Neighbor Does Matter: Density-Aware Contrastive Learning for Medical Semi-supervised Segmentation

2024-12-27

AI Summary

To address the challenges of label scarcity and low soft-tissue contrast in multi-organ semi-supervised medical image segmentation, this paper proposes a density-aware contrastive learning framework. Methodologically, it introduces— for the first time in medical semi-supervised segmentation—a density-aware mechanism: a density-weighted neighborhood graph is constructed to approximate cluster centers via high-density regions, yielding robust positive samples; further, label-guided co-training is integrated with density-guided geometric regularization to enhance intra-class compactness and inter-class separability in feature space. Evaluated on the Multi-Organ Segmentation Challenge dataset, the proposed method significantly outperforms existing state-of-the-art approaches, achieving higher Dice scores and improved model robustness—particularly in low-contrast soft-tissue regions.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Computer Vision: Segmentation
• Search and Optimization: Learning to Search

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: Robustness and generalizability of Web mining methods

Abstract

In medical image analysis, multi-organ semi-supervised segmentation faces challenges such as insufficient labels and low contrast in soft tissues. To address these issues, existing studies typically employ semi-supervised segmentation techniques using pseudo-labeling and consistency regularization. However, these methods mainly rely on individual data samples for training, ignoring the rich neighborhood information present in the feature space. In this work, we argue that supervisory information can be directly extracted from the geometry of the feature space. Inspired by the density-based clustering hypothesis, we propose using feature density to locate sparse regions within feature clusters. Our goal is to increase intra-class compactness by addressing sparsity issues. To achieve this, we propose a Density-Aware Contrastive Learning (DACL) strategy, pushing anchored features in sparse regions towards cluster centers approximated by high-density positive samples, resulting in more compact clusters. Specifically, our method constructs density-aware neighbor graphs using labeled and unlabeled data samples to estimate feature density and locate sparse regions. We also combine label-guided co-training with density-guided geometric regularization to form complementary supervision for unlabeled data. Experiments on the Multi-Organ Segmentation Challenge dataset demonstrate that our proposed method outperforms state-of-the-art methods, highlighting its efficacy in medical image segmentation tasks.

Problem

• Semi-supervised Learning
• Medical Image Segmentation
• Organ Segmentation

Innovation

• Density-Aware Contrastive Learning
• Medical Image Segmentation
• Semi-Supervised Learning