超越静态世界：面向一体化医学图像复原的终身学习
Beyond the Static-World: Lifelong Learning for All-in-One Medical Image Restoration
把「解耦-优化-巩固」范式用于多模态医学图像复原：用对抗平衡在内容保持与模态擦除之间解耦出模态不变特征流形，再用预测网络定位特征巩固点配合多样性损失抵抗域增量下的灾难性遗忘，可直接迁移到多模态视觉模型的持续学习场景。
原文依据 a temporal static-world assumption that ignores the continual data streams in real-world clinical settings, leading to catastrophic forgetting
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论一体化医学图像复原（MedIR）模型为通向泛化医学影像智能提供了一条有前景的路径，但面临两个关键的时空挑战：1）空间模态干扰，即来自不同模态（如 MRI、CT、PET）的冲突梯度会降低性能；2）时间上的静态世界假设，它忽略了真实临床环境中持续到来的数据流，从而导致灾难性遗忘。为应对这一双重挑战，我们提出了一种新颖的终身学习框架（称为 Resilient On-the-fly Medical Enhancement，ROME），它以「解耦—优化—巩固」范式为指导。ROME 首先通过基于对抗平衡的模态不变解耦（MIDAB）模块解决基础的模态冲突。该模块在「内容保持力」与「模态擦除力」之间建立一种策略性的「对抗平衡」，以优化一个解耦的、统一的特征流形。在这一稳定基础之上，自适应特征巩固（AFC）模块用于对抗遗忘。AFC 通过一个预测网络动态定位最优的特征巩固点，并由一种新颖的多样性损失加以约束，以确保稳健的持续学习。实验表明，ROME 不仅在静态设定下达到 SOTA 性能，而且在严格的域增量基准上展现出更优的韧性，将平均灾难性性能退化降低超过 10%。
英文原文摘要 1464 字符
All-in-one Medical Image Restoration (MedIR) models offer a promising path towards generalized medical imaging intelligence but face two critical spatiotemporal challenges: 1) Spatial modality interference, where conflicting gradients from diverse modalities (e.g., MRI, CT, PET) degrade performance; and 2) a temporal static-world assumption that ignores the continual data streams in real-world clinical settings, leading to catastrophic forgetting. To address this dual challenge, we propose a novel lifelong learning framework (called Resilient On-the-fly Medical Enhancement, ROME) governed by a "disentangle-optimize-consolidate" paradigm. ROME first resolves the foundational modality conflict via the Modality-Invariant Disentanglement via Adversarial Balancing (MIDAB) module. It establishes a strategic "adversarial balance" between a "content preservation force" and a "modality erasure force" to optimize a disentangled, unified feature manifold. Building on this stable foundation, the Adaptive Feature Consolidation (AFC) module combats forgetting. AFC dynamically locates an optimal feature consolidation point via a prediction network, enforced by a novel diversity loss to ensure robust continuous learning. Experiments demonstrate that ROME not only achieves SOTA performance in static settings but also exhibits superior resilience in rigorous domain-incremental benchmarks, reducing the average catastrophic performance degradation by over 10%.