Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
¹«¸ ÀÚ±â°ø¸í¿µ»ó¿¡¼ Áö¿ªÀû È®·ü ¾ÆƲ¶ó½º Á¤·Ä ¹× ¹Ýº¹Àû ±×·¡ÇÁ ÄÆÀ» ÀÌ¿ëÇÑ Àü¹æ½ÊÀÚÀÎ´ë ºÐÇÒ |
¿µ¹®Á¦¸ñ(English Title) |
Anterior Cruciate Ligament Segmentation in Knee MRI with Locally-aligned Probabilistic Atlas and Iterative Graph Cuts |
ÀúÀÚ(Author) |
ÀÌÇÑ»ó
È«Çï·»
Han Sang Lee
Helen Hong
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 42 NO. 10 PP. 1222 ~ 1230 (2015. 10) |
Çѱ۳»¿ë (Korean Abstract) |
¹«¸ ÀÚ±â°ø¸í¿µ»ó¿¡¼ Àü¹æ½ÊÀÚÀδëÀÇ ºÐÇÒÀº ¹à±â°ªÀÇ ºÒ±ÕÀϼº ¹× ÁÖº¯ Á¶Á÷µé°úÀÇ À¯»ç
¹à±â°ª Ư¼ºÀ¸·Î ÀÎÇØ ±âÁ¸ ºÐÇÒ±â¹ýÀÇ Àû¿ë¿¡ ÇÑ°è°¡ ÀÖ´Ù. º» ³í¹®¿¡¼´Â Áö¿ªÀû Á¤·ÄÀ» ÅëÇÑ È®·ü¾ÆƲ¶ó½º »ý¼º ¹× ¹Ýº¹Àû ±×·¡ÇÁ ÄÆÀ» ÅëÇÑ ´ÙÁß¾ÆƲ¶ó½º ±â¹Ý Àü¹æ½ÊÀÚÀÎ´ë ºÐÇÒ±â¹ýÀ» Á¦¾ÈÇÑ´Ù. ù°, Àü¿ª ¹× Áö¿ªÀû ´ÙÁß¾ÆƲ¶ó½º °Ã¼Á¤ÇÕÀ» ÅëÇØ Àü¹æ½ÊÀÚÀδëÀÇ È®·ü¾ÆƲ¶ó½º¸¦ »ý¼ºÇÑ´Ù. µÑ°, »ý¼ºµÈ È®·ü¾ÆƲ¶ó½º¸¦ ÀÌ¿ëÇÏ¿© ÃÖ´ë»çÈÄÃßÁ¤ ¹× ±×·¡ÇÁ ÄÆÀ» ÅëÇÏ¿© Àü¹æ½ÊÀÚÀδë Ãʱ⠺ÐÇÒÀ» ¼öÇàÇÑ´Ù. ¼Â°, ¸¶½ºÅ© ±â¹Ý °Ã¼Á¤ÇÕÀ» ÅëÇÑ Çü»óÁ¤º¸ °³¼± ¹× ¹Ýº¹Àû ±×·¡ÇÁ ÄÆÀ» ÅëÇØ Àü¹æ½ÊÀÚÀÎ´ë ºÐÇÒ °³¼±À» ¼öÇàÇÑ´Ù. Á¦¾È¹æ¹ýÀÇ ¼º´ÉÆò°¡¸¦ À§ÇÏ¿© À°¾ÈÆò°¡ ¹× Á¤È®¼ºÆò°¡¸¦ ¼öÇàÇÏ¿´À¸¸ç, Æò°¡ °á°ú Á¦¾È¹æ¹ýÀÇ Dice À¯»çµµ´Â 75.0%, Æò±ÕÇ¥¸é°Å¸®´Â 1.7ȼÒ, Á¦°ö±ÙÇ¥¸é°Å¸®´Â 2.7ȼҷμ ±âÁ¸ ±×·¡ÇÁ ÄÆ ¹æ¹ý¿¡ ºñÇÏ¿© Àü¹æ ½ÊÀÚÀδëÀÇ ºÐÇÒÁ¤È®µµ°¡ °¢°¢ 12.8%, 22.7%, ¹× 22.9% Çâ»óµÈ °ÍÀ¸·Î ³ªÅ¸³µ´Ù. |
¿µ¹®³»¿ë (English Abstract) |
Segmentation of the anterior cruciate ligament (ACL) in knee MRI remains a challenging task due to its inhomogeneous signal intensity and low contrast with surrounding soft tissues. In this paper, we propose a multi-atlas-based segmentation of the ACL in knee MRI with locally-aligned probabilistic atlas (PA) in an iterative graph cuts framework. First, a novel PA generation method is proposed with global and local multi-atlas alignment by means of rigid registration. Second, with the generated PA, segmentation of the ACL is performed by maximum-aposteriori(MAP) estimation and then by graph cuts. Third, refinement of ACL segmentation is performed by improving shape prior through mask-based PA generation and iterative graph cuts. Experiments were performed with a Dice similarity coefficients of 75.0%, an average surface distance of 1.7 pixels, and a root mean squared distance of 2.7 pixels, which increased accuracy by 12.8%, 22.7%, and 22.9%, respectively, from the graph cuts with patient-specific shape constraints.
|
Å°¿öµå(Keyword) |
¹«¸ ÀÚ±â°ø¸í¿µ»ó
Àü¹æ½ÊÀÚÀδë
¿µ»óºÐÇÒ
´ÙÁß ¾ÆƲ¶ó½º ºÐÇÒ
knee MRI
anterior cruciate ligament
image segmentation
multi-atlas segmentation
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|