发表机构
Central South University; Fudan University（中南大学; 复旦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对医学图像分割域泛化中模型牺牲源域知识导致灾难性遗忘的问题，提出结构引导风格扩散增强和双分支协作学习网络CoDG-Net，在多个基准上超越现有方法并降低遗忘率。
AI 中文摘要
医学图像分割的域泛化（DG）既极具挑战性又至关重要。然而，现有的医学域泛化方法在很大程度上忽视了灾难性遗忘（CF）问题：模型在追求跨域鲁棒性的同时，往往牺牲了保留源域知识的能力。这可能直接威胁到已部署临床场景中的诊断安全性。为解决这一问题，我们研究了数据增强策略和灾难性遗忘在医学图像域泛化分割中的应用。首先，我们提出了一种结构引导的风格扩散增强方法。该方法在频域中受解剖结构一致性约束，对幅度谱进行跨域扩散，生成具有更多样化和更广泛风格覆盖的样本，以更好地支持域泛化。然后，我们设计了一个具有双分支交互架构的协作学习网络（CoDG-Net），并配合一种新颖的学习偏差引导策略，该策略在层级别和任务级别自适应地调节知识迁移，从而有效缓解源域上的灾难性遗忘。在单源和多源医学域泛化基准数据集上的实验和消融研究表明，CoDG-Net不仅在目标域分割性能上优于现有最先进方法，而且在源域数据上实现了更低的遗忘率。代码可在以下网址获取：此https URL。
英文摘要
Domain Generalization (DG) for medical image segmentation is both highly challenging and critically important. However, existing medical DG methods largely overlook the issue of Catastrophic Forgetting (CF): \textbf{Models often sacrifice their ability to retain source-domain knowledge while pursuing cross-domain robustness.} This can directly threaten diagnostic safety in already-deployed clinical scenarios. To address this, we investigate data augmentation strategies and catastrophic forgetting for medical image DG segmentation. First, we propose a structure-guided style diffusion augmentation method. Constrained by anatomical structure consistency in the frequency domain, this method performs cross-domain diffusion on the amplitude spectrum, generating samples with more diverse and broader style coverage to better support domain generalization. Then, we design a collaborative learning network with a dual-branch interactive architecture (CoDG-Net), together with a novel learning bias-guided strategy that adaptively regulates knowledge transfer at both the layer level and the task level, thereby effectively mitigating catastrophic forgetting on the source domain. Experiments and ablation studies on single-source and multi-source medical DG benchmark datasets demonstrate that CoDG-Net not only outperforms existing state-of-the-art methods in target-domain segmentation performance, but also achieves a lower forgetting rate on the source-domain data. The code is available at: https://github.com/wangprocess/CoDG-Net.
CommentsProceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence Main Track. Pages 1622-1630. https://doi.org/10.24963/ijcai.2026/181
Journal refMain Track, 2026, Pages 1622-1630
