• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö

Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö

Current Result Document : 4 / 38 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) ÆÐÄ¡ Ư¡ ÄھƮ ±â¹ÝÀÇ ÈäºÎ X-Ray ¿µ»ó¿¡¼­ÀÇ º´º¯ À¯¹« °¨Áö
¿µ¹®Á¦¸ñ(English Title) Leision Detection in Chest X-ray Images based on Coreset of Patch Feature
ÀúÀÚ(Author) ±èÇöºó   ÀüÁØö   Hyun-bin Kim   Jun-Chul Chun  
¿ø¹®¼ö·Ïó(Citation) VOL 23 NO. 03 PP. 0035 ~ 0045 (2022. 06)
Çѱ۳»¿ë
(Korean Abstract)
Çö´ë¿¡µµ ÀϺΠ¼Ò¿ÜµÈ Áö¿ª¿¡¼­´Â ÀÇ·á ÀηÂÀÇ ºÎÁ·À¸·Î ÀÎÇØ À§•ÁßÁõ ȯÀÚ¿¡ ´ëÇÑ Ä¡·á°¡ Áö¿¬µÇ´Â °æ¿ì°¡ ¸¹´Ù. ÀÇ·á µ¥ÀÌÅÍ¿¡ ´ëÇÑ ºÐ¼®À» ÀÚµ¿È­ÇÏ¿© ÀÇ·á ¼­ºñ½ºÀÇ Á¢±Ù¼º ¹®Á¦ ¹× ÀÇ·á Àη ºÎÁ·À» ÇؼÒÇÏ°íÀÚ ÇÏ´Â ¿¬±¸°¡ °è¼ÓµÇ°í ÀÖ´Ù. ÄÄÇ»ÅÍ ºñÀü ±â¹ÝÀÇ Áø·á ÀÚµ¿È­´Â ÈÆ·Ã ¸ñÀû¿¡ ´ëÇÑ µ¥ÀÌÅÍ ¼öÁý ¹× ¶óº§¸µ ÀÛ¾÷¿¡¼­ ¸¹Àº ºñ¿ëÀÌ ¿ä±¸µÈ´Ù. ÀÌ·¯ÇÑ Á¡Àº Èñ±ÍÁúȯÀ̳ª ½Ã°¢ÀûÀ¸·Î ¶Ñ·ÇÇÏ°Ô Á¤ÀÇÇϱ⠾î·Á¿î º´¸®Àû Ư¡ ¹× ±âÀüÀ» ±¸ºÐÇÏ´Â ÀÛ¾÷¿¡¼­ µÎµå·¯Áø´Ù. ÀÌ»ó ŽÁö´Â ºñÁöµµ ÇнÀ Àü·«À» äÅÃÇÔÀ¸·Î½á µ¥ÀÌÅÍ ¼öÁý ºñ¿ëÀ» Å©°Ô Àý°¨ÇÒ ¼ö ÀÖ´Â ¹æ¹ýÀ¸·Î ÁÖ¸ñµÈ´Ù. º» ³í¹®¿¡¼­´Â ±âÁ¸ÀÇ ÀÌ»ó ŽÁö ±â¹ýµéÀ» ±â¹ÝÀ¸·Î, ÈäºÎ X-RAY ¿µ»ó¿¡ ´ëÇØ ÀÌ»ó ŽÁö¸¦ ¼öÇàÇÏ´Â ¹æ¹ýÀ» ´ÙÀ½°ú °°ÀÌ Á¦¾ÈÇÑ´Ù. (1) ÃÖÀû Çػ󵵷Π»ùÇøµµÈ ÀÇ·á ¿µ»óÀÇ »ö»ó ¹üÀ§¸¦ Á¤±ÔÈ­ÇÑ´Ù. (2) ¹«º´º¯ ¿µ»óÀ¸·ÎºÎÅÍ ÆÐÄ¡ ´ÜÀ§·Î ±¸ºÐµÈ Áß°£ ¼öÁØ Æ¯Â¡ ÁýÇÕÀ» ÃßÃâÇÏ¿© ±× Áß ³ôÀº Ç¥Çö·ÂÀ» °¡Áø ÀϺΠƯ¡ º¤Å͵éÀ» ¼±Á¤ÇÑ´Ù. (3) ÃÖ±ÙÁ¢ ÀÌ¿ô Ž»ö ¾Ë°í¸®ÁòÀ» ±â¹ÝÀ¸·Î ¹Ì¸® ¼±Á¤µÈ ¹«º´º¯(Á¤»ó) Ư¡ º¤Å͵é°úÀÇ Â÷À̸¦ ÃøÁ¤ÇÑ´Ù. º» ³í¹®¿¡¼­´Â PA ¹æ½ÄÀ¸·Î ÃÔ¿µµÈ ÈäºÎ X-RAY ¿µ»óµé¿¡ ´ëÇÑ Á¦¾È ½Ã½ºÅÛÀÇ ÀÌ»ó ŽÁö ¼º´ÉÀ» ¼¼ºÎ Á¶°Ç¿¡ µû¶ó »ó¼¼È÷ ÃøÁ¤ÇÏ¿© Á¦½ÃÇÑ´Ù. PadChest µ¥ÀÌÅͼ¼Æ®·ÎºÎÅÍ ÃßÃâÇÑ ¼­ºê¼¼Æ®¿¡ ´ëÇØ 0.705 ºÐ·ù AUROC¸¦ º¸ÀÓÀ¸·Î½á ÀÇ·á ¿µ»ó¿¡ ´ëÇÑ ÀÌ»ó ŽÁö Àû¿ëÀÇ È¿°ú¸¦ ÀÔÁõÇÏ¿´´Ù. Á¦¾È ½Ã½ºÅÛÀº ÀÇ·á ±â°üÀÇ ÀÓ»ó Áø´Ü ¿öÅ©Ç÷ο츦 °³¼±ÇÏ´Â µ¥¿¡ À¯¿ëÇÏ°Ô »ç¿ëµÉ ¼ö ÀÖÀ¸¸ç, ÀÇ·á ¼­ºñ½º Á¢±Ù¼ºÀÌ ³·Àº Áö¿ª¿¡¼­ÀÇ Á¶±â Áø´ÜÀ» È¿À²ÀûÀ¸·Î Áö¿øÇÒ ¼ö ÀÖ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Even in recent years, treatment of first-aid patients is still often delayed due