develop	VERB
cana-3838	142	14	for	for	ADP
cana-3838	142	15	use	use	NOUN
cana-3838	142	16	in	in	ADP
cana-3838	142	17	mri	mri	NOUN
cana-3838	142	18	image	image	NOUN
cana-3838	142	19	classification	classification	NOUN
cana-3838	142	20	and	and	CCONJ
cana-3838	142	21	tumor	tumor	NOUN
cana-3838	142	22	detection	detection	NOUN
cana-3838	142	23	.	.	PUNCT
cana-3838	143	1	statistically	statistically	ADV
cana-3838	143	2	speaking	speak	VERB
cana-3838	143	3	,	,	PUNCT
cana-3838	143	4	for	for	ADP
cana-3838	143	5	both	both	CCONJ
cana-3838	143	6	the	the	DET
cana-3838	143	7	non	non	ADJ
cana-3838	143	8	-	-	ADJ
cana-3838	143	9	tumor	tumor	ADJ
cana-3838	143	10	and	and	CCONJ
cana-3838	143	11	tumor	tumor	NOUN
cana-3838	143	12	classifications	classification	NOUN
cana-3838	143	13	,	,	PUNCT
cana-3838	143	14	the	the	DET
cana-3838	143	15	cnn	cnn	PROPN
cana-3838	143	16	model	model	NOUN
cana-3838	143	17	outperforms	outperform	VERB
cana-3838	143	18	the	the	DET
cana-3838	143	19	fine	fine	ADV
cana-3838	143	20	-	-	PUNCT
cana-3838	143	21	tuned	tune	VERB
cana-3838	143	22	resnet50	resnet50	NOUN
cana-3838	143	23	model	model	NOUN
cana-3838	143	24	.	.	PUNCT
cana-3838	144	1	the	the	DET
cana-3838	144	2	refined	refined	PROPN
cana-3838	144	3	resnet50	resnet50	NOUN
cana-3838	144	4	model	model	NOUN
cana-3838	144	5	obtained	obtain	VERB
cana-3838	144	6	an	an	DET
cana-3838	144	7	accuracy	accuracy	NOUN
cana-3838	144	8	rate	rate	NOUN
cana-3838	144	9	of	of	ADP
cana-3838	144	10	0.94	0.94	NUM
cana-3838	144	11	,	,	PUNCT
cana-3838	144	12	a	a	DET
cana-3838	144	13	recall	recall	NOUN
cana-3838	144	14	of	of	ADP
cana-3838	144	15	0.95	0.95	NUM
cana-3838	144	16	,	,	PUNCT
cana-3838	144	17	an	an	DET
cana-3838	144	18	f1	f1	ADJ
cana-3838	144	19	score	score	NOUN
cana-3838	144	20	of	of	ADP
cana-3838	144	21	0.93	0.93	NUM
cana-3838	144	22	,	,	PUNCT
cana-3838	144	23	and	and	CCONJ
cana-3838	144	24	a	a	DET
cana-3838	144	25	precision	precision	NOUN
cana-3838	144	26	of	of	ADP
cana-3838	144	27	0.98	0.98	NUM
cana-3838	144	28	in	in	ADP
cana-3838	144	29	the	the	DET
cana-3838	144	30	non	non	ADJ
cana-3838	144	31	-	-	ADJ
cana-3838	144	32	tumor	tumor	ADJ
cana-3838	144	33	class	class	NOUN
cana-3838	144	34	.	.	PUNCT
cana-3838	145	1	the	the	DET
cana-3838	145	2	model	model	NOUN
cana-3838	145	3	's	's	PART
cana-3838	145	4	preciseness	preciseness	NOUN
cana-3838	145	5	was	be	AUX
cana-3838	145	6	0.87	0.87	NUM
cana-3838	145	7	,	,	PUNCT
cana-3838	145	8	recall	recall	NOUN
cana-3838	145	9	was	be	AUX
cana-3838	145	10	0.92	0.92	NUM
cana-3838	145	11	,	,	PUNCT
cana-3838	145	12	f1	f1	ADJ
cana-3838	145	13	score	score	NOUN
cana-3838	145	14	was	be	AUX
cana-3838	145	15	0.88	0.88	NUM
cana-3838	145	16	,	,	PUNCT
cana-3838	145	17	and	and	CCONJ
cana-3838	145	18	accuracy	accuracy	NOUN
cana-3838	145	19	was	be	AUX
cana-3838	145	20	0.96	0.96	NUM
cana-3838	145	21	in	in	ADP
cana-3838	145	22	the	the	DET
cana-3838	145	23	tumor	tumor	NOUN
cana-3838	145	24	class	class	NOUN
cana-3838	145	25	.	.	PUNCT
cana-3838	146	1	two	two	NUM
cana-3838	146	2	pipelines	pipeline	NOUN
cana-3838	146	3	were	be	AUX
cana-3838	146	4	developed	develop	VERB
cana-3838	146	5	by	by	ADP
cana-3838	146	6	mostefa	mostefa	PROPN
cana-3838	146	7	ben	ben	PROPN
cana-3838	146	8	naceur	naceur	PROPN
cana-3838	146	9	et	et	PROPN
cana-3838	146	10	al	al	PROPN
cana-3838	146	11	.	.	PUNCT
cana-3838	147	1	[	[	X
cana-3838	147	2	18	18	NUM
cana-3838	147	3	]	]	PUNCT
cana-3838	147	4	to	to	PART
cana-3838	147	5	segment	segment	NOUN
cana-3838	147	6	gbm	gbm	PROPN
cana-3838	147	7	brain	brain	NOUN
cana-3838	147	8	tumors	tumor	NOUN
cana-3838	147	9	using	use	VERB
cana-3838	147	10	learnt	learn	VERB
cana-3838	147	11	feature	feature	NOUN
cana-3838	147	12	maps	map	NOUN
cana-3838	147	13	and	and	CCONJ
cana-3838	147	14	deep	deep	ADJ
cana-3838	147	15	convolutional	convolutional	ADJ
cana-3838	147	16	neural	neural	ADJ
cana-3838	147	17	networks	network	NOUN
cana-3838	147	18	(	(	PUNCT
cana-3838	147	19	dcnns	dcnns	ADJ
cana-3838	147	20	)	)	PUNCT
cana-3838	147	21	.	.	PUNCT
cana-3838	148	1	to	to	PART
cana-3838	148	2	optimize	optimize	VERB
cana-3838	148	3	the	the	DET
cana-3838	148	4	model	model	NOUN
cana-3838	148	5	's	's	PART
cana-3838	148	6	feature	feature	NOUN
cana-3838	148	7	representation	representation	NOUN
cana-3838	148	8	,	,	PUNCT
cana-3838	148	9	the	the	DET
cana-3838	148	10	first	first	ADJ
cana-3838	148	11	pipeline	pipeline	NOUN
cana-3838	148	12	employs	employ	VERB
cana-3838	148	13	up	up	ADV
cana-3838	148	14	-	-	PUNCT
cana-3838	148	15	sampling	sample	VERB
cana-3838	148	16	filters	filter	NOUN
cana-3838	148	17	and	and	CCONJ
cana-3838	148	18	skip	skip	ADJ
cana-3838	148	19	connections	connection	NOUN
cana-3838	148	20	.	.	PUNCT
cana-3838	149	1	the	the	DET
cana-3838	149	2	second	second	ADJ
cana-3838	149	3	pipeline	pipeline	NOUN
cana-3838	149	4	improves	improve	VERB
cana-3838	149	5	tumor	tumor	NOUN
cana-3838	149	6	area	area	NOUN
cana-3838	149	7	localization	localization	NOUN
cana-3838	149	8	by	by	ADP
cana-3838	149	9	combining	combine	VERB
cana-3838	149	10	low	low	ADJ
cana-3838	149	11	-	-	PUNCT
cana-3838	149	12	level	level	NOUN
cana-3838	149	13	and	and	CCONJ
cana-3838	149	14	high	high	ADJ
cana-3838	149	15	-	-	PUNCT
cana-3838	149	16	level	level	NOUN
cana-3838	149	17	features	feature	NOUN
cana-3838	149	18	via	via	ADP
cana-3838	149	19	lengthy	lengthy	ADJ
cana-3838	149	20	skip	skip	ADJ
cana-3838	149	21	links	link	NOUN
cana-3838	149	22	that	that	PRON
cana-3838	149	23	promote	promote	VERB
cana-3838	149	24	feature	feature	NOUN
cana-3838	149	25	reuse	reuse	NOUN
cana-3838	149	26	.	.	PUNCT
cana-3838	150	1	the	the	DET
cana-3838	150	2	scientists	scientist	NOUN
cana-3838	150	3	trained	train	VERB
cana-3838	150	4	two	two	NUM
cana-3838	150	5	more	more	ADJ
cana-3838	150	6	machine	machine	NOUN
cana-3838	150	7	learning	learn	VERB
cana-3838	150	8	algorithms	algorithm	NOUN
cana-3838	150	9	—	—	PUNCT
cana-3838	150	10	logistic	logistic	ADJ
cana-3838	150	11	regression	regression	NOUN
cana-3838	150	12	and	and	CCONJ
cana-3838	150	13	random	random	ADJ
cana-3838	150	14	forest	forest	NOUN
cana-3838	150	15	—	—	PUNCT
cana-3838	150	16	and	and	CCONJ
cana-3838	150	17	extracted	extract	VERB
cana-3838	150	18	the	the	DET
cana-3838	150	19	feature	feature	NOUN
cana-3838	150	20	maps	map	NOUN
cana-3838	150	21	to	to	PART
cana-3838	150	22	solve	solve	VERB
cana-3838	150	23	the	the	DET
cana-3838	150	24	issue	issue	NOUN
cana-3838	150	25	of	of	ADP
cana-3838	150	26	false	false	ADJ
cana-3838	150	27	positive	positive	ADJ
cana-3838	150	28	and	and	CCONJ
cana-3838	150	29	false	false	ADJ
cana-3838	150	30	negative	negative	ADJ
cana-3838	150	31	areas	area	NOUN
cana-3838	150	32	.	.	PUNCT
cana-3838	151	1	a	a	DET
cana-3838	151	2	technique	technique	NOUN
cana-3838	151	3	for	for	ADP
cana-3838	151	4	classifying	classify	VERB
cana-3838	151	5	data	datum	NOUN
cana-3838	151	6	and	and	CCONJ
cana-3838	151	7	detecting	detect	VERB
cana-3838	151	8	tumor	tumor	NOUN
cana-3838	151	9	locations	location	NOUN
cana-3838	151	10	using	use	VERB
cana-3838	151	11	deep	deep	ADJ
cana-3838	151	12	residual	residual	ADJ
cana-3838	151	13	networks	network	NOUN
cana-3838	151	14	(	(	PUNCT
cana-3838	151	15	resnet	resnet	NOUN
cana-3838	151	16	)	)	PUNCT
cana-3838	151	17	was	be	AUX
cana-3838	151	18	suggested	suggest	VERB
cana-3838	151	19	in	in	ADP
cana-3838	151	20	a	a	DET
cana-3838	151	21	publication	publication	NOUN
cana-3838	151	22	by	by	ADP
cana-3838	151	23	madona	madona	PROPN
cana-3838	151	24	b.	b.	PROPN
cana-3838	151	25	sahaai	sahaai	PROPN
cana-3838	151	26	et	et	PROPN
cana-3838	151	27	al	al	PROPN
cana-3838	151	28	.	.	PUNCT
cana-3838	152	1	[	[	X
cana-3838	152	2	19	19	NUM
cana-3838	152	3	]	]	PUNCT
cana-3838	152	4	.	.	PUNCT
cana-3838	153	1	in	in	ADP
cana-3838	153	2	the	the	DET
cana-3838	153	3	field	field	NOUN
cana-3838	153	4	of	of	ADP
cana-3838	153	5	restorative	restorative	ADJ
cana-3838	153	6	dentistry	dentistry	NOUN
cana-3838	153	7	,	,	PUNCT
cana-3838	153	8	their	their	PRON
cana-3838	153	9	model	model	NOUN
cana-3838	153	10	is	be	AUX
cana-3838	153	11	useful	useful	ADJ
cana-3838	153	12	for	for	ADP
cana-3838	153	13	more	more	ADV
cana-3838	153	14	accurate	accurate	ADJ
cana-3838	153	15	,	,	PUNCT
cana-3838	153	16	detailed	detailed	ADJ
cana-3838	153	17	,	,	PUNCT
cana-3838	153	18	precise	precise	ADJ
cana-3838	153	19	,	,	PUNCT
cana-3838	153	20	and	and	CCONJ
cana-3838	153	21	analytical	analytical	ADJ
cana-3838	153	22	prediction	prediction	NOUN
cana-3838	153	23	of	of	ADP
cana-3838	153	24	a	a	DET
cana-3838	153	25	patient	patient	NOUN
cana-3838	153	26	's	's	PART
cana-3838	153	27	brian	brian	PROPN
cana-3838	153	28	tumor	tumor	NOUN
cana-3838	153	29	.	.	PUNCT
cana-3838	154	1	across	across	ADP
cana-3838	154	2	several	several	ADJ
cana-3838	154	3	types	type	NOUN
cana-3838	154	4	of	of	ADP
cana-3838	154	5	brain	brain	NOUN
cana-3838	154	6	tumor	tumor	NOUN
cana-3838	154	7	datasets	dataset	NOUN
cana-3838	154	8	,	,	PUNCT
cana-3838	154	9	their	their	PRON
cana-3838	154	10	model	model	NOUN
cana-3838	154	11	achieves	achieve	VERB
cana-3838	154	12	a	a	DET
cana-3838	154	13	validation	validation	NOUN
cana-3838	154	14	accuracy	accuracy	NOUN
cana-3838	154	15	of	of	ADP
cana-3838	154	16	95.3	95.3	NUM
cana-3838	154	17	%	%	NOUN
cana-3838	154	18	.	.	PUNCT
cana-3838	155	1	in	in	ADP
cana-3838	155	2	their	their	PRON
cana-3838	155	3	study	study	NOUN
cana-3838	155	4	,	,	PUNCT
cana-3838	155	5	they	they	PRON
cana-3838	155	6	compared	compare	VERB
cana-3838	155	7	the	the	DET
cana-3838	155	8	results	result	NOUN
cana-3838	155	9	of	of	ADP
cana-3838	155	10	multi	multi	ADJ
cana-3838	155	11	class	class	NOUN
cana-3838	155	12	brain	brain	NOUN
cana-3838	155	13	tumor	tumor	NOUN
cana-3838	155	14	classification	classification	NOUN
cana-3838	155	15	using	use	VERB
cana-3838	155	16	transfer	transfer	NOUN
cana-3838	155	17	learning	learning	NOUN
cana-3838	155	18	with	with	ADP
cana-3838	155	19	a	a	DET
cana-3838	155	20	pre	pre	ADJ
cana-3838	155	21	-	-	ADJ
cana-3838	155	22	trained	train	VERB
cana-3838	155	23	resnet50	resnet50	NOUN
cana-3838	155	24	model	model	NOUN
cana-3838	155	25	that	that	PRON
cana-3838	155	26	used	use	VERB
cana-3838	155	27	cnn	cnn	PROPN
cana-3838	155	28	architecture	architecture	NOUN
cana-3838	155	29	.	.	PUNCT
cana-3838	156	1	in	in	ADP
cana-3838	156	2	the	the	DET
cana-3838	156	3	absence	absence	NOUN
cana-3838	156	4	of	of	ADP
cana-3838	156	5	the	the	DET
cana-3838	156	6	pre	pre	ADJ
cana-3838	156	7	-	-	ADJ
cana-3838	156	8	trained	train	VERB
cana-3838	156	9	pytorch	pytorch	NOUN
cana-3838	156	10	model	model	NOUN
cana-3838	156	11	,	,	PUNCT
cana-3838	156	12	the	the	DET
cana-3838	156	13	training	training	NOUN
cana-3838	156	14	accuracy	accuracy	NOUN
cana-3838	156	15	stands	stand	VERB
cana-3838	156	16	at	at	ADP
cana-3838	156	17	93.5	93.5	NUM
cana-3838	156	18	%	%	NOUN
cana-3838	156	19	and	and	CCONJ
cana-3838	156	20	the	the	DET
cana-3838	156	21	validation	validation	NOUN
cana-3838	156	22	accuracy	accuracy	NOUN
cana-3838	156	23	at	at	ADP
cana-3838	156	24	90	90	NUM
cana-3838	156	25	%	%	NOUN
cana-3838	156	26	.	.	PUNCT
cana-3838	157	1	mostefa	mostefa	PROPN
cana-3838	157	2	ben	ben	PROPN
cana-3838	157	3	naceur	naceur	PROPN
cana-3838	157	4	et	et	PROPN
cana-3838	157	5	al	al	PROPN
cana-3838	157	6	.	.	PUNCT
cana-3838	158	1	[	[	X
cana-3838	158	2	18	18	NUM
cana-3838	158	3	]	]	PUNCT
cana-3838	158	4	used	use	VERB
cana-3838	158	5	trained	train	VERB
cana-3838	158	6	feature	feature	NOUN
cana-3838	158	7	maps	map	NOUN
cana-3838	158	8	and	and	CCONJ
cana-3838	158	9	deep	deep	ADJ
cana-3838	158	10	convolutional	convolutional	ADJ
cana-3838	158	11	neural	neural	ADJ
cana-3838	158	12	networks	network	NOUN
cana-3838	158	13	(	(	PUNCT
cana-3838	158	14	dcnns	dcnns	ADJ
cana-3838	158	15	)	)	PUNCT
cana-3838	158	16	to	to	PART
cana-3838	158	17	build	build	VERB
cana-3838	158	18	two	two	NUM
cana-3838	158	19	pipelines	pipeline	NOUN
cana-3838	158	20	for	for	ADP
cana-3838	158	21	gbm	gbm	PROPN
cana-3838	158	22	brain	brain	PROPN
cana-3838	158	23	tumor	tumor	PROPN
cana-3838	158	24	segmentation	segmentation	NOUN
cana-3838	158	25	.	.	PUNCT
cana-3838	159	1	to	to	PART
cana-3838	159	2	make	make	VERB
cana-3838	159	3	the	the	DET
cana-3838	159	4	most	most	ADJ
cana-3838	159	5	of	of	ADP
cana-3838	159	6	the	the	DET
cana-3838	159	7	features	feature	NOUN
cana-3838	159	8	represented	represent	VERB
cana-3838	159	9	in	in	ADP
cana-3838	159	10	the	the	DET
cana-3838	159	11	model	model	NOUN
cana-3838	159	12	,	,	PUNCT
cana-3838	159	13	the	the	DET
cana-3838	159	14	first	first	ADJ
cana-3838	159	15	pipeline	pipeline	NOUN
cana-3838	159	16	employs	employ	VERB
cana-3838	159	17	up	up	ADV
cana-3838	159	18	-	-	PUNCT
cana-3838	159	19	sampling	sample	VERB
cana-3838	159	20	filters	filter	NOUN
cana-3838	159	21	and	and	CCONJ
cana-3838	159	22	skip	skip	ADJ
cana-3838	159	23	connections	connection	NOUN
cana-3838	159	24	.	.	PUNCT
cana-3838	160	1	to	to	PART
cana-3838	160	2	improve	improve	VERB
cana-3838	160	3	tumor	tumor	NOUN
cana-3838	160	4	area	area	NOUN
cana-3838	160	5	localization	localization	NOUN
cana-3838	160	6	,	,	PUNCT
cana-3838	160	7	the	the	DET
cana-3838	160	8	second	second	ADJ
cana-3838	160	9	pipeline	pipeline	NOUN
cana-3838	160	10	employs	employ	VERB
cana-3838	160	11	lengthy	lengthy	ADJ
cana-3838	160	12	skip	skip	ADJ
cana-3838	160	13	connections	connection	NOUN
cana-3838	160	14	to	to	PART
cana-3838	160	15	promote	promote	VERB
cana-3838	160	16	feature	feature	NOUN
cana-3838	160	17	reuse	reuse	NOUN
cana-3838	160	18	,	,	PUNCT
cana-3838	160	19	which	which	PRON
cana-3838	160	20	aids	aid	VERB
cana-3838	160	21	the	the	DET
cana-3838	160	22	model	model	NOUN
cana-3838	160	23	in	in	ADP
cana-3838	160	24	integrating	integrate	VERB
cana-3838	160	25	lowand	lowand	ADJ
cana-3838	160	26	high	high	ADJ
cana-3838	160	27	level	level	NOUN
cana-3838	160	28	information	information	NOUN
cana-3838	160	29	.	.	PUNCT
cana-3838	161	1	after	after	ADP
cana-3838	161	2	obtaining	obtain	VERB
cana-3838	161	3	the	the	DET
cana-3838	161	4	feature	feature	NOUN
cana-3838	161	5	maps	map	NOUN
cana-3838	161	6	,	,	PUNCT
cana-3838	161	7	the	the	DET
cana-3838	161	8	writers	writer	NOUN
cana-3838	161	9	trained	train	VERB
cana-3838	161	10	two	two	NUM
cana-3838	161	11	further	furth	ADJ
cana-3838	161	12	ml	ml	NOUN
cana-3838	161	13	algorithms	algorithm	NOUN
cana-3838	161	14	—	—	PUNCT
cana-3838	161	15	logistic	logistic	ADJ
cana-3838	161	16	regression	regression	NOUN
cana-3838	161	17	and	and	CCONJ
cana-3838	161	18	random	random	ADJ
cana-3838	161	19	forest	forest	NOUN
cana-3838	161	20	—	—	PUNCT
cana-3838	161	21	to	to	PART
cana-3838	161	22	deal	deal	VERB
cana-3838	161	23	with	with	ADP
cana-3838	161	24	the	the	DET
cana-3838	161	25	issue	issue	NOUN
cana-3838	161	26	of	of	ADP
cana-3838	161	27	false	false	ADJ
cana-3838	161	28	positive	positive	ADJ
cana-3838	161	29	and	and	CCONJ
cana-3838	161	30	false	false	ADJ
cana-3838	161	31	negative	negative	ADJ
cana-3838	161	32	areas	area	NOUN
cana-3838	161	33	.	.	PUNCT
cana-3838	162	1	summary	summary	NOUN
cana-3838	162	2	:	:	PUNCT
cana-3838	162	3	•	•	ADP
cana-3838	162	4	a	a	DET
cana-3838	162	5	brain	brain	NOUN
cana-3838	162	6	tumor	tumor	NOUN
cana-3838	162	7	develops	develop	VERB
cana-3838	162	8	when	when	SCONJ
cana-3838	162	9	an	an	DET
cana-3838	162	10	aberrant	aberrant	ADJ
cana-3838	162	11	cluster	cluster	NOUN
cana-3838	162	12	of	of	ADP
cana-3838	162	13	cells	cell	NOUN
cana-3838	162	14	grows	grow	VERB
cana-3838	162	15	in	in	ADP
cana-3838	162	16	the	the	DET
cana-3838	162	17	human	human	ADJ
cana-3838	162	18	brain	brain	NOUN
cana-3838	162	19	.	.	PUNCT
cana-3838	163	1	brain	brain	NOUN
cana-3838	163	2	and	and	CCONJ
cana-3838	163	3	spinal	spinal	ADJ
cana-3838	163	4	cord	cord	NOUN
cana-3838	163	5	tumors	tumor	NOUN
cana-3838	163	6	are	be	AUX
cana-3838	163	7	known	know	VERB
cana-3838	163	8	as	as	ADP
cana-3838	163	9	gliomas	glioma	NOUN
cana-3838	163	10	,	,	PUNCT
cana-3838	163	11	whereas	whereas	SCONJ
cana-3838	163	12	meningiomas	meningioma	NOUN
cana-3838	163	13	are	be	AUX
cana-3838	163	14	tumors	tumor	NOUN
cana-3838	163	15	that	that	PRON
cana-3838	163	16	form	form	VERB
cana-3838	163	17	in	in	ADP
cana-3838	163	18	the	the	DET
cana-3838	163	19	meninges	meninge	NOUN
cana-3838	163	20	.	.	PUNCT
cana-3838	164	1	when	when	SCONJ
cana-3838	164	2	cells	cell	NOUN
cana-3838	164	3	inside	inside	ADP
cana-3838	164	4	the	the	DET
cana-3838	164	5	pituitary	pituitary	ADJ
cana-3838	164	6	gland	gland	NOUN
cana-3838	164	7	multiply	multiply	NOUN
cana-3838	164	8	abnormally	abnormally	ADV
cana-3838	164	9	,	,	PUNCT
cana-3838	164	10	a	a	DET
cana-3838	164	11	tumor	tumor	NOUN
cana-3838	164	12	forms	form	NOUN
cana-3838	164	13	.	.	PUNCT
cana-3838	165	1	•	•	NUM
