Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
ÈäºÎ CT ¿µ»ó¿¡¼ ĸ½¶ ³×Æ®¿öÅ© ±â¹ÝÀÇ µà¾ó-À©µµ¿ì ¾Ó»óºí ÇнÀÀ» ÅëÇÑ Æó¾Ï ÀÚµ¿ ºÐÇÒ |
¿µ¹®Á¦¸ñ(English Title) |
Automatic Segmentation of Lung Cancer in Chest CT Images through Capsule Network-based Dual-Window Ensemble Learning |
ÀúÀÚ(Author) |
È«Á¤¼ö
¹ÚÁø¿í
ÀÌÁöÀº
±è°æÈÆ
È«½Â±Õ
¹Ú»óÇö
Jungsoo Hong
Jinuk Park
Jieun Lee
Kyeonghun Kim
Seung-Kyun Hong
Sanghyun Park
ÀÌÁÖ¹Î
Á¤ÁÖ¸³
È«Çï·»
±èºÀ¼®
Jumin Lee
Julip Jung
Helen Hong
Bong-Seog Kim
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 48 NO. 08 PP. 0905 ~ 0912 (2021. 08) |
Çѱ۳»¿ë (Korean Abstract) |
Æó¾ÏÀÌ ºÒ±ÔÄ¢ÇÑ ÇüŸ¦ °®°Å³ª À¯»çÇÑ ¹à±â°ªÀ» °®´Â ÁÖº¯ ±¸Á¶¹°ÀÌ Á¸ÀçÇÏ´Â °æ¿ì ÈäºÎ CT ¿µ»ó¿¡¼ Æó¾ÏÀÇ °æ°è¸¦ Á¤È®ÇÏ°Ô ±¸ºÐÇÏ´Â °ÍÀÌ ¾î·Æ´Ù. º» ³í¹®¿¡¼´Â Æó¾Ï°ú ÁÖº¯ ±¸Á¶¹°°úÀÇ °ü°è¸¦ ÇнÀÇϱâ À§ÇØ Ä¸½¶ ³×Æ®¿öÅ©¸¦ È°¿ëÇÏ°í ÁÖº¯ ±¸Á¶¹°°úÀÇ ±¸ºÐÀ» À§ÇØ Æó â ¿µ»ó¿¡ Á¾°Ýµ¿ â ¿µ»óÀ» Ãß°¡·Î °í·ÁÇÏ´Â µà¾ó-À©µµ¿ì ¾Ó»óºí ³×Æ®¿öÅ©¸¦ Á¦¾ÈÇÑ´Ù. ù°, ÀÔ·Â CT ¿µ»óÀ» Æó â ¿µ»ó°ú Á¾°Ýµ¿Ã¢ ¿µ»óÀ¸·Î ¹à±â°ª Á¤±ÔÈ ¹× °ø°£ Á¤±Ôȸ¦ ¼öÇàÇÑ´Ù. µÑ°, µÎ °³ÀÇ ÀÔ·Â ¿µ»óÀ» ÀÌ¿ëÇØ °¢°¢ÀÇ Ä¸½¶ ³×Æ®¿öÅ©¸¦ ÇнÀÇÏ¿© Æó¾ÏÀ» ºÐÇÒÇÑ´Ù. ¼Â°, Æó â ¿µ»ó°ú Á¾°Ýµ¿ â ¿µ»óÀ» ÀÌ¿ëÇÑ ºÐÇÒ °á°ú¸¦ °¢ ¿µ»óÀÇ Æ¯¼º¿¡ ±â¹ÝÇÑ °¡ÁßÄ¡¸¦ ¹Ý¿µÇÏ¿© Æò±Õ ÅõÇ¥¸¦ ÅëÇØ ¾Ó»óºí ÇÔÀ¸·Î½á ÃÖÁ¾ ºÐÇÒ ¸¶½ºÅ©¸¦ »ý¼ºÇÑ´Ù. Á¦¾È ¹æ¹ýÀ» ÅëÇÑ ºÐÇÒ °á°ú, DSC´Â 75.98%·Î °¡ÁßÄ¡¸¦ °í·ÁÇÏÁö ¾ÊÀº ºÐÇÒ ¹æ¹ý ´ëºñ 0.53%p Çâ»óµÇ¾ú´Ù. ¶ÇÇÑ Æó¾ÏÀÌ ÁÖº¯ ±¸Á¶¹°¿¡ µÑ·¯½Î¿© À־ ºÐÇÒ Á¤È®µµ°¡ °³¼±µÇ¾ú´Ù. |
¿µ¹®³»¿ë (English Abstract) |
It is difficult to accurately segment lung cancer in chest CT images when it has an irregular shape or nearby structures have a similar intensity as lung cancer. In this study, we proposed a dual window ensemble network that uses a capsule network to learn the relationship between lung cancer and nearby structures and additionally considers the mediastinal window image with the lung window image to distinguish lung cancer from the nearby structures. First, intensity and spacing normalization was performed on the input images of the lung window setting and mediastinal window setting. Second, two types of 2D capsule network were performed with the lung and mediastinal setting images. Third, the final segmentation mask was generated by ensemble the probability maps of the lung and mediastinal window images through average voting by reflecting the weight based on the characteristics of each image. The proposed method showed a Dice similarity coefficient(DSC) of 75.98% which was 0.53% higher than the method not considering the weight of each window setting. Furthermore, segmentation accuracy was improved even when lung cancer was surrounded by nearby structures. |
Å°¿öµå(Keyword) |
´Ùº¯·® ½Ã°è¿ ¿¹Ãø
¿¬¼Ó ¿¹Ãø
µð³ëÀÌ¡ ÈÆ·Ã ±â¹ý
´ÙÁß Áֱ⼺
ÁÖÀÇ ±âÁ¦ ±â¹ý
multivariate time series forecasting
multi-step ahead prediction
denoising training
multiple seasonality
attention mechanism
ÈäºÎ CT ¿µ»ó
Æó¾Ï ºÐÇÒ
ĸ½¶ ³×Æ®¿öÅ©
µö ·¯´×
chest CT images
lung cancer segmentation
capsule network
deep learning
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|