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

Weihao Yu, Xiaoqing Guo, Chenxin Li, Yifan Liu, Yixuan Yuan

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

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.
Original languageEnglish
Title of host publicationInformation Processing in Medical Imaging
Subtitle of host publication29th International Conference, IPMI 2025, Kos, Greece, May 25–30, 2025, Proceedings
EditorsIpek Oguz, Shaoting Zhang, Dimitris N. Metaxas
PublisherSpringer Cham
Publication statusAccepted/In press - 14 Feb 2025
Event29th International Conference on Information Processing in Medical Imaging, IPMI 2025 - Kos, Greece
Duration: 25 May 202530 May 2025
https://ipmi2025.org/scientific-program.html (Conference program)
https://link.springer.com/book/9783031966279 (Conference proceedings, Part I)
https://link.springer.com/book/9783031966248 (Conference proceedings, Part II)

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameIPMI: International Conference on Information Processing in Medical Imaging

Conference

Conference29th International Conference on Information Processing in Medical Imaging, IPMI 2025
Country/TerritoryGreece
CityKos
Period25/05/2530/05/25
Internet address

Fingerprint

Dive into the research topics of 'GeoT: Geometry-guided Instance-dependent Transition Matrix for Semi-supervised Tooth Point Cloud Segmentation'. Together they form a unique fingerprint.

Cite this