Shape-preserving Tooth Segmentation from CBCT Images Using Deep Learning with Semantic and Shape Awareness
This work addresses shape-preserving segmentation for digital dentistry, offering a domain-specific solution to improve anatomical fidelity in tooth boundaries.
The paper tackled the challenge of accurate tooth segmentation from CBCT images, particularly in cases of interdental adhesions that cause shape distortion, and achieved significant performance improvements over existing methods.
Background:Accurate tooth segmentation from cone beam computed tomography (CBCT) images is crucial for digital dentistry but remains challenging in cases of interdental adhesions, which cause severe anatomical shape distortion. Methods: To address this, we propose a deep learning framework that integrates semantic and shape awareness for shape-preserving segmentation. Our method introduces a target-tooth-centroid prompted multi-label learning strategy to model semantic relationships between teeth, reducing shape ambiguity. Additionally, a tooth-shape-aware learning mechanism explicitly enforces morphological constraints to preserve boundary integrity. These components are unified via multi-task learning, jointly optimizing segmentation and shape preservation. Results: Extensive evaluations on internal and external datasets demonstrate that our approach significantly outperforms existing methods. Conclusions: Our approach effectively mitigates shape distortions and providing anatomically faithful tooth boundaries.