cana-3838	165	2	when	when	SCONJ
cana-3838	165	3	diagnosing	diagnose	VERB
cana-3838	165	4	brain	brain	NOUN
cana-3838	165	5	tumors	tumor	NOUN
cana-3838	165	6	,	,	PUNCT
cana-3838	165	7	radiologists	radiologist	NOUN
cana-3838	165	8	often	often	ADV
cana-3838	165	9	employ	employ	VERB
cana-3838	165	10	magnetic	magnetic	ADJ
cana-3838	165	11	resonance	resonance	NOUN
cana-3838	165	12	imaging	imaging	NOUN
cana-3838	165	13	(	(	PUNCT
cana-3838	165	14	mri	mri	NOUN
cana-3838	165	15	)	)	PUNCT
cana-3838	165	16	.	.	PUNCT
cana-3838	166	1	•	•	NUM
cana-3838	166	2	a	a	DET
cana-3838	166	3	branch	branch	NOUN
cana-3838	166	4	of	of	ADP
cana-3838	166	5	ml	ml	ADV
cana-3838	166	6	known	know	VERB
cana-3838	166	7	as	as	ADP
cana-3838	166	8	deep	deep	ADJ
cana-3838	166	9	learning	learning	NOUN
cana-3838	166	10	(	(	PUNCT
cana-3838	166	11	dl	dl	INTJ
cana-3838	166	12	)	)	PUNCT
cana-3838	166	13	has	have	AUX
cana-3838	166	14	shown	show	VERB
cana-3838	166	15	impressive	impressive	ADJ
cana-3838	166	16	results	result	NOUN
cana-3838	166	17	in	in	ADP
cana-3838	166	18	several	several	ADJ
cana-3838	166	19	fields	field	NOUN
cana-3838	166	20	,	,	PUNCT
cana-3838	166	21	including	include	VERB
cana-3838	166	22	image	image	NOUN
cana-3838	166	23	analysis	analysis	NOUN
cana-3838	166	24	and	and	CCONJ
cana-3838	166	25	recognition	recognition	NOUN
cana-3838	166	26	.	.	PUNCT
cana-3838	167	1	its	its	PRON
cana-3838	167	2	revolutionary	revolutionary	ADJ
cana-3838	167	3	capacity	capacity	NOUN
cana-3838	167	4	to	to	PART
cana-3838	167	5	automate	automate	VERB
cana-3838	167	6	complicated	complicated	ADJ
cana-3838	167	7	operations	operation	NOUN
cana-3838	167	8	and	and	CCONJ
cana-3838	167	9	drastically	drastically	ADV
cana-3838	167	10	cut	cut	VERB
cana-3838	167	11	human	human	ADJ
cana-3838	167	12	effort	effort	NOUN
cana-3838	167	13	has	have	AUX
cana-3838	167	14	led	lead	VERB
cana-3838	167	15	to	to	ADP
cana-3838	167	16	its	its	PRON
cana-3838	167	17	widespread	widespread	ADJ
cana-3838	167	18	adoption	adoption	NOUN
cana-3838	167	19	and	and	CCONJ
cana-3838	167	20	changed	change	VERB
cana-3838	167	21	many	many	ADJ
cana-3838	167	22	industries	industry	NOUN
cana-3838	167	23	,	,	PUNCT
cana-3838	167	24	including	include	VERB
cana-3838	167	25	healthcare	healthcare	NOUN
cana-3838	167	26	.	.	PUNCT
cana-3838	168	1	deep	deep	ADJ
cana-3838	168	2	learning	learn	VERB
cana-3838	168	3	algorithms	algorithm	NOUN
cana-3838	168	4	have	have	AUX
cana-3838	168	5	shown	show	VERB
cana-3838	168	6	impressive	impressive	ADJ
cana-3838	168	7	accuracy	accuracy	NOUN
cana-3838	168	8	in	in	ADP
cana-3838	168	9	mri	mri	NOUN
cana-3838	168	10	-	-	PUNCT
cana-3838	168	11	based	base	VERB
cana-3838	168	12	brain	brain	NOUN
cana-3838	168	13	tumor	tumor	NOUN
cana-3838	168	14	identification	identification	NOUN
cana-3838	168	15	,	,	PUNCT
cana-3838	168	16	which	which	PRON
cana-3838	168	17	may	may	AUX
cana-3838	168	18	aid	aid	VERB
cana-3838	168	19	doctors	doctor	NOUN
cana-3838	168	20	in	in	ADP
cana-3838	168	21	making	make	VERB
cana-3838	168	22	well	well	ADV
cana-3838	168	23	informed	informed	ADJ
cana-3838	168	24	judgments	judgment	NOUN
cana-3838	168	25	.	.	PUNCT
cana-3838	169	1	communications	communication	NOUN
cana-3838	169	2	on	on	ADP
cana-3838	169	3	applied	apply	VERB
cana-3838	169	4	nonlinear	nonlinear	ADJ
cana-3838	169	5	analysis	analysis	NOUN
cana-3838	169	6	issn	issn	NOUN
cana-3838	169	7	:	:	PUNCT
cana-3838	169	8	1074	1074	NUM
cana-3838	169	9	-	-	PUNCT
cana-3838	169	10	133x	133x	NUM
cana-3838	169	11	vol	vol	NOUN
cana-3838	169	12	32	32	NUM
cana-3838	169	13	no	no	NOUN
cana-3838	169	14	.	.	PUNCT
cana-3838	170	1	9s	9s	NUM
cana-3838	170	2	(	(	PUNCT
cana-3838	170	3	2025	2025	NUM
cana-3838	170	4	)	)	PUNCT
cana-3838	170	5	69	69	NUM
cana-3838	170	6	https://internationalpubls.com	https://internationalpubls.com	NUM
cana-3838	170	7	iii.proposed	iii.propose	VERB
cana-3838	170	8	model	model	NOUN
cana-3838	170	9	when	when	SCONJ
cana-3838	170	10	it	it	PRON
cana-3838	170	11	comes	come	VERB
cana-3838	170	12	to	to	ADP
cana-3838	170	13	global	global	ADJ
cana-3838	170	14	mortality	mortality	NOUN
cana-3838	170	15	tolls	toll	NOUN
cana-3838	170	16	,	,	PUNCT
cana-3838	170	17	cancer	cancer	NOUN
cana-3838	170	18	is	be	AUX
cana-3838	170	19	second	second	ADJ
cana-3838	170	20	only	only	ADV
cana-3838	170	21	to	to	ADP
cana-3838	170	22	cardiovascular	cardiovascular	ADJ
cana-3838	170	23	diseases	disease	NOUN
cana-3838	170	24	.	.	PUNCT
cana-3838	171	1	brain	brain	NOUN
cana-3838	171	2	tumors	tumor	NOUN
cana-3838	171	3	are	be	AUX
cana-3838	171	4	very	very	ADV
cana-3838	171	5	dangerous	dangerous	ADJ
cana-3838	171	6	forms	form	NOUN
cana-3838	171	7	of	of	ADP
cana-3838	171	8	cancer	cancer	NOUN
cana-3838	171	9	due	due	ADP
cana-3838	171	10	to	to	ADP
cana-3838	171	11	their	their	PRON
cana-3838	171	12	aggressiveness	aggressiveness	NOUN
cana-3838	171	13	,	,	PUNCT
cana-3838	171	14	diversity	diversity	NOUN
cana-3838	171	15	,	,	PUNCT
cana-3838	171	16	and	and	CCONJ
cana-3838	171	17	poor	poor	ADJ
cana-3838	171	18	prognosis	prognosis	NOUN
cana-3838	171	19	.	.	PUNCT
cana-3838	172	1	some	some	PRON
cana-3838	172	2	of	of	ADP
cana-3838	172	3	the	the	DET
cana-3838	172	4	distinguishing	distinguish	VERB
cana-3838	172	5	features	feature	NOUN
cana-3838	172	6	that	that	PRON
cana-3838	172	7	cause	cause	VERB
cana-3838	172	8	a	a	DET
cana-3838	172	9	brain	brain	NOUN
cana-3838	172	10	tumor	tumor	NOUN
cana-3838	172	11	to	to	PART
cana-3838	172	12	be	be	AUX
cana-3838	172	13	named	name	VERB
cana-3838	172	14	include	include	VERB
cana-3838	172	15	its	its	PRON
cana-3838	172	16	location	location	NOUN
cana-3838	172	17	,	,	PUNCT
cana-3838	172	18	texture	texture	NOUN
cana-3838	172	19	,	,	PUNCT
cana-3838	172	20	shape	shape	NOUN
cana-3838	172	21	,	,	PUNCT
cana-3838	172	22	and	and	CCONJ
cana-3838	172	23	aggressiveness	aggressiveness	NOUN
cana-3838	172	24	[	[	X
cana-3838	172	25	2	2	NUM
cana-3838	172	26	]	]	PUNCT
cana-3838	172	27	.	.	PUNCT
cana-3838	173	1	among	among	ADP
cana-3838	173	2	brain	brain	NOUN
cana-3838	173	3	malignancies	malignancy	NOUN
cana-3838	173	4	,	,	PUNCT
cana-3838	173	5	glioma	glioma	NOUN
cana-3838	173	6	is	be	AUX
cana-3838	173	7	the	the	DET
cana-3838	173	8	most	most	ADV
cana-3838	173	9	common	common	ADJ
cana-3838	173	10	.	.	PUNCT
cana-3838	174	1	the	the	DET
cana-3838	174	2	location	location	NOUN
cana-3838	174	3	and	and	CCONJ
cana-3838	174	4	subtype	subtype	NOUN
cana-3838	174	5	of	of	ADP
cana-3838	174	6	a	a	DET
cana-3838	174	7	patient	patient	NOUN
cana-3838	174	8	's	's	PART
cana-3838	174	9	glioma	glioma	NOUN
cana-3838	174	10	determine	determine	VERB
cana-3838	174	11	their	their	PRON
cana-3838	174	12	symptoms	symptom	NOUN
cana-3838	174	13	and	and	CCONJ
cana-3838	174	14	prognosis	prognosis	NOUN
cana-3838	174	15	[	[	X
cana-3838	174	16	21	21	NUM
cana-3838	174	17	]	]	PUNCT
cana-3838	174	18	.	.	PUNCT
cana-3838	175	1	several	several	ADJ
cana-3838	175	2	approaches	approach	NOUN
cana-3838	175	3	to	to	PART
cana-3838	175	4	brain	brain	NOUN
cana-3838	175	5	tumor	tumor	NOUN
cana-3838	175	6	segmentation	segmentation	NOUN
cana-3838	175	7	make	make	VERB
cana-3838	175	8	use	use	NOUN
cana-3838	175	9	of	of	ADP
cana-3838	175	10	the	the	DET
cana-3838	175	11	underlying	underlie	VERB
cana-3838	175	12	data	datum	NOUN
cana-3838	175	13	to	to	PART
cana-3838	175	14	construct	construct	VERB
cana-3838	175	15	a	a	DET
cana-3838	175	16	probabilistic	probabilistic	ADJ
cana-3838	175	17	model	model	NOUN
cana-3838	175	18	,	,	PUNCT
cana-3838	175	19	either	either	CCONJ
cana-3838	175	20	parametric	parametric	ADJ
cana-3838	175	21	or	or	CCONJ
cana-3838	175	22	non	non	ADJ
cana-3838	175	23	-	-	ADJ
cana-3838	175	24	parametric	parametric	ADJ
cana-3838	175	25	.	.	PUNCT
cana-3838	176	1	a	a	DET
cana-3838	176	2	previous	previous	ADJ
cana-3838	176	3	model	model	NOUN
cana-3838	176	4	and	and	CCONJ
cana-3838	176	5	a	a	DET
cana-3838	176	6	probability	probability	NOUN
cana-3838	176	7	function	function	NOUN
cana-3838	176	8	that	that	PRON
cana-3838	176	9	match	match	VERB
cana-3838	176	10	the	the	DET
cana-3838	176	11	data	datum	NOUN
cana-3838	176	12	are	be	AUX
cana-3838	176	13	common	common	ADJ
cana-3838	176	14	components	component	NOUN
cana-3838	176	15	of	of	ADP
cana-3838	176	16	such	such	ADJ
cana-3838	176	17	models	model	NOUN
cana-3838	176	18	.	.	PUNCT
cana-3838	177	1	because	because	SCONJ
cana-3838	177	2	they	they	PRON
cana-3838	177	3	are	be	AUX
cana-3838	177	4	aberrant	aberrant	ADJ
cana-3838	177	5	,	,	PUNCT
cana-3838	177	6	tumors	tumor	NOUN
cana-3838	177	7	may	may	AUX
cana-3838	177	8	be	be	AUX
cana-3838	177	9	segregated	segregate	VERB
cana-3838	177	10	as	as	ADP
cana-3838	177	11	distinct	distinct	ADJ
cana-3838	177	12	from	from	ADP
cana-3838	177	13	normal	normal	ADJ
cana-3838	177	14	tissue	tissue	NOUN
cana-3838	177	15	and	and	CCONJ
cana-3838	177	16	subjected	subject	VERB
cana-3838	177	17	to	to	ADP
cana-3838	177	18	constraints	constraint	NOUN
cana-3838	177	19	on	on	ADP
cana-3838	177	20	form	form	NOUN
cana-3838	177	21	and	and	CCONJ
cana-3838	177	22	connection	connection	NOUN
cana-3838	178	1	[	[	X
cana-3838	178	2	22].when	22].when	ADV
cana-3838	178	3	it	it	PRON
cana-3838	178	4	comes	come	VERB
cana-3838	178	5	to	to	ADP
cana-3838	178	6	segmenting	segment	VERB
cana-3838	178	7	brain	brain	NOUN
cana-3838	178	8	tumors	tumor	NOUN
cana-3838	178	9	in	in	ADP
cana-3838	178	10	mri	mri	NOUN
cana-3838	178	11	images	image	NOUN
cana-3838	178	12	,	,	PUNCT
cana-3838	178	13	we	we	PRON
cana-3838	178	14	provide	provide	VERB
cana-3838	178	15	a	a	DET
cana-3838	178	16	hybrid	hybrid	ADJ
cana-3838	178	17	model	model	NOUN
cana-3838	178	18	that	that	PRON
cana-3838	178	19	combines	combine	VERB
cana-3838	178	20	vgg16	vgg16	NOUN
cana-3838	178	21	with	with	ADP
cana-3838	178	22	resnet50	resnet50	NOUN
cana-3838	178	23	in	in	ADP
cana-3838	178	24	this	this	DET
cana-3838	178	25	study	study	NOUN
cana-3838	178	26	.	.	PUNCT
cana-3838	179	1	in	in	ADP
cana-3838	179	2	addition	addition	NOUN
cana-3838	179	3	,	,	PUNCT
cana-3838	179	4	we	we	PRON
cana-3838	179	5	segmented	segment	VERB
cana-3838	179	6	brain	brain	NOUN
cana-3838	179	7	tumors	tumor	NOUN
cana-3838	179	8	by	by	ADP
cana-3838	179	9	using	use	VERB
cana-3838	179	10	data	datum	NOUN
cana-3838	179	11	preprocessing	preprocessing	NOUN
cana-3838	179	12	and	and	CCONJ
cana-3838	179	13	data	datum	NOUN
cana-3838	179	14	augmentation	augmentation	NOUN
cana-3838	179	15	.	.	PUNCT
cana-3838	180	1	figure1	figure1	X
cana-3838	180	2	.	.	PUNCT
cana-3838	181	1	block	block	NOUN
cana-3838	181	2	diagram	diagram	PROPN
cana-3838	181	3	of	of	ADP
cana-3838	181	4	vgg16+resnet50	vgg16+resnet50	PROPN
cana-3838	181	5	model	model	PROPN
cana-3838	181	6	i.	i.	PROPN
cana-3838	181	7	dataset	dataset	PROPN
cana-3838	181	8	description	description	NOUN
cana-3838	181	9	.	.	PUNCT
cana-3838	182	1	we	we	PRON
cana-3838	182	2	have	have	AUX
cana-3838	182	3	limited	limit	VERB
cana-3838	182	4	our	our	PRON
cana-3838	182	5	use	use	NOUN
cana-3838	182	6	to	to	PART
cana-3838	182	7	mri	mri	VERB
cana-3838	182	8	pictures	picture	NOUN
cana-3838	182	9	that	that	PRON
cana-3838	182	10	have	have	AUX
cana-3838	182	11	been	be	AUX
cana-3838	182	12	identified	identify	VERB
cana-3838	182	13	using	use	VERB
cana-3838	182	14	the	the	DET
cana-3838	182	15	recommended	recommend	VERB
cana-3838	182	16	approach	approach	NOUN
cana-3838	182	17	in	in	ADP
cana-3838	182	18	this	this	DET
cana-3838	182	19	work	work	NOUN
cana-3838	182	20	.	.	PUNCT
cana-3838	183	1	the	the	DET
cana-3838	183	2	kaggle	kaggle	ADJ
cana-3838	183	3	dataset	dataset	NOUN
cana-3838	183	4	has	have	VERB
cana-3838	183	5	253	253	NUM
cana-3838	183	6	images	image	NOUN
cana-3838	183	7	from	from	ADP
cana-3838	183	8	different	different	ADJ
cana-3838	183	9	imaging	imaging	NOUN
cana-3838	183	10	modalities	modality	NOUN
cana-3838	183	11	.	.	PUNCT
cana-3838	184	1	ii	ii	PROPN
cana-3838	184	2	.	.	PUNCT
cana-3838	185	1	image	image	NOUN
cana-3838	185	2	preprocessing	preprocesse	VERB
cana-3838	185	3	preprocessing	preprocessing	NOUN
cana-3838	185	4	is	be	AUX
cana-3838	185	5	necessary	necessary	ADJ
cana-3838	185	6	for	for	ADP
cana-3838	185	7	the	the	DET
cana-3838	185	8	dataset	dataset	NOUN
cana-3838	185	9	's	's	PART
cana-3838	185	10	pictures	picture	NOUN
cana-3838	185	11	because	because	SCONJ
cana-3838	185	12	to	to	ADP
cana-3838	185	13	the	the	DET
cana-3838	185	14	large	large	ADJ
cana-3838	185	15	variation	variation	NOUN
cana-3838	185	16	in	in	ADP
cana-3838	185	17	intensities	intensity	NOUN
cana-3838	185	18	,	,	PUNCT
cana-3838	185	19	which	which	PRON
cana-3838	185	20	exceed	exceed	VERB
cana-3838	185	21	the	the	DET
cana-3838	185	22	standard	standard	ADJ
cana-3838	185	23	industry	industry	NOUN
cana-3838	185	24	threshold	threshold	NOUN
cana-3838	185	25	of	of	ADP
cana-3838	185	26	255	255	NUM
cana-3838	185	27	.	.	PUNCT
cana-3838	186	1	the	the	DET
cana-3838	186	2	smooth	smooth	ADJ
cana-3838	186	3	and	and	CCONJ
cana-3838	186	4	quantitative	quantitative	ADJ
cana-3838	186	5	training	training	NOUN
cana-3838	186	6	of	of	ADP
cana-3838	186	7	the	the	DET
cana-3838	186	8	network	network	NOUN
cana-3838	186	9	depends	depend	VERB
cana-3838	186	10	on	on	ADP
cana-3838	186	11	completing	complete	VERB
cana-3838	186	12	a	a	DET
cana-3838	186	13	certain	certain	ADJ
cana-3838	186	14	set	set	NOUN
cana-3838	186	15	of	of	ADP
cana-3838	186	16	preprocessing	preprocessing	NOUN
cana-3838	186	17	processes	process	NOUN
cana-3838	186	18	.	.	PUNCT
cana-3838	187	1	there	there	PRON
cana-3838	187	2	is	be	VERB
cana-3838	187	3	some	some	DET
cana-3838	187	4	evidence	evidence	NOUN
cana-3838	187	5	that	that	SCONJ
cana-3838	187	6	preprocessing	preprocessing	NOUN
cana-3838	187	7	may	may	AUX
cana-3838	187	8	improve	improve	VERB
cana-3838	187	9	segmentation	segmentation	NOUN
cana-3838	187	10	accuracy	accuracy	NOUN
cana-3838	187	11	[	[	X
cana-3838	187	12	16	16	NUM
cana-3838	187	13	]	]	PUNCT
cana-3838	187	14	.	.	PUNCT
cana-3838	188	1	the	the	DET
cana-3838	188	2	process	process	NOUN
cana-3838	188	3	of	of	ADP
cana-3838	188	4	histogram	histogram	NOUN
cana-3838	188	5	equalization	equalization	NOUN
cana-3838	188	6	,	,	PUNCT
cana-3838	188	7	which	which	PRON
cana-3838	188	8	involves	involve	VERB
cana-3838	188	9	mapping	map	VERB
cana-3838	188	10	new	new	ADJ
cana-3838	188	11	pixel	pixel	NOUN
cana-3838	188	12	values	value	NOUN
cana-3838	188	13	to	to	ADP
cana-3838	188	14	the	the	DET
cana-3838	188	15	histogram	histogram	NOUN
cana-3838	188	16	,	,	PUNCT
cana-3838	188	17	enhances	enhance	VERB
cana-3838	188	18	the	the	DET
cana-3838	188	19	contrast	contrast	NOUN
cana-3838	188	20	of	of	ADP
cana-3838	188	21	a	a	DET
cana-3838	188	22	grayscale	grayscale	NOUN
cana-3838	188	23	image	image	NOUN
cana-3838	188	24	.	.	PUNCT
cana-3838	189	1	image	image	NOUN
cana-3838	189	2	histogram	histogram	NOUN
cana-3838	189	3	dynamic	dynamic	ADJ
cana-3838	189	4	range	range	NOUN
cana-3838	189	5	expansion	expansion	NOUN
cana-3838	189	6	is	be	AUX
cana-3838	189	7	the	the	DET
cana-3838	189	8	goal	goal	NOUN
cana-3838	189	9	of	of	ADP
cana-3838	189	10	this	this	DET
cana-3838	189	11	method	method	NOUN
cana-3838	189	12	.	.	PUNCT
cana-3838	190	1	histogram	histogram	PROPN
cana-3838	190	2	balancing	balancing	NOUN
cana-3838	190	3	increases	increase	VERB
cana-3838	190	4	image	image	NOUN
cana-3838	190	5	separation	separation	NOUN
cana-3838	190	6	and	and	CCONJ
cana-3838	190	7	segmentation	segmentation	NOUN
cana-3838	190	8	(	(	PUNCT
cana-3838	190	9	vgg16+resn	vgg16+resn	PROPN
cana-3838	190	10	et50	et50	PROPN
cana-3838	190	11	)	)	PUNCT
cana-3838	190	12	image	image	NOUN
cana-3838	190	13	augmentation	augmentation	NOUN
cana-3838	190	14	image	image	NOUN
cana-3838	190	15	dataset	dataset	VERB
cana-3838	190	16	image	image	NOUN
cana-3838	190	17	preprocessing	preprocesse	VERB
cana-3838	190	18	communications	communication	NOUN
cana-3838	190	19	on	on	ADP
cana-3838	190	20	applied	apply	VERB
cana-3838	190	21	nonlinear	nonlinear	ADJ
cana-3838	190	22	analysis	analysis	NOUN
cana-3838	190	23	issn	issn	NOUN
cana-3838	190	24	:	:	PUNCT
cana-3838	190	25	1074	1074	NUM
cana-3838	190	26	-	-	PUNCT
cana-3838	190	27	133x	133x	NUM
cana-3838	190	28	vol	vol	NOUN
cana-3838	190	29	32	32	NUM
cana-3838	190	30	no	no	NOUN
cana-3838	190	31	.	.	PUNCT
cana-3838	191	1	9s	9s	NUM
cana-3838	191	2	(	(	PUNCT
cana-3838	191	3	2025	2025	NUM
cana-3838	191	4	)	)	PUNCT
cana-3838	191	5	70	70	NUM
cana-3838	191	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-3838	191	7	ensures	ensure	VERB
cana-3838	191	8	a	a	DET
cana-3838	191	9	uniform	uniform	ADJ
cana-3838	191	10	distribution	distribution	NOUN
cana-3838	191	11	of	of	ADP
cana-3838	191	12	forces	force	NOUN
cana-3838	191	13	in	in	ADP
