MICCAI STSR 2025 Challenge: Semi-Supervised Teeth and Pulp Segmentation and CBCT-IOS Registration

• URL: http://arxiv.org/abs/2512.02867v1
• Date: Tue, 02 Dec 2025 15:29:04 GMT
• Title: MICCAI STSR 2025 Challenge: Semi-Supervised Teeth and Pulp Segmentation and CBCT-IOS Registration
• Authors: Yaqi Wang, Zhi Li, Chengyu Wu, Jun Liu, Yifan Zhang, Jialuo Chen, Jiaxue Ni, Qian Luo, Jin Liu, Can Han, Changkai Ji, Zhi Qin Tan, Ajo Babu George, Liangyu Chen, Qianni Zhang, Dahong Qian, Shuai Wang, Huiyu Zhou,
• Abstract summary: Cone-Beam Computed Tomography (CBCT) and Intraoral Scanning (IOS) are essential for digital dentistry, but data scarcity limits automated solutions.<n>We organized the STSR 2025 Challenge at MICCAI 2025 to benchmark semi-supervised learning (SSL) in this domain.<n>We provided 60 labeled and 640 unlabeled IOS samples, plus 30 labeled and 250 unlabeled CBCT scans with varying resolutions and fields of view.<n>The challenge attracted strong community participation, with top teams submitting open-source deep learning-based SSL solutions.
• Score: 30.64602516984303
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Cone-Beam Computed Tomography (CBCT) and Intraoral Scanning (IOS) are essential for digital dentistry, but annotated data scarcity limits automated solutions for pulp canal segmentation and cross-modal registration. To benchmark semi-supervised learning (SSL) in this domain, we organized the STSR 2025 Challenge at MICCAI 2025, featuring two tasks: (1) semi-supervised segmentation of teeth and pulp canals in CBCT, and (2) semi-supervised rigid registration of CBCT and IOS. We provided 60 labeled and 640 unlabeled IOS samples, plus 30 labeled and 250 unlabeled CBCT scans with varying resolutions and fields of view. The challenge attracted strong community participation, with top teams submitting open-source deep learning-based SSL solutions. For segmentation, leading methods used nnU-Net and Mamba-like State Space Models with pseudo-labeling and consistency regularization, achieving a Dice score of 0.967 and Instance Affinity of 0.738 on the hidden test set. For registration, effective approaches combined PointNetLK with differentiable SVD and geometric augmentation to handle modality gaps; hybrid neural-classical refinement enabled accurate alignment despite limited labels. All data and code are publicly available at https://github.com/ricoleehduu/STS-Challenge-2025 to ensure reproducibility.

