Microsoft Word - Title-template_sbornik36.doc


Mathematical Problems of Computer Science 36, 41--50, 2012. 

 
41 

 

 
 

Digital Mammogram Segmentation and Abnormal Masses 
Detection System 

 
Armen Sahakyan 

 

Institute for Informatics and Automation Problems of NAS of RA 
e-mail: armensahakyan@gmail.com 

 
Abstract 

 
   Digital Mammogram has emerged as the most popular screening 

technique for early detection of Breast Cancer and other abnormalities. Raw digital 
mammograms are medical images that are difficult to interpret so we need to develop 
Computer Aided Diagnosis (CAD) systems that will improve detection of 
abnormalities in mammogram images. Extraction of the breast region by delineation 
of the breast contour allows the search for abnormalities to be limited to the region of 
the breast. We need to perform essential pre-processing steps to suppress artifacts, 
enhance the breast region and then extract breast region by the process of 
segmentation. In this paper we present an automated system for detection of 
abnormal masses by anatomical segmentation of Breast Region of Interest (ROI). 

 
References 
 

[1] L.-M. Wun, R. M. Merrill, and E. J. Feuer, "Estimating Lifetime and Age-Conditional Probabilities 
of Developing Cancer," Lifetime Data Analysis, vol. 4, pp. 169-186, 1998. 
 
[2] "WHO Cancer Facts," http://www.who.int/cancer/en/, 2009. 

[3] L. Shen, R. Rangayyan, and J. Desaultels, “Detection and Classification Mammographic 
Calcifications”, International Journal of Pattern Recognition and Artificial Intelligence. 
Singapore: World Scientific,  pp. 1403–1416, 1994.  

[4] F. Aghdasi, R.Ward, and B. Palcic, “Restoration of mammographic images in the presence 
of signal-dependent noise”, in State of the Art in Digital Mammographic Image Analysis. 
Singapore: World Scientific, vol. 7, pp. 42–63, 1994.  
 
[5] Y. Chitre, A. Dhawan, and M. Moskowtz, “Artificial neural network based classification of 
mammographic microcalcifications using image structure features”, in State of the Art of 
Digital Mammographic Image Analysis. Singapore: World Scientific,  vol. 7, pp. 167–197, 
1994. 
 
[6] Pisano and F. Shtern,“Image processing and computer-aided diagnosis in digital 
mammography,” in State of the Art of Digital Mammographic Image Analysis. Singapore: 
World Scientific, vol. 7, pp. 280–291, 1994. 
 



Digital Mammogram Segmentation and Abnormal Masses Detection System 42 

[7] A. Sahakyan, H. Sarukhanyan, "Automatic Segmentation of the Breast Region in Digital 
Mammograms", Computer Science and Information Technologies, Proceedings of the 
Conference, pp. 386 - 389, Yerevan, Armenia, September 26-30, 2011. 

 
[8] Indra Kanta Maitra ; Sanjay Nag and Prof. Samir K. Bandyopadhyay, "Automated Digital 
Mammogram Segmentation For Detection Of Abnormal Masses Using Binary Homogeneity 
Enhancement Algorithm", Indian Journal of Computer Science and Engineering, Issue 3, vol. 2, 
pp. 416-427, 2011. 
 
[9] J. Suckling et al., “The Mammographic Image Analysis Society digital mammogram 
database”, Exerpta Medica., vol. 1069, pp. 375– 378, 1994. 

