id	sid	tid	token	lemma	pos
cana-3851	1	1	communications	communication	NOUN
cana-3851	1	2	on	on	ADP
cana-3851	1	3	applied	apply	VERB
cana-3851	1	4	nonlinear	nonlinear	ADJ
cana-3851	1	5	analysis	analysis	NOUN
cana-3851	1	6	issn	issn	NOUN
cana-3851	1	7	:	:	PUNCT
cana-3851	1	8	1074	1074	NUM
cana-3851	1	9	-	-	PUNCT
cana-3851	1	10	133x	133x	NUM
cana-3851	1	11	vol	vol	NOUN
cana-3851	1	12	32	32	NUM
cana-3851	1	13	no	no	NOUN
cana-3851	1	14	.	.	PUNCT
cana-3851	2	1	9s	9s	NUM
cana-3851	2	2	(	(	PUNCT
cana-3851	2	3	2025	2025	NUM
cana-3851	2	4	)	)	PUNCT
cana-3851	2	5	215	215	NUM
cana-3851	2	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-3851	2	7	a	a	DET
cana-3851	2	8	hybrid	hybrid	ADJ
cana-3851	2	9	model	model	NOUN
cana-3851	2	10	for	for	ADP
cana-3851	2	11	brain	brain	NOUN
cana-3851	2	12	tumor	tumor	NOUN
cana-3851	2	13	segmentation	segmentation	NOUN
cana-3851	2	14	using	use	VERB
cana-3851	2	15	vgg16	vgg16	PROPN
cana-3851	2	16	and	and	CCONJ
cana-3851	2	17	resnet50	resnet50	VERB
cana-3851	2	18	1dr.v.r	1dr.v.r	NOUN
cana-3851	2	19	.	.	PUNCT
cana-3851	3	1	elangovan	elangovan	PROPN
cana-3851	3	2	,	,	PUNCT
cana-3851	3	3	2dr.d.helen,3dr.s.gokila,4dr.s.rajeswari,5dr.m.ganesh	2dr.d.helen,3dr.s.gokila,4dr.s.rajeswari,5dr.m.ganesh	NUM
cana-3851	3	4	raja	raja	NOUN
cana-3851	3	5	1assistant	1assistant	NUM
cana-3851	3	6	professor	professor	NOUN
cana-3851	3	7	,	,	PUNCT
cana-3851	3	8	department	department	NOUN
cana-3851	3	9	of	of	ADP
cana-3851	3	10	computer	computer	NOUN
cana-3851	3	11	applications	application	NOUN
cana-3851	3	12	,	,	PUNCT
cana-3851	3	13	faculty	faculty	NOUN
cana-3851	3	14	of	of	ADP
cana-3851	3	15	science	science	NOUN
cana-3851	3	16	and	and	CCONJ
cana-3851	3	17	humanities	humanity	NOUN
cana-3851	3	18	,	,	PUNCT
cana-3851	3	19	srm	srm	PROPN
cana-3851	3	20	institute	institute	PROPN
cana-3851	3	21	of	of	ADP
cana-3851	3	22	science	science	NOUN
cana-3851	3	23	and	and	CCONJ
cana-3851	3	24	technology	technology	NOUN
cana-3851	3	25	,	,	PUNCT
cana-3851	3	26	kattankulathur	kattankulathur	PROPN
cana-3851	3	27	,	,	PUNCT
cana-3851	3	28	chennai	chennai	PROPN
cana-3851	3	29	.	.	PUNCT
cana-3851	4	1	elangotesting@gmail.com,elangovv1@srmist.edu.in	elangotesting@gmail.com,elangovv1@srmist.edu.in	PROPN
cana-3851	4	2	2assistant	2assistant	PROPN
cana-3851	4	3	professor	professor	NOUN
cana-3851	4	4	,	,	PUNCT
cana-3851	4	5	department	department	NOUN
cana-3851	4	6	of	of	ADP
cana-3851	4	7	computer	computer	NOUN
cana-3851	4	8	applications	application	NOUN
cana-3851	4	9	,	,	PUNCT
cana-3851	4	10	faculty	faculty	NOUN
cana-3851	4	11	of	of	ADP
cana-3851	4	12	science	science	NOUN
cana-3851	4	13	and	and	CCONJ
cana-3851	4	14	humanities	humanity	NOUN
cana-3851	4	15	,	,	PUNCT
cana-3851	4	16	srm	srm	PROPN
cana-3851	4	17	institute	institute	PROPN
cana-3851	4	18	of	of	ADP
cana-3851	4	19	science	science	NOUN
cana-3851	4	20	and	and	CCONJ
cana-3851	4	21	technology	technology	NOUN
cana-3851	4	22	,	,	PUNCT
cana-3851	4	23	kattankulathur	kattankulathur	PROPN
cana-3851	4	24	,	,	PUNCT
cana-3851	4	25	chennai	chennai	PROPN
cana-3851	4	26	.	.	PUNCT
cana-3851	5	1	helend@srmist.edu.in	helend@srmist.edu.in	PROPN
cana-3851	5	2	3associate	3associate	NUM
cana-3851	5	3	professor	professor	NOUN
cana-3851	5	4	,	,	PUNCT
cana-3851	5	5	department	department	NOUN
cana-3851	5	6	of	of	ADP
cana-3851	5	7	computer	computer	NOUN
cana-3851	5	8	application	application	NOUN
cana-3851	5	9	,	,	PUNCT
cana-3851	5	10	hindustan	hindustan	PROPN
cana-3851	5	11	institute	institute	PROPN
cana-3851	5	12	of	of	ADP
cana-3851	5	13	science	science	NOUN
cana-3851	5	14	and	and	CCONJ
cana-3851	5	15	technology	technology	NOUN
cana-3851	5	16	,	,	PUNCT
cana-3851	5	17	chennai	chennai	PROPN
cana-3851	5	18	,	,	PUNCT
cana-3851	5	19	sgokilas@gmail.com	sgokilas@gmail.com	PROPN
cana-3851	6	1	4assistant	4assistant	NUM
cana-3851	6	2	professor	professor	NOUN
cana-3851	6	3	,	,	PUNCT
cana-3851	6	4	pg	pg	PROPN
cana-3851	6	5	department	department	PROPN
cana-3851	6	6	of	of	ADP
cana-3851	6	7	computer	computer	NOUN
cana-3851	6	8	science	science	NOUN
cana-3851	6	9	,	,	PUNCT
cana-3851	6	10	shrimathi	shrimathi	PROPN
cana-3851	6	11	devkunvar	devkunvar	PROPN
cana-3851	6	12	nanalal	nanalal	PROPN
cana-3851	6	13	bhatt	bhatt	PROPN
cana-3851	6	14	vaishnav	vaishnav	PROPN
cana-3851	6	15	college	college	PROPN
cana-3851	6	16	for	for	ADP
cana-3851	6	17	women	woman	NOUN
cana-3851	6	18	,	,	PUNCT
cana-3851	6	19	chennai	chennai	PROPN
cana-3851	6	20	.	.	PUNCT
cana-3851	7	1	rajeswari.s@sdnbvc.edu.in	rajeswari.s@sdnbvc.edu.in	VERB
cana-3851	7	2	5assistant	5assistant	NUM
cana-3851	7	3	professor	professor	NOUN
cana-3851	7	4	,	,	PUNCT
cana-3851	7	5	department	department	NOUN
cana-3851	7	6	of	of	ADP
cana-3851	7	7	computer	computer	NOUN
cana-3851	7	8	science	science	NOUN
cana-3851	7	9	,	,	PUNCT
cana-3851	7	10	dhanraj	dhanraj	PROPN
cana-3851	7	11	baid	baid	PROPN
cana-3851	7	12	jain	jain	PROPN
cana-3851	7	13	college	college	PROPN
cana-3851	7	14	,	,	PUNCT
cana-3851	7	15	chennai	chennai	PROPN
cana-3851	7	16	,	,	PUNCT
cana-3851	7	17	ganeshraja888@gmail.com	ganeshraja888@gmail.com	X
cana-3851	7	18	article	article	NOUN
cana-3851	7	19	history	history	NOUN
cana-3851	7	20	:	:	PUNCT
cana-3851	7	21	received	receive	VERB
cana-3851	7	22	:	:	PUNCT
cana-3851	7	23	13	13	NUM
cana-3851	7	24	-	-	SYM
cana-3851	7	25	11	11	NUM
cana-3851	7	26	-	-	PUNCT
cana-3851	7	27	2024	2024	NUM
cana-3851	7	28	revised:25	revised:25	NOUN
cana-3851	7	29	-	-	PUNCT
cana-3851	7	30	12	12	NUM
cana-3851	7	31	-	-	PUNCT
cana-3851	7	32	2024	2024	NUM
cana-3851	7	33	accepted:09	accepted:09	NOUN
cana-3851	7	34	-	-	PUNCT
cana-3851	7	35	01	01	NUM
cana-3851	7	36	-	-	PUNCT
cana-3851	7	37	2025	2025	NUM
cana-3851	7	38	abstract	abstract	NOUN
cana-3851	7	39	:	:	PUNCT
cana-3851	7	40	cancers	cancer	NOUN
cana-3851	7	41	of	of	ADP
cana-3851	7	42	the	the	DET
cana-3851	7	43	brain	brain	NOUN
cana-3851	7	44	are	be	AUX
cana-3851	7	45	among	among	ADP
cana-3851	7	46	the	the	DET
cana-3851	7	47	worst	bad	ADJ
cana-3851	7	48	illnesses	illness	NOUN
cana-3851	7	49	a	a	DET
cana-3851	7	50	person	person	NOUN
cana-3851	7	51	may	may	AUX
cana-3851	7	52	get	get	VERB
cana-3851	7	53	.	.	PUNCT
cana-3851	8	1	the	the	DET
cana-3851	8	2	course	course	NOUN
cana-3851	8	3	of	of	ADP
cana-3851	8	4	medical	medical	ADJ
cana-3851	8	5	therapy	therapy	NOUN
cana-3851	8	6	is	be	AUX
cana-3851	8	7	mostly	mostly	ADV
cana-3851	8	8	determined	determine	VERB
cana-3851	8	9	by	by	ADP
cana-3851	8	10	the	the	DET
cana-3851	8	11	tumor	tumor	NOUN
cana-3851	8	12	's	's	PART
cana-3851	8	13	location	location	NOUN
cana-3851	8	14	and	and	CCONJ
cana-3851	8	15	kind	kind	ADJ
cana-3851	8	16	.	.	PUNCT
cana-3851	9	1	neuro	neuro	PROPN
cana-3851	9	2	specialists	specialist	NOUN
cana-3851	9	3	and	and	CCONJ
cana-3851	9	4	radiologists	radiologist	NOUN
cana-3851	9	5	must	must	AUX
cana-3851	9	6	carefully	carefully	ADV
cana-3851	9	7	review	review	VERB
cana-3851	9	8	magnetic	magnetic	ADJ
cana-3851	9	9	resonance	resonance	NOUN
cana-3851	9	10	imaging	imaging	NOUN
cana-3851	9	11	(	(	PUNCT
cana-3851	9	12	mri	mri	NOUN
cana-3851	9	13	)	)	PUNCT
cana-3851	9	14	pictures	picture	NOUN
cana-3851	9	15	in	in	ADP
cana-3851	9	16	order	order	NOUN
cana-3851	9	17	to	to	PART
cana-3851	9	18	arrive	arrive	VERB
cana-3851	9	19	at	at	ADP
cana-3851	9	20	a	a	DET
cana-3851	9	21	definitive	definitive	ADJ
cana-3851	9	22	diagnosis	diagnosis	NOUN
cana-3851	9	23	of	of	ADP
cana-3851	9	24	a	a	DET
cana-3851	9	25	malignancy	malignancy	NOUN
cana-3851	9	26	.	.	PUNCT
cana-3851	10	1	treatment	treatment	NOUN
cana-3851	10	2	option	option	NOUN
cana-3851	10	3	mapping	mapping	NOUN
cana-3851	10	4	,	,	PUNCT
cana-3851	10	5	disease	disease	NOUN
cana-3851	10	6	progression	progression	NOUN
cana-3851	10	7	monitoring	monitoring	NOUN
cana-3851	10	8	,	,	PUNCT
cana-3851	10	9	and	and	CCONJ
cana-3851	10	10	image	image	NOUN
cana-3851	10	11	-	-	PUNCT
cana-3851	10	12	based	base	VERB
cana-3851	10	13	tumor	tumor	NOUN
cana-3851	10	14	segmentation	segmentation	NOUN
cana-3851	10	15	are	be	AUX
cana-3851	10	16	of	of	ADP
cana-3851	10	17	utmost	utmost	ADJ
cana-3851	10	18	importance	importance	NOUN
cana-3851	10	19	in	in	ADP
cana-3851	10	20	medical	medical	ADJ
cana-3851	10	21	imaging	imaging	NOUN
cana-3851	10	22	because	because	SCONJ
cana-3851	10	23	they	they	PRON
cana-3851	10	24	provide	provide	VERB
cana-3851	10	25	information	information	NOUN
cana-3851	10	26	vital	vital	ADJ
cana-3851	10	27	for	for	ADP
cana-3851	10	28	cancer	cancer	NOUN
cana-3851	10	29	analysis	analysis	NOUN
cana-3851	10	30	and	and	CCONJ
cana-3851	10	31	diagnosis	diagnosis	NOUN
cana-3851	10	32	.	.	PUNCT
cana-3851	11	1	some	some	PRON
cana-3851	11	2	have	have	AUX
cana-3851	11	3	speculated	speculate	VERB
cana-3851	11	4	that	that	SCONJ
cana-3851	11	5	deep	deep	ADJ
cana-3851	11	6	learning	learning	NOUN
cana-3851	11	7	might	might	AUX
cana-3851	11	8	be	be	AUX
cana-3851	11	9	the	the	DET
cana-3851	11	10	key	key	NOUN
cana-3851	11	11	to	to	ADP
cana-3851	11	12	better	well	ADJ
cana-3851	11	13	brain	brain	NOUN
cana-3851	11	14	cancer	cancer	NOUN
cana-3851	11	15	diagnosis	diagnosis	NOUN
cana-3851	11	16	and	and	CCONJ
cana-3851	11	17	treatment	treatment	NOUN
cana-3851	11	18	.	.	PUNCT
cana-3851	12	1	with	with	ADP
cana-3851	12	2	its	its	PRON
cana-3851	12	3	state	state	NOUN
cana-3851	12	4	-	-	PUNCT
cana-3851	12	5	of	of	ADP
cana-3851	12	6	-	-	PUNCT
cana-3851	12	7	the	the	DET
cana-3851	12	8	-	-	PUNCT
cana-3851	12	9	art	art	NOUN
cana-3851	12	10	segmentation	segmentation	NOUN
cana-3851	12	11	and	and	CCONJ
cana-3851	12	12	detection	detection	NOUN
cana-3851	12	13	capabilities	capability	NOUN
cana-3851	12	14	,	,	PUNCT
cana-3851	12	15	the	the	DET
cana-3851	12	16	segmentation	segmentation	NOUN
cana-3851	12	17	strategy	strategy	NOUN
cana-3851	12	18	has	have	AUX
cana-3851	12	19	significantly	significantly	ADV
cana-3851	12	20	improved	improve	VERB
cana-3851	12	21	the	the	DET
cana-3851	12	22	removal	removal	NOUN
cana-3851	12	23	of	of	ADP
cana-3851	12	24	abnormal	abnormal	ADJ
cana-3851	12	25	tumor	tumor	NOUN
cana-3851	12	26	regions	region	NOUN
cana-3851	12	27	from	from	ADP
cana-3851	12	28	the	the	DET
cana-3851	12	29	brain	brain	NOUN
cana-3851	12	30	.	.	PUNCT
cana-3851	13	1	in	in	ADP
cana-3851	13	2	this	this	DET
cana-3851	13	3	study	study	NOUN
cana-3851	13	4	,	,	PUNCT
cana-3851	13	5	we	we	PRON
cana-3851	13	6	published	publish	VERB
cana-3851	13	7	a	a	DET
cana-3851	13	8	vgg16	vgg16	NOUN
cana-3851	13	9	and	and	CCONJ
cana-3851	13	10	resnet50	resnet50	VERB
cana-3851	13	11	hybrid	hybrid	ADJ
cana-3851	13	12	model	model	NOUN
cana-3851	13	13	for	for	ADP
cana-3851	13	14	mri	mri	NOUN
cana-3851	13	15	brain	brain	NOUN
cana-3851	13	16	tumor	tumor	NOUN
cana-3851	13	17	segmentation	segmentation	NOUN
cana-3851	13	18	.	.	PUNCT
cana-3851	14	1	with	with	ADP
cana-3851	14	2	the	the	DET
cana-3851	14	3	use	use	NOUN
cana-3851	14	4	of	of	ADP
cana-3851	14	5	the	the	DET
cana-3851	14	6	resnet50	resnet50	NOUN
cana-3851	14	7	algorithm	algorithm	NOUN
cana-3851	14	8	and	and	CCONJ
cana-3851	14	9	the	the	DET
cana-3851	14	10	vgg16	vgg16	NOUN
cana-3851	14	11	,	,	PUNCT
cana-3851	14	12	a	a	DET
cana-3851	14	13	transfer	transfer	NOUN
cana-3851	14	14	learning	learning	NOUN
cana-3851	14	15	method	method	NOUN
cana-3851	14	16	,	,	PUNCT
cana-3851	14	17	brain	brain	NOUN
cana-3851	14	18	tumors	tumor	NOUN
cana-3851	14	19	may	may	AUX
cana-3851	14	20	be	be	AUX
cana-3851	14	21	detected	detect	VERB
cana-3851	14	22	in	in	ADP
cana-3851	14	23	segmented	segment	VERB
cana-3851	14	24	pictures	picture	NOUN
cana-3851	14	25	.	.	PUNCT
cana-3851	15	1	the	the	DET
cana-3851	15	2	findings	finding	NOUN
cana-3851	15	3	show	show	VERB
cana-3851	15	4	that	that	SCONJ
cana-3851	15	5	our	our	PRON
cana-3851	15	6	suggested	suggest	VERB
cana-3851	15	7	approach	approach	NOUN
cana-3851	15	8	is	be	AUX
cana-3851	15	9	more	more	ADV
cana-3851	15	10	accurate	accurate	ADJ
cana-3851	15	11	and	and	CCONJ
cana-3851	15	12	performs	perform	VERB
cana-3851	15	13	better	well	ADJ
cana-3851	15	14	than	than	ADP
cana-3851	15	15	other	other	ADJ
cana-3851	15	16	models	model	NOUN
cana-3851	15	17	when	when	SCONJ
cana-3851	15	18	compared	compare	VERB
cana-3851	15	19	side	side	NOUN
cana-3851	15	20	by	by	ADP
cana-3851	15	21	side	side	NOUN
cana-3851	15	22	.	.	PUNCT
cana-3851	16	1	keywords	keyword	NOUN
cana-3851	16	2	:	:	PUNCT
cana-3851	16	3	image	image	NOUN
cana-3851	16	4	segmentation	segmentation	NOUN
cana-3851	16	5	,	,	PUNCT
cana-3851	16	6	cnn	cnn	PROPN
cana-3851	16	7	,	,	PUNCT
cana-3851	16	8	transfer	transfer	NOUN
cana-3851	16	9	learning	learning	NOUN
cana-3851	16	10	,	,	PUNCT
cana-3851	16	11	vgg16	vgg16	PROPN
cana-3851	16	12	,	,	PUNCT
cana-3851	16	13	resnet50	resnet50	NOUN
cana-3851	16	14	1	1	NUM
cana-3851	16	15	.	.	PUNCT
cana-3851	17	1	introduction	introduction	NOUN
cana-3851	17	2	tumors	tumor	NOUN
cana-3851	17	3	in	in	ADP
cana-3851	17	4	the	the	DET
cana-3851	17	5	brain	brain	NOUN
cana-3851	17	6	develop	develop	VERB
cana-3851	17	7	when	when	SCONJ
cana-3851	17	8	the	the	DET
cana-3851	17	9	brain	brain	NOUN
cana-3851	17	10	's	's	PART
cana-3851	17	11	cell	cell	NOUN
cana-3851	17	12	development	development	NOUN
cana-3851	17	13	is	be	AUX
cana-3851	17	14	abnormal	abnormal	ADJ
cana-3851	17	15	and	and	CCONJ
cana-3851	17	16	uncontrolled	uncontrolled	ADJ
cana-3851	17	17	.	.	PUNCT
cana-3851	18	1	since	since	SCONJ
cana-3851	18	2	the	the	DET
cana-3851	18	3	human	human	ADJ
cana-3851	18	4	skull	skull	NOUN
cana-3851	18	5	is	be	AUX
cana-3851	18	6	inflexible	inflexible	ADJ
cana-3851	18	7	and	and	CCONJ
cana-3851	18	8	has	have	VERB
cana-3851	18	9	limited	limited	ADJ
cana-3851	18	10	space	space	NOUN
cana-3851	18	11	,	,	PUNCT
cana-3851	18	12	any	any	DET
cana-3851	18	13	sudden	sudden	ADJ
cana-3851	18	14	alteration	alteration	NOUN
cana-3851	18	15	would	would	AUX
cana-3851	18	16	have	have	VERB
cana-3851	18	17	an	an	DET
cana-3851	18	18	effect	effect	NOUN
cana-3851	18	19	on	on	ADP
cana-3851	18	20	human	human	ADJ
cana-3851	18	21	function	function	NOUN
cana-3851	18	22	according	accord	VERB
cana-3851	18	23	to	to	ADP
cana-3851	18	24	the	the	DET
cana-3851	18	25	region	region	NOUN
cana-3851	18	26	of	of	ADP
cana-3851	18	27	the	the	DET
cana-3851	18	28	brain	brain	NOUN
cana-3851	18	29	impacted	impact	VERB
cana-3851	18	30	,	,	PUNCT
cana-3851	18	31	and	and	CCONJ
cana-3851	18	32	the	the	DET
cana-3851	18	33	cancer	cancer	NOUN
cana-3851	18	34	might	might	AUX
cana-3851	18	35	spread	spread	VERB
cana-3851	18	36	to	to	ADP
cana-3851	18	37	other	other	ADJ
cana-3851	18	38	organs	organ	NOUN
cana-3851	18	39	.	.	PUNCT
cana-3851	19	1	as	as	ADP
cana-3851	19	2	to	to	ADP
cana-3851	19	3	the	the	DET
cana-3851	19	4	world	world	PROPN
cana-3851	19	5	health	health	PROPN
cana-3851	19	6	organization	organization	PROPN
cana-3851	19	7	’s	’s	PART
cana-3851	19	8	world	world	NOUN
cana-3851	19	9	cancer	cancer	NOUN
cana-3851	19	10	report	report	NOUN
cana-3851	19	11	,	,	PUNCT
cana-3851	19	12	fewer	few	ADJ
cana-3851	19	13	than	than	ADP
cana-3851	19	14	2	2	NUM
cana-3851	19	15	%	%	NOUN
cana-3851	19	16	of	of	ADP
cana-3851	19	17	all	all	DET
cana-3851	19	18	human	human	ADJ
cana-3851	19	19	malignant	malignant	ADJ
cana-3851	19	20	growths	growth	NOUN
cana-3851	19	21	are	be	AUX
cana-3851	19	22	cerebral	cerebral	ADJ
cana-3851	19	23	illnesses	illness	NOUN
cana-3851	19	24	.	.	PUNCT
cana-3851	20	1	whatever	whatever	PRON
cana-3851	20	2	the	the	DET
cana-3851	20	3	case	case	NOUN
cana-3851	20	4	may	may	AUX
cana-3851	20	5	be	be	AUX
cana-3851	20	6	,	,	PUNCT
cana-3851	20	7	it	it	PRON
cana-3851	20	8	leads	lead	VERB
cana-3851	20	9	to	to	ADP
cana-3851	20	10	major	major	ADJ
cana-3851	20	11	problems	problem	NOUN
cana-3851	20	12	and	and	CCONJ
cana-3851	20	13	harm	harm	NOUN
cana-3851	20	14	.	.	PUNCT
cana-3851	21	1	worldwide	worldwide	ADV
cana-3851	21	2	,	,	PUNCT
cana-3851	21	3	some	some	DET
cana-3851	21	4	5,250	5,250	NUM
cana-3851	21	5	people	people	NOUN
cana-3851	21	6	lose	lose	VERB
cana-3851	21	7	their	their	PRON
cana-3851	21	8	lives	life	NOUN
cana-3851	21	9	each	each	DET
cana-3851	21	10	year	year	NOUN
cana-3851	21	11	to	to	ADP
cana-3851	21	12	malignancies	malignancy	NOUN
cana-3851	21	13	of	of	ADP
cana-3851	21	14	the	the	DET
cana-3851	21	15	brain	brain	NOUN
cana-3851	21	16	,	,	PUNCT
cana-3851	21	17	cns	cns	NOUN
cana-3851	21	18	,	,	PUNCT
cana-3851	21	19	and	and	CCONJ
cana-3851	21	20	other	other	ADJ
cana-3851	21	21	parts	part	NOUN
cana-3851	21	22	of	of	ADP
cana-3851	21	23	the	the	DET
cana-3851	21	24	brain	brain	NOUN
cana-3851	21	25	and	and	CCONJ
cana-3851	21	26	spinal	spinal	ADJ
cana-3851	21	27	cord	cord	NOUN
cana-3851	22	1	[	[	X
cana-3851	22	2	1	1	NUM
cana-3851	22	3	]	]	PUNCT
cana-3851	22	4	.	.	PUNCT
cana-3851	23	1	cancer	cancer	NOUN
cana-3851	23	2	has	have	AUX
cana-3851	23	3	risen	rise	VERB
cana-3851	23	4	sharply	sharply	ADV
cana-3851	23	5	in	in	ADP
cana-3851	23	6	recent	recent	ADJ
cana-3851	23	7	years	year	NOUN
cana-3851	23	8	to	to	PART
cana-3851	23	9	become	become	VERB
cana-3851	23	10	the	the	DET
cana-3851	23	11	leading	lead	VERB
cana-3851	23	12	global	global	ADJ
cana-3851	23	13	health	health	NOUN
cana-3851	23	14	concern	concern	NOUN
cana-3851	23	15	.	.	PUNCT
cana-3851	24	1	according	accord	VERB
cana-3851	24	2	to	to	ADP
cana-3851	24	3	data	datum	NOUN
cana-3851	24	4	collected	collect	VERB
cana-3851	24	5	from	from	ADP
cana-3851	24	6	the	the	DET
cana-3851	24	7	country	country	NOUN
cana-3851	24	8	's	's	PART
cana-3851	24	9	population	population	NOUN
cana-3851	24	10	registry	registry	NOUN
cana-3851	24	11	,	,	PUNCT
cana-3851	24	12	cancer	cancer	NOUN
cana-3851	24	13	claims	claim	VERB
cana-3851	24	14	the	the	DET
cana-3851	24	15	lives	life	NOUN
cana-3851	24	16	of	of	ADP
cana-3851	24	17	around	around	ADP
cana-3851	24	18	8	8	NUM
cana-3851	24	19	lacs	lac	NOUN
cana-3851	24	20	people	people	NOUN
cana-3851	24	21	year	year	NOUN
cana-3851	24	22	,	,	PUNCT
cana-3851	24	23	making	make	VERB
cana-3851	24	24	it	it	PRON
cana-3851	24	25	the	the	DET
cana-3851	24	26	second	second	ADV
cana-3851	24	27	-	-	PUNCT
cana-3851	24	28	leading	lead	VERB
cana-3851	24	29	chronic	chronic	ADJ
cana-3851	24	30	killer	killer	NOUN
cana-3851	24	31	in	in	ADP
cana-3851	24	32	india	india	PROPN
cana-3851	24	33	.	.	PUNCT
cana-3851	25	1	the	the	DET
cana-3851	25	2	indian	indian	PROPN
cana-3851	25	3	council	council	PROPN
cana-3851	25	4	of	of	ADP
cana-3851	25	5	medical	medical	ADJ
cana-3851	25	6	research	research	NOUN
cana-3851	25	7	(	(	PUNCT
cana-3851	25	8	icmr	icmr	PROPN
cana-3851	25	9	)	)	PUNCT
cana-3851	25	10	estimated	estimate	VERB
cana-3851	25	11	in	in	ADP
cana-3851	25	12	2016	2016	NUM
cana-3851	25	13	that	that	PRON
cana-3851	25	14	the	the	DET
cana-3851	25	15	indian	indian	ADJ
cana-3851	25	16	territory	territory	NOUN
cana-3851	25	17	had	have	VERB
cana-3851	25	18	around	around	ADV
cana-3851	25	19	14	14	NUM
cana-3851	25	20	lacs	lac	NOUN
cana-3851	25	21	recorded	record	VERB
cana-3851	25	22	cases	case	NOUN
cana-3851	25	23	of	of	ADP
cana-3851	25	24	cancer	cancer	NOUN
cana-3851	25	25	,	,	PUNCT
cana-3851	25	26	however	however	ADV
cana-3851	25	27	the	the	DET
cana-3851	25	28	true	true	ADJ
cana-3851	25	29	number	number	NOUN
cana-3851	25	30	of	of	ADP
cana-3851	25	31	cases	case	NOUN
cana-3851	25	32	was	be	AUX
cana-3851	25	33	probably	probably	ADV
cana-3851	25	34	far	far	ADV
cana-3851	25	35	higher	high	ADJ
cana-3851	25	36	.	.	PUNCT
cana-3851	26	1	communications	communication	NOUN
cana-3851	26	2	on	on	ADP
cana-3851	26	3	applied	apply	VERB
cana-3851	26	4	nonlinear	nonlinear	ADJ
cana-3851	26	5	analysis	analysis	NOUN
cana-3851	26	6	issn	issn	NOUN
cana-3851	26	7	:	:	PUNCT
cana-3851	26	8	1074	1074	NUM
cana-3851	26	9	-	-	PUNCT
cana-3851	26	10	133x	133x	NUM
cana-3851	26	11	vol	vol	NOUN
cana-3851	26	12	32	32	NUM
cana-3851	26	13	no	no	NOUN
cana-3851	26	14	.	.	PUNCT
cana-3851	27	1	9s	9s	NUM
cana-3851	27	2	(	(	PUNCT
cana-3851	27	3	2025	2025	NUM
cana-3851	27	4	)	)	PUNCT
cana-3851	27	5	216	216	NUM
cana-3851	27	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-3851	27	7	additionally	additionally	ADV
cana-3851	27	8	,	,	PUNCT
cana-3851	27	9	a	a	DET
cana-3851	27	10	number	number	NOUN
cana-3851	27	11	of	of	ADP
cana-3851	27	12	occurrences	occurrence	NOUN
cana-3851	27	13	that	that	PRON
cana-3851	27	14	were	be	AUX
cana-3851	27	15	unrecorded	unrecorde	VERB
cana-3851	27	16	by	by	ADP
cana-3851	27	17	healthcare	healthcare	NOUN
cana-3851	27	18	institutions	institution	NOUN
cana-3851	27	19	were	be	AUX
cana-3851	27	20	considered	consider	VERB
cana-3851	27	21	.	.	PUNCT
cana-3851	28	1	furthermore	furthermore	ADV
cana-3851	28	2	,	,	PUNCT
cana-3851	28	3	the	the	DET
cana-3851	28	4	icmr	icmr	NOUN
cana-3851	28	5	observed	observe	VERB
cana-3851	28	6	that	that	SCONJ
cana-3851	28	7	the	the	DET
cana-3851	28	8	cancer	cancer	NOUN
cana-3851	28	9	diagnosis	diagnosis	NOUN
cana-3851	28	10	rate	rate	NOUN
cana-3851	28	11	was	be	AUX
cana-3851	28	12	at	at	ADP
cana-3851	28	13	25.8	25.8	NUM
cana-3851	28	14	per	per	ADP
cana-3851	28	15	lac	lac	X
cana-3851	28	16	population	population	NOUN
cana-3851	28	17	up	up	ADP
cana-3851	28	18	to	to	ADP
cana-3851	28	19	2019	2019	NUM
cana-3851	28	20	,	,	PUNCT
cana-3851	28	21	and	and	CCONJ
cana-3851	28	22	it	it	PRON
cana-3851	28	23	is	be	AUX
cana-3851	28	24	anticipated	anticipate	VERB
cana-3851	28	25	to	to	PART
cana-3851	28	26	reach	reach	VERB
cana-3851	28	27	35	35	NUM
cana-3851	28	28	per	per	ADP
cana-3851	28	29	year	year	NOUN
cana-3851	28	30	by	by	ADP
cana-3851	28	31	2029	2029	NUM
cana-3851	28	32	.	.	PUNCT
cana-3851	29	1	the	the	DET
cana-3851	29	2	cancer	cancer	NOUN
cana-3851	29	3	diagnosis	diagnosis	NOUN
cana-3851	29	4	rate	rate	NOUN
cana-3851	29	5	in	in	ADP
cana-3851	29	6	india	india	PROPN
cana-3851	29	7	is	be	AUX
cana-3851	29	8	third	third	ADV
cana-3851	29	9	highest	high	ADJ
cana-3851	29	10	in	in	ADP
cana-3851	29	11	the	the	DET
cana-3851	29	12	world	world	NOUN
cana-3851	29	13	,	,	PUNCT
cana-3851	29	14	behind	behind	ADP
cana-3851	29	15	only	only	ADV
cana-3851	29	16	china	china	PROPN
cana-3851	29	17	and	and	CCONJ
cana-3851	29	18	the	the	DET
cana-3851	29	19	us	us	PROPN
cana-3851	29	20	.	.	PUNCT
cana-3851	30	1	more	more	ADJ
cana-3851	30	2	than	than	ADP
cana-3851	30	3	2,000	2,000	NUM
cana-3851	30	4	cases	case	NOUN
cana-3851	30	5	of	of	ADP
cana-3851	30	6	brain	brain	NOUN
cana-3851	30	7	tumors	tumor	NOUN
cana-3851	30	8	are	be	AUX
cana-3851	30	9	reported	report	VERB
cana-3851	30	10	every	every	DET
cana-3851	30	11	day	day	NOUN
cana-3851	30	12	in	in	ADP
cana-3851	30	13	three	three	NUM
cana-3851	30	14	important	important	ADJ
cana-3851	30	15	indian	indian	ADJ
cana-3851	30	16	states	state	NOUN
cana-3851	30	17	:	:	PUNCT
cana-3851	30	18	kerala	kerala	PROPN
cana-3851	30	19	,	,	PUNCT
cana-3851	30	20	tamil	tamil	PROPN
cana-3851	30	21	nadu	nadu	NOUN
cana-3851	30	22	,	,	PUNCT
cana-3851	30	23	and	and	CCONJ
cana-3851	30	24	delhi	delhi	PROPN
cana-3851	30	25	.	.	PUNCT
cana-3851	31	1	the	the	DET
cana-3851	31	2	survival	survival	NOUN
cana-3851	31	3	rate	rate	NOUN
cana-3851	31	4	is	be	AUX
cana-3851	31	5	four	four	NUM
cana-3851	31	6	to	to	PART
cana-3851	31	7	seventeen	seventeen	NUM
cana-3851	31	8	times	time	NOUN
cana-3851	31	9	lower	low	ADJ
cana-3851	31	10	since	since	SCONJ
cana-3851	31	11	around	around	ADP
cana-3851	31	12	1200	1200	NUM
cana-3851	31	13	of	of	ADP
cana-3851	31	14	these	these	DET
cana-3851	31	15	individuals	individual	NOUN
cana-3851	31	16	are	be	AUX
cana-3851	31	17	in	in	ADP
cana-3851	31	18	the	the	DET
cana-3851	31	19	advanced	advanced	ADJ
cana-3851	31	20	or	or	CCONJ
cana-3851	31	21	late	late	ADJ
cana-3851	31	22	stages	stage	NOUN
cana-3851	31	23	.	.	PUNCT
cana-3851	32	1	among	among	ADP
cana-3851	32	2	female	female	ADJ
cana-3851	32	3	cancer	cancer	NOUN
cana-3851	32	4	patients	patient	NOUN
cana-3851	32	5	,	,	PUNCT
cana-3851	32	6	brain	brain	NOUN
cana-3851	32	7	tumors	tumor	NOUN
cana-3851	32	8	rank	rank	VERB
cana-3851	32	9	second	second	ADV
cana-3851	32	10	in	in	ADP
cana-3851	32	11	incidence	incidence	NOUN
cana-3851	32	12	and	and	CCONJ
cana-3851	32	13	second	second	ADJ
cana-3851	32	14	in	in	ADP
cana-3851	32	15	fatality	fatality	NOUN
cana-3851	32	16	rates	rate	NOUN
cana-3851	32	17	,	,	PUNCT
cana-3851	32	18	behind	behind	ADP
cana-3851	32	19	only	only	ADJ
cana-3851	32	20	lung	lung	NOUN
cana-3851	32	21	cancer	cancer	NOUN
cana-3851	32	22	.	.	PUNCT
cana-3851	33	1	a	a	DET
cana-3851	33	2	recent	recent	ADJ
cana-3851	33	3	study	study	NOUN
cana-3851	33	4	found	find	VERB
cana-3851	33	5	that	that	SCONJ
cana-3851	33	6	brain	brain	NOUN
cana-3851	33	7	tumors	tumor	NOUN
cana-3851	33	8	were	be	AUX
cana-3851	33	9	the	the	DET
cana-3851	33	10	cause	cause	NOUN
cana-3851	33	11	of	of	ADP
cana-3851	33	12	death	death	NOUN
cana-3851	33	13	for	for	ADP
cana-3851	33	14	about	about	ADV
cana-3851	33	15	5	5	NUM
cana-3851	33	16	lacs	lac	NOUN
cana-3851	33	17	of	of	ADP
cana-3851	33	18	women	woman	NOUN
cana-3851	33	19	in	in	ADP
cana-3851	33	20	2015	2015	NUM
cana-3851	33	21	.	.	PUNCT
cana-3851	34	1	the	the	DET
cana-3851	34	2	world	world	PROPN
cana-3851	34	3	health	health	PROPN
cana-3851	34	4	organization	organization	NOUN
cana-3851	34	5	estimates	estimate	VERB
cana-3851	34	6	that	that	SCONJ
cana-3851	34	7	1.5	1.5	NUM
cana-3851	34	8	million	million	NUM
cana-3851	34	9	more	more	ADJ
cana-3851	34	10	women	woman	NOUN
cana-3851	34	11	will	will	AUX
cana-3851	34	12	lose	lose	VERB
cana-3851	34	13	their	their	PRON
cana-3851	34	14	lives	life	NOUN
cana-3851	34	15	to	to	ADP
cana-3851	34	16	brain	brain	NOUN
cana-3851	34	17	tumors	tumor	NOUN
cana-3851	34	18	in	in	ADP
cana-3851	34	19	the	the	DET
cana-3851	34	20	next	next	ADJ
cana-3851	34	21	year	year	NOUN
cana-3851	34	22	.	.	PUNCT
cana-3851	35	1	even	even	ADV
cana-3851	35	2	though	though	SCONJ
cana-3851	35	3	it	it	PRON
cana-3851	35	4	has	have	VERB
cana-3851	35	5	one	one	NUM
cana-3851	35	6	of	of	ADP
cana-3851	35	7	the	the	DET
cana-3851	35	8	best	good	ADJ
cana-3851	35	9	healthcare	healthcare	NOUN
cana-3851	35	10	systems	system	NOUN
cana-3851	35	11	in	in	ADP
cana-3851	35	12	the	the	DET
cana-3851	35	13	world	world	NOUN
cana-3851	35	14	,	,	PUNCT
cana-3851	35	15	the	the	DET
cana-3851	35	16	united	united	PROPN
cana-3851	35	17	states	states	PROPN
cana-3851	35	18	had	have	VERB
cana-3851	35	19	about	about	ADP
cana-3851	35	20	2.5	2.5	NUM
cana-3851	35	21	million	million	NUM
cana-3851	35	22	cases	case	NOUN
cana-3851	35	23	of	of	ADP
cana-3851	35	24	brain	brain	NOUN
cana-3851	35	25	tumors	tumor	NOUN
cana-3851	35	26	and	and	CCONJ
cana-3851	35	27	40,000	40,000	NUM
cana-3851	35	28	deaths	death	NOUN
cana-3851	35	29	from	from	ADP
cana-3851	35	30	them	they	PRON
cana-3851	35	31	in	in	ADP
cana-3851	35	32	2017	2017	NUM
cana-3851	36	1	[	[	X
cana-3851	36	2	2	2	NUM
cana-3851	36	3	]	]	PUNCT
cana-3851	36	4	.	.	PUNCT
cana-3851	37	1	there	there	PRON
cana-3851	37	2	is	be	VERB
cana-3851	37	3	a	a	DET
cana-3851	37	4	dramatic	dramatic	ADJ
cana-3851	37	5	decrease	decrease	NOUN
cana-3851	37	6	in	in	ADP
cana-3851	37	7	survival	survival	NOUN
cana-3851	37	8	rate	rate	NOUN
cana-3851	37	9	(	(	PUNCT
cana-3851	37	10	4	4	NUM
cana-3851	37	11	-	-	SYM
cana-3851	37	12	17	17	NUM
cana-3851	37	13	times	time	NOUN
cana-3851	37	14	)	)	PUNCT
cana-3851	37	15	as	as	SCONJ
cana-3851	37	16	over	over	ADP
cana-3851	37	17	1200	1200	NUM
cana-3851	37	18	of	of	ADP
cana-3851	37	19	these	these	DET
cana-3851	37	20	patients	patient	NOUN
cana-3851	37	21	are	be	AUX
cana-3851	37	22	in	in	ADP
cana-3851	37	23	advanced	advanced	ADJ
cana-3851	37	24	or	or	CCONJ
cana-3851	37	25	later	later	ADJ
cana-3851	37	26	stages	stage	NOUN
cana-3851	37	27	.	.	PUNCT
cana-3851	38	1	in	in	ADP
cana-3851	38	2	terms	term	NOUN
cana-3851	38	3	of	of	ADP
cana-3851	38	4	cancer	cancer	NOUN
cana-3851	38	5	incidence	incidence	NOUN
cana-3851	38	6	and	and	CCONJ
cana-3851	38	7	fatality	fatality	NOUN
cana-3851	38	8	rates	rate	NOUN
cana-3851	38	9	in	in	ADP
cana-3851	38	10	females	female	NOUN
cana-3851	38	11	,	,	PUNCT
cana-3851	38	12	brain	brain	NOUN
cana-3851	38	13	tumors	tumor	NOUN
cana-3851	38	14	rank	rank	VERB
cana-3851	38	15	second	second	ADV
cana-3851	38	16	,	,	PUNCT
cana-3851	38	17	after	after	ADP
cana-3851	38	18	lung	lung	NOUN
cana-3851	38	19	cancer	cancer	NOUN
cana-3851	38	20	.	.	PUNCT
cana-3851	39	1	in	in	ADP
cana-3851	39	2	2015	2015	NUM
cana-3851	39	3	,	,	PUNCT
cana-3851	39	4	brain	brain	NOUN
cana-3851	39	5	tumors	tumor	NOUN
cana-3851	39	6	claimed	claim	VERB
cana-3851	39	7	the	the	DET
cana-3851	39	8	lives	life	NOUN
