Àá½Ã¸¸ ±â´Ù·Á ÁÖ¼¼¿ä. ·ÎµùÁßÀÔ´Ï´Ù.

À¯Ä¡ÀÇ Ä¡±Ù´Ü ¹æ»ç¼± »çÁø¿¡¼­ µö ·¯´× ¾Ë°í¸®ÁòÀ» ÀÌ¿ëÇÑ ¸ðµ¨ÀÇ ÀÎÁ¢¸é ¿ì½ÄÁõ °´Ã¼ ŽÁö ´É·ÂÀÇ Æò°¡

Assessment of the Object Detection Ability of Interproximal Caries on Primary Teeth in Periapical Radiographs Using Deep Learning Algorithms

´ëÇѼҾÆÄ¡°úÇÐȸÁö 2023³â 50±Ç 3È£ p.263 ~ 276
ÀüÈ«ÁÖ, ±è¼±¹Ì, ÃÖ³²±â,
¼Ò¼Ó »ó¼¼Á¤º¸
ÀüÈ«ÁÖ ( Jeon Hong-Ju ) - 
±è¼±¹Ì ( Kim Seon-Mi ) - 
ÃÖ³²±â ( Choi Nam-Ki ) - 

Abstract

ÀÌ ¿¬±¸ÀÇ ¸ñÀûÀº ¼Ò¾ÆÀÇ Ä¡±Ù´Ü ¹æ»ç¼± »çÁø¿¡¼­ ÀÎÁ¢¸é ¿ì½ÄÁõ °´Ã¼ ŽÁö ÀÇ °´Ã¼ ŽÁö¸¦ À§ÇØ YOLO (You Only Look Once)¸¦ »ç¿ëÇÑ ¸ðµ¨ÀÇ ¼º´ÉÀ» Æò°¡ÇÏ´Â °ÍÀÌ´Ù. M6 µ¥ÀÌÅͺ£À̽º¿¡¼­ ÇнÀÀڷᱺÀ¸·Î 2016°³ÀÇ Ä¡±Ù´Ü ¹æ»ç¼± »çÁøÀÌ ¼±ÅõǾú°í ÀÌ Áß 1143 °³´Â ÇÑ ¸íÀÇ ¼÷·ÃµÈ Ä¡°úÀǻ簡 ÁÖ¼® µµ±¸¸¦ »ç¿ëÇÏ¿© ÀÎÁ¢¸é ¿ì½ÄÁõÀ» Ç¥½ÃÇÏ¿´´Ù. Ç¥½ÃÇÑ ÁÖ¼®À» µ¥ÀÌÅÍ ¼¼Æ®·Î º¯È¯ÇÑ ÈÄ ´ÜÀÏ ÇÕ¼º°ö ½Å°æ¸Á(CNN) ¸ðµ¨À» ±â¹ÝÀ¸·Î ÇÏ´ÂYOLO¸¦ µ¥ÀÌÅÍ ¼¼Æ®¿¡ ÇнÀ½ÃÄ×´Ù. 187°³ÀÇ Æò°¡Àڷᱺ¿¡¼­ °´Ã¼ ŽÁö ¸ðµ¨ ¼º´É Æò°¡¸¦À§ÇØ Á¤È®µµ, ÀçÇöÀ², ƯÀ̵µ, Á¤¹Ðµµ, NPV, F1-score, PR °î¼± ¹× AP¸¦ °è»êÇÏ¿´´Ù. °á°ú·Î Á¤È®µµ 0.95, ÀçÇöÀ² 0.94, ƯÀ̵µ 0.97, Á¤¹Ðµµ 0.82, NPV 0.96, F1-score 0.81, AP 0.83 À¸·Î ÀÎÁ¢¸é ¿ì½ÄÁõ ŽÁö¿¡ ÁÁÀº ¼º´ÉÀ» º¸¿´´Ù. ÀÌ ¸ðµ¨Àº Ä¡°úÀǻ翡°Ô Ä¡±Ù´Ü ¹æ»ç¼± »çÁø¿¡¼­ ÀÎÁ¢¸é ¿ì½ÄÁõ º´º¯À» °´Ã¼ ŽÁöÇÏ´Â µµ±¸·Î À¯¿ëÇÏ°Ô »ç¿ëµÉ ¼ö ÀÖ´Ù.

The purpose of this study was to evaluate the performance of a model using You Only Look Once (YOLO) for object detection of proximal caries in periapical radiographs of children. A total of 2016 periapical radiographs in primary dentition were selected from the M6 database as a learning material group, of which 1143 were labeled as proximal caries by an experienced dentist using an annotation tool. After converting the annotations into a training dataset, YOLO was trained on the dataset using a single convolutional neural network (CNN) model. Accuracy, recall, specificity, precision, negative predictive value (NPV), F1-score, Precision-Recall curve, and AP (area under curve) were calculated for evaluation of the object detection model¡¯s performance in the 187 test datasets. The results showed that the CNN-based object detection model performed well in detecting proximal caries, with a diagnostic accuracy of 0.95, a recall of 0.94, a specificity of 0.97, a precision of 0.82, a NPV of 0.96, and an F1-score of 0.81. The AP was 0.83. This model could be a valuable tool for dentists in detecting carious lesions in periapical radiographs.

Å°¿öµå

Object Detection; Dental Caries; Deep Learning; Radiographs

¿ø¹® ¹× ¸µÅ©¾Æ¿ô Á¤º¸

 

µîÀçÀú³Î Á¤º¸