A Dental Caries Segmentation Method Based on Dental Bitewings

Abstract:
Computer Aided Diagnosis (CAD) has become a hot research field in oral clinic. Due to the similar contrast between caries and periodontal tissues, especially the proximal caries, it is difficult for general CAD methods to accurately de-tect the location of caries. Aiming at this problem, an image semantic segmentation algorithm based on U-Net and at-tention mechanism is proposed. First, the dental bitewings dataset was constructed. Second, the CBAM module is inte-grated into the U-Net network for focusing on caries-affected areas. Finally, the semantic segmentation accuracy is fur-ther improved by multi-scale feature fusion. The experimental results show that the model proposed in this paper has significant improvements in multiple performances compared with algorithms such as PSP-Net.