cana-3851	39	9	of	of	ADP
cana-3851	39	10	about	about	ADV
cana-3851	39	11	5	5	NUM
cana-3851	39	12	lacs	lac	NOUN
cana-3851	39	13	of	of	ADP
cana-3851	39	14	women	woman	NOUN
cana-3851	39	15	,	,	PUNCT
cana-3851	39	16	as	as	SCONJ
cana-3851	39	17	revealed	reveal	VERB
cana-3851	39	18	by	by	ADP
cana-3851	39	19	new	new	ADJ
cana-3851	39	20	study	study	NOUN
cana-3851	39	21	.	.	PUNCT
cana-3851	40	1	brain	brain	NOUN
cana-3851	40	2	tumors	tumor	NOUN
cana-3851	40	3	may	may	AUX
cana-3851	40	4	kill	kill	VERB
cana-3851	40	5	1.5	1.5	NUM
cana-3851	40	6	million	million	NUM
cana-3851	40	7	more	more	ADJ
cana-3851	40	8	women	woman	NOUN
cana-3851	40	9	,	,	PUNCT
cana-3851	40	10	says	say	VERB
cana-3851	40	11	the	the	DET
cana-3851	40	12	world	world	PROPN
cana-3851	40	13	health	health	NOUN
cana-3851	40	14	organization	organization	NOUN
cana-3851	40	15	(	(	PUNCT
cana-3851	40	16	who	who	PRON
cana-3851	40	17	)	)	PUNCT
cana-3851	40	18	.	.	PUNCT
cana-3851	41	1	despite	despite	SCONJ
cana-3851	41	2	being	be	AUX
cana-3851	41	3	one	one	NUM
cana-3851	41	4	of	of	ADP
cana-3851	41	5	the	the	DET
cana-3851	41	6	most	most	ADV
cana-3851	41	7	industrialized	industrialize	VERB
cana-3851	41	8	nations	nation	NOUN
cana-3851	41	9	with	with	ADP
cana-3851	41	10	the	the	DET
cana-3851	41	11	finest	fine	ADJ
cana-3851	41	12	healthcare	healthcare	NOUN
cana-3851	41	13	infrastructure	infrastructure	NOUN
cana-3851	41	14	,	,	PUNCT
cana-3851	41	15	the	the	DET
cana-3851	41	16	united	united	PROPN
cana-3851	41	17	states	states	PROPN
cana-3851	41	18	reported	report	VERB
cana-3851	41	19	about	about	ADP
cana-3851	41	20	2.5	2.5	NUM
cana-3851	41	21	lacs	lac	NOUN
cana-3851	41	22	of	of	ADP
cana-3851	41	23	brain	brain	NOUN
cana-3851	41	24	tumor	tumor	NOUN
cana-3851	41	25	patients	patient	NOUN
cana-3851	41	26	and	and	CCONJ
cana-3851	41	27	forty	forty	NUM
cana-3851	41	28	thousand	thousand	NUM
cana-3851	41	29	deaths	death	NOUN
cana-3851	41	30	in	in	ADP
cana-3851	41	31	2017	2017	NUM
cana-3851	41	32	[	[	X
cana-3851	41	33	2	2	NUM
cana-3851	41	34	]	]	PUNCT
cana-3851	41	35	.	.	PUNCT
cana-3851	42	1	this	this	DET
cana-3851	42	2	remarkable	remarkable	ADJ
cana-3851	42	3	soft	soft	ADJ
cana-3851	42	4	tissue	tissue	NOUN
cana-3851	42	5	delineation	delineation	NOUN
cana-3851	42	6	becomes	become	VERB
cana-3851	42	7	very	very	ADV
cana-3851	42	8	important	important	ADJ
cana-3851	42	9	when	when	SCONJ
cana-3851	42	10	attempting	attempt	VERB
cana-3851	42	11	to	to	PART
cana-3851	42	12	distinguish	distinguish	VERB
cana-3851	42	13	between	between	ADP
cana-3851	42	14	healthy	healthy	ADJ
cana-3851	42	15	tissues	tissue	NOUN
cana-3851	42	16	and	and	CCONJ
cana-3851	42	17	infectious	infectious	ADJ
cana-3851	42	18	organisms	organism	NOUN
cana-3851	42	19	[	[	X
cana-3851	42	20	3	3	NUM
cana-3851	42	21	]	]	PUNCT
cana-3851	42	22	.	.	PUNCT
cana-3851	43	1	medical	medical	ADJ
cana-3851	43	2	image	image	NOUN
cana-3851	43	3	analysis	analysis	NOUN
cana-3851	43	4	often	often	ADV
cana-3851	43	5	use	use	VERB
cana-3851	43	6	a	a	DET
cana-3851	43	7	number	number	NOUN
cana-3851	43	8	of	of	ADP
cana-3851	43	9	techniques	technique	NOUN
cana-3851	43	10	to	to	PART
cana-3851	43	11	generate	generate	VERB
cana-3851	43	12	pictures	picture	NOUN
cana-3851	43	13	of	of	ADP
cana-3851	43	14	the	the	DET
cana-3851	43	15	human	human	ADJ
cana-3851	43	16	body	body	NOUN
cana-3851	43	17	's	's	PART
cana-3851	43	18	soft	soft	ADJ
cana-3851	43	19	tissues	tissue	NOUN
cana-3851	43	20	.	.	PUNCT
cana-3851	44	1	magnetic	magnetic	ADJ
cana-3851	44	2	resonance	resonance	NOUN
cana-3851	44	3	imaging	imaging	NOUN
cana-3851	44	4	(	(	PUNCT
cana-3851	44	5	mri	mri	NOUN
cana-3851	44	6	)	)	PUNCT
cana-3851	44	7	is	be	AUX
cana-3851	44	8	one	one	NUM
cana-3851	44	9	of	of	ADP
cana-3851	44	10	these	these	DET
cana-3851	44	11	tools	tool	NOUN
cana-3851	44	12	that	that	PRON
cana-3851	44	13	clinicians	clinician	NOUN
cana-3851	44	14	use	use	VERB
cana-3851	44	15	often	often	ADV
cana-3851	44	16	.	.	PUNCT
cana-3851	45	1	in	in	ADP
cana-3851	45	2	order	order	NOUN
cana-3851	45	3	to	to	PART
cana-3851	45	4	aid	aid	VERB
cana-3851	45	5	physicians	physician	NOUN
cana-3851	45	6	in	in	ADP
cana-3851	45	7	determining	determine	VERB
cana-3851	45	8	the	the	DET
cana-3851	45	9	patient	patient	NOUN
cana-3851	45	10	's	's	PART
cana-3851	45	11	health	health	NOUN
cana-3851	45	12	,	,	PUNCT
cana-3851	45	13	this	this	DET
cana-3851	45	14	approach	approach	NOUN
cana-3851	45	15	correctly	correctly	ADV
cana-3851	45	16	interprets	interpret	VERB
cana-3851	45	17	imaging	imaging	NOUN
cana-3851	45	18	data	datum	NOUN
cana-3851	45	19	of	of	ADP
cana-3851	45	20	human	human	ADJ
cana-3851	45	21	brain	brain	NOUN
cana-3851	45	22	tumors	tumor	NOUN
cana-3851	45	23	without	without	ADP
cana-3851	45	24	invasive	invasive	ADJ
cana-3851	45	25	procedures	procedure	NOUN
cana-3851	45	26	.	.	PUNCT
cana-3851	46	1	thanks	thank	NOUN
cana-3851	46	2	to	to	ADP
cana-3851	46	3	its	its	PRON
cana-3851	46	4	high	high	ADJ
cana-3851	46	5	-	-	PUNCT
cana-3851	46	6	resolution	resolution	NOUN
cana-3851	46	7	pictures	picture	NOUN
cana-3851	46	8	and	and	CCONJ
cana-3851	46	9	tissue	tissue	NOUN
cana-3851	46	10	contrast	contrast	NOUN
cana-3851	46	11	normalization	normalization	NOUN
cana-3851	46	12	,	,	PUNCT
cana-3851	46	13	it	it	PRON
cana-3851	46	14	is	be	AUX
cana-3851	46	15	a	a	DET
cana-3851	46	16	great	great	ADJ
cana-3851	46	17	tool	tool	NOUN
cana-3851	46	18	.	.	PUNCT
cana-3851	47	1	imaging	imaging	NOUN
cana-3851	47	2	studies	study	NOUN
cana-3851	47	3	using	use	VERB
cana-3851	47	4	magnetic	magnetic	ADJ
cana-3851	47	5	resonance	resonance	NOUN
cana-3851	47	6	imaging	imaging	NOUN
cana-3851	47	7	(	(	PUNCT
cana-3851	47	8	mri	mri	NOUN
cana-3851	47	9	)	)	PUNCT
cana-3851	47	10	may	may	AUX
cana-3851	47	11	provide	provide	VERB
cana-3851	47	12	light	light	NOUN
cana-3851	47	13	on	on	ADP
cana-3851	47	14	the	the	DET
cana-3851	47	15	genetics	genetic	NOUN
cana-3851	47	16	,	,	PUNCT
cana-3851	47	17	chemistry	chemistry	NOUN
cana-3851	47	18	,	,	PUNCT
cana-3851	47	19	physiology	physiology	NOUN
cana-3851	47	20	,	,	PUNCT
cana-3851	47	21	and	and	CCONJ
cana-3851	47	22	biology	biology	NOUN
cana-3851	47	23	of	of	ADP
cana-3851	47	24	brain	brain	NOUN
cana-3851	47	25	problems	problem	NOUN
cana-3851	47	26	.	.	PUNCT
cana-3851	48	1	there	there	PRON
cana-3851	48	2	are	be	VERB
cana-3851	48	3	several	several	ADJ
cana-3851	48	4	types	type	NOUN
cana-3851	48	5	of	of	ADP
cana-3851	48	6	tumors	tumor	NOUN
cana-3851	48	7	that	that	PRON
cana-3851	48	8	are	be	AUX
cana-3851	48	9	defined	define	VERB
cana-3851	48	10	by	by	ADP
cana-3851	48	11	their	their	PRON
cana-3851	48	12	origin	origin	NOUN
cana-3851	48	13	and	and	CCONJ
cana-3851	48	14	cell	cell	NOUN
cana-3851	48	15	type	type	NOUN
cana-3851	48	16	.	.	PUNCT
cana-3851	49	1	it	it	PRON
cana-3851	49	2	's	be	AUX
cana-3851	49	3	important	important	ADJ
cana-3851	49	4	to	to	PART
cana-3851	49	5	remember	remember	VERB
cana-3851	49	6	that	that	PRON
cana-3851	49	7	primary	primary	ADJ
cana-3851	49	8	brain	brain	NOUN
cana-3851	49	9	tumors	tumor	NOUN
cana-3851	49	10	originate	originate	VERB
cana-3851	49	11	in	in	ADP
cana-3851	49	12	different	different	ADJ
cana-3851	49	13	human	human	ADJ
cana-3851	49	14	organs	organ	NOUN
cana-3851	49	15	and	and	CCONJ
cana-3851	49	16	spread	spread	VERB
cana-3851	49	17	to	to	ADP
cana-3851	49	18	the	the	DET
cana-3851	49	19	brain	brain	NOUN
cana-3851	49	20	,	,	PUNCT
cana-3851	49	21	while	while	SCONJ
cana-3851	49	22	vertebrate	vertebrate	ADJ
cana-3851	49	23	cerebrum	cerebrum	NOUN
cana-3851	49	24	malignancies	malignancy	NOUN
cana-3851	49	25	often	often	ADV
cana-3851	49	26	show	show	VERB
cana-3851	49	27	up	up	ADP
cana-3851	49	28	in	in	ADP
cana-3851	49	29	the	the	DET
cana-3851	49	30	area	area	NOUN
cana-3851	49	31	of	of	ADP
cana-3851	49	32	the	the	DET
cana-3851	49	33	brain	brain	NOUN
cana-3851	49	34	's	's	PART
cana-3851	49	35	central	central	ADJ
cana-3851	49	36	hemispheres	hemisphere	NOUN
cana-3851	49	37	.	.	PUNCT
cana-3851	50	1	gliomas	glioma	NOUN
cana-3851	50	2	,	,	PUNCT
cana-3851	50	3	meningiomas	meningioma	NOUN
cana-3851	50	4	,	,	PUNCT
cana-3851	50	5	and	and	CCONJ
cana-3851	50	6	pituitary	pituitary	ADJ
cana-3851	50	7	tumors	tumor	NOUN
cana-3851	50	8	are	be	AUX
cana-3851	50	9	the	the	DET
cana-3851	50	10	three	three	NUM
cana-3851	50	11	main	main	ADJ
cana-3851	50	12	forms	form	NOUN
cana-3851	50	13	of	of	ADP
cana-3851	50	14	primary	primary	ADJ
cana-3851	50	15	brain	brain	NOUN
cana-3851	50	16	tumors	tumor	NOUN
cana-3851	50	17	,	,	PUNCT
cana-3851	50	18	as	as	SCONJ
cana-3851	50	19	seen	see	VERB
cana-3851	50	20	in	in	ADP
cana-3851	50	21	figure1[4	figure1[4	PROPN
cana-3851	50	22	]	]	PUNCT
cana-3851	50	23	.	.	PUNCT
cana-3851	51	1	(	(	PUNCT
cana-3851	51	2	a	a	X
cana-3851	51	3	)	)	PUNCT
cana-3851	51	4	(	(	PUNCT
cana-3851	51	5	b	b	X
cana-3851	51	6	)	)	PUNCT
cana-3851	51	7	(	(	PUNCT
cana-3851	51	8	c	c	X
cana-3851	51	9	)	)	PUNCT
cana-3851	51	10	figure	figure	NOUN
cana-3851	51	11	1	1	NUM
cana-3851	51	12	:	:	PUNCT
cana-3851	51	13	typical	typical	ADJ
cana-3851	51	14	brain	brain	NOUN
cana-3851	51	15	tumor	tumor	NOUN
cana-3851	51	16	types	type	NOUN
cana-3851	51	17	.	.	PUNCT
cana-3851	52	1	the	the	DET
cana-3851	52	2	abnormal	abnormal	ADJ
cana-3851	52	3	and	and	CCONJ
cana-3851	52	4	uncontrolled	uncontrolled	ADJ
cana-3851	52	5	growth	growth	NOUN
cana-3851	52	6	of	of	ADP
cana-3851	52	7	cells	cell	NOUN
cana-3851	52	8	all	all	ADV
cana-3851	52	9	across	across	ADP
cana-3851	52	10	the	the	DET
cana-3851	52	11	body	body	NOUN
cana-3851	52	12	is	be	AUX
cana-3851	52	13	what	what	PRON
cana-3851	52	14	defines	define	VERB
cana-3851	52	15	cancer	cancer	NOUN
cana-3851	52	16	.	.	PUNCT
cana-3851	53	1	when	when	SCONJ
cana-3851	53	2	these	these	DET
cana-3851	53	3	aberrant	aberrant	ADJ
cana-3851	53	4	cell	cell	NOUN
cana-3851	53	5	divisions	division	NOUN
cana-3851	53	6	proliferate	proliferate	VERB
cana-3851	53	7	in	in	ADP
cana-3851	53	8	the	the	DET
cana-3851	53	9	brain	brain	NOUN
cana-3851	53	10	at	at	ADP
cana-3851	53	11	an	an	DET
cana-3851	53	12	abnormal	abnormal	ADJ
cana-3851	53	13	rate	rate	NOUN
cana-3851	53	14	,	,	PUNCT
cana-3851	53	15	the	the	DET
cana-3851	53	16	result	result	NOUN
cana-3851	53	17	is	be	AUX
cana-3851	53	18	a	a	DET
cana-3851	53	19	tumor	tumor	NOUN
cana-3851	53	20	.	.	PUNCT
cana-3851	54	1	despite	despite	SCONJ
cana-3851	54	2	their	their	PRON
cana-3851	54	3	communications	communication	NOUN
cana-3851	54	4	on	on	ADP
cana-3851	54	5	applied	apply	VERB
cana-3851	54	6	nonlinear	nonlinear	ADJ
cana-3851	54	7	analysis	analysis	NOUN
cana-3851	54	8	issn	issn	NOUN
cana-3851	54	9	:	:	PUNCT
cana-3851	54	10	1074	1074	NUM
cana-3851	54	11	-	-	PUNCT
cana-3851	54	12	133x	133x	NUM
cana-3851	54	13	vol	vol	NOUN
cana-3851	54	14	32	32	NUM
cana-3851	54	15	no	no	NOUN
cana-3851	54	16	.	.	PUNCT
cana-3851	55	1	9s	9s	NUM
cana-3851	55	2	(	(	PUNCT
cana-3851	55	3	2025	2025	NUM
cana-3851	55	4	)	)	PUNCT
cana-3851	55	5	217	217	NUM
cana-3851	55	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-3851	55	7	rarity	rarity	NOUN
cana-3851	55	8	,	,	PUNCT
cana-3851	55	9	brain	brain	NOUN
cana-3851	55	10	tumors	tumor	NOUN
cana-3851	55	11	are	be	AUX
cana-3851	55	12	on	on	ADP
cana-3851	55	13	the	the	DET
cana-3851	55	14	list	list	NOUN
cana-3851	55	15	of	of	ADP
cana-3851	55	16	the	the	DET
cana-3851	55	17	most	most	ADV
cana-3851	55	18	lethal	lethal	ADJ
cana-3851	55	19	malignancies	malignancy	NOUN
cana-3851	55	20	.	.	PUNCT
cana-3851	56	1	although	although	SCONJ
cana-3851	56	2	they	they	PRON
cana-3851	56	3	originate	originate	VERB
cana-3851	56	4	from	from	ADP
cana-3851	56	5	different	different	ADJ
cana-3851	56	6	places	place	NOUN
cana-3851	56	7	,	,	PUNCT
cana-3851	56	8	the	the	DET
cana-3851	56	9	same	same	ADJ
cana-3851	56	10	kind	kind	NOUN
cana-3851	56	11	of	of	ADP
cana-3851	56	12	brain	brain	NOUN
cana-3851	56	13	tumor	tumor	NOUN
cana-3851	56	14	is	be	AUX
cana-3851	56	15	known	know	VERB
cana-3851	56	16	as	as	ADP
cana-3851	56	17	a	a	DET
cana-3851	56	18	primary	primary	ADJ
cana-3851	56	19	brain	brain	NOUN
cana-3851	56	20	tumor	tumor	NOUN
cana-3851	56	21	or	or	CCONJ
cana-3851	56	22	a	a	DET
cana-3851	56	23	metastatic	metastatic	ADJ
cana-3851	56	24	brain	brain	NOUN
cana-3851	56	25	tumor	tumor	NOUN
cana-3851	56	26	.	.	PUNCT
cana-3851	57	1	although	although	SCONJ
cana-3851	57	2	both	both	CCONJ
cana-3851	57	3	primary	primary	ADJ
cana-3851	57	4	and	and	CCONJ
cana-3851	57	5	metastatic	metastatic	ADJ
cana-3851	57	6	brain	brain	NOUN
cana-3851	57	7	tumors	tumor	NOUN
cana-3851	57	8	originate	originate	VERB
cana-3851	57	9	in	in	ADP
cana-3851	57	10	cells	cell	NOUN
cana-3851	57	11	of	of	ADP
cana-3851	57	12	brain	brain	NOUN
cana-3851	57	13	tissue	tissue	NOUN
cana-3851	57	14	,	,	PUNCT
cana-3851	57	15	the	the	DET
cana-3851	57	16	former	former	ADJ
cana-3851	57	17	originates	originate	NOUN
cana-3851	57	18	in	in	ADP
cana-3851	57	19	another	another	DET
cana-3851	57	20	part	part	NOUN
cana-3851	57	21	of	of	ADP
cana-3851	57	22	the	the	DET
cana-3851	57	23	body	body	NOUN
cana-3851	57	24	and	and	CCONJ
cana-3851	57	25	the	the	DET
cana-3851	57	26	latter	latter	ADJ
cana-3851	57	27	spreads	spread	NOUN
cana-3851	57	28	to	to	ADP
cana-3851	57	29	it	it	PRON
cana-3851	57	30	.	.	PUNCT
cana-3851	58	1	unregulated	unregulated	ADJ
cana-3851	58	2	and	and	CCONJ
cana-3851	58	3	abnormal	abnormal	ADJ
cana-3851	58	4	cell	cell	NOUN
cana-3851	58	5	growth	growth	NOUN
cana-3851	58	6	throughout	throughout	ADP
cana-3851	58	7	the	the	DET
cana-3851	58	8	body	body	NOUN
cana-3851	58	9	is	be	AUX
cana-3851	58	10	a	a	DET
cana-3851	58	11	hallmark	hallmark	NOUN
cana-3851	58	12	of	of	ADP
cana-3851	58	13	cancer	cancer	NOUN
cana-3851	58	14	.	.	PUNCT
cana-3851	59	1	the	the	DET
cana-3851	59	2	accumulation	accumulation	NOUN
cana-3851	59	3	of	of	ADP
cana-3851	59	4	these	these	DET
cana-3851	59	5	aberrant	aberrant	ADJ
cana-3851	59	6	cell	cell	NOUN
cana-3851	59	7	divisions	division	NOUN
cana-3851	59	8	in	in	ADP
cana-3851	59	9	brain	brain	NOUN
cana-3851	59	10	tissue	tissue	NOUN
cana-3851	59	11	is	be	AUX
cana-3851	59	12	known	know	VERB
cana-3851	59	13	as	as	ADP
cana-3851	59	14	a	a	DET
cana-3851	59	15	brain	brain	NOUN
cana-3851	59	16	tumor	tumor	NOUN
cana-3851	59	17	.	.	PUNCT
cana-3851	60	1	despite	despite	SCONJ
cana-3851	60	2	their	their	PRON
cana-3851	60	3	rarity	rarity	NOUN
cana-3851	60	4	,	,	PUNCT
cana-3851	60	5	brain	brain	NOUN
cana-3851	60	6	tumors	tumor	NOUN
cana-3851	60	7	are	be	AUX
cana-3851	60	8	among	among	ADP
cana-3851	60	9	the	the	DET
cana-3851	60	10	most	most	ADV
cana-3851	60	11	lethal	lethal	ADJ
cana-3851	60	12	forms	form	NOUN
cana-3851	60	13	of	of	ADP
cana-3851	60	14	cancer	cancer	NOUN
cana-3851	60	15	.	.	PUNCT
cana-3851	61	1	metastatic	metastatic	ADJ
cana-3851	61	2	brain	brain	NOUN
cana-3851	61	3	tumors	tumor	NOUN
cana-3851	61	4	and	and	CCONJ
cana-3851	61	5	primary	primary	ADJ
cana-3851	61	6	brain	brain	NOUN
cana-3851	61	7	tumors	tumor	NOUN
cana-3851	61	8	both	both	PRON
cana-3851	61	9	refer	refer	VERB
cana-3851	61	10	to	to	ADP
cana-3851	61	11	the	the	DET
cana-3851	61	12	same	same	ADJ
cana-3851	61	13	kind	kind	NOUN
cana-3851	61	14	of	of	ADP
cana-3851	61	15	tumor	tumor	NOUN
cana-3851	61	16	,	,	PUNCT
cana-3851	61	17	although	although	SCONJ
cana-3851	61	18	they	they	PRON
cana-3851	61	19	originate	originate	VERB
cana-3851	61	20	from	from	ADP
cana-3851	61	21	distinct	distinct	ADJ
cana-3851	61	22	places	place	NOUN
cana-3851	61	23	in	in	ADP
cana-3851	61	24	the	the	DET
cana-3851	61	25	brain	brain	NOUN
cana-3851	61	26	.	.	PUNCT
cana-3851	62	1	while	while	SCONJ
cana-3851	62	2	primary	primary	ADJ
cana-3851	62	3	tumors	tumor	NOUN
cana-3851	62	4	begin	begin	VERB
cana-3851	62	5	in	in	ADP
cana-3851	62	6	the	the	DET
cana-3851	62	7	cells	cell	NOUN
cana-3851	62	8	of	of	ADP
cana-3851	62	9	brain	brain	NOUN
cana-3851	62	10	tissue	tissue	NOUN
cana-3851	62	11	,	,	PUNCT
cana-3851	62	12	metastatic	metastatic	ADJ
cana-3851	62	13	malignancies	malignancy	NOUN
cana-3851	62	14	travel	travel	VERB
cana-3851	62	15	from	from	ADP
cana-3851	62	16	another	another	DET
cana-3851	62	17	part	part	NOUN
cana-3851	62	18	of	of	ADP
cana-3851	62	19	the	the	DET
cana-3851	62	20	body	body	NOUN
cana-3851	62	21	to	to	ADP
cana-3851	62	22	the	the	DET
cana-3851	62	23	brain	brain	NOUN
cana-3851	62	24	.	.	PUNCT
cana-3851	63	1	the	the	DET
cana-3851	63	2	future	future	NOUN
cana-3851	63	3	of	of	ADP
cana-3851	63	4	image	image	NOUN
cana-3851	63	5	processing	processing	NOUN
cana-3851	63	6	is	be	AUX
cana-3851	63	7	highly	highly	ADV
cana-3851	63	8	dependent	dependent	ADJ
cana-3851	63	9	on	on	ADP
cana-3851	63	10	image	image	NOUN
cana-3851	63	11	segmentation	segmentation	NOUN
cana-3851	63	12	,	,	PUNCT
cana-3851	63	13	a	a	DET
cana-3851	63	14	fundamental	fundamental	ADJ
cana-3851	63	15	and	and	CCONJ
cana-3851	63	16	important	important	ADJ
cana-3851	63	17	phase	phase	NOUN
cana-3851	63	18	in	in	ADP
cana-3851	63	19	the	the	DET
cana-3851	63	20	process	process	NOUN
cana-3851	63	21	.	.	PUNCT
cana-3851	64	1	brain	brain	NOUN
cana-3851	64	2	tumor	tumor	NOUN
cana-3851	64	3	segmentation	segmentation	NOUN
cana-3851	64	4	from	from	ADP
cana-3851	64	5	mri	mri	NOUN
cana-3851	64	6	scans	scan	NOUN
cana-3851	64	7	has	have	AUX
cana-3851	64	8	been	be	AUX
cana-3851	64	9	our	our	PRON
cana-3851	64	10	primary	primary	ADJ
cana-3851	64	11	emphasis	emphasis	NOUN
cana-3851	64	12	here	here	ADV
cana-3851	64	13	.	.	PUNCT
cana-3851	65	1	it	it	PRON
cana-3851	65	2	helps	help	VERB
cana-3851	65	3	doctors	doctor	NOUN
cana-3851	65	4	get	get	VERB
cana-3851	65	5	a	a	DET
cana-3851	65	6	precise	precise	ADJ
cana-3851	65	7	location	location	NOUN
cana-3851	65	8	of	of	ADP
cana-3851	65	9	the	the	DET
cana-3851	65	10	tumor	tumor	NOUN
cana-3851	65	11	in	in	ADP
cana-3851	65	12	the	the	DET
cana-3851	65	13	brain	brain	NOUN
cana-3851	65	14	.	.	PUNCT
cana-3851	66	1	when	when	SCONJ
cana-3851	66	2	we	we	PRON
cana-3851	66	3	talk	talk	VERB
cana-3851	66	4	about	about	ADP
cana-3851	66	5	"	"	PUNCT
cana-3851	66	6	medical	medical	ADJ
cana-3851	66	7	image	image	NOUN
cana-3851	66	8	processing	processing	NOUN
cana-3851	66	9	,	,	PUNCT
cana-3851	66	10	"	"	PUNCT
cana-3851	66	11	we	we	PRON
cana-3851	66	12	're	be	AUX
cana-3851	66	13	referring	refer	VERB
cana-3851	66	14	to	to	ADP
cana-3851	66	15	the	the	DET
cana-3851	66	16	steps	step	NOUN
cana-3851	66	17	used	use	VERB
cana-3851	66	18	to	to	ADP
cana-3851	66	19	decipher	decipher	NOUN
cana-3851	66	20	and	and	CCONJ
cana-3851	66	21	make	make	VERB
cana-3851	66	22	sense	sense	NOUN
cana-3851	66	23	of	of	ADP
cana-3851	66	24	massive	massive	ADJ
cana-3851	66	25	databases	database	NOUN
cana-3851	66	26	of	of	ADP
cana-3851	66	27	three	three	NUM
cana-3851	66	28	-	-	PUNCT
cana-3851	66	29	dimensional	dimensional	ADJ
cana-3851	66	30	(	(	PUNCT
cana-3851	66	31	3d	3d	NOUN
cana-3851	66	32	)	)	PUNCT
cana-3851	66	33	medical	medical	ADJ
cana-3851	66	34	pictures	picture	NOUN
cana-3851	66	35	,	,	PUNCT
cana-3851	66	36	often	often	ADV
cana-3851	66	37	captured	capture	VERB
cana-3851	66	38	by	by	ADP
cana-3851	66	39	mri	mri	NOUN
cana-3851	66	40	or	or	CCONJ
cana-3851	66	41	ct	ct	NUM
cana-3851	66	42	scanners	scanner	NOUN
cana-3851	66	43	,	,	PUNCT
cana-3851	66	44	for	for	ADP
cana-3851	66	45	the	the	DET
cana-3851	66	46	benefit	benefit	NOUN
cana-3851	66	47	of	of	ADP
cana-3851	66	48	research	research	NOUN
cana-3851	66	49	,	,	PUNCT
cana-3851	66	50	diagnosis	diagnosis	NOUN
cana-3851	66	51	,	,	PUNCT
cana-3851	66	52	or	or	CCONJ
cana-3851	66	53	treatment	treatment	NOUN
cana-3851	66	54	planning	planning	NOUN
cana-3851	66	55	.	.	PUNCT
cana-3851	67	1	medical	medical	ADJ
cana-3851	67	2	professionals	professional	NOUN
cana-3851	67	3	,	,	PUNCT
cana-3851	67	4	engineers	engineer	NOUN
cana-3851	67	5	,	,	PUNCT
cana-3851	67	6	and	and	CCONJ
cana-3851	67	7	radiologists	radiologist	NOUN
cana-3851	67	8	may	may	AUX
cana-3851	67	9	learn	learn	VERB
cana-3851	67	10	a	a	DET
cana-3851	67	11	great	great	ADJ
cana-3851	67	12	deal	deal	NOUN
cana-3851	67	13	about	about	ADP
cana-3851	67	14	the	the	DET
cana-3851	67	15	anatomy	anatomy	NOUN
cana-3851	67	16	of	of	ADP
cana-3851	67	17	individuals	individual	NOUN
cana-3851	67	18	and	and	CCONJ
cana-3851	67	19	whole	whole	ADJ
cana-3851	67	20	populations	population	NOUN
cana-3851	67	21	via	via	ADP
cana-3851	67	22	medical	medical	ADJ
cana-3851	67	23	image	image	NOUN
cana-3851	67	24	processing	processing	NOUN
cana-3851	67	25	.	.	PUNCT
cana-3851	68	1	statistical	statistical	ADJ
cana-3851	68	2	analysis	analysis	NOUN
cana-3851	68	3	,	,	PUNCT
cana-3851	68	4	measurement	measurement	NOUN
cana-3851	68	5	,	,	PUNCT
cana-3851	68	6	and	and	CCONJ
cana-3851	68	7	the	the	DET
cana-3851	68	8	development	development	NOUN
cana-3851	68	9	of	of	ADP
cana-3851	68	10	simulation	simulation	NOUN
cana-3851	68	11	models	model	NOUN
cana-3851	68	12	that	that	PRON
cana-3851	68	13	include	include	VERB
cana-3851	68	14	actual	actual	ADJ
cana-3851	68	15	anatomical	anatomical	ADJ
cana-3851	68	16	geometries	geometry	NOUN
cana-3851	68	17	all	all	PRON
cana-3851	68	18	provide	provide	VERB
cana-3851	68	19	the	the	DET
cana-3851	68	20	possibility	possibility	NOUN
cana-3851	68	21	of	of	ADP
cana-3851	68	22	a	a	DET
cana-3851	68	23	more	more	ADV
cana-3851	68	24	comprehensive	comprehensive	ADJ
cana-3851	68	25	knowledge	knowledge	NOUN
cana-3851	68	26	of	of	ADP
cana-3851	68	27	the	the	DET
cana-3851	68	28	interplay	interplay	NOUN
cana-3851	68	29	between	between	ADP
cana-3851	68	30	medical	medical	ADJ
cana-3851	68	31	equipment	equipment	NOUN
cana-3851	68	32	and	and	CCONJ
cana-3851	68	33	human	human	ADJ
cana-3851	68	34	anatomy	anatomy	NOUN
cana-3851	68	35	,	,	PUNCT
cana-3851	68	36	for	for	ADP
cana-3851	68	37	instance	instance	NOUN
cana-3851	68	38	[	[	X
cana-3851	68	39	6	6	NUM
cana-3851	68	40	]	]	PUNCT
cana-3851	68	41	.	.	PUNCT
cana-3851	69	1	incorrect	incorrect	ADJ
cana-3851	69	2	results	result	NOUN
cana-3851	69	3	are	be	AUX
cana-3851	69	4	produced	produce	VERB
cana-3851	69	5	by	by	ADP
cana-3851	69	6	several	several	ADJ
cana-3851	69	7	ml	ml	NOUN
cana-3851	69	8	algorithms	algorithm	NOUN
cana-3851	69	9	when	when	SCONJ
cana-3851	69	10	pixel	pixel	PROPN
cana-3851	69	11	classification	classification	NOUN
cana-3851	69	12	occurs	occur	VERB
cana-3851	69	13	because	because	SCONJ
cana-3851	69	14	these	these	DET
cana-3851	69	15	algorithms	algorithm	NOUN
cana-3851	69	16	do	do	AUX
cana-3851	69	17	not	not	PART
cana-3851	69	18	take	take	VERB
cana-3851	69	19	into	into	ADP
cana-3851	69	20	account	account	NOUN
cana-3851	69	21	the	the	DET
cana-3851	69	22	local	local	ADJ
cana-3851	69	23	dependencies	dependency	NOUN
cana-3851	69	24	of	of	ADP
cana-3851	69	25	labels	label	NOUN
cana-3851	69	26	.	.	PUNCT
cana-3851	70	1	in	in	ADP
cana-3851	70	2	other	other	ADJ
cana-3851	70	3	words	word	NOUN
cana-3851	70	4	,	,	PUNCT
cana-3851	70	5	segmentation	segmentation	NOUN
cana-3851	70	6	labels	label	NOUN
cana-3851	70	7	are	be	AUX
cana-3851	70	8	conditionally	conditionally	ADV
cana-3851	70	9	independent	independent	ADJ
cana-3851	70	10	given	give	VERB
cana-3851	70	11	the	the	DET
cana-3851	70	12	input	input	NOUN
cana-3851	70	13	picture	picture	NOUN
cana-3851	70	14	.	.	PUNCT
cana-3851	71	1	conditional	conditional	ADJ
cana-3851	71	2	random	random	ADJ
cana-3851	71	3	fields	field	NOUN
cana-3851	71	4	(	(	PUNCT
cana-3851	71	5	crfs	crfs	PROPN
cana-3851	71	6	)	)	PUNCT
cana-3851	71	7	and	and	CCONJ
cana-3851	71	8	other	other	ADJ
cana-3851	71	9	computationally	computationally	ADV
cana-3851	71	10	expensive	expensive	ADJ
cana-3851	71	11	inference	inference	NOUN
cana-3851	71	12	methods	method	NOUN
cana-3851	71	13	with	with	ADP
cana-3851	71	14	structured	structured	ADJ
cana-3851	71	15	outputs	output	NOUN
cana-3851	71	16	may	may	AUX
cana-3851	71	17	help	help	VERB
cana-3851	71	18	with	with	ADP
cana-3851	71	19	this	this	PRON
cana-3851	71	20	.	.	PUNCT
cana-3851	72	1	another	another	DET
cana-3851	72	2	option	option	NOUN
cana-3851	72	3	is	be	AUX
cana-3851	72	4	to	to	PART
cana-3851	72	5	utilize	utilize	VERB
cana-3851	72	6	a	a	DET
cana-3851	72	7	cascaded	cascade	VERB
cana-3851	72	8	architecture	architecture	NOUN
cana-3851	72	9	,	,	PUNCT
cana-3851	72	10	which	which	PRON
cana-3851	72	11	involves	involve	VERB
cana-3851	72	12	passing	pass	VERB
cana-3851	72	13	the	the	DET
cana-3851	72	14	pixel	pixel	ADJ
cana-3851	72	15	-	-	ADJ
cana-3851	72	16	wise	wise	ADJ
cana-3851	72	17	probability	probability	NOUN
cana-3851	72	18	estimates	estimate	NOUN
cana-3851	72	19	from	from	ADP
cana-3851	72	20	one	one	NUM
cana-3851	72	21	cnn	cnn	NOUN
cana-3851	72	22	into	into	ADP
cana-3851	72	23	specified	specified	ADJ
cana-3851	72	24	layers	layer	NOUN
cana-3851	72	25	of	of	ADP
cana-3851	72	26	another	another	DET
cana-3851	72	27	dnn	dnn	NOUN
cana-3851	72	28	,	,	PUNCT
cana-3851	72	29	to	to	PART
cana-3851	72	30	explain	explain	VERB
cana-3851	72	31	label	label	NOUN
cana-3851	72	32	relationships	relationship	NOUN
cana-3851	72	33	.	.	PUNCT
cana-3851	73	1	the	the	DET
cana-3851	73	2	effectiveness	effectiveness	NOUN
cana-3851	73	3	of	of	ADP
cana-3851	73	4	convolutions	convolution	NOUN
cana-3851	73	5	suggests	suggest	VERB
cana-3851	73	6	that	that	SCONJ
cana-3851	73	7	this	this	DET
cana-3851	73	8	technique	technique	NOUN
cana-3851	73	9	might	might	AUX
cana-3851	73	10	be	be	AUX
cana-3851	73	11	much	much	ADV
cana-3851	73	12	faster	fast	ADJ
cana-3851	73	13	than	than	ADP
cana-3851	73	14	building	build	VERB
cana-3851	73	15	a	a	DET
cana-3851	73	16	crf	crf	NOUN
cana-3851	74	1	[	[	X
cana-3851	74	2	7	7	NUM
cana-3851	74	3	]	]	PUNCT
cana-3851	74	4	.	.	PUNCT
cana-3851	75	1	subfield	subfield	NOUN
cana-3851	75	2	of	of	ADP
cana-3851	75	3	machine	machine	NOUN
cana-3851	75	4	learning	learning	NOUN
cana-3851	75	5	known	know	VERB
cana-3851	75	6	as	as	ADP
cana-3851	75	7	"	"	PUNCT
cana-3851	75	8	deep	deep	ADJ
cana-3851	75	9	learning	learning	NOUN
cana-3851	75	10	"	"	PUNCT
cana-3851	75	11	allows	allow	VERB
cana-3851	75	12	computers	computer	NOUN
cana-3851	75	13	to	to	PART
cana-3851	75	14	learn	learn	VERB
cana-3851	75	15	data	data	NOUN
cana-3851	75	16	representations	representation	NOUN
cana-3851	75	17	,	,	PUNCT
cana-3851	75	18	which	which	PRON
cana-3851	75	19	in	in	ADP
cana-3851	75	20	turn	turn	NOUN
cana-3851	75	21	allows	allow	VERB
cana-3851	75	22	them	they	PRON
cana-3851	75	23	to	to	PART
cana-3851	75	24	draw	draw	VERB
cana-3851	75	25	inferences	inference	NOUN
cana-3851	75	26	and	and	CCONJ
cana-3851	75	27	make	make	VERB
cana-3851	75	28	predictions	prediction	NOUN
cana-3851	75	29	based	base	VERB
cana-3851	75	30	on	on	ADP
cana-3851	75	31	data	datum	NOUN
cana-3851	75	32	.	.	PUNCT
cana-3851	76	1	these	these	DET
cana-3851	76	2	methods	method	NOUN
cana-3851	76	3	constitute	constitute	VERB
cana-3851	76	4	a	a	DET
cana-3851	76	5	significant	significant	ADJ
cana-3851	76	6	computational	computational	ADJ
cana-3851	76	7	intelligence	intelligence	NOUN
cana-3851	76	8	approach	approach	NOUN
cana-3851	76	9	and	and	CCONJ
cana-3851	76	10	find	find	VERB
cana-3851	76	11	widespread	widespread	ADJ
cana-3851	76	12	use	use	NOUN
cana-3851	76	13	in	in	ADP
cana-3851	76	14	medical	medical	ADJ
cana-3851	76	15	imaging	imaging	NOUN
cana-3851	76	16	categorization	categorization	NOUN
cana-3851	76	17	.	.	PUNCT
cana-3851	77	1	deep	deep	ADJ
cana-3851	77	2	learning	learning	NOUN
cana-3851	77	3	has	have	AUX
cana-3851	77	4	been	be	AUX
cana-3851	77	5	very	very	ADV
cana-3851	77	6	successful	successful	ADJ
cana-3851	77	7	in	in	ADP
cana-3851	77	8	many	many	ADJ
cana-3851	77	9	various	various	ADJ
cana-3851	77	10	domains	domain	NOUN
cana-3851	77	11	and	and	CCONJ
cana-3851	77	12	applications	application	NOUN
cana-3851	77	13	,	,	PUNCT
cana-3851	77	14	but	but	CCONJ
cana-3851	77	15	it	it	PRON
cana-3851	77	16	is	be	AUX
cana-3851	77	17	a	a	DET
cana-3851	77	18	data	data	NOUN
cana-3851	77	19	thirsty	thirsty	ADJ
cana-3851	77	20	method	method	NOUN
cana-3851	77	21	that	that	PRON
cana-3851	77	22	requires	require	VERB
cana-3851	77	23	at	at	ADV
cana-3851	77	24	least	least	ADV
cana-3851	77	25	10	10	NUM
cana-3851	77	26	times	time	NOUN
cana-3851	77	27	as	as	ADV
cana-3851	77	28	many	many	ADJ
cana-3851	77	29	samples	sample	NOUN
cana-3851	77	30	with	with	ADP
cana-3851	77	31	degrees	degree	NOUN
cana-3851	77	32	of	of	ADP
cana-3851	77	33	freedom	freedom	NOUN
cana-3851	77	34	.	.	PUNCT
cana-3851	78	1	if	if	SCONJ
cana-3851	78	2	we	we	PRON
cana-3851	78	3	use	use	VERB
cana-3851	78	4	transfer	transfer	NOUN
cana-3851	78	5	learning	learn	VERB
cana-3851	78	6	to	to	PART
