Detection of Dental Restorations in Digital Panoramic Radiographs Using YOLOv11

AbstractPurposeThe aim of this study was to evaluate the performance of the YOLOv11 deep learning–based object detection model in detecting dental restorations on digital panoramic radiographs.Materials and MethodsA total of 320 panoramic radiographs obtained from adult patients were included in this study. Four types of dental restorations—amalgam, composite, crown, and bridge—were manually annotated and used for model training and evaluation. The dataset was divided into training and testing subsets at a ratio of 75% and 25%, respectively. A validation subset was derived from the training data. Model performance was assessed using precision, recall, F1-score, and mean Average Precision (mAP) metrics.ResultsThe YOLOv11 model achieved an overall precision of 0.663, recall of 0.665, and F1-score of 0.663 across all restoration categories. The mAP@50 value was 0.671, while the mAP@50–95 value was 0.432, indicating variations in detection performance across different Intersection over Union thresholds. Differences in detection performance were observed among the various types of dental restorations.ConclusionThe findings indicate that YOLOv11 demonstrates measurable potential as an automated support tool for detecting dental restorations on panoramic radiographs; however, the achieved performance remains lower than that reported in several previous studies. Successful clinical integration of such AI-assisted systems requires further optimization and validation using larger and more heterogeneous datasets to enhance generalizability and clinical applicability.Keywords: deep learning; dental restorations; panoramic radiography; YOLOv11