Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Semantic Class Distribution Learning for Debiasing Semi-Supervised Medical Image Segmentation

Yingxue Su, Yiheng Zhong, Keying Zhu, Zimu Zhang, Zhuoru Zhang, Yifang Wang, Yuxin Zhang, Jingxin Liu

TL;DR

Experiments demonstrate that SCDL significantly improves segmentation performance across both overall and class-level metrics, with particularly strong gains on minority classes, achieving state-of-the-art results.

Abstract

Medical image segmentation is critical for computer-aided diagnosis. However, dense pixel-level annotation is time-consuming and expensive, and medical datasets often exhibit severe class imbalance. Such imbalance causes minority structures to be overwhelmed by dominant classes in feature representations, hindering the learning of discriminative features and making reliable segmentation particularly challenging. To address this, we propose the Semantic Class Distribution Learning (SCDL) framework, a plug-and-play module that mitigates supervision and representation biases by learning structured class-conditional feature distributions. SCDL integrates Class Distribution Bidirectional Alignment (CDBA) to align embeddings with learnable class proxies and leverages Semantic Anchor Constraints (SAC) to guide proxies using labeled data. Experiments on the Synapse and AMOS datasets demonstrate that SCDL significantly improves segmentation performance across both overall and class-level metrics, with particularly strong gains on minority classes, achieving state-of-the-art results. Our code is released at https://github.com/Zyh55555/SCDL.

Semantic Class Distribution Learning for Debiasing Semi-Supervised Medical Image Segmentation

TL;DR

Experiments demonstrate that SCDL significantly improves segmentation performance across both overall and class-level metrics, with particularly strong gains on minority classes, achieving state-of-the-art results.

Abstract

Medical image segmentation is critical for computer-aided diagnosis. However, dense pixel-level annotation is time-consuming and expensive, and medical datasets often exhibit severe class imbalance. Such imbalance causes minority structures to be overwhelmed by dominant classes in feature representations, hindering the learning of discriminative features and making reliable segmentation particularly challenging. To address this, we propose the Semantic Class Distribution Learning (SCDL) framework, a plug-and-play module that mitigates supervision and representation biases by learning structured class-conditional feature distributions. SCDL integrates Class Distribution Bidirectional Alignment (CDBA) to align embeddings with learnable class proxies and leverages Semantic Anchor Constraints (SAC) to guide proxies using labeled data. Experiments on the Synapse and AMOS datasets demonstrate that SCDL significantly improves segmentation performance across both overall and class-level metrics, with particularly strong gains on minority classes, achieving state-of-the-art results. Our code is released at https://github.com/Zyh55555/SCDL.
Paper Structure (9 sections, 9 equations, 2 figures, 4 tables)

This paper contains 9 sections, 9 equations, 2 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. Class Distribution Bidirectional Alignment (CDBA)
  4. Semantic Anchor Constraints (SAC)
  5. Experiment
  6. Dataset and Implementation Details
  7. Comparisons with State-of-the-art Methods
  8. Ablation Study
  9. Conclusion

Figures (2)

  • Figure 1: Comparison of imbalance-aware SSMIS paradigms: (a) Self-generated supervision uses model-derived unlabeled signals and may amplify head-class bias. (b) Loss reweighting and output calibration rebalance training but do not constrain class-conditional features. (c) SCDL debiases feature distributions via CDBA, distribution priors, and SAC anchoring.
  • Figure 2: Overview of SCDL. (a) CDBA learns class proxy distributions and aligns them with token features to generate proxy-guided priors for downstream tasks. (b) SAC extracts semantic anchors from labeled regions and uses them to regularize the proxies, ensuring consistent class semantics across categories.