AI-powered detection of dental anatomy: a YOLO-based approach.

OBJECTIVE This study aims to develop an AI-powered detection system for identifying dental anatomy-specifically tooth numbers and names-using YOLO (You Only Look Once) models to enhance diagnostic efficiency and automation in dentistry STUDY DESIGN: An annotated dataset of 724 high-resolution digital intraoral dental photographs (505 for training, 112 for validation, 107 for testing), obtained from Kaggle and Roboflow, was used. Multiple YOLO versions (YOLOv8l, YOLOv9c, YOLOv10l, YOLO11l) were implemented. Model performance was evaluated based on recall, precision, F1 score, and mean Average Precision (mAP@50).

RESULTS YOLOv8l achieved the highest F1 score (96.7%) and recall (97.8%). YOLO11l yielded the best precision (96.6%) and highest mAP@50 (98.4%). All models demonstrated strong potential in detecting teeth accurately from high-resolution images.

CONCLUSION YOLO-based models offer an effective solution for automatic detection of dental anatomy. Their integration into telemedicine and digital dentistry platforms can streamline diagnostic workflows, reduce manual workload, and expand access to dental care, particularly in underserved regions.