发表机构
Central China Normal University; Huazhong University of Science and Technology; Guangzhou University of Chinese Medicine; The First Affiliated Hospital of Guangzhou University of Chinese Medicine; University of North Carolina, Chapel Hill（华中师范大学; 华中科技大学; 广州中医药大学; 广州中医药大学第一附属医院; 北卡罗来纳大学教堂山分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对多模态医学图像分割中质量差异导致融合失败的问题，提出腐败感知再平衡融合框架CoReFuse-Med，抑制特征腐败并再平衡模态贡献，实验验证了其有效性。
AI 中文摘要
多模态医学图像分割利用互补的诊断信息，然而当空间对齐的输入在质量上存在差异时，融合可能不如单模态基线。这里，“腐败”主要指分辨率引起的退化，而非错位或模态完全缺失，而合成噪声仅作为辅助设置进行评估。我们识别出一个关键的优化-推理不一致性：退化的模态可能获得较弱的训练更新，却显著影响预测，表明对融合存在主动干扰。我们将此失败归因于重采样引起的特征腐败和优化偏差，其中噪声特征通过跳跃连接传播并鼓励不可靠的模态选择。因此，我们提出CoReFuse-Med，一种腐败感知再平衡融合框架，在特征传输期间抑制腐败，并在高层融合期间再平衡模态贡献。在EPVS、BraTS和WMH上的实验，包括多种Z轴切片保留比例和辅助噪声测试，证明了在模态质量差异下准确性和鲁棒性的提升。我们的代码可在该https URL获取。
英文摘要
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 https://github.com/lrever/CoReFuse.
CommentsAccepted by ACM Multimedia (ACM MM 2026)
