AI 中文总结
针对联邦医学影像中的高标注成本、领域偏移和OOD干扰，提出FIDAL框架，结合证据不确定性、多样性加权和自适应OOD拒绝，在三个基准上优于现有方法，节省标注时间。
AI 中文摘要
联邦学习使得各机构无需集中数据即可进行协作模型训练，然而高标注成本、领域偏移和类别不平衡仍是主要障碍，尤其是在无关的分布外（OOD）样本稀释了标注数据的情况下。现有的主动学习方法针对分布内（ID）数据的不确定性或多样性，而忽视了联邦临床环境中的未知样本。我们提出了FIDAL，一个开放集联邦主动学习框架，结合了校准的全局-局部证据不确定性、支持集多样性加权和自适应OOD拒绝。拒绝门通过Otsu准则按客户端和轮次阈值化基础模型的高斯覆盖信号，从而查询高信息量的ID样本，同时排除无关的离群点，无需手动调整阈值。在三个多中心医学影像基准（皮肤病理学、组织病理学和带有自然产生伪影的乳腺X线摄影）上的现实开放集场景评估中，FIDAL在平衡准确率上比基于检测器的开放集方法高出约12个百分点，并且是唯一在全部三个基准的准确率-ID纯度Pareto前沿上的方法。在相同的查询预算下，它比每个准确率匹配的基线在OOD样本上至少少花费1.3倍的标注，在乳腺X线摄影基准上节省了估计7-29小时的专家阅读时间。通过仅标注数据池的一小部分，它在各模态上达到或超过了全监督性能。这些结果突显了在医学开放集联邦主动学习中整合不确定性、多样性和OOD拒绝的价值。
英文摘要
Federated learning enables collaborative model training across institutions without centralizing data, yet high annotation costs, domain shifts, and class imbalance remain major obstacles, especially when irrelevant out-of-distribution (OOD) samples dilute the labeled data. Existing active learning methods target uncertainty or diversity within in-distribution (ID) data and overlook unknown samples in federated clinical settings. We propose FIDAL, an open-set federated active learning framework that combines calibrated global-local evidential uncertainty, support-set diversity weighting, and adaptive OOD rejection. The rejection gate thresholds a foundation-model Gaussian-coverage signal per client and per round with Otsu's criterion, so that highly informative ID samples are queried while irrelevant outliers are excluded without any hand-tuned threshold. Evaluated on three multi-center medical imaging benchmarks (dermatology, histopathology, and mammography with organically occurring artifacts) in realistic open-set scenarios, FIDAL outperforms detector-based open-set methods by up to about 12 percentage points of balanced accuracy and is the only method on the accuracy-ID purity Pareto front of all three benchmarks. At an equal query budget it spends at least 1.3 times fewer annotations on OOD samples than every accuracy-matched baseline, saving an estimated 7-29 hours of expert reading on the mammography benchmark. By labeling only a fraction of the data pool, it matches or exceeds fully supervised performance across modalities. These results highlight the value of integrating uncertainty, diversity, and OOD rejection in open-set federated active learning for medicine.
