A Feature Selection and Enhanced Reuse Framework for Detection and Classification of Dental Diseases in Panoramic Dental X-Rays Images

Panoramic dental X-rays images are crucial tools in dental diagnosis, and accurate detection of teeth and related lesions is essential for clinical decision-making. However, the complexity of tooth structures, variability in image quality, and scarcity of annotated data make achieving precise automatic target detection in this field challenging. In this study, a dental X-ray disease target detection framework based on feature selection and enhanced reuse is proposed to address these challenges. An improved convolutional neural network architecture is designed and implemented, combining selective receptive field fusion with shape-sensitive multi-scale feature extraction modules to enhance the ability to detect targets of different scales and shapes. Additionally, a novel feature reuse and skip fusion technique is introduced to further improve the utilization of features by the backbone network. To address the current lack of annotation for impacted teeth positions, an impacted tooth location image dataset named DENIMPACT is also presented, which significantly addresses the shortcomings of current deep learning object detection algorithms in the clinical diagnosis of dental impacted teeth detection on panoramic X-rays. Through experiments on our dataset, our method achieved a significant improvement in detection accuracy, with mAP50 increasing from 0.410 to 0.631. The experimental results demonstrate that our model reaches state-of-the-art performance levels in tooth and lesion detection tasks, providing new solutions for automated analysis of oral medical images.