Transformative Deep Learning Modular Segmentation for Dental Panoramic Radiographs

Purpose: Oral health encompasses conditions such as caries, periodontal disease, tooth loss, and oral cancer. Detection of oral conditions in time is crucial for effective prevention and treatment, yet clinical inspections have limitations in identifying hidden or inaccessible lesions. Dental radiography aids in the precise diagnosis but may be prone to misinterpretation. Computational techniques offer potential solutions, including tools for cavity detection and root canal guidance, with tooth detection as a foundational step. We create a modular teeth instance segmentation model to enhance this step. Methods: We annotated 935 dentomaxillary region bounding boxes on panoramic radiographs and segmented 605 of these images, generating 14,582 tooth polygon annotations. RetinaNet detected dentomaxillary regions and Cascade Mask R-CNN identified individual teeth. Results: Our system achieved satisfactory detection of the dentomaxillary region (92.446 mAP, 0.982 F1 score) and tooth segmentation (79.222 mAP, 0.989 F1 score), exceeding the benchmarks of comparable studies. Conclusions: Our proposal effectively segments teeth on panoramic radiographs, establishing a robust basis for future modules such as tooth numbering and caries detection. Besides aiding diagnosis, it can expedite epidemiological reports and find utility in forensic medicine.