Ai-aided diagnosis of oral X-ray images of periapical films based on deep learning

Oral X-ray images provide a useful technical means by which dentists examine teeth for dental problems, but the diagnostic process is defective due to its over-reliance on dentists' subjective judgments, lack of objective criteria, etc. In this context, this study examined the AI-aided diagnosis of periapical films based on deep learning. .Based on YOLOv7-X, a YOLO-DENTAL network architecture was used to detect dental caries, dental defects, periapical lesions, and coronal restorations in periapical films. Firstly, the coordinate attention (CA) mechanism was introduced into the backbone feature extraction network, and a backbone-CA structure was presented to enhance the feature extraction capability of the network. Secondly, a simplified Bi-FPN structure was put forward and applied to the feature fusion part of the network to effectively improve its multi-scale feature fusion effect. Thirdly, the existing anchor-based detection head was replaced by an anchor-free decoupled head to simplify operational parameters while improving the generalized detection capability of the model over lesion regions. In the loss function part, existing CIoU loss was replaced by SIoU loss, a border loss function containing direction information. The focal loss containing a weight factor was introduced in calculating confidence loss as a substitute for the existing binary cross entropy loss function to balance positive and negative samples. Meanwhile, a study of ablation experiment was completed. The results validated the positive gain effect of each optimization strategy on the model. The final YOLO-DENTAL network structure exhibited an mAP value of 86.81%, higher than that of YOLOv7-X (79.95%). The effect of aided diagnosis was well achieved.