无需存储病人数据，用扩散模型生成图像实现医疗影像的持续学习。
EWC-Guided Diffusion Replay for Exemplar-Free Continual Learning in Medical Imaging
- 用条件扩散模型生成虚拟样本，替代真实患者数据进行持续学习。
- 在CheXpert上达0.851 AUROC，遗忘率比DER++降低30%以上。
- 适合需要隐私保护和低成本更新的医疗AI系统部署。
医学影像基础模型需随时间持续适应，但因隐私限制与成本问题，全量重训练常不可行。本文提出一种无需存储患者样本的持续学习框架，结合类别条件扩散重放与弹性权重巩固（EWC）。采用紧凑的Vision Transformer骨干网络，在八项MedMNIST v2任务和CheXpert数据集上评估。在CheXpert上，本方法取得0.851 AUROC，相比DER++遗忘率降低超过30%，接近联合训练的0.869 AUROC，且兼具高效与隐私保护优势。分析表明，遗忘程度与重放图像保真度及费雪信息加权的参数漂移相关，揭示了扩散重放与突触稳定性之间的互补作用。结果为可扩展、隐私友好的临床影像模型持续适配提供了可行路径。
原文摘要 · Abstract (English)
Medical imaging foundation models must adapt over time, yet full retraining is often blocked by privacy constraints and cost. We present a continual learning framework that avoids storing patient exemplars by pairing class conditional diffusion replay with Elastic Weight Consolidation. Using a compact Vision Transformer backbone, we evaluate across eight MedMNIST v2 tasks and CheXpert. On CheXpert our approach attains 0.851 AUROC, reduces forgetting by more than 30\% relative to DER\texttt{++}, and approaches joint training at 0.869 AUROC, while remaining efficient and privacy preserving. Analyses connect forgetting to two measurable factors: fidelity of replay and Fisher weighted parameter drift, highlighting the complementary roles of replay diffusion and synaptic stability. The results indicate a practical route for scalable, privacy aware continual adaptation of clinical imaging models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。