3D Tooth Segmentation and Labeling using Deep Convolutional Neural Networks.

In this paper, we present a novel approach for 3D dental model segmentation via deep Convolutional Neural Networks (CNNs). Traditional geometry-based methods tend to receive undesirable results due to the complex appearance of human teeth (e.g., missing/rotten tooth, feature-less regions, crowding teeth, extra medical attachments, etc.). To address these issues, we propose to learn a generic and robust segmentation model by exploiting deep neural networks, namely NNs. To this end, we extensively experiment with various network structures, and eventually arrive at a two-level hierarchical CNNs structure for tooth segmentation: one for teeth-gingiva labelling and the other for inter-teeth labelling. Further, we propose a novel boundary-aware tooth simplification method to significantly improve efficiency in the stage of feature extraction. After CNNs prediction, we do graph-based label optimization and further refine the boundary with an improved version of fuzzy clustering. The accuracy of our mesh labelling method exceeds that of the state-of-art geometry-base methods, reaching 99.06% measured by area which is directly applicable in orthodontic CAD systems. It is also robust to any possible foreign matters on model surface, e.g., air bubbles, dental accessories, and many more.