Faster-RCNN based intelligent detection and localization of dental caries

• The object detection algorithm of Faster-RCNN was used to automatically determine the location of caries in periapical films, which solved the limitation of current AI application in caries assisted diagnosis. • The ResNet50, which is with the ability to solve network degradation, is used for feature extraction of Faster-RCNN. And the pre-training network is loaded simultaneously to improve the detection accuracy of the network. • The deploying of caries-detection model on the server and the building of caries-detection online platform endows the whole work with higher clinical significance. This work can also provide references for AI-assisted diagnosis in other medical fields. The use of AI (artificial intelligence) for auxiliary diagnosis of medical images is a current development trend, where the automatic recognition of lesion location is a key problem in AI-assisted diagnosis of medical images. In the past, most of the studies on AI-assisted diagnosis of dental caries based on X-ray image primarily focused on the classification of abnormalities rather than the detection and localization of dental caries, which is not conducive to expanding the clinical application of this technique. Accordingly, in this work, an AI-assisted diagnosis method is developed that employs Faster-RCNN to predict the number and locations of caries lesions based on periapical films. To support the application of this diagnosis method, an open Web platform for detection of dental caries is constructed in the following way: First, clinical samples acquired by professional doctors are collected and labeled to build the sample space and label space. Then, a caries detection model is built through training and testing on samples. Finally, the contents of Web platform are set up, the layout is configured through HTML/CSS programming, and the model is deployed on Alibaba cloud server using the Flask framework. After the diagnosis platform is put into operation, doctors and patients can upload the medical images to be tested onto the website of platform, where test results can be obtained. These test results can help doctors diagnose the diseases with higher efficiency and precision.