cana-3851	78	7	improve	improve	VERB
cana-3851	78	8	storing	store	VERB
cana-3851	78	9	knowledge	knowledge	NOUN
cana-3851	78	10	we	we	PRON
cana-3851	78	11	've	have	AUX
cana-3851	78	12	already	already	ADV
cana-3851	78	13	learned	learn	VERB
cana-3851	78	14	on	on	ADP
cana-3851	78	15	similar	similar	ADJ
cana-3851	78	16	situations	situation	NOUN
cana-3851	78	17	,	,	PUNCT
cana-3851	78	18	we	we	PRON
cana-3851	78	19	may	may	AUX
cana-3851	78	20	potentially	potentially	ADV
cana-3851	78	21	solve	solve	VERB
cana-3851	78	22	the	the	DET
cana-3851	78	23	difficulty	difficulty	NOUN
cana-3851	78	24	of	of	ADP
cana-3851	78	25	tiny	tiny	ADJ
cana-3851	78	26	training	training	NOUN
cana-3851	78	27	samples	sample	NOUN
cana-3851	78	28	.	.	PUNCT
cana-3851	79	1	in	in	ADP
cana-3851	79	2	transfer	transfer	NOUN
cana-3851	79	3	learning	learning	NOUN
cana-3851	79	4	,	,	PUNCT
cana-3851	79	5	a	a	DET
cana-3851	79	6	large	large	ADJ
cana-3851	79	7	dataset	dataset	NOUN
cana-3851	79	8	(	(	PUNCT
cana-3851	79	9	the	the	DET
cana-3851	79	10	base	base	NOUN
cana-3851	79	11	dataset	dataset	NOUN
cana-3851	79	12	)	)	PUNCT
cana-3851	79	13	is	be	AUX
cana-3851	79	14	used	use	VERB
cana-3851	79	15	to	to	PART
cana-3851	79	16	train	train	VERB
cana-3851	79	17	the	the	DET
cana-3851	79	18	network	network	NOUN
cana-3851	79	19	,	,	PUNCT
cana-3851	79	20	and	and	CCONJ
cana-3851	79	21	then	then	ADV
cana-3851	79	22	its	its	PRON
cana-3851	79	23	knowledge	knowledge	NOUN
cana-3851	79	24	is	be	AUX
cana-3851	79	25	applied	apply	VERB
cana-3851	79	26	to	to	ADP
cana-3851	79	27	a	a	DET
cana-3851	79	28	smaller	small	ADJ
cana-3851	79	29	dataset	dataset	NOUN
cana-3851	79	30	(	(	PUNCT
cana-3851	79	31	the	the	DET
cana-3851	79	32	target	target	NOUN
cana-3851	79	33	dataset	dataset	NOUN
cana-3851	79	34	)	)	PUNCT
cana-3851	80	1	[	[	X
cana-3851	80	2	8	8	NUM
cana-3851	80	3	]	]	PUNCT
cana-3851	80	4	.	.	PUNCT
cana-3851	81	1	this	this	PRON
cana-3851	81	2	is	be	AUX
cana-3851	81	3	one	one	NUM
cana-3851	81	4	way	way	NOUN
cana-3851	81	5	of	of	ADP
cana-3851	81	6	deep	deep	ADJ
cana-3851	81	7	learning	learning	NOUN
cana-3851	81	8	.	.	PUNCT
cana-3851	82	1	in	in	ADP
cana-3851	82	2	this	this	DET
cana-3851	82	3	study	study	NOUN
cana-3851	82	4	,	,	PUNCT
cana-3851	82	5	we	we	PRON
cana-3851	82	6	use	use	VERB
cana-3851	82	7	residual	residual	ADJ
cana-3851	82	8	networks	network	NOUN
cana-3851	82	9	(	(	PUNCT
cana-3851	82	10	resnets	resnet	NOUN
cana-3851	82	11	)	)	PUNCT
cana-3851	82	12	to	to	PART
cana-3851	82	13	improve	improve	VERB
cana-3851	82	14	computation	computation	NOUN
cana-3851	82	15	time	time	NOUN
cana-3851	82	16	and	and	CCONJ
cana-3851	82	17	get	get	VERB
cana-3851	82	18	around	around	ADP
cana-3851	82	19	the	the	DET
cana-3851	82	20	problems	problem	NOUN
cana-3851	82	21	with	with	ADP
cana-3851	82	22	convolutional	convolutional	ADJ
cana-3851	82	23	neural	neural	ADJ
cana-3851	82	24	networks	network	NOUN
cana-3851	82	25	(	(	PUNCT
cana-3851	82	26	cnns	cnns	PROPN
cana-3851	82	27	)	)	PUNCT
cana-3851	82	28	and	and	CCONJ
cana-3851	82	29	fcns	fcns	NOUN
cana-3851	82	30	.	.	PUNCT
cana-3851	83	1	the	the	DET
cana-3851	83	2	idea	idea	NOUN
cana-3851	83	3	behind	behind	ADP
cana-3851	83	4	resnets	resnet	NOUN
cana-3851	83	5	is	be	AUX
cana-3851	83	6	to	to	PART
cana-3851	83	7	add	add	VERB
cana-3851	83	8	the	the	DET
cana-3851	83	9	layer	layer	NOUN
cana-3851	83	10	's	's	PART
cana-3851	83	11	output	output	NOUN
cana-3851	83	12	to	to	ADP
cana-3851	83	13	its	its	PRON
cana-3851	83	14	input	input	NOUN
cana-3851	83	15	.	.	PUNCT
cana-3851	84	1	since	since	SCONJ
cana-3851	84	2	deep	deep	ADJ
cana-3851	84	3	networks	network	NOUN
cana-3851	84	4	already	already	ADV
cana-3851	84	5	include	include	VERB
cana-3851	84	6	shortcut	shortcut	NOUN
cana-3851	84	7	connections	connection	NOUN
cana-3851	84	8	running	run	VERB
cana-3851	84	9	parallel	parallel	NOUN
cana-3851	84	10	to	to	ADP
cana-3851	84	11	their	their	PRON
cana-3851	84	12	regular	regular	ADJ
cana-3851	84	13	convolutional	convolutional	ADJ
cana-3851	84	14	layers	layer	NOUN
cana-3851	84	15	,	,	PUNCT
cana-3851	84	16	this	this	DET
cana-3851	84	17	little	little	ADJ
cana-3851	84	18	tweak	tweak	NOUN
cana-3851	84	19	makes	make	VERB
cana-3851	84	20	training	train	VERB
cana-3851	84	21	them	they	PRON
cana-3851	84	22	much	much	ADV
cana-3851	84	23	easier	easy	ADJ
cana-3851	84	24	.	.	PUNCT
cana-3851	85	1	training	training	NOUN
cana-3851	85	2	goes	go	VERB
cana-3851	85	3	more	more	ADV
cana-3851	85	4	quickly	quickly	ADV
cana-3851	85	5	and	and	CCONJ
cana-3851	85	6	accurately	accurately	ADV
cana-3851	85	7	because	because	SCONJ
cana-3851	85	8	to	to	ADP
cana-3851	85	9	these	these	DET
cana-3851	85	10	live	live	ADJ
cana-3851	85	11	shortcuts	shortcut	NOUN
cana-3851	85	12	,	,	PUNCT
cana-3851	85	13	and	and	CCONJ
cana-3851	85	14	gradients	gradient	NOUN
cana-3851	85	15	propagate	propagate	VERB
cana-3851	85	16	communications	communication	NOUN
cana-3851	85	17	on	on	ADP
cana-3851	85	18	applied	apply	VERB
cana-3851	85	19	nonlinear	nonlinear	ADJ
cana-3851	85	20	analysis	analysis	NOUN
cana-3851	85	21	issn	issn	NOUN
cana-3851	85	22	:	:	PUNCT
cana-3851	85	23	1074	1074	NUM
cana-3851	85	24	-	-	PUNCT
cana-3851	85	25	133x	133x	NUM
cana-3851	85	26	vol	vol	NOUN
cana-3851	85	27	32	32	NUM
cana-3851	85	28	no	no	NOUN
cana-3851	85	29	.	.	PUNCT
cana-3851	86	1	9s	9s	NUM
cana-3851	86	2	(	(	PUNCT
cana-3851	86	3	2025	2025	NUM
cana-3851	86	4	)	)	PUNCT
cana-3851	86	5	218	218	NUM
cana-3851	86	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-3851	86	7	readily	readily	ADV
cana-3851	86	8	across	across	ADP
cana-3851	86	9	them	they	PRON
cana-3851	86	10	,	,	PUNCT
cana-3851	86	11	thanks	thank	NOUN
cana-3851	86	12	to	to	ADP
cana-3851	86	13	the	the	DET
cana-3851	86	14	much	much	ADV
cana-3851	86	15	enhanced	enhance	VERB
cana-3851	86	16	depth.one	depth.one	X
cana-3851	86	17	deep	deep	ADJ
cana-3851	86	18	cnn	cnn	NOUN
cana-3851	86	19	architecture	architecture	NOUN
cana-3851	86	20	is	be	AUX
cana-3851	86	21	vggnet	vggnet	ADJ
cana-3851	86	22	.	.	PUNCT
cana-3851	87	1	in	in	ADP
cana-3851	87	2	2014	2014	NUM
cana-3851	87	3	,	,	PUNCT
cana-3851	87	4	it	it	PRON
cana-3851	87	5	came	come	VERB
cana-3851	87	6	in	in	ADP
cana-3851	87	7	second	second	ADJ
cana-3851	87	8	place	place	NOUN
cana-3851	87	9	in	in	ADP
cana-3851	87	10	the	the	DET
cana-3851	87	11	ilsvrc	ilsvrc	ADJ
cana-3851	87	12	competition	competition	NOUN
cana-3851	87	13	[	[	X
cana-3851	87	14	10	10	NUM
cana-3851	87	15	]	]	PUNCT
cana-3851	87	16	.	.	PUNCT
cana-3851	88	1	here	here	ADV
cana-3851	88	2	,	,	PUNCT
cana-3851	88	3	we	we	PRON
cana-3851	88	4	provide	provide	VERB
cana-3851	88	5	a	a	DET
cana-3851	88	6	vgg16+resnet50	vgg16+resnet50	NOUN
cana-3851	88	7	hybrid	hybrid	ADJ
cana-3851	88	8	model	model	NOUN
cana-3851	88	9	for	for	ADP
cana-3851	88	10	mri	mri	NOUN
cana-3851	88	11	-	-	PUNCT
cana-3851	88	12	based	base	VERB
cana-3851	88	13	brain	brain	NOUN
cana-3851	88	14	tumor	tumor	NOUN
cana-3851	88	15	segmentation	segmentation	NOUN
cana-3851	88	16	.	.	PUNCT
cana-3851	89	1	ii.related	ii.relate	VERB
cana-3851	89	2	work	work	VERB
cana-3851	89	3	the	the	DET
cana-3851	89	4	visual	visual	ADJ
cana-3851	89	5	characteristics	characteristic	NOUN
cana-3851	89	6	of	of	ADP
cana-3851	89	7	the	the	DET
cana-3851	89	8	tumor	tumor	NOUN
cana-3851	89	9	region	region	NOUN
cana-3851	89	10	significantly	significantly	ADV
cana-3851	89	11	influence	influence	VERB
cana-3851	89	12	the	the	DET
cana-3851	89	13	accuracy	accuracy	NOUN
cana-3851	89	14	of	of	ADP
cana-3851	89	15	brain	brain	NOUN
cana-3851	89	16	tumor	tumor	NOUN
cana-3851	89	17	identification	identification	NOUN
cana-3851	89	18	and	and	CCONJ
cana-3851	89	19	segmentation	segmentation	NOUN
cana-3851	89	20	.	.	PUNCT
cana-3851	90	1	it	it	PRON
cana-3851	90	2	is	be	AUX
cana-3851	90	3	possible	possible	ADJ
cana-3851	90	4	for	for	SCONJ
cana-3851	90	5	similar	similar	ADJ
cana-3851	90	6	scans	scan	NOUN
cana-3851	90	7	to	to	PART
cana-3851	90	8	show	show	VERB
cana-3851	90	9	different	different	ADJ
cana-3851	90	10	tumor	tumor	NOUN
cana-3851	90	11	areas	area	NOUN
cana-3851	90	12	in	in	ADP
cana-3851	90	13	terms	term	NOUN
cana-3851	90	14	of	of	ADP
cana-3851	90	15	intensity	intensity	NOUN
cana-3851	90	16	,	,	PUNCT
cana-3851	90	17	shape	shape	NOUN
cana-3851	90	18	,	,	PUNCT
cana-3851	90	19	location	location	NOUN
cana-3851	90	20	,	,	PUNCT
cana-3851	90	21	and	and	CCONJ
cana-3851	90	22	size	size	NOUN
cana-3851	90	23	.	.	PUNCT
cana-3851	91	1	in	in	ADP
cana-3851	91	2	this	this	DET
cana-3851	91	3	article	article	NOUN
cana-3851	91	4	,	,	PUNCT
cana-3851	91	5	we	we	PRON
cana-3851	91	6	review	review	VERB
cana-3851	91	7	the	the	DET
cana-3851	91	8	research	research	NOUN
cana-3851	91	9	on	on	ADP
cana-3851	91	10	methods	method	NOUN
cana-3851	91	11	for	for	ADP
cana-3851	91	12	segmenting	segment	VERB
cana-3851	91	13	and	and	CCONJ
cana-3851	91	14	detecting	detect	VERB
cana-3851	91	15	brain	brain	NOUN
cana-3851	91	16	tumors	tumor	NOUN
cana-3851	91	17	in	in	ADP
cana-3851	91	18	images	image	NOUN
cana-3851	91	19	.	.	PUNCT
cana-3851	92	1	with	with	ADP
cana-3851	92	2	the	the	DET
cana-3851	92	3	addition	addition	NOUN
cana-3851	92	4	of	of	ADP
cana-3851	92	5	volumetric	volumetric	ADJ
cana-3851	92	6	input	input	NOUN
cana-3851	92	7	patches	patch	NOUN
cana-3851	92	8	,	,	PUNCT
cana-3851	92	9	jonas	jonas	PROPN
cana-3851	92	10	wacker	wacker	PROPN
cana-3851	92	11	et	et	PROPN
cana-3851	92	12	al	al	PROPN
cana-3851	92	13	.	.	PUNCT
cana-3851	93	1	[	[	X
cana-3851	93	2	11	11	NUM
cana-3851	93	3	]	]	PUNCT
cana-3851	93	4	shown	show	VERB
cana-3851	93	5	that	that	SCONJ
cana-3851	93	6	albunet3d	albunet3d	ADJ
cana-3851	93	7	outperforms	outperform	VERB
cana-3851	93	8	albunet2d	albunet2d	PROPN
cana-3851	93	9	even	even	ADV
cana-3851	93	10	more	more	ADJ
cana-3851	93	11	.	.	PUNCT
cana-3851	94	1	a	a	DET
cana-3851	94	2	more	more	ADV
cana-3851	94	3	robust	robust	ADJ
cana-3851	94	4	training	training	NOUN
cana-3851	94	5	method	method	NOUN
cana-3851	94	6	and	and	CCONJ
cana-3851	94	7	better	well	ADJ
cana-3851	94	8	segmentation	segmentation	NOUN
cana-3851	94	9	outcomes	outcome	NOUN
cana-3851	94	10	using	use	VERB
cana-3851	94	11	u	u	NOUN
cana-3851	94	12	-	-	ADJ
cana-3851	94	13	net	net	ADJ
cana-3851	94	14	based	base	VERB
cana-3851	94	15	architectures	architecture	NOUN
cana-3851	94	16	for	for	ADP
cana-3851	94	17	the	the	DET
cana-3851	94	18	problem	problem	NOUN
cana-3851	94	19	of	of	ADP
cana-3851	94	20	brain	brain	NOUN
cana-3851	94	21	tumor	tumor	NOUN
cana-3851	94	22	segmentation	segmentation	NOUN
cana-3851	94	23	are	be	AUX
cana-3851	94	24	shown	show	VERB
cana-3851	94	25	by	by	ADP
cana-3851	94	26	using	use	VERB
cana-3851	94	27	encoders	encoder	NOUN
cana-3851	94	28	pretrained	pretraine	VERB
cana-3851	94	29	on	on	ADP
cana-3851	94	30	imagenet	imagenet	NOUN
cana-3851	94	31	.	.	PUNCT
cana-3851	95	1	regrettably	regrettably	ADV
cana-3851	95	2	,	,	PUNCT
cana-3851	95	3	this	this	PRON
cana-3851	95	4	is	be	AUX
cana-3851	95	5	not	not	PART
cana-3851	95	6	applicable	applicable	ADJ
cana-3851	95	7	to	to	ADP
cana-3851	95	8	their	their	PRON
cana-3851	95	9	privately	privately	ADV
cana-3851	95	10	obtained	obtain	VERB
cana-3851	95	11	clinical	clinical	ADJ
cana-3851	95	12	dataset	dataset	NOUN
cana-3851	95	13	,	,	PUNCT
cana-3851	95	14	which	which	PRON
cana-3851	95	15	necessitates	necessitate	VERB
cana-3851	95	16	further	further	ADJ
cana-3851	95	17	robustness	robustness	NOUN
cana-3851	95	18	via	via	ADP
cana-3851	95	19	future	future	ADJ
cana-3851	95	20	study	study	NOUN
cana-3851	95	21	.	.	PUNCT
cana-3851	96	1	compared	compare	VERB
cana-3851	96	2	to	to	ADP
cana-3851	96	3	the	the	DET
cana-3851	96	4	brats	brat	NOUN
cana-3851	96	5	benchmark	benchmark	NOUN
cana-3851	96	6	,	,	PUNCT
cana-3851	96	7	the	the	DET
cana-3851	96	8	mri	mri	NOUN
cana-3851	96	9	data	datum	NOUN
cana-3851	96	10	that	that	PRON
cana-3851	96	11	is	be	AUX
cana-3851	96	12	accessible	accessible	ADJ
cana-3851	96	13	in	in	ADP
cana-3851	96	14	a	a	DET
cana-3851	96	15	real	real	ADJ
cana-3851	96	16	-	-	PUNCT
cana-3851	96	17	world	world	NOUN
cana-3851	96	18	clinical	clinical	ADJ
cana-3851	96	19	setting	setting	NOUN
cana-3851	96	20	is	be	AUX
cana-3851	96	21	far	far	ADV
cana-3851	96	22	more	more	ADV
cana-3851	96	23	diverse	diverse	ADJ
cana-3851	96	24	.	.	PUNCT
cana-3851	97	1	in	in	ADP
cana-3851	97	2	order	order	NOUN
cana-3851	97	3	to	to	PART
cana-3851	97	4	automatically	automatically	ADV
cana-3851	97	5	detect	detect	VERB
cana-3851	97	6	brain	brain	NOUN
cana-3851	97	7	cancers	cancer	NOUN
cana-3851	97	8	from	from	ADP
cana-3851	97	9	mri	mri	NOUN
cana-3851	97	10	data	datum	NOUN
cana-3851	97	11	,	,	PUNCT
cana-3851	97	12	ayesha	ayesha	PROPN
cana-3851	97	13	younis	younis	PROPN
cana-3851	97	14	et	et	VERB
cana-3851	97	15	al	al	PROPN
cana-3851	97	16	.	.	PUNCT
cana-3851	98	1	[	[	X
cana-3851	98	2	12	12	NUM
cana-3851	98	3	]	]	PUNCT
cana-3851	98	4	constructed	construct	VERB
cana-3851	98	5	a	a	DET
cana-3851	98	6	convolutional	convolutional	ADJ
cana-3851	98	7	neural	neural	ADJ
cana-3851	98	8	network	network	NOUN
cana-3851	98	9	(	(	PUNCT
cana-3851	98	10	cnn	cnn	PROPN
cana-3851	98	11	)	)	PUNCT
cana-3851	98	12	.	.	PUNCT
cana-3851	99	1	it	it	PRON
cana-3851	99	2	would	would	AUX
cana-3851	99	3	be	be	AUX
cana-3851	99	4	easier	easy	ADJ
cana-3851	99	5	and	and	CCONJ
cana-3851	99	6	faster	fast	ADV
cana-3851	99	7	to	to	PART
cana-3851	99	8	train	train	VERB
cana-3851	99	9	the	the	DET
cana-3851	99	10	network	network	NOUN
cana-3851	99	11	using	use	VERB
cana-3851	99	12	a	a	DET
cana-3851	99	13	pretrained	pretraine	VERB
cana-3851	99	14	vgg	vgg	ADJ
cana-3851	99	15	16	16	NUM
cana-3851	99	16	model	model	NOUN
cana-3851	99	17	.	.	PUNCT
cana-3851	100	1	when	when	SCONJ
cana-3851	100	2	choosing	choose	VERB
cana-3851	100	3	a	a	DET
cana-3851	100	4	commercial	commercial	ADJ
cana-3851	100	5	model	model	NOUN
cana-3851	100	6	,	,	PUNCT
cana-3851	100	7	it	it	PRON
cana-3851	100	8	is	be	AUX
cana-3851	100	9	vital	vital	ADJ
cana-3851	100	10	to	to	PART
cana-3851	100	11	examine	examine	VERB
cana-3851	100	12	vgg	vgg	PROPN
cana-3851	100	13	16	16	NUM
cana-3851	100	14	,	,	PUNCT
cana-3851	100	15	a	a	DET
cana-3851	100	16	cnn	cnn	PROPN
cana-3851	100	17	model	model	NOUN
cana-3851	100	18	with	with	ADP
cana-3851	100	19	sixteen	sixteen	NUM
cana-3851	100	20	layers	layer	NOUN
cana-3851	100	21	.	.	PUNCT
cana-3851	101	1	their	their	PRON
cana-3851	101	2	paper	paper	NOUN
cana-3851	101	3	's	's	PART
cana-3851	101	4	stated	state	VERB
cana-3851	101	5	goal	goal	NOUN
cana-3851	101	6	was	be	AUX
cana-3851	101	7	to	to	PART
cana-3851	101	8	find	find	VERB
cana-3851	101	9	a	a	DET
cana-3851	101	10	brain	brain	NOUN
cana-3851	101	11	tumor	tumor	NOUN
cana-3851	101	12	using	use	VERB
cana-3851	101	13	vgg	vgg	PROPN
cana-3851	101	14	16	16	NUM
cana-3851	101	15	,	,	PUNCT
cana-3851	101	16	cnn	cnn	PROPN
cana-3851	101	17	model	model	NOUN
cana-3851	101	18	architecture	architecture	NOUN
cana-3851	101	19	,	,	PUNCT
cana-3851	101	20	and	and	CCONJ
cana-3851	101	21	weights	weight	NOUN
cana-3851	101	22	to	to	ADP
cana-3851	101	23	training	training	NOUN
cana-3851	101	24	data	datum	NOUN
cana-3851	101	25	.	.	PUNCT
cana-3851	102	1	the	the	DET
cana-3851	102	2	precision	precision	NOUN
cana-3851	102	3	of	of	ADP
cana-3851	102	4	the	the	DET
cana-3851	102	5	outcome	outcome	NOUN
cana-3851	102	6	was	be	AUX
cana-3851	102	7	verified	verify	VERB
cana-3851	102	8	.	.	PUNCT
cana-3851	103	1	they	they	PRON
cana-3851	103	2	planned	plan	VERB
cana-3851	103	3	to	to	PART
cana-3851	103	4	use	use	VERB
cana-3851	103	5	magnetic	magnetic	ADJ
cana-3851	103	6	resonance	resonance	NOUN
cana-3851	103	7	imaging	imaging	NOUN
cana-3851	103	8	(	(	PUNCT
cana-3851	103	9	mri	mri	NOUN
cana-3851	103	10	)	)	PUNCT
cana-3851	103	11	scans	scan	NOUN
cana-3851	103	12	of	of	ADP
cana-3851	103	13	the	the	DET
cana-3851	103	14	brain	brain	NOUN
cana-3851	103	15	to	to	PART
cana-3851	103	16	look	look	VERB
cana-3851	103	17	for	for	ADP
cana-3851	103	18	tumors	tumor	NOUN
cana-3851	103	19	.	.	PUNCT
cana-3851	104	1	the	the	DET
cana-3851	104	2	findings	finding	NOUN
cana-3851	104	3	showed	show	VERB
cana-3851	104	4	that	that	SCONJ
cana-3851	104	5	the	the	DET
cana-3851	104	6	proposed	propose	VERB
cana-3851	104	7	network	network	NOUN
cana-3851	104	8	design	design	NOUN
cana-3851	104	9	was	be	AUX
cana-3851	104	10	both	both	PRON
cana-3851	104	11	aesthetically	aesthetically	ADV
cana-3851	104	12	pleasing	pleasing	ADJ
cana-3851	104	13	and	and	CCONJ
cana-3851	104	14	much	much	ADV
cana-3851	104	15	more	more	ADV
cana-3851	104	16	effective	effective	ADJ
cana-3851	104	17	than	than	ADP
cana-3851	104	18	conventional	conventional	ADJ
cana-3851	104	19	approaches	approach	NOUN
cana-3851	104	20	in	in	ADP
cana-3851	104	21	tumor	tumor	NOUN
cana-3851	104	22	identification	identification	NOUN
cana-3851	104	23	.	.	PUNCT
cana-3851	105	1	several	several	ADJ
cana-3851	105	2	processing	processing	NOUN
cana-3851	105	3	techniques	technique	NOUN
cana-3851	105	4	were	be	AUX
cana-3851	105	5	also	also	ADV
cana-3851	105	6	carried	carry	VERB
cana-3851	105	7	out	out	ADP
cana-3851	105	8	to	to	PART
cana-3851	105	9	enhance	enhance	VERB
cana-3851	105	10	the	the	DET
cana-3851	105	11	model	model	NOUN
cana-3851	105	12	's	's	PART
cana-3851	105	13	performance	performance	NOUN
cana-3851	105	14	even	even	ADV
cana-3851	105	15	more	more	ADV
cana-3851	105	16	.	.	PUNCT
cana-3851	106	1	biomedical	biomedical	ADJ
cana-3851	106	2	image	image	NOUN
cana-3851	106	3	segmentation	segmentation	NOUN
cana-3851	106	4	is	be	AUX
cana-3851	106	5	a	a	DET
cana-3851	106	6	common	common	ADJ
cana-3851	106	7	goal	goal	NOUN
cana-3851	106	8	for	for	ADP
cana-3851	106	9	both	both	PRON
cana-3851	106	10	of	of	ADP
cana-3851	106	11	the	the	DET
cana-3851	106	12	networks	network	NOUN
cana-3851	106	13	described	describe	VERB
cana-3851	106	14	by	by	ADP
cana-3851	106	15	mahnoor	mahnoor	PROPN
cana-3851	106	16	ali	ali	PROPN
cana-3851	106	17	et	et	PROPN
cana-3851	106	18	al	al	PROPN
cana-3851	106	19	.	.	PUNCT
cana-3851	107	1	[	[	X
cana-3851	107	2	13	13	NUM
cana-3851	107	3	]	]	PUNCT
cana-3851	107	4	,	,	PUNCT
cana-3851	107	5	which	which	PRON
cana-3851	107	6	form	form	VERB
cana-3851	107	7	an	an	DET
cana-3851	107	8	ensemble	ensemble	NOUN
cana-3851	107	9	.	.	PUNCT
cana-3851	108	1	when	when	SCONJ
cana-3851	108	2	presented	present	VERB
cana-3851	108	3	with	with	ADP
cana-3851	108	4	the	the	DET
cana-3851	108	5	multimodal	multimodal	NOUN
cana-3851	108	6	mri	mri	NOUN
cana-3851	108	7	images	image	NOUN
cana-3851	108	8	from	from	ADP
cana-3851	108	9	the	the	DET
cana-3851	108	10	brats	brat	NOUN
cana-3851	108	11	2019	2019	NUM
cana-3851	108	12	challenge	challenge	NOUN
cana-3851	108	13	,	,	PUNCT
cana-3851	108	14	the	the	DET
cana-3851	108	15	ensemble	ensemble	ADJ
cana-3851	108	16	is	be	AUX
cana-3851	108	17	able	able	ADJ
cana-3851	108	18	to	to	PART
cana-3851	108	19	provide	provide	VERB
cana-3851	108	20	very	very	ADV
cana-3851	108	21	accurate	accurate	ADJ
cana-3851	108	22	tumor	tumor	NOUN
cana-3851	108	23	segmentation	segmentation	NOUN
cana-3851	108	24	,	,	PUNCT
cana-3851	108	25	which	which	PRON
cana-3851	108	26	compares	compare	VERB
cana-3851	108	27	well	well	ADV
cana-3851	108	28	with	with	ADP
cana-3851	108	29	predictions	prediction	NOUN
cana-3851	108	30	made	make	VERB
cana-3851	108	31	by	by	ADP
cana-3851	108	32	other	other	ADJ
cana-3851	108	33	state	state	NOUN
cana-3851	108	34	-	-	PUNCT
cana-3851	108	35	ofart	ofart	NOUN
cana-3851	108	36	models	model	NOUN
cana-3851	108	37	.	.	PUNCT
cana-3851	109	1	they	they	PRON
cana-3851	109	2	blend	blend	VERB
cana-3851	109	3	the	the	DET
cana-3851	109	4	individual	individual	ADJ
cana-3851	109	5	model	model	NOUN
cana-3851	109	6	outputs	output	NOUN
cana-3851	109	7	using	use	VERB
cana-3851	109	8	a	a	DET
cana-3851	109	9	variable	variable	NOUN
cana-3851	109	10	ensembling	ensemble	VERB
cana-3851	109	11	strategy	strategy	NOUN
cana-3851	109	12	to	to	PART
cana-3851	109	13	get	get	VERB
cana-3851	109	14	the	the	DET
cana-3851	109	15	best	good	ADJ
cana-3851	109	16	ratings	rating	NOUN
cana-3851	109	17	.	.	PUNCT
cana-3851	110	1	to	to	PART
cana-3851	110	2	help	help	VERB
cana-3851	110	3	with	with	ADP
cana-3851	110	4	disease	disease	NOUN
cana-3851	110	5	planning	planning	NOUN
cana-3851	110	6	and	and	CCONJ
cana-3851	110	7	patient	patient	ADJ
cana-3851	110	8	care	care	NOUN
cana-3851	110	9	in	in	ADP
cana-3851	110	10	the	the	DET
cana-3851	110	11	clinic	clinic	NOUN
cana-3851	110	12	,	,	PUNCT
cana-3851	110	13	the	the	DET
cana-3851	110	14	suggested	suggest	VERB
cana-3851	110	15	ensemble	ensemble	NOUN
cana-3851	110	16	provides	provide	VERB
cana-3851	110	17	an	an	DET
cana-3851	110	18	objective	objective	NOUN
cana-3851	110	19	and	and	CCONJ
cana-3851	110	20	automated	automated	ADJ
cana-3851	110	21	way	way	NOUN
cana-3851	110	22	to	to	PART
cana-3851	110	23	generate	generate	VERB
cana-3851	110	24	brain	brain	NOUN
cana-3851	110	25	tumor	tumor	NOUN
cana-3851	110	26	segmentation	segmentation	NOUN
cana-3851	110	27	.	.	PUNCT
cana-3851	111	1	in	in	ADP
cana-3851	111	2	their	their	PRON
cana-3851	111	3	study	study	NOUN
cana-3851	111	4	,	,	PUNCT
cana-3851	111	5	yakubbhanothu	yakubbhanothu	PROPN
cana-3851	111	6	et	et	PROPN
cana-3851	111	7	al	al	PROPN
cana-3851	111	8	.	.	PUNCT
cana-3851	112	1	[	[	X
cana-3851	112	2	14	14	NUM
cana-3851	112	3	]	]	PUNCT
cana-3851	112	4	discussed	discuss	VERB
cana-3851	112	5	the	the	DET
cana-3851	112	6	use	use	NOUN
cana-3851	112	7	of	of	ADP
cana-3851	112	8	a	a	DET
cana-3851	112	9	deep	deep	ADJ
cana-3851	112	10	learning	learning	NOUN
cana-3851	112	11	system	system	NOUN
cana-3851	112	12	for	for	ADP
cana-3851	112	13	the	the	DET
cana-3851	112	14	automatic	automatic	ADJ
cana-3851	112	15	detection	detection	NOUN
cana-3851	112	16	and	and	CCONJ
cana-3851	112	17	categorization	categorization	NOUN
cana-3851	112	18	of	of	ADP
cana-3851	112	19	brain	brain	NOUN
cana-3851	112	20	cancers	cancer	NOUN
cana-3851	112	21	from	from	ADP
cana-3851	112	22	mri	mri	NOUN
cana-3851	112	23	images	image	NOUN
cana-3851	112	24	.	.	PUNCT
cana-3851	113	1	the	the	DET
cana-3851	113	2	faster	fast	ADJ
cana-3851	113	3	r	r	NOUN
cana-3851	113	4	-	-	PUNCT
cana-3851	113	5	cnn	cnn	PROPN
cana-3851	113	6	approach	approach	NOUN
cana-3851	113	7	was	be	AUX
cana-3851	113	8	used	use	VERB
cana-3851	113	9	to	to	PART
cana-3851	113	10	detect	detect	VERB
cana-3851	113	11	tumor	tumor	NOUN
cana-3851	113	12	areas	area	NOUN
cana-3851	113	13	and	and	CCONJ
cana-3851	113	14	classify	classify	VERB
cana-3851	113	15	them	they	PRON
cana-3851	113	16	as	as	ADP
cana-3851	113	17	glioma	glioma	NOUN
cana-3851	113	18	,	,	PUNCT
cana-3851	113	19	meningioma	meningioma	NOUN
cana-3851	113	20	,	,	PUNCT
cana-3851	113	21	or	or	CCONJ
cana-3851	113	22	pituitary	pituitary	ADJ
cana-3851	113	23	tumor	tumor	NOUN
cana-3851	113	24	.	.	PUNCT
cana-3851	114	1	the	the	DET
cana-3851	114	2	faster	fast	ADJ
cana-3851	114	3	r	r	NOUN
cana-3851	114	4	-	-	PUNCT
cana-3851	114	5	cnn	cnn	PROPN
cana-3851	114	6	approach	approach	NOUN
cana-3851	114	7	was	be	AUX
cana-3851	114	8	built	build	VERB
cana-3851	114	9	on	on	ADP
cana-3851	114	10	top	top	NOUN
cana-3851	114	11	of	of	ADP
cana-3851	114	12	a	a	DET
cana-3851	114	13	vgg-16	vgg-16	NOUN
cana-3851	114	14	deep	deep	ADJ
cana-3851	114	15	convolutional	convolutional	ADJ
cana-3851	114	16	network	network	NOUN
cana-3851	114	17	.	.	PUNCT
cana-3851	115	1	the	the	DET
cana-3851	115	2	proposed	propose	VERB
cana-3851	115	3	approach	approach	NOUN
cana-3851	115	4	employs	employ	VERB
cana-3851	115	5	rpn	rpn	NOUN
cana-3851	115	6	to	to	PART
cana-3851	115	7	ascertain	ascertain	VERB
cana-3851	115	8	the	the	DET
cana-3851	115	9	optimal	optimal	ADJ
cana-3851	115	10	bounding	bounding	NOUN
cana-3851	115	11	box	box	NOUN
cana-3851	115	12	for	for	ADP
cana-3851	115	13	the	the	DET
cana-3851	115	14	successful	successful	ADJ
cana-3851	115	15	localization	localization	NOUN
cana-3851	115	16	of	of	ADP
cana-3851	115	17	brain	brain	NOUN
cana-3851	115	18	tumors	tumor	NOUN
cana-3851	115	19	.	.	PUNCT
cana-3851	116	1	we	we	PRON
cana-3851	116	2	enhanced	enhance	VERB
cana-3851	116	3	the	the	DET
cana-3851	116	4	map	map	NOUN
cana-3851	116	5	for	for	ADP
cana-3851	116	6	detecting	detect	VERB
cana-3851	116	7	brain	brain	NOUN
cana-3851	116	8	tumors	tumor	NOUN
cana-3851	116	9	using	use	VERB
cana-3851	116	10	the	the	DET
cana-3851	116	11	test	test	NOUN
cana-3851	116	12	dataset	dataset	NOUN
cana-3851	116	13	.	.	PUNCT
cana-3851	117	1	they	they	PRON
cana-3851	117	2	should	should	AUX
cana-3851	117	3	broaden	broaden	VERB
cana-3851	117	4	their	their	PRON
cana-3851	117	5	research	research	NOUN
cana-3851	117	6	to	to	PART
cana-3851	117	7	find	find	VERB
cana-3851	117	8	the	the	DET
cana-3851	117	9	tumor	tumor	NOUN
cana-3851	117	10	's	's	PART
cana-3851	117	11	percentage	percentage	NOUN
cana-3851	117	12	area	area	NOUN
cana-3851	117	13	in	in	ADP
cana-3851	117	14	relation	relation	NOUN
cana-3851	117	15	to	to	ADP
cana-3851	117	16	the	the	DET
cana-3851	117	17	brain	brain	NOUN
cana-3851	117	18	area	area	NOUN
cana-3851	117	19	as	as	ADV
cana-3851	117	20	well	well	ADV
cana-3851	117	21	.	.	PUNCT
cana-3851	118	1	their	their	PRON
cana-3851	118	2	approach	approach	NOUN
cana-3851	118	3	may	may	AUX
cana-3851	118	4	also	also	ADV
cana-3851	118	5	be	be	AUX
cana-3851	118	6	useful	useful	ADJ
cana-3851	118	7	for	for	ADP
cana-3851	118	8	the	the	DET
cana-3851	118	9	categorization	categorization	NOUN
cana-3851	118	10	and	and	CCONJ
cana-3851	118	11	segmentation	segmentation	NOUN
cana-3851	118	12	of	of	ADP
cana-3851	118	13	skin	skin	NOUN
cana-3851	118	14	lesions	lesion	NOUN
cana-3851	118	15	,	,	PUNCT
cana-3851	118	16	two	two	NUM
cana-3851	118	17	additional	additional	ADJ
cana-3851	118	18	medicinal	medicinal	ADJ
cana-3851	118	19	applications	application	NOUN
cana-3851	118	20	.	.	PUNCT
cana-3851	119	1	communications	communication	NOUN
cana-3851	119	2	on	on	ADP
cana-3851	119	3	applied	apply	VERB
cana-3851	119	4	nonlinear	nonlinear	ADJ
cana-3851	119	5	analysis	analysis	NOUN
cana-3851	119	6	issn	issn	NOUN
cana-3851	119	7	:	:	PUNCT
cana-3851	119	8	1074	1074	NUM
cana-3851	119	9	-	-	PUNCT
cana-3851	119	10	133x	133x	NUM
cana-3851	119	11	vol	vol	NOUN
cana-3851	119	12	32	32	NUM
cana-3851	119	13	no	no	NOUN
cana-3851	119	14	.	.	PUNCT
cana-3851	120	1	9s	9s	NUM
cana-3851	120	2	(	(	PUNCT
cana-3851	120	3	2025	2025	NUM
cana-3851	120	4	)	)	PUNCT
cana-3851	120	5	219	219	NUM
cana-3851	120	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-3851	121	1	fahad	fahad	PROPN
cana-3851	121	2	ahmed	ahmed	PROPN
cana-3851	121	3	et	et	PROPN
cana-3851	121	4	al	al	PROPN
cana-3851	121	5	.	.	PUNCT
cana-3851	122	1	[	[	X
cana-3851	122	2	15	15	NUM
cana-3851	122	3	]	]	PUNCT
cana-3851	122	4	created	create	VERB
cana-3851	122	5	a	a	DET
cana-3851	122	6	vgg16	vgg16	NOUN
cana-3851	122	7	model	model	NOUN
cana-3851	122	8	that	that	PRON
cana-3851	122	9	trained	train	VERB
cana-3851	122	10	with	with	ADP
cana-3851	122	11	a	a	DET
cana-3851	122	12	precision	precision	NOUN
cana-3851	122	13	of	of	ADP
cana-3851	122	14	99.88	99.88	NUM
cana-3851	122	15	%	%	NOUN
cana-3851	122	16	and	and	CCONJ
cana-3851	122	17	a	a	DET
cana-3851	122	18	testing	testing	NOUN
cana-3851	122	19	accuracy	accuracy	NOUN
cana-3851	122	20	of	of	ADP
cana-3851	122	21	97.33	97.33	NUM
cana-3851	122	22	%	%	NOUN
cana-3851	122	23	using	use	VERB
cana-3851	122	24	a	a	DET
cana-3851	122	25	dataset	dataset	NOUN
cana-3851	122	26	of	of	ADP
cana-3851	122	27	brain	brain	NOUN
cana-3851	122	28	pictures	picture	NOUN
cana-3851	122	29	that	that	PRON
cana-3851	122	30	included	include	VERB
cana-3851	122	31	both	both	CCONJ
cana-3851	122	32	normal	normal	ADJ
cana-3851	122	33	and	and	CCONJ
cana-3851	122	34	tumor	tumor	NOUN
cana-3851	122	35	images	image	NOUN
cana-3851	122	36	.	.	PUNCT
cana-3851	123	1	the	the	DET
cana-3851	123	2	model	model	NOUN
cana-3851	123	3	successfully	successfully	ADV
cana-3851	123	4	identified	identify	VERB
cana-3851	123	5	and	and	CCONJ
cana-3851	123	6	predicted	predict	VERB
cana-3851	123	7	brain	brain	NOUN
cana-3851	123	8	images	image	NOUN
cana-3851	123	9	.	.	PUNCT
cana-3851	124	1	applying	apply	VERB
cana-3851	124	2	layer	layer	NOUN
cana-3851	124	3	-	-	PUNCT
cana-3851	124	4	wise	wise	ADJ
cana-3851	124	5	relevance	relevance	NOUN
cana-3851	124	6	propagation	propagation	NOUN
cana-3851	124	7	(	(	PUNCT
cana-3851	124	8	lrp	lrp	PROPN
cana-3851	124	9	)	)	PUNCT
cana-3851	124	10	helped	help	VERB
cana-3851	124	11	shed	shed	VERB
