Tooth Detection with Convolutional Neural Networks

Abstract

Detection of teeth from dental panoramic Xray images is the a crucial step for the computerized tooth applications. In this a paper, we present a method for detecting teeth in dental panoramic X-ray images with Convolutional Neural Networks (CNN). After finding the mouth gap, possible positions of three tooth type (incisors, premolars, and molars) are determined. Teeth are detected with a modified version of AlexNet architecture where multi-class classification is performed. The accuracy of the method is over 90% and the presented method can be used as the first step of the computerized dental applications.