µðÁöÅÐ À¯¹æ¿µ»ó¿¡¼ ¹Ì¼¼¼®È¸ÈÀÇ ÀÚµ¿±ºÁýÈ ±â¹ý °³¹ß
Development of Automatic Cluster Algorithm for Microcalcification in Digital Mammography
ÃÖ¼®À± ( Choi Seok-Yoon ) - °í·Á´ëÇб³ ´ëÇпø ÀǰøÇÐÇùµ¿
±èâ¼ö ( Kim Chang-Soo ) - ºÎ»ê°¡Å縯´ëÇб³ º¸°Ç°úÇдëÇÐ ¹æ»ç¼±°ú
±èâ¼ö ( Kim Chang-Soo ) - ºÎ»ê°¡Å縯´ëÇб³ º¸°Ç°úÇдëÇÐ ¹æ»ç¼±Çаú
Abstract
À¯¹æ ÃÔ¿µ¼ú(Digital mammography)Àº À¯¹æ¾ÏÀÇ Á¶±â Áø´Ü¿¡¼ ¸Å¿ì Áß¿äÇÑ Áø´Ü ¹æ¹ýÀ¸·Î¼ ºñÃËÁö¼º À¯¹æ¾ÏÀÇ Á¶±â ¹ß°ßÀ²À» ³ô¿© À¯¹æ¾Ï¿¡ µû¸¥ ¿©¼ºÀÇ »ç¸Á·üÀ» °¨¼Ò½Ã۰í ÀÖ´Ù. ±× Áß¿¡¼µµ À¯¹æ º´º¯ÀÇ ¹Ì¼¼¼®È¸È(Microcalcification)´Â Á¶±â À¯¹æ¾ÏÀÇ Áø´Ü¿¡ ÀÖ¾î¼ Áß¿äÇÑ º´º¯À¸·Î º¸°í µÇ°í ÀÖÀ¸¸ç, ¼±º° °Ë»ç·Î ÀÓ»óÀû À¯¿ë¼ºÀÌ È®¸³µÈ »óÅÂÀÌ´Ù. À¯¹æ ÃÔ¿µ¼ú¿¡¼ ¹Ì¼¼¼®È¸È ¼Ò°ßÀº ¿µ»óÀÇÇаú Àü¹®Àǰ¡ ÆÇµ¶ÇÏ¿© Á¶Á÷ °Ë»ç¿¡¼ ¾ç¼º ¹× ¾Ç¼º º´º¯¿¡ ´ëÇÏ¿© °¢°¢ ±ºÁýÀÇ °³¼ö, ±ºÁý ´ç ¼®È¸È ¼ö, ¹Ì¼¼¼®È¸È Å©±â¿Í ¹üÀ§, ¹Ì¼¼¼®È¸È ÇüÅÂ, µ¿¹Ý Á¾±«ÀÇ À¯¹« µîÀ» ºÐ¼®ÇÏ¿© ÃÖÁ¾ÀûÀ¸·Î Áø´ÜÀ» È®Á¤ÇÑ´Ù. ±×·¯¹Ç·Î ±ºÁýÈµÈ ¹Ì¼¼¼®È¸ÈÀÇ Á¤º¸´Â À¯¹æ¾Ï ¿¹Ãø¿¡ ÀÖ¾î ÀÓ»óÀûÀÎ ½ÇÁú Á¤º¸¸¦ °¡Áö°í ÀÖÀ¸¸ç, Àǻ翡°Ô Áø´ÜÀ» À§ÇÑ °Ë»çÀÇ ±âº»ÀûÀÎ °¡À̵å¶óÀÎÀ» Á¦½ÃÇÑ´Ù. µû¶ó¼ º» ¿¬±¸¿¡¼´Â À¯¹æ ÃÔ¿µ¼úÀÇ µðÁöÅÐ ¿µ»ó¿¡ ³ªÅ¸³ ¹Ì¼¼¼®È¸ÈÀÇ Á¤·®ÀûÀÎ °è»êÀ» À§Çؼ DoG filter, Adaptive thresholding, Expectation MaximizationÀÇ 3´Ü°è¸¦ Á¦¾ÈÇÑ´Ù. Á¦¾ÈÇÑ ¾Ë°í¸®µëÀ» ½ÇÇèÀ» ÅëÇÏ¿© ±ºÁýÈ ¹× °¢ Ŭ·¯½ºÅÍ ³»ÀÇ ¹Ì¼¼¼®È¸ÈÀÇ ºÐÆ÷ °³¼ö, ±æÀ̸¦ ÃøÁ¤ÇÏ¿´À¸¸ç, ÀÓ»óÀÇ »ç¿¡°Ô µðÁöÅÐ À¯¹æ¿µ»óÀÇ ºÐ¼®À» ÅëÇÏ¿© Ãʱâ À¯¹æ¾Ï Áø´ÜÀÇ ÁöÇ¥¸¦ Á¦½ÃÇÒ °ÍÀ¸·Î »ç·áµÈ´Ù. ±×¸®°í ÀÌ´Â °´°üÀûÀÎ À¯¹æ¾Ï ÄÄÇ»ÅÍÀÚµ¿°ËÃâ(CAD)¿¡ »ç¿ëµÉ ¼ö ÀÖ´Â º´º¯ÀÇ Á¤º¸·Î¼ °¡´É¼ºÀ» º¸¿´´Ù.
Digital Mammography is an efficient imaging technique for the detection and diagnosis of breast pathological disorders. Six mammographic criteria such as number of cluster, number, size, extent and morphologic shape of microcalcification, and presence of mass, were reviewed and correlation with pathologic diagnosis were evaluated. It is very important to find breast cancer early when treatment can reduce deaths from breast cancer and breast incision. In screening breast cancer, mammography is typically used to view the internal organization. Clusterig microcalcifications on mammography represent an important feature of breast mass, especially that of intraductal carcinoma. Because microcalcification has high correlation with breast cancer, a cluster of a microcalcification can be very helpful for the clinical doctor to predict breast cancer. For this study, three steps of quantitative evaluation are proposed : DoG filter, adaptive thresholding, Expectation maximization. Through the proposed algorithm, each cluster in the distribution of microcalcification was able to measure the number calcification and length of cluster also can be used to automatically diagnose breast cancer as indicators of the primary diagnosis.
Ű¿öµå
À¯¹æ¾Ï; À¯¹æÃÔ¿µ¼ú; ÄÄÇ»ÅÍÀÚµ¿°ËÃâ; ¹Ì¼¼¼®È¸È; ±ºÁýÈ
Breast cancer; Digital Mammography; Computer-aided detection; Microcalcification; Cluster
KMID :
0357520090320010045
DOI :
¿ø¹® ¹× ¸µÅ©¾Æ¿ô Á¤º¸
µîÀçÀú³Î Á¤º¸