An Automatic Dental Decay Treatment Prediction using a Deep Convolutional Neural Network on X-Ray Images

Abstract

In this paper, we propose an automatic method to detect the decay from dental X-Ray images to predict the needed treatment. Specifically, in our study, we propose a deep learning model based on X-Ray images to predict the treatment of dental decay. The approach mainly predicts three types of treatments namely Fluoride, Filling and Root canal treatments. The model has been trained to learn on dataset of 200 X-ray images of various patients' teeth collected anonymously. The overall accuracy of the model is 87%. The best prediction was the fluoride treatment with a rate of 98%, followed by the root canal detection with a rate of 88% The filling treatment gave lower classification accuracy, with a rate of 77%.