Self-Supervised Learning With Masked Autoencoders for Teeth Segmentation From Intra-Oral 3D Scans

Amani Almalki, Longin Jan Latecki; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024, pp. 7820-7830

In modern dentistry, teeth localization, segmentation, and labeling from intra-oral 3D scans are crucial for improving dental diagnostics, treatment planning, and population-based studies on oral health. However, creating automated algorithms for teeth analysis is a challenging task due to the limited availability of accessible data for training, particularly from the point of view of deep learning. This study extends the self-supervised learning framework of the mesh masked autoencoder (MeshMAE) transformer. While the MeshMAE loss measures the quality of reconstructed masked mesh triangles, the loss of the proposed DentalMAE evaluates the predicted deep embeddings of masked mesh triangles. This yields a better generalization ability on a very limited number of 3D dental scans, as documented by our results on teeth segmentation of intra-oral scans. Our results show that masking-based unsupervised learning methods may, for the first time, provide convincing transfer learning improvements on 3D intra-oral scans, increasing the overall accuracy over both MeshMAE and prior self-supervised pre-training.