{"ID":2866613,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.20154","arxiv_id":"2509.20154","title":"U-Mamba2-SSL for Semi-Supervised Tooth and Pulp Segmentation in CBCT","abstract":"Accurate segmentation of teeth and pulp in Cone-Beam Computed Tomography (CBCT) is vital for clinical applications like treatment planning and diagnosis. However, this process requires extensive expertise and is exceptionally time-consuming, highlighting the critical need for automated algorithms that can effectively utilize unlabeled data. In this paper, we propose U-Mamba2-SSL, a novel semi-supervised learning framework that builds on the U-Mamba2 model and employs a multi-stage training strategy. The framework first pre-trains U-Mamba2 in a self-supervised manner using a disruptive autoencoder. It then leverages unlabeled data through consistency regularization, where we introduce input and feature perturbations to ensure stable model outputs. Finally, a pseudo-labeling strategy is implemented with a reduced loss weighting to minimize the impact of potential errors. U-Mamba2-SSL achieved an average score of 0.789 and a DSC of 0.917 on the hidden test set, achieving first place in Task 1 of the STSR 2025 challenge. The code is available at https://github.com/zhiqin1998/UMamba2.","short_abstract":"Accurate segmentation of teeth and pulp in Cone-Beam Computed Tomography (CBCT) is vital for clinical applications like treatment planning and diagnosis. However, this process requires extensive expertise and is exceptionally time-consuming, highlighting the critical need for automated algorithms that can effectively u...","url_abs":"https://arxiv.org/abs/2509.20154","url_pdf":"https://arxiv.org/pdf/2509.20154v2","authors":"[\"Zhi Qin Tan\",\"Xiatian Zhu\",\"Owen Addison\",\"Yunpeng Li\"]","published":"2025-09-24T14:19:33Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false,"code_links":[{"ID":609390,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2866613,"paper_url":"https://arxiv.org/abs/2509.20154","paper_title":"U-Mamba2-SSL for Semi-Supervised Tooth and Pulp Segmentation in CBCT","repo_url":"https://github.com/zhiqin1998/UMamba2","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}