Uncertainty-Aware Cross-Training for Semi-Supervised Medical Image Segmentation

Kaiwen Huang, Tao Zhou, Huazhu Fu, Yizhe Zhang, Yi Zhou, Xiaojun Wu

Introduction

Deep learning has significantly advanced medical image segmentation, yet the reliance on extensive pixel-level annotations remains a major hurdle. Expert clinicians' time is costly, making large-scale labeled datasets rare. Semi-supervised learning (SSL) offers a solution by training models on a small amount of labeled data and a large pool of unlabeled data.

However, traditional SSL methods, such as the Mean-Teacher (MT) framework, often suffer from "cognitive bias." In MT, the teacher is a temporal average of the student; if the student makes an error, the teacher reinforces it, creating an echo chamber that hinders performance. UC-Seg addresses this by introducing a cross-training framework that utilizes structural diversity and explicit uncertainty modeling.

The UC-Seg Framework

UC-Seg moves away from the traditional student-teacher paradigm, instead employing two structurally different subnets—a U-Net and a V-Net—to perform mutual correction.

Conceptual comparison of SSL architectures: (a) Mean-Teacher, (b) Two subnets, and (c) the proposed UC-Seg framework featuring mutual correction.

Core Components

  1. Cross-subnet Consistency Preservation (CCP): This module ensures that both subnets align their feature representations. It includes Intra-subnet Feature Enhancement (IFE), which uses contrastive learning and a "feature bank" to cluster features of the same class together in the embedding space while pushing different classes apart.
  2. Uncertainty-aware Pseudo-label Generation (UPG): This is the core of the pseudo-labeling process. Instead of simple thresholding, UPG uses Subjective Logic (via a Dirichlet distribution) to estimate pixel-wise uncertainty. A cross-attention mechanism fuses predictions from both subnets, giving higher weight to confident regions and lower weight to uncertain ones, resulting in cleaner training signals.

Experimental Results

The authors evaluated UC-Seg across seven diverse tasks, including five colonoscopy datasets, skin lesion detection, and various 3D volumetric datasets (Brain, Cardiac, and Pancreas).

UC-Seg consistently outperformed state-of-the-art (SOTA) methods like BCP and CAML. For instance, on the CVC-ClinicDB polyp segmentation task with only 10% labeled data, UC-Seg achieved a Dice score of 80.63%, significantly higher than its closest competitors. Qualitative results demonstrate that UC-Seg produces segmentation maps that are much closer to the ground truth, especially in challenging regions where other models fail.

Qualitative comparison of UC-Seg against other semi-supervised methods. UC-Seg (Ours) demonstrates superior alignment with the Ground Truth (GT) across various colonoscopy images.

Conclusion and Future Work

UC-Seg effectively mitigates cognitive bias in semi-supervised medical image segmentation by leveraging architectural diversity and uncertainty-aware fusion. The model's ability to generalize to unseen datasets highlights its robustness. While the dual-subnet architecture increases computational costs during training, the gains in accuracy and reliability make it a promising framework for real-world clinical applications where labeled data is scarce. Future research will explore refining the UPG module using unlabeled data to further enhance its performance.

Summary updated

BibTeX
@article{huang2025uncertainty,
  author = {Kaiwen Huang and Tao Zhou and Huazhu Fu and Yizhe Zhang and Yi Zhou and Xiaojun Wu},
  title = {{Uncertainty-Aware Cross-Training for Semi-Supervised Medical Image Segmentation}},
  journal = {IEEE Trans. Image Process.},
  year = {2025},
  doi = {10.1109/tip.2025.3599783},
}

Loading related content...

Figure