cana-3851	124	12	light	light	NOUN
cana-3851	124	13	on	on	ADP
cana-3851	124	14	how	how	SCONJ
cana-3851	124	15	the	the	DET
cana-3851	124	16	model	model	NOUN
cana-3851	124	17	arrived	arrive	VERB
cana-3851	124	18	at	at	ADP
cana-3851	124	19	its	its	PRON
cana-3851	124	20	decisions	decision	NOUN
cana-3851	124	21	.	.	PUNCT
cana-3851	125	1	the	the	DET
cana-3851	125	2	combination	combination	NOUN
cana-3851	125	3	of	of	ADP
cana-3851	125	4	the	the	DET
cana-3851	125	5	vgg16	vgg16	NOUN
cana-3851	125	6	model	model	NOUN
cana-3851	125	7	with	with	ADP
cana-3851	125	8	lrp	lrp	PROPN
cana-3851	125	9	offers	offer	VERB
cana-3851	125	10	a	a	DET
cana-3851	125	11	promising	promising	ADJ
cana-3851	125	12	strategy	strategy	NOUN
cana-3851	125	13	for	for	ADP
cana-3851	125	14	the	the	DET
cana-3851	125	15	identification	identification	NOUN
cana-3851	125	16	and	and	CCONJ
cana-3851	125	17	understanding	understanding	NOUN
cana-3851	125	18	of	of	ADP
cana-3851	125	19	brain	brain	NOUN
cana-3851	125	20	tumors	tumor	NOUN
cana-3851	125	21	.	.	PUNCT
cana-3851	126	1	using	use	VERB
cana-3851	126	2	multi	multi	ADJ
cana-3851	126	3	-	-	ADJ
cana-3851	126	4	modal	modal	ADJ
cana-3851	126	5	images	image	NOUN
cana-3851	126	6	,	,	PUNCT
cana-3851	126	7	sajid	sajid	PROPN
cana-3851	126	8	iqbal	iqbal	PROPN
cana-3851	126	9	et	et	PROPN
cana-3851	126	10	al	al	PROPN
cana-3851	126	11	.	.	PUNCT
cana-3851	127	1	[	[	X
cana-3851	127	2	16	16	NUM
cana-3851	127	3	]	]	PUNCT
cana-3851	127	4	demonstrated	demonstrate	VERB
cana-3851	127	5	a	a	DET
cana-3851	127	6	similar	similar	ADJ
cana-3851	127	7	network	network	NOUN
cana-3851	127	8	design	design	NOUN
cana-3851	127	9	for	for	ADP
cana-3851	127	10	segmenting	segment	VERB
cana-3851	127	11	brain	brain	NOUN
cana-3851	127	12	tumors	tumor	NOUN
cana-3851	127	13	.	.	PUNCT
cana-3851	128	1	there	there	PRON
cana-3851	128	2	were	be	VERB
cana-3851	128	3	three	three	NUM
cana-3851	128	4	models	model	NOUN
cana-3851	128	5	offered	offer	VERB
cana-3851	128	6	,	,	PUNCT
cana-3851	128	7	each	each	PRON
cana-3851	128	8	with	with	ADP
cana-3851	128	9	an	an	DET
cana-3851	128	10	escalating	escalate	VERB
cana-3851	128	11	performance	performance	NOUN
cana-3851	128	12	level	level	NOUN
cana-3851	128	13	.	.	PUNCT
cana-3851	129	1	the	the	DET
cana-3851	129	2	findings	finding	NOUN
cana-3851	129	3	show	show	VERB
cana-3851	129	4	that	that	SCONJ
cana-3851	129	5	interpolation	interpolation	NOUN
cana-3851	129	6	methods	method	NOUN
cana-3851	129	7	and	and	CCONJ
cana-3851	129	8	intermediate	intermediate	ADJ
cana-3851	129	9	convolutional	convolutional	ADJ
cana-3851	129	10	maps	map	NOUN
cana-3851	129	11	are	be	AUX
cana-3851	129	12	viable	viable	ADJ
cana-3851	129	13	options	option	NOUN
cana-3851	129	14	with	with	ADP
cana-3851	129	15	good	good	ADJ
cana-3851	129	16	potential	potential	NOUN
cana-3851	129	17	.	.	PUNCT
cana-3851	130	1	the	the	DET
cana-3851	130	2	vast	vast	ADJ
cana-3851	130	3	majority	majority	NOUN
cana-3851	130	4	of	of	ADP
cana-3851	130	5	the	the	DET
cana-3851	130	6	networks	network	NOUN
cana-3851	130	7	published	publish	VERB
cana-3851	130	8	so	so	ADV
cana-3851	130	9	far	far	ADV
cana-3851	130	10	are	be	AUX
cana-3851	130	11	deep	deep	ADJ
cana-3851	130	12	networks	network	NOUN
cana-3851	130	13	,	,	PUNCT
cana-3851	130	14	which	which	PRON
cana-3851	130	15	need	need	VERB
cana-3851	130	16	extensive	extensive	ADJ
cana-3851	130	17	training	training	NOUN
cana-3851	130	18	before	before	SCONJ
cana-3851	130	19	they	they	PRON
cana-3851	130	20	can	can	AUX
cana-3851	130	21	converge	converge	VERB
cana-3851	130	22	.	.	PUNCT
cana-3851	131	1	nevertheless	nevertheless	ADV
cana-3851	131	2	,	,	PUNCT
cana-3851	131	3	the	the	DET
cana-3851	131	4	suggested	suggest	VERB
cana-3851	131	5	network	network	NOUN
cana-3851	131	6	architecture	architecture	NOUN
cana-3851	131	7	is	be	AUX
cana-3851	131	8	compact	compact	ADJ
cana-3851	131	9	,	,	PUNCT
cana-3851	131	10	quick	quick	ADJ
cana-3851	131	11	,	,	PUNCT
cana-3851	131	12	and	and	CCONJ
cana-3851	131	13	requires	require	VERB
cana-3851	131	14	less	less	ADJ
cana-3851	131	15	memory	memory	NOUN
cana-3851	131	16	.	.	PUNCT
cana-3851	132	1	their	their	PRON
cana-3851	132	2	plans	plan	NOUN
cana-3851	132	3	for	for	ADP
cana-3851	132	4	the	the	DET
cana-3851	132	5	future	future	NOUN
cana-3851	132	6	include	include	VERB
cana-3851	132	7	investigating	investigate	VERB
cana-3851	132	8	se	se	PROPN
cana-3851	132	9	blocks	block	NOUN
cana-3851	132	10	'	'	PART
cana-3851	132	11	potential	potential	ADJ
cana-3851	132	12	application	application	NOUN
cana-3851	132	13	at	at	ADP
cana-3851	132	14	various	various	ADJ
cana-3851	132	15	levels	level	NOUN
cana-3851	132	16	.	.	PUNCT
cana-3851	133	1	investigations	investigation	NOUN
cana-3851	133	2	into	into	ADP
cana-3851	133	3	the	the	DET
cana-3851	133	4	relative	relative	ADJ
cana-3851	133	5	merits	merit	NOUN
cana-3851	133	6	of	of	ADP
cana-3851	133	7	different	different	ADJ
cana-3851	133	8	weighting	weighting	NOUN
cana-3851	133	9	strategies	strategy	NOUN
cana-3851	133	10	and	and	CCONJ
cana-3851	133	11	the	the	DET
cana-3851	133	12	potential	potential	ADJ
cana-3851	133	13	benefits	benefit	NOUN
cana-3851	133	14	of	of	ADP
cana-3851	133	15	various	various	ADJ
cana-3851	133	16	combinations	combination	NOUN
cana-3851	133	17	thereof	thereof	ADV
cana-3851	133	18	are	be	AUX
cana-3851	133	19	equally	equally	ADV
cana-3851	133	20	intriguing	intriguing	ADJ
cana-3851	133	21	.	.	PUNCT
cana-3851	134	1	an	an	DET
cana-3851	134	2	mri	mri	NOUN
cana-3851	134	3	model	model	NOUN
cana-3851	134	4	for	for	ADP
cana-3851	134	5	brain	brain	NOUN
cana-3851	134	6	cancers	cancer	NOUN
cana-3851	134	7	was	be	AUX
cana-3851	134	8	proposed	propose	VERB
cana-3851	134	9	by	by	ADP
cana-3851	134	10	abdullah	abdullah	PROPN
cana-3851	134	11	a.	a.	PROPN
cana-3851	134	12	asiri	asiri	PROPN
cana-3851	134	13	et	et	PROPN
cana-3851	134	14	al	al	PROPN
cana-3851	134	15	.	.	PUNCT
cana-3851	135	1	[	[	X
cana-3851	135	2	17	17	NUM
cana-3851	135	3	]	]	PUNCT
cana-3851	135	4	using	use	VERB
cana-3851	135	5	a	a	DET
cana-3851	135	6	convolutional	convolutional	ADJ
cana-3851	135	7	neural	neural	ADJ
cana-3851	135	8	network	network	NOUN
cana-3851	135	9	(	(	PUNCT
cana-3851	135	10	cnn	cnn	PROPN
cana-3851	135	11	)	)	PUNCT
cana-3851	135	12	that	that	PRON
cana-3851	135	13	incorporates	incorporate	VERB
cana-3851	135	14	fine	fine	ADV
cana-3851	135	15	-	-	PUNCT
cana-3851	135	16	tuned	tune	VERB
cana-3851	135	17	resnet50	resnet50	NOUN
cana-3851	135	18	and	and	CCONJ
cana-3851	135	19	u	u	NOUN
cana-3851	135	20	-	-	NOUN
cana-3851	135	21	net	net	NOUN
cana-3851	135	22	.	.	PUNCT
cana-3851	136	1	their	their	PRON
cana-3851	136	2	approach	approach	NOUN
cana-3851	136	3	is	be	AUX
cana-3851	136	4	superior	superior	ADJ
cana-3851	136	5	in	in	ADP
cana-3851	136	6	both	both	DET
cana-3851	136	7	tasks	task	NOUN
cana-3851	136	8	because	because	SCONJ
cana-3851	136	9	it	it	PRON
cana-3851	136	10	combines	combine	VERB
cana-3851	136	11	the	the	DET
cana-3851	136	12	greatest	great	ADJ
cana-3851	136	13	aspects	aspect	NOUN
cana-3851	136	14	of	of	ADP
cana-3851	136	15	two	two	NUM
cana-3851	136	16	different	different	ADJ
cana-3851	136	17	designs	design	NOUN
cana-3851	136	18	.	.	PUNCT
cana-3851	137	1	the	the	DET
cana-3851	137	2	fine	fine	ADV
cana-3851	137	3	-	-	PUNCT
cana-3851	137	4	tuned	tune	VERB
cana-3851	137	5	resnet50	resnet50	NOUN
cana-3851	137	6	configuration	configuration	NOUN
cana-3851	137	7	is	be	AUX
cana-3851	137	8	used	use	VERB
cana-3851	137	9	for	for	ADP
cana-3851	137	10	brain	brain	NOUN
cana-3851	137	11	tumor	tumor	NOUN
cana-3851	137	12	detection	detection	NOUN
cana-3851	137	13	,	,	PUNCT
cana-3851	137	14	which	which	PRON
cana-3851	137	15	comprises	comprise	VERB
cana-3851	137	16	detecting	detect	VERB
cana-3851	137	17	tumors	tumor	NOUN
cana-3851	137	18	in	in	ADP
cana-3851	137	19	mris	mris	PROPN
cana-3851	137	20	.	.	PUNCT
cana-3851	138	1	the	the	DET
cana-3851	138	2	u	u	ADJ
cana-3851	138	3	-	-	ADJ
cana-3851	138	4	net	net	ADJ
cana-3851	138	5	design	design	NOUN
cana-3851	138	6	may	may	AUX
cana-3851	138	7	be	be	AUX
cana-3851	138	8	used	use	VERB
cana-3851	138	9	to	to	ADP
cana-3851	138	10	the	the	DET
cana-3851	138	11	task	task	NOUN
cana-3851	138	12	of	of	ADP
cana-3851	138	13	brain	brain	NOUN
cana-3851	138	14	tumor	tumor	NOUN
cana-3851	138	15	segmentation	segmentation	NOUN
cana-3851	138	16	,	,	PUNCT
cana-3851	138	17	which	which	PRON
cana-3851	138	18	comprises	comprise	VERB
cana-3851	138	19	the	the	DET
cana-3851	138	20	exact	exact	ADJ
cana-3851	138	21	separation	separation	NOUN
cana-3851	138	22	of	of	ADP
cana-3851	138	23	the	the	DET
cana-3851	138	24	tumor	tumor	NOUN
cana-3851	138	25	from	from	ADP
cana-3851	138	26	the	the	DET
cana-3851	138	27	surrounding	surround	VERB
cana-3851	138	28	healthy	healthy	ADJ
cana-3851	138	29	tissue	tissue	NOUN
cana-3851	138	30	.	.	PUNCT
cana-3851	139	1	the	the	DET
cana-3851	139	2	study	study	NOUN
cana-3851	139	3	compared	compare	VERB
cana-3851	139	4	cnn	cnn	PROPN
cana-3851	139	5	with	with	ADP
cana-3851	139	6	fine	fine	ADV
cana-3851	139	7	-	-	PUNCT
cana-3851	139	8	tuned	tune	VERB
cana-3851	139	9	resnet50	resnet50	NOUN
cana-3851	139	10	,	,	PUNCT
cana-3851	139	11	two	two	NUM
cana-3851	139	12	models	model	NOUN
cana-3851	139	13	developed	develop	VERB
cana-3851	139	14	for	for	ADP
cana-3851	139	15	use	use	NOUN
cana-3851	139	16	in	in	ADP
cana-3851	139	17	mri	mri	NOUN
cana-3851	139	18	image	image	NOUN
cana-3851	139	19	classification	classification	NOUN
cana-3851	139	20	and	and	CCONJ
cana-3851	139	21	tumor	tumor	NOUN
cana-3851	139	22	detection	detection	NOUN
cana-3851	139	23	.	.	PUNCT
cana-3851	140	1	statistically	statistically	ADV
cana-3851	140	2	speaking	speak	VERB
cana-3851	140	3	,	,	PUNCT
cana-3851	140	4	for	for	ADP
cana-3851	140	5	both	both	CCONJ
cana-3851	140	6	the	the	DET
cana-3851	140	7	non	non	ADJ
cana-3851	140	8	-	-	ADJ
cana-3851	140	9	tumor	tumor	ADJ
cana-3851	140	10	and	and	CCONJ
cana-3851	140	11	tumor	tumor	NOUN
cana-3851	140	12	classifications	classification	NOUN
cana-3851	140	13	,	,	PUNCT
cana-3851	140	14	the	the	DET
cana-3851	140	15	cnn	cnn	PROPN
cana-3851	140	16	model	model	NOUN
cana-3851	140	17	outperforms	outperform	VERB
cana-3851	140	18	the	the	DET
cana-3851	140	19	fine	fine	ADV
cana-3851	140	20	-	-	PUNCT
cana-3851	140	21	tuned	tune	VERB
cana-3851	140	22	resnet50	resnet50	NOUN
cana-3851	140	23	model	model	NOUN
cana-3851	140	24	.	.	PUNCT
cana-3851	141	1	the	the	DET
cana-3851	141	2	refined	refined	PROPN
cana-3851	141	3	resnet50	resnet50	NOUN
cana-3851	141	4	model	model	NOUN
cana-3851	141	5	obtained	obtain	VERB
cana-3851	141	6	an	an	DET
cana-3851	141	7	accuracy	accuracy	NOUN
cana-3851	141	8	rate	rate	NOUN
cana-3851	141	9	of	of	ADP
cana-3851	141	10	0.94	0.94	NUM
cana-3851	141	11	,	,	PUNCT
cana-3851	141	12	a	a	DET
cana-3851	141	13	recall	recall	NOUN
cana-3851	141	14	of	of	ADP
cana-3851	141	15	0.95	0.95	NUM
cana-3851	141	16	,	,	PUNCT
cana-3851	141	17	an	an	DET
cana-3851	141	18	f1	f1	ADJ
cana-3851	141	19	score	score	NOUN
cana-3851	141	20	of	of	ADP
cana-3851	141	21	0.93	0.93	NUM
cana-3851	141	22	,	,	PUNCT
cana-3851	141	23	and	and	CCONJ
cana-3851	141	24	a	a	DET
cana-3851	141	25	precision	precision	NOUN
cana-3851	141	26	of	of	ADP
cana-3851	141	27	0.98	0.98	NUM
cana-3851	141	28	in	in	ADP
cana-3851	141	29	the	the	DET
cana-3851	141	30	non	non	ADJ
cana-3851	141	31	-	-	ADJ
cana-3851	141	32	tumor	tumor	ADJ
cana-3851	141	33	class	class	NOUN
cana-3851	141	34	.	.	PUNCT
cana-3851	142	1	the	the	DET
cana-3851	142	2	model	model	NOUN
cana-3851	142	3	's	's	PART
cana-3851	142	4	preciseness	preciseness	NOUN
cana-3851	142	5	was	be	AUX
cana-3851	142	6	0.87	0.87	NUM
cana-3851	142	7	,	,	PUNCT
cana-3851	142	8	recall	recall	NOUN
cana-3851	142	9	was	be	AUX
cana-3851	142	10	0.92	0.92	NUM
cana-3851	142	11	,	,	PUNCT
cana-3851	142	12	f1	f1	ADJ
cana-3851	142	13	score	score	NOUN
cana-3851	142	14	was	be	AUX
cana-3851	142	15	0.88	0.88	NUM
cana-3851	142	16	,	,	PUNCT
cana-3851	142	17	and	and	CCONJ
cana-3851	142	18	accuracy	accuracy	NOUN
cana-3851	142	19	was	be	AUX
cana-3851	142	20	0.96	0.96	NUM
cana-3851	142	21	in	in	ADP
cana-3851	142	22	the	the	DET
cana-3851	142	23	tumor	tumor	NOUN
cana-3851	142	24	class	class	NOUN
cana-3851	142	25	.	.	PUNCT
cana-3851	143	1	two	two	NUM
cana-3851	143	2	pipelines	pipeline	NOUN
cana-3851	143	3	were	be	AUX
cana-3851	143	4	developed	develop	VERB
cana-3851	143	5	by	by	ADP
cana-3851	143	6	mostefa	mostefa	PROPN
cana-3851	143	7	ben	ben	PROPN
cana-3851	143	8	naceur	naceur	PROPN
cana-3851	143	9	et	et	PROPN
cana-3851	143	10	al	al	PROPN
cana-3851	143	11	.	.	PUNCT
cana-3851	144	1	[	[	X
cana-3851	144	2	18	18	NUM
cana-3851	144	3	]	]	PUNCT
cana-3851	144	4	to	to	PART
cana-3851	144	5	segment	segment	NOUN
cana-3851	144	6	gbm	gbm	PROPN
cana-3851	144	7	brain	brain	NOUN
cana-3851	144	8	tumors	tumor	NOUN
cana-3851	144	9	using	use	VERB
cana-3851	144	10	learnt	learn	VERB
cana-3851	144	11	feature	feature	NOUN
cana-3851	144	12	maps	map	NOUN
cana-3851	144	13	and	and	CCONJ
cana-3851	144	14	deep	deep	ADJ
cana-3851	144	15	convolutional	convolutional	ADJ
cana-3851	144	16	neural	neural	ADJ
cana-3851	144	17	networks	network	NOUN
cana-3851	144	18	(	(	PUNCT
cana-3851	144	19	dcnns	dcnns	ADJ
cana-3851	144	20	)	)	PUNCT
cana-3851	144	21	.	.	PUNCT
cana-3851	145	1	to	to	PART
cana-3851	145	2	optimize	optimize	VERB
cana-3851	145	3	the	the	DET
cana-3851	145	4	model	model	NOUN
cana-3851	145	5	's	's	PART
cana-3851	145	6	feature	feature	NOUN
cana-3851	145	7	representation	representation	NOUN
cana-3851	145	8	,	,	PUNCT
cana-3851	145	9	the	the	DET
cana-3851	145	10	first	first	ADJ
cana-3851	145	11	pipeline	pipeline	NOUN
cana-3851	145	12	employs	employ	VERB
cana-3851	145	13	up	up	ADV
cana-3851	145	14	-	-	PUNCT
cana-3851	145	15	sampling	sample	VERB
cana-3851	145	16	filters	filter	NOUN
cana-3851	145	17	and	and	CCONJ
cana-3851	145	18	skip	skip	ADJ
cana-3851	145	19	connections	connection	NOUN
cana-3851	145	20	.	.	PUNCT
cana-3851	146	1	the	the	DET
cana-3851	146	2	second	second	ADJ
cana-3851	146	3	pipeline	pipeline	NOUN
cana-3851	146	4	improves	improve	VERB
cana-3851	146	5	tumor	tumor	NOUN
cana-3851	146	6	area	area	NOUN
cana-3851	146	7	localization	localization	NOUN
cana-3851	146	8	by	by	ADP
cana-3851	146	9	combining	combine	VERB
cana-3851	146	10	low	low	ADJ
cana-3851	146	11	-	-	PUNCT
cana-3851	146	12	level	level	NOUN
cana-3851	146	13	and	and	CCONJ
cana-3851	146	14	high	high	ADJ
cana-3851	146	15	-	-	PUNCT
cana-3851	146	16	level	level	NOUN
cana-3851	146	17	features	feature	NOUN
cana-3851	146	18	via	via	ADP
cana-3851	146	19	lengthy	lengthy	ADJ
cana-3851	146	20	skip	skip	ADJ
cana-3851	146	21	links	link	NOUN
cana-3851	146	22	that	that	PRON
cana-3851	146	23	promote	promote	VERB
cana-3851	146	24	feature	feature	NOUN
cana-3851	146	25	reuse	reuse	NOUN
cana-3851	146	26	.	.	PUNCT
cana-3851	147	1	the	the	DET
cana-3851	147	2	scientists	scientist	NOUN
cana-3851	147	3	trained	train	VERB
cana-3851	147	4	two	two	NUM
cana-3851	147	5	more	more	ADJ
cana-3851	147	6	machine	machine	NOUN
cana-3851	147	7	learning	learn	VERB
cana-3851	147	8	algorithms	algorithm	NOUN
cana-3851	147	9	—	—	PUNCT
cana-3851	147	10	logistic	logistic	ADJ
cana-3851	147	11	regression	regression	NOUN
cana-3851	147	12	and	and	CCONJ
cana-3851	147	13	random	random	ADJ
cana-3851	147	14	forest	forest	NOUN
cana-3851	147	15	—	—	PUNCT
cana-3851	147	16	and	and	CCONJ
cana-3851	147	17	extracted	extract	VERB
cana-3851	147	18	the	the	DET
cana-3851	147	19	feature	feature	NOUN
cana-3851	147	20	maps	map	NOUN
cana-3851	147	21	to	to	PART
cana-3851	147	22	solve	solve	VERB
cana-3851	147	23	the	the	DET
cana-3851	147	24	issue	issue	NOUN
cana-3851	147	25	of	of	ADP
cana-3851	147	26	false	false	ADJ
cana-3851	147	27	positive	positive	ADJ
cana-3851	147	28	and	and	CCONJ
cana-3851	147	29	false	false	ADJ
cana-3851	147	30	negative	negative	ADJ
cana-3851	147	31	areas	area	NOUN
cana-3851	147	32	.	.	PUNCT
cana-3851	148	1	a	a	DET
cana-3851	148	2	technique	technique	NOUN
cana-3851	148	3	for	for	ADP
cana-3851	148	4	classifying	classify	VERB
cana-3851	148	5	data	datum	NOUN
cana-3851	148	6	and	and	CCONJ
cana-3851	148	7	detecting	detect	VERB
cana-3851	148	8	tumor	tumor	NOUN
cana-3851	148	9	locations	location	NOUN
cana-3851	148	10	using	use	VERB
cana-3851	148	11	deep	deep	ADJ
cana-3851	148	12	residual	residual	ADJ
cana-3851	148	13	networks	network	NOUN
cana-3851	148	14	(	(	PUNCT
cana-3851	148	15	resnet	resnet	NOUN
cana-3851	148	16	)	)	PUNCT
cana-3851	148	17	was	be	AUX
cana-3851	148	18	suggested	suggest	VERB
cana-3851	148	19	in	in	ADP
cana-3851	148	20	a	a	DET
cana-3851	148	21	publication	publication	NOUN
cana-3851	148	22	by	by	ADP
cana-3851	148	23	madona	madona	PROPN
cana-3851	148	24	b.	b.	PROPN
cana-3851	148	25	sahaai	sahaai	PROPN
cana-3851	148	26	et	et	PROPN
cana-3851	148	27	al	al	PROPN
cana-3851	148	28	.	.	PUNCT
cana-3851	149	1	[	[	X
cana-3851	149	2	19	19	NUM
cana-3851	149	3	]	]	PUNCT
cana-3851	149	4	.	.	PUNCT
cana-3851	150	1	in	in	ADP
cana-3851	150	2	the	the	DET
cana-3851	150	3	field	field	NOUN
cana-3851	150	4	of	of	ADP
cana-3851	150	5	restorative	restorative	ADJ
cana-3851	150	6	dentistry	dentistry	NOUN
cana-3851	150	7	,	,	PUNCT
cana-3851	150	8	their	their	PRON
cana-3851	150	9	model	model	NOUN
cana-3851	150	10	is	be	AUX
cana-3851	150	11	useful	useful	ADJ
cana-3851	150	12	for	for	ADP
cana-3851	150	13	more	more	ADV
cana-3851	150	14	accurate	accurate	ADJ
cana-3851	150	15	,	,	PUNCT
cana-3851	150	16	detailed	detailed	ADJ
cana-3851	150	17	,	,	PUNCT
cana-3851	150	18	precise	precise	ADJ
cana-3851	150	19	,	,	PUNCT
cana-3851	150	20	and	and	CCONJ
cana-3851	150	21	analytical	analytical	ADJ
cana-3851	150	22	prediction	prediction	NOUN
cana-3851	150	23	of	of	ADP
cana-3851	150	24	a	a	DET
cana-3851	150	25	patient	patient	NOUN
cana-3851	150	26	's	's	PART
cana-3851	150	27	brian	brian	PROPN
cana-3851	150	28	tumor	tumor	NOUN
cana-3851	150	29	.	.	PUNCT
cana-3851	151	1	across	across	ADP
cana-3851	151	2	several	several	ADJ
cana-3851	151	3	types	type	NOUN
cana-3851	151	4	of	of	ADP
cana-3851	151	5	brain	brain	NOUN
cana-3851	151	6	tumor	tumor	NOUN
cana-3851	151	7	datasets	dataset	NOUN
cana-3851	151	8	,	,	PUNCT
cana-3851	151	9	their	their	PRON
cana-3851	151	10	model	model	NOUN
cana-3851	151	11	achieves	achieve	VERB
cana-3851	151	12	a	a	DET
cana-3851	151	13	validation	validation	NOUN
cana-3851	151	14	accuracy	accuracy	NOUN
cana-3851	151	15	of	of	ADP
cana-3851	151	16	95.3	95.3	NUM
cana-3851	151	17	%	%	NOUN
cana-3851	151	18	.	.	PUNCT
cana-3851	152	1	in	in	ADP
cana-3851	152	2	their	their	PRON
cana-3851	152	3	study	study	NOUN
cana-3851	152	4	,	,	PUNCT
cana-3851	152	5	they	they	PRON
cana-3851	152	6	compared	compare	VERB
cana-3851	152	7	the	the	DET
cana-3851	152	8	results	result	NOUN
cana-3851	152	9	of	of	ADP
cana-3851	152	10	multi	multi	ADJ
cana-3851	152	11	-	-	ADJ
cana-3851	152	12	class	class	ADJ
cana-3851	152	13	brain	brain	NOUN
cana-3851	152	14	tumor	tumor	NOUN
cana-3851	152	15	classification	classification	NOUN
cana-3851	152	16	using	use	VERB
cana-3851	152	17	transfer	transfer	NOUN
cana-3851	152	18	learning	learning	NOUN
cana-3851	152	19	with	with	ADP
cana-3851	152	20	a	a	DET
cana-3851	152	21	pre	pre	ADJ
cana-3851	152	22	-	-	ADJ
cana-3851	152	23	trained	train	VERB
cana-3851	152	24	resnet50	resnet50	NOUN
cana-3851	152	25	model	model	NOUN
cana-3851	152	26	that	that	PRON
cana-3851	152	27	used	use	VERB
cana-3851	152	28	cnn	cnn	PROPN
cana-3851	152	29	architecture	architecture	NOUN
cana-3851	152	30	.	.	PUNCT
cana-3851	153	1	in	in	ADP
cana-3851	153	2	the	the	DET
cana-3851	153	3	absence	absence	NOUN
cana-3851	153	4	of	of	ADP
cana-3851	153	5	the	the	DET
cana-3851	153	6	pretrained	pretraine	VERB
cana-3851	153	7	pytorch	pytorch	NOUN
cana-3851	153	8	model	model	NOUN
cana-3851	153	9	,	,	PUNCT
cana-3851	153	10	the	the	DET
cana-3851	153	11	training	training	NOUN
cana-3851	153	12	accuracy	accuracy	NOUN
cana-3851	153	13	stands	stand	VERB
cana-3851	153	14	at	at	ADP
cana-3851	153	15	93.5	93.5	NUM
cana-3851	153	16	%	%	NOUN
cana-3851	153	17	and	and	CCONJ
cana-3851	153	18	the	the	DET
cana-3851	153	19	validation	validation	NOUN
cana-3851	153	20	accuracy	accuracy	NOUN
cana-3851	153	21	at	at	ADP
cana-3851	153	22	90	90	NUM
cana-3851	153	23	%	%	NOUN
cana-3851	153	24	.	.	PUNCT
cana-3851	154	1	communications	communication	NOUN
cana-3851	154	2	on	on	ADP
cana-3851	154	3	applied	apply	VERB
cana-3851	154	4	nonlinear	nonlinear	ADJ
cana-3851	154	5	analysis	analysis	NOUN
cana-3851	154	6	issn	issn	NOUN
cana-3851	154	7	:	:	PUNCT
cana-3851	154	8	1074	1074	NUM
cana-3851	154	9	-	-	PUNCT
cana-3851	154	10	133x	133x	NUM
cana-3851	154	11	vol	vol	NOUN
cana-3851	154	12	32	32	NUM
cana-3851	154	13	no	no	NOUN
cana-3851	154	14	.	.	PUNCT
cana-3851	155	1	9s	9s	NUM
cana-3851	155	2	(	(	PUNCT
cana-3851	155	3	2025	2025	NUM
cana-3851	155	4	)	)	PUNCT
cana-3851	155	5	220	220	NUM
cana-3851	155	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-3851	155	7	mostefa	mostefa	PROPN
cana-3851	155	8	ben	ben	PROPN
cana-3851	155	9	naceur	naceur	PROPN
cana-3851	155	10	et	et	PROPN
cana-3851	155	11	al	al	PROPN
cana-3851	155	12	.	.	PUNCT
cana-3851	156	1	[	[	X
cana-3851	156	2	18	18	NUM
cana-3851	156	3	]	]	PUNCT
cana-3851	156	4	used	use	VERB
cana-3851	156	5	trained	train	VERB
cana-3851	156	6	feature	feature	NOUN
cana-3851	156	7	maps	map	NOUN
cana-3851	156	8	and	and	CCONJ
cana-3851	156	9	deep	deep	ADJ
cana-3851	156	10	convolutional	convolutional	ADJ
cana-3851	156	11	neural	neural	ADJ
cana-3851	156	12	networks	network	NOUN
cana-3851	156	13	(	(	PUNCT
cana-3851	156	14	dcnns	dcnns	ADJ
cana-3851	156	15	)	)	PUNCT
cana-3851	156	16	to	to	PART
cana-3851	156	17	build	build	VERB
cana-3851	156	18	two	two	NUM
cana-3851	156	19	pipelines	pipeline	NOUN
cana-3851	156	20	for	for	ADP
cana-3851	156	21	gbm	gbm	PROPN
cana-3851	156	22	brain	brain	PROPN
cana-3851	156	23	tumor	tumor	PROPN
cana-3851	156	24	segmentation	segmentation	NOUN
cana-3851	156	25	.	.	PUNCT
cana-3851	157	1	to	to	PART
cana-3851	157	2	make	make	VERB
cana-3851	157	3	the	the	DET
cana-3851	157	4	most	most	ADJ
cana-3851	157	5	of	of	ADP
cana-3851	157	6	the	the	DET
cana-3851	157	7	features	feature	NOUN
cana-3851	157	8	represented	represent	VERB
cana-3851	157	9	in	in	ADP
cana-3851	157	10	the	the	DET
cana-3851	157	11	model	model	NOUN
cana-3851	157	12	,	,	PUNCT
cana-3851	157	13	the	the	DET
cana-3851	157	14	first	first	ADJ
cana-3851	157	15	pipeline	pipeline	NOUN
cana-3851	157	16	employs	employ	VERB
cana-3851	157	17	up	up	ADV
cana-3851	157	18	-	-	PUNCT
cana-3851	157	19	sampling	sample	VERB
cana-3851	157	20	filters	filter	NOUN
cana-3851	157	21	and	and	CCONJ
cana-3851	157	22	skip	skip	ADJ
cana-3851	157	23	connections	connection	NOUN
cana-3851	157	24	.	.	PUNCT
cana-3851	158	1	to	to	PART
cana-3851	158	2	improve	improve	VERB
cana-3851	158	3	tumor	tumor	NOUN
cana-3851	158	4	area	area	NOUN
cana-3851	158	5	localization	localization	NOUN
cana-3851	158	6	,	,	PUNCT
cana-3851	158	7	the	the	DET
cana-3851	158	8	second	second	ADJ
cana-3851	158	9	pipeline	pipeline	NOUN
cana-3851	158	10	employs	employ	VERB
cana-3851	158	11	lengthy	lengthy	ADJ
cana-3851	158	12	skip	skip	ADJ
cana-3851	158	13	connections	connection	NOUN
cana-3851	158	14	to	to	PART
cana-3851	158	15	promote	promote	VERB
cana-3851	158	16	feature	feature	NOUN
cana-3851	158	17	reuse	reuse	NOUN
cana-3851	158	18	,	,	PUNCT
cana-3851	158	19	which	which	PRON
cana-3851	158	20	aids	aid	VERB
cana-3851	158	21	the	the	DET
cana-3851	158	22	model	model	NOUN
cana-3851	158	23	in	in	ADP
cana-3851	158	24	integrating	integrate	VERB
cana-3851	158	25	lowand	lowand	ADJ
cana-3851	158	26	high	high	ADJ
cana-3851	158	27	-	-	PUNCT
cana-3851	158	28	level	level	NOUN
cana-3851	158	29	information	information	NOUN
cana-3851	158	30	.	.	PUNCT
cana-3851	159	1	after	after	ADP
cana-3851	159	2	obtaining	obtain	VERB
cana-3851	159	3	the	the	DET
cana-3851	159	4	feature	feature	NOUN
cana-3851	159	5	maps	map	NOUN
cana-3851	159	6	,	,	PUNCT
cana-3851	159	7	the	the	DET
cana-3851	159	8	writers	writer	NOUN
cana-3851	159	9	trained	train	VERB
cana-3851	159	10	two	two	NUM
cana-3851	159	11	further	furth	ADJ
cana-3851	159	12	ml	ml	NOUN
cana-3851	159	13	algorithms	algorithm	NOUN
cana-3851	159	14	—	—	PUNCT
cana-3851	159	15	logistic	logistic	ADJ
cana-3851	159	16	regression	regression	NOUN
cana-3851	159	17	and	and	CCONJ
cana-3851	159	18	random	random	ADJ
cana-3851	159	19	forest	forest	NOUN
cana-3851	159	20	—	—	PUNCT
cana-3851	159	21	to	to	PART
cana-3851	159	22	deal	deal	VERB
cana-3851	159	23	with	with	ADP
cana-3851	159	24	the	the	DET
cana-3851	159	25	issue	issue	NOUN
cana-3851	159	26	of	of	ADP
cana-3851	159	27	false	false	ADJ
cana-3851	159	28	positive	positive	ADJ
cana-3851	159	29	and	and	CCONJ
cana-3851	159	30	false	false	ADJ
cana-3851	159	31	negative	negative	ADJ
cana-3851	159	32	areas	area	NOUN
cana-3851	159	33	.	.	PUNCT
cana-3851	160	1	summary	summary	NOUN
cana-3851	160	2	:	:	PUNCT
cana-3851	160	3	•	•	ADP
cana-3851	160	4	a	a	DET
cana-3851	160	5	brain	brain	NOUN
cana-3851	160	6	tumor	tumor	NOUN
cana-3851	160	7	develops	develop	VERB
cana-3851	160	8	when	when	SCONJ
cana-3851	160	9	an	an	DET
cana-3851	160	10	aberrant	aberrant	ADJ
cana-3851	160	11	cluster	cluster	NOUN
cana-3851	160	12	of	of	ADP
cana-3851	160	13	cells	cell	NOUN
cana-3851	160	14	grows	grow	VERB
cana-3851	160	15	in	in	ADP
cana-3851	160	16	the	the	DET
cana-3851	160	17	human	human	ADJ
cana-3851	160	18	brain	brain	NOUN
cana-3851	160	19	.	.	PUNCT
cana-3851	161	1	brain	brain	NOUN
cana-3851	161	2	and	and	CCONJ
cana-3851	161	3	spinal	spinal	ADJ
cana-3851	161	4	cord	cord	NOUN
cana-3851	161	5	tumors	tumor	NOUN
cana-3851	161	6	are	be	AUX
cana-3851	161	7	known	know	VERB
cana-3851	161	8	as	as	ADP
cana-3851	161	9	gliomas	glioma	NOUN
cana-3851	161	10	,	,	PUNCT
cana-3851	161	11	whereas	whereas	SCONJ
cana-3851	161	12	meningiomas	meningioma	NOUN
cana-3851	161	13	are	be	AUX
cana-3851	161	14	tumors	tumor	NOUN
cana-3851	161	15	that	that	PRON
cana-3851	161	16	form	form	VERB
cana-3851	161	17	in	in	ADP
cana-3851	161	18	the	the	DET
cana-3851	161	19	meninges	meninge	NOUN
cana-3851	161	20	.	.	PUNCT
cana-3851	162	1	when	when	SCONJ
cana-3851	162	2	cells	cell	NOUN
cana-3851	162	3	inside	inside	ADP
cana-3851	162	4	the	the	DET
cana-3851	162	5	pituitary	pituitary	ADJ
cana-3851	162	6	gland	gland	NOUN
cana-3851	162	7	multiply	multiply	NOUN
cana-3851	162	8	abnormally	abnormally	ADV
cana-3851	162	9	,	,	PUNCT
cana-3851	162	10	a	a	DET
cana-3851	162	11	tumor	tumor	NOUN
cana-3851	162	12	forms	form	NOUN
cana-3851	162	13	.	.	PUNCT
cana-3851	163	1	•	•	NUM
cana-3851	163	2	when	when	SCONJ
cana-3851	163	3	diagnosing	diagnose	VERB
cana-3851	163	4	brain	brain	NOUN
cana-3851	163	5	tumors	tumor	NOUN
cana-3851	163	6	,	,	PUNCT
cana-3851	163	7	radiologists	radiologist	NOUN
cana-3851	163	8	often	often	ADV
cana-3851	163	9	employ	employ	VERB
cana-3851	163	10	magnetic	magnetic	ADJ
cana-3851	163	11	resonance	resonance	NOUN
cana-3851	163	12	imaging	imaging	NOUN
cana-3851	163	13	(	(	PUNCT
cana-3851	163	14	mri	mri	NOUN
cana-3851	163	15	)	)	PUNCT
cana-3851	163	16	.	.	PUNCT
cana-3851	164	1	•	•	NUM
cana-3851	164	2	a	a	DET
cana-3851	164	3	branch	branch	NOUN
cana-3851	164	4	of	of	ADP
cana-3851	164	5	ml	ml	ADV
cana-3851	164	6	known	know	VERB
cana-3851	164	7	as	as	ADP
cana-3851	164	8	deep	deep	ADJ
cana-3851	164	9	learning	learning	NOUN
cana-3851	164	10	(	(	PUNCT
cana-3851	164	11	dl	dl	INTJ
cana-3851	164	12	)	)	PUNCT
cana-3851	164	13	has	have	AUX
cana-3851	164	14	shown	show	VERB
cana-3851	164	15	impressive	impressive	ADJ
cana-3851	164	16	results	result	NOUN
cana-3851	164	17	in	in	ADP
cana-3851	164	18	several	several	ADJ
cana-3851	164	19	fields	field	NOUN
cana-3851	164	20	,	,	PUNCT
cana-3851	164	21	including	include	VERB
cana-3851	164	22	image	image	NOUN
cana-3851	164	23	analysis	analysis	NOUN
cana-3851	164	24	and	and	CCONJ
cana-3851	164	25	recognition	recognition	NOUN
cana-3851	164	26	.	.	PUNCT
cana-3851	165	1	its	its	PRON
cana-3851	165	2	revolutionary	revolutionary	ADJ
cana-3851	165	3	capacity	capacity	NOUN
cana-3851	165	4	to	to	PART
cana-3851	165	5	automate	automate	VERB
cana-3851	165	6	complicated	complicated	ADJ
cana-3851	165	7	operations	operation	NOUN
cana-3851	165	8	and	and	CCONJ
cana-3851	165	9	drastically	drastically	ADV
cana-3851	165	10	cut	cut	VERB
cana-3851	165	11	human	human	ADJ
cana-3851	165	12	effort	effort	NOUN
cana-3851	165	13	has	have	AUX
