GeoT: Geometry-guided Instance-dependent Transition Matrix for Semi-supervised Tooth Point Cloud Segmentation

2025-03-21

AI Summary

In dental orthodontics, semi-supervised intraoral scanning point cloud segmentation suffers significant performance degradation due to noisy pseudo-labels. Method: We propose an Instance-Dependent Transition Matrix (IDTM) to model sample-level pseudo-label noise distributions, integrated with point-wise geometric regularization and class-wise geometric smoothing, all constrained by anatomical priors of teeth to guide IDTM estimation. Contribution/Results: This work is the first to embed geometric structural priors into both noise modeling and consistency regularization frameworks, effectively suppressing error propagation from erroneous pseudo-labels. Evaluated on Teeth3DS and a private dataset, our method achieves full-supervision performance using only 20% labeled data—substantially improving unlabeled data utilization efficiency. It establishes a novel paradigm for low-label-cost 3D medical point cloud segmentation.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Computer Vision: Segmentation
• Intelligent Robots: State Estimation

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Security and Privacy: Data transparency and provenance

Abstract

Achieving meticulous segmentation of tooth point clouds from intra-oral scans stands as an indispensable prerequisite for various orthodontic applications. Given the labor-intensive nature of dental annotation, a significant amount of data remains unlabeled, driving increasing interest in semi-supervised approaches. One primary challenge of existing semi-supervised medical segmentation methods lies in noisy pseudo labels generated for unlabeled data. To address this challenge, we propose GeoT, the first framework that employs instance-dependent transition matrix (IDTM) to explicitly model noise in pseudo labels for semi-supervised dental segmentation. Specifically, to handle the extensive solution space of IDTM arising from tens of thousands of dental points, we introduce tooth geometric priors through two key components: point-level geometric regularization (PLGR) to enhance consistency between point adjacency relationships in 3D and IDTM spaces, and class-level geometric smoothing (CLGS) to leverage the fixed spatial distribution of tooth categories for optimal IDTM estimation. Extensive experiments performed on the public Teeth3DS dataset and private dataset demonstrate that our method can make full utilization of unlabeled data to facilitate segmentation, achieving performance comparable to fully supervised methods with only $20%$ of the labeled data.

Problem

• Segment tooth point clouds accurately for orthodontic applications
• Reduce noisy pseudo labels in semi-supervised dental segmentation
• Utilize geometric priors to optimize transition matrix estimation

Innovation

• Uses instance-dependent transition matrix (IDTM)
• Incorporates point-level geometric regularization (PLGR)
• Applies class-level geometric smoothing (CLGS)