Modality-Specific Enhancement and Complementary Fusion for Semi-Supervised Multi-Modal Brain Tumor Segmentation

TL;DR

This paper introduces a semi-supervised multi-modal brain tumor segmentation framework that enhances modality-specific features and adaptively fuses cross-modal information, significantly improving segmentation accuracy with limited labeled data.

Contribution

It proposes novel MEM and CIF modules for explicit modality enhancement and adaptive fusion, addressing semantic discrepancies in multi-modal SSL for medical imaging.

Findings

Outperforms existing semi-supervised and multi-modal baselines on BraTS 2019 dataset.

Achieves significant improvements in Dice and Sensitivity scores with limited labeled data.

Demonstrates effectiveness of MEM and CIF modules through ablation studies.

Abstract

Semi-supervised learning (SSL) has become a promising direction for medical image segmentation, enabling models to learn from limited labeled data alongside abundant unlabeled samples. However, existing SSL approaches for multi-modal medical imaging often struggle to exploit the complementary information between modalities due to semantic discrepancies and misalignment across MRI sequences. To address this, we propose a novel semi-supervised multi-modal framework that explicitly enhances modality-specific representations and facilitates adaptive cross-modal information fusion. Specifically, we introduce a Modality-specific Enhancing Module (MEM) to strengthen semantic cues unique to each modality via channel-wise attention, and a learnable Complementary Information Fusion (CIF) module to adaptively exchange complementary knowledge between modalities. The overall framework is optimized using a hybrid objective combining supervised segmentation loss and cross-modal consistency regularization on unlabeled data. Extensive experiments on the BraTS 2019 (HGG subset) demonstrate that our method consistently outperforms strong semi-supervised and multi-modal baselines under 1\%, 5\%, and 10\% labeled data settings, achieving significant improvements in both Dice and Sensitivity scores. Ablation studies further confirm the complementary effects of our proposed MEM and CIF in bridging cross-modality discrepancies and improving segmentation robustness under scarce supervision.