DK-DDIL：面向医学影像动态领域增量学习的自适应知识保持
DK-DDIL: Adaptive Knowledge Retention for Dynamic Domain-Incremental Learning in Medical Imaging
面向医学影像的免回放领域增量学习框架：用动态秩选择+自适应正则化在域漂移下分配容量，再用选择性适配器融合与原型级对比精炼稳定跨域知识迁移，可直接迁移到视觉基础模型的持续适配场景。
原文依据 a rehearsal-free framework for dynamic DIL that integrates two synergistic modules
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在大规模数据集上预训练的大规模基础模型已在医学图像分析中展现出强大的泛化能力。然而，它们通常在静态数据集上训练，难以应对临床数据持续演化的特性——新的成像设备、医疗机构和疾病亚型不断涌现。领域增量学习（DIL）为在不重访历史数据的前提下进行顺序适配提供了解决方案，但现有方法通常假设标签空间固定且领域异质性有限，限制了其在真实临床场景中的适用性。为应对这些挑战，我们提出 DK-DDIL，一个面向动态 DIL 的免回放框架，集成了两个协同模块：动态适配模块（DAM）采用动态秩选择与自适应正则化，在域漂移下灵活分配模型容量；知识继承与精炼（KIR）模块通过选择性适配器融合与原型级对比精炼来稳定跨域知识迁移。在皮肤病理诊断数据集、Cyst-X 3D MRI 队列以及 OfficeHome 基准上的实验表明，DK-DDIL 持续优于最优的 DIL 方法，凸显了其在动态 2D 医学、3D 医学与自然图像域上的有效性与通用性。
英文原文摘要 1398 字符
Large-scale foundation models pretrained on massive datasets have demonstrated strong generalization capabilities in medical image analysis. However, they are typically trained on static datasets and struggle to cope with the continuously evolving nature of clinical data, where new imaging devices, institutions, and disease subtypes constantly emerge. While domain-incremental learning (DIL) provides a solution for sequential adaptation without revisiting historical data, existing methods typically assume fixed label spaces and limited domain heterogeneity, restricting their applicability to real-world clinical scenarios. To address these challenges, we propose DK-DDIL, a rehearsal-free framework for dynamic DIL that integrates two synergistic modules: a Dynamic Adaptation Module (DAM) employing dynamic rank selection and adaptive regularization to flexibly allocate model capacity under domain shifts, and a Knowledge Inheritance and Refinement (KIR) module that stabilizes cross-domain knowledge transfer through selective adapter fusion and prototype-level contrastive refinement. Experiments on the Skin Pathology Diagnosis dataset, the Cyst-X 3D MRI cohort, and the OfficeHome benchmark demonstrate that DK-DDIL consistently outperforms state-of-the-art DIL approaches, highlighting its effectiveness and versatility across dynamic 2D medical, 3D medical, and natural image domains.