Related papers

• FUGC: Benchmarking Semi-Supervised Learning Methods for Cervical Segmentation [63.7829089874007]
  This paper introduces the Fetal Ultrasound Grand Challenge (FUGC), the first benchmark for semi-supervised learning in cervical segmentation.<n>FUGC provides a dataset of 890 TVS images, including 500 training images, 90 validation images, and 300 test images.<n> Methods were evaluated using the Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), and runtime (RT), with a weighted combination of 0.4/0.4/0.2.
  arXiv  Detail & Related papers  (2026-01-22T01:34:39Z)
• MICCAI STS 2024 Challenge: Semi-Supervised Instance-Level Tooth Segmentation in Panoramic X-ray and CBCT Images [33.12982357985314]
  This research aimed to benchmark and advance semi-supervised learning (SSL)<n>We organized the 2nd Semi-supervised Teeth (STS 2024) Challenge at MII 2024.<n>We provided a large-scale dataset comprising over 90,000 2D images and 3D axial slices, which includes 2,380 OPG images and 330 CBCT scans.<n>The winning semi-supervised models demonstrated impressive performance gains over a fully-supervised nnU-Net baseline trained only on the labeled data.
  arXiv  Detail & Related papers  (2025-11-28T06:33:55Z)
• Hierarchical Self-Supervised Representation Learning for Depression Detection from Speech [51.14752758616364]
  Speech-based depression detection (SDD) is a promising, non-invasive alternative to traditional clinical assessments.<n>We propose HAREN-CTC, a novel architecture that integrates multi-layer SSL features using cross-attention within a multitask learning framework.<n>The model achieves state-of-the-art macro F1-scores of 0.81 on DAIC-WOZ and 0.82 on MODMA, outperforming prior methods across both evaluation scenarios.
  arXiv  Detail & Related papers  (2025-10-05T09:32:12Z)
• U-Mamba2-SSL for Semi-Supervised Tooth and Pulp Segmentation in CBCT [44.3806898357896]
  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.<n>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.
  arXiv  Detail & Related papers  (2025-09-24T14:19:33Z)
• QMaxViT-Unet+: A Query-Based MaxViT-Unet with Edge Enhancement for Scribble-Supervised Segmentation of Medical Images [0.0]
  We propose QMaxViT-Unet+, a novel framework for scribble-supervised medical image segmentation.<n>This framework is built on the U-Net architecture, with the encoder and decoder replaced by Multi-Axis Vision Transformer (MaxViT) blocks.<n>We evaluate the proposed QMaxViT-Unet+ on four public datasets focused on cardiac structures, colorectal polyps, and breast cancer.
  arXiv  Detail & Related papers  (2025-02-14T16:56:24Z)
• Semi-Supervised Semantic Segmentation using Redesigned Self-Training for White Blood Cells [3.957784193707817]
  We propose a semi-supervised learning framework to efficiently capitalize on the scarcity of the dataset available. Self-training is a technique that utilizes the model trained on labeled data to generate pseudo-labels for the unlabeled data and then re-train on both of them. We discover that by incorporating FixMatch in the self-training pipeline, the performance improves in the majority of cases.
  arXiv  Detail & Related papers  (2024-01-14T12:22:34Z)
• Inferior Alveolar Nerve Segmentation in CBCT images using Connectivity-Based Selective Re-training [9.15971170814049]
  Inferior Alveolar Nerve (IAN) canal detection in CBCT is an important step in many dental and maxillofacial surgery applications. The ToothFairy2023 Challenge aims to establish a 3D maxillofacial dataset consisting of all sparse labels and partial dense labels. Inspired by self-training via pseudo labeling, we propose a selective re-training framework based on IAN connectivity.
  arXiv  Detail & Related papers  (2023-08-18T04:48:23Z)
• The Devil is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation [61.027468209465354]
  We introduce a novel learning scheme named weakly semi-supervised instance segmentation (WSSIS) with point labels. We propose a method for WSSIS that can effectively leverage the budget-friendly point labels as a powerful weak supervision source. We conduct extensive experiments on COCO and BDD100K datasets, and the proposed method achieves promising results comparable to those of the fully-supervised model.
  arXiv  Detail & Related papers  (2023-03-27T10:11:22Z)
• 1st Place Solution of The Robust Vision Challenge (RVC) 2022 Semantic Segmentation Track [67.56316745239629]
  This report describes the winning solution to the semantic segmentation task of the Robust Vision Challenge on ECCV 2022. Our method adopts the FAN-B-Hybrid model as the encoder and uses Segformer as the segmentation framework. The proposed method could serve as a strong baseline for the multi-domain segmentation task and benefit future works.
  arXiv  Detail & Related papers  (2022-10-23T20:52:22Z)
• Two-Stream Consensus Network: Submission to HACS Challenge 2021 Weakly-Supervised Learning Track [78.64815984927425]
  The goal of weakly-supervised temporal action localization is to temporally locate and classify action of interest in untrimmed videos. We adopt the two-stream consensus network (TSCN) as the main framework in this challenge. Our solution ranked 2rd in this challenge, and we hope our method can serve as a baseline for future academic research.
  arXiv  Detail & Related papers  (2021-06-21T03:36:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.