Modality-Specific Enhancement and Complementary Fusion for Semi-Supervised Multi-Modal Brain Tumor Segmentation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909955123052544 |
|---|---|
| author | Chung, Tien-Dat Lam, Ba-Thinh Nguyen, Thanh-Huy Nguyen, Thien Vu, Nguyen Lan Vi Cao, Hoang-Loc Huynh, Phat Kim Xu, Min |
| author_facet | Chung, Tien-Dat Lam, Ba-Thinh Nguyen, Thanh-Huy Nguyen, Thien Vu, Nguyen Lan Vi Cao, Hoang-Loc Huynh, Phat Kim Xu, Min |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_09801 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Modality-Specific Enhancement and Complementary Fusion for Semi-Supervised Multi-Modal Brain Tumor Segmentation Chung, Tien-Dat Lam, Ba-Thinh Nguyen, Thanh-Huy Nguyen, Thien Vu, Nguyen Lan Vi Cao, Hoang-Loc Huynh, Phat Kim Xu, Min Computer Vision and Pattern Recognition 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. |
| title | Modality-Specific Enhancement and Complementary Fusion for Semi-Supervised Multi-Modal Brain Tumor Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.09801 |