Diversity-enhanced Collaborative Mamba for Semi-supervised Medical Image Segmentation
This work addresses the costly annotation burden in medical imaging by improving semi-supervised segmentation performance, though it appears incremental as it builds on existing Mamba models with diversity enhancements.
The paper tackles the problem of limited annotated data for medical image segmentation by proposing a semi-supervised framework called DCMamba that enhances diversity across data, network, and feature perspectives, achieving a 6.69% improvement over the latest SSM-based method on the Synapse dataset with 20% labeled data.
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.