A Deep Learning and Intelligent Vision-Based Approach for Dental Health Detection

With the rapid development of artificial intelligence technology, deep learning has shown great potential in the field of medical image analysis, particularly in dental health detection. This paper designs and implements an automated dental health detection system based on the YOLOv8 object detection algorithm. The system first preprocesses collected oral images, then uses the YOLOv8 model for end-to-end identification of common lesion areas such as cavities and tartar. Users can upload images or videos through the front-end interface to obtain real-time detection results, and support historical record queries to track changes in dental health. Experimental results show that as the confidence threshold increases, the model’s precision significantly increases: at a threshold of 0.8, the overall precision reaches 95.6%, and at 0.988, the precision can reach 1.0, providing a highly reliable basis for clinical diagnosis. This system effectively improves the efficiency and accuracy of dental disease detection and has good clinical application prospects.