联邦学习让多机构协作数字化心电图，既保隐私又提精度。
Privacy-Aware Federated nnU-Net for ECG Page Digitization
- 用联邦学习训练完整nnU-Net模型，不共享原始图像。
- FedAdam比FedAvg和FedProx收敛更快，接近集中式性能。
- 结合差分隐私与安全聚合，可审计地保护用户隐私。
深度神经网络可将心电图图像转换为可分析波形，但集中训练常与跨机构隐私及部署约束冲突。本文提出一种跨孤岛联邦数字化框架，在真实非独立同分布异构性（布局、网格样式、扫描仪配置、噪声）下训练全模型nnU-Net分割主干，不共享图像，并在各站点间聚合更新。协议集成三种标准服务器聚合器——FedAvg、FedProx和FedAdam，结合安全聚合与中心级用户级差分隐私（采用Renyi追踪），确保实用性与形式化隐私保障。关键特性包括：(i) 客户端端到端全模型训练与同步；(ii) 安全聚合，仅当参与阈值满足时，服务器观察到一次截断加权和；(iii) 后聚合应用中心高斯差分隐私（使用Renyi追踪），实现可审计的用户级隐私；(iv) 校准感知数字化流程，包含页面归一化、轨迹分割、网格泄露抑制与向量化为十二导联信号。在来自PTB-XL的数据上实验表明，采用自适应服务器更新（FedAdam）相较FedAvg和FedProx收敛更迅速，后期性能更高，逼近集中式表现。隐私机制在保持竞争力准确率的同时，防止原始图像或单客户端更新暴露，提供适用于多机构场景的可部署、可审计保障。
原文摘要 · Abstract (English)
Deep neural networks can convert ECG page images into analyzable waveforms, yet centralized training often conflicts with cross-institutional privacy and deployment constraints. A cross-silo federated digitization framework is presented that trains a full-model nnU-Net segmentation backbone without sharing images and aggregates updates across sites under realistic non-IID heterogeneity (layout, grid style, scanner profile, noise). The protocol integrates three standard server-side aggregators--FedAvg, FedProx, and FedAdam--and couples secure aggregation with central, user-level differential privacy to align utility with formal guarantees. Key features include: (i) end-to-end full-model training and synchronization across clients; (ii) secure aggregation so the server only observes a clipped, weighted sum once a participation threshold is met; (iii) central Gaussian DP with Renyi accounting applied post-aggregation for auditable user-level privacy; and (iv) a calibration-aware digitization pipeline comprising page normalization, trace segmentation, grid-leakage suppression, and vectorization to twelve-lead signals. Experiments on ECG pages rendered from PTB-XL show consistently faster convergence and higher late-round plateaus with adaptive server updates (FedAdam) relative to FedAvg and FedProx, while approaching centralized performance. The privacy mechanism maintains competitive accuracy while preventing exposure of raw images or per-client updates, yielding deployable, auditable guarantees suitable for multi-institution settings.
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。