OmniFM：面向异构医学影像的模态鲁棒与任务无关联邦学习
OmniFM: Toward Modality-Robust and Task-Agnostic Federated Learning for Heterogeneous Medical Imaging
把低频频谱分量当作跨模态共享的解剖结构先验，这一思路可直接迁移到多模态医学图像的分割/超分骨干上，用频域提示替代模态专属适配器；其前缀-后缀频谱提示与嵌入级交叉注意力融合也可作为跨模态对齐的轻量插件。
原文依据 low-frequency spectral components exhibit strong cross-modality consistency and encode modality-invariant anatomical structures
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论联邦学习已成为协作式医学图像分析的一种有前景的范式，但现有框架仍与任务专属骨干网络紧密耦合，且在异构成像模态下十分脆弱。这些限制阻碍了实际部署，因为各机构的模态分布差异很大，且必须支持多样化的下游任务。为解决这一局限，我们提出 OmniFM，一个模态无关且任务无关的联邦学习框架，无需重新设计优化流程即可统一分类、分割、超分辨率、视觉问答与多模态融合的训练。OmniFM 建立在一个关键的频域洞见之上：低频频谱分量表现出很强的跨模态一致性，并编码了模态无关的解剖结构。据此，OmniFM 集成了（i）全局频谱知识检索以注入全局频率先验，（ii）嵌入级交叉注意力融合以对齐表征，以及（iii）前缀-后缀频谱提示以联合调节全局与个性化线索，并由频谱近端对齐目标统一正则化以稳定聚合。在真实数据集上的实验表明，OmniFM 在模态内与跨模态异构性下均持续超越最优的联邦学习基线，在微调与从零训练两种设置下都取得更优结果。
英文原文摘要 1413 字符
Federated learning (FL) has become a promising paradigm for collaborative medical image analysis, yet existing frameworks remain tightly coupled to task-specific backbones and are fragile under heterogeneous imaging modalities. Such constraints hinder real-world deployment, where institutions vary widely in modality distributions and must support diverse downstream tasks. To address this limitation, we propose OmniFM,a modality- and task-agnostic FL framework that unifies training across classification,segmentation, super-resolution, visual question answering,and multimodal fusion without re-engineering the optimization pipeline. OmniFM builds on a key frequency-domain insight: low-frequency spectral components exhibit strong cross-modality consistency and encode modality-invariant anatomical structures. Accordingly, OmniFM integrates(i) Global Spectral Knowledge Retrieval to inject global frequency priors, (ii) Embedding-wise Cross-Attention Fusion to align representations, and (iii) Prefix-Suffix Spectral Prompting to jointly condition global and personalized cues, together regularized by a Spectral-Proximal Alignment objective that stabilizes aggregation. Experiments on real-world datasets show that OmniFM consistently surpasses state-of-the-art FL baselines across intra- and cross-modality heterogeneity, achieving superior results under both fine-tuning and training-from-scratch setups.