Fully automated deep learning model for detecting proximity of mandibular third molar root to inferior alveolar canal using panoramic radiographs

Abstract

ObjectiveThis study endeavored to develop a novel fully-automated deep learning model to determine the topographic relationship between mandibular third molar (MM3) roots and inferior alveolar canal (IAC) using panoramic radiographs (PR). Study DesignA total of 1570 eligible patients with MM3s who had paired PR and cone-beam computed tomography (CBCT) from January 2019 to December 2020 were retrospectively collected and randomly grouped into training (80%), validation (10%), and testing (10%) cohorts. Spatial relationship of MM3/IAC was assessed by CBCT and set as the ground truth. MM3-IACnet, a modified deep learning network based on YOLOv5 (You only look once) was trained to detect MM3/IAC proximity using PR. Its diagnostic performance was further compared with dentists, AlexNet, GoogleNet, VGG-16, ResNet-50, and YOLOv5 in another independent cohort with 100 high-risk MM3 defined as root overlapping with IAC on PR. ResultsThe MM3-IACnet performed best in predicting the MM3/IAC proximity as evidenced by the highest accuracy (0.885), precision (0.899), AUC value (0.95) and minimal time-spending compared to other models. Moreover, our MM3-IACnet outperformed other models in MM3/IAC risk prediction in high-risk cases. ConclusionMM3-IACnet model can assist clinicians in MM3s risk assessment and treatment planning by detecting MM3/IAC topographic relationship using PR.