A high-precision framework for teeth instance segmentation in panoramic radiographs

Panoramic radiography plays a vital role in dental diagnosis and treatment, characterized by low radiation exposure, cost-effectiveness, and high accessibility, rendering it suitable for initial screening of oral diseases. However, inexperienced dentists may find it challenging to accurately interpret the information presented in panoramic images regarding the teeth, jaw bone, and maxillary sinus, which can result in missed diagnoses or misdiagnoses. This study proposed a deep learning-based framework for segmenting teeth and alveolar bone from panoramic radiographs and also provided examples of its application for disease diagnosis. This study incorporated relevant medical knowledge when designing algorithms, including graphic optimization algorithms and medical optimization algorithms. The experimental results indicated that the proposed segmentation method was very accurate in segmenting teeth and alveolar bone. The proposed method also improved the accuracy of disease diagnosis in panoramic radiographs, further demonstrating the clinical value of the method for segmenting teeth and alveolar bone.