PloS one
RCTE: A multi-class object detection framework for dental panoramic radiographs
Par Peng J, Liu J, Shen Y et 6 autres.
Contenu en anglais
Résumé
Background
Dental panoramic radiographs play an important role in oral disease screening, computer-aided diagnosis, and clinical treatment planning. However, accurate multi-class detection remains challenging due to small lesion sizes, ambiguous anatomical boundaries, insufficient multi-scale feature representation, and missed detections of complex dental structures.
Objective
This study aims to develop an accurate and efficient multi-class object detection framework for dental panoramic radiographs to improve the detection performance of small lesions, weak-boundary structures, and complex anatomical targets.