FedHisto-PAST：用于跨站点肺组织病理学分类的参数高效染色感知联邦学习
FedHisto-PAST: Parameter-Efficient Stain-Aware Federated Learning for Cross-Site Lung Histopathology Classification
浏览论文内容
中文总结 AI 辅助
本研究提出FedHisto-PAST v2，一种参数高效、染色感知的联邦学习方法，用于跨站点肺组织病理学分类，在LungHist700上取得宏F1为0.728560，仅更新1.25%参数。
中文摘要 AI 辅助
跨站点肺组织病理学分类必须考虑染色差异、非独立同分布客户端数据、缺失类别以及适配大型病理编码器的成本。本研究评估了FedHisto-PAST v2在腺癌（ACA）、正常组织和鳞状细胞癌（SCC）三类分类中的表现。FedHisto-PAST v2结合了冻结的HIBOU-B基础模型与参数高效适配、染色条件成对视图预测和特征一致性、可靠性感知原型学习以及自适应联邦聚合。实验采用五客户端、非独立同分布、原始数据本地的模拟，并包含固定内部评估、客户端级分析、组件消融、通信核算以及一个受开发影响的探索性LungHist700队列。所有主要方法在内部性能上均接近上限，这限制了在固定划分上的区分能力。在LungHist700上，FedHisto-PAST v2实现了0.728560的宏F1分数和0.730454的平衡准确率。对正常组织和SCC的更高识别伴随着较低的ACA召回率，且校准仍不完善。预测级一致性是外部消融分析中唯一具有明确支持的独立贡献的组件。特征一致性和原型正则化在宏F1分数上未显示出结论性的独立整体增益。该框架更新了模型参数的1.253841%。研究结果为染色感知、参数高效的联邦学习提供了探索性的跨数据集证据；但并未建立正式的隐私保护、患者级独立性、前瞻性部署或临床验证。
英文摘要
Cross-site lung histopathology classification must account for stain variation, non-IID client data, missing classes, and the cost of adapting large pathology encoders. This study evaluates FedHisto-PAST v2 for three-way classification of adenocarcinoma (ACA), Normal, and squamous cell carcinoma (SCC). FedHisto-PAST v2 combines a frozen HIBOU-B foundation model with parameter-efficient adaptation, stain-conditioned paired-view prediction and feature consistency, reliability-aware prototype learning, and adaptive federated aggregation. Experiments used a five-client, non-IID, raw-data-local simulation with fixed internal evaluation, client-level analysis, component ablations, communication accounting, and a development-influenced exploratory LungHist700 cohort. All principal methods achieved near- ceiling internal performance, which limited discrimination on the fixed split. On LungHist700, FedHisto- PAST v2 achieved a Macro-F1 of 0.728560 and a balanced accuracy of 0.730454. Higher recognition of Normal and SCC was accompanied by lower ACA recall, and calibration remained imperfect. Prediction-level consistency was the only component with a clearly supported independent contribution in the external ablation analysis. Feature consistency and prototype regularization showed no conclusive independent overall gains in Macro-F1. The framework updated 1.253841% of the model parameters. The results provide exploratory cross-dataset evidence for stain-aware, parameter-efficient federation; they do not establish formal privacy, patient-level independence, prospective deployment, or clinical validation.
发表机构
- International Islamic University Chittagong (IIUC)（吉大港国际伊斯兰大学）
- American International University-Bangladesh (AIUB)（美国国际大学孟加拉分校）
- King Saud University（沙特国王大学）
- Charles Sturt University（查尔斯特大学）
机构由 AI 辅助整理，请以论文原文为准。
