mlsanityData to 14 Oct 2026

Diverse Teaching and Label Propagation for Generic Semi-Supervised Medical Image Segmentation

arXiv 2508.08549 ↗First posted 12 Aug 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Both limited annotation and domain shift are significant challenges frequently encountered in medical image segmentation, leading to derivative scenarios like semi-supervised medical (SSMIS), semi-supervised medical domain generalization (Semi-MDG) and unsupervised medical domain adaptation (UMDA). Conventional methods are generally tailored to specific tasks in isolation, the error accumulation hinders the effective utilization of unlabeled data and limits further improvements, resulting in suboptimal performance when these issues occur. In this paper, we aim to develop a generic framework that masters all three tasks. We found that the key to solving the problem lies in how to generate reliable pseudo labels for the unlabeled data in the presence of domain shift with labeled data and increasing the diversity of the model. To tackle this issue, we employ a Diverse Teaching and Label Propagation Network (DTLP-Net) to boosting the Generic Semi-Supervised Medical Image Segmentation. Our DTLP-Net involves a single student model and two diverse teacher models, which can generate reliable pseudo-labels for the student model. The first teacher model decouple the training process with labeled and unlabeled data, The second teacher is momentum-updated periodically, thus generating reliable yet divers pseudo-labels. To fully utilize the information within the data, we adopt inter-sample and intra-sample data augmentation to learn the global and local knowledge. In addition, to further capture the voxel-level correlations, we propose label propagation to enhance the model robust. We evaluate our proposed framework on five benchmark datasets for SSMIS, UMDA, and Semi-MDG tasks. The results showcase notable improvements compared to state-of-the-art methods across all five settings, indicating the potential of our framework to tackle more challenging SSL scenarios.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 56 references that are in the map. First posted on arXiv 12 Aug 2025.

Builds on

35 of 56 references.

References · 35

  1. 2020Denoising Diffusion Implicit Modelscited by 9,781
  2. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  3. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  4. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  5. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  6. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  7. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 510
  8. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 463
  9. 2019Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentationcited by 379
  10. 2022AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentationcited by 351
  11. 2020Semi-supervised Medical Image Segmentation through Dual-task Consistencycited by 216
  12. 2022MIC: Masked Image Consistency for Context-Enhanced Domain Adaptationcited by 178
23 more
  1. 2020Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Imagescited by 152
  2. 2020Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domainscited by 124
  3. 2020Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularizationcited by 123
  4. 2023Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentationcited by 116
  5. 2021Semi-supervised Left Atrium Segmentation with Mutual Consistency Trainingcited by 104
  6. 2020Efficient Semi-Supervised Gross Target Volume of Nasopharyngeal Carcinoma Segmentation via Uncertainty Rectified Pyramid Consistencycited by 102
  7. 2022Exploring Smoothness and Class-Separation for Semi-supervised Medical Image Segmentationcited by 93
  8. 2022Debiased Learning from Naturally Imbalanced Pseudo-Labelscited by 85
  9. 2020Annotation-efficient deep learning for automatic medical image segmentationcited by 79
  10. 2022Enhancing Pseudo Label Quality for Semi-Supervised Domain-Generalized Medical Image Segmentationcited by 51
  11. 2021Semi-Supervised Domain Generalization with Stochastic StyleMatchcited by 43
  12. 2023Diff-UNet: A Diffusion Embedded Network for Volumetric Segmentationcited by 41
  13. 2021Deep Symmetric Adaptation Network for Cross-modality Medical Image Segmentationcited by 39
  14. 2021Semi-supervised Meta-learning with Disentanglement for Domain-generalised Medical Image Segmentationcited by 36
  15. 2023Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentationcited by 35
  16. 2024AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentationcited by 35
  17. 2023DHC: Dual-debiased Heterogeneous Co-training Framework for Class-imbalanced Semi-supervised Medical Image Segmentationcited by 25
  18. 2022ACT: Semi-supervised Domain-adaptive Medical Image Segmentation with Asymmetric Co-trainingcited by 20
  19. 2020Disentangled Representations for Domain-generalized Cardiac Segmentationcited by 14
  20. 2018PnP-AdaNet: Plug-and-Play Adversarial Domain Adaptation Network with a Benchmark at Cross-modality Cardiac Segmentationcited by 12
  21. 2022An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learningcited by 12
  22. 2022vMFNet: Compositionality Meets Domain-generalised Segmentationcited by 11
  23. 2022ConFUDA: Contrastive Fewshot Unsupervised Domain Adaptation for Medical Image Segmentationcited by 3

Built on by

Not cited yet.