Shape-preserving Tooth Segmentation from CBCT Images Using Deep Learning with Semantic and Shape Awareness
By: Zongrui Ji , Zhiming Cui , Na Li and more
Potential Business Impact:
Makes dental scans show teeth perfectly.
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.
Similar Papers
Multi-Phase Automated Segmentation of Dental Structures in CBCT Using a Lightweight Auto3DSeg and SegResNet Implementation
CV and Pattern Recognition
Finds hidden problems in teeth using 3D scans.
Multimodal Contrastive Pretraining of CBCT and IOS for Enhanced Tooth Segmentation
CV and Pattern Recognition
Helps dentists perfectly map teeth from scans.
Tooth-Diffusion: Guided 3D CBCT Synthesis with Fine-Grained Tooth Conditioning
CV and Pattern Recognition
Creates fake, realistic teeth for dental planning.