Metraipolis › archive › dc_235df3573e04

When Fusion Fails: Corruption-Aware Rebalanced Fusion for Multi-Modal Medical Image Segmentation — arXiv:2609.10261

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.10261
License (as archived)
CC0-1.0
Archived
2026-10-16T10:59:58.799Z
SHA-256 of the archived text
96d6106882012f5b8e0c4337b38fd556d5dc8a25d15c3e814108b6c71a27b5ed
Stable URL of this page
https://metraipolis.com/documento/dc_235df3573e04

How to cite

When Fusion Fails: Corruption-Aware Rebalanced Fusion for Multi-Modal Medical Image Segmentation — arXiv:2609.10261 — arXiv (en), https://arxiv.org/abs/2609.10261 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_235df3573e04 (Metraipolis archive dc_235df3573e04, sha256 96d6106882012f5b8e0c4337b38fd556d5dc8a25d15c3e814108b6c71a27b5ed)
BibTeX
@misc{dc235df3573e04,
  title = {When Fusion Fails: Corruption-Aware Rebalanced Fusion for Multi-Modal Medical Image Segmentation — arXiv:2609.10261},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.10261},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_235df3573e04; sha256 96d6106882012f5b8e0c4337b38fd556d5dc8a25d15c3e814108b6c71a27b5ed},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10261. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-modal medical image segmentation leverages complementary diagnostic information, yet fusion can underperform single-modality baselines when spatially aligned inputs differ in quality. Here, "corruption" primarily denotes resolution-induced degradation rather than misalignment or complete modality absence, while synthetic noise is evaluated only as an auxiliary setting. We identify a critical optimization-inference inconsistency: degraded modalities can receive weak training updates yet substantially affect predictions, indicating active interference with fusion. We attribute this failure to resampling-induced feature corruption and optimization bias, where noisy features propagate through skip connections and encourage unreliable modality selection. We therefore propose CoReFuse-Med, a Corruption-aware Rebalanced Fusion framework that suppresses corruption during feature transmission and rebalances modality contributions during high-level fusion. Experiments on EPVS, BraTS, and WMH, including multiple Z-axis slice-retention ratios and an auxiliary noise test, demonstrate improved accuracy and robustness under modality-quality discrepancies. Our code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-10 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.10261 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T10:02:34.361Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).