用于组织病理学图像分类的去中心化八卦学习与联邦平均
Decentralized Gossip Learning and Federated Averaging for Histopathology Image Classification
浏览论文内容
中文总结 AI 辅助
本研究比较了FedAvg、去中心化八卦学习及混合方法在IDC组织病理学图像分类中的性能，发现混合八卦-FedAvg在ROC-AUC上略优，FedAvg作为服务器基线最稳定，拓扑感知八卦提供了可行的去中心化替代方案。
中文摘要 AI 辅助
乳腺组织病理学分析日益依赖于分布式学习，因为跨机构的直接数据汇集往往受到隐私、治理和通信限制的约束。本研究比较了基于服务器的联邦平均（FedAvg）、完全去中心化的八卦学习以及混合八卦-FedAvg在浸润性导管癌（IDC）斑块分类中的性能。实验使用了277,524个彩色图像斑块，采用患者不相交的训练、验证和测试分区，并在六个节点上进行工作负载均衡、基于Dirichlet分布的分配。评估了环形、随机度3和全连接八卦拓扑，并进行了统计异质性、混合系数、学习率、模型漂移、预测分歧、校准、临床动机操作点、通信负载和患者级IDC负担的敏感性分析，以及辅助骨干网络鲁棒性分析。在主要的alpha=0.3实验中，混合八卦-FedAvg实现了0.8811的测试受试者工作特征曲线下面积（ROC-AUC），紧随其后的是FedAvg（0.8801）和全连接八卦（0.8751）。在三次独立的患者级重复实验中，FedAvg和混合八卦-FedAvg获得了相同的平均ROC-AUC 0.9082，标准差分别为0.0037和0.0043。混合方法实现了最高的平均精确率-召回率曲线下面积0.8240，而FedAvg产生了最低的平均Brier分数0.1335。更密集的八卦图改善了判别能力，但增加了理论模型负载，而环形八卦对学习率和混合强度仍然敏感。总体而言，FedAvg提供了最一致可靠的基于服务器的基线，拓扑感知的八卦提供了一种可行的去中心化替代方案，而混合八卦-FedAvg在点对点扩散和周期性全局协调之间提供了平衡的折衷。
英文摘要
Breast histopathology analysis increasingly relies on distributed learning because direct data pooling across institutions is often restricted by privacy, governance, and communication constraints. This study compares server-based Federated Averaging (FedAvg), fully decentralized gossip learning, and Hybrid Gossip-FedAvg for invasive ductal carcinoma (IDC) patch classification. Experiments used 277,524 color image patches with patient-disjoint training, validation, and test partitions and a workload-balanced, Dirichlet-guided allocation across six nodes. Ring, random degree-3, and fully connected gossip topologies were evaluated together with sensitivity analyses for statistical heterogeneity, mixing coefficient, learning rate, model drift, prediction disagreement, calibration, clinically motivated operating points, communication payload, and patient-level IDC burden, together with auxiliary backbone robustness analyses. In the principal alpha=0.3 experiment, Hybrid Gossip-FedAvg achieved a test area under the receiver operating characteristic curve (ROC-AUC) of 0.8811, closely followed by FedAvg at 0.8801 and fully connected gossip at 0.8751. Across three independent patient-level repetitions, FedAvg and Hybrid Gossip-FedAvg obtained the same mean ROC-AUC of 0.9082, with standard deviations of 0.0037 and 0.0043, respectively. Hybrid achieved the highest mean area under the precision-recall curve of 0.8240, whereas FedAvg produced the lowest mean Brier score of 0.1335. Denser gossip graphs improved discrimination but increased theoretical model payload, while ring gossip remained sensitive to learning rate and mixing strength. Overall, FedAvg provided the most consistently reliable server-based baseline, topology-aware gossip offered a viable decentralized alternative, and Hybrid Gossip-FedAvg provided a balanced compromise between peer-to-peer diffusion and periodic global coordination.
发表机构
- Antalya Bilim University（安塔利亚比尔姆大学）
- Ankara University（安卡拉大学）
- Northwestern University（西北大学）
机构由 AI 辅助整理，请以论文原文为准。
