Enhancing Dual Network Based Semi-Supervised Medical Image Segmentation with Uncertainty-Guided Pseudo-Labeling

2025-09-16

AI Summary

To address the scarcity of labeled data in medical image segmentation, this paper proposes an uncertainty-guided dual-network semi-supervised framework. Methodologically, it integrates cross-consistency augmentation, KL-divergence-driven dynamic weight adjustment, entropy-based pseudo-label filtering, and feature-space contrastive learning to jointly suppress noisy pseudo-labels and reduce prediction uncertainty. Its key innovation lies in explicitly incorporating uncertainty quantification—via KL divergence—into both pseudo-label generation and weighting, while jointly optimizing feature representations through dual-network cross-supervision and self-supervised contrastive learning. Evaluated on the Left Atrial, NIH Pancreas, and BraTS-2019 datasets, the method achieves a Dice score of 89.95% on the Left Atrial dataset using only 10% labeled data, significantly outperforming existing semi-supervised approaches.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Computer Vision: Segmentation
• Reasoning under Uncertainty: Uncertainty Representations

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Despite the remarkable performance of supervised medical image segmentation models, relying on a large amount of labeled data is impractical in real-world situations. Semi-supervised learning approaches aim to alleviate this challenge using unlabeled data through pseudo-label generation. Yet, existing semi-supervised segmentation methods still suffer from noisy pseudo-labels and insufficient supervision within the feature space. To solve these challenges, this paper proposes a novel semi-supervised 3D medical image segmentation framework based on a dual-network architecture. Specifically, we investigate a Cross Consistency Enhancement module using both cross pseudo and entropy-filtered supervision to reduce the noisy pseudo-labels, while we design a dynamic weighting strategy to adjust the contributions of pseudo-labels using an uncertainty-aware mechanism (i.e., Kullback-Leibler divergence). In addition, we use a self-supervised contrastive learning mechanism to align uncertain voxel features with reliable class prototypes by effectively differentiating between trustworthy and uncertain predictions, thus reducing prediction uncertainty. Extensive experiments are conducted on three 3D segmentation datasets, Left Atrial, NIH Pancreas and BraTS-2019. The proposed approach consistently exhibits superior performance across various settings (e.g., 89.95% Dice score on left Atrial with 10% labeled data) compared to the state-of-the-art methods. Furthermore, the usefulness of the proposed modules is further validated via ablation experiments.

Problem

• Reducing noisy pseudo-labels in semi-supervised medical segmentation
• Addressing insufficient supervision in feature space alignment
• Improving 3D medical image segmentation with limited labeled data

Innovation

• Dual-network architecture for semi-supervised segmentation
• Uncertainty-guided pseudo-labeling with KL divergence
• Self-supervised contrastive learning for feature alignment