cana-3851	165	14	led	lead	VERB
cana-3851	165	15	to	to	ADP
cana-3851	165	16	its	its	PRON
cana-3851	165	17	widespread	widespread	ADJ
cana-3851	165	18	adoption	adoption	NOUN
cana-3851	165	19	and	and	CCONJ
cana-3851	165	20	changed	change	VERB
cana-3851	165	21	many	many	ADJ
cana-3851	165	22	industries	industry	NOUN
cana-3851	165	23	,	,	PUNCT
cana-3851	165	24	including	include	VERB
cana-3851	165	25	healthcare	healthcare	NOUN
cana-3851	165	26	.	.	PUNCT
cana-3851	166	1	deep	deep	ADJ
cana-3851	166	2	learning	learn	VERB
cana-3851	166	3	algorithms	algorithm	NOUN
cana-3851	166	4	have	have	AUX
cana-3851	166	5	shown	show	VERB
cana-3851	166	6	impressive	impressive	ADJ
cana-3851	166	7	accuracy	accuracy	NOUN
cana-3851	166	8	in	in	ADP
cana-3851	166	9	mribased	mribased	ADJ
cana-3851	166	10	brain	brain	NOUN
cana-3851	166	11	tumor	tumor	NOUN
cana-3851	166	12	identification	identification	NOUN
cana-3851	166	13	,	,	PUNCT
cana-3851	166	14	which	which	PRON
cana-3851	166	15	may	may	AUX
cana-3851	166	16	aid	aid	VERB
cana-3851	166	17	doctors	doctor	NOUN
cana-3851	166	18	in	in	ADP
cana-3851	166	19	making	make	VERB
cana-3851	166	20	well	well	ADV
cana-3851	166	21	-	-	PUNCT
cana-3851	166	22	informed	inform	VERB
cana-3851	166	23	judgments	judgment	NOUN
cana-3851	166	24	.	.	PUNCT
cana-3851	167	1	iii.proposed	iii.propose	VERB
cana-3851	167	2	model	model	NOUN
cana-3851	167	3	when	when	SCONJ
cana-3851	167	4	it	it	PRON
cana-3851	167	5	comes	come	VERB
cana-3851	167	6	to	to	ADP
cana-3851	167	7	global	global	ADJ
cana-3851	167	8	mortality	mortality	NOUN
cana-3851	167	9	tolls	toll	NOUN
cana-3851	167	10	,	,	PUNCT
cana-3851	167	11	cancer	cancer	NOUN
cana-3851	167	12	is	be	AUX
cana-3851	167	13	second	second	ADJ
cana-3851	167	14	only	only	ADV
cana-3851	167	15	to	to	ADP
cana-3851	167	16	cardiovascular	cardiovascular	ADJ
cana-3851	167	17	diseases	disease	NOUN
cana-3851	167	18	.	.	PUNCT
cana-3851	168	1	brain	brain	NOUN
cana-3851	168	2	tumors	tumor	NOUN
cana-3851	168	3	are	be	AUX
cana-3851	168	4	very	very	ADV
cana-3851	168	5	dangerous	dangerous	ADJ
cana-3851	168	6	forms	form	NOUN
cana-3851	168	7	of	of	ADP
cana-3851	168	8	cancer	cancer	NOUN
cana-3851	168	9	due	due	ADP
cana-3851	168	10	to	to	ADP
cana-3851	168	11	their	their	PRON
cana-3851	168	12	aggressiveness	aggressiveness	NOUN
cana-3851	168	13	,	,	PUNCT
cana-3851	168	14	diversity	diversity	NOUN
cana-3851	168	15	,	,	PUNCT
cana-3851	168	16	and	and	CCONJ
cana-3851	168	17	poor	poor	ADJ
cana-3851	168	18	prognosis	prognosis	NOUN
cana-3851	168	19	.	.	PUNCT
cana-3851	169	1	some	some	PRON
cana-3851	169	2	of	of	ADP
cana-3851	169	3	the	the	DET
cana-3851	169	4	distinguishing	distinguish	VERB
cana-3851	169	5	features	feature	NOUN
cana-3851	169	6	that	that	PRON
cana-3851	169	7	cause	cause	VERB
cana-3851	169	8	a	a	DET
cana-3851	169	9	brain	brain	NOUN
cana-3851	169	10	tumor	tumor	NOUN
cana-3851	169	11	to	to	PART
cana-3851	169	12	be	be	AUX
cana-3851	169	13	named	name	VERB
cana-3851	169	14	include	include	VERB
cana-3851	169	15	its	its	PRON
cana-3851	169	16	location	location	NOUN
cana-3851	169	17	,	,	PUNCT
cana-3851	169	18	texture	texture	NOUN
cana-3851	169	19	,	,	PUNCT
cana-3851	169	20	shape	shape	NOUN
cana-3851	169	21	,	,	PUNCT
cana-3851	169	22	and	and	CCONJ
cana-3851	169	23	aggressiveness	aggressiveness	NOUN
cana-3851	169	24	[	[	X
cana-3851	169	25	2	2	NUM
cana-3851	169	26	]	]	PUNCT
cana-3851	169	27	.	.	PUNCT
cana-3851	170	1	among	among	ADP
cana-3851	170	2	brain	brain	NOUN
cana-3851	170	3	malignancies	malignancy	NOUN
cana-3851	170	4	,	,	PUNCT
cana-3851	170	5	glioma	glioma	NOUN
cana-3851	170	6	is	be	AUX
cana-3851	170	7	the	the	DET
cana-3851	170	8	most	most	ADV
cana-3851	170	9	common	common	ADJ
cana-3851	170	10	.	.	PUNCT
cana-3851	171	1	the	the	DET
cana-3851	171	2	location	location	NOUN
cana-3851	171	3	and	and	CCONJ
cana-3851	171	4	subtype	subtype	NOUN
cana-3851	171	5	of	of	ADP
cana-3851	171	6	a	a	DET
cana-3851	171	7	patient	patient	NOUN
cana-3851	171	8	's	's	PART
cana-3851	171	9	glioma	glioma	NOUN
cana-3851	171	10	determine	determine	VERB
cana-3851	171	11	their	their	PRON
cana-3851	171	12	symptoms	symptom	NOUN
cana-3851	171	13	and	and	CCONJ
cana-3851	171	14	prognosis	prognosis	NOUN
cana-3851	171	15	[	[	X
cana-3851	171	16	21	21	NUM
cana-3851	171	17	]	]	PUNCT
cana-3851	171	18	.	.	PUNCT
cana-3851	172	1	several	several	ADJ
cana-3851	172	2	approaches	approach	NOUN
cana-3851	172	3	to	to	PART
cana-3851	172	4	brain	brain	NOUN
cana-3851	172	5	tumor	tumor	NOUN
cana-3851	172	6	segmentation	segmentation	NOUN
cana-3851	172	7	make	make	VERB
cana-3851	172	8	use	use	NOUN
cana-3851	172	9	of	of	ADP
cana-3851	172	10	the	the	DET
cana-3851	172	11	underlying	underlie	VERB
cana-3851	172	12	data	datum	NOUN
cana-3851	172	13	to	to	PART
cana-3851	172	14	construct	construct	VERB
cana-3851	172	15	a	a	DET
cana-3851	172	16	probabilistic	probabilistic	ADJ
cana-3851	172	17	model	model	NOUN
cana-3851	172	18	,	,	PUNCT
cana-3851	172	19	either	either	CCONJ
cana-3851	172	20	parametric	parametric	ADJ
cana-3851	172	21	or	or	CCONJ
cana-3851	172	22	non	non	ADJ
cana-3851	172	23	-	-	ADJ
cana-3851	172	24	parametric	parametric	ADJ
cana-3851	172	25	.	.	PUNCT
cana-3851	173	1	a	a	DET
cana-3851	173	2	previous	previous	ADJ
cana-3851	173	3	model	model	NOUN
cana-3851	173	4	and	and	CCONJ
cana-3851	173	5	a	a	DET
cana-3851	173	6	probability	probability	NOUN
cana-3851	173	7	function	function	NOUN
cana-3851	173	8	that	that	PRON
cana-3851	173	9	match	match	VERB
cana-3851	173	10	the	the	DET
cana-3851	173	11	data	datum	NOUN
cana-3851	173	12	are	be	AUX
cana-3851	173	13	common	common	ADJ
cana-3851	173	14	components	component	NOUN
cana-3851	173	15	of	of	ADP
cana-3851	173	16	such	such	ADJ
cana-3851	173	17	models	model	NOUN
cana-3851	173	18	.	.	PUNCT
cana-3851	174	1	because	because	SCONJ
cana-3851	174	2	they	they	PRON
cana-3851	174	3	are	be	AUX
cana-3851	174	4	aberrant	aberrant	ADJ
cana-3851	174	5	,	,	PUNCT
cana-3851	174	6	tumors	tumor	NOUN
cana-3851	174	7	may	may	AUX
cana-3851	174	8	be	be	AUX
cana-3851	174	9	segregated	segregate	VERB
cana-3851	174	10	as	as	ADP
cana-3851	174	11	distinct	distinct	ADJ
cana-3851	174	12	from	from	ADP
cana-3851	174	13	normal	normal	ADJ
cana-3851	174	14	tissue	tissue	NOUN
cana-3851	174	15	and	and	CCONJ
cana-3851	174	16	subjected	subject	VERB
cana-3851	174	17	to	to	ADP
cana-3851	174	18	constraints	constraint	NOUN
cana-3851	174	19	on	on	ADP
cana-3851	174	20	form	form	NOUN
cana-3851	174	21	and	and	CCONJ
cana-3851	174	22	connection	connection	NOUN
cana-3851	175	1	[	[	X
cana-3851	175	2	22].when	22].when	ADV
cana-3851	175	3	it	it	PRON
cana-3851	175	4	comes	come	VERB
cana-3851	175	5	to	to	ADP
cana-3851	175	6	segmenting	segment	VERB
cana-3851	175	7	brain	brain	NOUN
cana-3851	175	8	tumors	tumor	NOUN
cana-3851	175	9	in	in	ADP
cana-3851	175	10	mri	mri	NOUN
cana-3851	175	11	images	image	NOUN
cana-3851	175	12	,	,	PUNCT
cana-3851	175	13	we	we	PRON
cana-3851	175	14	provide	provide	VERB
cana-3851	175	15	a	a	DET
cana-3851	175	16	hybrid	hybrid	ADJ
cana-3851	175	17	model	model	NOUN
cana-3851	175	18	that	that	PRON
cana-3851	175	19	combines	combine	VERB
cana-3851	175	20	vgg16	vgg16	NOUN
cana-3851	175	21	with	with	ADP
cana-3851	175	22	resnet50	resnet50	NOUN
cana-3851	175	23	in	in	ADP
cana-3851	175	24	this	this	DET
cana-3851	175	25	study	study	NOUN
cana-3851	175	26	.	.	PUNCT
cana-3851	176	1	in	in	ADP
cana-3851	176	2	addition	addition	NOUN
cana-3851	176	3	,	,	PUNCT
cana-3851	176	4	we	we	PRON
cana-3851	176	5	segmented	segment	VERB
cana-3851	176	6	brain	brain	NOUN
cana-3851	176	7	tumors	tumor	NOUN
cana-3851	176	8	by	by	ADP
cana-3851	176	9	using	use	VERB
cana-3851	176	10	data	datum	NOUN
cana-3851	176	11	preprocessing	preprocessing	NOUN
cana-3851	176	12	and	and	CCONJ
cana-3851	176	13	data	datum	NOUN
cana-3851	176	14	augmentation	augmentation	NOUN
cana-3851	176	15	.	.	PUNCT
cana-3851	177	1	communications	communication	NOUN
cana-3851	177	2	on	on	ADP
cana-3851	177	3	applied	apply	VERB
cana-3851	177	4	nonlinear	nonlinear	ADJ
cana-3851	177	5	analysis	analysis	NOUN
cana-3851	177	6	issn	issn	NOUN
cana-3851	177	7	:	:	PUNCT
cana-3851	177	8	1074	1074	NUM
cana-3851	177	9	-	-	PUNCT
cana-3851	177	10	133x	133x	NUM
cana-3851	177	11	vol	vol	NOUN
cana-3851	177	12	32	32	NUM
cana-3851	177	13	no	no	NOUN
cana-3851	177	14	.	.	PUNCT
cana-3851	178	1	9s	9s	NUM
cana-3851	178	2	(	(	PUNCT
cana-3851	178	3	2025	2025	NUM
cana-3851	178	4	)	)	PUNCT
cana-3851	178	5	221	221	NUM
cana-3851	178	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-3851	178	7	figure1	figure1	X
cana-3851	178	8	.	.	PUNCT
cana-3851	179	1	block	block	NOUN
cana-3851	179	2	diagram	diagram	PROPN
cana-3851	179	3	of	of	ADP
cana-3851	179	4	vgg16+resnet50	vgg16+resnet50	PROPN
cana-3851	179	5	model	model	PROPN
cana-3851	179	6	i.	i.	PROPN
cana-3851	179	7	dataset	dataset	PROPN
cana-3851	179	8	description	description	NOUN
cana-3851	179	9	.	.	PUNCT
cana-3851	180	1	we	we	PRON
cana-3851	180	2	have	have	AUX
cana-3851	180	3	limited	limit	VERB
cana-3851	180	4	our	our	PRON
cana-3851	180	5	use	use	NOUN
cana-3851	180	6	to	to	PART
cana-3851	180	7	mri	mri	VERB
cana-3851	180	8	pictures	picture	NOUN
cana-3851	180	9	that	that	PRON
cana-3851	180	10	have	have	AUX
cana-3851	180	11	been	be	AUX
cana-3851	180	12	identified	identify	VERB
cana-3851	180	13	using	use	VERB
cana-3851	180	14	the	the	DET
cana-3851	180	15	recommended	recommend	VERB
cana-3851	180	16	approach	approach	NOUN
cana-3851	180	17	in	in	ADP
cana-3851	180	18	this	this	DET
cana-3851	180	19	work	work	NOUN
cana-3851	180	20	.	.	PUNCT
cana-3851	181	1	the	the	DET
cana-3851	181	2	kaggle	kaggle	ADJ
cana-3851	181	3	dataset	dataset	NOUN
cana-3851	181	4	has	have	VERB
cana-3851	181	5	253	253	NUM
cana-3851	181	6	images	image	NOUN
cana-3851	181	7	from	from	ADP
cana-3851	181	8	different	different	ADJ
cana-3851	181	9	imaging	imaging	NOUN
cana-3851	181	10	modalities	modality	NOUN
cana-3851	181	11	.	.	PUNCT
cana-3851	182	1	ii	ii	PROPN
cana-3851	182	2	.	.	PUNCT
cana-3851	183	1	image	image	NOUN
cana-3851	183	2	preprocessing	preprocesse	VERB
cana-3851	183	3	preprocessing	preprocessing	NOUN
cana-3851	183	4	is	be	AUX
cana-3851	183	5	necessary	necessary	ADJ
cana-3851	183	6	for	for	ADP
cana-3851	183	7	the	the	DET
cana-3851	183	8	dataset	dataset	NOUN
cana-3851	183	9	's	's	PART
cana-3851	183	10	pictures	picture	NOUN
cana-3851	183	11	because	because	SCONJ
cana-3851	183	12	to	to	ADP
cana-3851	183	13	the	the	DET
cana-3851	183	14	large	large	ADJ
cana-3851	183	15	variation	variation	NOUN
cana-3851	183	16	in	in	ADP
cana-3851	183	17	intensities	intensity	NOUN
cana-3851	183	18	,	,	PUNCT
cana-3851	183	19	which	which	PRON
cana-3851	183	20	exceed	exceed	VERB
cana-3851	183	21	the	the	DET
cana-3851	183	22	standard	standard	ADJ
cana-3851	183	23	industry	industry	NOUN
cana-3851	183	24	threshold	threshold	NOUN
cana-3851	183	25	of	of	ADP
cana-3851	183	26	255	255	NUM
cana-3851	183	27	.	.	PUNCT
cana-3851	184	1	the	the	DET
cana-3851	184	2	smooth	smooth	ADJ
cana-3851	184	3	and	and	CCONJ
cana-3851	184	4	quantitative	quantitative	ADJ
cana-3851	184	5	training	training	NOUN
cana-3851	184	6	of	of	ADP
cana-3851	184	7	the	the	DET
cana-3851	184	8	network	network	NOUN
cana-3851	184	9	depends	depend	VERB
cana-3851	184	10	on	on	ADP
cana-3851	184	11	completing	complete	VERB
cana-3851	184	12	a	a	DET
cana-3851	184	13	certain	certain	ADJ
cana-3851	184	14	set	set	NOUN
cana-3851	184	15	of	of	ADP
cana-3851	184	16	preprocessing	preprocessing	NOUN
cana-3851	184	17	processes	process	NOUN
cana-3851	184	18	.	.	PUNCT
cana-3851	185	1	there	there	PRON
cana-3851	185	2	is	be	VERB
cana-3851	185	3	some	some	DET
cana-3851	185	4	evidence	evidence	NOUN
cana-3851	185	5	that	that	SCONJ
cana-3851	185	6	preprocessing	preprocessing	NOUN
cana-3851	185	7	may	may	AUX
cana-3851	185	8	improve	improve	VERB
cana-3851	185	9	segmentation	segmentation	NOUN
cana-3851	185	10	accuracy	accuracy	NOUN
cana-3851	185	11	[	[	X
cana-3851	185	12	16	16	NUM
cana-3851	185	13	]	]	PUNCT
cana-3851	185	14	.	.	PUNCT
cana-3851	186	1	the	the	DET
cana-3851	186	2	process	process	NOUN
cana-3851	186	3	of	of	ADP
cana-3851	186	4	histogram	histogram	NOUN
cana-3851	186	5	equalization	equalization	NOUN
cana-3851	186	6	,	,	PUNCT
cana-3851	186	7	which	which	PRON
cana-3851	186	8	involves	involve	VERB
cana-3851	186	9	mapping	map	VERB
cana-3851	186	10	new	new	ADJ
cana-3851	186	11	pixel	pixel	NOUN
cana-3851	186	12	values	value	NOUN
cana-3851	186	13	to	to	ADP
cana-3851	186	14	the	the	DET
cana-3851	186	15	histogram	histogram	NOUN
cana-3851	186	16	,	,	PUNCT
cana-3851	186	17	enhances	enhance	VERB
cana-3851	186	18	the	the	DET
cana-3851	186	19	contrast	contrast	NOUN
cana-3851	186	20	of	of	ADP
cana-3851	186	21	a	a	DET
cana-3851	186	22	grayscale	grayscale	NOUN
cana-3851	186	23	image	image	NOUN
cana-3851	186	24	.	.	PUNCT
cana-3851	187	1	image	image	NOUN
cana-3851	187	2	histogram	histogram	NOUN
cana-3851	187	3	dynamic	dynamic	ADJ
cana-3851	187	4	range	range	NOUN
cana-3851	187	5	expansion	expansion	NOUN
cana-3851	187	6	is	be	AUX
cana-3851	187	7	the	the	DET
cana-3851	187	8	goal	goal	NOUN
cana-3851	187	9	of	of	ADP
cana-3851	187	10	this	this	DET
cana-3851	187	11	method	method	NOUN
cana-3851	187	12	.	.	PUNCT
cana-3851	188	1	histogram	histogram	PROPN
cana-3851	188	2	balancing	balancing	NOUN
cana-3851	188	3	increases	increase	VERB
cana-3851	188	4	image	image	NOUN
cana-3851	188	5	separation	separation	NOUN
cana-3851	188	6	and	and	CCONJ
cana-3851	188	7	ensures	ensure	VERB
cana-3851	188	8	a	a	DET
cana-3851	188	9	uniform	uniform	ADJ
cana-3851	188	10	distribution	distribution	NOUN
cana-3851	188	11	of	of	ADP
cana-3851	188	12	forces	force	NOUN
cana-3851	188	13	in	in	ADP
cana-3851	188	14	the	the	DET
cana-3851	188	15	output	output	NOUN
cana-3851	188	16	image	image	NOUN
cana-3851	188	17	by	by	ADP
cana-3851	188	18	assigning	assign	VERB
cana-3851	188	19	force	force	NOUN
cana-3851	188	20	estimates	estimate	NOUN
cana-3851	188	21	to	to	ADP
cana-3851	188	22	pixels	pixel	NOUN
cana-3851	188	23	in	in	ADP
cana-3851	188	24	the	the	DET
cana-3851	188	25	input	input	NOUN
cana-3851	188	26	image	image	NOUN
cana-3851	188	27	.	.	PUNCT
cana-3851	189	1	(	(	PUNCT
cana-3851	189	2	𝑎	𝑎	X
cana-3851	189	3	,	,	PUNCT
cana-3851	189	4	𝑏	𝑏	NOUN
cana-3851	189	5	)	)	PUNCT
cana-3851	189	6	=	=	SYM
cana-3851	189	7	{	{	PUNCT
cana-3851	189	8	1	1	NUM
cana-3851	189	9	𝑓(𝑎	𝑓(𝑎	NOUN
cana-3851	189	10	,	,	PUNCT
cana-3851	189	11	𝑏	𝑏	NOUN
cana-3851	189	12	)	)	PUNCT
cana-3851	189	13	≥	≥	NOUN
cana-3851	189	14	𝑇	𝑇	PROPN
cana-3851	189	15	0	0	SYM
cana-3851	189	16	𝑓(𝑎	𝑓(𝑎	PROPN
cana-3851	189	17	,	,	PUNCT
cana-3851	189	18	𝑏	𝑏	NOUN
cana-3851	189	19	)	)	PUNCT
cana-3851	189	20	≤	≤	NOUN
cana-3851	189	21	𝑇	𝑇	PROPN
cana-3851	189	22	(	(	PUNCT
cana-3851	189	23	1	1	NUM
cana-3851	189	24	)	)	PUNCT
cana-3851	189	25	in	in	ADP
cana-3851	189	26	this	this	DET
cana-3851	189	27	case	case	NOUN
cana-3851	189	28	,	,	PUNCT
cana-3851	189	29	a	a	PRON
cana-3851	189	30	and	and	CCONJ
cana-3851	189	31	b	b	NOUN
cana-3851	189	32	are	be	AUX
cana-3851	189	33	two	two	NUM
cana-3851	189	34	spatial	spatial	ADJ
cana-3851	189	35	coordinates	coordinate	NOUN
cana-3851	189	36	,	,	PUNCT
cana-3851	189	37	and	and	CCONJ
cana-3851	189	38	t	t	PROPN
cana-3851	189	39	is	be	AUX
cana-3851	189	40	the	the	DET
cana-3851	189	41	image	image	NOUN
cana-3851	189	42	's	's	PART
cana-3851	189	43	gray	gray	ADJ
cana-3851	189	44	level	level	NOUN
cana-3851	189	45	count	count	NOUN
cana-3851	189	46	.	.	PUNCT
cana-3851	190	1	the	the	DET
cana-3851	190	2	imagegraphs	imagegraph	NOUN
cana-3851	190	3	have	have	VERB
cana-3851	190	4	too	too	ADV
cana-3851	190	5	much	much	ADJ
cana-3851	190	6	noise	noise	NOUN
cana-3851	190	7	for	for	ADP
cana-3851	190	8	resnets	resnet	NOUN
cana-3851	190	9	to	to	PART
cana-3851	190	10	make	make	VERB
cana-3851	190	11	a	a	DET
cana-3851	190	12	difference	difference	NOUN
cana-3851	190	13	.	.	PUNCT
cana-3851	191	1	the	the	DET
cana-3851	191	2	noise	noise	NOUN
cana-3851	191	3	in	in	ADP
cana-3851	191	4	images	image	NOUN
cana-3851	191	5	will	will	AUX
cana-3851	191	6	be	be	AUX
cana-3851	191	7	reduced	reduce	VERB
cana-3851	191	8	via	via	ADP
cana-3851	191	9	binarization	binarization	NOUN
cana-3851	191	10	.	.	PUNCT
cana-3851	192	1	the	the	DET
cana-3851	192	2	rgb	rgb	PROPN
cana-3851	192	3	(	(	PUNCT
cana-3851	192	4	red	red	ADJ
cana-3851	192	5	,	,	PUNCT
cana-3851	192	6	green	green	ADJ
cana-3851	192	7	,	,	PUNCT
cana-3851	192	8	and	and	CCONJ
cana-3851	192	9	blue	blue	ADJ
cana-3851	192	10	)	)	PUNCT
cana-3851	192	11	channels	channel	NOUN
cana-3851	192	12	of	of	ADP
cana-3851	192	13	a	a	DET
cana-3851	192	14	color	color	NOUN
cana-3851	192	15	image	image	NOUN
cana-3851	192	16	may	may	AUX
cana-3851	192	17	take	take	VERB
cana-3851	192	18	on	on	ADP
cana-3851	192	19	values	value	NOUN
cana-3851	192	20	between	between	ADP
cana-3851	192	21	zero	zero	NUM
cana-3851	192	22	and	and	CCONJ
cana-3851	192	23	two	two	NUM
cana-3851	192	24	hundred	hundred	NUM
cana-3851	192	25	and	and	CCONJ
cana-3851	192	26	fifty	fifty	NUM
cana-3851	192	27	.	.	PUNCT
cana-3851	193	1	the	the	DET
cana-3851	193	2	transformation	transformation	NOUN
cana-3851	193	3	of	of	ADP
cana-3851	193	4	grayscale	grayscale	NOUN
cana-3851	193	5	images	image	NOUN
cana-3851	193	6	into	into	ADP
cana-3851	193	7	monochrome	monochrome	NOUN
cana-3851	193	8	(	(	PUNCT
cana-3851	193	9	0	0	NUM
cana-3851	193	10	to	to	PART
cana-3851	193	11	1	1	NUM
cana-3851	193	12	)	)	PUNCT
cana-3851	193	13	images	image	NOUN
cana-3851	193	14	is	be	AUX
cana-3851	193	15	a	a	DET
cana-3851	193	16	crucial	crucial	ADJ
cana-3851	193	17	part	part	NOUN
cana-3851	193	18	of	of	ADP
cana-3851	193	19	binarization	binarization	NOUN
cana-3851	193	20	.	.	PUNCT
cana-3851	194	1	the	the	DET
cana-3851	194	2	contours	contours	NOUN
cana-3851	194	3	of	of	ADP
cana-3851	194	4	different	different	ADJ
cana-3851	194	5	objects	object	NOUN
cana-3851	194	6	in	in	ADP
cana-3851	194	7	the	the	DET
cana-3851	194	8	image	image	NOUN
cana-3851	194	9	are	be	AUX
cana-3851	194	10	simplified	simplify	VERB
cana-3851	194	11	and	and	CCONJ
cana-3851	194	12	smoothed	smooth	VERB
cana-3851	194	13	down	down	ADP
cana-3851	194	14	via	via	ADP
cana-3851	194	15	binarization	binarization	NOUN
cana-3851	194	16	.	.	PUNCT
cana-3851	195	1	the	the	DET
cana-3851	195	2	model	model	NOUN
cana-3851	195	3	's	's	PART
cana-3851	195	4	learning	learning	NOUN
cana-3851	195	5	is	be	AUX
cana-3851	195	6	facilitated	facilitate	VERB
cana-3851	195	7	by	by	ADP
cana-3851	195	8	this	this	DET
cana-3851	195	9	function	function	NOUN
cana-3851	195	10	extraction	extraction	NOUN
cana-3851	195	11	.	.	PUNCT
cana-3851	196	1	iii	iii	X
cana-3851	196	2	.	.	PUNCT
cana-3851	196	3	data	datum	NOUN
cana-3851	196	4	augmentation	augmentation	PROPN
cana-3851	196	5	:	:	PUNCT
cana-3851	196	6	when	when	SCONJ
cana-3851	196	7	applied	apply	VERB
cana-3851	196	8	to	to	ADP
cana-3851	196	9	larger	large	ADJ
cana-3851	196	10	training	training	NOUN
cana-3851	196	11	sets	set	NOUN
cana-3851	196	12	,	,	PUNCT
cana-3851	196	13	it	it	PRON
cana-3851	196	14	helps	help	VERB
cana-3851	196	15	to	to	PART
cana-3851	196	16	decrease	decrease	VERB
cana-3851	196	17	overfitting	overfitte	VERB
cana-3851	196	18	.	.	PUNCT
cana-3851	197	1	the	the	DET
cana-3851	197	2	data	data	NOUN
cana-3851	197	3	augmentation	augmentation	NOUN
cana-3851	197	4	was	be	AUX
cana-3851	197	5	limited	limit	VERB
cana-3851	197	6	to	to	ADP
cana-3851	197	7	rotational	rotational	ADJ
cana-3851	197	8	operations	operation	NOUN
cana-3851	197	9	as	as	SCONJ
cana-3851	197	10	the	the	DET
cana-3851	197	11	patch	patch	NOUN
cana-3851	197	12	's	's	PART
cana-3851	197	13	class	class	NOUN
cana-3851	197	14	is	be	AUX
cana-3851	197	15	retrieved	retrieve	VERB
cana-3851	197	16	by	by	ADP
cana-3851	197	17	the	the	DET
cana-3851	197	18	center	center	NOUN
cana-3851	197	19	voxel	voxel	PROPN
cana-3851	197	20	.	.	PUNCT
cana-3851	198	1	image	image	NOUN
cana-3851	198	2	translations	translation	NOUN
cana-3851	198	3	are	be	AUX
cana-3851	198	4	also	also	ADV
cana-3851	198	5	considered	consider	VERB
cana-3851	198	6	by	by	ADP
cana-3851	198	7	some	some	DET
cana-3851	198	8	writers	writer	NOUN
cana-3851	198	9	,	,	PUNCT
cana-3851	198	10	although	although	SCONJ
cana-3851	198	11	they	they	PRON
cana-3851	198	12	may	may	AUX
cana-3851	198	13	assign	assign	VERB
cana-3851	198	14	the	the	DET
cana-3851	198	15	incorrect	incorrect	ADJ
cana-3851	198	16	class	class	NOUN
cana-3851	198	17	to	to	ADP
cana-3851	198	18	the	the	DET
cana-3851	198	19	patch	patch	NOUN
cana-3851	198	20	when	when	SCONJ
cana-3851	198	21	used	use	VERB
cana-3851	198	22	for	for	ADP
cana-3851	198	23	segmentation	segmentation	NOUN
cana-3851	198	24	.	.	PUNCT
cana-3851	199	1	as	as	ADP
cana-3851	199	2	a	a	DET
cana-3851	199	3	result	result	NOUN
cana-3851	199	4	,	,	PUNCT
cana-3851	199	5	we	we	PRON
cana-3851	199	6	rotated	rotate	VERB
cana-3851	199	7	an	an	DET
cana-3851	199	8	existing	exist	VERB
cana-3851	199	9	patch	patch	NOUN
cana-3851	199	10	to	to	PART
cana-3851	199	11	create	create	VERB
cana-3851	199	12	new	new	ADJ
cana-3851	199	13	ones	one	NOUN
cana-3851	199	14	during	during	ADP
cana-3851	199	15	training	training	NOUN
cana-3851	199	16	,	,	PUNCT
cana-3851	199	17	which	which	DET
cana-3851	199	18	image	image	NOUN
cana-3851	199	19	dataset	dataset	NOUN
cana-3851	199	20	image	image	NOUN
cana-3851	199	21	augmentation	augmentation	NOUN
cana-3851	199	22	image	image	NOUN
cana-3851	199	23	preprocessing	preprocesse	VERB
cana-3851	199	24	segmentation	segmentation	NOUN
cana-3851	199	25	(	(	PUNCT
cana-3851	199	26	vgg16+resn	vgg16+resn	PROPN
cana-3851	199	27	et50	et50	PROPN
cana-3851	199	28	)	)	PUNCT
cana-3851	199	29	communications	communication	NOUN
cana-3851	199	30	on	on	ADP
cana-3851	199	31	applied	apply	VERB
cana-3851	199	32	nonlinear	nonlinear	ADJ
cana-3851	199	33	analysis	analysis	NOUN
cana-3851	199	34	issn	issn	NOUN
cana-3851	199	35	:	:	PUNCT
cana-3851	199	36	1074	1074	NUM
cana-3851	199	37	-	-	PUNCT
cana-3851	199	38	133x	133x	NUM
cana-3851	199	39	vol	vol	NOUN
cana-3851	199	40	32	32	NUM
cana-3851	199	41	no	no	NOUN
cana-3851	199	42	.	.	PUNCT
cana-3851	200	1	9s	9s	NUM
cana-3851	200	2	(	(	PUNCT
cana-3851	200	3	2025	2025	NUM
cana-3851	200	4	)	)	PUNCT
cana-3851	200	5	222	222	NUM
cana-3851	200	6	https://internationalpubls.com	https://internationalpubls.com	NUM
cana-3851	200	7	enriched	enrich	VERB
cana-3851	200	8	our	our	PRON
cana-3851	200	9	data	datum	NOUN
cana-3851	200	10	set	set	VERB
cana-3851	200	11	.	.	PUNCT
cana-3851	201	1	even	even	ADV
cana-3851	201	2	though	though	SCONJ
cana-3851	201	3	we	we	PRON
cana-3851	201	4	used	use	VERB
cana-3851	201	5	angles	angle	NOUN
cana-3851	201	6	that	that	PRON
cana-3851	201	7	are	be	AUX
cana-3851	201	8	multiples	multiple	NOUN
cana-3851	201	9	of	of	ADP
cana-3851	201	10	90	90	NUM
cana-3851	201	11	degrees	degree	NOUN
cana-3851	201	12	in	in	ADP
cana-3851	201	13	our	our	PRON
cana-3851	201	14	suggestion	suggestion	NOUN
cana-3851	201	15	,	,	PUNCT
cana-3851	201	16	we	we	PRON
cana-3851	201	17	will	will	AUX
cana-3851	201	18	be	be	AUX
cana-3851	201	19	contemplating	contemplate	VERB
cana-3851	201	20	an	an	DET
cana-3851	201	21	alternative	alternative	ADJ
cana-3851	201	22	option	option	NOUN
cana-3851	202	1	[	[	X
cana-3851	202	2	22	22	NUM
cana-3851	202	3	]	]	PUNCT
cana-3851	202	4	.	.	PUNCT
cana-3851	203	1	with	with	ADP
cana-3851	203	2	data	datum	NOUN
cana-3851	203	3	augmentation	augmentation	NOUN
cana-3851	203	4	,	,	PUNCT
cana-3851	203	5	we	we	PRON
cana-3851	203	6	may	may	AUX
cana-3851	203	7	make	make	VERB
cana-3851	203	8	inputs	input	NOUN
cana-3851	203	9	that	that	PRON
cana-3851	203	10	are	be	AUX
cana-3851	203	11	n't	not	PART
cana-3851	203	12	always	always	ADV
cana-3851	203	13	accurate	accurate	ADJ
cana-3851	203	14	.	.	PUNCT
cana-3851	204	1	cropping	cropping	NOUN
cana-3851	204	2	,	,	PUNCT
cana-3851	204	3	zooming	zooming	NOUN
cana-3851	204	4	,	,	PUNCT
cana-3851	204	5	and	and	CCONJ
cana-3851	204	6	rotating	rotate	VERB
cana-3851	204	7	mri	mri	NOUN
cana-3851	204	8	images	image	NOUN
cana-3851	204	9	is	be	AUX
cana-3851	204	10	as	as	ADV
cana-3851	204	11	easy	easy	ADJ
cana-3851	204	12	as	as	ADP
cana-3851	204	13	using	use	VERB
cana-3851	204	14	image	image	NOUN
cana-3851	204	15	editing	edit	VERB
cana-3851	204	16	software	software	NOUN
cana-3851	204	17	.	.	PUNCT
cana-3851	205	1	by	by	ADP
cana-3851	205	2	excluding	exclude	VERB
cana-3851	205	3	morphological	morphological	ADJ
cana-3851	205	4	arrangements	arrangement	NOUN
cana-3851	205	5	that	that	PRON
cana-3851	205	6	are	be	AUX
cana-3851	205	7	not	not	PART
cana-3851	205	8	meaningful	meaningful	ADJ
cana-3851	205	9	across	across	ADP
cana-3851	205	10	images	image	NOUN
cana-3851	205	11	,	,	PUNCT
cana-3851	205	12	the	the	DET
cana-3851	205	13	neural	neural	ADJ
cana-3851	205	14	network	network	NOUN
cana-3851	205	15	is	be	AUX
cana-3851	205	16	able	able	ADJ
cana-3851	205	17	to	to	PART
cana-3851	205	18	avoid	avoid	VERB
cana-3851	205	19	overfitting	overfitte	VERB
cana-3851	205	20	and	and	CCONJ
cana-3851	205	21	avoid	avoid	VERB
cana-3851	205	22	recognizing	recognize	VERB
cana-3851	205	23	particular	particular	ADJ
cana-3851	205	24	patterns	pattern	NOUN
cana-3851	205	25	in	in	ADP
cana-3851	205	26	the	the	DET
cana-3851	205	27	input	input	NOUN
cana-3851	205	28	dataset	dataset	NOUN
cana-3851	205	29	.	.	PUNCT
cana-3851	206	1	to	to	PART
cana-3851	206	2	introduce	introduce	VERB
cana-3851	206	3	uncertainty	uncertainty	NOUN
cana-3851	206	4	into	into	ADP
cana-3851	206	5	the	the	DET
cana-3851	206	6	dataset	dataset	NOUN
cana-3851	206	7	,	,	PUNCT
cana-3851	206	8	dropout	dropout	NOUN
cana-3851	206	9	briefly	briefly	NOUN
cana-3851	206	10	removes	remove	VERB
cana-3851	206	11	nodes	node	NOUN
cana-3851	206	12	from	from	ADP
cana-3851	206	13	the	the	DET
cana-3851	206	14	convolutional	convolutional	ADJ
cana-3851	206	15	neural	neural	ADJ
cana-3851	206	16	network	network	NOUN
cana-3851	206	17	.	.	PUNCT
cana-3851	207	1	one	one	NUM
cana-3851	207	2	way	way	NOUN
cana-3851	207	3	to	to	PART
cana-3851	207	4	lower	lower	VERB
cana-3851	207	5	the	the	DET
cana-3851	207	6	weighting	weighting	NOUN
cana-3851	207	7	strength	strength	NOUN
cana-3851	207	8	of	of	ADP
cana-3851	207	9	biased	biased	ADJ
cana-3851	207	10	nodes	node	NOUN
cana-3851	207	11	is	be	AUX
cana-3851	207	12	to	to	PART
cana-3851	207	13	use	use	VERB
cana-3851	207	14	batch	batch	NOUN
cana-3851	207	15	normalization	normalization	NOUN
cana-3851	207	16	.	.	PUNCT
cana-3851	208	1	since	since	SCONJ
cana-3851	208	2	these	these	DET
cana-3851	208	3	heavy	heavy	ADJ
cana-3851	208	4	weights	weight	NOUN
cana-3851	208	5	could	could	AUX
cana-3851	208	6	be	be	AUX
cana-3851	208	7	linked	link	VERB
cana-3851	208	8	to	to	ADP
cana-3851	208	9	particular	particular	ADJ
cana-3851	208	10	,	,	PUNCT
cana-3851	208	11	accurate	accurate	ADJ
cana-3851	208	12	traits	trait	NOUN
cana-3851	208	13	in	in	ADP
cana-3851	208	14	the	the	DET
cana-3851	208	15	training	training	NOUN
cana-3851	208	16	set	set	NOUN
cana-3851	208	17	,	,	PUNCT
cana-3851	208	18	they	they	PRON
cana-3851	208	19	do	do	AUX
cana-3851	208	20	provide	provide	VERB
cana-3851	208	21	generalizability	generalizability	NOUN
cana-3851	208	22	to	to	ADP
cana-3851	208	23	other	other	ADJ
cana-3851	208	24	datasets	dataset	NOUN
cana-3851	208	25	[	[	X
cana-3851	208	26	20	20	NUM
cana-3851	208	27	]	]	PUNCT
cana-3851	208	28	.	.	PUNCT
cana-3851	209	1	iv.proposed	iv.proposed	PROPN
cana-3851	209	2	vgg	vgg	PROPN
cana-3851	209	3	16	16	NUM
cana-3851	209	4	+	+	NUM
cana-3851	209	5	resnet50	resnet50	NOUN
cana-3851	209	6	segmentation	segmentation	NOUN
cana-3851	209	7	model	model	NOUN
cana-3851	209	8	:	:	PUNCT
cana-3851	209	9	an	an	DET
cana-3851	209	10	efficient	efficient	ADJ
cana-3851	209	11	dl	dl	NOUN
cana-3851	209	12	technique	technique	NOUN
cana-3851	209	13	,	,	PUNCT
cana-3851	209	14	transfer	transfer	NOUN
cana-3851	209	15	learning	learning	NOUN
cana-3851	209	16	(	(	PUNCT
cana-3851	209	17	tl	tl	PROPN
cana-3851	209	18	)	)	PUNCT
cana-3851	209	19	allows	allow	VERB
cana-3851	209	20	for	for	ADP
cana-3851	209	21	the	the	DET
cana-3851	209	22	reuse	reuse	NOUN
cana-3851	209	23	of	of	ADP
cana-3851	209	24	trained	train	VERB
cana-3851	209	25	models	model	NOUN
cana-3851	209	26	and	and	CCONJ
cana-3851	209	27	the	the	DET
cana-3851	209	28	approximations	approximation	NOUN
cana-3851	209	29	they	they	PRON
cana-3851	209	30	acquired	acquire	VERB
cana-3851	209	31	for	for	ADP
cana-3851	209	32	new	new	ADJ
