Automated detection and labeling of posterior teeth in dental bitewing X-rays using deep learning

Abstract

Standardized tooth numbering is crucial in dentistry for accurate recordkeeping, targeted procedures, and effective communication in both clinical and forensic contexts. However, conventional manual methods are prone to errors, time-consuming, and susceptible to inconsistencies. This study presents an artificial intelligence (AI)-powered system that uses a deep learning-based object detection approach to automate tooth numbering in bitewing radiographs (BRs). The system follows the widely accepted FDI two-digit notation system and employs a state-of-the-art YOLO architecture. This one-stage model provides fast inference by simultaneously performing object detection and classification. A comprehensive dataset of 3000 adult digital BRs was used for training and evaluation, covering various scenarios to improve the robustness of the tooth numbering approach. Performance was assessed based on precision, recall, and mean average precision (mAP). The proposed method showcases the potential of AI-powered systems utilizing sophisticated YOLO architectures to automatically detect and label teeth in dental X-rays. It achieved impressive results, demonstrating a precision of 0.99 and 0.963, recall of 0.995 and 0.965, and mAP of 0.99 and 0.963 for tooth detecting and tooth numbering, respectively. With an average inference time of 303 ms per BR when using a central processing unit (CPU) and 9.1 ms when using a graphics processing unit (GPU), the system seamlessly integrates into clinical workflows without sacrificing efficiency. This results in significant time savings for dental professionals while maintaining productivity in fast-paced clinical environments.

Keywords: Bitewing radiographs; Deep learning; Object detection; Tooth numbering; YOLO.