Teeth YOLACT: An Instance Segmentation Model Based on Impacted Tooth Panoramic X-Ray Images

The instance segmentation of impacted teeth in the oral panoramic X-ray images is hotly researched. However, due to the complex structure, low contrast, and complex background of teeth in panoramic X-ray images, the task of instance segmentation is technically tricky. In this study, the contrast between impacted Teeth and periodontal tissues such as gingiva, periodontal membrane, and alveolar bone is low, resulting in fuzzy boundaries of impacted teeth. A model based on Teeth YOLACT is proposed to provide a more efficient and accurate solution for the segmentation of impacted teeth in oral panoramic X-ray films. Firstly, a Multi-scale Res-Transformer Module (MRTM) is designed. In the module, depthwise separable convolutions with different receptive fields are used to enhance the sensitivity of the model to lesion size. Additionally, the Vision Transformer is integrated to improve the model’s ability to perceive global features. Secondly, the Context Interaction-awareness Module (CIaM) is designed to fuse deep and shallow features. The deep semantic features guide the shallow spatial features. Then, the shallow spatial features are embedded into the deep semantic features, and the cross-weighted attention mechanism is used to aggregate the deep and shallow features efficiently, and richer context information is obtained. Thirdly, the Edge-preserving perception Module (E2PM) is designed to enhance the teeth edge features. The first-order differential operator is used to get the tooth edge weight, and the perception ability of tooth edge features is improved. The shallow spatial feature is fused by linear mapping, weight concatenation, and matrix multiplication operations to preserve the tooth edge information. Finally, comparison experiments and ablation experiments are conducted on the oral panoramic X-ray image datasets. The results show that the APdet, APseg, ARdet, ARseg, mAPdet, and mAPseg indicators of the proposed model are 89.9%, 91.9%, 77.4%, 77.6%, 72.8%, and 73.5%, respectively. This study further verifies the application potential of the method combining multi-scale feature extraction, multi-scale feature fusion, and edge perception enhancement in medical image segmentation, which provides a valuable reference for future related research.