cana-3851	209	33	uses	use	NOUN
cana-3851	209	34	.	.	PUNCT
cana-3851	210	1	because	because	SCONJ
cana-3851	210	2	it	it	PRON
cana-3851	210	3	increases	increase	VERB
cana-3851	210	4	performance	performance	NOUN
cana-3851	210	5	,	,	PUNCT
cana-3851	210	6	speeds	speed	VERB
cana-3851	210	7	up	up	ADP
cana-3851	210	8	training	training	NOUN
cana-3851	210	9	,	,	PUNCT
cana-3851	210	10	and	and	CCONJ
cana-3851	210	11	makes	make	VERB
cana-3851	210	12	better	well	ADJ
cana-3851	210	13	generalization	generalization	NOUN
cana-3851	210	14	,	,	PUNCT
cana-3851	210	15	it	it	PRON
cana-3851	210	16	is	be	AUX
cana-3851	210	17	useful	useful	ADJ
cana-3851	210	18	in	in	ADP
cana-3851	210	19	many	many	ADJ
cana-3851	210	20	applications	application	NOUN
cana-3851	210	21	where	where	SCONJ
cana-3851	210	22	data	datum	NOUN
cana-3851	210	23	is	be	AUX
cana-3851	210	24	few	few	ADJ
cana-3851	210	25	and	and	CCONJ
cana-3851	210	26	computer	computer	NOUN
cana-3851	210	27	resources	resource	NOUN
cana-3851	210	28	are	be	AUX
cana-3851	210	29	constrained	constrain	VERB
cana-3851	210	30	.	.	PUNCT
cana-3851	211	1	another	another	DET
cana-3851	211	2	benefit	benefit	NOUN
cana-3851	211	3	of	of	ADP
cana-3851	211	4	tl	tl	PROPN
cana-3851	211	5	is	be	AUX
cana-3851	211	6	that	that	SCONJ
cana-3851	211	7	it	it	PRON
cana-3851	211	8	allows	allow	VERB
cana-3851	211	9	data	datum	NOUN
cana-3851	211	10	training	training	NOUN
cana-3851	211	11	with	with	ADP
cana-3851	211	12	lower	low	ADJ
cana-3851	211	13	model	model	NOUN
cana-3851	211	14	design	design	NOUN
cana-3851	211	15	expenses	expense	NOUN
cana-3851	211	16	[	[	X
cana-3851	211	17	20	20	NUM
cana-3851	211	18	]	]	PUNCT
cana-3851	211	19	.	.	PUNCT
cana-3851	212	1	specifically	specifically	ADV
cana-3851	212	2	,	,	PUNCT
cana-3851	212	3	this	this	DET
cana-3851	212	4	piece	piece	NOUN
cana-3851	212	5	makes	make	VERB
cana-3851	212	6	use	use	NOUN
cana-3851	212	7	of	of	ADP
cana-3851	212	8	a	a	DET
cana-3851	212	9	vgg	vgg	NOUN
cana-3851	212	10	16	16	NUM
cana-3851	212	11	+	+	NUM
cana-3851	212	12	resnet50	resnet50	NOUN
cana-3851	212	13	hybrid	hybrid	ADJ
cana-3851	212	14	model	model	NOUN
cana-3851	212	15	[	[	X
cana-3851	212	16	15	15	NUM
cana-3851	212	17	]	]	PUNCT
cana-3851	212	18	.	.	PUNCT
cana-3851	213	1	a	a	DET
cana-3851	213	2	combination	combination	NOUN
cana-3851	213	3	of	of	ADP
cana-3851	213	4	resnet50	resnet50	NOUN
cana-3851	213	5	and	and	CCONJ
cana-3851	213	6	vgg16	vgg16	VERB
cana-3851	213	7	for	for	ADP
cana-3851	213	8	mri	mri	NOUN
cana-3851	213	9	-	-	PUNCT
cana-3851	213	10	based	base	VERB
cana-3851	213	11	tumor	tumor	NOUN
cana-3851	213	12	detection	detection	NOUN
cana-3851	213	13	and	and	CCONJ
cana-3851	213	14	segmentation	segmentation	NOUN
cana-3851	213	15	via	via	ADP
cana-3851	213	16	a	a	DET
cana-3851	213	17	hybrid	hybrid	ADJ
cana-3851	213	18	technique	technique	NOUN
cana-3851	213	19	.	.	PUNCT
cana-3851	214	1	using	use	VERB
cana-3851	214	2	the	the	DET
cana-3851	214	3	enormous	enormous	ADJ
cana-3851	214	4	imagenet	imagenet	NOUN
cana-3851	214	5	dataset	dataset	NOUN
cana-3851	214	6	,	,	PUNCT
cana-3851	214	7	resnet50	resnet50	NOUN
cana-3851	214	8	is	be	AUX
cana-3851	214	9	a	a	DET
cana-3851	214	10	convolutional	convolutional	ADJ
cana-3851	214	11	neural	neural	ADJ
cana-3851	214	12	network	network	NOUN
cana-3851	214	13	(	(	PUNCT
cana-3851	214	14	cnn	cnn	PROPN
cana-3851	214	15	)	)	PUNCT
cana-3851	214	16	model	model	NOUN
cana-3851	214	17	trained	train	VERB
cana-3851	214	18	for	for	ADP
cana-3851	214	19	object	object	NOUN
cana-3851	214	20	recognition	recognition	NOUN
cana-3851	214	21	tasks	task	NOUN
cana-3851	214	22	.	.	PUNCT
cana-3851	215	1	completely	completely	ADV
cana-3851	215	2	linked	link	VERB
cana-3851	215	3	,	,	PUNCT
cana-3851	215	4	pooling	pooling	NOUN
cana-3851	215	5	,	,	PUNCT
cana-3851	215	6	and	and	CCONJ
cana-3851	215	7	convolutional	convolutional	ADJ
cana-3851	215	8	layers	layer	NOUN
cana-3851	215	9	are	be	AUX
cana-3851	215	10	among	among	ADP
cana-3851	215	11	its	its	PRON
cana-3851	215	12	many	many	ADJ
cana-3851	215	13	components	component	NOUN
cana-3851	215	14	.	.	PUNCT
cana-3851	216	1	this	this	DET
cana-3851	216	2	model	model	NOUN
cana-3851	216	3	's	's	PART
cana-3851	216	4	feature	feature	NOUN
cana-3851	216	5	extraction	extraction	NOUN
cana-3851	216	6	capabilities	capability	NOUN
cana-3851	216	7	could	could	AUX
cana-3851	216	8	be	be	AUX
cana-3851	216	9	useful	useful	ADJ
cana-3851	216	10	for	for	ADP
cana-3851	216	11	solving	solve	VERB
cana-3851	216	12	the	the	DET
cana-3851	216	13	brain	brain	NOUN
cana-3851	216	14	tumor	tumor	NOUN
cana-3851	216	15	detection	detection	NOUN
cana-3851	216	16	problem	problem	NOUN
cana-3851	216	17	.	.	PUNCT
cana-3851	217	1	using	use	VERB
cana-3851	217	2	public	public	ADJ
cana-3851	217	3	picture	picture	NOUN
cana-3851	217	4	features	feature	NOUN
cana-3851	217	5	as	as	ADP
cana-3851	217	6	a	a	DET
cana-3851	217	7	basis	basis	NOUN
cana-3851	217	8	,	,	PUNCT
cana-3851	217	9	the	the	DET
cana-3851	217	10	resnet50	resnet50	NOUN
cana-3851	217	11	model	model	NOUN
cana-3851	217	12	's	's	PART
cana-3851	217	13	bottom	bottom	ADJ
cana-3851	217	14	layers	layer	NOUN
cana-3851	217	15	learn	learn	VERB
cana-3851	217	16	to	to	PART
cana-3851	217	17	detect	detect	VERB
cana-3851	217	18	brain	brain	NOUN
cana-3851	217	19	cancers	cancer	NOUN
cana-3851	217	20	.	.	PUNCT
cana-3851	218	1	to	to	PART
cana-3851	218	2	detect	detect	VERB
cana-3851	218	3	and	and	CCONJ
cana-3851	218	4	separate	separate	ADJ
cana-3851	218	5	brain	brain	NOUN
cana-3851	218	6	tumors	tumor	NOUN
cana-3851	218	7	,	,	PUNCT
cana-3851	218	8	a	a	DET
cana-3851	218	9	new	new	ADJ
cana-3851	218	10	set	set	NOUN
cana-3851	218	11	of	of	ADP
cana-3851	218	12	fully	fully	ADV
cana-3851	218	13	connected	connected	ADJ
cana-3851	218	14	layers	layer	NOUN
cana-3851	218	15	takes	take	VERB
cana-3851	218	16	the	the	DET
cana-3851	218	17	place	place	NOUN
cana-3851	218	18	of	of	ADP
cana-3851	218	19	the	the	DET
cana-3851	218	20	resnet50	resnet50	NOUN
cana-3851	218	21	model	model	PROPN
cana-3851	218	22	's	's	PART
cana-3851	218	23	last	last	ADJ
cana-3851	218	24	few	few	ADJ
cana-3851	218	25	levels	level	NOUN
cana-3851	218	26	[	[	X
cana-3851	218	27	17	17	NUM
cana-3851	218	28	]	]	PUNCT
cana-3851	218	29	.	.	PUNCT
cana-3851	219	1	a	a	DET
cana-3851	219	2	cnn	cnn	PROPN
cana-3851	219	3	architecture	architecture	NOUN
cana-3851	219	4	was	be	AUX
cana-3851	219	5	presented	present	VERB
cana-3851	219	6	in	in	ADP
cana-3851	219	7	2014	2014	NUM
cana-3851	219	8	by	by	ADP
cana-3851	219	9	the	the	DET
cana-3851	219	10	visual	visual	ADJ
cana-3851	219	11	geometry	geometry	NOUN
cana-3851	219	12	group	group	NOUN
cana-3851	219	13	(	(	PUNCT
cana-3851	219	14	vgg	vgg	PROPN
cana-3851	219	15	)	)	PUNCT
cana-3851	219	16	at	at	ADP
cana-3851	219	17	oxford	oxford	PROPN
cana-3851	219	18	university	university	PROPN
cana-3851	219	19	.	.	PUNCT
cana-3851	220	1	a	a	DET
cana-3851	220	2	number	number	NOUN
cana-3851	220	3	of	of	ADP
cana-3851	220	4	computer	computer	NOUN
cana-3851	220	5	vision	vision	NOUN
cana-3851	220	6	applications	application	NOUN
cana-3851	220	7	heavily	heavily	ADV
cana-3851	220	8	use	use	VERB
cana-3851	220	9	its	its	PRON
cana-3851	220	10	deep	deep	ADJ
cana-3851	220	11	architecture	architecture	NOUN
cana-3851	220	12	,	,	PUNCT
cana-3851	220	13	including	include	VERB
cana-3851	220	14	image	image	NOUN
cana-3851	220	15	segmentation	segmentation	NOUN
cana-3851	220	16	,	,	PUNCT
cana-3851	220	17	object	object	VERB
cana-3851	220	18	detection	detection	NOUN
cana-3851	220	19	,	,	PUNCT
cana-3851	220	20	and	and	CCONJ
cana-3851	220	21	classification	classification	NOUN
cana-3851	220	22	[	[	X
cana-3851	220	23	15	15	NUM
cana-3851	220	24	]	]	PUNCT
cana-3851	220	25	.	.	PUNCT
cana-3851	221	1	we	we	PRON
cana-3851	221	2	name	name	VERB
cana-3851	221	3	a	a	DET
cana-3851	221	4	cnn	cnn	PROPN
cana-3851	221	5	model	model	NOUN
cana-3851	221	6	with	with	ADP
cana-3851	221	7	sixteen	sixteen	NUM
cana-3851	221	8	layers	layer	NOUN
cana-3851	221	9	vgg	vgg	VERB
cana-3851	221	10	16	16	NUM
cana-3851	221	11	.	.	PUNCT
cana-3851	222	1	one	one	NUM
cana-3851	222	2	of	of	ADP
cana-3851	222	3	the	the	DET
cana-3851	222	4	most	most	ADV
cana-3851	222	5	well	well	ADV
cana-3851	222	6	-	-	PUNCT
cana-3851	222	7	known	know	VERB
cana-3851	222	8	and	and	CCONJ
cana-3851	222	9	effective	effective	ADJ
cana-3851	222	10	models	model	NOUN
cana-3851	222	11	still	still	ADV
cana-3851	222	12	in	in	ADP
cana-3851	222	13	use	use	NOUN
cana-3851	222	14	today	today	NOUN
cana-3851	222	15	is	be	AUX
cana-3851	222	16	this	this	DET
cana-3851	222	17	one	one	NOUN
cana-3851	222	18	.	.	PUNCT
cana-3851	223	1	having	have	VERB
cana-3851	223	2	a	a	DET
cana-3851	223	3	large	large	ADJ
cana-3851	223	4	number	number	NOUN
cana-3851	223	5	of	of	ADP
cana-3851	223	6	parameters	parameter	NOUN
cana-3851	223	7	is	be	AUX
cana-3851	223	8	not	not	PART
cana-3851	223	9	as	as	ADV
cana-3851	223	10	important	important	ADJ
cana-3851	223	11	as	as	ADP
cana-3851	223	12	using	use	VERB
cana-3851	223	13	convnet	convnet	NOUN
cana-3851	223	14	layers	layer	NOUN
cana-3851	223	15	with	with	ADP
cana-3851	223	16	a	a	DET
cana-3851	223	17	3	3	NUM
cana-3851	223	18	×	×	NOUN
cana-3851	223	19	3	3	NUM
cana-3851	223	20	kernel	kernel	NOUN
cana-3851	223	21	size	size	NOUN
cana-3851	223	22	in	in	ADP
cana-3851	223	23	the	the	DET
cana-3851	223	24	vgg	vgg	ADJ
cana-3851	223	25	16	16	NUM
cana-3851	223	26	model	model	NOUN
cana-3851	223	27	architecture	architecture	NOUN
cana-3851	223	28	.	.	PUNCT
cana-3851	224	1	what	what	PRON
cana-3851	224	2	makes	make	VERB
cana-3851	224	3	this	this	DET
cana-3851	224	4	model	model	NOUN
cana-3851	224	5	unique	unique	ADJ
cana-3851	224	6	is	be	AUX
cana-3851	224	7	that	that	SCONJ
cana-3851	224	8	its	its	PRON
cana-3851	224	9	values	value	NOUN
cana-3851	224	10	are	be	AUX
cana-3851	224	11	freely	freely	ADV
cana-3851	224	12	available	available	ADJ
cana-3851	224	13	online	online	ADV
cana-3851	224	14	and	and	CCONJ
cana-3851	224	15	may	may	AUX
cana-3851	224	16	be	be	AUX
cana-3851	224	17	integrated	integrate	VERB
cana-3851	224	18	into	into	ADP
cana-3851	224	19	many	many	ADJ
cana-3851	224	20	systems	system	NOUN
cana-3851	224	21	and	and	CCONJ
cana-3851	224	22	applications	application	NOUN
cana-3851	224	23	.	.	PUNCT
cana-3851	225	1	when	when	SCONJ
cana-3851	225	2	compared	compare	VERB
cana-3851	225	3	to	to	ADP
cana-3851	225	4	other	other	ADJ
cana-3851	225	5	wellestablished	wellestablished	ADJ
cana-3851	225	6	comprehensives	comprehensive	NOUN
cana-3851	225	7	,	,	PUNCT
cana-3851	225	8	it	it	PRON
cana-3851	225	9	stands	stand	VERB
cana-3851	225	10	out	out	ADP
cana-3851	225	11	for	for	ADP
cana-3851	225	12	being	be	AUX
cana-3851	225	13	very	very	ADV
cana-3851	225	14	straightforward	straightforward	ADJ
cana-3851	225	15	to	to	PART
cana-3851	225	16	comprehend	comprehend	VERB
cana-3851	225	17	.	.	PUNCT
cana-3851	226	1	this	this	DET
cana-3851	226	2	model	model	NOUN
cana-3851	226	3	is	be	AUX
cana-3851	226	4	capable	capable	ADJ
cana-3851	226	5	of	of	ADP
cana-3851	226	6	handling	handle	VERB
cana-3851	226	7	input	input	NOUN
cana-3851	226	8	images	image	NOUN
cana-3851	226	9	as	as	ADV
cana-3851	226	10	tiny	tiny	ADJ
cana-3851	226	11	as	as	ADP
cana-3851	226	12	224	224	NUM
cana-3851	226	13	×	×	NOUN
cana-3851	226	14	224	224	NUM
cana-3851	226	15	pixels	pixel	NOUN
cana-3851	226	16	with	with	ADP
cana-3851	226	17	three	three	NUM
cana-3851	226	18	channels	channel	NOUN
cana-3851	226	19	.	.	PUNCT
cana-3851	227	1	optimization	optimization	NOUN
cana-3851	227	2	methods	method	NOUN
cana-3851	227	3	compute	compute	VERB
cana-3851	227	4	the	the	DET
cana-3851	227	5	weighted	weighted	ADJ
cana-3851	227	6	sum	sum	NOUN
cana-3851	227	7	of	of	ADP
cana-3851	227	8	the	the	DET
cana-3851	227	9	input	input	NOUN
cana-3851	227	10	to	to	PART
cana-3851	227	11	ascertain	ascertain	VERB
cana-3851	227	12	whether	whether	SCONJ
cana-3851	227	13	a	a	DET
cana-3851	227	14	neuron	neuron	NOUN
cana-3851	227	15	is	be	AUX
cana-3851	227	16	necessary	necessary	ADJ
cana-3851	227	17	for	for	SCONJ
cana-3851	227	18	a	a	DET
cana-3851	227	19	neural	neural	ADJ
cana-3851	227	20	network	network	NOUN
cana-3851	227	21	to	to	PART
cana-3851	227	22	be	be	AUX
cana-3851	227	23	active	active	ADJ
cana-3851	227	24	.	.	PUNCT
cana-3851	228	1	kernel	kernel	PROPN
cana-3851	228	2	function	function	PROPN
cana-3851	228	3	is	be	AUX
cana-3851	228	4	necessary	necessary	ADJ
cana-3851	228	5	since	since	SCONJ
cana-3851	228	6	it	it	PRON
cana-3851	228	7	induces	induce	VERB
cana-3851	228	8	non	non	ADJ
cana-3851	228	9	-	-	ADJ
cana-3851	228	10	linearity	linearity	NOUN
cana-3851	228	11	into	into	ADP
cana-3851	228	12	the	the	DET
cana-3851	228	13	output	output	NOUN
cana-3851	228	14	neuron	neuron	NOUN
cana-3851	228	15	.	.	PUNCT
cana-3851	229	1	the	the	DET
cana-3851	229	2	training	training	NOUN
cana-3851	229	3	procedure	procedure	NOUN
cana-3851	229	4	,	,	PUNCT
cana-3851	229	5	bias	bias	NOUN
cana-3851	229	6	,	,	PUNCT
cana-3851	229	7	and	and	CCONJ
cana-3851	229	8	weight	weight	NOUN
cana-3851	229	9	all	all	DET
cana-3851	229	10	function	function	VERB
cana-3851	229	11	together	together	ADV
cana-3851	229	12	in	in	ADP
cana-3851	229	13	a	a	DET
cana-3851	229	14	neural	neural	ADJ
cana-3851	229	15	network	network	NOUN
cana-3851	229	16	.	.	PUNCT
cana-3851	230	1	inaccurate	inaccurate	ADJ
cana-3851	230	2	output	output	NOUN
cana-3851	230	3	causes	cause	VERB
cana-3851	230	4	changes	change	NOUN
cana-3851	230	5	to	to	ADP
cana-3851	230	6	the	the	DET
cana-3851	230	7	neuronal	neuronal	ADJ
cana-3851	230	8	connection	connection	NOUN
cana-3851	230	9	weights	weight	NOUN
cana-3851	230	10	.	.	PUNCT
cana-3851	231	1	with	with	ADP
cana-3851	231	2	the	the	DET
cana-3851	231	3	use	use	NOUN
cana-3851	231	4	of	of	ADP
cana-3851	231	5	activation	activation	NOUN
cana-3851	231	6	functions	function	NOUN
cana-3851	231	7	and	and	CCONJ
cana-3851	231	8	input	input	NOUN
cana-3851	231	9	layers	layer	NOUN
cana-3851	231	10	that	that	PRON
cana-3851	231	11	give	give	VERB
cana-3851	231	12	non	non	ADJ
cana-3851	231	13	-	-	ADJ
cana-3851	231	14	linear	linear	ADJ
cana-3851	231	15	input	input	NOUN
cana-3851	231	16	,	,	PUNCT
cana-3851	231	17	a	a	DET
cana-3851	231	18	neural	neural	ADJ
cana-3851	231	19	network	network	NOUN
cana-3851	231	20	may	may	AUX
cana-3851	231	21	learn	learn	VERB
cana-3851	231	22	and	and	CCONJ
cana-3851	231	23	do	do	VERB
cana-3851	231	24	complex	complex	ADJ
cana-3851	231	25	tasks	task	NOUN
cana-3851	231	26	[	[	X
cana-3851	231	27	12	12	NUM
cana-3851	231	28	]	]	PUNCT
cana-3851	231	29	.	.	PUNCT
cana-3851	232	1	figure	figure	NOUN
cana-3851	232	2	3	3	NUM
cana-3851	232	3	shows	show	VERB
cana-3851	232	4	a	a	DET
cana-3851	232	5	typical	typical	ADJ
cana-3851	232	6	architecture	architecture	NOUN
cana-3851	232	7	of	of	ADP
cana-3851	232	8	a	a	DET
cana-3851	232	9	vgg	vgg	ADJ
cana-3851	232	10	16	16	NUM
cana-3851	232	11	network	network	NOUN
cana-3851	232	12	.	.	PUNCT
cana-3851	233	1	communications	communication	NOUN
cana-3851	233	2	on	on	ADP
cana-3851	233	3	applied	apply	VERB
cana-3851	233	4	nonlinear	nonlinear	ADJ
cana-3851	233	5	analysis	analysis	NOUN
cana-3851	233	6	issn	issn	NOUN
cana-3851	233	7	:	:	PUNCT
cana-3851	233	8	1074	1074	NUM
cana-3851	233	9	-	-	PUNCT
cana-3851	233	10	133x	133x	NUM
cana-3851	233	11	vol	vol	NOUN
cana-3851	233	12	32	32	NUM
cana-3851	233	13	no	no	NOUN
cana-3851	233	14	.	.	PUNCT
cana-3851	234	1	9s	9s	NUM
cana-3851	234	2	(	(	PUNCT
cana-3851	234	3	2025	2025	NUM
cana-3851	234	4	)	)	PUNCT
cana-3851	234	5	223	223	NUM
cana-3851	235	1	https://internationalpubls.com	https://internationalpubls.com	X
cana-3851	235	2	figure	figure	NOUN
cana-3851	235	3	3	3	NUM
cana-3851	235	4	.	.	PUNCT
cana-3851	236	1	a	a	DET
cana-3851	236	2	standard	standard	ADJ
cana-3851	236	3	vgg	vgg	ADJ
cana-3851	236	4	16	16	NUM
cana-3851	236	5	network	network	NOUN
cana-3851	236	6	architecture	architecture	NOUN
cana-3851	236	7	dcnn	dcnn	ADJ
cana-3851	236	8	models	model	NOUN
cana-3851	236	9	include	include	VERB
cana-3851	236	10	resnet	resnet	NOUN
cana-3851	236	11	,	,	PUNCT
cana-3851	236	12	also	also	ADV
cana-3851	236	13	known	know	VERB
cana-3851	236	14	as	as	ADP
cana-3851	236	15	residual	residual	ADJ
cana-3851	236	16	network	network	NOUN
cana-3851	236	17	.	.	PUNCT
cana-3851	237	1	it	it	PRON
cana-3851	237	2	improves	improve	VERB
cana-3851	237	3	performance	performance	NOUN
cana-3851	237	4	in	in	ADP
cana-3851	237	5	a	a	DET
cana-3851	237	6	number	number	NOUN
cana-3851	237	7	of	of	ADP
cana-3851	237	8	areas	area	NOUN
cana-3851	237	9	by	by	ADP
cana-3851	237	10	employing	employ	VERB
cana-3851	237	11	transfer	transfer	NOUN
cana-3851	237	12	learning	learning	NOUN
cana-3851	237	13	,	,	PUNCT
cana-3851	237	14	which	which	PRON
cana-3851	237	15	leads	lead	VERB
cana-3851	237	16	to	to	ADP
cana-3851	237	17	high	high	ADJ
cana-3851	237	18	classification	classification	NOUN
cana-3851	237	19	results	result	NOUN
cana-3851	237	20	.	.	PUNCT
cana-3851	238	1	in	in	ADP
cana-3851	238	2	2015	2015	NUM
cana-3851	238	3	,	,	PUNCT
cana-3851	238	4	resnet	resnet	NOUN
cana-3851	238	5	won	win	VERB
cana-3851	238	6	first	first	ADJ
cana-3851	238	7	place	place	NOUN
cana-3851	238	8	in	in	ADP
cana-3851	238	9	the	the	DET
cana-3851	238	10	common	common	ADJ
cana-3851	238	11	objects	object	NOUN
cana-3851	238	12	in	in	ADP
cana-3851	238	13	context	context	NOUN
cana-3851	238	14	(	(	PUNCT
cana-3851	238	15	coco	coco	PROPN
cana-3851	238	16	)	)	PUNCT
cana-3851	238	17	and	and	CCONJ
cana-3851	238	18	imagenet	imagenet	VERB
cana-3851	238	19	large	large	ADJ
cana-3851	238	20	scale	scale	NOUN
cana-3851	238	21	visual	visual	ADJ
cana-3851	238	22	recognition	recognition	NOUN
cana-3851	238	23	challenge	challenge	NOUN
cana-3851	238	24	(	(	PUNCT
cana-3851	238	25	ilsvrc	ilsvrc	PROPN
cana-3851	238	26	)	)	PUNCT
cana-3851	238	27	.	.	PUNCT
cana-3851	239	1	when	when	SCONJ
cana-3851	239	2	a	a	DET
cana-3851	239	3	deep	deep	ADJ
cana-3851	239	4	network	network	NOUN
cana-3851	239	5	's	's	PART
cana-3851	239	6	layer	layer	NOUN
cana-3851	239	7	count	count	NOUN
cana-3851	239	8	increases	increase	NOUN
cana-3851	239	9	,	,	PUNCT
cana-3851	239	10	a	a	DET
cana-3851	239	11	degradation	degradation	NOUN
cana-3851	239	12	issue	issue	NOUN
cana-3851	239	13	arises	arise	VERB
cana-3851	239	14	.	.	PUNCT
cana-3851	240	1	it	it	PRON
cana-3851	240	2	is	be	AUX
cana-3851	240	3	not	not	PART
cana-3851	240	4	possible	possible	ADJ
cana-3851	240	5	to	to	PART
cana-3851	240	6	properly	properly	ADV
cana-3851	240	7	update	update	VERB
cana-3851	240	8	the	the	DET
cana-3851	240	9	layer	layer	NOUN
cana-3851	240	10	's	's	PART
cana-3851	240	11	weights	weight	NOUN
cana-3851	240	12	to	to	ADP
cana-3851	240	13	the	the	DET
cana-3851	240	14	following	follow	VERB
cana-3851	240	15	layer	layer	NOUN
cana-3851	240	16	.	.	PUNCT
cana-3851	241	1	using	use	VERB
cana-3851	241	2	short	short	ADJ
cana-3851	241	3	connections	connection	NOUN
cana-3851	241	4	in	in	ADP
cana-3851	241	5	parallel	parallel	NOUN
cana-3851	241	6	with	with	ADP
cana-3851	241	7	the	the	DET
cana-3851	241	8	standard	standard	ADJ
cana-3851	241	9	convolutional	convolutional	ADJ
cana-3851	241	10	layers	layer	NOUN
cana-3851	241	11	,	,	PUNCT
cana-3851	241	12	resnet	resnet	NOUN
cana-3851	241	13	eliminates	eliminate	VERB
cana-3851	241	14	this	this	DET
cana-3851	241	15	degradation	degradation	NOUN
cana-3851	241	16	issue	issue	NOUN
cana-3851	241	17	.	.	PUNCT
cana-3851	242	1	in	in	ADP
cana-3851	242	2	figure	figure	NOUN
cana-3851	242	3	4	4	NUM
cana-3851	242	4	,	,	PUNCT
cana-3851	242	5	we	we	PRON
cana-3851	242	6	can	can	AUX
cana-3851	242	7	see	see	VERB
cana-3851	242	8	the	the	DET
cana-3851	242	9	lone	lone	ADJ
cana-3851	242	10	remaining	remain	VERB
cana-3851	242	11	construction	construction	NOUN
cana-3851	242	12	component	component	NOUN
cana-3851	242	13	that	that	PRON
cana-3851	242	14	has	have	VERB
cana-3851	242	15	a	a	DET
cana-3851	242	16	short	short	ADJ
cana-3851	242	17	link	link	NOUN
cana-3851	242	18	.	.	PUNCT
cana-3851	243	1	the	the	DET
cana-3851	243	2	equation	equation	NOUN
cana-3851	243	3	h(x	h(x	PROPN
cana-3851	243	4	)	)	PUNCT
cana-3851	243	5	that	that	PRON
cana-3851	243	6	defines	define	VERB
cana-3851	243	7	the	the	DET
cana-3851	243	8	residual	residual	ADJ
cana-3851	243	9	block	block	NOUN
cana-3851	243	10	's	's	PART
cana-3851	243	11	output	output	NOUN
cana-3851	243	12	is	be	AUX
cana-3851	243	13	as	as	SCONJ
cana-3851	243	14	follows	follow	VERB
cana-3851	243	15	:	:	PUNCT
cana-3851	243	16	𝐻(𝑥	𝐻(𝑥	NUM
cana-3851	243	17	)	)	PUNCT
cana-3851	243	18	=	=	PRON
cana-3851	243	19	𝐹(𝑥	𝐹(𝑥	X
cana-3851	243	20	)	)	PUNCT
cana-3851	243	21	+	+	CCONJ
cana-3851	243	22	𝑥	𝑥	X
cana-3851	243	23	(	(	PUNCT
cana-3851	243	24	2	2	NUM
cana-3851	243	25	)	)	PUNCT
cana-3851	243	26	the	the	DET
cana-3851	243	27	stocked	stock	VERB
cana-3851	243	28	nonlinear	nonlinear	ADJ
cana-3851	243	29	weight	weight	NOUN
cana-3851	243	30	layer	layer	NOUN
cana-3851	243	31	f(x	f(x	PROPN
cana-3851	243	32	)	)	PUNCT
cana-3851	243	33	is	be	AUX
cana-3851	243	34	given	give	VERB
cana-3851	243	35	as	as	ADP
cana-3851	243	36	:	:	PUNCT
cana-3851	243	37	𝐹(𝑥	𝐹(𝑥	NUM
cana-3851	243	38	)	)	PUNCT
cana-3851	243	39	=	=	SYM
cana-3851	243	40	𝐻(𝑥	𝐻(𝑥	NUM
cana-3851	243	41	)	)	PUNCT
cana-3851	243	42	–	–	PUNCT
cana-3851	243	43	𝑥	𝑥	X
cana-3851	243	44	(	(	PUNCT
cana-3851	243	45	3	3	NUM
cana-3851	243	46	)	)	PUNCT
cana-3851	243	47	figure4	figure4	NOUN
cana-3851	243	48	.	.	PUNCT
cana-3851	244	1	residual	residual	ADJ
cana-3851	244	2	network	network	NOUN
cana-3851	244	3	:	:	PUNCT
cana-3851	244	4	a	a	DET
cana-3851	244	5	building	building	NOUN
cana-3851	244	6	block	block	NOUN
cana-3851	244	7	.	.	PUNCT
cana-3851	245	1	the	the	DET
cana-3851	245	2	categorization	categorization	NOUN
cana-3851	245	3	of	of	ADP
cana-3851	245	4	brain	brain	NOUN
cana-3851	245	5	tumors	tumor	NOUN
cana-3851	245	6	is	be	AUX
cana-3851	245	7	carried	carry	VERB
cana-3851	245	8	out	out	ADP
cana-3851	245	9	in	in	ADP
cana-3851	245	10	this	this	DET
cana-3851	245	11	study	study	NOUN
cana-3851	245	12	using	use	VERB
cana-3851	245	13	the	the	DET
cana-3851	245	14	resnet50	resnet50	NOUN
cana-3851	245	15	model	model	NOUN
cana-3851	245	16	.	.	PUNCT
cana-3851	246	1	a	a	DET
cana-3851	246	2	7×7	7×7	NUM
cana-3851	246	3	convolution	convolution	NOUN
cana-3851	246	4	layer	layer	NOUN
cana-3851	246	5	,	,	PUNCT
cana-3851	246	6	a	a	DET
cana-3851	246	7	3×3	3×3	NUM
cana-3851	246	8	max	max	NOUN
cana-3851	246	9	-	-	PUNCT
cana-3851	246	10	pooling	pool	VERB
cana-3851	246	11	layer	layer	NOUN
cana-3851	246	12	,	,	PUNCT
cana-3851	246	13	16	16	NUM
cana-3851	246	14	residual	residual	ADJ
cana-3851	246	15	building	building	NOUN
cana-3851	246	16	blocks	block	NOUN
cana-3851	246	17	,	,	PUNCT
cana-3851	246	18	a	a	DET
cana-3851	246	19	7×7	7×7	NUM
cana-3851	246	20	average	average	ADJ
cana-3851	246	21	pooling	pool	VERB
cana-3851	246	22	layer	layer	NOUN
cana-3851	246	23	,	,	PUNCT
cana-3851	246	24	a	a	DET
cana-3851	246	25	new	new	ADJ
cana-3851	246	26	fully	fully	ADV
cana-3851	246	27	-	-	PUNCT
cana-3851	246	28	connected	connect	VERB
cana-3851	246	29	layer	layer	NOUN
cana-3851	246	30	,	,	PUNCT
cana-3851	246	31	and	and	CCONJ
cana-3851	246	32	segmentation	segmentation	NOUN
cana-3851	246	33	at	at	ADP
cana-3851	246	34	the	the	DET
cana-3851	246	35	final	final	ADJ
cana-3851	246	36	layer	layer	NOUN
cana-3851	246	37	make	make	VERB
cana-3851	246	38	up	up	ADP
cana-3851	246	39	the	the	DET
cana-3851	246	40	modified	modified	ADJ
cana-3851	246	41	resnet50	resnet50	NOUN
cana-3851	246	42	that	that	PRON
cana-3851	246	43	utilizes	utilize	VERB
cana-3851	246	44	transfer	transfer	NOUN
cana-3851	246	45	learning	learning	NOUN
cana-3851	246	46	,	,	PUNCT
cana-3851	246	47	as	as	SCONJ
cana-3851	246	48	shown	show	VERB
cana-3851	246	49	in	in	ADP
cana-3851	246	50	figure	figure	NOUN
cana-3851	246	51	5	5	NUM
cana-3851	246	52	.	.	PUNCT
cana-3851	247	1	for	for	ADP
cana-3851	247	2	this	this	DET
cana-3851	247	3	network	network	NOUN
cana-3851	247	4	,	,	PUNCT
cana-3851	247	5	224	224	NUM
cana-3851	247	6	x	x	SYM
cana-3851	247	7	224	224	NUM
cana-3851	247	8	x	x	SYM
cana-3851	247	9	3	3	NUM
cana-3851	247	10	is	be	AUX
cana-3851	247	11	the	the	DET
cana-3851	247	12	input	input	NOUN
cana-3851	247	13	image	image	NOUN
cana-3851	247	14	size	size	NOUN
cana-3851	247	15	.	.	PUNCT
cana-3851	248	1	communications	communication	NOUN
cana-3851	248	2	on	on	ADP
cana-3851	248	3	applied	apply	VERB
cana-3851	248	4	nonlinear	nonlinear	ADJ
cana-3851	248	5	analysis	analysis	NOUN
cana-3851	248	6	issn	issn	NOUN
cana-3851	248	7	:	:	PUNCT
cana-3851	248	8	1074	1074	NUM
cana-3851	248	9	-	-	PUNCT
cana-3851	248	10	133x	133x	NUM
cana-3851	248	11	vol	vol	NOUN
cana-3851	248	12	32	32	NUM
cana-3851	248	13	no	no	NOUN
cana-3851	248	14	.	.	PUNCT
cana-3851	249	1	9s	9s	NUM
cana-3851	249	2	(	(	PUNCT
cana-3851	249	3	2025	2025	NUM
cana-3851	249	4	)	)	PUNCT
cana-3851	249	5	224	224	NUM
cana-3851	249	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-3851	249	7	figure	figure	NOUN
cana-3851	249	8	5	5	NUM
cana-3851	249	9	.	.	NOUN
cana-3851	249	10	resnet50	resnet50	NOUN
cana-3851	249	11	architecture	architecture	NOUN
cana-3851	249	12	there	there	PRON
cana-3851	249	13	were	be	VERB
cana-3851	249	14	few	few	ADJ
cana-3851	249	15	blocks	block	NOUN
cana-3851	249	16	cut	cut	VERB
cana-3851	249	17	out	out	ADP
cana-3851	249	18	of	of	ADP
cana-3851	249	19	the	the	DET
cana-3851	249	20	current	current	ADJ
cana-3851	249	21	vgg-16	vgg-16	NOUN
cana-3851	249	22	model	model	NOUN
cana-3851	249	23	at	at	ADP
cana-3851	249	24	the	the	DET
cana-3851	249	25	encoder	encoder	NOUN
cana-3851	249	26	area	area	NOUN
cana-3851	249	27	.	.	PUNCT
cana-3851	250	1	the	the	DET
cana-3851	250	2	pre	pre	ADJ
cana-3851	250	3	-	-	ADJ
cana-3851	250	4	trained	train	VERB
cana-3851	250	5	model	model	NOUN
cana-3851	250	6	's	's	PART
cana-3851	250	7	first	first	ADJ
cana-3851	250	8	layers	layer	NOUN
cana-3851	250	9	were	be	AUX
cana-3851	250	10	removed	remove	VERB
cana-3851	250	11	.	.	PUNCT
cana-3851	251	1	basic	basic	ADJ
cana-3851	251	2	characteristics	characteristic	NOUN
cana-3851	251	3	,	,	PUNCT
cana-3851	251	4	such	such	ADJ
cana-3851	251	5	as	as	ADP
cana-3851	251	6	horizontal	horizontal	ADJ
cana-3851	251	7	and	and	CCONJ
cana-3851	251	8	vertical	vertical	ADJ
cana-3851	251	9	edges	edge	NOUN
cana-3851	251	10	,	,	PUNCT
cana-3851	251	11	are	be	AUX
cana-3851	251	12	detected	detect	VERB
cana-3851	251	13	by	by	ADP
cana-3851	251	14	the	the	DET
cana-3851	251	15	earliest	early	ADJ
cana-3851	251	16	layers	layer	NOUN
cana-3851	251	17	of	of	ADP
cana-3851	251	18	the	the	DET
cana-3851	251	19	model	model	NOUN
cana-3851	251	20	.	.	PUNCT
cana-3851	252	1	the	the	DET
cana-3851	252	2	further	far	ADV
cana-3851	252	3	you	you	PRON
cana-3851	252	4	go	go	VERB
cana-3851	252	5	into	into	ADP
cana-3851	252	6	the	the	DET
cana-3851	252	7	network	network	NOUN
cana-3851	252	8	,	,	PUNCT
cana-3851	252	9	the	the	DET
cana-3851	252	10	more	more	ADV
cana-3851	252	11	complicated	complicated	ADJ
cana-3851	252	12	the	the	DET
cana-3851	252	13	model	model	NOUN
cana-3851	252	14	becomes	become	VERB
cana-3851	252	15	,	,	PUNCT
cana-3851	252	16	which	which	PRON
cana-3851	252	17	makes	make	VERB
cana-3851	252	18	feature	feature	NOUN
cana-3851	252	19	extraction	extraction	NOUN
cana-3851	252	20	much	much	ADV
cana-3851	252	21	easier	easy	ADJ
cana-3851	252	22	.	.	PUNCT
cana-3851	253	1	for	for	ADP
cana-3851	253	2	layers	layer	NOUN
cana-3851	253	3	that	that	PRON
cana-3851	253	4	are	be	AUX
cana-3851	253	5	not	not	PART
cana-3851	253	6	sequential	sequential	ADJ
cana-3851	253	7	,	,	PUNCT
cana-3851	253	8	concatenation	concatenation	NOUN
cana-3851	253	9	skip	skip	ADJ
cana-3851	253	10	connections	connection	NOUN
cana-3851	253	11	are	be	AUX
cana-3851	253	12	used	use	VERB
cana-3851	253	13	.	.	PUNCT
cana-3851	254	1	dense	dense	ADJ
cana-3851	254	2	blocks	block	NOUN
cana-3851	254	3	provide	provide	VERB
cana-3851	254	4	an	an	DET
cana-3851	254	5	extra	extra	ADJ
cana-3851	254	6	benefit	benefit	NOUN
cana-3851	254	7	:	:	PUNCT
cana-3851	254	8	access	access	NOUN
cana-3851	254	9	to	to	ADP
cana-3851	254	10	a	a	DET
cana-3851	254	11	massive	massive	ADJ
cana-3851	254	12	quantity	quantity	NOUN
cana-3851	254	13	of	of	ADP
cana-3851	254	14	feature	feature	NOUN
cana-3851	254	15	channels	channel	NOUN
cana-3851	254	16	in	in	ADP
cana-3851	254	17	the	the	DET
cana-3851	254	18	network	network	NOUN
cana-3851	254	19	's	's	PART
cana-3851	254	20	final	final	ADJ