to a shortage of medical resources in marginalized areas. Research on automating the analysis of medical data to solve the problems of inaccessibility for medical services and shortage of medical personnel is ongoing. Computer vision-based medical inspection automation requires a lot of cost in data collection and labeling for training purposes. These problems stand out in the works of classifying lesion that are rare, or pathological features and pathogenesis that are difficult to clearly define visually. Anomaly detection is attracting as a method that can significantly reduce the cost of data collection by adopting an unsupervised learning strategy. In this paper, we propose methods for detecting abnormal images on chest X-RAY images as follows based on existing anomaly detection techniques. (1) Normalize the brightness range of medical images resampled as optimal resolution. (2) Some feature vectors with high representative power are selected in set of patch features extracted as intermediate-level from lesion-free images. (3) Measure the difference from the feature vectors of lesion-free data selected based on the nearest neighbor search algorithm. The proposed system can simultaneously perform anomaly classification and localization for each image. In this paper, the anomaly detection performance of the proposed system for chest X-RAY images of PA projection is measured and presented by detailed conditions. We demonstrate effect of anomaly detection for medical images by showing 0.705 classification AUROC for random subset extracted from the PadChest dataset. The proposed system can be usefully used to improve the clinical diagnosis workflow of medical institutions, and can effectively support early diagnosis in medically poor area.
Å°¿öµå(Keyword) ÀÌ»óŽÁö   X-Ray ¿µ»ó   ´Éµ¿ÇнÀ   ºñÁöµµÇнÀ   µö·¯´×   anomaly detection   X-Ray image   active learning   unsupervision   deep learning  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå