Diversity-enhanced Collaborative Mamba for Semi-supervised Medical Image Segmentation

TL;DR

This paper introduces DCMamba, a novel semi-supervised medical image segmentation framework that leverages data, network, and feature diversity to improve segmentation accuracy using limited labeled data.

Contribution

The paper proposes a new Diversity-enhanced Collaborative Mamba framework that integrates patch-level augmentation, diverse-scan collaboration, and uncertainty-weighted contrastive learning.

Findings

Outperforms existing semi-supervised methods by 6.69% on Synapse dataset

Effectively utilizes unlabeled data to improve segmentation accuracy

Demonstrates robustness across different scanning directions

Abstract

Acquiring high-quality annotated data for medical image segmentation is tedious and costly. Semi-supervised segmentation techniques alleviate this burden by leveraging unlabeled data to generate pseudo labels. Recently, advanced state space models, represented by Mamba, have shown efficient handling of long-range dependencies. This drives us to explore their potential in semi-supervised medical image segmentation. In this paper, we propose a novel Diversity-enhanced Collaborative Mamba framework (namely DCMamba) for semi-supervised medical image segmentation, which explores and utilizes the diversity from data, network, and feature perspectives. Firstly, from the data perspective, we develop patch-level weak-strong mixing augmentation with Mamba's scanning modeling characteristics. Moreover, from the network perspective, we introduce a diverse-scan collaboration module, which could benefit from the prediction discrepancies arising from different scanning directions. Furthermore, from the feature perspective, we adopt an uncertainty-weighted contrastive learning mechanism to enhance the diversity of feature representation. Experiments demonstrate that our DCMamba significantly outperforms other semi-supervised medical image segmentation methods, e.g., yielding the latest SSM-based method by 6.69% on the Synapse dataset with 20% labeled data.