cana-3851	254	21	layers	layer	NOUN
cana-3851	254	22	,	,	PUNCT
cana-3851	254	23	which	which	PRON
cana-3851	254	24	allows	allow	VERB
cana-3851	254	25	for	for	ADP
cana-3851	254	26	more	more	ADJ
cana-3851	254	27	compact	compact	ADJ
cana-3851	254	28	models	model	NOUN
cana-3851	254	29	and	and	CCONJ
cana-3851	254	30	drastically	drastically	ADV
cana-3851	254	31	increased	increase	VERB
cana-3851	254	32	feature	feature	NOUN
cana-3851	254	33	re	re	NOUN
cana-3851	254	34	-	-	NOUN
cana-3851	254	35	usability	usability	NOUN
cana-3851	254	36	.	.	PUNCT
cana-3851	255	1	to	to	PART
cana-3851	255	2	predict	predict	VERB
cana-3851	255	3	what	what	PRON
cana-3851	255	4	will	will	AUX
cana-3851	255	5	be	be	AUX
cana-3851	255	6	in	in	ADP
cana-3851	255	7	the	the	DET
cana-3851	255	8	output	output	NOUN
cana-3851	255	9	region	region	NOUN
cana-3851	255	10	,	,	PUNCT
cana-3851	255	11	the	the	DET
cana-3851	255	12	model	model	NOUN
cana-3851	255	13	looks	look	VERB
cana-3851	255	14	at	at	ADP
cana-3851	255	15	the	the	DET
cana-3851	255	16	segmentation	segmentation	NOUN
cana-3851	255	17	map	map	NOUN
cana-3851	255	18	of	of	ADP
cana-3851	255	19	the	the	DET
cana-3851	255	20	output	output	NOUN
cana-3851	255	21	[	[	X
cana-3851	255	22	23	23	NUM
cana-3851	255	23	]	]	PUNCT
cana-3851	255	24	.	.	PUNCT
cana-3851	256	1	the	the	DET
cana-3851	256	2	goal	goal	NOUN
cana-3851	256	3	is	be	AUX
cana-3851	256	4	to	to	PART
cana-3851	256	5	train	train	VERB
cana-3851	256	6	a	a	DET
cana-3851	256	7	resnet50	resnet50	NOUN
cana-3851	256	8	model	model	NOUN
cana-3851	256	9	using	use	VERB
cana-3851	256	10	vgg16	vgg16	NOUN
cana-3851	256	11	to	to	PART
cana-3851	256	12	differentiate	differentiate	VERB
cana-3851	256	13	between	between	ADP
cana-3851	256	14	normal	normal	ADJ
cana-3851	256	15	and	and	CCONJ
cana-3851	256	16	abnormal	abnormal	ADJ
cana-3851	256	17	brain	brain	NOUN
cana-3851	256	18	mri	mri	NOUN
cana-3851	256	19	images	image	NOUN
cana-3851	256	20	.	.	PUNCT
cana-3851	257	1	the	the	DET
cana-3851	257	2	pre	pre	ADJ
cana-3851	257	3	-	-	ADJ
cana-3851	257	4	trained	train	VERB
cana-3851	257	5	resnet50	resnet50	NOUN
cana-3851	257	6	model	model	NOUN
cana-3851	257	7	provides	provide	VERB
cana-3851	257	8	a	a	DET
cana-3851	257	9	solid	solid	ADJ
cana-3851	257	10	foundation	foundation	NOUN
cana-3851	257	11	for	for	ADP
cana-3851	257	12	brain	brain	NOUN
cana-3851	257	13	tumor	tumor	NOUN
cana-3851	257	14	diagnosis	diagnosis	NOUN
cana-3851	257	15	,	,	PUNCT
cana-3851	257	16	and	and	CCONJ
cana-3851	257	17	it	it	PRON
cana-3851	257	18	may	may	AUX
cana-3851	257	19	be	be	AUX
cana-3851	257	20	fine	fine	ADV
cana-3851	257	21	-	-	PUNCT
cana-3851	257	22	tuned	tune	VERB
cana-3851	257	23	using	use	VERB
cana-3851	257	24	a	a	DET
cana-3851	257	25	new	new	ADJ
cana-3851	257	26	dataset	dataset	NOUN
cana-3851	257	27	of	of	ADP
cana-3851	257	28	mri	mri	NOUN
cana-3851	257	29	images	image	NOUN
cana-3851	257	30	to	to	PART
cana-3851	257	31	make	make	VERB
cana-3851	257	32	it	it	PRON
cana-3851	257	33	suit	suit	VERB
cana-3851	257	34	the	the	DET
cana-3851	257	35	task	task	NOUN
cana-3851	257	36	at	at	ADP
cana-3851	257	37	hand	hand	NOUN
cana-3851	257	38	.	.	PUNCT
cana-3851	258	1	this	this	DET
cana-3851	258	2	approach	approach	NOUN
cana-3851	258	3	has	have	AUX
cana-3851	258	4	effectively	effectively	ADV
cana-3851	258	5	used	use	VERB
cana-3851	258	6	magnetic	magnetic	ADJ
cana-3851	258	7	resonance	resonance	NOUN
cana-3851	258	8	imaging	imaging	NOUN
cana-3851	258	9	(	(	PUNCT
cana-3851	258	10	mris	mris	PROPN
cana-3851	258	11	)	)	PUNCT
cana-3851	258	12	to	to	PART
cana-3851	258	13	accurately	accurately	ADV
cana-3851	258	14	detect	detect	VERB
cana-3851	258	15	and	and	CCONJ
cana-3851	258	16	separate	separate	ADJ
cana-3851	258	17	bts	bt	NOUN
cana-3851	258	18	.	.	PUNCT
cana-3851	259	1	algorithm1	algorithm1	PROPN
cana-3851	259	2	.	.	PROPN
cana-3851	259	3	vgg16+resnet50	vgg16+resnet50	PROPN
cana-3851	259	4	algorithm	algorithm	PROPN
cana-3851	259	5	1	1	NUM
cana-3851	259	6	.	.	PUNCT
cana-3851	259	7	starts	start	VERB
cana-3851	259	8	2	2	NUM
cana-3851	259	9	.	.	PUNCT
cana-3851	259	10	loading	load	VERB
cana-3851	259	11	the	the	DET
cana-3851	259	12	dataset	dataset	NOUN
cana-3851	259	13	of	of	ADP
cana-3851	259	14	brain	brain	NOUN
cana-3851	259	15	image	image	NOUN
cana-3851	259	16	3	3	NUM
cana-3851	259	17	.	.	PUNCT
cana-3851	259	18	pre	pre	ADJ
cana-3851	259	19	-	-	ADJ
cana-3851	259	20	processing	processing	ADJ
cana-3851	259	21	histogram	histogram	NOUN
cana-3851	259	22	equalization	equalization	NOUN
cana-3851	259	23	4	4	NUM
cana-3851	259	24	.	.	PUNCT
cana-3851	260	1	i	i	PRON
cana-3851	260	2	=	=	SYM
cana-3851	260	3	imread("gfg.jfif	imread("gfg.jfif	PROPN
cana-3851	260	4	"	"	PUNCT
cana-3851	260	5	)	)	PUNCT
cana-3851	260	6	;	;	PUNCT
cana-3851	260	7	5	5	X
cana-3851	260	8	.	.	X
cana-3851	260	9	figure	figure	NOUN
cana-3851	260	10	6	6	NUM
cana-3851	260	11	.	.	PUNCT
cana-3851	261	1	subplot(1,3,1	subplot(1,3,1	NOUN
cana-3851	261	2	)	)	PUNCT
cana-3851	261	3	7	7	NUM
cana-3851	261	4	.	.	X
cana-3851	261	5	imshow(i	imshow(i	NUM
cana-3851	261	6	)	)	PUNCT
cana-3851	261	7	8	8	NUM
cana-3851	261	8	.	.	PUNCT
cana-3851	261	9	subplot(1,3,2:3	subplot(1,3,2:3	VERB
cana-3851	261	10	)	)	PUNCT
cana-3851	261	11	9	9	NUM
cana-3851	261	12	.	.	X
cana-3851	262	1	imhist(i	imhist(i	X
cana-3851	262	2	)	)	PUNCT
cana-3851	262	3	10	10	NUM
cana-3851	262	4	.	.	PUNCT
cana-3851	263	1	data	datum	NOUN
cana-3851	263	2	augmentaion	augmentaion	NOUN
cana-3851	263	3	using	use	VERB
cana-3851	263	4	cnn	cnn	PROPN
cana-3851	263	5	model	model	NOUN
cana-3851	263	6	11	11	NUM
cana-3851	263	7	.	.	PUNCT
cana-3851	264	1	transfer	transfer	VERB
cana-3851	264	2	learning_model	learning_model	PROPN
cana-3851	264	3	t	t	PROPN
cana-3851	264	4	=	=	PUNCT
cana-3851	265	1	[	[	X
cana-3851	265	2	a1,a2	a1,a2	PROPN
cana-3851	265	3	,	,	PUNCT
cana-3851	265	4	.	.	PUNCT
cana-3851	265	5	.	.	PUNCT
cana-3851	265	6	.	.	PUNCT
cana-3851	266	1	ak	ak	PROPN
cana-3851	266	2	]	]	PUNCT
cana-3851	266	3	12	12	NUM
cana-3851	266	4	.	.	PUNCT
cana-3851	267	1	for	for	ADP
cana-3851	267	2	j	j	PROPN
cana-3851	267	3	=	=	SYM
cana-3851	267	4	1	1	NUM
cana-3851	267	5	to	to	PART
cana-3851	267	6	m	m	PROPN
cana-3851	267	7	do	do	AUX
cana-3851	267	8	13	13	NUM
cana-3851	267	9	.	.	PUNCT
cana-3851	268	1	predict	predict	VERB
cana-3851	268	2	,	,	PUNCT
cana-3851	268	3	q	q	X
cana-3851	268	4	=	=	SYM
cana-3851	268	5	generate(o	generate(o	PROPN
cana-3851	268	6	)	)	PUNCT
cana-3851	268	7	14	14	NUM
cana-3851	268	8	.	.	PUNCT
cana-3851	269	1	z	z	NOUN
cana-3851	269	2	=	=	PRON
cana-3851	269	3	add	add	VERB
cana-3851	269	4	(	(	PUNCT
cana-3851	269	5	q	q	INTJ
cana-3851	269	6	,	,	PUNCT
cana-3851	269	7	along	along	ADP
cana-3851	269	8	c	c	NOUN
cana-3851	269	9	axis	axis	NOUN
cana-3851	269	10	)	)	PUNCT
cana-3851	269	11	15	15	NUM
cana-3851	269	12	.	.	PUNCT
cana-3851	270	1	ic	ic	PUNCT
cana-3851	271	1	=	=	NOUN
cana-3851	271	2	index_max	index_max	X
cana-3851	271	3	(	(	PUNCT
cana-3851	271	4	z	z	NOUN
cana-3851	271	5	,	,	PUNCT
cana-3851	271	6	along	along	ADP
cana-3851	271	7	d	d	PRON
cana-3851	271	8	axis	axis	NOUN
cana-3851	271	9	)	)	PUNCT
cana-3851	271	10	16	16	NUM
cana-3851	271	11	.	.	PUNCT
cana-3851	272	1	print(accuracy(i),segmentation_report	print(accuracy(i),segmentation_report	NOUN
cana-3851	272	2	)	)	PUNCT
cana-3851	272	3	;	;	PUNCT
cana-3851	273	1	17	17	NUM
cana-3851	273	2	.	.	NOUN
cana-3851	273	3	end	end	NOUN
cana-3851	273	4	communications	communication	NOUN
cana-3851	273	5	on	on	ADP
cana-3851	273	6	applied	apply	VERB
cana-3851	273	7	nonlinear	nonlinear	ADJ
cana-3851	273	8	analysis	analysis	NOUN
cana-3851	273	9	issn	issn	NOUN
cana-3851	273	10	:	:	PUNCT
cana-3851	273	11	1074	1074	NUM
cana-3851	273	12	-	-	PUNCT
cana-3851	273	13	133x	133x	NUM
cana-3851	273	14	vol	vol	NOUN
cana-3851	273	15	32	32	NUM
cana-3851	273	16	no	no	NOUN
cana-3851	273	17	.	.	PUNCT
cana-3851	274	1	9s	9s	NUM
cana-3851	274	2	(	(	PUNCT
cana-3851	274	3	2025	2025	NUM
cana-3851	274	4	)	)	PUNCT
cana-3851	274	5	225	225	NUM
cana-3851	275	1	https://internationalpubls.com	https://internationalpubls.com	X
cana-3851	275	2	v.results	v.result	VERB
cana-3851	275	3	the	the	DET
cana-3851	275	4	capacity	capacity	NOUN
cana-3851	275	5	to	to	PART
cana-3851	275	6	accurately	accurately	ADV
cana-3851	275	7	distinguish	distinguish	VERB
cana-3851	275	8	between	between	ADP
cana-3851	275	9	the	the	DET
cana-3851	275	10	various	various	ADJ
cana-3851	275	11	forms	form	NOUN
cana-3851	275	12	of	of	ADP
cana-3851	275	13	brain	brain	NOUN
cana-3851	275	14	tumors	tumor	NOUN
cana-3851	275	15	is	be	AUX
cana-3851	275	16	dependent	dependent	ADJ
cana-3851	275	17	on	on	ADP
cana-3851	275	18	accuracy	accuracy	NOUN
cana-3851	275	19	.	.	PUNCT
cana-3851	276	1	the	the	DET
cana-3851	276	2	following	follow	VERB
cana-3851	276	3	relations	relation	NOUN
cana-3851	276	4	are	be	AUX
cana-3851	276	5	used	use	VERB
cana-3851	276	6	to	to	PART
cana-3851	276	7	determine	determine	VERB
cana-3851	276	8	the	the	DET
cana-3851	276	9	fraction	fraction	NOUN
cana-3851	276	10	of	of	ADP
cana-3851	276	11	analyzed	analyze	VERB
cana-3851	276	12	examples	example	NOUN
cana-3851	276	13	with	with	ADP
cana-3851	276	14	true	true	ADJ
cana-3851	276	15	positives	positive	NOUN
cana-3851	276	16	and	and	CCONJ
cana-3851	276	17	true	true	ADJ
cana-3851	276	18	negatives	negative	NOUN
cana-3851	276	19	,	,	PUNCT
cana-3851	276	20	which	which	PRON
cana-3851	276	21	allows	allow	VERB
cana-3851	276	22	us	we	PRON
cana-3851	276	23	to	to	PART
cana-3851	276	24	quantify	quantify	VERB
cana-3851	276	25	the	the	DET
cana-3851	276	26	test	test	NOUN
cana-3851	276	27	's	's	PART
cana-3851	276	28	accuracy	accuracy	NOUN
cana-3851	276	29	:	:	PUNCT
cana-3851	277	1	𝐴𝑐𝑐𝑢𝑟𝑎𝑐𝑦	𝐴𝑐𝑐𝑢𝑟𝑎𝑐𝑦	PROPN
cana-3851	277	2	=	=	PROPN
cana-3851	278	1	tp	tp	ADP
cana-3851	278	2	+	+	NUM
cana-3851	278	3	tn	tn	NOUN
cana-3851	278	4	tp	tp	NOUN
cana-3851	278	5	+	+	CCONJ
cana-3851	278	6	fp	fp	PROPN
cana-3851	278	7	+	+	NUM
cana-3851	278	8	tn	tn	PROPN
cana-3851	279	1	+	+	CCONJ
cana-3851	279	2	fn	fn	PROPN
cana-3851	279	3	(	(	PUNCT
cana-3851	279	4	3	3	NUM
cana-3851	279	5	)	)	PUNCT
cana-3851	279	6	𝑅𝑒𝑐𝑎𝑙𝑙	𝑅𝑒𝑐𝑎𝑙𝑙	PROPN
cana-3851	279	7	=	=	SYM
cana-3851	279	8	𝑇𝑃/𝑇𝑃	𝑇𝑃/𝑇𝑃	X
cana-3851	279	9	+	+	X
cana-3851	279	10	𝐹𝑁	𝐹𝑁	PROPN
cana-3851	279	11	(	(	PUNCT
cana-3851	279	12	4	4	NUM
cana-3851	279	13	)	)	PUNCT
cana-3851	279	14	the	the	DET
cana-3851	279	15	capacity	capacity	NOUN
cana-3851	279	16	of	of	ADP
cana-3851	279	17	the	the	DET
cana-3851	279	18	model	model	NOUN
cana-3851	279	19	to	to	PART
cana-3851	279	20	correctly	correctly	ADV
cana-3851	279	21	identify	identify	VERB
cana-3851	279	22	the	the	DET
cana-3851	279	23	specific	specific	ADJ
cana-3851	279	24	kind	kind	NOUN
cana-3851	279	25	of	of	ADP
cana-3851	279	26	brain	brain	NOUN
cana-3851	279	27	tumor	tumor	NOUN
cana-3851	279	28	is	be	AUX
cana-3851	279	29	called	call	VERB
cana-3851	279	30	specificity	specificity	NOUN
cana-3851	279	31	,	,	PUNCT
cana-3851	279	32	and	and	CCONJ
cana-3851	279	33	it	it	PRON
cana-3851	279	34	is	be	AUX
cana-3851	279	35	calculated	calculate	VERB
cana-3851	279	36	as	as	ADP
cana-3851	279	37	:	:	PUNCT
cana-3851	279	38	𝑆𝑝𝑒𝑐𝑖𝑓𝑖𝑐𝑖𝑡𝑦	𝑆𝑝𝑒𝑐𝑖𝑓𝑖𝑐𝑖𝑡𝑦	PROPN
cana-3851	279	39	=	=	SYM
cana-3851	279	40	𝑇𝑁/𝑇𝑁	𝑇𝑁/𝑇𝑁	PUNCT
cana-3851	280	1	+	+	CCONJ
cana-3851	280	2	𝐹𝑃	𝐹𝑃	NOUN
cana-3851	280	3	(	(	PUNCT
cana-3851	280	4	5	5	X
cana-3851	280	5	)	)	PUNCT
cana-3851	280	6	it	it	PRON
cana-3851	280	7	is	be	AUX
cana-3851	280	8	possible	possible	ADJ
cana-3851	280	9	to	to	PART
cana-3851	280	10	calculate	calculate	VERB
cana-3851	280	11	precision	precision	NOUN
cana-3851	280	12	,	,	PUNCT
cana-3851	280	13	the	the	DET
cana-3851	280	14	genuine	genuine	ADJ
cana-3851	280	15	positive	positive	ADJ
cana-3851	280	16	measure	measure	NOUN
cana-3851	280	17	,	,	PUNCT
cana-3851	280	18	using	use	VERB
cana-3851	280	19	the	the	DET
cana-3851	280	20	following	follow	VERB
cana-3851	280	21	relation	relation	NOUN
cana-3851	280	22	:	:	PUNCT
cana-3851	281	1	𝑃𝑟𝑒𝑐𝑖𝑠𝑖𝑜𝑛	𝑃𝑟𝑒𝑐𝑖𝑠𝑖𝑜𝑛	PROPN
cana-3851	281	2	=	=	SYM
cana-3851	281	3	t	t	PROPN
cana-3851	281	4	p	p	X
cana-3851	281	5	t	t	PROPN
cana-3851	281	6	p	p	X
cana-3851	282	1	+	+	X
cana-3851	282	2	fp	fp	X
cana-3851	282	3	(	(	PUNCT
cana-3851	282	4	6	6	NUM
cana-3851	282	5	)	)	PUNCT
cana-3851	282	6	v.conclusion	v.conclusion	NOUN
cana-3851	282	7	a	a	DET
cana-3851	282	8	brain	brain	NOUN
cana-3851	282	9	tumor	tumor	NOUN
cana-3851	282	10	is	be	AUX
cana-3851	282	11	the	the	DET
cana-3851	282	12	growth	growth	NOUN
cana-3851	282	13	of	of	ADP
cana-3851	282	14	abnormal	abnormal	ADJ
cana-3851	282	15	brain	brain	NOUN
cana-3851	282	16	cells	cell	NOUN
cana-3851	282	17	in	in	ADP
cana-3851	282	18	a	a	DET
cana-3851	282	19	person	person	NOUN
cana-3851	282	20	.	.	PUNCT
cana-3851	283	1	researchers	researcher	NOUN
cana-3851	283	2	still	still	ADV
cana-3851	283	3	do	do	AUX
cana-3851	283	4	n't	not	PART
cana-3851	283	5	fully	fully	ADV
cana-3851	283	6	understand	understand	VERB
cana-3851	283	7	what	what	PRON
cana-3851	283	8	causes	cause	VERB
cana-3851	283	9	brain	brain	NOUN
cana-3851	283	10	tumors	tumor	NOUN
cana-3851	283	11	,	,	PUNCT
cana-3851	283	12	but	but	CCONJ
cana-3851	283	13	they	they	PRON
cana-3851	283	14	have	have	AUX
cana-3851	283	15	identified	identify	VERB
cana-3851	283	16	several	several	ADJ
cana-3851	283	17	risk	risk	NOUN
cana-3851	283	18	indicators	indicator	NOUN
cana-3851	283	19	that	that	PRON
cana-3851	283	20	may	may	AUX
cana-3851	283	21	be	be	AUX
cana-3851	283	22	used	use	VERB
cana-3851	283	23	to	to	PART
cana-3851	283	24	track	track	VERB
cana-3851	283	25	the	the	DET
cana-3851	283	26	progression	progression	NOUN
cana-3851	283	27	of	of	ADP
cana-3851	283	28	a	a	DET
cana-3851	283	29	tumor	tumor	NOUN
cana-3851	283	30	.	.	PUNCT
cana-3851	284	1	a	a	DET
cana-3851	284	2	glioma	glioma	NOUN
cana-3851	284	3	is	be	AUX
cana-3851	284	4	a	a	DET
cana-3851	284	5	tumor	tumor	NOUN
cana-3851	284	6	that	that	PRON
cana-3851	284	7	develops	develop	VERB
cana-3851	284	8	in	in	ADP
cana-3851	284	9	the	the	DET
cana-3851	284	10	brain	brain	NOUN
cana-3851	284	11	or	or	CCONJ
cana-3851	284	12	spinal	spinal	NOUN
cana-3851	284	13	cord	cord	NOUN
cana-3851	284	14	;	;	PUNCT
cana-3851	284	15	a	a	DET
cana-3851	284	16	meningioma	meningioma	NOUN
cana-3851	284	17	is	be	AUX
cana-3851	284	18	a	a	DET
cana-3851	284	19	tumor	tumor	NOUN
cana-3851	284	20	that	that	PRON
cana-3851	284	21	develops	develop	VERB
cana-3851	284	22	in	in	ADP
cana-3851	284	23	the	the	DET
cana-3851	284	24	meninges	meninge	NOUN
cana-3851	284	25	.	.	PUNCT
cana-3851	285	1	pituitary	pituitary	ADJ
cana-3851	285	2	tumors	tumor	NOUN
cana-3851	285	3	are	be	AUX
cana-3851	285	4	the	the	DET
cana-3851	285	5	result	result	NOUN
cana-3851	285	6	of	of	ADP
cana-3851	285	7	an	an	DET
cana-3851	285	8	aberrant	aberrant	ADJ
cana-3851	285	9	proliferation	proliferation	NOUN
cana-3851	285	10	of	of	ADP
cana-3851	285	11	cells	cell	NOUN
cana-3851	285	12	inside	inside	ADP
cana-3851	285	13	the	the	DET
cana-3851	285	14	pituitary	pituitary	ADJ
cana-3851	285	15	gland	gland	NOUN
cana-3851	285	16	.	.	PUNCT
cana-3851	286	1	when	when	SCONJ
cana-3851	286	2	it	it	PRON
cana-3851	286	3	comes	come	VERB
cana-3851	286	4	to	to	ADP
cana-3851	286	5	segmenting	segment	VERB
cana-3851	286	6	brain	brain	NOUN
cana-3851	286	7	tumors	tumor	NOUN
cana-3851	286	8	in	in	ADP
cana-3851	286	9	mri	mri	NOUN
cana-3851	286	10	images	image	NOUN
cana-3851	286	11	,	,	PUNCT
cana-3851	286	12	we	we	PRON
cana-3851	286	13	provide	provide	VERB
cana-3851	286	14	a	a	DET
cana-3851	286	15	hybrid	hybrid	ADJ
cana-3851	286	16	model	model	NOUN
cana-3851	286	17	that	that	PRON
cana-3851	286	18	combines	combine	VERB
cana-3851	286	19	vgg16	vgg16	NOUN
cana-3851	286	20	with	with	ADP
cana-3851	286	21	resnet50	resnet50	NOUN
cana-3851	286	22	in	in	ADP
cana-3851	286	23	this	this	DET
cana-3851	286	24	study	study	NOUN
cana-3851	286	25	.	.	PUNCT
cana-3851	287	1	compared	compare	VERB
cana-3851	287	2	to	to	ADP
cana-3851	287	3	other	other	ADJ
cana-3851	287	4	models	model	NOUN
cana-3851	287	5	already	already	ADV
cana-3851	287	6	available	available	ADJ
cana-3851	287	7	,	,	PUNCT
cana-3851	287	8	our	our	PRON
cana-3851	287	9	proposed	propose	VERB
cana-3851	287	10	technique	technique	NOUN
cana-3851	287	11	outperforms	outperform	VERB
cana-3851	287	12	them	they	PRON
cana-3851	287	13	in	in	ADP
cana-3851	287	14	terms	term	NOUN
cana-3851	287	15	of	of	ADP
cana-3851	287	16	accuracy	accuracy	NOUN
cana-3851	287	17	and	and	CCONJ
cana-3851	287	18	performance	performance	NOUN
cana-3851	287	19	.	.	PUNCT
cana-3851	288	1	eventually	eventually	ADV
cana-3851	288	2	,	,	PUNCT
cana-3851	288	3	we	we	PRON
cana-3851	288	4	'll	will	AUX
cana-3851	288	5	be	be	AUX
cana-3851	288	6	able	able	ADJ
cana-3851	288	7	to	to	PART
cana-3851	288	8	use	use	VERB
cana-3851	288	9	more	more	ADV
cana-3851	288	10	advanced	advanced	ADJ
cana-3851	288	11	transfer	transfer	NOUN
cana-3851	288	12	learning	learn	VERB
cana-3851	288	13	algorithms	algorithm	NOUN
cana-3851	288	14	for	for	ADP
cana-3851	288	15	more	more	ADV
cana-3851	288	16	precise	precise	ADJ
cana-3851	288	17	brain	brain	NOUN
cana-3851	288	18	image	image	NOUN
cana-3851	288	19	segmentation	segmentation	NOUN
cana-3851	288	20	.	.	PUNCT
cana-3851	289	1	references	reference	NOUN
cana-3851	289	2	[	[	X
cana-3851	289	3	1	1	NUM
cana-3851	289	4	]	]	PUNCT
cana-3851	289	5	ramakrishna	ramakrishna	PROPN
cana-3851	289	6	sajja	sajja	PROPN
cana-3851	289	7	,	,	PUNCT
cana-3851	289	8	v.	v.	PROPN
cana-3851	289	9	,	,	PUNCT
cana-3851	289	10	&	&	CCONJ
cana-3851	289	11	kumar	kumar	PROPN
cana-3851	289	12	kalluri	kalluri	PROPN
cana-3851	289	13	,	,	PUNCT
cana-3851	289	14	h.	h.	PROPN
cana-3851	289	15	(	(	PUNCT
cana-3851	289	16	2021	2021	NUM
cana-3851	289	17	)	)	PUNCT
cana-3851	289	18	.	.	PUNCT
cana-3851	290	1	classification	classification	NOUN
cana-3851	290	2	of	of	ADP
cana-3851	290	3	brain	brain	NOUN
cana-3851	290	4	tumors	tumor	NOUN
cana-3851	290	5	using	use	VERB
cana-3851	290	6	fuzzy	fuzzy	ADJ
cana-3851	290	7	c	c	NOUN
cana-3851	290	8	-	-	PUNCT
cana-3851	290	9	means	means	NOUN
cana-3851	290	10	and	and	CCONJ
cana-3851	290	11	vgg16	vgg16	PROPN
cana-3851	290	12	.	.	PUNCT
cana-3851	291	1	turkish	turkish	ADJ
cana-3851	291	2	journal	journal	NOUN
cana-3851	291	3	of	of	ADP
cana-3851	291	4	computer	computer	NOUN
cana-3851	291	5	and	and	CCONJ
cana-3851	291	6	mathematics	mathematic	NOUN
cana-3851	291	7	education	education	NOUN
cana-3851	291	8	,	,	PUNCT
cana-3851	291	9	12(9	12(9	NUM
cana-3851	291	10	)	)	PUNCT
cana-3851	291	11	,	,	PUNCT
cana-3851	291	12	2103–2113	2103–2113	NUM
cana-3851	291	13	.	.	PUNCT
cana-3851	292	1	https://turcomat.org/index.php/turkbilmat/article/view/3680	https://turcomat.org/index.php/turkbilmat/article/view/3680	X
cana-3851	292	2	[	[	X
cana-3851	292	3	2	2	NUM
cana-3851	292	4	]	]	PUNCT
cana-3851	292	5	sharma	sharma	PROPN
cana-3851	292	6	,	,	PUNCT
cana-3851	292	7	a.	a.	PROPN
cana-3851	292	8	k.	k.	PROPN
cana-3851	292	9	,	,	PUNCT
cana-3851	292	10	nandal	nandal	PROPN
cana-3851	292	11	,	,	PUNCT
cana-3851	292	12	a.	a.	NOUN
cana-3851	292	13	,	,	PUNCT
cana-3851	292	14	dhaka	dhaka	PROPN
cana-3851	292	15	,	,	PUNCT
cana-3851	292	16	a.	a.	NOUN
cana-3851	292	17	,	,	PUNCT
cana-3851	292	18	koundal	koundal	NOUN
cana-3851	292	19	,	,	PUNCT
cana-3851	292	20	d.	d.	PROPN
cana-3851	292	21	,	,	PUNCT
cana-3851	292	22	bogatinoska	bogatinoska	VERB
cana-3851	292	23	,	,	PUNCT
cana-3851	292	24	d.	d.	PROPN
cana-3851	292	25	c.	c.	PROPN
cana-3851	292	26	,	,	PUNCT
cana-3851	292	27	&	&	CCONJ
cana-3851	292	28	alyami	alyami	NOUN
cana-3851	292	29	,	,	PUNCT
cana-3851	292	30	h.	h.	PROPN
cana-3851	292	31	(	(	PUNCT
cana-3851	292	32	2022	2022	NUM
cana-3851	292	33	)	)	PUNCT
cana-3851	292	34	.	.	PUNCT
cana-3851	293	1	enhanced	enhance	VERB
cana-3851	293	2	watershed	watershed	ADJ
cana-3851	293	3	segmentation	segmentation	NOUN
cana-3851	293	4	algorithm	algorithm	NOUN
cana-3851	293	5	-	-	PUNCT
cana-3851	293	6	based	base	VERB
cana-3851	293	7	modified	modified	ADJ
cana-3851	293	8	resnet50	resnet50	NOUN
cana-3851	293	9	model	model	NOUN
cana-3851	293	10	for	for	ADP
cana-3851	293	11	brain	brain	NOUN
cana-3851	293	12	tumor	tumor	NOUN
cana-3851	293	13	detection	detection	NOUN
cana-3851	293	14	.	.	PUNCT
cana-3851	294	1	biomed	biome	VERB
cana-3851	294	2	research	research	NOUN
cana-3851	294	3	international	international	NOUN
cana-3851	294	4	,	,	PUNCT
cana-3851	294	5	2022	2022	NUM
cana-3851	294	6	.	.	PUNCT
cana-3851	295	1	[	[	X
cana-3851	295	2	3	3	NUM
cana-3851	295	3	]	]	X
cana-3851	295	4	khanna	khanna	PROPN
cana-3851	295	5	,	,	PUNCT
cana-3851	295	6	s.	s.	PROPN
cana-3851	295	7	(	(	PUNCT
cana-3851	295	8	2019	2019	NUM
cana-3851	295	9	)	)	PUNCT
cana-3851	295	10	.	.	PUNCT
cana-3851	296	1	brain	brain	NOUN
cana-3851	296	2	tumor	tumor	NOUN
cana-3851	296	3	segmentation	segmentation	NOUN
cana-3851	296	4	using	use	VERB
cana-3851	296	5	deep	deep	ADJ
cana-3851	296	6	transfer	transfer	NOUN
cana-3851	296	7	learning	learning	NOUN
cana-3851	296	8	models	model	NOUN
cana-3851	296	9	on	on	ADP
cana-3851	296	10	the	the	DET
cana-3851	296	11	cancer	cancer	NOUN
cana-3851	296	12	genome	genome	NOUN
cana-3851	296	13	atlas	atlas	PROPN
cana-3851	296	14	(	(	PUNCT
cana-3851	296	15	tcga	tcga	PROPN
cana-3851	296	16	)	)	PUNCT
cana-3851	296	17	dataset	dataset	NOUN
cana-3851	296	18	.	.	PUNCT
cana-3851	297	1	48–56	48–56	NUM
cana-3851	297	2	.	.	PUNCT
cana-3851	298	1	[	[	X
cana-3851	298	2	4	4	NUM
cana-3851	298	3	]	]	X
cana-3851	298	4	srinivas	srinivas	PROPN
cana-3851	298	5	,	,	PUNCT
cana-3851	298	6	c.	c.	PROPN
cana-3851	298	7	,	,	PUNCT
cana-3851	298	8	s	s	PROPN
cana-3851	298	9	,	,	PUNCT
cana-3851	298	10	n.	n.	PROPN
cana-3851	298	11	p.	p.	PROPN
cana-3851	298	12	k.	k.	PROPN
cana-3851	298	13	,	,	PUNCT
cana-3851	298	14	zakariah	zakariah	PROPN
cana-3851	298	15	,	,	PUNCT
cana-3851	298	16	m.	m.	NOUN
cana-3851	298	17	,	,	PUNCT
cana-3851	298	18	alothaibi	alothaibi	NOUN
cana-3851	298	19	,	,	PUNCT
cana-3851	298	20	y.	y.	PROPN
cana-3851	298	21	a.	a.	PROPN
cana-3851	298	22	,	,	PUNCT
cana-3851	298	23	shaukat	shaukat	PROPN
cana-3851	298	24	,	,	PUNCT
cana-3851	298	25	k.	k.	PROPN
cana-3851	298	26	,	,	PUNCT
cana-3851	298	27	partibane	partibane	PROPN
cana-3851	298	28	,	,	PUNCT
cana-3851	298	29	b.	b.	PROPN
cana-3851	298	30	,	,	PUNCT
cana-3851	298	31	&	&	CCONJ
cana-3851	298	32	awal	awal	PROPN
cana-3851	298	33	,	,	PUNCT
cana-3851	298	34	h.	h.	PROPN
cana-3851	298	35	(	(	PUNCT
cana-3851	298	36	2022	2022	NUM
cana-3851	298	37	)	)	PUNCT
cana-3851	298	38	.	.	PUNCT
cana-3851	299	1	brain	brain	NOUN
cana-3851	299	2	tumor	tumor	NOUN
cana-3851	299	3	classification	classification	NOUN
cana-3851	299	4	using	use	VERB
cana-3851	299	5	mri	mri	NOUN
cana-3851	299	6	images	image	NOUN
cana-3851	299	7	.	.	PUNCT
cana-3851	300	1	2022	2022	NUM
cana-3851	300	2	.	.	PUNCT
cana-3851	301	1	[	[	X
cana-3851	301	2	5	5	NUM
cana-3851	301	3	]	]	PUNCT
cana-3851	301	4	işin	işin	PROPN
cana-3851	301	5	,	,	PUNCT
cana-3851	301	6	a.	a.	NOUN
cana-3851	301	7	,	,	PUNCT
cana-3851	301	8	direkoǧlu	direkoǧlu	NOUN
cana-3851	301	9	,	,	PUNCT
cana-3851	301	10	c.	c.	NOUN
cana-3851	301	11	,	,	PUNCT
cana-3851	301	12	&	&	CCONJ
cana-3851	301	13	şah	şah	ADJ
cana-3851	301	14	,	,	PUNCT
cana-3851	301	15	m.	m.	NOUN
cana-3851	301	16	(	(	PUNCT
cana-3851	301	17	2016	2016	NUM
cana-3851	301	18	)	)	PUNCT
cana-3851	301	19	.	.	PUNCT
cana-3851	302	1	review	review	NOUN
cana-3851	302	2	of	of	ADP
cana-3851	302	3	mri	mri	NOUN
cana-3851	302	4	-	-	PUNCT
cana-3851	302	5	based	base	VERB
cana-3851	302	6	brain	brain	NOUN
cana-3851	302	7	tumor	tumor	NOUN
cana-3851	302	8	image	image	NOUN
cana-3851	302	9	segmentation	segmentation	NOUN
cana-3851	302	10	using	use	VERB
cana-3851	302	11	deep	deep	ADJ
cana-3851	302	12	learning	learning	NOUN
cana-3851	302	13	methods	method	NOUN
cana-3851	302	14	.	.	PUNCT
cana-3851	303	1	procedia	procedia	PROPN
cana-3851	303	2	computer	computer	NOUN
cana-3851	303	3	science	science	NOUN
cana-3851	303	4	,	,	PUNCT
cana-3851	303	5	102(august	102(august	NUM
cana-3851	303	6	)	)	PUNCT
cana-3851	303	7	,	,	PUNCT
cana-3851	303	8	317–324	317–324	NUM
cana-3851	303	9	.	.	PUNCT
cana-3851	304	1	https://doi.org/10.1016/j.procs.2016.09.407	https://doi.org/10.1016/j.procs.2016.09.407	X
cana-3851	304	2	[	[	PUNCT
cana-3851	304	3	6	6	NUM
cana-3851	304	4	]	]	X
cana-3851	304	5	chattopadhyay	chattopadhyay	PROPN
cana-3851	304	6	,	,	PUNCT
cana-3851	304	7	a.	a.	PROPN
cana-3851	304	8	,	,	PUNCT
cana-3851	304	9	&	&	CCONJ
cana-3851	304	10	maitra	maitra	NOUN
cana-3851	304	11	,	,	PUNCT
cana-3851	304	12	m.	m.	NOUN
cana-3851	304	13	(	(	PUNCT
cana-3851	304	14	2022	2022	NUM
cana-3851	304	15	)	)	PUNCT
cana-3851	304	16	.	.	PUNCT
cana-3851	305	1	mri	mri	NOUN
cana-3851	305	2	-	-	PUNCT
cana-3851	305	3	based	base	VERB
cana-3851	305	4	brain	brain	NOUN
cana-3851	305	5	tumour	tumour	NOUN
cana-3851	305	6	image	image	NOUN
cana-3851	305	7	detection	detection	NOUN
cana-3851	305	8	using	use	VERB
cana-3851	305	9	cnn	cnn	PROPN
cana-3851	305	10	based	base	VERB
cana-3851	305	11	deep	deep	ADJ
cana-3851	305	12	learning	learning	NOUN
cana-3851	305	13	method	method	NOUN
cana-3851	305	14	.	.	PUNCT
cana-3851	306	1	smart	smart	ADJ
cana-3851	306	2	agricultural	agricultural	ADJ
cana-3851	306	3	technology	technology	NOUN
cana-3851	306	4	,	,	PUNCT
cana-3851	306	5	2(4	2(4	NUM
cana-3851	306	6	)	)	PUNCT
cana-3851	306	7	,	,	PUNCT
cana-3851	306	8	100060	100060	NUM
cana-3851	306	9	.	.	PUNCT
cana-3851	307	1	https://doi.org/10.1016/j.neuri.2022.100060	https://doi.org/10.1016/j.neuri.2022.100060	NOUN
cana-3851	307	2	[	[	X
cana-3851	307	3	7	7	NUM
cana-3851	307	4	]	]	X
cana-3851	307	5	havaei	havaei	PROPN
cana-3851	307	6	,	,	PUNCT
cana-3851	307	7	m.	m.	NOUN
cana-3851	307	8	,	,	PUNCT
cana-3851	307	9	davy	davy	PROPN
cana-3851	307	10	,	,	PUNCT
cana-3851	307	11	a.	a.	PROPN
cana-3851	307	12	,	,	PUNCT
cana-3851	307	13	warde	warde	PROPN
cana-3851	307	14	-	-	PUNCT
cana-3851	307	15	farley	farley	PROPN
cana-3851	307	16	,	,	PUNCT
cana-3851	307	17	d.	d.	PROPN
cana-3851	307	18	,	,	PUNCT
cana-3851	307	19	biard	biard	NOUN
cana-3851	307	20	,	,	PUNCT
cana-3851	307	21	a.	a.	NOUN
cana-3851	307	22	,	,	PUNCT
cana-3851	307	23	courville	courville	NOUN
cana-3851	307	24	,	,	PUNCT
cana-3851	307	25	a.	a.	NOUN
cana-3851	307	26	,	,	PUNCT
cana-3851	307	27	bengio	bengio	PROPN
cana-3851	307	28	,	,	PUNCT
cana-3851	307	29	y.	y.	PROPN
cana-3851	307	30	,	,	PUNCT
cana-3851	307	31	pal	pal	NOUN
cana-3851	307	32	,	,	PUNCT
cana-3851	307	33	c.	c.	PROPN
cana-3851	307	34	,	,	PUNCT
cana-3851	307	35	jodoin	jodoin	PROPN
cana-3851	307	36	,	,	PUNCT
cana-3851	307	37	p.	p.	NOUN
cana-3851	307	38	m.	m.	NOUN
cana-3851	307	39	,	,	PUNCT
cana-3851	307	40	&	&	CCONJ
cana-3851	307	41	larochelle	larochelle	PROPN
cana-3851	307	42	,	,	PUNCT
cana-3851	307	43	h.	h.	PROPN
cana-3851	307	44	(	(	PUNCT
cana-3851	307	45	2017	2017	NUM
cana-3851	307	46	)	)	PUNCT
cana-3851	307	47	.	.	PUNCT
cana-3851	308	1	brain	brain	NOUN
cana-3851	308	2	tumor	tumor	NOUN
cana-3851	308	3	segmentation	segmentation	NOUN
cana-3851	308	4	with	with	ADP
cana-3851	308	5	deep	deep	ADJ
cana-3851	308	6	neural	neural	ADJ
cana-3851	308	7	networks	network	NOUN
cana-3851	308	8	.	.	PUNCT
cana-3851	309	1	medical	medical	ADJ
cana-3851	309	2	image	image	NOUN
cana-3851	309	3	analysis	analysis	NOUN
cana-3851	309	4	,	,	PUNCT
cana-3851	309	5	35	35	NUM
cana-3851	309	6	,	,	PUNCT
cana-3851	309	7	18–31	18–31	NUM
cana-3851	309	8	.	.	PUNCT
cana-3851	310	1	https://doi.org/10.1016/j.media.2016.05.004	https://doi.org/10.1016/j.media.2016.05.004	PROPN
cana-3851	310	2	communications	communication	NOUN
cana-3851	310	3	on	on	ADP
cana-3851	310	4	applied	apply	VERB
cana-3851	310	5	nonlinear	nonlinear	ADJ
cana-3851	310	6	analysis	analysis	NOUN
cana-3851	310	7	issn	issn	NOUN
cana-3851	310	8	:	:	PUNCT
cana-3851	310	9	1074	1074	NUM
cana-3851	310	10	-	-	PUNCT
cana-3851	310	11	133x	133x	NUM
cana-3851	310	12	vol	vol	NOUN
cana-3851	310	13	32	32	NUM
cana-3851	310	14	no	no	NOUN
cana-3851	310	15	.	.	PUNCT
cana-3851	311	1	9s	9s	NUM
cana-3851	311	2	(	(	PUNCT
cana-3851	311	3	2025	2025	NUM
cana-3851	311	4	)	)	PUNCT
cana-3851	311	5	226	226	NUM
cana-3851	311	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-3851	312	1	[	[	X
cana-3851	312	2	8	8	NUM
cana-3851	312	3	]	]	X
cana-3851	312	4	rehman	rehman	NOUN
cana-3851	312	5	,	,	PUNCT
cana-3851	312	6	a.	a.	PROPN
cana-3851	312	7	,	,	PUNCT
cana-3851	312	8	naz	naz	PROPN
cana-3851	312	9	,	,	PUNCT
cana-3851	312	10	s.	s.	PROPN
cana-3851	312	11	,	,	PUNCT
cana-3851	312	12	razzak	razzak	PROPN
