Tooth and Pulp Chamber Automatic Segmentation with Artificial Intelligence Network and Morphometry Method in Cone-beam CT

This study aims to extract teeth and alveolar bone structures in CBCT images automatically, which is a key step image analysis the field of stomatology. In this study, semantic segmentation was used for automatic segmentation. Five marked classes were input U-net neural network training. Tooth hard tissue (including enamel, dentin, cementum), dental pulp cavity, cortical bone, cancellous other tissues manually each class. The output data from different regions interest. configuration training parameters optimized adjusted according prediction effect. method can be segment peripheral using CBCT. time process less than 13 min. Dice evaluation reference 98 %. model combined with watershed effectively teeth, images. It provide morphological information clinical treatment.