A Novel Deep Learning-Based Approach for Segmentation of Different Type Caries Lesions on Panoramic Radiographs

Abstract

The study aims to evaluate the diagnostic performance of an artificial intelligence system based on deep learning for the segmentation of occlusal, proximal and cervical caries lesions on panoramic radiographs. The study included 504 anonymous panoramic radiographs obtained from the radiology archive of Inonu University Faculty of Dentistry's Department of Oral and Maxillofacial Radiology from January 2018 to January 2020. This study proposes Dental Caries Detection Network (DCDNet) architecture for dental caries segmentation. The main difference between DCDNet and other segmentation architecture is that the last part of DCDNet contains a Multi-Predicted Output (MPO) structure. In MPO, the final feature map split into three different paths for detecting occlusal, proximal and cervical caries. Extensive experimental analyses were executed to analyze the DCDNet network architecture performance. In these comparison results, while the proposed model achieved an average F1-score of 62.79%, the highest average F1-score of 15.69% was achieved with the state-of-the-art segmentation models. These results show that the proposed artificial intelligence-based model can be one of the indispensable auxiliary tools of dentists in the diagnosis and treatment planning of carious lesions by enabling their detection in different locations with high success.

Keywords: caries diagnosis; convolutional neural network; deep learning; dental panoramic radiographs.

Figure 1

Example images (a,c,e,g) and labels (b,d,f,h). Type I (Occlusal caries). Type II (Proximal caries). Type III (Cervical caries).

Figure 2

Proposed deep architecture.

Figure 3

Sample images from the dataset and the prediction outputs of the models.