cana-3851	312	13	,	,	PUNCT
cana-3851	312	14	m.	m.	NOUN
cana-3851	312	15	i.	i.	PROPN
cana-3851	312	16	,	,	PUNCT
cana-3851	312	17	akram	akram	PROPN
cana-3851	312	18	,	,	PUNCT
cana-3851	312	19	f.	f.	PROPN
cana-3851	312	20	,	,	PUNCT
cana-3851	312	21	&	&	CCONJ
cana-3851	312	22	imran	imran	PROPN
cana-3851	312	23	,	,	PUNCT
cana-3851	312	24	m.	m.	NOUN
cana-3851	312	25	(	(	PUNCT
cana-3851	312	26	2020	2020	NUM
cana-3851	312	27	)	)	PUNCT
cana-3851	312	28	.	.	PUNCT
cana-3851	313	1	a	a	DET
cana-3851	313	2	deep	deep	ADJ
cana-3851	313	3	learning	learning	NOUN
cana-3851	313	4	-	-	PUNCT
cana-3851	313	5	based	base	VERB
cana-3851	313	6	framework	framework	NOUN
cana-3851	313	7	for	for	ADP
cana-3851	313	8	automatic	automatic	ADJ
cana-3851	313	9	brain	brain	NOUN
cana-3851	313	10	tumors	tumor	NOUN
cana-3851	313	11	classification	classification	NOUN
cana-3851	313	12	using	use	VERB
cana-3851	313	13	transfer	transfer	NOUN
cana-3851	313	14	learning	learning	NOUN
cana-3851	313	15	.	.	PUNCT
cana-3851	314	1	circuits	circuit	NOUN
cana-3851	314	2	,	,	PUNCT
cana-3851	314	3	systems	system	NOUN
cana-3851	314	4	,	,	PUNCT
cana-3851	314	5	and	and	CCONJ
cana-3851	314	6	signal	signal	NOUN
cana-3851	314	7	processing	processing	NOUN
cana-3851	314	8	,	,	PUNCT
cana-3851	314	9	39(2	39(2	NUM
cana-3851	314	10	)	)	PUNCT
cana-3851	314	11	,	,	PUNCT
cana-3851	314	12	757–775	757–775	NUM
cana-3851	314	13	.	.	PUNCT
cana-3851	314	14	https://doi.org/10.1007/s00034-019-01246-3	https://doi.org/10.1007/s00034-019-01246-3	NUM
cana-3851	315	1	[	[	PUNCT
cana-3851	315	2	9	9	NUM
cana-3851	315	3	]	]	SYM
cana-3851	315	4	shehab	shehab	NOUN
cana-3851	315	5	,	,	PUNCT
cana-3851	315	6	l.	l.	PROPN
cana-3851	315	7	h.	h.	PROPN
cana-3851	315	8	,	,	PUNCT
cana-3851	315	9	fahmy	fahmy	PROPN
cana-3851	315	10	,	,	PUNCT
cana-3851	315	11	o.	o.	NOUN
cana-3851	315	12	m.	m.	NOUN
cana-3851	315	13	,	,	PUNCT
cana-3851	315	14	gasser	gasser	NOUN
cana-3851	315	15	,	,	PUNCT
cana-3851	315	16	s.	s.	PROPN
cana-3851	315	17	m.	m.	PROPN
cana-3851	315	18	,	,	PUNCT
cana-3851	315	19	&	&	CCONJ
cana-3851	315	20	el	el	PROPN
cana-3851	315	21	-	-	PUNCT
cana-3851	315	22	mahallawy	mahallawy	PROPN
cana-3851	315	23	,	,	PUNCT
cana-3851	315	24	m.	m.	NOUN
cana-3851	315	25	s.	s.	PROPN
cana-3851	315	26	(	(	PUNCT
cana-3851	315	27	2021	2021	NUM
cana-3851	315	28	)	)	PUNCT
cana-3851	315	29	.	.	PUNCT
cana-3851	316	1	an	an	DET
cana-3851	316	2	efficient	efficient	ADJ
cana-3851	316	3	brain	brain	NOUN
cana-3851	316	4	tumor	tumor	NOUN
cana-3851	316	5	image	image	NOUN
cana-3851	316	6	segmentation	segmentation	NOUN
cana-3851	316	7	based	base	VERB
cana-3851	316	8	on	on	ADP
cana-3851	316	9	deep	deep	ADJ
cana-3851	316	10	residual	residual	ADJ
cana-3851	316	11	networks	network	NOUN
cana-3851	316	12	(	(	PUNCT
cana-3851	316	13	resnets	resnet	NOUN
cana-3851	316	14	)	)	PUNCT
cana-3851	316	15	.	.	PUNCT
cana-3851	317	1	journal	journal	PROPN
cana-3851	317	2	of	of	ADP
cana-3851	317	3	king	king	PROPN
cana-3851	317	4	saud	saud	PROPN
cana-3851	317	5	university	university	PROPN
cana-3851	317	6	engineering	engineering	NOUN
cana-3851	317	7	sciences	sciences	PROPN
cana-3851	317	8	,	,	PUNCT
cana-3851	317	9	33(6	33(6	NUM
cana-3851	317	10	)	)	PUNCT
cana-3851	317	11	,	,	PUNCT
cana-3851	317	12	404–412	404–412	NUM
cana-3851	317	13	.	.	PUNCT
cana-3851	318	1	https://doi.org/10.1016/j.jksues.2020.06.001	https://doi.org/10.1016/j.jksues.2020.06.001	PROPN
cana-3851	318	2	[	[	X
cana-3851	318	3	10	10	NUM
cana-3851	318	4	]	]	X
cana-3851	318	5	kuraparthi	kuraparthi	NOUN
cana-3851	318	6	,	,	PUNCT
cana-3851	318	7	s.	s.	PROPN
cana-3851	318	8	,	,	PUNCT
cana-3851	318	9	reddy	reddy	PROPN
cana-3851	318	10	,	,	PUNCT
cana-3851	318	11	m.	m.	PROPN
cana-3851	318	12	k.	k.	PROPN
cana-3851	318	13	,	,	PUNCT
cana-3851	318	14	sujatha	sujatha	PROPN
cana-3851	318	15	,	,	PUNCT
cana-3851	318	16	c.	c.	PROPN
cana-3851	318	17	n.	n.	PROPN
cana-3851	318	18	,	,	PUNCT
cana-3851	318	19	valiveti	valiveti	PROPN
cana-3851	318	20	,	,	PUNCT
cana-3851	318	21	h.	h.	PROPN
cana-3851	318	22	,	,	PUNCT
cana-3851	318	23	duggineni	duggineni	PROPN
cana-3851	318	24	,	,	PUNCT
cana-3851	318	25	c.	c.	PROPN
cana-3851	318	26	,	,	PUNCT
cana-3851	318	27	kollati	kollati	PROPN
cana-3851	318	28	,	,	PUNCT
cana-3851	318	29	m.	m.	NOUN
cana-3851	318	30	,	,	PUNCT
cana-3851	318	31	kora	kora	PROPN
cana-3851	318	32	,	,	PUNCT
cana-3851	318	33	p.	p.	PROPN
cana-3851	318	34	,	,	PUNCT
cana-3851	318	35	&	&	CCONJ
cana-3851	318	36	sravan	sravan	PROPN
cana-3851	318	37	,	,	PUNCT
cana-3851	318	38	v.	v.	PROPN
cana-3851	318	39	(	(	PUNCT
cana-3851	318	40	2021	2021	NUM
cana-3851	318	41	)	)	PUNCT
cana-3851	318	42	.	.	PUNCT
cana-3851	319	1	brain	brain	NOUN
cana-3851	319	2	tumor	tumor	NOUN
cana-3851	319	3	classification	classification	NOUN
cana-3851	319	4	of	of	ADP
cana-3851	319	5	mri	mri	NOUN
cana-3851	319	6	images	image	NOUN
cana-3851	319	7	using	use	VERB
cana-3851	319	8	deep	deep	ADJ
cana-3851	319	9	convolutional	convolutional	ADJ
cana-3851	319	10	neural	neural	ADJ
cana-3851	319	11	network	network	NOUN
cana-3851	319	12	.	.	PUNCT
cana-3851	320	1	traitement	traitement	NOUN
cana-3851	320	2	du	du	PROPN
cana-3851	320	3	signal	signal	NOUN
cana-3851	320	4	,	,	PUNCT
cana-3851	320	5	38(4	38(4	NUM
cana-3851	320	6	)	)	PUNCT
cana-3851	320	7	,	,	PUNCT
cana-3851	320	8	1171–1179	1171–1179	NUM
cana-3851	320	9	.	.	PUNCT
cana-3851	321	1	https://doi.org/10.18280/ts.380428	https://doi.org/10.18280/ts.380428	VERB
cana-3851	322	1	[	[	X
cana-3851	322	2	11	11	NUM
cana-3851	322	3	]	]	PUNCT
cana-3851	322	4	wacker	wacker	NOUN
cana-3851	322	5	,	,	PUNCT
cana-3851	322	6	j.	j.	PROPN
cana-3851	322	7	,	,	PUNCT
cana-3851	322	8	ladeira	ladeira	PROPN
cana-3851	322	9	,	,	PUNCT
cana-3851	322	10	m.	m.	NOUN
cana-3851	322	11	,	,	PUNCT
cana-3851	322	12	&	&	CCONJ
cana-3851	322	13	nascimento	nascimento	PROPN
cana-3851	322	14	,	,	PUNCT
cana-3851	322	15	j.	j.	PROPN
cana-3851	322	16	e.	e.	PROPN
cana-3851	322	17	v.	v.	PROPN
cana-3851	322	18	(	(	PUNCT
cana-3851	322	19	2021	2021	NUM
cana-3851	322	20	)	)	PUNCT
cana-3851	322	21	.	.	PUNCT
cana-3851	323	1	transfer	transfer	NOUN
cana-3851	323	2	learning	learning	NOUN
cana-3851	323	3	for	for	ADP
cana-3851	323	4	brain	brain	NOUN
cana-3851	323	5	tumor	tumor	NOUN
cana-3851	323	6	segmentation	segmentation	NOUN
cana-3851	323	7	.	.	PUNCT
cana-3851	324	1	lecture	lecture	NOUN
cana-3851	324	2	notes	note	NOUN
cana-3851	324	3	in	in	ADP
cana-3851	324	4	computer	computer	NOUN
cana-3851	324	5	science	science	NOUN
cana-3851	324	6	(	(	PUNCT
cana-3851	324	7	including	include	VERB
cana-3851	324	8	subseries	subserie	NOUN
cana-3851	324	9	lecture	lecture	VERB
cana-3851	324	10	notes	note	NOUN
cana-3851	324	11	in	in	ADP
cana-3851	324	12	artificial	artificial	ADJ
cana-3851	324	13	intelligence	intelligence	NOUN
cana-3851	324	14	and	and	CCONJ
cana-3851	324	15	lecture	lecture	NOUN
cana-3851	324	16	notes	note	NOUN
cana-3851	324	17	in	in	ADP
cana-3851	324	18	bioinformatics	bioinformatics	NOUN
cana-3851	324	19	)	)	PUNCT
cana-3851	324	20	,	,	PUNCT
cana-3851	324	21	12658	12658	NUM
cana-3851	324	22	lncs	lnc	NOUN
cana-3851	324	23	,	,	PUNCT
cana-3851	324	24	241–251	241–251	NUM
cana-3851	324	25	.	.	PUNCT
cana-3851	325	1	https://doi.org/10.1007/978-3-030-72084-1_22	https://doi.org/10.1007/978-3-030-72084-1_22	PART
cana-3851	326	1	[	[	X
cana-3851	326	2	12	12	NUM
cana-3851	326	3	]	]	X
cana-3851	326	4	younis	younis	PROPN
cana-3851	326	5	,	,	PUNCT
cana-3851	326	6	a.	a.	PROPN
cana-3851	326	7	,	,	PUNCT
cana-3851	326	8	qiang	qiang	PROPN
cana-3851	326	9	,	,	PUNCT
cana-3851	326	10	l.	l.	PROPN
cana-3851	326	11	,	,	PUNCT
cana-3851	326	12	nyatega	nyatega	PROPN
cana-3851	326	13	,	,	PUNCT
cana-3851	326	14	c.	c.	PROPN
cana-3851	326	15	o.	o.	PROPN
cana-3851	326	16	,	,	PUNCT
cana-3851	326	17	adamu	adamu	PROPN
cana-3851	326	18	,	,	PUNCT
cana-3851	326	19	m.	m.	PROPN
cana-3851	326	20	j.	j.	PROPN
cana-3851	326	21	,	,	PUNCT
cana-3851	326	22	&	&	CCONJ
cana-3851	326	23	kawuwa	kawuwa	PROPN
cana-3851	326	24	,	,	PUNCT
cana-3851	326	25	h.	h.	PROPN
cana-3851	326	26	b.	b.	PROPN
cana-3851	326	27	(	(	PUNCT
cana-3851	326	28	2022	2022	NUM
cana-3851	326	29	)	)	PUNCT
cana-3851	326	30	.	.	PUNCT
cana-3851	327	1	brain	brain	NOUN
cana-3851	327	2	tumor	tumor	NOUN
cana-3851	327	3	analysis	analysis	NOUN
cana-3851	327	4	using	use	VERB
cana-3851	327	5	deep	deep	ADJ
cana-3851	327	6	learning	learning	NOUN
cana-3851	327	7	and	and	CCONJ
cana-3851	327	8	vgg-16	vgg-16	X
cana-3851	327	9	ensembling	ensemble	VERB
cana-3851	327	10	learning	learn	VERB
cana-3851	327	11	approaches	approach	NOUN
cana-3851	327	12	.	.	PUNCT
cana-3851	328	1	applied	apply	VERB
cana-3851	328	2	sciences	sciences	PROPN
cana-3851	328	3	(	(	PUNCT
cana-3851	328	4	switzerland	switzerland	PROPN
cana-3851	328	5	)	)	PUNCT
cana-3851	328	6	,	,	PUNCT
cana-3851	328	7	12(14	12(14	NUM
cana-3851	328	8	)	)	PUNCT
cana-3851	328	9	.	.	PUNCT
cana-3851	329	1	https://doi.org/10.3390/app12147282	https://doi.org/10.3390/app12147282	X
cana-3851	330	1	[	[	X
cana-3851	330	2	13	13	NUM
cana-3851	330	3	]	]	SYM
cana-3851	330	4	ali	ali	PROPN
cana-3851	330	5	,	,	PUNCT
cana-3851	330	6	m.	m.	NOUN
cana-3851	330	7	,	,	PUNCT
cana-3851	330	8	gilani	gilani	PROPN
cana-3851	330	9	,	,	PUNCT
cana-3851	330	10	s.	s.	PROPN
cana-3851	330	11	o.	o.	PROPN
cana-3851	330	12	,	,	PUNCT
cana-3851	330	13	waris	waris	PROPN
cana-3851	330	14	,	,	PUNCT
cana-3851	330	15	a.	a.	PROPN
cana-3851	330	16	,	,	PUNCT
cana-3851	330	17	zafar	zafar	PROPN
cana-3851	330	18	,	,	PUNCT
cana-3851	330	19	k.	k.	PROPN
cana-3851	330	20	,	,	PUNCT
cana-3851	330	21	&	&	CCONJ
cana-3851	330	22	jamil	jamil	PROPN
cana-3851	330	23	,	,	PUNCT
cana-3851	330	24	m.	m.	NOUN
cana-3851	330	25	(	(	PUNCT
cana-3851	330	26	2020	2020	NUM
cana-3851	330	27	)	)	PUNCT
cana-3851	330	28	.	.	PUNCT
cana-3851	331	1	brain	brain	NOUN
cana-3851	331	2	tumour	tumour	NOUN
cana-3851	331	3	image	image	NOUN
cana-3851	331	4	segmentation	segmentation	NOUN
cana-3851	331	5	using	use	VERB
cana-3851	331	6	deep	deep	ADJ
cana-3851	331	7	networks	network	NOUN
cana-3851	331	8	.	.	PUNCT
cana-3851	332	1	ieee	ieee	NOUN
cana-3851	332	2	access	access	NOUN
cana-3851	332	3	,	,	PUNCT
cana-3851	332	4	8	8	NUM
cana-3851	332	5	,	,	PUNCT
cana-3851	332	6	153589–153598	153589–153598	NUM
cana-3851	332	7	.	.	PUNCT
cana-3851	333	1	https://doi.org/10.1109/access.2020.3018160	https://doi.org/10.1109/access.2020.3018160	PROPN
cana-3851	333	2	[	[	X
cana-3851	333	3	14	14	NUM
cana-3851	333	4	]	]	X
cana-3851	333	5	bhanothu	bhanothu	NOUN
cana-3851	333	6	,	,	PUNCT
cana-3851	333	7	y.	y.	PROPN
cana-3851	333	8	,	,	PUNCT
cana-3851	333	9	kamalakannan	kamalakannan	PROPN
cana-3851	333	10	,	,	PUNCT
cana-3851	333	11	a.	a.	NOUN
cana-3851	333	12	,	,	PUNCT
cana-3851	333	13	&	&	CCONJ
cana-3851	333	14	rajamanickam	rajamanickam	PROPN
cana-3851	333	15	,	,	PUNCT
cana-3851	333	16	g.	g.	PROPN
cana-3851	333	17	(	(	PUNCT
cana-3851	333	18	2020	2020	NUM
cana-3851	333	19	)	)	PUNCT
cana-3851	333	20	.	.	PUNCT
cana-3851	334	1	detection	detection	NOUN
cana-3851	334	2	and	and	CCONJ
cana-3851	334	3	classification	classification	NOUN
cana-3851	334	4	of	of	ADP
cana-3851	334	5	brain	brain	NOUN
cana-3851	334	6	tumor	tumor	NOUN
cana-3851	334	7	in	in	ADP
cana-3851	334	8	mri	mri	NOUN
cana-3851	334	9	images	image	NOUN
cana-3851	334	10	using	use	VERB
cana-3851	334	11	deep	deep	ADJ
cana-3851	334	12	convolutional	convolutional	ADJ
cana-3851	334	13	network	network	NOUN
cana-3851	334	14	.	.	PUNCT
cana-3851	335	1	2020	2020	NUM
cana-3851	335	2	6th	6th	ADJ
cana-3851	335	3	international	international	ADJ
cana-3851	335	4	conference	conference	NOUN
cana-3851	335	5	on	on	ADP
cana-3851	335	6	advanced	advanced	ADJ
cana-3851	335	7	computing	computing	NOUN
cana-3851	335	8	and	and	CCONJ
cana-3851	335	9	communication	communication	NOUN
cana-3851	335	10	systems	system	NOUN
cana-3851	335	11	,	,	PUNCT
cana-3851	335	12	icaccs	icaccs	NOUN
cana-3851	335	13	2020	2020	NUM
cana-3851	335	14	,	,	PUNCT
cana-3851	335	15	248–252	248–252	NUM
cana-3851	335	16	.	.	PUNCT
cana-3851	336	1	https://doi.org/10.1109/icaccs48705.2020.9074375	https://doi.org/10.1109/icaccs48705.2020.9074375	PUNCT
cana-3851	337	1	[	[	X
cana-3851	337	2	15	15	NUM
cana-3851	337	3	]	]	X
cana-3851	337	4	ahmed	ahmed	PROPN
cana-3851	337	5	,	,	PUNCT
cana-3851	337	6	f.	f.	PROPN
cana-3851	337	7	,	,	PUNCT
cana-3851	337	8	asif	asif	PROPN
cana-3851	337	9	,	,	PUNCT
cana-3851	337	10	m.	m.	NOUN
cana-3851	337	11	,	,	PUNCT
cana-3851	337	12	saleem	saleem	PROPN
cana-3851	337	13	,	,	PUNCT
cana-3851	337	14	m.	m.	NOUN
cana-3851	337	15	,	,	PUNCT
cana-3851	337	16	mushtaq	mushtaq	PROPN
cana-3851	337	17	,	,	PUNCT
cana-3851	337	18	u.	u.	PROPN
cana-3851	337	19	f.	f.	PROPN
cana-3851	337	20	,	,	PUNCT
cana-3851	337	21	&	&	CCONJ
cana-3851	337	22	imran	imran	PROPN
cana-3851	337	23	,	,	PUNCT
cana-3851	337	24	m.	m.	NOUN
cana-3851	337	25	(	(	PUNCT
cana-3851	337	26	2023	2023	NUM
cana-3851	337	27	)	)	PUNCT
cana-3851	337	28	.	.	PUNCT
cana-3851	338	1	identification	identification	NOUN
cana-3851	338	2	and	and	CCONJ
cana-3851	338	3	prediction	prediction	NOUN
cana-3851	338	4	of	of	ADP
cana-3851	338	5	brain	brain	NOUN
cana-3851	338	6	tumor	tumor	NOUN
cana-3851	338	7	using	use	VERB
cana-3851	338	8	vgg-16	vgg-16	NOUN
cana-3851	338	9	empowered	empower	VERB
cana-3851	338	10	with	with	ADP
cana-3851	338	11	explainable	explainable	ADJ
cana-3851	338	12	artificial	artificial	ADJ
cana-3851	338	13	intelligence	intelligence	NOUN
cana-3851	338	14	.	.	PUNCT
cana-3851	339	1	international	international	ADJ
cana-3851	339	2	journal	journal	PROPN
cana-3851	339	3	of	of	ADP
cana-3851	339	4	computational	computational	ADJ
cana-3851	339	5	and	and	CCONJ
cana-3851	339	6	innovative	innovative	ADJ
cana-3851	339	7	sciences	science	NOUN
cana-3851	339	8	,	,	PUNCT
cana-3851	339	9	2(2	2(2	NUM
cana-3851	339	10	)	)	PUNCT
cana-3851	339	11	,	,	PUNCT
cana-3851	339	12	24	24	NUM
cana-3851	339	13	-	-	SYM
cana-3851	339	14	33	33	NUM
cana-3851	339	15	.	.	PUNCT
cana-3851	340	1	[	[	X
cana-3851	340	2	16	16	NUM
cana-3851	340	3	]	]	X
cana-3851	340	4	iqbal	iqbal	PROPN
cana-3851	340	5	,	,	PUNCT
cana-3851	340	6	s.	s.	PROPN
cana-3851	340	7	,	,	PUNCT
cana-3851	340	8	ghani	ghani	PROPN
cana-3851	340	9	,	,	PUNCT
cana-3851	340	10	m.	m.	NOUN
cana-3851	340	11	u.	u.	PROPN
cana-3851	340	12	,	,	PUNCT
cana-3851	340	13	saba	saba	PROPN
cana-3851	340	14	,	,	PUNCT
cana-3851	340	15	t.	t.	PROPN
cana-3851	340	16	,	,	PUNCT
cana-3851	340	17	&	&	CCONJ
cana-3851	340	18	rehman	rehman	PROPN
cana-3851	340	19	,	,	PUNCT
cana-3851	340	20	a.	a.	NOUN
cana-3851	340	21	(	(	PUNCT
cana-3851	340	22	2018	2018	NUM
cana-3851	340	23	)	)	PUNCT
cana-3851	340	24	.	.	PUNCT
cana-3851	341	1	brain	brain	NOUN
cana-3851	341	2	tumor	tumor	PROPN
cana-3851	341	3	segmentation	segmentation	NOUN
cana-3851	341	4	in	in	ADP
cana-3851	341	5	multi	multi	ADJ
cana-3851	341	6	-	-	ADJ
cana-3851	341	7	spectral	spectral	ADJ
cana-3851	341	8	mri	mri	NOUN
cana-3851	341	9	using	use	VERB
cana-3851	341	10	convolutional	convolutional	ADJ
cana-3851	341	11	neural	neural	ADJ
cana-3851	341	12	networks	network	NOUN
cana-3851	341	13	(	(	PUNCT
cana-3851	341	14	cnn	cnn	PROPN
cana-3851	341	15	)	)	PUNCT
cana-3851	341	16	.	.	PUNCT
cana-3851	342	1	microscopy	microscopy	PROPN
cana-3851	342	2	research	research	NOUN
cana-3851	342	3	and	and	CCONJ
cana-3851	342	4	technique	technique	NOUN
cana-3851	342	5	,	,	PUNCT
cana-3851	342	6	81(4	81(4	NUM
cana-3851	342	7	)	)	PUNCT
cana-3851	342	8	,	,	PUNCT
cana-3851	342	9	419–427	419–427	NUM
cana-3851	342	10	.	.	PUNCT
cana-3851	342	11	https://doi.org/10.1002/jemt.22994	https://doi.org/10.1002/jemt.22994	NOUN
cana-3851	343	1	[	[	X
cana-3851	343	2	17	17	NUM
cana-3851	343	3	]	]	SYM
cana-3851	343	4	asiri	asiri	PROPN
cana-3851	343	5	,	,	PUNCT
cana-3851	343	6	a.	a.	NOUN
cana-3851	343	7	a.	a.	PROPN
cana-3851	343	8	,	,	PUNCT
cana-3851	343	9	shaf	shaf	PROPN
cana-3851	343	10	,	,	PUNCT
cana-3851	343	11	a.	a.	PROPN
cana-3851	343	12	,	,	PUNCT
cana-3851	343	13	ali	ali	PROPN
cana-3851	343	14	,	,	PUNCT
cana-3851	343	15	t.	t.	PROPN
cana-3851	343	16	,	,	PUNCT
cana-3851	343	17	aamir	aamir	PROPN
cana-3851	343	18	,	,	PUNCT
cana-3851	343	19	m.	m.	NOUN
cana-3851	343	20	,	,	PUNCT
cana-3851	343	21	irfan	irfan	PROPN
cana-3851	343	22	,	,	PUNCT
cana-3851	343	23	m.	m.	NOUN
cana-3851	343	24	,	,	PUNCT
cana-3851	343	25	alqahtani	alqahtani	PROPN
cana-3851	343	26	,	,	PUNCT
cana-3851	343	27	s.	s.	PROPN
cana-3851	343	28	,	,	PUNCT
cana-3851	343	29	mehdar	mehdar	NOUN
cana-3851	343	30	,	,	PUNCT
cana-3851	343	31	k.	k.	PROPN
cana-3851	343	32	m.	m.	PROPN
cana-3851	343	33	,	,	PUNCT
cana-3851	343	34	halawani	halawani	PROPN
cana-3851	343	35	,	,	PUNCT
cana-3851	343	36	h.	h.	PROPN
cana-3851	343	37	t.	t.	PROPN
cana-3851	343	38	,	,	PUNCT
cana-3851	343	39	alghamdi	alghamdi	NOUN
cana-3851	343	40	,	,	PUNCT
cana-3851	343	41	a.	a.	PROPN
cana-3851	343	42	h.	h.	PROPN
cana-3851	343	43	,	,	PUNCT
cana-3851	343	44	alshamrani	alshamrani	ADJ
cana-3851	343	45	,	,	PUNCT
cana-3851	343	46	a.	a.	PROPN
cana-3851	343	47	f.	f.	PROPN
cana-3851	343	48	a.	a.	PROPN
cana-3851	343	49	,	,	PUNCT
cana-3851	343	50	&	&	CCONJ
cana-3851	343	51	alqhtani	alqhtani	ADJ
cana-3851	343	52	,	,	PUNCT
cana-3851	343	53	s.	s.	PROPN
cana-3851	343	54	m.	m.	PROPN
cana-3851	343	55	(	(	PUNCT
cana-3851	343	56	2023	2023	NUM
cana-3851	343	57	)	)	PUNCT
cana-3851	343	58	.	.	PUNCT
cana-3851	344	1	brain	brain	NOUN
cana-3851	344	2	tumor	tumor	NOUN
cana-3851	344	3	detection	detection	NOUN
cana-3851	344	4	and	and	CCONJ
cana-3851	344	5	classification	classification	NOUN
cana-3851	344	6	using	use	VERB
cana-3851	344	7	fine	fine	ADV
cana-3851	344	8	-	-	PUNCT
cana-3851	344	9	tuned	tune	VERB
cana-3851	344	10	cnn	cnn	PROPN
cana-3851	344	11	with	with	ADP
cana-3851	344	12	resnet50	resnet50	NOUN
cana-3851	344	13	and	and	CCONJ
cana-3851	344	14	u	u	NOUN
cana-3851	344	15	-	-	ADJ
cana-3851	344	16	net	net	ADJ
cana-3851	344	17	model	model	NOUN
cana-3851	344	18	:	:	PUNCT
cana-3851	344	19	a	a	DET
cana-3851	344	20	study	study	NOUN
cana-3851	344	21	on	on	ADP
cana-3851	344	22	tcga	tcga	PROPN
cana-3851	344	23	-	-	PUNCT
cana-3851	344	24	lgg	lgg	NOUN
cana-3851	344	25	and	and	CCONJ
cana-3851	344	26	tcia	tcia	NOUN
cana-3851	344	27	dataset	dataset	VERB
cana-3851	344	28	for	for	ADP
cana-3851	344	29	mri	mri	NOUN
cana-3851	344	30	applications	application	NOUN
cana-3851	344	31	.	.	PUNCT
cana-3851	345	1	life	life	NOUN
cana-3851	345	2	,	,	PUNCT
cana-3851	345	3	13(7	13(7	NUM
cana-3851	345	4	)	)	PUNCT
cana-3851	345	5	.	.	PUNCT
cana-3851	346	1	https://doi.org/10.3390/life13071449	https://doi.org/10.3390/life13071449	PROPN
cana-3851	347	1	[	[	X
cana-3851	347	2	18	18	NUM
cana-3851	347	3	]	]	X
cana-3851	347	4	ben	ben	PROPN
cana-3851	347	5	naceur	naceur	PROPN
cana-3851	347	6	,	,	PUNCT
cana-3851	347	7	m.	m.	NOUN
cana-3851	347	8	,	,	PUNCT
cana-3851	347	9	akil	akil	PROPN
cana-3851	347	10	,	,	PUNCT
cana-3851	347	11	m.	m.	NOUN
cana-3851	347	12	,	,	PUNCT
cana-3851	347	13	saouli	saouli	PROPN
cana-3851	347	14	,	,	PUNCT
cana-3851	347	15	r.	r.	PROPN
cana-3851	347	16	,	,	PUNCT
cana-3851	347	17	&	&	CCONJ
cana-3851	347	18	kachouri	kachouri	PROPN
cana-3851	347	19	,	,	PUNCT
cana-3851	347	20	r.	r.	PROPN
cana-3851	347	21	(	(	PUNCT
cana-3851	347	22	2020	2020	NUM
cana-3851	347	23	)	)	PUNCT
cana-3851	347	24	.	.	PUNCT
cana-3851	348	1	deep	deep	ADJ
cana-3851	348	2	convolutional	convolutional	ADJ
cana-3851	348	3	neural	neural	ADJ
cana-3851	348	4	networks	network	NOUN
cana-3851	348	5	for	for	ADP
cana-3851	348	6	brain	brain	NOUN
cana-3851	348	7	tumor	tumor	NOUN
cana-3851	348	8	segmentation	segmentation	NOUN
cana-3851	348	9	:	:	PUNCT
cana-3851	348	10	boosting	boost	VERB
cana-3851	348	11	performance	performance	NOUN
cana-3851	348	12	using	use	VERB
cana-3851	348	13	deep	deep	ADJ
cana-3851	348	14	transfer	transfer	NOUN
cana-3851	348	15	learning	learning	NOUN
cana-3851	348	16	:	:	PUNCT
cana-3851	348	17	preliminary	preliminary	ADJ
cana-3851	348	18	results	result	NOUN
cana-3851	348	19	.	.	PUNCT
cana-3851	349	1	lecture	lecture	NOUN
cana-3851	349	2	notes	note	NOUN
cana-3851	349	3	in	in	ADP
cana-3851	349	4	computer	computer	NOUN
cana-3851	349	5	science	science	NOUN
cana-3851	349	6	(	(	PUNCT
cana-3851	349	7	including	include	VERB
cana-3851	349	8	subseries	subserie	NOUN
cana-3851	349	9	lecture	lecture	VERB
cana-3851	349	10	notes	note	NOUN
cana-3851	349	11	in	in	ADP
cana-3851	349	12	artificial	artificial	ADJ
cana-3851	349	13	intelligence	intelligence	NOUN
cana-3851	349	14	and	and	CCONJ
cana-3851	349	15	lecture	lecture	NOUN
cana-3851	349	16	notes	note	NOUN
cana-3851	349	17	in	in	ADP
cana-3851	349	18	bioinformatics	bioinformatics	NOUN
cana-3851	349	19	)	)	PUNCT
cana-3851	349	20	,	,	PUNCT
cana-3851	349	21	11993	11993	NUM
cana-3851	349	22	lncs	lnc	NOUN
cana-3851	349	23	,	,	PUNCT
cana-3851	349	24	303–315	303–315	NUM
cana-3851	349	25	.	.	PUNCT
cana-3851	350	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-3851	351	1	[	[	X
cana-3851	351	2	19	19	NUM
cana-3851	351	3	]	]	X
cana-3851	351	4	sahaai	sahaai	PROPN
cana-3851	351	5	,	,	PUNCT
cana-3851	351	6	m.	m.	PROPN
cana-3851	351	7	b.	b.	PROPN
cana-3851	351	8	,	,	PUNCT
cana-3851	351	9	jothilakshmi	jothilakshmi	PROPN
cana-3851	351	10	,	,	PUNCT
cana-3851	351	11	g.	g.	PROPN
cana-3851	351	12	r.	r.	PROPN
cana-3851	351	13	,	,	PUNCT
cana-3851	351	14	ravikumar	ravikumar	PROPN
cana-3851	351	15	,	,	PUNCT
cana-3851	351	16	d.	d.	PROPN
cana-3851	351	17	,	,	PUNCT
cana-3851	351	18	prasath	prasath	PROPN
cana-3851	351	19	,	,	PUNCT
cana-3851	351	20	r.	r.	PROPN
cana-3851	351	21	,	,	PUNCT
cana-3851	351	22	&	&	CCONJ
cana-3851	351	23	singh	singh	PROPN
cana-3851	351	24	,	,	PUNCT
cana-3851	351	25	s.	s.	PROPN
cana-3851	351	26	(	(	PUNCT
cana-3851	351	27	2022	2022	NUM
cana-3851	351	28	)	)	PUNCT
cana-3851	351	29	.	.	PUNCT
cana-3851	352	1	resnet-50	resnet-50	PROPN
cana-3851	352	2	based	base	VERB
cana-3851	352	3	deep	deep	ADJ
cana-3851	352	4	neural	neural	ADJ
cana-3851	352	5	network	network	NOUN
cana-3851	352	6	using	use	VERB
cana-3851	352	7	transfer	transfer	NOUN
cana-3851	352	8	learning	learning	NOUN
cana-3851	352	9	for	for	ADP
cana-3851	352	10	brain	brain	NOUN
cana-3851	352	11	tumor	tumor	NOUN
cana-3851	352	12	classification	classification	NOUN
cana-3851	352	13	.	.	PUNCT
cana-3851	353	1	aip	aip	PROPN
cana-3851	353	2	conference	conference	NOUN
cana-3851	353	3	proceedings	proceeding	NOUN
cana-3851	353	4	,	,	PUNCT
cana-3851	353	5	2463(may	2463(may	NUM
cana-3851	353	6	)	)	PUNCT
cana-3851	353	7	.	.	PUNCT
cana-3851	354	1	https://doi.org/10.1063/5.0082328	https://doi.org/10.1063/5.0082328	PROPN
cana-3851	355	1	[	[	X
cana-3851	355	2	20	20	NUM
cana-3851	355	3	]	]	PUNCT
cana-3851	355	4	bhandari	bhandari	PROPN
cana-3851	355	5	,	,	PUNCT
cana-3851	355	6	a.	a.	PROPN
cana-3851	355	7	,	,	PUNCT
cana-3851	355	8	koppen	koppen	PROPN
cana-3851	355	9	,	,	PUNCT
cana-3851	355	10	j.	j.	PROPN
cana-3851	355	11	,	,	PUNCT
cana-3851	355	12	&	&	CCONJ
cana-3851	355	13	agzarian	agzarian	ADJ
cana-3851	355	14	,	,	PUNCT
cana-3851	355	15	m.	m.	NOUN
cana-3851	355	16	(	(	PUNCT
cana-3851	355	17	2020	2020	NUM
cana-3851	355	18	)	)	PUNCT
cana-3851	355	19	.	.	PUNCT
cana-3851	356	1	convolutional	convolutional	ADJ
cana-3851	356	2	neural	neural	ADJ
cana-3851	356	3	networks	network	NOUN
cana-3851	356	4	for	for	ADP
cana-3851	356	5	brain	brain	NOUN
cana-3851	356	6	tumour	tumour	NOUN
cana-3851	356	7	segmentation	segmentation	NOUN
cana-3851	356	8	.	.	PUNCT
cana-3851	357	1	insights	insight	NOUN
cana-3851	357	2	into	into	ADP
cana-3851	357	3	imaging	imaging	NOUN
cana-3851	357	4	,	,	PUNCT
cana-3851	357	5	11(1	11(1	NUM
cana-3851	357	6	)	)	PUNCT
cana-3851	357	7	.	.	PUNCT
cana-3851	358	1	https://doi.org/10.1186/s13244-020-00869-4	https://doi.org/10.1186/s13244-020-00869-4	PUNCT
cana-3851	359	1	[	[	X
cana-3851	359	2	21	21	NUM
cana-3851	359	3	]	]	PUNCT
cana-3851	359	4	tandel	tandel	NOUN
cana-3851	359	5	,	,	PUNCT
cana-3851	359	6	g.	g.	PROPN
cana-3851	359	7	s.	s.	PROPN
cana-3851	359	8	,	,	PUNCT
cana-3851	359	9	tiwari	tiwari	PROPN
cana-3851	359	10	,	,	PUNCT
cana-3851	359	11	a.	a.	PROPN
cana-3851	359	12	,	,	PUNCT
cana-3851	359	13	&	&	CCONJ
cana-3851	359	14	kakde	kakde	PROPN
cana-3851	359	15	,	,	PUNCT
cana-3851	359	16	o.	o.	PROPN
cana-3851	359	17	g.	g.	PROPN
cana-3851	359	18	(	(	PUNCT
cana-3851	359	19	2022	2022	NUM
cana-3851	359	20	)	)	PUNCT
cana-3851	359	21	.	.	PUNCT
cana-3851	360	1	performance	performance	NOUN
cana-3851	360	2	enhancement	enhancement	NOUN
cana-3851	360	3	of	of	ADP
cana-3851	360	4	mri	mri	NOUN
cana-3851	360	5	-	-	PUNCT
cana-3851	360	6	based	base	VERB
cana-3851	360	7	brain	brain	NOUN
cana-3851	360	8	tumor	tumor	NOUN
cana-3851	360	9	classification	classification	NOUN
cana-3851	360	10	using	use	VERB
cana-3851	360	11	suitable	suitable	ADJ
cana-3851	360	12	segmentation	segmentation	NOUN
cana-3851	360	13	method	method	NOUN
cana-3851	360	14	and	and	CCONJ
cana-3851	360	15	deep	deep	ADJ
cana-3851	360	16	learning	learning	NOUN
cana-3851	360	17	-	-	PUNCT
cana-3851	360	18	based	base	VERB
cana-3851	360	19	ensemble	ensemble	ADJ
cana-3851	360	20	algorithm	algorithm	NOUN
cana-3851	360	21	.	.	PUNCT
cana-3851	361	1	biomedical	biomedical	ADJ
cana-3851	361	2	signal	signal	NOUN
cana-3851	361	3	processing	processing	NOUN
cana-3851	361	4	and	and	CCONJ
cana-3851	361	5	control	control	NOUN
cana-3851	361	6	,	,	PUNCT
cana-3851	361	7	78	78	NUM
cana-3851	361	8	,	,	PUNCT
cana-3851	361	9	104018	104018	NUM
cana-3851	361	10	.	.	PUNCT
cana-3851	362	1	[	[	X
cana-3851	362	2	22	22	NUM
cana-3851	362	3	]	]	X
cana-3851	362	4	pereira	pereira	PROPN
cana-3851	362	5	,	,	PUNCT
cana-3851	362	6	s.	s.	PROPN
cana-3851	362	7	,	,	PUNCT
cana-3851	362	8	pinto	pinto	NOUN
cana-3851	362	9	,	,	PUNCT
cana-3851	362	10	a.	a.	NOUN
cana-3851	362	11	,	,	PUNCT
cana-3851	362	12	alves	alves	PROPN
cana-3851	362	13	,	,	PUNCT
cana-3851	362	14	v.	v.	PROPN
cana-3851	362	15	,	,	PUNCT
cana-3851	362	16	&	&	CCONJ
cana-3851	362	17	silva	silva	PROPN
cana-3851	362	18	,	,	PUNCT
cana-3851	362	19	c.	c.	PROPN
cana-3851	362	20	a.	a.	PROPN
cana-3851	362	21	(	(	PUNCT
cana-3851	362	22	2016	2016	NUM
cana-3851	362	23	)	)	PUNCT
cana-3851	362	24	.	.	PUNCT
cana-3851	363	1	brain	brain	NOUN
cana-3851	363	2	tumor	tumor	NOUN
cana-3851	363	3	segmentation	segmentation	NOUN
cana-3851	363	4	using	use	VERB
cana-3851	363	5	convolutional	convolutional	ADJ
cana-3851	363	6	neural	neural	ADJ
cana-3851	363	7	networks	network	NOUN
cana-3851	363	8	in	in	ADP
cana-3851	363	9	mri	mri	NOUN
cana-3851	363	10	images	image	NOUN
cana-3851	363	11	.	.	PUNCT
cana-3851	364	1	ieee	ieee	NOUN
cana-3851	364	2	transactions	transaction	NOUN
cana-3851	364	3	on	on	ADP
cana-3851	364	4	medical	medical	ADJ
cana-3851	364	5	imaging	imaging	NOUN
cana-3851	364	6	,	,	PUNCT
cana-3851	364	7	35(5	35(5	NUM
cana-3851	364	8	)	)	PUNCT
cana-3851	364	9	,	,	PUNCT
cana-3851	364	10	1240–1251	1240–1251	NUM
cana-3851	364	11	.	.	PUNCT
cana-3851	365	1	https://doi.org/10.1109/tmi.2016.2538465	https://doi.org/10.1109/tmi.2016.2538465	NOUN
cana-3851	366	1	[	[	X
cana-3851	366	2	23	23	NUM
cana-3851	366	3	]	]	X
cana-3851	366	4	ghosh	ghosh	PROPN
cana-3851	366	5	,	,	PUNCT
cana-3851	366	6	s.	s.	PROPN
cana-3851	366	7	,	,	PUNCT
cana-3851	366	8	chaki	chaki	PROPN
cana-3851	366	9	,	,	PUNCT
cana-3851	366	10	a.	a.	NOUN
cana-3851	366	11	,	,	PUNCT
cana-3851	366	12	&	&	CCONJ
cana-3851	366	13	santosh	santosh	PROPN
cana-3851	366	14	,	,	PUNCT
cana-3851	366	15	k.	k.	PROPN
cana-3851	366	16	(	(	PUNCT
cana-3851	366	17	2021	2021	NUM
cana-3851	366	18	)	)	PUNCT
cana-3851	366	19	.	.	PUNCT
cana-3851	367	1	improved	improve	VERB
cana-3851	367	2	u	u	ADJ
cana-3851	367	3	-	-	ADJ
cana-3851	367	4	net	net	ADJ
cana-3851	367	5	architecture	architecture	NOUN
cana-3851	367	6	with	with	ADP
cana-3851	367	7	vgg-16	vgg-16	NOUN
cana-3851	367	8	for	for	ADP
cana-3851	367	9	brain	brain	NOUN
cana-3851	367	10	tumor	tumor	NOUN
cana-3851	367	11	segmentation	segmentation	NOUN
cana-3851	367	12	.	.	PUNCT
cana-3851	368	1	physical	physical	ADJ
cana-3851	368	2	and	and	CCONJ
cana-3851	368	3	engineering	engineering	NOUN
cana-3851	368	4	sciences	science	NOUN
cana-3851	368	5	in	in	ADP
cana-3851	368	6	medicine	medicine	NOUN
cana-3851	368	7	,	,	PUNCT
cana-3851	368	8	44(3	44(3	NOUN
cana-3851	368	9	)	)	PUNCT
cana-3851	368	10	,	,	PUNCT
cana-3851	368	11	703–712	703–712	NUM
cana-3851	368	12	.	.	PUNCT
cana-3851	369	1	https://doi.org/10.1007/s13246-021-01019-w	https://doi.org/10.1007/s13246-021-01019-w	NOUN