cana-3838	191	14	the	the	DET
cana-3838	191	15	output	output	NOUN
cana-3838	191	16	image	image	NOUN
cana-3838	191	17	by	by	ADP
cana-3838	191	18	assigning	assign	VERB
cana-3838	191	19	force	force	NOUN
cana-3838	191	20	estimates	estimate	NOUN
cana-3838	191	21	to	to	ADP
cana-3838	191	22	pixels	pixel	NOUN
cana-3838	191	23	in	in	ADP
cana-3838	191	24	the	the	DET
cana-3838	191	25	input	input	NOUN
cana-3838	191	26	image	image	NOUN
cana-3838	191	27	.	.	PUNCT
cana-3838	192	1	(	(	PUNCT
cana-3838	192	2	𝑎	𝑎	X
cana-3838	192	3	,	,	PUNCT
cana-3838	192	4	𝑏	𝑏	NOUN
cana-3838	192	5	)	)	PUNCT
cana-3838	192	6	1	1	NUM
cana-3838	192	7	(	(	PUNCT
cana-3838	192	8	𝑎	𝑎	NOUN
cana-3838	192	9	,	,	PUNCT
cana-3838	192	10	𝑏	𝑏	NOUN
cana-3838	192	11	)	)	PUNCT
cana-3838	192	12	≥	≥	NOUN
cana-3838	192	13	𝑇	𝑇	NOUN
cana-3838	192	14	=	=	PRON
cana-3838	192	15	{	{	PUNCT
cana-3838	192	16	0	0	NUM
cana-3838	192	17	(	(	PUNCT
cana-3838	192	18	𝑎	𝑎	NOUN
cana-3838	192	19	,	,	PUNCT
cana-3838	192	20	𝑏	𝑏	NOUN
cana-3838	192	21	)	)	PUNCT
cana-3838	192	22	≤	≤	NOUN
cana-3838	192	23	𝑇	𝑇	PROPN
cana-3838	192	24	(	(	PUNCT
cana-3838	192	25	1	1	NUM
cana-3838	192	26	)	)	PUNCT
cana-3838	192	27	in	in	ADP
cana-3838	192	28	this	this	DET
cana-3838	192	29	case	case	NOUN
cana-3838	192	30	,	,	PUNCT
cana-3838	192	31	a	a	PRON
cana-3838	192	32	and	and	CCONJ
cana-3838	192	33	b	b	NOUN
cana-3838	192	34	are	be	AUX
cana-3838	192	35	two	two	NUM
cana-3838	192	36	spatial	spatial	ADJ
cana-3838	192	37	coordinates	coordinate	NOUN
cana-3838	192	38	,	,	PUNCT
cana-3838	192	39	and	and	CCONJ
cana-3838	192	40	t	t	PROPN
cana-3838	192	41	is	be	AUX
cana-3838	192	42	the	the	DET
cana-3838	192	43	image	image	NOUN
cana-3838	192	44	's	's	PART
cana-3838	192	45	gray	gray	ADJ
cana-3838	192	46	level	level	NOUN
cana-3838	192	47	count	count	NOUN
cana-3838	192	48	.	.	PUNCT
cana-3838	193	1	the	the	DET
cana-3838	193	2	imagegraphs	imagegraph	NOUN
cana-3838	193	3	have	have	VERB
cana-3838	193	4	too	too	ADV
cana-3838	193	5	much	much	ADJ
cana-3838	193	6	noise	noise	NOUN
cana-3838	193	7	for	for	ADP
cana-3838	193	8	resnets	resnet	NOUN
cana-3838	193	9	to	to	PART
cana-3838	193	10	make	make	VERB
cana-3838	193	11	a	a	DET
cana-3838	193	12	difference	difference	NOUN
cana-3838	193	13	.	.	PUNCT
cana-3838	194	1	the	the	DET
cana-3838	194	2	noise	noise	NOUN
cana-3838	194	3	in	in	ADP
cana-3838	194	4	images	image	NOUN
cana-3838	194	5	will	will	AUX
cana-3838	194	6	be	be	AUX
cana-3838	194	7	reduced	reduce	VERB
cana-3838	194	8	via	via	ADP
cana-3838	194	9	binarization	binarization	NOUN
cana-3838	194	10	.	.	PUNCT
cana-3838	195	1	the	the	DET
cana-3838	195	2	rgb	rgb	PROPN
cana-3838	195	3	(	(	PUNCT
cana-3838	195	4	red	red	ADJ
cana-3838	195	5	,	,	PUNCT
cana-3838	195	6	green	green	ADJ
cana-3838	195	7	,	,	PUNCT
cana-3838	195	8	and	and	CCONJ
cana-3838	195	9	blue	blue	ADJ
cana-3838	195	10	)	)	PUNCT
cana-3838	195	11	channels	channel	NOUN
cana-3838	195	12	of	of	ADP
cana-3838	195	13	a	a	DET
cana-3838	195	14	color	color	NOUN
cana-3838	195	15	image	image	NOUN
cana-3838	195	16	may	may	AUX
cana-3838	195	17	take	take	VERB
cana-3838	195	18	on	on	ADP
cana-3838	195	19	values	value	NOUN
cana-3838	195	20	between	between	ADP
cana-3838	195	21	zero	zero	NUM
cana-3838	195	22	and	and	CCONJ
cana-3838	195	23	two	two	NUM
cana-3838	195	24	hundred	hundred	NUM
cana-3838	195	25	and	and	CCONJ
cana-3838	195	26	fifty	fifty	NUM
cana-3838	195	27	.	.	PUNCT
cana-3838	196	1	the	the	DET
cana-3838	196	2	transformation	transformation	NOUN
cana-3838	196	3	of	of	ADP
cana-3838	196	4	grayscale	grayscale	NOUN
cana-3838	196	5	images	image	NOUN
cana-3838	196	6	into	into	ADP
cana-3838	196	7	monochrome	monochrome	NOUN
cana-3838	196	8	(	(	PUNCT
cana-3838	196	9	0	0	NUM
cana-3838	196	10	to	to	PART
cana-3838	196	11	1	1	NUM
cana-3838	196	12	)	)	PUNCT
cana-3838	196	13	images	image	NOUN
cana-3838	196	14	is	be	AUX
cana-3838	196	15	a	a	DET
cana-3838	196	16	crucial	crucial	ADJ
cana-3838	196	17	part	part	NOUN
cana-3838	196	18	of	of	ADP
cana-3838	196	19	binarization	binarization	NOUN
cana-3838	196	20	.	.	PUNCT
cana-3838	197	1	the	the	DET
cana-3838	197	2	contours	contours	NOUN
cana-3838	197	3	of	of	ADP
cana-3838	197	4	different	different	ADJ
cana-3838	197	5	objects	object	NOUN
cana-3838	197	6	in	in	ADP
cana-3838	197	7	the	the	DET
cana-3838	197	8	image	image	NOUN
cana-3838	197	9	are	be	AUX
cana-3838	197	10	simplified	simplify	VERB
cana-3838	197	11	and	and	CCONJ
cana-3838	197	12	smoothed	smooth	VERB
cana-3838	197	13	down	down	ADP
cana-3838	197	14	via	via	ADP
cana-3838	197	15	binarization	binarization	NOUN
cana-3838	197	16	.	.	PUNCT
cana-3838	198	1	the	the	DET
cana-3838	198	2	model	model	NOUN
cana-3838	198	3	's	's	PART
cana-3838	198	4	learning	learning	NOUN
cana-3838	198	5	is	be	AUX
cana-3838	198	6	facilitated	facilitate	VERB
cana-3838	198	7	by	by	ADP
cana-3838	198	8	this	this	DET
cana-3838	198	9	function	function	NOUN
cana-3838	198	10	extraction	extraction	NOUN
cana-3838	198	11	.	.	PUNCT
cana-3838	199	1	iii	iii	X
cana-3838	199	2	.	.	PUNCT
cana-3838	199	3	data	datum	NOUN
cana-3838	199	4	augmentation	augmentation	PROPN
cana-3838	199	5	:	:	PUNCT
cana-3838	199	6	when	when	SCONJ
cana-3838	199	7	applied	apply	VERB
cana-3838	199	8	to	to	ADP
cana-3838	199	9	larger	large	ADJ
cana-3838	199	10	training	training	NOUN
cana-3838	199	11	sets	set	NOUN
cana-3838	199	12	,	,	PUNCT
cana-3838	199	13	it	it	PRON
cana-3838	199	14	helps	help	VERB
cana-3838	199	15	to	to	PART
cana-3838	199	16	decrease	decrease	VERB
cana-3838	199	17	overfitting	overfitte	VERB
cana-3838	199	18	.	.	PUNCT
cana-3838	200	1	the	the	DET
cana-3838	200	2	data	data	NOUN
cana-3838	200	3	augmentation	augmentation	NOUN
cana-3838	200	4	was	be	AUX
cana-3838	200	5	limited	limit	VERB
cana-3838	200	6	to	to	ADP
cana-3838	200	7	rotational	rotational	ADJ
cana-3838	200	8	operations	operation	NOUN
cana-3838	200	9	as	as	SCONJ
cana-3838	200	10	the	the	DET
cana-3838	200	11	patch	patch	NOUN
cana-3838	200	12	's	's	PART
cana-3838	200	13	class	class	NOUN
cana-3838	200	14	is	be	AUX
cana-3838	200	15	retrieved	retrieve	VERB
cana-3838	200	16	by	by	ADP
cana-3838	200	17	the	the	DET
cana-3838	200	18	center	center	NOUN
cana-3838	200	19	voxel	voxel	PROPN
cana-3838	200	20	.	.	PUNCT
cana-3838	201	1	image	image	NOUN
cana-3838	201	2	translations	translation	NOUN
cana-3838	201	3	are	be	AUX
cana-3838	201	4	also	also	ADV
cana-3838	201	5	considered	consider	VERB
cana-3838	201	6	by	by	ADP
cana-3838	201	7	some	some	DET
cana-3838	201	8	writers	writer	NOUN
cana-3838	201	9	,	,	PUNCT
cana-3838	201	10	although	although	SCONJ
cana-3838	201	11	they	they	PRON
cana-3838	201	12	may	may	AUX
cana-3838	201	13	assign	assign	VERB
cana-3838	201	14	the	the	DET
cana-3838	201	15	incorrect	incorrect	ADJ
cana-3838	201	16	class	class	NOUN
cana-3838	201	17	to	to	ADP
cana-3838	201	18	the	the	DET
cana-3838	201	19	patch	patch	NOUN
cana-3838	201	20	when	when	SCONJ
cana-3838	201	21	used	use	VERB
cana-3838	201	22	for	for	ADP
cana-3838	201	23	segmentation	segmentation	NOUN
cana-3838	201	24	.	.	PUNCT
cana-3838	202	1	as	as	ADP
cana-3838	202	2	a	a	DET
cana-3838	202	3	result	result	NOUN
cana-3838	202	4	,	,	PUNCT
cana-3838	202	5	we	we	PRON
cana-3838	202	6	rotated	rotate	VERB
cana-3838	202	7	an	an	DET
cana-3838	202	8	existing	exist	VERB
cana-3838	202	9	patch	patch	NOUN
cana-3838	202	10	to	to	PART
cana-3838	202	11	create	create	VERB
cana-3838	202	12	new	new	ADJ
cana-3838	202	13	ones	one	NOUN
cana-3838	202	14	during	during	ADP
cana-3838	202	15	training	training	NOUN
cana-3838	202	16	,	,	PUNCT
cana-3838	202	17	which	which	PRON
cana-3838	202	18	enriched	enrich	VERB
cana-3838	202	19	our	our	PRON
cana-3838	202	20	data	datum	NOUN
cana-3838	202	21	set	set	VERB
cana-3838	202	22	.	.	PUNCT
cana-3838	203	1	even	even	ADV
cana-3838	203	2	though	though	SCONJ
cana-3838	203	3	we	we	PRON
cana-3838	203	4	used	use	VERB
cana-3838	203	5	angles	angle	NOUN
cana-3838	203	6	that	that	PRON
cana-3838	203	7	are	be	AUX
cana-3838	203	8	multiples	multiple	NOUN
cana-3838	203	9	of	of	ADP
cana-3838	203	10	90	90	NUM
cana-3838	203	11	degrees	degree	NOUN
cana-3838	203	12	in	in	ADP
cana-3838	203	13	our	our	PRON
cana-3838	203	14	suggestion	suggestion	NOUN
cana-3838	203	15	,	,	PUNCT
cana-3838	203	16	we	we	PRON
cana-3838	203	17	will	will	AUX
cana-3838	203	18	be	be	AUX
cana-3838	203	19	contemplating	contemplate	VERB
cana-3838	203	20	an	an	DET
cana-3838	203	21	alternative	alternative	ADJ
cana-3838	203	22	option	option	NOUN
cana-3838	204	1	[	[	X
cana-3838	204	2	22	22	NUM
cana-3838	204	3	]	]	PUNCT
cana-3838	204	4	.	.	PUNCT
cana-3838	205	1	with	with	ADP
cana-3838	205	2	data	datum	NOUN
cana-3838	205	3	augmentation	augmentation	NOUN
cana-3838	205	4	,	,	PUNCT
cana-3838	205	5	we	we	PRON
cana-3838	205	6	may	may	AUX
cana-3838	205	7	make	make	VERB
cana-3838	205	8	inputs	input	NOUN
cana-3838	205	9	that	that	PRON
cana-3838	205	10	are	be	AUX
cana-3838	205	11	n't	not	PART
cana-3838	205	12	always	always	ADV
cana-3838	205	13	accurate	accurate	ADJ
cana-3838	205	14	.	.	PUNCT
cana-3838	206	1	cropping	cropping	NOUN
cana-3838	206	2	,	,	PUNCT
cana-3838	206	3	zooming	zooming	NOUN
cana-3838	206	4	,	,	PUNCT
cana-3838	206	5	and	and	CCONJ
cana-3838	206	6	rotating	rotate	VERB
cana-3838	206	7	mri	mri	NOUN
cana-3838	206	8	images	image	NOUN
cana-3838	206	9	is	be	AUX
cana-3838	206	10	as	as	ADV
cana-3838	206	11	easy	easy	ADJ
cana-3838	206	12	as	as	ADP
cana-3838	206	13	using	use	VERB
cana-3838	206	14	image	image	NOUN
cana-3838	206	15	editing	edit	VERB
cana-3838	206	16	software	software	NOUN
cana-3838	206	17	.	.	PUNCT
cana-3838	207	1	by	by	ADP
cana-3838	207	2	excluding	exclude	VERB
cana-3838	207	3	morphological	morphological	ADJ
cana-3838	207	4	arrangements	arrangement	NOUN
cana-3838	207	5	that	that	PRON
cana-3838	207	6	are	be	AUX
cana-3838	207	7	not	not	PART
cana-3838	207	8	meaningful	meaningful	ADJ
cana-3838	207	9	across	across	ADP
cana-3838	207	10	images	image	NOUN
cana-3838	207	11	,	,	PUNCT
cana-3838	207	12	the	the	DET
cana-3838	207	13	neural	neural	ADJ
cana-3838	207	14	network	network	NOUN
cana-3838	207	15	is	be	AUX
cana-3838	207	16	able	able	ADJ
cana-3838	207	17	to	to	PART
cana-3838	207	18	avoid	avoid	VERB
cana-3838	207	19	overfitting	overfitte	VERB
cana-3838	207	20	and	and	CCONJ
cana-3838	207	21	avoid	avoid	VERB
cana-3838	207	22	recognizing	recognize	VERB
cana-3838	207	23	particular	particular	ADJ
cana-3838	207	24	patterns	pattern	NOUN
cana-3838	207	25	in	in	ADP
cana-3838	207	26	the	the	DET
cana-3838	207	27	input	input	NOUN
cana-3838	207	28	dataset	dataset	NOUN
cana-3838	207	29	.	.	PUNCT
cana-3838	208	1	to	to	PART
cana-3838	208	2	introduce	introduce	VERB
cana-3838	208	3	uncertainty	uncertainty	NOUN
cana-3838	208	4	into	into	ADP
cana-3838	208	5	the	the	DET
cana-3838	208	6	dataset	dataset	NOUN
cana-3838	208	7	,	,	PUNCT
cana-3838	208	8	dropout	dropout	NOUN
cana-3838	208	9	briefly	briefly	NOUN
cana-3838	208	10	removes	remove	VERB
cana-3838	208	11	nodes	node	NOUN
cana-3838	208	12	from	from	ADP
cana-3838	208	13	the	the	DET
cana-3838	208	14	convolutional	convolutional	ADJ
cana-3838	208	15	neural	neural	ADJ
cana-3838	208	16	network	network	NOUN
cana-3838	208	17	.	.	PUNCT
cana-3838	209	1	one	one	NUM
cana-3838	209	2	way	way	NOUN
cana-3838	209	3	to	to	PART
cana-3838	209	4	lower	lower	VERB
cana-3838	209	5	the	the	DET
cana-3838	209	6	weighting	weighting	NOUN
cana-3838	209	7	strength	strength	NOUN
cana-3838	209	8	of	of	ADP
cana-3838	209	9	biased	biased	ADJ
cana-3838	209	10	nodes	node	NOUN
cana-3838	209	11	is	be	AUX
cana-3838	209	12	to	to	PART
cana-3838	209	13	use	use	VERB
cana-3838	209	14	batch	batch	NOUN
cana-3838	209	15	normalization	normalization	NOUN
cana-3838	209	16	.	.	PUNCT
cana-3838	210	1	since	since	SCONJ
cana-3838	210	2	these	these	DET
cana-3838	210	3	heavy	heavy	ADJ
cana-3838	210	4	weights	weight	NOUN
cana-3838	210	5	could	could	AUX
cana-3838	210	6	be	be	AUX
cana-3838	210	7	linked	link	VERB
cana-3838	210	8	to	to	ADP
cana-3838	210	9	particular	particular	ADJ
cana-3838	210	10	,	,	PUNCT
cana-3838	210	11	accurate	accurate	ADJ
cana-3838	210	12	traits	trait	NOUN
cana-3838	210	13	in	in	ADP
cana-3838	210	14	the	the	DET
cana-3838	210	15	training	training	NOUN
cana-3838	210	16	set	set	NOUN
cana-3838	210	17	,	,	PUNCT
cana-3838	210	18	they	they	PRON
cana-3838	210	19	do	do	AUX
cana-3838	210	20	provide	provide	VERB
cana-3838	210	21	generalizability	generalizability	NOUN
cana-3838	210	22	to	to	ADP
cana-3838	210	23	other	other	ADJ
cana-3838	210	24	datasets	dataset	NOUN
cana-3838	210	25	[	[	X
cana-3838	210	26	20	20	NUM
cana-3838	210	27	]	]	PUNCT
cana-3838	210	28	.	.	PUNCT
cana-3838	211	1	iv	iv	X
cana-3838	211	2	.	.	PUNCT
cana-3838	211	3	proposed	propose	VERB
cana-3838	211	4	vgg	vgg	PROPN
cana-3838	211	5	16	16	NUM
cana-3838	211	6	+	+	NUM
cana-3838	211	7	resnet50	resnet50	NOUN
cana-3838	211	8	segmentation	segmentation	NOUN
cana-3838	211	9	model	model	NOUN
cana-3838	211	10	:	:	PUNCT
cana-3838	211	11	an	an	DET
cana-3838	211	12	efficient	efficient	ADJ
cana-3838	211	13	dl	dl	NOUN
cana-3838	211	14	technique	technique	NOUN
cana-3838	211	15	,	,	PUNCT
cana-3838	211	16	transfer	transfer	NOUN
cana-3838	211	17	learning	learning	NOUN
cana-3838	211	18	(	(	PUNCT
cana-3838	211	19	tl	tl	PROPN
cana-3838	211	20	)	)	PUNCT
cana-3838	211	21	allows	allow	VERB
cana-3838	211	22	for	for	ADP
cana-3838	211	23	the	the	DET
cana-3838	211	24	reuse	reuse	NOUN
cana-3838	211	25	of	of	ADP
cana-3838	211	26	trained	train	VERB
cana-3838	211	27	models	model	NOUN
cana-3838	211	28	and	and	CCONJ
cana-3838	211	29	the	the	DET
cana-3838	211	30	approximations	approximation	NOUN
cana-3838	211	31	they	they	PRON
cana-3838	211	32	acquired	acquire	VERB
cana-3838	211	33	for	for	ADP
cana-3838	211	34	new	new	ADJ
cana-3838	211	35	uses	use	NOUN
cana-3838	211	36	.	.	PUNCT
cana-3838	212	1	because	because	SCONJ
cana-3838	212	2	it	it	PRON
cana-3838	212	3	increases	increase	VERB
cana-3838	212	4	performance	performance	NOUN
cana-3838	212	5	,	,	PUNCT
cana-3838	212	6	speeds	speed	VERB
cana-3838	212	7	up	up	ADP
cana-3838	212	8	training	training	NOUN
cana-3838	212	9	,	,	PUNCT
cana-3838	212	10	and	and	CCONJ
cana-3838	212	11	makes	make	VERB
cana-3838	212	12	better	well	ADJ
cana-3838	212	13	generalization	generalization	NOUN
cana-3838	212	14	,	,	PUNCT
cana-3838	212	15	it	it	PRON
cana-3838	212	16	is	be	AUX
cana-3838	212	17	useful	useful	ADJ
cana-3838	212	18	in	in	ADP
cana-3838	212	19	many	many	ADJ
cana-3838	212	20	applications	application	NOUN
cana-3838	212	21	where	where	SCONJ
cana-3838	212	22	data	datum	NOUN
cana-3838	212	23	is	be	AUX
cana-3838	212	24	few	few	ADJ
cana-3838	212	25	and	and	CCONJ
cana-3838	212	26	computer	computer	NOUN
cana-3838	212	27	resources	resource	NOUN
cana-3838	212	28	are	be	AUX
cana-3838	212	29	constrained	constrain	VERB
cana-3838	212	30	.	.	PUNCT
cana-3838	213	1	another	another	DET
cana-3838	213	2	benefit	benefit	NOUN
cana-3838	213	3	of	of	ADP
cana-3838	213	4	tl	tl	PROPN
cana-3838	213	5	is	be	AUX
cana-3838	213	6	that	that	SCONJ
cana-3838	213	7	it	it	PRON
cana-3838	213	8	allows	allow	VERB
cana-3838	213	9	data	datum	NOUN
cana-3838	213	10	training	training	NOUN
cana-3838	213	11	with	with	ADP
cana-3838	213	12	lower	low	ADJ
cana-3838	213	13	model	model	NOUN
cana-3838	213	14	design	design	NOUN
cana-3838	213	15	expenses	expense	NOUN
cana-3838	213	16	[	[	X
cana-3838	213	17	20	20	NUM
cana-3838	213	18	]	]	PUNCT
cana-3838	213	19	.	.	PUNCT
cana-3838	214	1	specifically	specifically	ADV
cana-3838	214	2	,	,	PUNCT
cana-3838	214	3	this	this	DET
cana-3838	214	4	piece	piece	NOUN
cana-3838	214	5	makes	make	VERB
cana-3838	214	6	use	use	NOUN
cana-3838	214	7	of	of	ADP
cana-3838	214	8	a	a	DET
cana-3838	214	9	vgg	vgg	NOUN
cana-3838	214	10	16	16	NUM
cana-3838	214	11	+	+	NUM
cana-3838	214	12	resnet50	resnet50	NOUN
cana-3838	214	13	hybrid	hybrid	ADJ
cana-3838	214	14	model	model	NOUN
cana-3838	214	15	[	[	X
cana-3838	214	16	15	15	NUM
cana-3838	214	17	]	]	PUNCT
cana-3838	214	18	.	.	PUNCT
cana-3838	215	1	a	a	DET
cana-3838	215	2	combination	combination	NOUN
cana-3838	215	3	of	of	ADP
cana-3838	215	4	resnet50	resnet50	NOUN
cana-3838	215	5	and	and	CCONJ
cana-3838	215	6	vgg16	vgg16	VERB
cana-3838	215	7	for	for	ADP
cana-3838	215	8	mri	mri	NOUN
cana-3838	215	9	-	-	PUNCT
cana-3838	215	10	based	base	VERB
cana-3838	215	11	tumor	tumor	NOUN
cana-3838	215	12	detection	detection	NOUN
cana-3838	215	13	and	and	CCONJ
cana-3838	215	14	segmentation	segmentation	NOUN
cana-3838	215	15	via	via	ADP
cana-3838	215	16	a	a	DET
cana-3838	215	17	hybrid	hybrid	ADJ
cana-3838	215	18	technique	technique	NOUN
cana-3838	215	19	.	.	PUNCT
cana-3838	216	1	using	use	VERB
cana-3838	216	2	the	the	DET
cana-3838	216	3	enormous	enormous	ADJ
