A unfied convolution neural network for dental caries classification

Abstract

Dental caries is one of the most common chronic diseases in the oral cav- ity. The early detection of initial dental caries is needed for treatment. It is problematic to diagnose the initial carious lesion, as known as enamel caries, due to the similarity of a tiny hole to human perception error. In this paper, we propose a uni ed convolution neural network to improve the diagnostic and treatment performance for dentists using classi cation from bitewing radiographs. We adapt the AlexNet and ResNet models to properly classify the dental caries dataset. The modi ed ResNet success- fully achieves excellent binary-classi cation performance with accuracy of 86.67%, 87.78% and 82.78% of teeth with all conditions, teeth without den- tal restoration, and only teeth with dental restorations, respectively. For multilevel classi cation, our model has good performance with 5-class av- erage accuracy of 80%. Remarkably, our adapted ResNet-18 has good per- formance with enamel caries and secondary caries with accuracy of 86.67% and 77.78%, respectively. Conversely, our ResNet-50 and ResNet-101 have contradictory low performance with enamel and secondary caries but high performance with sound teeth, dentin caries and teeth with restoration of 90%, 78.89% and 88.89%, respectively. The accuracies of our model are good enough that our model could support dentists to enhance diagnostic performance.