대한구강악안면병리학회지 제45권 제2호 (p.59-65)

|원 저|
파노라마방사선사진상에서 골다공증의 판독에서 인공지능의 민감영역 연구

Sensitive Area of Artificial Intelligence in Interpreting Osteoporosis on Panoramic Radiograph
키워드 :
Panoramic radiograph,Neural network,Osteoporosis,Mandible

목차

<Abstract>
Ⅰ. INTRODUCTION
Ⅱ. MATERIALS and METHODS
   1. 연구대상
   2. 파노라마방사선사진을 이용한 골다공증의판독
   3. 데이터 전처리 및 데이터 증강
   4. Convolutional Neural Networks 학습 및테스트
   5. CNN의 민감부위의 시각화
Ⅲ. RESUTLS
Ⅳ. DISCUSSION
REFERENCES

초록

Artificial intelligence, has been applied in interpreting osteoporosis on dental panoramic radiograph with high accuracy. The purpose of this study was to investigate the sensitive area of convolutional neural network(CNN), one of artificial intelligence, in interpreting osteoporosis on dental panoramic radiograph. Dental panoramic radiographs taken from 1,170 female (49.19 ±21.91 average age, 21 minimum age, and 84 maximum age) were selected for this study. Two oral maxillofacial radiologists agreed upon interpreting osteoporosis by interpreting mandibular inferior cortical changes. The region of interest included upper and lower jaws for training and testing CNN in interpreting osteoporosis. A filter which was set to look for image characteristics moved through the entire panoramic radiography to identify sensitive areas that distinguish normal groups and osteoporosis patients. In interpreting osteoporosis on panoramic radiograph, CNN responded sensitively at the cancellous bone of the upper and lower jaws while oral maxillofacial radiologists interpreted mandibular inferior cortical change.