 
Âí³ÛÇÝ Ù³Ùá·ñ³ÙÝ»ñÇ ë»·Ù»Ýï³íáñÙ³Ý ¨ ³ÝÝáñÙ³É ½³Ý·í³ÍÝ»ñÇ 

ѳÛï³µ»ñÙ³Ý Ñ³Ù³Ï³ñ· 
 

². ê³Ñ³ÏÛ³Ý 
 

²Ù÷á÷áõÙ 
 

ÎñÍù³·»ÕÓÇ ù³ÕóÏ»ÕÇ ¨ ³ÛÉ ³ÝÝáñÙ³É ½³Ý·í³ÍÝ»ñÇ í³Õ  ѳÛïݳµ»ñÙ³Ý Ù»Ãá¹Ý»ñÇó ¿ 
Ãí³ÛÇÝ Ù³Ùá·ñ³ýdzÝ։ Âí³ÛÇÝ Ù³Ùá·ñ³ÙÝ»ñÁ µÅßÏ³Ï³Ý å³ïÏ»ñÝ»ñ »Ý, áñáÝó 
í»ñ³Ùß³ÏÙ³Ý ¨ í»ñÉáõÍáõÃÛ³Ý Ñ³Ù³ñ ³ÝÑñ³Å»ßï ¿  Ùß³Ï»É Ñ³Ù³Ï³ñ·ã³ÛÇÝ ³ËïáñáßÙ³Ý 
¹Ç³·ÝáëïÇÏ (CAD) ѳٳϳñ·, áñÁ Ïû·ÝÇ ³ÝÝáñÙ³É ½³Ý·í³ÍÝ»ñÇ Ñ³Ûïݳµ»ñÙ³ÝÁ։ ÎñÍùÇ 
»½ñ³·Í»ñÇ ßñç³·ÍÙ³Ý û·ÝáõÃÛ³Ùµ, ÏñÍù³ÛÇÝ ßñç³ÝÇ ³é³ÝÓݳóáõÙÁ ÃáõÛÉ ¿ ï³ÉÇë, áñ 
³ÝÝáñÙ³É ½³Ý·í³ÍÝ»ñÇ áñáÝáõÙÁ ë³Ñٳݳ÷³ÏíÇ ÙdzÛÝ ÏñÍùÇ ßñç³·Íáí։ ²ÝÑñ³Å»ßï ¿ 
Çñ³Ï³Ý³óÝ»É ³ÕÙáõÏÝ»ñÇ Ñ»é³óÙ³Ý Ý³Ë³Ùß³ÏÙ³Ý ù³ÛÉ»ñ, µ³ñ»É³í»É ÏñÍù³·»ÕÓÇ 
å³ïÏ»ñÁ ¨ ³ÛÝáõÑ»ï¨ ë»·Ù»Ýï³íáñ»É։ ²Ûë Ñá¹í³ÍáõÙ Ý»ñϳ۳óí³Í ¿ ³ÝÝáñÙ³É 
½³Ý·í³ÍÝ»ñÇ Ñ³Ûïݳµ»ñÙ³Ý Íñ³·ñ³ÛÇÝ Ñ³Ù³Ï³ñ·, áñÁ Çñ³Ï³Ý³óÝáõÙ ¿  å³ïÏ»ñÇ 
Ñ»ï³ùñùÇñ ïÇñáõÛÃÝ»ñÇ (ROI) ë»·Ù»Ýï³íáñáõÙÁ։ 

 
 

Ñèñòåìà öèôðîâîé ñåãìåíòàöèè ìàììîãðàì è îáíàðóæåíèÿ 
àíîìàëüíûõ ìàññ 

 

À. Ñààêÿí 
 

Àííîòàöèÿ 
 
Öèôðîâàÿ ìàììîãðàôèÿ ÿâëÿåòñÿ ñàìîé ïîïóëÿðíîé òåõíèêîé ñêðèíèíãà äëÿ 
ðàííåãî âûÿâëåíèÿ ðàêà ìîëî÷íîé æåëåçû è äðóãèõ íàðóøåíèé. Öèôðîâûå 
ìàììîãðàìû ÿâëÿþòñÿ ìåäèöèíñêèìè èçîáðàæåíèÿìè è äëÿ èõ îáðàáîòêè 
íûæíî ðàçàðàáîòàòü âñïîìîãàòåëüíûå äèàãíîñòè÷åñêèå êîìïüþòåðíûå (CAD) 
ñèñòåìû, êîòîðûå áóäóò ñïîñîáñòâîâàòü âûÿâëåíèþ íàðóøåíèé. Îòìå÷åíèå 
îáëàñòè ãðóäè êîíòóðîì ïîçâîëÿåò ïîèñêû àíîìàëèè áûòü îðãàíèÿåííûì 
òîëüêî îáëàñòüþ ãðóäè. Ìû äîëæíû âûïîëíèòü øàãè ïðåâàðèòåëüíîé 
îáðàáîòêè, ÷òîáû ïîäàâèòü øóìû, óëóòøèòü èçîáðàæåíèå îáëàñòè ãðóäè è 
çàòåì îòìåòèòü îáëàñòü ãðóäè ïðîöåññîì ñåôìåíòàöèè. Â ýòîé ñòàòüå ìû 
ïðåäñòàâëÿåì àâòîìàòèçèðîâàííóþ ñèñòåìû äëÿ îáíàðóæåíèÿ àíîìàëüíûõ 
ìàññ àíàòîìè÷åñêîé ñåôìåíòàöèåé îáëàñòè èíòåðåñà (ROI) ãðóäè.