À¯¹æÃÔ¿µ¼ú¿¡¼ ÀΰøÁö´ÉÀÇ Àû¿ë: ¾Ë°í¸®Áò °³¹ß ¹× Æò°¡ °üÁ¡
Applications of Artificial Intelligence in Mammography from a Development and Validation Perspective
´ëÇÑ¿µ»óÀÇÇÐȸÁö 2021³â 82±Ç 1È£ p.12 ~ p.28
±è±âȯ(Kim Ki-Hwan) - Lunit Inc.
ÀÌ»óÇù(Lee Sang-Hyup) - Lunit Inc.
Abstract
À¯¹æÃÔ¿µ¼úÀº À¯¹æ¾Ï °ËÁø ¹× Áø´ÜÀ» À§ÇÑ ±âº»ÀûÀÎ ¿µ»ó °Ë»çÀÌÁö¸¸, Æǵ¶ÀÌ ¾î·Á¿ì¸ç ³ôÀº ¼÷·Ãµµ¸¦ ÇÊ¿ä·Î ÇÑ´Ù°í Àß ¾Ë·ÁÁ® ÀÖ´Ù. ÀÌ·¯ÇÑ ¾î·Á¿òÀ» ±Øº¹Çϱâ À§ÇØ ÃÖ±Ù ¸î ³â »çÀÌ¿¡ ÀΰøÁö´ÉÀ» ÀÌ¿ëÇÑ À¯¹æ¾Ï °ËÃâ ¾Ë°í¸®ÁòµéÀÌ È°¹ßÈ÷ ¿¬±¸µÇ°í ÀÖ´Ù. º» Á¾¼³¿¡¼ ÀúÀÚ´Â °íÀüÀûÀÎ computer-aided detection ¼ÒÇÁÆ®¿þ¾î ´ëºñ ÃÖ±Ù ¸¹ÀÌ »ç¿ëµÇ´Â µö·¯´×ÀÇ Æ¯Â¡À» ¾Ë¾Æº¸°í, µö·¯´× ¾Ë°í¸®ÁòÀÇ °³¹ß ¹æ¹ý°ú ÀÓ»óÀû °ËÁõ ¹æ¹ý¿¡ ´ëÇؼ ±â¼úÇÏ¿´´Ù. ¶ÇÇÑ µö·¯´× ±â¹ÝÀÇ °ËÁø À¯¹æÃÔ¿µ¼úÀÇ Æǵ¶ ¹æ¹ý ºÐ·ù, À¯¹æ Ä¡¹Ðµµ Æò°¡, ±×¸®°í À¯¹æ¾Ï À§Çèµµ ¿¹Ãø ¸ðµ¨ µîÀ» À§ÇÑ µö·¯´× ¿¬±¸µéµµ ¼Ò°³ÇÏ¿´´Ù. ¸¶Áö¸·À¸·Î À¯¹æÃÔ¿µ¼ú °ü·Ã ÀΰøÁö´É ±â¼úµé¿¡ ´ëÇÑ ¿µ»óÀÇÇаú Àü¹®ÀÇÀÇ °ü½É°ú ÀÇ°ßÀÇ Çʿ伺À» ±â¼úÇÏ¿´´Ù.
Mammography is the primary imaging modality for breast cancer detection; however, a high level of expertise is needed for its interpretation. To overcome this difficulty, artificial intelligence (AI) algorithms for breast cancer detection have recently been investigated. In this review, we describe the characteristics of AI algorithms compared to conventional computer-aided diagnosis software and share our thoughts on the best methods to develop and validate the algorithms. Additionally, several AI algorithms have introduced for triaging screening mammograms, breast density assessment, and prediction of breast cancer risk have been introduced. Finally, we emphasize the need for interest and guidance from radiologists regarding AI research in mammography, considering the possibility that AI will be introduced shortly into clinical practice.
Å°¿öµå
Mammography, Artificial Intelligence, Breast Cancer
¿ø¹® ¹× ¸µÅ©¾Æ¿ô Á¤º¸
µîÀçÀú³Î Á¤º¸
À¯È¿¼º°á°ú(Recomendation)
In this review, authors describe the characteristics of AI algorithms compared to conventional computer-aided diagnosis software.