cana-3838	216	4	imagenet	imagenet	NOUN
cana-3838	216	5	dataset	dataset	NOUN
cana-3838	216	6	,	,	PUNCT
cana-3838	216	7	resnet50	resnet50	NOUN
cana-3838	216	8	is	be	AUX
cana-3838	216	9	a	a	DET
cana-3838	216	10	convolutional	convolutional	ADJ
cana-3838	216	11	neural	neural	ADJ
cana-3838	216	12	network	network	NOUN
cana-3838	216	13	(	(	PUNCT
cana-3838	216	14	cnn	cnn	PROPN
cana-3838	216	15	)	)	PUNCT
cana-3838	216	16	model	model	NOUN
cana-3838	216	17	trained	train	VERB
cana-3838	216	18	for	for	ADP
cana-3838	216	19	object	object	NOUN
cana-3838	216	20	recognition	recognition	NOUN
cana-3838	216	21	tasks	task	NOUN
cana-3838	216	22	.	.	PUNCT
cana-3838	217	1	completely	completely	ADV
cana-3838	217	2	linked	link	VERB
cana-3838	217	3	,	,	PUNCT
cana-3838	217	4	pooling	pooling	NOUN
cana-3838	217	5	,	,	PUNCT
cana-3838	217	6	and	and	CCONJ
cana-3838	217	7	convolutional	convolutional	ADJ
cana-3838	217	8	layers	layer	NOUN
cana-3838	217	9	are	be	AUX
cana-3838	217	10	among	among	ADP
cana-3838	217	11	its	its	PRON
cana-3838	217	12	many	many	ADJ
cana-3838	217	13	components	component	NOUN
cana-3838	217	14	.	.	PUNCT
cana-3838	218	1	this	this	DET
cana-3838	218	2	model	model	NOUN
cana-3838	218	3	's	's	PART
cana-3838	218	4	feature	feature	NOUN
cana-3838	218	5	extraction	extraction	NOUN
cana-3838	218	6	capabilities	capability	NOUN
cana-3838	218	7	could	could	AUX
cana-3838	218	8	be	be	AUX
cana-3838	218	9	useful	useful	ADJ
cana-3838	218	10	for	for	ADP
cana-3838	218	11	solving	solve	VERB
cana-3838	218	12	the	the	DET
cana-3838	218	13	brain	brain	NOUN
cana-3838	218	14	tumor	tumor	NOUN
cana-3838	218	15	detection	detection	NOUN
cana-3838	218	16	problem	problem	NOUN
cana-3838	218	17	.	.	PUNCT
cana-3838	219	1	using	use	VERB
cana-3838	219	2	public	public	ADJ
cana-3838	219	3	picture	picture	NOUN
cana-3838	219	4	communications	communication	NOUN
cana-3838	219	5	on	on	ADP
cana-3838	219	6	applied	apply	VERB
cana-3838	219	7	nonlinear	nonlinear	ADJ
cana-3838	219	8	analysis	analysis	NOUN
cana-3838	219	9	issn	issn	NOUN
cana-3838	219	10	:	:	PUNCT
cana-3838	219	11	1074	1074	NUM
cana-3838	219	12	-	-	PUNCT
cana-3838	219	13	133x	133x	NUM
cana-3838	219	14	vol	vol	NOUN
cana-3838	219	15	32	32	NUM
cana-3838	219	16	no	no	NOUN
cana-3838	219	17	.	.	PUNCT
cana-3838	220	1	9s	9s	NUM
cana-3838	220	2	(	(	PUNCT
cana-3838	220	3	2025	2025	NUM
cana-3838	220	4	)	)	PUNCT
cana-3838	220	5	71	71	NUM
cana-3838	221	1	https://internationalpubls.com	https://internationalpubls.com	X
cana-3838	221	2	features	feature	VERB
cana-3838	221	3	as	as	ADP
cana-3838	221	4	a	a	DET
cana-3838	221	5	basis	basis	NOUN
cana-3838	221	6	,	,	PUNCT
cana-3838	221	7	the	the	DET
cana-3838	221	8	resnet50	resnet50	NOUN
cana-3838	221	9	model	model	NOUN
cana-3838	221	10	's	's	PART
cana-3838	221	11	bottom	bottom	ADJ
cana-3838	221	12	layers	layer	NOUN
cana-3838	221	13	learn	learn	VERB
cana-3838	221	14	to	to	PART
cana-3838	221	15	detect	detect	VERB
cana-3838	221	16	brain	brain	NOUN
cana-3838	221	17	cancers	cancer	NOUN
cana-3838	221	18	.	.	PUNCT
cana-3838	222	1	to	to	PART
cana-3838	222	2	detect	detect	VERB
cana-3838	222	3	and	and	CCONJ
cana-3838	222	4	separate	separate	ADJ
cana-3838	222	5	brain	brain	NOUN
cana-3838	222	6	tumors	tumor	NOUN
cana-3838	222	7	,	,	PUNCT
cana-3838	222	8	a	a	DET
cana-3838	222	9	new	new	ADJ
cana-3838	222	10	set	set	NOUN
cana-3838	222	11	of	of	ADP
cana-3838	222	12	fully	fully	ADV
cana-3838	222	13	connected	connected	ADJ
cana-3838	222	14	layers	layer	NOUN
cana-3838	222	15	takes	take	VERB
cana-3838	222	16	the	the	DET
cana-3838	222	17	place	place	NOUN
cana-3838	222	18	of	of	ADP
cana-3838	222	19	the	the	DET
cana-3838	222	20	resnet50	resnet50	NOUN
cana-3838	222	21	model	model	PROPN
cana-3838	222	22	's	's	PART
cana-3838	222	23	last	last	ADJ
cana-3838	222	24	few	few	ADJ
cana-3838	222	25	levels	level	NOUN
cana-3838	222	26	[	[	X
cana-3838	222	27	17	17	NUM
cana-3838	222	28	]	]	PUNCT
cana-3838	222	29	.	.	PUNCT
cana-3838	223	1	a	a	DET
cana-3838	223	2	cnn	cnn	PROPN
cana-3838	223	3	architecture	architecture	NOUN
cana-3838	223	4	was	be	AUX
cana-3838	223	5	presented	present	VERB
cana-3838	223	6	in	in	ADP
cana-3838	223	7	2014	2014	NUM
cana-3838	223	8	by	by	ADP
cana-3838	223	9	the	the	DET
cana-3838	223	10	visual	visual	ADJ
cana-3838	223	11	geometry	geometry	NOUN
cana-3838	223	12	group	group	NOUN
cana-3838	223	13	(	(	PUNCT
cana-3838	223	14	vgg	vgg	PROPN
cana-3838	223	15	)	)	PUNCT
cana-3838	223	16	at	at	ADP
cana-3838	223	17	oxford	oxford	PROPN
cana-3838	223	18	university	university	PROPN
cana-3838	223	19	.	.	PUNCT
cana-3838	224	1	a	a	DET
cana-3838	224	2	number	number	NOUN
cana-3838	224	3	of	of	ADP
cana-3838	224	4	computer	computer	NOUN
cana-3838	224	5	vision	vision	NOUN
cana-3838	224	6	applications	application	NOUN
cana-3838	224	7	heavily	heavily	ADV
cana-3838	224	8	use	use	VERB
cana-3838	224	9	its	its	PRON
cana-3838	224	10	deep	deep	ADJ
cana-3838	224	11	architecture	architecture	NOUN
cana-3838	224	12	,	,	PUNCT
cana-3838	224	13	including	include	VERB
cana-3838	224	14	image	image	NOUN
cana-3838	224	15	segmentation	segmentation	NOUN
cana-3838	224	16	,	,	PUNCT
cana-3838	224	17	object	object	VERB
cana-3838	224	18	detection	detection	NOUN
cana-3838	224	19	,	,	PUNCT
cana-3838	224	20	and	and	CCONJ
cana-3838	224	21	classification	classification	NOUN
cana-3838	224	22	[	[	X
cana-3838	224	23	15	15	NUM
cana-3838	224	24	]	]	PUNCT
cana-3838	224	25	.	.	PUNCT
cana-3838	225	1	we	we	PRON
cana-3838	225	2	name	name	VERB
cana-3838	225	3	a	a	DET
cana-3838	225	4	cnn	cnn	PROPN
cana-3838	225	5	model	model	NOUN
cana-3838	225	6	with	with	ADP
cana-3838	225	7	sixteen	sixteen	NUM
cana-3838	225	8	layers	layer	NOUN
cana-3838	225	9	vgg	vgg	VERB
cana-3838	225	10	16	16	NUM
cana-3838	225	11	.	.	PUNCT
cana-3838	226	1	one	one	NUM
cana-3838	226	2	of	of	ADP
cana-3838	226	3	the	the	DET
cana-3838	226	4	most	most	ADV
cana-3838	226	5	well	well	ADV
cana-3838	226	6	-	-	PUNCT
cana-3838	226	7	known	know	VERB
cana-3838	226	8	and	and	CCONJ
cana-3838	226	9	effective	effective	ADJ
cana-3838	226	10	models	model	NOUN
cana-3838	226	11	still	still	ADV
cana-3838	226	12	in	in	ADP
cana-3838	226	13	use	use	NOUN
cana-3838	226	14	today	today	NOUN
cana-3838	226	15	is	be	AUX
cana-3838	226	16	this	this	DET
cana-3838	226	17	one	one	NOUN
cana-3838	226	18	.	.	PUNCT
cana-3838	227	1	having	have	VERB
cana-3838	227	2	a	a	DET
cana-3838	227	3	large	large	ADJ
cana-3838	227	4	number	number	NOUN
cana-3838	227	5	of	of	ADP
cana-3838	227	6	parameters	parameter	NOUN
cana-3838	227	7	is	be	AUX
cana-3838	227	8	not	not	PART
cana-3838	227	9	as	as	ADV
cana-3838	227	10	important	important	ADJ
cana-3838	227	11	as	as	ADP
cana-3838	227	12	using	use	VERB
cana-3838	227	13	convnet	convnet	NOUN
cana-3838	227	14	layers	layer	NOUN
cana-3838	227	15	with	with	ADP
cana-3838	227	16	a	a	DET
cana-3838	227	17	3	3	NUM
cana-3838	227	18	×	×	NOUN
cana-3838	227	19	3	3	NUM
cana-3838	227	20	kernel	kernel	NOUN
cana-3838	227	21	size	size	NOUN
cana-3838	227	22	in	in	ADP
cana-3838	227	23	the	the	DET
cana-3838	227	24	vgg	vgg	ADJ
cana-3838	227	25	16	16	NUM
cana-3838	227	26	model	model	NOUN
cana-3838	227	27	architecture	architecture	NOUN
cana-3838	227	28	.	.	PUNCT
cana-3838	228	1	what	what	PRON
cana-3838	228	2	makes	make	VERB
cana-3838	228	3	this	this	DET
cana-3838	228	4	model	model	NOUN
cana-3838	228	5	unique	unique	ADJ
cana-3838	228	6	is	be	AUX
cana-3838	228	7	that	that	SCONJ
cana-3838	228	8	its	its	PRON
cana-3838	228	9	values	value	NOUN
cana-3838	228	10	are	be	AUX
cana-3838	228	11	freely	freely	ADV
cana-3838	228	12	available	available	ADJ
cana-3838	228	13	online	online	ADV
cana-3838	228	14	and	and	CCONJ
cana-3838	228	15	may	may	AUX
cana-3838	228	16	be	be	AUX
cana-3838	228	17	integrated	integrate	VERB
cana-3838	228	18	into	into	ADP
cana-3838	228	19	many	many	ADJ
cana-3838	228	20	systems	system	NOUN
cana-3838	228	21	and	and	CCONJ
cana-3838	228	22	applications	application	NOUN
cana-3838	228	23	.	.	PUNCT
cana-3838	229	1	when	when	SCONJ
cana-3838	229	2	compared	compare	VERB
cana-3838	229	3	to	to	ADP
cana-3838	229	4	other	other	ADJ
cana-3838	229	5	well	well	ADV
cana-3838	229	6	-	-	PUNCT
cana-3838	229	7	established	establish	VERB
cana-3838	229	8	comprehensives	comprehensive	NOUN
cana-3838	229	9	,	,	PUNCT
cana-3838	229	10	it	it	PRON
cana-3838	229	11	stands	stand	VERB
cana-3838	229	12	out	out	ADP
cana-3838	229	13	for	for	ADP
cana-3838	229	14	being	be	AUX
cana-3838	229	15	very	very	ADV
cana-3838	229	16	straightforward	straightforward	ADJ
cana-3838	229	17	to	to	PART
cana-3838	229	18	comprehend	comprehend	VERB
cana-3838	229	19	.	.	PUNCT
cana-3838	230	1	this	this	DET
cana-3838	230	2	model	model	NOUN
cana-3838	230	3	is	be	AUX
cana-3838	230	4	capable	capable	ADJ
cana-3838	230	5	of	of	ADP
cana-3838	230	6	handling	handle	VERB
cana-3838	230	7	input	input	NOUN
cana-3838	230	8	images	image	NOUN
cana-3838	230	9	as	as	ADV
cana-3838	230	10	tiny	tiny	ADJ
cana-3838	230	11	as	as	ADP
cana-3838	230	12	224	224	NUM
cana-3838	230	13	×	×	NOUN
cana-3838	230	14	224	224	NUM
cana-3838	230	15	pixels	pixel	NOUN
cana-3838	230	16	with	with	ADP
cana-3838	230	17	three	three	NUM
cana-3838	230	18	channels	channel	NOUN
cana-3838	230	19	.	.	PUNCT
cana-3838	231	1	optimization	optimization	NOUN
cana-3838	231	2	methods	method	NOUN
cana-3838	231	3	compute	compute	VERB
cana-3838	231	4	the	the	DET
cana-3838	231	5	weighted	weighted	ADJ
cana-3838	231	6	sum	sum	NOUN
cana-3838	231	7	of	of	ADP
cana-3838	231	8	the	the	DET
cana-3838	231	9	input	input	NOUN
cana-3838	231	10	to	to	PART
cana-3838	231	11	ascertain	ascertain	VERB
cana-3838	231	12	whether	whether	SCONJ
cana-3838	231	13	a	a	DET
cana-3838	231	14	neuron	neuron	NOUN
cana-3838	231	15	is	be	AUX
cana-3838	231	16	necessary	necessary	ADJ
cana-3838	231	17	for	for	SCONJ
cana-3838	231	18	a	a	DET
cana-3838	231	19	neural	neural	ADJ
cana-3838	231	20	network	network	NOUN
cana-3838	231	21	to	to	PART
cana-3838	231	22	be	be	AUX
cana-3838	231	23	active	active	ADJ
cana-3838	231	24	.	.	PUNCT
cana-3838	232	1	kernel	kernel	PROPN
cana-3838	232	2	function	function	PROPN
cana-3838	232	3	is	be	AUX
cana-3838	232	4	necessary	necessary	ADJ
cana-3838	232	5	since	since	SCONJ
cana-3838	232	6	it	it	PRON
cana-3838	232	7	induces	induce	VERB
cana-3838	232	8	non	non	ADJ
cana-3838	232	9	-	-	ADJ
cana-3838	232	10	linearity	linearity	NOUN
cana-3838	232	11	into	into	ADP
cana-3838	232	12	the	the	DET
cana-3838	232	13	output	output	NOUN
cana-3838	232	14	neuron	neuron	NOUN
cana-3838	232	15	.	.	PUNCT
cana-3838	233	1	the	the	DET
cana-3838	233	2	training	training	NOUN
cana-3838	233	3	procedure	procedure	NOUN
cana-3838	233	4	,	,	PUNCT
cana-3838	233	5	bias	bias	NOUN
cana-3838	233	6	,	,	PUNCT
cana-3838	233	7	and	and	CCONJ
cana-3838	233	8	weight	weight	NOUN
cana-3838	233	9	all	all	DET
cana-3838	233	10	function	function	VERB
cana-3838	233	11	together	together	ADV
cana-3838	233	12	in	in	ADP
cana-3838	233	13	a	a	DET
cana-3838	233	14	neural	neural	ADJ
cana-3838	233	15	network	network	NOUN
cana-3838	233	16	.	.	PUNCT
cana-3838	234	1	inaccurate	inaccurate	ADJ
cana-3838	234	2	output	output	NOUN
cana-3838	234	3	causes	cause	VERB
cana-3838	234	4	changes	change	NOUN
cana-3838	234	5	to	to	ADP
cana-3838	234	6	the	the	DET
cana-3838	234	7	neuronal	neuronal	ADJ
cana-3838	234	8	connection	connection	NOUN
cana-3838	234	9	weights	weight	NOUN
cana-3838	234	10	.	.	PUNCT
cana-3838	235	1	with	with	ADP
cana-3838	235	2	the	the	DET
cana-3838	235	3	use	use	NOUN
cana-3838	235	4	of	of	ADP
cana-3838	235	5	activation	activation	NOUN
cana-3838	235	6	functions	function	NOUN
cana-3838	235	7	and	and	CCONJ
cana-3838	235	8	input	input	NOUN
cana-3838	235	9	layers	layer	NOUN
cana-3838	235	10	that	that	PRON
cana-3838	235	11	give	give	VERB
cana-3838	235	12	non	non	ADJ
cana-3838	235	13	-	-	ADJ
cana-3838	235	14	linear	linear	ADJ
cana-3838	235	15	input	input	NOUN
cana-3838	235	16	,	,	PUNCT
cana-3838	235	17	a	a	DET
cana-3838	235	18	neural	neural	ADJ
cana-3838	235	19	network	network	NOUN
cana-3838	235	20	may	may	AUX
cana-3838	235	21	learn	learn	VERB
cana-3838	235	22	and	and	CCONJ
cana-3838	235	23	do	do	VERB
cana-3838	235	24	complex	complex	ADJ
cana-3838	235	25	tasks	task	NOUN
cana-3838	235	26	[	[	X
cana-3838	235	27	12	12	NUM
cana-3838	235	28	]	]	PUNCT
cana-3838	235	29	.	.	PUNCT
cana-3838	236	1	figure	figure	NOUN
cana-3838	236	2	3	3	NUM
cana-3838	236	3	shows	show	VERB
cana-3838	236	4	a	a	DET
cana-3838	236	5	typical	typical	ADJ
cana-3838	236	6	architecture	architecture	NOUN
cana-3838	236	7	of	of	ADP
cana-3838	236	8	a	a	DET
cana-3838	236	9	vgg	vgg	ADJ
cana-3838	236	10	16	16	NUM
cana-3838	236	11	network	network	NOUN
cana-3838	236	12	.	.	PUNCT
cana-3838	237	1	figure	figure	NOUN
cana-3838	237	2	3	3	NUM
cana-3838	237	3	.	.	PUNCT
cana-3838	238	1	a	a	DET
cana-3838	238	2	standard	standard	ADJ
cana-3838	238	3	vgg	vgg	ADJ
cana-3838	238	4	16	16	NUM
cana-3838	238	5	network	network	NOUN
cana-3838	238	6	architecture	architecture	NOUN
cana-3838	238	7	dcnn	dcnn	ADJ
cana-3838	238	8	models	model	NOUN
cana-3838	238	9	include	include	VERB
cana-3838	238	10	resnet	resnet	NOUN
cana-3838	238	11	,	,	PUNCT
cana-3838	238	12	also	also	ADV
cana-3838	238	13	known	know	VERB
cana-3838	238	14	as	as	ADP
cana-3838	238	15	residual	residual	ADJ
cana-3838	238	16	network	network	NOUN
cana-3838	238	17	.	.	PUNCT
cana-3838	239	1	it	it	PRON
cana-3838	239	2	improves	improve	VERB
cana-3838	239	3	performance	performance	NOUN
cana-3838	239	4	in	in	ADP
cana-3838	239	5	a	a	DET
cana-3838	239	6	number	number	NOUN
cana-3838	239	7	of	of	ADP
cana-3838	239	8	areas	area	NOUN
cana-3838	239	9	by	by	ADP
cana-3838	239	10	employing	employ	VERB
cana-3838	239	11	transfer	transfer	NOUN
cana-3838	239	12	learning	learning	NOUN
cana-3838	239	13	,	,	PUNCT
cana-3838	239	14	which	which	PRON
cana-3838	239	15	leads	lead	VERB
cana-3838	239	16	to	to	ADP
cana-3838	239	17	high	high	ADJ
cana-3838	239	18	classification	classification	NOUN
cana-3838	239	19	results	result	NOUN
cana-3838	239	20	.	.	PUNCT
cana-3838	240	1	in	in	ADP
cana-3838	240	2	2015	2015	NUM
cana-3838	240	3	,	,	PUNCT
cana-3838	240	4	resnet	resnet	NOUN
cana-3838	240	5	won	win	VERB
cana-3838	240	6	first	first	ADJ
cana-3838	240	7	place	place	NOUN
cana-3838	240	8	in	in	ADP
cana-3838	240	9	the	the	DET
cana-3838	240	10	common	common	ADJ
cana-3838	240	11	objects	object	NOUN
cana-3838	240	12	in	in	ADP
cana-3838	240	13	context	context	NOUN
cana-3838	240	14	(	(	PUNCT
cana-3838	240	15	coco	coco	PROPN
cana-3838	240	16	)	)	PUNCT
cana-3838	240	17	and	and	CCONJ
cana-3838	240	18	imagenet	imagenet	VERB
cana-3838	240	19	large	large	ADJ
cana-3838	240	20	scale	scale	NOUN
cana-3838	240	21	visual	visual	ADJ
cana-3838	240	22	recognition	recognition	NOUN
cana-3838	240	23	challenge	challenge	NOUN
cana-3838	240	24	(	(	PUNCT
cana-3838	240	25	ilsvrc	ilsvrc	PROPN
cana-3838	240	26	)	)	PUNCT
cana-3838	240	27	.	.	PUNCT
cana-3838	241	1	when	when	SCONJ
cana-3838	241	2	a	a	DET
cana-3838	241	3	deep	deep	ADJ
cana-3838	241	4	network	network	NOUN
cana-3838	241	5	's	's	PART
cana-3838	241	6	layer	layer	NOUN
cana-3838	241	7	count	count	NOUN
cana-3838	241	8	increases	increase	NOUN
cana-3838	241	9	,	,	PUNCT
cana-3838	241	10	a	a	DET
cana-3838	241	11	degradation	degradation	NOUN
cana-3838	241	12	issue	issue	NOUN
cana-3838	241	13	arises	arise	VERB
cana-3838	241	14	.	.	PUNCT
cana-3838	242	1	it	it	PRON
cana-3838	242	2	is	be	AUX
cana-3838	242	3	not	not	PART
cana-3838	242	4	possible	possible	ADJ
cana-3838	242	5	to	to	PART
cana-3838	242	6	properly	properly	ADV
cana-3838	242	7	update	update	VERB
cana-3838	242	8	the	the	DET
cana-3838	242	9	layer	layer	NOUN
cana-3838	242	10	's	's	PART
cana-3838	242	11	weights	weight	NOUN
cana-3838	242	12	to	to	ADP
cana-3838	242	13	the	the	DET
cana-3838	242	14	following	follow	VERB
cana-3838	242	15	layer	layer	NOUN
cana-3838	242	16	.	.	PUNCT
cana-3838	243	1	using	use	VERB
cana-3838	243	2	short	short	ADJ
cana-3838	243	3	connections	connection	NOUN
cana-3838	243	4	in	in	ADP
cana-3838	243	5	parallel	parallel	NOUN
cana-3838	243	6	with	with	ADP
cana-3838	243	7	the	the	DET
cana-3838	243	8	standard	standard	ADJ
cana-3838	243	9	convolutional	convolutional	ADJ
cana-3838	243	10	layers	layer	NOUN
cana-3838	243	11	,	,	PUNCT
cana-3838	243	12	resnet	resnet	NOUN
cana-3838	243	13	eliminates	eliminate	VERB
cana-3838	243	14	this	this	DET
cana-3838	243	15	degradation	degradation	NOUN
cana-3838	243	16	issue	issue	NOUN
cana-3838	243	17	.	.	PUNCT
cana-3838	244	1	in	in	ADP
cana-3838	244	2	figure	figure	NOUN
cana-3838	244	3	4	4	NUM
cana-3838	244	4	,	,	PUNCT
cana-3838	244	5	we	we	PRON
cana-3838	244	6	can	can	AUX
cana-3838	244	7	see	see	VERB
cana-3838	244	8	the	the	DET
cana-3838	244	9	lone	lone	ADJ
cana-3838	244	10	remaining	remain	VERB
cana-3838	244	11	construction	construction	NOUN
cana-3838	244	12	component	component	NOUN
cana-3838	244	13	that	that	PRON
cana-3838	244	14	has	have	VERB
cana-3838	244	15	a	a	DET
cana-3838	244	16	short	short	ADJ
cana-3838	244	17	link	link	NOUN
cana-3838	244	18	.	.	PUNCT
cana-3838	245	1	the	the	DET
cana-3838	245	2	equation	equation	NOUN
cana-3838	245	3	h(x	h(x	PROPN
cana-3838	245	4	)	)	PUNCT
cana-3838	245	5	that	that	PRON
cana-3838	245	6	defines	define	VERB
cana-3838	245	7	the	the	DET
cana-3838	245	8	residual	residual	ADJ
cana-3838	245	9	block	block	NOUN
cana-3838	245	10	's	's	PART
cana-3838	245	11	output	output	NOUN
cana-3838	245	12	is	be	AUX
cana-3838	245	13	as	as	SCONJ
cana-3838	245	14	follows	follow	VERB
cana-3838	245	15	:	:	PUNCT
cana-3838	245	16	communications	communication	NOUN
cana-3838	245	17	on	on	ADP
cana-3838	245	18	applied	apply	VERB
cana-3838	245	19	nonlinear	nonlinear	ADJ
cana-3838	245	20	analysis	analysis	NOUN
cana-3838	245	21	issn	issn	NOUN
cana-3838	245	22	:	:	PUNCT
cana-3838	245	23	1074	1074	NUM
cana-3838	245	24	-	-	PUNCT
cana-3838	245	25	133x	133x	NUM
cana-3838	245	26	vol	vol	NOUN
cana-3838	245	27	32	32	NUM
cana-3838	246	1	no	no	NOUN
cana-3838	246	2	.	.	PUNCT
cana-3838	247	1	9s	9s	NUM
cana-3838	247	2	(	(	PUNCT
cana-3838	247	3	2025	2025	NUM
cana-3838	247	4	)	)	PUNCT
cana-3838	247	5	72	72	NUM
cana-3838	248	1	https://internationalpubls.com	https://internationalpubls.com	X
cana-3838	248	2	(	(	PUNCT
cana-3838	248	3	𝑥	𝑥	NOUN
cana-3838	248	4	)	)	PUNCT
cana-3838	248	5	=	=	SYM
cana-3838	248	6	𝐹(𝑥	𝐹(𝑥	X
cana-3838	248	7	)	)	PUNCT
cana-3838	248	8	+	+	CCONJ
cana-3838	248	9	𝑥	𝑥	X
cana-3838	248	10	(	(	PUNCT
cana-3838	248	11	2	2	NUM
cana-3838	248	12	)	)	PUNCT
cana-3838	248	13	the	the	DET
cana-3838	248	14	stocked	stock	VERB
cana-3838	248	15	nonlinear	nonlinear	ADJ
cana-3838	248	16	weight	weight	NOUN
cana-3838	248	17	layer	layer	NOUN
cana-3838	248	18	f(x	f(x	PROPN
cana-3838	248	19	)	)	PUNCT
cana-3838	248	20	is	be	AUX
cana-3838	248	21	given	give	VERB
cana-3838	248	22	as	as	ADP
cana-3838	248	23	:	:	PUNCT
cana-3838	248	24	(	(	PUNCT
cana-3838	248	25	𝑥	𝑥	NOUN
cana-3838	248	26	)	)	PUNCT
cana-3838	248	27	=	=	SYM
cana-3838	248	28	𝐻(𝑥	𝐻(𝑥	NUM
cana-3838	248	29	)	)	PUNCT
cana-3838	248	30	–	–	PUNCT
cana-3838	248	31	𝑥	𝑥	X
cana-3838	248	32	(	(	PUNCT
cana-3838	248	33	3	3	NUM
cana-3838	248	34	)	)	PUNCT
cana-3838	248	35	figure4	figure4	NOUN
cana-3838	248	36	.	.	PUNCT
cana-3838	249	1	residual	residual	ADJ
cana-3838	249	2	network	network	NOUN
cana-3838	249	3	:	:	PUNCT
cana-3838	249	4	a	a	DET
cana-3838	249	5	building	building	NOUN
cana-3838	249	6	block	block	NOUN
cana-3838	249	7	.	.	PUNCT
cana-3838	250	1	the	the	DET
cana-3838	250	2	categorization	categorization	NOUN
cana-3838	250	3	of	of	ADP
cana-3838	250	4	brain	brain	NOUN
cana-3838	250	5	tumors	tumor	NOUN
cana-3838	250	6	is	be	AUX
cana-3838	250	7	carried	carry	VERB
cana-3838	250	8	out	out	ADP
cana-3838	250	9	in	in	ADP
cana-3838	250	10	this	this	DET
cana-3838	250	11	study	study	NOUN
cana-3838	250	12	using	use	VERB
cana-3838	250	13	the	the	DET
cana-3838	250	14	resnet50	resnet50	NOUN
cana-3838	250	15	model	model	NOUN
cana-3838	250	16	.	.	PUNCT
cana-3838	251	1	a	a	DET
cana-3838	251	2	7×7	7×7	NUM
cana-3838	251	3	convolution	convolution	NOUN
cana-3838	251	4	layer	layer	NOUN
cana-3838	251	5	,	,	PUNCT
cana-3838	251	6	a	a	DET
cana-3838	251	7	3×3	3×3	NUM
cana-3838	251	8	max	max	NOUN
cana-3838	251	9	-	-	PUNCT
cana-3838	251	10	pooling	pool	VERB
cana-3838	251	11	layer	layer	NOUN
cana-3838	251	12	,	,	PUNCT
cana-3838	251	13	16	16	NUM
cana-3838	251	14	residual	residual	ADJ
cana-3838	251	15	building	building	NOUN
cana-3838	251	16	blocks	block	NOUN
cana-3838	251	17	,	,	PUNCT
cana-3838	251	18	a	a	DET
cana-3838	251	19	7×7	7×7	NUM
cana-3838	251	20	average	average	ADJ
cana-3838	251	21	pooling	pool	VERB
cana-3838	251	22	layer	layer	NOUN
cana-3838	251	23	,	,	PUNCT
cana-3838	251	24	a	a	DET
cana-3838	251	25	new	new	ADJ
cana-3838	251	26	fully	fully	ADV
cana-3838	251	27	-	-	PUNCT
cana-3838	251	28	connected	connect	VERB
cana-3838	251	29	layer	layer	NOUN
cana-3838	251	30	,	,	PUNCT
cana-3838	251	31	and	and	CCONJ
cana-3838	251	32	segmentation	segmentation	NOUN
cana-3838	251	33	at	at	ADP
cana-3838	251	34	the	the	DET
cana-3838	251	35	final	final	ADJ
cana-3838	251	36	layer	layer	NOUN
cana-3838	251	37	make	make	VERB
cana-3838	251	38	up	up	ADP
cana-3838	251	39	the	the	DET
cana-3838	251	40	modified	modified	ADJ
cana-3838	251	41	resnet50	resnet50	NOUN
cana-3838	251	42	that	that	PRON
cana-3838	251	43	utilizes	utilize	VERB
cana-3838	251	44	transfer	transfer	NOUN
cana-3838	251	45	learning	learning	NOUN
cana-3838	251	46	,	,	PUNCT
cana-3838	251	47	as	as	SCONJ
cana-3838	251	48	shown	show	VERB
cana-3838	251	49	in	in	ADP
cana-3838	251	50	figure	figure	NOUN
cana-3838	251	51	5	5	NUM
cana-3838	251	52	.	.	PUNCT
cana-3838	252	1	for	for	ADP
cana-3838	252	2	this	this	DET
cana-3838	252	3	network	network	NOUN
cana-3838	252	4	,	,	PUNCT
cana-3838	252	5	224	224	NUM
cana-3838	252	6	x	x	SYM
cana-3838	252	7	224	224	NUM
cana-3838	252	8	x	x	SYM
cana-3838	252	9	3	3	NUM
cana-3838	252	10	is	be	AUX
cana-3838	252	11	the	the	DET
cana-3838	252	12	input	input	NOUN
cana-3838	252	13	image	image	NOUN
cana-3838	252	14	size	size	NOUN
cana-3838	252	15	.	.	PUNCT
cana-3838	253	1	figure	figure	NOUN
cana-3838	253	2	5	5	NUM
cana-3838	253	3	.	.	NOUN
cana-3838	253	4	resnet50	resnet50	NOUN
cana-3838	253	5	architecture	architecture	NOUN
cana-3838	253	6	there	there	PRON
cana-3838	253	7	were	be	VERB
cana-3838	253	8	few	few	ADJ
cana-3838	253	9	blocks	block	NOUN
cana-3838	253	10	cut	cut	VERB
cana-3838	253	11	out	out	ADP
cana-3838	253	12	of	of	ADP
cana-3838	253	13	the	the	DET
cana-3838	253	14	current	current	ADJ
cana-3838	253	15	vgg-16	vgg-16	NOUN
cana-3838	253	16	model	model	NOUN
cana-3838	253	17	at	at	ADP
cana-3838	253	18	the	the	DET
cana-3838	253	19	encoder	encoder	NOUN
cana-3838	253	20	area	area	NOUN
cana-3838	253	21	.	.	PUNCT
cana-3838	254	1	the	the	DET
cana-3838	254	2	pre	pre	ADJ
cana-3838	254	3	trained	train	VERB
cana-3838	254	4	model	model	NOUN
cana-3838	254	5	's	's	PART
cana-3838	254	6	first	first	ADJ
cana-3838	254	7	layers	layer	NOUN
cana-3838	254	8	were	be	AUX
cana-3838	254	9	removed	remove	VERB
cana-3838	254	10	.	.	PUNCT
cana-3838	255	1	basic	basic	ADJ
cana-3838	255	2	characteristics	characteristic	NOUN
cana-3838	255	3	,	,	PUNCT
cana-3838	255	4	such	such	ADJ
cana-3838	255	5	as	as	ADP
cana-3838	255	6	horizontal	horizontal	ADJ
cana-3838	255	7	and	and	CCONJ
cana-3838	255	8	vertical	vertical	ADJ
cana-3838	255	9	edges	edge	NOUN
cana-3838	255	10	,	,	PUNCT
cana-3838	255	11	are	be	AUX
cana-3838	255	12	detected	detect	VERB
cana-3838	255	13	by	by	ADP
cana-3838	255	14	the	the	DET
cana-3838	255	15	earliest	early	ADJ
cana-3838	255	16	layers	layer	NOUN
cana-3838	255	17	of	of	ADP
cana-3838	255	18	the	the	DET
cana-3838	255	19	model	model	NOUN
cana-3838	255	20	.	.	PUNCT
cana-3838	256	1	the	the	DET
cana-3838	256	2	further	far	ADV
cana-3838	256	3	you	you	PRON
cana-3838	256	4	go	go	VERB
cana-3838	256	5	into	into	ADP
cana-3838	256	6	the	the	DET
cana-3838	256	7	network	network	NOUN
cana-3838	256	8	,	,	PUNCT
cana-3838	256	9	the	the	DET
cana-3838	256	10	more	more	ADV
cana-3838	256	11	complicated	complicated	ADJ
cana-3838	256	12	the	the	DET
cana-3838	256	13	model	model	NOUN
cana-3838	256	14	becomes	become	VERB
cana-3838	256	15	,	,	PUNCT
cana-3838	256	16	which	which	PRON
cana-3838	256	17	makes	make	VERB
cana-3838	256	18	feature	feature	NOUN
cana-3838	256	19	extraction	extraction	NOUN
cana-3838	256	20	much	much	ADV
cana-3838	256	21	easier	easy	ADJ
cana-3838	256	22	.	.	PUNCT
cana-3838	257	1	for	for	ADP
cana-3838	257	2	layers	layer	NOUN
cana-3838	257	3	that	that	PRON
cana-3838	257	4	are	be	AUX
cana-3838	257	5	not	not	PART
cana-3838	257	6	sequential	sequential	ADJ
cana-3838	257	7	,	,	PUNCT
cana-3838	257	8	concatenation	concatenation	NOUN
cana-3838	257	9	skip	skip	ADJ
cana-3838	257	10	connections	connection	NOUN
cana-3838	257	11	are	be	AUX
cana-3838	257	12	used	use	VERB
cana-3838	257	13	.	.	PUNCT
cana-3838	258	1	dense	dense	ADJ
cana-3838	258	2	blocks	block	NOUN
cana-3838	258	3	provide	provide	VERB
cana-3838	258	4	an	an	DET
cana-3838	258	5	extra	extra	ADJ
cana-3838	258	6	benefit	benefit	NOUN
cana-3838	258	7	:	:	PUNCT
cana-3838	258	8	access	access	NOUN
cana-3838	258	9	to	to	ADP
cana-3838	258	10	a	a	DET
cana-3838	258	11	massive	massive	ADJ
cana-3838	258	12	quantity	quantity	NOUN
cana-3838	258	13	of	of	ADP
cana-3838	258	14	feature	feature	NOUN
cana-3838	258	15	channels	channel	NOUN
cana-3838	258	16	in	in	ADP
cana-3838	258	17	the	the	DET
cana-3838	258	18	network	network	NOUN
cana-3838	258	19	's	's	PART
cana-3838	258	20	final	final	ADJ
cana-3838	258	21	layers	layer	NOUN
cana-3838	258	22	,	,	PUNCT
cana-3838	258	23	which	which	PRON
cana-3838	258	24	allows	allow	VERB
cana-3838	258	25	for	for	ADP
cana-3838	258	26	more	more	ADJ
cana-3838	258	27	compact	compact	ADJ
cana-3838	258	28	models	model	NOUN
cana-3838	258	29	and	and	CCONJ
cana-3838	258	30	drastically	drastically	ADV
cana-3838	258	31	increased	increase	VERB
cana-3838	258	32	feature	feature	NOUN
cana-3838	258	33	re	re	NOUN
cana-3838	258	34	-	-	NOUN
cana-3838	258	35	usability	usability	NOUN
cana-3838	258	36	.	.	PUNCT
cana-3838	259	1	to	to	PART
cana-3838	259	2	predict	predict	VERB
cana-3838	259	3	what	what	PRON
cana-3838	259	4	will	will	AUX
cana-3838	259	5	be	be	AUX
cana-3838	259	6	in	in	ADP
cana-3838	259	7	the	the	DET
cana-3838	259	8	output	output	NOUN
cana-3838	259	9	region	region	NOUN
cana-3838	259	10	,	,	PUNCT
cana-3838	259	11	the	the	DET
cana-3838	259	12	model	model	NOUN
cana-3838	259	13	looks	look	VERB
cana-3838	259	14	at	at	ADP
cana-3838	259	15	the	the	DET
cana-3838	259	16	segmentation	segmentation	NOUN
cana-3838	259	17	map	map	NOUN
cana-3838	259	18	of	of	ADP
cana-3838	259	19	the	the	DET
cana-3838	259	20	output	output	NOUN
cana-3838	259	21	[	[	X
cana-3838	259	22	23	23	NUM
cana-3838	259	23	]	]	PUNCT
cana-3838	259	24	.	.	PUNCT
cana-3838	260	1	the	the	DET
cana-3838	260	2	goal	goal	NOUN
cana-3838	260	3	is	be	AUX
cana-3838	260	4	to	to	PART
cana-3838	260	5	train	train	VERB
cana-3838	260	6	a	a	DET
cana-3838	260	7	resnet50	resnet50	NOUN
cana-3838	260	8	model	model	NOUN
cana-3838	260	9	using	use	VERB
cana-3838	260	10	vgg16	vgg16	NOUN
cana-3838	260	11	to	to	PART
cana-3838	260	12	differentiate	differentiate	VERB
cana-3838	260	13	between	between	ADP
cana-3838	260	14	normal	normal	ADJ
cana-3838	260	15	and	and	CCONJ
cana-3838	260	16	abnormal	abnormal	ADJ
cana-3838	260	17	brain	brain	NOUN
cana-3838	260	18	mri	mri	NOUN
cana-3838	260	19	images	image	NOUN
cana-3838	260	20	.	.	PUNCT
cana-3838	261	1	the	the	DET
cana-3838	261	2	pre	pre	ADJ
cana-3838	261	3	-	-	ADJ
cana-3838	261	4	trained	train	VERB
cana-3838	261	5	resnet50	resnet50	NOUN
cana-3838	261	6	model	model	NOUN
cana-3838	261	7	provides	provide	VERB
cana-3838	261	8	a	a	DET
cana-3838	261	9	solid	solid	ADJ
cana-3838	261	10	foundation	foundation	NOUN
cana-3838	261	11	for	for	ADP
cana-3838	261	12	brain	brain	NOUN
cana-3838	261	13	tumor	tumor	NOUN
cana-3838	261	14	diagnosis	diagnosis	NOUN
cana-3838	261	15	,	,	PUNCT
cana-3838	261	16	and	and	CCONJ
cana-3838	261	17	it	it	PRON
cana-3838	261	18	may	may	AUX
cana-3838	261	19	be	be	AUX
cana-3838	261	20	fine	fine	ADV
cana-3838	261	21	-	-	PUNCT
cana-3838	261	22	tuned	tune	VERB
cana-3838	261	23	using	use	VERB
cana-3838	261	24	a	a	DET
cana-3838	261	25	new	new	ADJ
cana-3838	261	26	dataset	dataset	NOUN
cana-3838	261	27	of	of	ADP
cana-3838	261	28	mri	mri	NOUN
cana-3838	261	29	images	image	NOUN
cana-3838	261	30	to	to	PART
cana-3838	261	31	make	make	VERB
cana-3838	261	32	it	it	PRON
cana-3838	261	33	suit	suit	VERB
cana-3838	261	34	the	the	DET
cana-3838	261	35	task	task	NOUN
cana-3838	261	36	at	at	ADP
cana-3838	261	37	hand	hand	NOUN
cana-3838	261	38	.	.	PUNCT
cana-3838	262	1	this	this	DET
cana-3838	262	2	approach	approach	NOUN
cana-3838	262	3	has	have	AUX
cana-3838	262	4	effectively	effectively	ADV
cana-3838	262	5	used	use	VERB
cana-3838	262	6	magnetic	magnetic	ADJ
cana-3838	262	7	resonance	resonance	NOUN
cana-3838	262	8	imaging	imaging	NOUN
cana-3838	262	9	(	(	PUNCT
cana-3838	262	10	mris	mris	PROPN
cana-3838	262	11	)	)	PUNCT
cana-3838	262	12	to	to	PART
cana-3838	262	13	accurately	accurately	ADV
cana-3838	262	14	detect	detect	VERB
cana-3838	262	15	and	and	CCONJ
cana-3838	262	16	separate	separate	ADJ
cana-3838	262	17	bts	bt	NOUN
cana-3838	262	18	.	.	PUNCT
cana-3838	263	1	communications	communication	NOUN
cana-3838	263	2	on	on	ADP
cana-3838	263	3	applied	apply	VERB
cana-3838	263	4	nonlinear	nonlinear	ADJ
cana-3838	263	5	analysis	analysis	NOUN
cana-3838	263	6	issn	issn	NOUN
cana-3838	263	7	:	:	PUNCT
cana-3838	263	8	1074	1074	NUM
cana-3838	263	9	-	-	PUNCT
cana-3838	263	10	133x	133x	NUM
cana-3838	263	11	vol	vol	NOUN
cana-3838	263	12	32	32	NUM
cana-3838	263	13	no	no	NOUN
cana-3838	263	14	.	.	PUNCT
cana-3838	264	1	9s	9s	NUM
cana-3838	264	2	(	(	PUNCT
cana-3838	264	3	2025	2025	NUM
cana-3838	264	4	)	)	PUNCT
cana-3838	264	5	73	73	NUM
cana-3838	265	1	https://internationalpubls.com	https://internationalpubls.com	X
cana-3838	265	2	algorithm1	algorithm1	PROPN
cana-3838	265	3	.	.	PROPN
cana-3838	265	4	vgg16+resnet50	vgg16+resnet50	PROPN
cana-3838	265	5	algorithm	algorithm	PROPN
cana-3838	265	6	v.	v.	ADP
cana-3838	265	7	results	result	VERB
cana-3838	265	8	the	the	DET
cana-3838	265	9	capacity	capacity	NOUN
cana-3838	265	10	to	to	PART
cana-3838	265	11	accurately	accurately	ADV
cana-3838	265	12	distinguish	distinguish	VERB
cana-3838	265	13	between	between	ADP
cana-3838	265	14	the	the	DET
cana-3838	265	15	various	various	ADJ
cana-3838	265	16	forms	form	NOUN
cana-3838	265	17	of	of	ADP
cana-3838	265	18	brain	brain	NOUN
cana-3838	265	19	tumors	tumor	NOUN
cana-3838	265	20	is	be	AUX
cana-3838	265	21	dependent	dependent	ADJ
cana-3838	265	22	on	on	ADP
cana-3838	265	23	accuracy	accuracy	NOUN
cana-3838	265	24	.	.	PUNCT
cana-3838	266	1	the	the	DET
cana-3838	266	2	following	follow	VERB
cana-3838	266	3	relations	relation	NOUN
cana-3838	266	4	are	be	AUX
cana-3838	266	5	used	use	VERB
cana-3838	266	6	to	to	PART
cana-3838	266	7	determine	determine	VERB
cana-3838	266	8	the	the	DET
cana-3838	266	9	fraction	fraction	NOUN
cana-3838	266	10	of	of	ADP
cana-3838	266	11	analyzed	analyze	VERB
cana-3838	266	12	examples	example	NOUN
cana-3838	266	13	with	with	ADP
cana-3838	266	14	true	true	ADJ
cana-3838	266	15	positives	positive	NOUN
cana-3838	266	16	and	and	CCONJ
cana-3838	266	17	true	true	ADJ
cana-3838	266	18	negatives	negative	NOUN
cana-3838	266	19	,	,	PUNCT
cana-3838	266	20	which	which	PRON
cana-3838	266	21	allows	allow	VERB
cana-3838	266	22	us	we	PRON
cana-3838	266	23	to	to	PART
cana-3838	266	24	quantify	quantify	VERB
cana-3838	266	25	the	the	DET
cana-3838	266	26	test	test	NOUN
cana-3838	266	27	's	's	PART
cana-3838	266	28	accuracy	accuracy	NOUN
cana-3838	266	29	:	:	PUNCT
cana-3838	267	1	𝐴𝑐𝑐𝑢𝑟𝑎𝑐𝑦	𝐴𝑐𝑐𝑢𝑟𝑎𝑐𝑦	PROPN
cana-3838	267	2	=	=	PROPN
cana-3838	268	1	tp	tp	ADP
cana-3838	268	2	+	+	NUM
cana-3838	268	3	tn	tn	NOUN
cana-3838	268	4	tp	tp	NOUN
cana-3838	268	5	+	+	CCONJ
cana-3838	268	6	fp	fp	PROPN
cana-3838	268	7	+	+	NUM
cana-3838	268	8	tn	tn	PROPN
cana-3838	269	1	+	+	CCONJ
cana-3838	269	2	fn	fn	PROPN
cana-3838	269	3	(	(	PUNCT
cana-3838	269	4	3	3	NUM
cana-3838	269	5	)	)	PUNCT
cana-3838	269	6	𝑅𝑒𝑐𝑎𝑙𝑙	𝑅𝑒𝑐𝑎𝑙𝑙	PROPN
cana-3838	269	7	=	=	SYM
cana-3838	269	8	𝑇𝑃/𝑇𝑃	𝑇𝑃/𝑇𝑃	X
cana-3838	269	9	+	+	X
cana-3838	269	10	𝐹𝑁	𝐹𝑁	PROPN
cana-3838	269	11	(	(	PUNCT
cana-3838	269	12	4	4	NUM
cana-3838	269	13	)	)	PUNCT
cana-3838	269	14	the	the	DET
cana-3838	269	15	capacity	capacity	NOUN
cana-3838	269	16	of	of	ADP
cana-3838	269	17	the	the	DET
cana-3838	269	18	model	model	NOUN
cana-3838	269	19	to	to	PART
cana-3838	269	20	correctly	correctly	ADV
cana-3838	269	21	identify	identify	VERB
cana-3838	269	22	the	the	DET
cana-3838	269	23	specific	specific	ADJ
cana-3838	269	24	kind	kind	NOUN
cana-3838	269	25	of	of	ADP
cana-3838	269	26	brain	brain	NOUN
cana-3838	269	27	tumor	tumor	NOUN
cana-3838	269	28	is	be	AUX
cana-3838	269	29	called	call	VERB
cana-3838	269	30	specificity	specificity	NOUN
cana-3838	269	31	,	,	PUNCT
cana-3838	269	32	and	and	CCONJ
cana-3838	269	33	it	it	PRON
cana-3838	269	34	is	be	AUX
cana-3838	269	35	calculated	calculate	VERB
cana-3838	269	36	as	as	ADP
cana-3838	269	37	:	:	PUNCT
cana-3838	269	38	𝑆𝑝𝑒𝑐𝑖𝑓𝑖𝑐𝑖𝑡𝑦	𝑆𝑝𝑒𝑐𝑖𝑓𝑖𝑐𝑖𝑡𝑦	PROPN
cana-3838	269	39	=	=	SYM
cana-3838	269	40	𝑇𝑁/𝑇𝑁	𝑇𝑁/𝑇𝑁	PUNCT
cana-3838	270	1	+	+	CCONJ
cana-3838	270	2	𝐹𝑃	𝐹𝑃	NOUN
cana-3838	270	3	(	(	PUNCT
cana-3838	270	4	5	5	X
cana-3838	270	5	)	)	PUNCT
cana-3838	270	6	it	it	PRON
cana-3838	270	7	is	be	AUX
cana-3838	270	8	possible	possible	ADJ
cana-3838	270	9	to	to	PART
cana-3838	270	10	calculate	calculate	VERB
cana-3838	270	11	precision	precision	NOUN
cana-3838	270	12	,	,	PUNCT
cana-3838	270	13	the	the	DET
cana-3838	270	14	genuine	genuine	ADJ
cana-3838	270	15	positive	positive	ADJ
cana-3838	270	16	measure	measure	NOUN
cana-3838	270	17	,	,	PUNCT
cana-3838	270	18	using	use	VERB
cana-3838	270	19	the	the	DET
cana-3838	270	20	following	follow	VERB
cana-3838	270	21	relation	relation	NOUN
cana-3838	270	22	:	:	PUNCT
cana-3838	271	1	𝑃𝑟𝑒𝑐𝑖𝑠𝑖𝑜𝑛	𝑃𝑟𝑒𝑐𝑖𝑠𝑖𝑜𝑛	PROPN
cana-3838	271	2	=	=	SYM
cana-3838	271	3	t	t	PROPN
cana-3838	271	4	p	p	X
cana-3838	271	5	t	t	PROPN
cana-3838	271	6	p	p	X
cana-3838	271	7	+	+	CCONJ
cana-3838	271	8	fp	fp	ADJ
cana-3838	271	9	v.conclusion	v.conclusion	NOUN
cana-3838	271	10	(	(	PUNCT
cana-3838	271	11	6	6	NUM
cana-3838	271	12	)	)	PUNCT
cana-3838	271	13	1	1	NUM
cana-3838	271	14	.	.	PUNCT
cana-3838	271	15	starts	start	VERB
cana-3838	271	16	2	2	NUM
cana-3838	271	17	.	.	PUNCT
cana-3838	271	18	loading	load	VERB
cana-3838	271	19	the	the	DET
cana-3838	271	20	dataset	dataset	NOUN
cana-3838	271	21	of	of	ADP
cana-3838	271	22	brain	brain	NOUN
cana-3838	271	23	image	image	NOUN
cana-3838	271	24	3	3	NUM
cana-3838	271	25	.	.	PUNCT
cana-3838	271	26	pre	pre	ADJ
cana-3838	271	27	-	-	ADJ
cana-3838	271	28	processing	processing	ADJ
cana-3838	271	29	histogram	histogram	NOUN
cana-3838	271	30	equalization	equalization	NOUN
cana-3838	271	31	4	4	NUM
cana-3838	271	32	.	.	PUNCT
cana-3838	272	1	i	i	PRON
cana-3838	272	2	=	=	SYM
cana-3838	272	3	imread("gfg.jfif	imread("gfg.jfif	PROPN
cana-3838	272	4	"	"	PUNCT
cana-3838	272	5	)	)	PUNCT
cana-3838	272	6	;	;	PUNCT
cana-3838	272	7	5	5	X
cana-3838	272	8	.	.	X
cana-3838	272	9	figure	figure	NOUN
cana-3838	272	10	6	6	NUM
cana-3838	272	11	.	.	PUNCT
cana-3838	273	1	subplot(1,3,1	subplot(1,3,1	NOUN
cana-3838	273	2	)	)	PUNCT
cana-3838	273	3	7	7	NUM
cana-3838	273	4	.	.	X
cana-3838	273	5	imshow(i	imshow(i	NUM
cana-3838	273	6	)	)	PUNCT
cana-3838	273	7	8	8	NUM
cana-3838	273	8	.	.	PUNCT
cana-3838	273	9	subplot(1,3,2:3	subplot(1,3,2:3	VERB
cana-3838	273	10	)	)	PUNCT
cana-3838	273	11	9	9	NUM
cana-3838	273	12	.	.	X
cana-3838	274	1	imhist(i	imhist(i	X
cana-3838	274	2	)	)	PUNCT
cana-3838	274	3	10	10	NUM
cana-3838	274	4	.	.	PUNCT
cana-3838	275	1	data	datum	NOUN
cana-3838	275	2	augmentaion	augmentaion	NOUN
cana-3838	275	3	using	use	VERB
cana-3838	275	4	cnn	cnn	PROPN
cana-3838	275	5	model	model	NOUN
cana-3838	275	6	11	11	NUM
cana-3838	275	7	.	.	PUNCT
cana-3838	276	1	transfer	transfer	VERB
cana-3838	276	2	learning_model	learning_model	PROPN
cana-3838	276	3	t	t	PROPN
cana-3838	276	4	=	=	PUNCT
cana-3838	277	1	[	[	X
cana-3838	277	2	a1,a2	a1,a2	PROPN
cana-3838	277	3	,	,	PUNCT
cana-3838	277	4	.	.	PUNCT
cana-3838	277	5	.	.	PUNCT
cana-3838	277	6	.	.	PUNCT
cana-3838	278	1	ak	ak	PROPN
cana-3838	278	2	]	]	PUNCT
cana-3838	278	3	12	12	NUM
cana-3838	278	4	.	.	PUNCT
cana-3838	279	1	for	for	ADP
cana-3838	279	2	j	j	PROPN
cana-3838	279	3	=	=	SYM
cana-3838	279	4	1	1	NUM
cana-3838	279	5	to	to	PART
cana-3838	279	6	m	m	PROPN
cana-3838	279	7	do	do	AUX
cana-3838	279	8	13	13	NUM
cana-3838	279	9	.	.	PUNCT
cana-3838	280	1	predict	predict	VERB
cana-3838	280	2	,	,	PUNCT
cana-3838	280	3	q	q	X
cana-3838	280	4	=	=	SYM
cana-3838	280	5	generate(o	generate(o	PROPN
cana-3838	280	6	)	)	PUNCT
cana-3838	280	7	14	14	NUM
cana-3838	280	8	.	.	PUNCT
cana-3838	281	1	z	z	NOUN
cana-3838	281	2	=	=	PRON
cana-3838	281	3	add	add	VERB
cana-3838	281	4	(	(	PUNCT
cana-3838	281	5	q	q	INTJ
cana-3838	281	6	,	,	PUNCT
cana-3838	281	7	along	along	ADP
cana-3838	281	8	c	c	NOUN
cana-3838	281	9	axis	axis	NOUN
cana-3838	281	10	)	)	PUNCT
cana-3838	281	11	15	15	NUM
cana-3838	281	12	.	.	PUNCT
cana-3838	282	1	ic	ic	PUNCT
cana-3838	283	1	=	=	NOUN
cana-3838	283	2	index_max	index_max	X
cana-3838	283	3	(	(	PUNCT
cana-3838	283	4	z	z	NOUN
cana-3838	283	5	,	,	PUNCT
cana-3838	283	6	along	along	ADP
cana-3838	283	7	d	d	PRON
cana-3838	283	8	axis	axis	NOUN
cana-3838	283	9	)	)	PUNCT
cana-3838	283	10	16	16	NUM
cana-3838	283	11	.	.	PUNCT
cana-3838	284	1	print(accuracy(i),segmentation_report	print(accuracy(i),segmentation_report	NOUN
cana-3838	284	2	)	)	PUNCT
cana-3838	284	3	;	;	PUNCT
cana-3838	285	1	17	17	NUM
cana-3838	285	2	.	.	NOUN
cana-3838	285	3	end	end	NOUN
cana-3838	285	4	communications	communication	NOUN
cana-3838	285	5	on	on	ADP
cana-3838	285	6	applied	apply	VERB
cana-3838	285	7	nonlinear	nonlinear	ADJ
cana-3838	285	8	analysis	analysis	NOUN
cana-3838	285	9	issn	issn	NOUN
cana-3838	285	10	:	:	PUNCT
cana-3838	285	11	1074	1074	NUM
cana-3838	285	12	-	-	PUNCT
cana-3838	285	13	133x	133x	NUM
cana-3838	285	14	vol	vol	NOUN
cana-3838	285	15	32	32	NUM
cana-3838	285	16	no	no	NOUN
cana-3838	285	17	.	.	PUNCT
cana-3838	286	1	9s	9s	NUM
cana-3838	286	2	(	(	PUNCT
cana-3838	286	3	2025	2025	NUM
cana-3838	286	4	)	)	PUNCT
cana-3838	286	5	74	74	NUM
cana-3838	286	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-3838	286	7	a	a	DET
cana-3838	286	8	brain	brain	NOUN
cana-3838	286	9	tumor	tumor	NOUN
cana-3838	286	10	is	be	AUX
cana-3838	286	11	the	the	DET
cana-3838	286	12	growth	growth	NOUN
cana-3838	286	13	of	of	ADP
cana-3838	286	14	abnormal	abnormal	ADJ
cana-3838	286	15	brain	brain	NOUN
cana-3838	286	16	cells	cell	NOUN
cana-3838	286	17	in	in	ADP
cana-3838	286	18	a	a	DET
cana-3838	286	19	person	person	NOUN
cana-3838	286	20	.	.	PUNCT
cana-3838	287	1	researchers	researcher	NOUN
cana-3838	287	2	still	still	ADV
cana-3838	287	3	do	do	AUX
cana-3838	287	4	n't	not	PART
cana-3838	287	5	fully	fully	ADV
cana-3838	287	6	understand	understand	VERB
cana-3838	287	7	what	what	PRON
cana-3838	287	8	causes	cause	VERB
cana-3838	287	9	brain	brain	NOUN
cana-3838	287	10	tumors	tumor	NOUN
cana-3838	287	11	,	,	PUNCT
cana-3838	287	12	but	but	CCONJ
cana-3838	287	13	they	they	PRON
cana-3838	287	14	have	have	AUX
cana-3838	287	15	identified	identify	VERB
cana-3838	287	16	several	several	ADJ
cana-3838	287	17	risk	risk	NOUN
cana-3838	287	18	indicators	indicator	NOUN
cana-3838	287	19	that	that	PRON
cana-3838	287	20	may	may	AUX
cana-3838	287	21	be	be	AUX
cana-3838	287	22	used	use	VERB
cana-3838	287	23	to	to	PART
cana-3838	287	24	track	track	VERB
cana-3838	287	25	the	the	DET
cana-3838	287	26	progression	progression	NOUN
cana-3838	287	27	of	of	ADP
cana-3838	287	28	a	a	DET
cana-3838	287	29	tumor	tumor	NOUN
cana-3838	287	30	.	.	PUNCT
cana-3838	288	1	a	a	DET
cana-3838	288	2	glioma	glioma	NOUN
cana-3838	288	3	is	be	AUX
cana-3838	288	4	a	a	DET
cana-3838	288	5	tumor	tumor	NOUN
cana-3838	288	6	that	that	PRON
cana-3838	288	7	develops	develop	VERB
cana-3838	288	8	in	in	ADP
cana-3838	288	9	the	the	DET
cana-3838	288	10	brain	brain	NOUN
cana-3838	288	11	or	or	CCONJ
cana-3838	288	12	spinal	spinal	NOUN
cana-3838	288	13	cord	cord	NOUN
cana-3838	288	14	;	;	PUNCT
cana-3838	288	15	a	a	DET
cana-3838	288	16	meningioma	meningioma	NOUN
cana-3838	288	17	is	be	AUX
cana-3838	288	18	a	a	DET
cana-3838	288	19	tumor	tumor	NOUN
cana-3838	288	20	that	that	PRON
cana-3838	288	21	develops	develop	VERB
cana-3838	288	22	in	in	ADP
cana-3838	288	23	the	the	DET
cana-3838	288	24	meninges	meninge	NOUN
cana-3838	288	25	.	.	PUNCT
cana-3838	289	1	pituitary	pituitary	ADJ
cana-3838	289	2	tumors	tumor	NOUN
cana-3838	289	3	are	be	AUX
cana-3838	289	4	the	the	DET
cana-3838	289	5	result	result	NOUN
cana-3838	289	6	of	of	ADP
cana-3838	289	7	an	an	DET
cana-3838	289	8	aberrant	aberrant	ADJ
cana-3838	289	9	proliferation	proliferation	NOUN
cana-3838	289	10	of	of	ADP
cana-3838	289	11	cells	cell	NOUN
cana-3838	289	12	inside	inside	ADP
cana-3838	289	13	the	the	DET
cana-3838	289	14	pituitary	pituitary	ADJ
cana-3838	289	15	gland	gland	NOUN
cana-3838	289	16	.	.	PUNCT
cana-3838	290	1	when	when	SCONJ
cana-3838	290	2	it	it	PRON
cana-3838	290	3	comes	come	VERB
cana-3838	290	4	to	to	ADP
cana-3838	290	5	segmenting	segment	VERB
cana-3838	290	6	brain	brain	NOUN
cana-3838	290	7	tumors	tumor	NOUN
cana-3838	290	8	in	in	ADP
cana-3838	290	9	mri	mri	NOUN
cana-3838	290	10	images	image	NOUN
cana-3838	290	11	,	,	PUNCT
cana-3838	290	12	we	we	PRON
cana-3838	290	13	provide	provide	VERB
cana-3838	290	14	a	a	DET
cana-3838	290	15	hybrid	hybrid	ADJ
cana-3838	290	16	model	model	NOUN
cana-3838	290	17	that	that	PRON
cana-3838	290	18	combines	combine	VERB
cana-3838	290	19	vgg16	vgg16	NOUN
cana-3838	290	20	with	with	ADP
cana-3838	290	21	resnet50	resnet50	NOUN
cana-3838	290	22	in	in	ADP
cana-3838	290	23	this	this	DET
cana-3838	290	24	study	study	NOUN
cana-3838	290	25	.	.	PUNCT
cana-3838	291	1	compared	compare	VERB
cana-3838	291	2	to	to	ADP
cana-3838	291	3	other	other	ADJ
cana-3838	291	4	models	model	NOUN
cana-3838	291	5	already	already	ADV
cana-3838	291	6	available	available	ADJ
cana-3838	291	7	,	,	PUNCT
cana-3838	291	8	our	our	PRON
cana-3838	291	9	proposed	propose	VERB
cana-3838	291	10	technique	technique	NOUN
cana-3838	291	11	outperforms	outperform	VERB
cana-3838	291	12	them	they	PRON
cana-3838	291	13	in	in	ADP
cana-3838	291	14	terms	term	NOUN
cana-3838	291	15	of	of	ADP
cana-3838	291	16	accuracy	accuracy	NOUN
cana-3838	291	17	and	and	CCONJ
cana-3838	291	18	performance	performance	NOUN
cana-3838	291	19	.	.	PUNCT
cana-3838	292	1	eventually	eventually	ADV
cana-3838	292	2	,	,	PUNCT
cana-3838	292	3	we	we	PRON
cana-3838	292	4	'll	will	AUX
cana-3838	292	5	be	be	AUX
cana-3838	292	6	able	able	ADJ
cana-3838	292	7	to	to	PART
cana-3838	292	8	use	use	VERB
cana-3838	292	9	more	more	ADV
cana-3838	292	10	advanced	advanced	ADJ
cana-3838	292	11	transfer	transfer	NOUN
cana-3838	292	12	learning	learn	VERB
cana-3838	292	13	algorithms	algorithm	NOUN
cana-3838	292	14	for	for	ADP
cana-3838	292	15	more	more	ADV
cana-3838	292	16	precise	precise	ADJ
cana-3838	292	17	brain	brain	NOUN
cana-3838	292	18	image	image	NOUN
cana-3838	292	19	segmentation	segmentation	NOUN
cana-3838	292	20	.	.	PUNCT
cana-3838	293	1	refrences	refrence	VERB
cana-3838	293	2	1	1	NUM
cana-3838	293	3	.	.	PUNCT
cana-3838	294	1	ramakrishna	ramakrishna	PROPN
cana-3838	294	2	sajja	sajja	PROPN
cana-3838	294	3	,	,	PUNCT
cana-3838	294	4	v.	v.	PROPN
cana-3838	294	5	,	,	PUNCT
cana-3838	294	6	&	&	CCONJ
cana-3838	294	7	kumar	kumar	PROPN
cana-3838	294	8	kalluri	kalluri	PROPN
cana-3838	294	9	,	,	PUNCT
cana-3838	294	10	h.	h.	PROPN
cana-3838	294	11	(	(	PUNCT
cana-3838	294	12	2021	2021	NUM
cana-3838	294	13	)	)	PUNCT
cana-3838	294	14	.	.	PUNCT
cana-3838	295	1	classification	classification	NOUN
cana-3838	295	2	of	of	ADP
cana-3838	295	3	brain	brain	NOUN
cana-3838	295	4	tumors	tumor	NOUN
cana-3838	295	5	using	use	VERB
cana-3838	295	6	fuzzy	fuzzy	ADJ
cana-3838	295	7	c	c	NOUN
cana-3838	295	8	-	-	PUNCT
cana-3838	295	9	means	means	NOUN
cana-3838	295	10	and	and	CCONJ
cana-3838	295	11	vgg16	vgg16	PROPN
cana-3838	295	12	.	.	PUNCT
cana-3838	296	1	turkish	turkish	ADJ
cana-3838	296	2	journal	journal	NOUN
cana-3838	296	3	of	of	ADP
cana-3838	296	4	computer	computer	NOUN
cana-3838	296	5	and	and	CCONJ
cana-3838	296	6	mathematics	mathematic	NOUN
cana-3838	296	7	education	education	NOUN
cana-3838	296	8	,	,	PUNCT
cana-3838	296	9	12(9	12(9	NUM
cana-3838	296	10	)	)	PUNCT
cana-3838	296	11	,	,	PUNCT
cana-3838	296	12	2103–2113	2103–2113	NUM
cana-3838	296	13	.	.	PUNCT
cana-3838	297	1	https://turcomat.org/index.php/turkbilmat/article/view/3680	https://turcomat.org/index.php/turkbilmat/article/view/3680	X
cana-3838	297	2	2	2	X
cana-3838	297	3	.	.	X
cana-3838	297	4	sharma	sharma	PROPN
cana-3838	297	5	,	,	PUNCT
cana-3838	297	6	a.	a.	PROPN
cana-3838	297	7	k.	k.	PROPN
cana-3838	297	8	,	,	PUNCT
cana-3838	297	9	nandal	nandal	PROPN
cana-3838	297	10	,	,	PUNCT
cana-3838	297	11	a.	a.	NOUN
cana-3838	297	12	,	,	PUNCT
cana-3838	297	13	dhaka	dhaka	PROPN
cana-3838	297	14	,	,	PUNCT
cana-3838	297	15	a.	a.	NOUN
cana-3838	297	16	,	,	PUNCT
cana-3838	297	17	koundal	koundal	NOUN
cana-3838	297	18	,	,	PUNCT
cana-3838	297	19	d.	d.	PROPN
cana-3838	297	20	,	,	PUNCT
cana-3838	297	21	bogatinoska	bogatinoska	VERB
cana-3838	297	22	,	,	PUNCT
cana-3838	297	23	d.	d.	PROPN
cana-3838	297	24	c.	c.	PROPN
cana-3838	297	25	,	,	PUNCT
cana-3838	297	26	&	&	CCONJ
cana-3838	297	27	alyami	alyami	NOUN
cana-3838	297	28	,	,	PUNCT
cana-3838	297	29	h.	h.	PROPN
cana-3838	297	30	(	(	PUNCT
cana-3838	297	31	2022	2022	NUM
cana-3838	297	32	)	)	PUNCT
cana-3838	297	33	.	.	PUNCT
cana-3838	298	1	enhanced	enhance	VERB
cana-3838	298	2	watershed	watershed	ADJ
cana-3838	298	3	segmentation	segmentation	NOUN
cana-3838	298	4	algorithm	algorithm	NOUN
cana-3838	298	5	-	-	PUNCT
cana-3838	298	6	based	base	VERB
cana-3838	298	7	modified	modified	ADJ
cana-3838	298	8	resnet50	resnet50	NOUN
cana-3838	298	9	model	model	NOUN
cana-3838	298	10	for	for	ADP
cana-3838	298	11	brain	brain	NOUN
cana-3838	298	12	tumor	tumor	NOUN
cana-3838	298	13	detection	detection	NOUN
cana-3838	298	14	.	.	PUNCT
cana-3838	299	1	biomed	biome	VERB
cana-3838	299	2	research	research	NOUN
cana-3838	299	3	international	international	NOUN
cana-3838	299	4	,	,	PUNCT
cana-3838	299	5	2022	2022	NUM
cana-3838	299	6	.	.	PUNCT
cana-3838	300	1	3	3	X
cana-3838	300	2	.	.	X
cana-3838	300	3	khanna	khanna	PROPN
cana-3838	300	4	,	,	PUNCT
cana-3838	300	5	s.	s.	PROPN
cana-3838	300	6	(	(	PUNCT
cana-3838	300	7	2019	2019	NUM
cana-3838	300	8	)	)	PUNCT
cana-3838	300	9	.	.	PUNCT
cana-3838	301	1	brain	brain	NOUN
cana-3838	301	2	tumor	tumor	NOUN
cana-3838	301	3	segmentation	segmentation	NOUN
cana-3838	301	4	using	use	VERB
cana-3838	301	5	deep	deep	ADJ
cana-3838	301	6	transfer	transfer	NOUN
cana-3838	301	7	learning	learning	NOUN
cana-3838	301	8	models	model	NOUN
cana-3838	301	9	on	on	ADP
cana-3838	301	10	the	the	DET
cana-3838	301	11	cancer	cancer	NOUN
cana-3838	301	12	genome	genome	NOUN
cana-3838	301	13	atlas	atlas	PROPN
cana-3838	301	14	(	(	PUNCT
cana-3838	301	15	tcga	tcga	PROPN
cana-3838	301	16	)	)	PUNCT
cana-3838	301	17	dataset	dataset	NOUN
cana-3838	301	18	.	.	PUNCT
cana-3838	302	1	48–56	48–56	NUM
cana-3838	302	2	.	.	PUNCT
cana-3838	303	1	4	4	NUM
cana-3838	303	2	.	.	X
cana-3838	303	3	srinivas	srinivas	PROPN
cana-3838	303	4	,	,	PUNCT
cana-3838	303	5	c.	c.	PROPN
cana-3838	303	6	,	,	PUNCT
cana-3838	303	7	s	s	PROPN
cana-3838	303	8	,	,	PUNCT
cana-3838	303	9	n.	n.	PROPN
cana-3838	303	10	p.	p.	PROPN
cana-3838	303	11	k.	k.	PROPN
cana-3838	303	12	,	,	PUNCT
cana-3838	303	13	zakariah	zakariah	PROPN
cana-3838	303	14	,	,	PUNCT
cana-3838	303	15	m.	m.	NOUN
cana-3838	303	16	,	,	PUNCT
cana-3838	303	17	alothaibi	alothaibi	NOUN
cana-3838	303	18	,	,	PUNCT
cana-3838	303	19	y.	y.	PROPN
cana-3838	303	20	a.	a.	PROPN
cana-3838	303	21	,	,	PUNCT
cana-3838	303	22	shaukat	shaukat	PROPN
cana-3838	303	23	,	,	PUNCT
cana-3838	303	24	k.	k.	PROPN
cana-3838	303	25	,	,	PUNCT
cana-3838	303	26	partibane	partibane	PROPN
cana-3838	303	27	,	,	PUNCT
cana-3838	303	28	b.	b.	PROPN
cana-3838	303	29	,	,	PUNCT
cana-3838	303	30	&	&	CCONJ
cana-3838	303	31	awal	awal	PROPN
cana-3838	303	32	,	,	PUNCT
cana-3838	303	33	h.	h.	PROPN
cana-3838	303	34	(	(	PUNCT
cana-3838	303	35	2022	2022	NUM
cana-3838	303	36	)	)	PUNCT
cana-3838	303	37	.	.	PUNCT
cana-3838	304	1	brain	brain	NOUN
cana-3838	304	2	tumor	tumor	NOUN
cana-3838	304	3	classification	classification	NOUN
cana-3838	304	4	using	use	VERB
cana-3838	304	5	mri	mri	NOUN
cana-3838	304	6	images	image	NOUN
cana-3838	304	7	.	.	PUNCT
cana-3838	305	1	2022	2022	NUM
cana-3838	305	2	.	.	PUNCT
cana-3838	306	1	5	5	NUM
cana-3838	306	2	.	.	X
cana-3838	306	3	işin	işin	PROPN
cana-3838	306	4	,	,	PUNCT
cana-3838	306	5	a.	a.	NOUN
cana-3838	306	6	,	,	PUNCT
cana-3838	306	7	direkoǧlu	direkoǧlu	NOUN
cana-3838	306	8	,	,	PUNCT
cana-3838	306	9	c.	c.	NOUN
cana-3838	306	10	,	,	PUNCT
cana-3838	306	11	&	&	CCONJ
cana-3838	306	12	şah	şah	ADJ
cana-3838	306	13	,	,	PUNCT
cana-3838	306	14	m.	m.	NOUN
cana-3838	306	15	(	(	PUNCT
cana-3838	306	16	2016	2016	NUM
cana-3838	306	17	)	)	PUNCT
cana-3838	306	18	.	.	PUNCT
cana-3838	307	1	review	review	NOUN
cana-3838	307	2	of	of	ADP
cana-3838	307	3	mri	mri	NOUN
cana-3838	307	4	-	-	PUNCT
cana-3838	307	5	based	base	VERB
cana-3838	307	6	brain	brain	NOUN
cana-3838	307	7	tumor	tumor	NOUN
cana-3838	307	8	image	image	NOUN
cana-3838	307	9	segmentation	segmentation	NOUN
cana-3838	307	10	using	use	VERB
cana-3838	307	11	deep	deep	ADJ
cana-3838	307	12	learning	learning	NOUN
cana-3838	307	13	methods	method	NOUN
cana-3838	307	14	.	.	PUNCT
cana-3838	308	1	procedia	procedia	PROPN
cana-3838	308	2	computer	computer	NOUN
cana-3838	308	3	science	science	NOUN
cana-3838	308	4	,	,	PUNCT
cana-3838	308	5	102(august	102(august	NUM
cana-3838	308	6	)	)	PUNCT
cana-3838	308	7	,	,	PUNCT
cana-3838	308	8	317	317	NUM
cana-3838	308	9	–	–	PUNCT
cana-3838	308	10	324	324	NUM
cana-3838	308	11	.	.	PUNCT
cana-3838	309	1	https://doi.org/10.1016/j.procs.2016.09.407	https://doi.org/10.1016/j.procs.2016.09.407	VERB
cana-3838	309	2	6	6	NUM
cana-3838	309	3	.	.	PUNCT
cana-3838	310	1	chattopadhyay	chattopadhyay	PROPN
cana-3838	310	2	,	,	PUNCT
cana-3838	310	3	a.	a.	PROPN
cana-3838	310	4	,	,	PUNCT
cana-3838	310	5	&	&	CCONJ
cana-3838	310	6	maitra	maitra	NOUN
cana-3838	310	7	,	,	PUNCT
cana-3838	310	8	m.	m.	NOUN
cana-3838	310	9	(	(	PUNCT
cana-3838	310	10	2022	2022	NUM
cana-3838	310	11	)	)	PUNCT
cana-3838	310	12	.	.	PUNCT
cana-3838	311	1	mri	mri	NOUN
cana-3838	311	2	-	-	PUNCT
cana-3838	311	3	based	base	VERB
cana-3838	311	4	brain	brain	NOUN
cana-3838	311	5	tumour	tumour	NOUN
cana-3838	311	6	image	image	NOUN
cana-3838	311	7	detection	detection	NOUN
cana-3838	311	8	using	use	VERB
cana-3838	311	9	cnn	cnn	PROPN
cana-3838	311	10	based	base	VERB
cana-3838	311	11	deep	deep	ADJ
cana-3838	311	12	learning	learning	NOUN
cana-3838	311	13	method	method	NOUN
cana-3838	311	14	.	.	PUNCT
cana-3838	312	1	smart	smart	ADJ
cana-3838	312	2	agricultural	agricultural	ADJ
cana-3838	312	3	technology	technology	NOUN
cana-3838	312	4	,	,	PUNCT
cana-3838	312	5	2(4	2(4	NUM
cana-3838	312	6	)	)	PUNCT
cana-3838	312	7	,	,	PUNCT
cana-3838	312	8	100060	100060	NUM
cana-3838	312	9	.	.	PUNCT
cana-3838	313	1	https://doi.org/10.1016/j.neuri.2022.100060	https://doi.org/10.1016/j.neuri.2022.100060	NOUN
cana-3838	313	2	7	7	NUM
cana-3838	313	3	.	.	PUNCT
cana-3838	314	1	havaei	havaei	PROPN
cana-3838	314	2	,	,	PUNCT
cana-3838	314	3	m.	m.	NOUN
cana-3838	314	4	,	,	PUNCT
cana-3838	314	5	davy	davy	PROPN
cana-3838	314	6	,	,	PUNCT
cana-3838	314	7	a.	a.	PROPN
cana-3838	314	8	,	,	PUNCT
cana-3838	314	9	warde	warde	PROPN
cana-3838	314	10	-	-	PUNCT
cana-3838	314	11	farley	farley	PROPN
cana-3838	314	12	,	,	PUNCT
cana-3838	314	13	d.	d.	PROPN
cana-3838	314	14	,	,	PUNCT
cana-3838	314	15	biard	biard	NOUN
cana-3838	314	16	,	,	PUNCT
cana-3838	314	17	a.	a.	NOUN
cana-3838	314	18	,	,	PUNCT
cana-3838	314	19	courville	courville	NOUN
cana-3838	314	20	,	,	PUNCT
cana-3838	314	21	a.	a.	NOUN
cana-3838	314	22	,	,	PUNCT
cana-3838	314	23	bengio	bengio	PROPN
cana-3838	314	24	,	,	PUNCT
cana-3838	314	25	y.	y.	PROPN
cana-3838	314	26	,	,	PUNCT
cana-3838	314	27	pal	pal	NOUN
cana-3838	314	28	,	,	PUNCT
cana-3838	314	29	c.	c.	PROPN
cana-3838	314	30	,	,	PUNCT
cana-3838	314	31	jodoin	jodoin	PROPN
cana-3838	314	32	,	,	PUNCT
cana-3838	314	33	p.	p.	NOUN
cana-3838	314	34	m.	m.	NOUN
cana-3838	314	35	,	,	PUNCT
cana-3838	314	36	&	&	CCONJ
cana-3838	314	37	larochelle	larochelle	PROPN
cana-3838	314	38	,	,	PUNCT
cana-3838	314	39	h.	h.	PROPN
cana-3838	314	40	(	(	PUNCT
cana-3838	314	41	2017	2017	NUM
cana-3838	314	42	)	)	PUNCT
cana-3838	314	43	.	.	PUNCT
cana-3838	315	1	brain	brain	NOUN
cana-3838	315	2	tumor	tumor	NOUN
cana-3838	315	3	segmentation	segmentation	NOUN
cana-3838	315	4	with	with	ADP
cana-3838	315	5	deep	deep	ADJ
cana-3838	315	6	neural	neural	ADJ
cana-3838	315	7	networks	network	NOUN
cana-3838	315	8	.	.	PUNCT
cana-3838	316	1	medical	medical	ADJ
cana-3838	316	2	image	image	NOUN
cana-3838	316	3	analysis	analysis	NOUN
cana-3838	316	4	,	,	PUNCT
cana-3838	316	5	35	35	NUM
cana-3838	316	6	,	,	PUNCT
cana-3838	316	7	18–31	18–31	NUM
cana-3838	316	8	.	.	PUNCT
cana-3838	317	1	https://doi.org/10.1016/j.media.2016.05.004	https://doi.org/10.1016/j.media.2016.05.004	PROPN
cana-3838	317	2	8	8	NUM
cana-3838	317	3	.	.	PUNCT
cana-3838	318	1	rehman	rehman	PROPN
cana-3838	318	2	,	,	PUNCT
cana-3838	318	3	a.	a.	PROPN
cana-3838	318	4	,	,	PUNCT
cana-3838	318	5	naz	naz	PROPN
cana-3838	318	6	,	,	PUNCT
cana-3838	318	7	s.	s.	PROPN
cana-3838	318	8	,	,	PUNCT
cana-3838	318	9	razzak	razzak	PROPN
cana-3838	318	10	,	,	PUNCT
cana-3838	318	11	m.	m.	NOUN
cana-3838	318	12	i.	i.	PROPN
cana-3838	318	13	,	,	PUNCT
cana-3838	318	14	akram	akram	PROPN
cana-3838	318	15	,	,	PUNCT
cana-3838	318	16	f.	f.	PROPN
cana-3838	318	17	,	,	PUNCT
cana-3838	318	18	&	&	CCONJ
cana-3838	318	19	imran	imran	PROPN
cana-3838	318	20	,	,	PUNCT
cana-3838	318	21	m.	m.	NOUN
cana-3838	318	22	(	(	PUNCT
cana-3838	318	23	2020	2020	NUM
cana-3838	318	24	)	)	PUNCT
cana-3838	318	25	.	.	PUNCT
cana-3838	319	1	a	a	DET
cana-3838	319	2	deep	deep	ADJ
cana-3838	319	3	learning	learning	NOUN
cana-3838	319	4	-	-	PUNCT
cana-3838	319	5	based	base	VERB
cana-3838	319	6	framework	framework	NOUN
cana-3838	319	7	for	for	ADP
cana-3838	319	8	automatic	automatic	ADJ
cana-3838	319	9	brain	brain	NOUN
cana-3838	319	10	tumors	tumor	NOUN
cana-3838	319	11	classification	classification	NOUN
cana-3838	319	12	using	use	VERB
cana-3838	319	13	transfer	transfer	NOUN
cana-3838	319	14	learning	learning	NOUN
cana-3838	319	15	.	.	PUNCT
cana-3838	320	1	circuits	circuit	NOUN
cana-3838	320	2	,	,	PUNCT
cana-3838	320	3	systems	system	NOUN
cana-3838	320	4	,	,	PUNCT
cana-3838	320	5	and	and	CCONJ
cana-3838	320	6	signal	signal	NOUN
cana-3838	320	7	processing	processing	NOUN
cana-3838	320	8	,	,	PUNCT
cana-3838	320	9	39(2	39(2	NUM
cana-3838	320	10	)	)	PUNCT
cana-3838	320	11	,	,	PUNCT
cana-3838	320	12	757–775	757–775	NUM
cana-3838	320	13	.	.	PUNCT
cana-3838	320	14	https://doi.org/10.1007/s00034-019-01246-3	https://doi.org/10.1007/s00034-019-01246-3	NUM
cana-3838	320	15	9	9	NUM
cana-3838	320	16	.	.	PUNCT
cana-3838	320	17	shehab	shehab	PROPN
cana-3838	320	18	,	,	PUNCT
cana-3838	320	19	l.	l.	PROPN
cana-3838	320	20	h.	h.	PROPN
cana-3838	320	21	,	,	PUNCT
cana-3838	320	22	fahmy	fahmy	PROPN
cana-3838	320	23	,	,	PUNCT
cana-3838	320	24	o.	o.	NOUN
cana-3838	320	25	m.	m.	NOUN
cana-3838	320	26	,	,	PUNCT
cana-3838	320	27	gasser	gasser	NOUN
cana-3838	320	28	,	,	PUNCT
cana-3838	320	29	s.	s.	PROPN
cana-3838	320	30	m.	m.	PROPN
cana-3838	320	31	,	,	PUNCT
cana-3838	320	32	&	&	CCONJ
cana-3838	320	33	el	el	PROPN
cana-3838	320	34	-	-	PUNCT
cana-3838	320	35	mahallawy	mahallawy	PROPN
cana-3838	320	36	,	,	PUNCT
cana-3838	320	37	m.	m.	NOUN
cana-3838	320	38	s.	s.	PROPN
cana-3838	320	39	(	(	PUNCT
cana-3838	320	40	2021	2021	NUM
cana-3838	320	41	)	)	PUNCT
cana-3838	320	42	.	.	PUNCT
cana-3838	321	1	an	an	DET
cana-3838	321	2	efficient	efficient	ADJ
cana-3838	321	3	brain	brain	NOUN
cana-3838	321	4	tumor	tumor	NOUN
cana-3838	321	5	image	image	NOUN
cana-3838	321	6	segmentation	segmentation	NOUN
cana-3838	321	7	based	base	VERB
cana-3838	321	8	on	on	ADP
cana-3838	321	9	deep	deep	ADJ
cana-3838	321	10	residual	residual	ADJ
cana-3838	321	11	networks	network	NOUN
cana-3838	321	12	(	(	PUNCT
cana-3838	321	13	resnets	resnet	NOUN
cana-3838	321	14	)	)	PUNCT
cana-3838	321	15	.	.	PUNCT
cana-3838	322	1	journal	journal	PROPN
cana-3838	322	2	of	of	ADP
cana-3838	322	3	king	king	PROPN
cana-3838	322	4	saud	saud	PROPN
cana-3838	322	5	university	university	PROPN
cana-3838	322	6	engineering	engineering	NOUN
cana-3838	322	7	sciences	sciences	PROPN
cana-3838	322	8	,	,	PUNCT
cana-3838	322	9	33(6	33(6	NUM
cana-3838	322	10	)	)	PUNCT
cana-3838	322	11	,	,	PUNCT
cana-3838	322	12	404–412	404–412	NUM
cana-3838	322	13	.	.	PUNCT
cana-3838	323	1	https://doi.org/10.1016/j.jksues.2020.06.001	https://doi.org/10.1016/j.jksues.2020.06.001	ADJ
cana-3838	323	2	communications	communication	NOUN
cana-3838	323	3	on	on	ADP
cana-3838	323	4	applied	apply	VERB
cana-3838	323	5	nonlinear	nonlinear	ADJ
cana-3838	323	6	analysis	analysis	NOUN
cana-3838	323	7	issn	issn	NOUN
cana-3838	323	8	:	:	PUNCT
cana-3838	323	9	1074	1074	NUM
cana-3838	323	10	-	-	PUNCT
cana-3838	323	11	133x	133x	NUM
cana-3838	323	12	vol	vol	NOUN
cana-3838	323	13	32	32	NUM
cana-3838	323	14	no	no	NOUN
cana-3838	323	15	.	.	PUNCT
cana-3838	324	1	9s	9s	NUM
cana-3838	324	2	(	(	PUNCT
cana-3838	324	3	2025	2025	NUM
cana-3838	324	4	)	)	PUNCT
cana-3838	324	5	75	75	NUM
cana-3838	324	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-3838	324	7	10	10	NUM
cana-3838	324	8	.	.	PUNCT
cana-3838	325	1	kuraparthi	kuraparthi	PROPN
cana-3838	325	2	,	,	PUNCT
cana-3838	325	3	s.	s.	PROPN
cana-3838	325	4	,	,	PUNCT
cana-3838	325	5	reddy	reddy	PROPN
cana-3838	325	6	,	,	PUNCT
cana-3838	325	7	m.	m.	PROPN
cana-3838	325	8	k.	k.	PROPN
cana-3838	325	9	,	,	PUNCT
cana-3838	325	10	sujatha	sujatha	PROPN
cana-3838	325	11	,	,	PUNCT
cana-3838	325	12	c.	c.	PROPN
cana-3838	325	13	n.	n.	PROPN
cana-3838	325	14	,	,	PUNCT
cana-3838	325	15	valiveti	valiveti	PROPN
cana-3838	325	16	,	,	PUNCT
cana-3838	325	17	h.	h.	PROPN
cana-3838	325	18	,	,	PUNCT
cana-3838	325	19	duggineni	duggineni	PROPN
cana-3838	325	20	,	,	PUNCT
cana-3838	325	21	c.	c.	PROPN
cana-3838	325	22	,	,	PUNCT
cana-3838	325	23	kollati	kollati	PROPN
cana-3838	325	24	,	,	PUNCT
cana-3838	325	25	m.	m.	NOUN
cana-3838	325	26	,	,	PUNCT
cana-3838	325	27	kora	kora	PROPN
cana-3838	325	28	,	,	PUNCT
cana-3838	325	29	p.	p.	PROPN
cana-3838	325	30	,	,	PUNCT
cana-3838	325	31	&	&	CCONJ
cana-3838	325	32	sravan	sravan	PROPN
cana-3838	325	33	,	,	PUNCT
cana-3838	325	34	v.	v.	PROPN
cana-3838	325	35	(	(	PUNCT
cana-3838	325	36	2021	2021	NUM
cana-3838	325	37	)	)	PUNCT
cana-3838	325	38	.	.	PUNCT
cana-3838	326	1	brain	brain	NOUN
cana-3838	326	2	tumor	tumor	NOUN
cana-3838	326	3	classification	classification	NOUN
cana-3838	326	4	of	of	ADP
cana-3838	326	5	mri	mri	NOUN
cana-3838	326	6	images	image	NOUN
cana-3838	326	7	using	use	VERB
cana-3838	326	8	deep	deep	ADJ
cana-3838	326	9	convolutional	convolutional	ADJ
cana-3838	326	10	neural	neural	ADJ
cana-3838	326	11	network	network	NOUN
cana-3838	326	12	.	.	PUNCT
cana-3838	327	1	traitement	traitement	NOUN
cana-3838	327	2	du	du	PROPN
cana-3838	327	3	signal	signal	NOUN
cana-3838	327	4	,	,	PUNCT
cana-3838	327	5	38(4	38(4	NUM
cana-3838	327	6	)	)	PUNCT
cana-3838	327	7	,	,	PUNCT
cana-3838	327	8	1171–1179	1171–1179	NUM
cana-3838	327	9	.	.	PUNCT
cana-3838	328	1	https://doi.org/10.18280/ts.380428	https://doi.org/10.18280/ts.380428	VERB
cana-3838	328	2	11	11	NUM
cana-3838	328	3	.	.	PUNCT
cana-3838	328	4	wacker	wacker	NOUN
cana-3838	328	5	,	,	PUNCT
cana-3838	328	6	j.	j.	PROPN
cana-3838	328	7	,	,	PUNCT
cana-3838	328	8	ladeira	ladeira	PROPN
cana-3838	328	9	,	,	PUNCT
cana-3838	328	10	m.	m.	NOUN
cana-3838	328	11	,	,	PUNCT
cana-3838	328	12	&	&	CCONJ
cana-3838	328	13	nascimento	nascimento	PROPN
cana-3838	328	14	,	,	PUNCT
cana-3838	328	15	j.	j.	PROPN
cana-3838	328	16	e.	e.	PROPN
cana-3838	328	17	v.	v.	PROPN
cana-3838	328	18	(	(	PUNCT
cana-3838	328	19	2021	2021	NUM
cana-3838	328	20	)	)	PUNCT
cana-3838	328	21	.	.	PUNCT
cana-3838	329	1	transfer	transfer	NOUN
cana-3838	329	2	learning	learning	NOUN
cana-3838	329	3	for	for	ADP
cana-3838	329	4	brain	brain	NOUN
cana-3838	329	5	tumor	tumor	NOUN
cana-3838	329	6	segmentation	segmentation	NOUN
cana-3838	329	7	.	.	PUNCT
cana-3838	330	1	lecture	lecture	NOUN
cana-3838	330	2	notes	note	NOUN
cana-3838	330	3	in	in	ADP
cana-3838	330	4	computer	computer	NOUN
cana-3838	330	5	science	science	NOUN
cana-3838	330	6	(	(	PUNCT
cana-3838	330	7	including	include	VERB
cana-3838	330	8	subseries	subserie	NOUN
cana-3838	330	9	lecture	lecture	VERB
cana-3838	330	10	notes	note	NOUN
cana-3838	330	11	in	in	ADP
cana-3838	330	12	artificial	artificial	ADJ
cana-3838	330	13	intelligence	intelligence	NOUN
cana-3838	330	14	and	and	CCONJ
cana-3838	330	15	lecture	lecture	NOUN
cana-3838	330	16	notes	note	NOUN
cana-3838	330	17	in	in	ADP
cana-3838	330	18	bioinformatics	bioinformatics	NOUN
cana-3838	330	19	)	)	PUNCT
cana-3838	330	20	,	,	PUNCT
cana-3838	330	21	12658	12658	NUM
cana-3838	330	22	lncs	lnc	NOUN
cana-3838	330	23	,	,	PUNCT
cana-3838	330	24	241–251	241–251	NUM
cana-3838	330	25	.	.	PUNCT
cana-3838	331	1	https://doi.org/10.1007/978-3-030-72084-1_22	https://doi.org/10.1007/978-3-030-72084-1_22	PRON
cana-3838	331	2	12	12	NUM
cana-3838	331	3	.	.	PUNCT
cana-3838	332	1	younis	younis	PROPN
cana-3838	332	2	,	,	PUNCT
cana-3838	332	3	a.	a.	PROPN
cana-3838	332	4	,	,	PUNCT
cana-3838	332	5	qiang	qiang	PROPN
cana-3838	332	6	,	,	PUNCT
cana-3838	332	7	l.	l.	PROPN
cana-3838	332	8	,	,	PUNCT
cana-3838	332	9	nyatega	nyatega	PROPN
cana-3838	332	10	,	,	PUNCT
cana-3838	332	11	c.	c.	PROPN
cana-3838	332	12	o.	o.	PROPN
cana-3838	332	13	,	,	PUNCT
cana-3838	332	14	adamu	adamu	PROPN
cana-3838	332	15	,	,	PUNCT
cana-3838	332	16	m.	m.	PROPN
cana-3838	332	17	j.	j.	PROPN
cana-3838	332	18	,	,	PUNCT
cana-3838	332	19	&	&	CCONJ
cana-3838	332	20	kawuwa	kawuwa	PROPN
cana-3838	332	21	,	,	PUNCT
cana-3838	332	22	h.	h.	PROPN
cana-3838	332	23	b.	b.	PROPN
cana-3838	332	24	(	(	PUNCT
cana-3838	332	25	2022	2022	NUM
cana-3838	332	26	)	)	PUNCT
cana-3838	332	27	.	.	PUNCT
cana-3838	333	1	brain	brain	NOUN
cana-3838	333	2	tumor	tumor	NOUN
cana-3838	333	3	analysis	analysis	NOUN
cana-3838	333	4	using	use	VERB
cana-3838	333	5	deep	deep	ADJ
cana-3838	333	6	learning	learning	NOUN
cana-3838	333	7	and	and	CCONJ
cana-3838	333	8	vgg-16	vgg-16	X
cana-3838	333	9	ensembling	ensemble	VERB
cana-3838	333	10	learning	learn	VERB
cana-3838	333	11	approaches	approach	NOUN
cana-3838	333	12	.	.	PUNCT
cana-3838	334	1	applied	apply	VERB
cana-3838	334	2	sciences	sciences	PROPN
cana-3838	334	3	(	(	PUNCT
cana-3838	334	4	switzerland	switzerland	PROPN
cana-3838	334	5	)	)	PUNCT
cana-3838	334	6	,	,	PUNCT
cana-3838	334	7	12(14	12(14	NUM
cana-3838	334	8	)	)	PUNCT
cana-3838	334	9	.	.	PUNCT
cana-3838	335	1	https://doi.org/10.3390/app12147282	https://doi.org/10.3390/app12147282	PROPN
cana-3838	335	2	13	13	NUM
cana-3838	335	3	.	.	X
cana-3838	335	4	ali	ali	PROPN
cana-3838	335	5	,	,	PUNCT
cana-3838	335	6	m.	m.	NOUN
cana-3838	335	7	,	,	PUNCT
cana-3838	335	8	gilani	gilani	PROPN
cana-3838	335	9	,	,	PUNCT
cana-3838	335	10	s.	s.	PROPN
cana-3838	335	11	o.	o.	PROPN
cana-3838	335	12	,	,	PUNCT
cana-3838	335	13	waris	waris	PROPN
cana-3838	335	14	,	,	PUNCT
cana-3838	335	15	a.	a.	PROPN
cana-3838	335	16	,	,	PUNCT
cana-3838	335	17	zafar	zafar	PROPN
cana-3838	335	18	,	,	PUNCT
cana-3838	335	19	k.	k.	PROPN
cana-3838	335	20	,	,	PUNCT
cana-3838	335	21	&	&	CCONJ
cana-3838	335	22	jamil	jamil	PROPN
cana-3838	335	23	,	,	PUNCT
cana-3838	335	24	m.	m.	NOUN
cana-3838	335	25	(	(	PUNCT
cana-3838	335	26	2020	2020	NUM
cana-3838	335	27	)	)	PUNCT
cana-3838	335	28	.	.	PUNCT
cana-3838	336	1	brain	brain	NOUN
cana-3838	336	2	tumour	tumour	NOUN
cana-3838	336	3	image	image	NOUN
cana-3838	336	4	segmentation	segmentation	NOUN
cana-3838	336	5	using	use	VERB
cana-3838	336	6	deep	deep	ADJ
cana-3838	336	7	networks	network	NOUN
cana-3838	336	8	.	.	PUNCT
cana-3838	337	1	ieee	ieee	NOUN
cana-3838	337	2	access	access	NOUN
cana-3838	337	3	,	,	PUNCT
cana-3838	337	4	8	8	NUM
cana-3838	337	5	,	,	PUNCT
cana-3838	337	6	153589–153598	153589–153598	NUM
cana-3838	337	7	.	.	PUNCT
cana-3838	338	1	https://doi.org/10.1109/access.2020.3018160	https://doi.org/10.1109/access.2020.3018160	PROPN
cana-3838	338	2	14	14	NUM
cana-3838	338	3	.	.	PUNCT
cana-3838	339	1	bhanothu	bhanothu	PROPN
cana-3838	339	2	,	,	PUNCT
cana-3838	339	3	y.	y.	PROPN
cana-3838	339	4	,	,	PUNCT
cana-3838	339	5	kamalakannan	kamalakannan	PROPN
cana-3838	339	6	,	,	PUNCT
cana-3838	339	7	a.	a.	NOUN
cana-3838	339	8	,	,	PUNCT
cana-3838	339	9	&	&	CCONJ
cana-3838	339	10	rajamanickam	rajamanickam	PROPN
cana-3838	339	11	,	,	PUNCT
cana-3838	339	12	g.	g.	PROPN
cana-3838	339	13	(	(	PUNCT
cana-3838	339	14	2020	2020	NUM
cana-3838	339	15	)	)	PUNCT
cana-3838	339	16	.	.	PUNCT
cana-3838	340	1	detection	detection	NOUN
cana-3838	340	2	and	and	CCONJ
cana-3838	340	3	classification	classification	NOUN
cana-3838	340	4	of	of	ADP
cana-3838	340	5	brain	brain	NOUN
cana-3838	340	6	tumor	tumor	NOUN
cana-3838	340	7	in	in	ADP
cana-3838	340	8	mri	mri	NOUN
cana-3838	340	9	images	image	NOUN
cana-3838	340	10	using	use	VERB
cana-3838	340	11	deep	deep	ADJ
cana-3838	340	12	convolutional	convolutional	ADJ
cana-3838	340	13	network	network	NOUN
cana-3838	340	14	.	.	PUNCT
cana-3838	341	1	2020	2020	NUM
cana-3838	341	2	6th	6th	ADJ
cana-3838	341	3	international	international	ADJ
cana-3838	341	4	conference	conference	NOUN
cana-3838	341	5	on	on	ADP
cana-3838	341	6	advanced	advanced	ADJ
cana-3838	341	7	computing	computing	NOUN
cana-3838	341	8	and	and	CCONJ
cana-3838	341	9	communication	communication	NOUN
cana-3838	341	10	systems	system	NOUN
cana-3838	341	11	,	,	PUNCT
cana-3838	341	12	icaccs	icaccs	NOUN
cana-3838	341	13	2020	2020	NUM
cana-3838	341	14	,	,	PUNCT
cana-3838	341	15	248–252	248–252	NUM
cana-3838	341	16	.	.	PUNCT
cana-3838	342	1	https://doi.org/10.1109/icaccs48705.2020.9074375	https://doi.org/10.1109/icaccs48705.2020.9074375	PROPN
cana-3838	342	2	15	15	NUM
cana-3838	342	3	.	.	PUNCT
cana-3838	343	1	ahmed	ahmed	PROPN
cana-3838	343	2	,	,	PUNCT
cana-3838	343	3	f.	f.	PROPN
cana-3838	343	4	,	,	PUNCT
cana-3838	343	5	asif	asif	PROPN
cana-3838	343	6	,	,	PUNCT
cana-3838	343	7	m.	m.	NOUN
cana-3838	343	8	,	,	PUNCT
cana-3838	343	9	saleem	saleem	PROPN
cana-3838	343	10	,	,	PUNCT
cana-3838	343	11	m.	m.	NOUN
cana-3838	343	12	,	,	PUNCT
cana-3838	343	13	mushtaq	mushtaq	PROPN
cana-3838	343	14	,	,	PUNCT
cana-3838	343	15	u.	u.	PROPN
cana-3838	343	16	f.	f.	PROPN
cana-3838	343	17	,	,	PUNCT
cana-3838	343	18	&	&	CCONJ
cana-3838	343	19	imran	imran	PROPN
cana-3838	343	20	,	,	PUNCT
cana-3838	343	21	m.	m.	NOUN
cana-3838	343	22	(	(	PUNCT
cana-3838	343	23	2023	2023	NUM
cana-3838	343	24	)	)	PUNCT
cana-3838	343	25	.	.	PUNCT
cana-3838	344	1	identification	identification	NOUN
cana-3838	344	2	and	and	CCONJ
cana-3838	344	3	prediction	prediction	NOUN
cana-3838	344	4	of	of	ADP
cana-3838	344	5	brain	brain	NOUN
cana-3838	344	6	tumor	tumor	NOUN
cana-3838	344	7	using	use	VERB
cana-3838	344	8	vgg-16	vgg-16	NOUN
cana-3838	344	9	empowered	empower	VERB
cana-3838	344	10	with	with	ADP
cana-3838	344	11	explainable	explainable	ADJ
cana-3838	344	12	artificial	artificial	ADJ
cana-3838	344	13	intelligence	intelligence	NOUN
cana-3838	344	14	.	.	PUNCT
cana-3838	345	1	international	international	ADJ
cana-3838	345	2	journal	journal	PROPN
cana-3838	345	3	of	of	ADP
cana-3838	345	4	computational	computational	ADJ
cana-3838	345	5	and	and	CCONJ
cana-3838	345	6	innovative	innovative	ADJ
cana-3838	345	7	sciences	science	NOUN
cana-3838	345	8	,	,	PUNCT
cana-3838	345	9	2(2	2(2	NUM
cana-3838	345	10	)	)	PUNCT
cana-3838	345	11	,	,	PUNCT
cana-3838	345	12	24	24	NUM
cana-3838	345	13	-	-	SYM
cana-3838	345	14	33	33	NUM
cana-3838	345	15	.	.	PUNCT
cana-3838	346	1	16	16	NUM
cana-3838	346	2	.	.	PUNCT
cana-3838	347	1	iqbal	iqbal	PROPN
cana-3838	347	2	,	,	PUNCT
cana-3838	347	3	s.	s.	PROPN
cana-3838	347	4	,	,	PUNCT
cana-3838	347	5	ghani	ghani	PROPN
cana-3838	347	6	,	,	PUNCT
cana-3838	347	7	m.	m.	NOUN
cana-3838	347	8	u.	u.	PROPN
cana-3838	347	9	,	,	PUNCT
cana-3838	347	10	saba	saba	PROPN
cana-3838	347	11	,	,	PUNCT
cana-3838	347	12	t.	t.	PROPN
cana-3838	347	13	,	,	PUNCT
cana-3838	347	14	&	&	CCONJ
cana-3838	347	15	rehman	rehman	PROPN
cana-3838	347	16	,	,	PUNCT
cana-3838	347	17	a.	a.	NOUN
cana-3838	347	18	(	(	PUNCT
cana-3838	347	19	2018	2018	NUM
cana-3838	347	20	)	)	PUNCT
cana-3838	347	21	.	.	PUNCT
cana-3838	348	1	brain	brain	NOUN
cana-3838	348	2	tumor	tumor	NOUN
cana-3838	348	3	segmentation	segmentation	NOUN
cana-3838	348	4	in	in	ADP
cana-3838	348	5	multi	multi	ADJ
cana-3838	348	6	spectral	spectral	ADJ
cana-3838	348	7	mri	mri	NOUN
cana-3838	348	8	using	use	VERB
cana-3838	348	9	convolutional	convolutional	ADJ
cana-3838	348	10	neural	neural	ADJ
cana-3838	348	11	networks	network	NOUN
cana-3838	348	12	(	(	PUNCT
cana-3838	348	13	cnn	cnn	PROPN
cana-3838	348	14	)	)	PUNCT
cana-3838	348	15	.	.	PUNCT
cana-3838	349	1	microscopy	microscopy	PROPN
cana-3838	349	2	research	research	NOUN
cana-3838	349	3	and	and	CCONJ
cana-3838	349	4	technique	technique	NOUN
cana-3838	349	5	,	,	PUNCT
cana-3838	349	6	81(4	81(4	NUM
cana-3838	349	7	)	)	PUNCT
cana-3838	349	8	,	,	PUNCT
cana-3838	349	9	419–427	419–427	NUM
cana-3838	349	10	.	.	PUNCT
cana-3838	349	11	https://doi.org/10.1002/jemt.22994	https://doi.org/10.1002/jemt.22994	NOUN
cana-3838	349	12	17	17	NUM
cana-3838	349	13	.	.	PUNCT
cana-3838	350	1	asiri	asiri	PROPN
cana-3838	350	2	,	,	PUNCT
cana-3838	350	3	a.	a.	NOUN
cana-3838	350	4	a.	a.	PROPN
cana-3838	350	5	,	,	PUNCT
cana-3838	350	6	shaf	shaf	PROPN
cana-3838	350	7	,	,	PUNCT
cana-3838	350	8	a.	a.	PROPN
cana-3838	350	9	,	,	PUNCT
cana-3838	350	10	ali	ali	PROPN
cana-3838	350	11	,	,	PUNCT
cana-3838	350	12	t.	t.	PROPN
cana-3838	350	13	,	,	PUNCT
cana-3838	350	14	aamir	aamir	PROPN
cana-3838	350	15	,	,	PUNCT
cana-3838	350	16	m.	m.	NOUN
cana-3838	350	17	,	,	PUNCT
cana-3838	350	18	irfan	irfan	PROPN
cana-3838	350	19	,	,	PUNCT
cana-3838	350	20	m.	m.	NOUN
cana-3838	350	21	,	,	PUNCT
cana-3838	350	22	alqahtani	alqahtani	PROPN
cana-3838	350	23	,	,	PUNCT
cana-3838	350	24	s.	s.	PROPN
cana-3838	350	25	,	,	PUNCT
cana-3838	350	26	mehdar	mehdar	NOUN
cana-3838	350	27	,	,	PUNCT
cana-3838	350	28	k.	k.	PROPN
cana-3838	350	29	m.	m.	PROPN
cana-3838	350	30	,	,	PUNCT
cana-3838	350	31	halawani	halawani	PROPN
cana-3838	350	32	,	,	PUNCT
cana-3838	350	33	h.	h.	PROPN
cana-3838	350	34	t.	t.	PROPN
cana-3838	350	35	,	,	PUNCT
cana-3838	350	36	alghamdi	alghamdi	NOUN
cana-3838	350	37	,	,	PUNCT
cana-3838	350	38	a.	a.	PROPN
cana-3838	350	39	h.	h.	PROPN
cana-3838	350	40	,	,	PUNCT
cana-3838	350	41	alshamrani	alshamrani	ADJ
cana-3838	350	42	,	,	PUNCT
cana-3838	350	43	a.	a.	PROPN
cana-3838	350	44	f.	f.	PROPN
cana-3838	350	45	a.	a.	PROPN
cana-3838	350	46	,	,	PUNCT
cana-3838	350	47	&	&	CCONJ
cana-3838	350	48	alqhtani	alqhtani	ADJ
cana-3838	350	49	,	,	PUNCT
cana-3838	350	50	s.	s.	PROPN
cana-3838	350	51	m.	m.	PROPN
cana-3838	350	52	(	(	PUNCT
cana-3838	350	53	2023	2023	NUM
cana-3838	350	54	)	)	PUNCT
cana-3838	350	55	.	.	PUNCT
cana-3838	351	1	brain	brain	NOUN
cana-3838	351	2	tumor	tumor	NOUN
cana-3838	351	3	detection	detection	NOUN
cana-3838	351	4	and	and	CCONJ
cana-3838	351	5	classification	classification	NOUN
cana-3838	351	6	using	use	VERB
cana-3838	351	7	fine	fine	ADV
cana-3838	351	8	-	-	PUNCT
cana-3838	351	9	tuned	tune	VERB
cana-3838	351	10	cnn	cnn	PROPN
cana-3838	351	11	with	with	ADP
cana-3838	351	12	resnet50	resnet50	NOUN
cana-3838	351	13	and	and	CCONJ
cana-3838	351	14	u	u	NOUN
cana-3838	351	15	-	-	ADJ
cana-3838	351	16	net	net	ADJ
cana-3838	351	17	model	model	NOUN
cana-3838	351	18	:	:	PUNCT
cana-3838	351	19	a	a	DET
cana-3838	351	20	study	study	NOUN
cana-3838	351	21	on	on	ADP
cana-3838	351	22	tcga	tcga	PROPN
cana-3838	351	23	-	-	PUNCT
cana-3838	351	24	lgg	lgg	NOUN
cana-3838	351	25	and	and	CCONJ
cana-3838	351	26	tcia	tcia	NOUN
cana-3838	351	27	dataset	dataset	VERB
cana-3838	351	28	for	for	ADP
cana-3838	351	29	mri	mri	NOUN
cana-3838	351	30	applications	application	NOUN
cana-3838	351	31	.	.	PUNCT
cana-3838	352	1	life	life	NOUN
cana-3838	352	2	,	,	PUNCT
cana-3838	352	3	13(7	13(7	NUM
cana-3838	352	4	)	)	PUNCT
cana-3838	352	5	.	.	PUNCT
cana-3838	353	1	https://doi.org/10.3390/life13071449	https://doi.org/10.3390/life13071449	PROPN
cana-3838	353	2	18	18	NUM
cana-3838	353	3	.	.	PUNCT
cana-3838	354	1	ben	ben	PROPN
cana-3838	354	2	naceur	naceur	PROPN
cana-3838	354	3	,	,	PUNCT
cana-3838	354	4	m.	m.	NOUN
cana-3838	354	5	,	,	PUNCT
cana-3838	354	6	akil	akil	PROPN
cana-3838	354	7	,	,	PUNCT
cana-3838	354	8	m.	m.	NOUN
cana-3838	354	9	,	,	PUNCT
cana-3838	354	10	saouli	saouli	PROPN
cana-3838	354	11	,	,	PUNCT
cana-3838	354	12	r.	r.	PROPN
cana-3838	354	13	,	,	PUNCT
cana-3838	354	14	&	&	CCONJ
cana-3838	354	15	kachouri	kachouri	PROPN
cana-3838	354	16	,	,	PUNCT
cana-3838	354	17	r.	r.	PROPN
cana-3838	354	18	(	(	PUNCT
cana-3838	354	19	2020	2020	NUM
cana-3838	354	20	)	)	PUNCT
cana-3838	354	21	.	.	PUNCT
cana-3838	355	1	deep	deep	ADJ
cana-3838	355	2	convolutional	convolutional	ADJ
cana-3838	355	3	neural	neural	ADJ
cana-3838	355	4	networks	network	NOUN
cana-3838	355	5	for	for	ADP
cana-3838	355	6	brain	brain	NOUN
cana-3838	355	7	tumor	tumor	NOUN
cana-3838	355	8	segmentation	segmentation	NOUN
cana-3838	355	9	:	:	PUNCT
cana-3838	355	10	boosting	boost	VERB
cana-3838	355	11	performance	performance	NOUN
cana-3838	355	12	using	use	VERB
cana-3838	355	13	deep	deep	ADJ
cana-3838	355	14	transfer	transfer	NOUN
cana-3838	355	15	learning	learning	NOUN
cana-3838	355	16	:	:	PUNCT
cana-3838	355	17	preliminary	preliminary	ADJ
cana-3838	355	18	results	result	NOUN
cana-3838	355	19	.	.	PUNCT
cana-3838	356	1	lecture	lecture	NOUN
cana-3838	356	2	notes	note	NOUN
cana-3838	356	3	in	in	ADP
cana-3838	356	4	computer	computer	NOUN
cana-3838	356	5	science	science	NOUN
cana-3838	356	6	(	(	PUNCT
cana-3838	356	7	including	include	VERB
cana-3838	356	8	subseries	subserie	NOUN
cana-3838	356	9	lecture	lecture	VERB
cana-3838	356	10	notes	note	NOUN
cana-3838	356	11	in	in	ADP
cana-3838	356	12	artificial	artificial	ADJ
cana-3838	356	13	intelligence	intelligence	NOUN
cana-3838	356	14	and	and	CCONJ
cana-3838	356	15	lecture	lecture	NOUN
cana-3838	356	16	notes	note	NOUN
cana-3838	356	17	in	in	ADP
cana-3838	356	18	bioinformatics	bioinformatics	NOUN
cana-3838	356	19	)	)	PUNCT
cana-3838	356	20	,	,	PUNCT
cana-3838	356	21	11993	11993	NUM
cana-3838	356	22	lncs	lnc	NOUN
cana-3838	356	23	,	,	PUNCT
cana-3838	356	24	303–315	303–315	NUM
cana-3838	356	25	.	.	PUNCT
cana-3838	357	1	https://doi.org/10.1007/978-3-030-46643-5_30	https://doi.org/10.1007/978-3-030-46643-5_30	PROPN
cana-3838	357	2	19	19	NUM
cana-3838	357	3	.	.	PUNCT
cana-3838	357	4	sahaai	sahaai	PROPN
cana-3838	357	5	,	,	PUNCT
cana-3838	357	6	m.	m.	PROPN
cana-3838	357	7	b.	b.	PROPN
cana-3838	357	8	,	,	PUNCT
cana-3838	357	9	jothilakshmi	jothilakshmi	PROPN
cana-3838	357	10	,	,	PUNCT
cana-3838	357	11	g.	g.	PROPN
cana-3838	357	12	r.	r.	PROPN
cana-3838	357	13	,	,	PUNCT
cana-3838	357	14	ravikumar	ravikumar	PROPN
cana-3838	357	15	,	,	PUNCT
cana-3838	357	16	d.	d.	PROPN
cana-3838	357	17	,	,	PUNCT
cana-3838	357	18	prasath	prasath	PROPN
cana-3838	357	19	,	,	PUNCT
cana-3838	357	20	r.	r.	PROPN
cana-3838	357	21	,	,	PUNCT
cana-3838	357	22	&	&	CCONJ
cana-3838	357	23	singh	singh	PROPN
cana-3838	357	24	,	,	PUNCT
cana-3838	357	25	s.	s.	PROPN
cana-3838	357	26	(	(	PUNCT
cana-3838	357	27	2022	2022	NUM
cana-3838	357	28	)	)	PUNCT
cana-3838	357	29	.	.	PUNCT
cana-3838	358	1	resnet-50	resnet-50	PROPN
cana-3838	358	2	based	base	VERB
cana-3838	358	3	deep	deep	ADJ
cana-3838	358	4	neural	neural	ADJ
cana-3838	358	5	network	network	NOUN
cana-3838	358	6	using	use	VERB
cana-3838	358	7	transfer	transfer	NOUN
cana-3838	358	8	learning	learning	NOUN
cana-3838	358	9	for	for	ADP
cana-3838	358	10	brain	brain	NOUN
cana-3838	358	11	tumor	tumor	NOUN
cana-3838	358	12	classification	classification	NOUN
cana-3838	358	13	.	.	PUNCT
cana-3838	359	1	aip	aip	PROPN
cana-3838	359	2	conference	conference	NOUN
cana-3838	359	3	proceedings	proceeding	NOUN
cana-3838	359	4	,	,	PUNCT
cana-3838	359	5	2463(may	2463(may	NUM
cana-3838	359	6	)	)	PUNCT
cana-3838	359	7	.	.	PUNCT
cana-3838	360	1	https://doi.org/10.1063/5.0082328	https://doi.org/10.1063/5.0082328	PROPN
cana-3838	360	2	communications	communication	NOUN
cana-3838	360	3	on	on	ADP
cana-3838	360	4	applied	apply	VERB
cana-3838	360	5	nonlinear	nonlinear	ADJ
cana-3838	360	6	analysis	analysis	NOUN
cana-3838	360	7	issn	issn	NOUN
cana-3838	360	8	:	:	PUNCT
cana-3838	360	9	1074	1074	NUM
cana-3838	360	10	-	-	PUNCT
cana-3838	360	11	133x	133x	NUM
cana-3838	360	12	vol	vol	NOUN
cana-3838	360	13	32	32	NUM
cana-3838	360	14	no	no	NOUN
cana-3838	360	15	.	.	PUNCT
cana-3838	361	1	9s	9s	NUM
cana-3838	361	2	(	(	PUNCT
cana-3838	361	3	2025	2025	NUM
cana-3838	361	4	)	)	PUNCT
cana-3838	361	5	76	76	NUM
cana-3838	362	1	https://internationalpubls.com	https://internationalpubls.com	X
cana-3838	362	2	20	20	NUM
cana-3838	362	3	.	.	PUNCT
cana-3838	363	1	bhandari	bhandari	PROPN
cana-3838	363	2	,	,	PUNCT
cana-3838	363	3	a.	a.	PROPN
cana-3838	363	4	,	,	PUNCT
cana-3838	363	5	koppen	koppen	PROPN
cana-3838	363	6	,	,	PUNCT
cana-3838	363	7	j.	j.	PROPN
cana-3838	363	8	,	,	PUNCT
cana-3838	363	9	&	&	CCONJ
cana-3838	363	10	agzarian	agzarian	ADJ
cana-3838	363	11	,	,	PUNCT
cana-3838	363	12	m.	m.	NOUN
cana-3838	363	13	(	(	PUNCT
cana-3838	363	14	2020	2020	NUM
cana-3838	363	15	)	)	PUNCT
cana-3838	363	16	.	.	PUNCT
cana-3838	364	1	convolutional	convolutional	ADJ
cana-3838	364	2	neural	neural	ADJ
cana-3838	364	3	networks	network	NOUN
cana-3838	364	4	for	for	ADP
cana-3838	364	5	brain	brain	NOUN
cana-3838	364	6	tumour	tumour	NOUN
cana-3838	364	7	segmentation	segmentation	NOUN
cana-3838	364	8	.	.	PUNCT
cana-3838	365	1	insights	insight	NOUN
cana-3838	365	2	into	into	ADP
cana-3838	365	3	imaging	imaging	NOUN
cana-3838	365	4	,	,	PUNCT
cana-3838	365	5	11(1	11(1	NUM
cana-3838	365	6	)	)	PUNCT
cana-3838	365	7	.	.	PUNCT
cana-3838	366	1	https://doi.org/10.1186/s13244-020	https://doi.org/10.1186/s13244-020	VERB
cana-3838	366	2	00869	00869	NUM
cana-3838	366	3	-	-	SYM
cana-3838	366	4	4	4	NUM
cana-3838	366	5	21	21	NUM
cana-3838	366	6	.	.	PUNCT
cana-3838	367	1	tandel	tandel	PROPN
cana-3838	367	2	,	,	PUNCT
cana-3838	367	3	g.	g.	PROPN
cana-3838	367	4	s.	s.	PROPN
cana-3838	367	5	,	,	PUNCT
cana-3838	367	6	tiwari	tiwari	PROPN
cana-3838	367	7	,	,	PUNCT
cana-3838	367	8	a.	a.	PROPN
cana-3838	367	9	,	,	PUNCT
cana-3838	367	10	&	&	CCONJ
cana-3838	367	11	kakde	kakde	PROPN
cana-3838	367	12	,	,	PUNCT
cana-3838	367	13	o.	o.	PROPN
cana-3838	367	14	g.	g.	PROPN
cana-3838	367	15	(	(	PUNCT
cana-3838	367	16	2022	2022	NUM
cana-3838	367	17	)	)	PUNCT
cana-3838	367	18	.	.	PUNCT
cana-3838	368	1	performance	performance	NOUN
cana-3838	368	2	enhancement	enhancement	NOUN
cana-3838	368	3	of	of	ADP
cana-3838	368	4	mri	mri	NOUN
cana-3838	368	5	-	-	PUNCT
cana-3838	368	6	based	base	VERB
cana-3838	368	7	brain	brain	NOUN
cana-3838	368	8	tumor	tumor	NOUN
cana-3838	368	9	classification	classification	NOUN
cana-3838	368	10	using	use	VERB
cana-3838	368	11	suitable	suitable	ADJ
cana-3838	368	12	segmentation	segmentation	NOUN
cana-3838	368	13	method	method	NOUN
cana-3838	368	14	and	and	CCONJ
cana-3838	368	15	deep	deep	ADJ
cana-3838	368	16	learning	learning	NOUN
cana-3838	368	17	-	-	PUNCT
cana-3838	368	18	based	base	VERB
cana-3838	368	19	ensemble	ensemble	ADJ
cana-3838	368	20	algorithm	algorithm	NOUN
cana-3838	368	21	.	.	PUNCT
cana-3838	369	1	biomedical	biomedical	ADJ
cana-3838	369	2	signal	signal	NOUN
cana-3838	369	3	processing	processing	NOUN
cana-3838	369	4	and	and	CCONJ
cana-3838	369	5	control	control	NOUN
cana-3838	369	6	,	,	PUNCT
cana-3838	369	7	78	78	NUM
cana-3838	369	8	,	,	PUNCT
cana-3838	369	9	104018	104018	NUM
cana-3838	369	10	.	.	PUNCT
cana-3838	370	1	22	22	NUM
cana-3838	370	2	.	.	PUNCT
cana-3838	371	1	pereira	pereira	PROPN
cana-3838	371	2	,	,	PUNCT
cana-3838	371	3	s.	s.	PROPN
cana-3838	371	4	,	,	PUNCT
cana-3838	371	5	pinto	pinto	NOUN
cana-3838	371	6	,	,	PUNCT
cana-3838	371	7	a.	a.	NOUN
cana-3838	371	8	,	,	PUNCT
cana-3838	371	9	alves	alves	PROPN
cana-3838	371	10	,	,	PUNCT
cana-3838	371	11	v.	v.	PROPN
cana-3838	371	12	,	,	PUNCT
cana-3838	371	13	&	&	CCONJ
cana-3838	371	14	silva	silva	PROPN
cana-3838	371	15	,	,	PUNCT
cana-3838	371	16	c.	c.	PROPN
cana-3838	371	17	a.	a.	PROPN
cana-3838	371	18	(	(	PUNCT
cana-3838	371	19	2016	2016	NUM
cana-3838	371	20	)	)	PUNCT
cana-3838	371	21	.	.	PUNCT
cana-3838	372	1	brain	brain	NOUN
cana-3838	372	2	tumor	tumor	NOUN
cana-3838	372	3	segmentation	segmentation	NOUN
cana-3838	372	4	using	use	VERB
cana-3838	372	5	convolutional	convolutional	ADJ
cana-3838	372	6	neural	neural	ADJ
cana-3838	372	7	networks	network	NOUN
cana-3838	372	8	in	in	ADP
cana-3838	372	9	mri	mri	NOUN
cana-3838	372	10	images	image	NOUN
cana-3838	372	11	.	.	PUNCT
cana-3838	373	1	ieee	ieee	NOUN
cana-3838	373	2	transactions	transaction	NOUN
cana-3838	373	3	on	on	ADP
cana-3838	373	4	medical	medical	ADJ
cana-3838	373	5	imaging	imaging	NOUN
cana-3838	373	6	,	,	PUNCT
cana-3838	373	7	35(5	35(5	NUM
cana-3838	373	8	)	)	PUNCT
cana-3838	373	9	,	,	PUNCT
cana-3838	373	10	1240–1251	1240–1251	NUM
cana-3838	373	11	.	.	PUNCT
cana-3838	374	1	https://doi.org/10.1109/tmi.2016.2538465	https://doi.org/10.1109/tmi.2016.2538465	NOUN
cana-3838	374	2	23	23	NUM
cana-3838	374	3	.	.	PUNCT
cana-3838	375	1	ghosh	ghosh	PROPN
cana-3838	375	2	,	,	PUNCT
cana-3838	375	3	s.	s.	PROPN
cana-3838	375	4	,	,	PUNCT
cana-3838	375	5	chaki	chaki	PROPN
cana-3838	375	6	,	,	PUNCT
cana-3838	375	7	a.	a.	NOUN
cana-3838	375	8	,	,	PUNCT
cana-3838	375	9	&	&	CCONJ
cana-3838	375	10	santosh	santosh	PROPN
cana-3838	375	11	,	,	PUNCT
cana-3838	375	12	k.	k.	PROPN
cana-3838	375	13	(	(	PUNCT
cana-3838	375	14	2021	2021	NUM
cana-3838	375	15	)	)	PUNCT
cana-3838	375	16	.	.	PUNCT
cana-3838	375	17	improved	improve	VERB
cana-3838	375	18	u	u	ADJ
cana-3838	375	19	-	-	ADJ
cana-3838	375	20	net	net	ADJ
cana-3838	375	21	architecture	architecture	NOUN
cana-3838	375	22	with	with	ADP
cana-3838	375	23	vgg-16	vgg-16	NOUN
cana-3838	375	24	for	for	ADP
cana-3838	375	25	brain	brain	NOUN
cana-3838	375	26	tumor	tumor	NOUN
cana-3838	375	27	segmentation	segmentation	NOUN
cana-3838	375	28	.	.	PUNCT
cana-3838	376	1	physical	physical	ADJ
cana-3838	376	2	and	and	CCONJ
cana-3838	376	3	engineering	engineering	NOUN
cana-3838	376	4	sciences	science	NOUN
cana-3838	376	5	in	in	ADP
cana-3838	376	6	medicine	medicine	NOUN
cana-3838	376	7	,	,	PUNCT
cana-3838	376	8	44(3	44(3	NOUN
cana-3838	376	9	)	)	PUNCT
cana-3838	376	10	,	,	PUNCT
cana-3838	376	11	703–712	703–712	NUM
cana-3838	376	12	.	.	PUNCT
cana-3838	377	1	https://doi.org/10.1007/s13246-021-01019-w	https://doi.org/10.1007/s13246-021-01019-w	NOUN