Panoramic Dental X-Ray Restorative Elements Segmentation using Hybrid Deep Learning

Panoramic radiography is a commonly used imaging technique for dental X-rays, it is used as a diagnostics tool in dentistry. The study introduced a hybrid deep learning approach for detecting and segmenting dental restorative elements from panoramic dental X-rays. By integrating the You Look Only Once (YOLO v8) model for object detection and the Segment Anything Model (SAM) for segmentation, the aim is to enhance the identification of different dental restorative elements such as dental implants, crowns, fillings, and root canals. The datasets of the study comprised 1290 dental X-ray images. The YOLO model effectively recognizes regions of interest and generates bounding boxes and then for achieving precise segmentation SAM is utilized. The results demonstrate high accuracy for classification rates of 95% for fillings, 88% for crowns, 93% for root canals, and 97% for implants and the Intersection over Union (IoU) metrics results also improve systems accuracy. The results show significant improvement in accuracy and highlight the effectiveness of the hybrid approach in refining diagnostic precision and enhancing efficiency in dental imaging.