Recently, federated learning has raised increasing interest in the medical image analysis field due to its ability to aggregate multi-center data with privacy-preserving properties. A large amount of federated training schemes have been published, which we categorize into global (one final model), personalized (one model per institution) or hybrid (one model per cluster of institutions) methods. However, their applicability on the recently published Federated Brain Tumor Segmentation 2022 dataset has not been explored yet. We propose an extensive benchmark of federated learning algorithms from all three classes on this task. While standard FedAvg already performs very well, we show that some methods from each category can bring a slight performance improvement and potentially limit the final model(s) bias toward the predominant data distribution of the federation. Moreover, we provide a deeper understanding of the behavior of federated learning on this task through alternative ways of distributing the pooled dataset among institutions, namely an Independent and Identical Distributed (IID) setup, and a limited data setup. Our code is available at (https://github.com/MatthisManthe/Benchmark_FeTS2022).

中文翻译：

---

联合脑肿瘤分割：广泛的基准


最近，联邦学习因其能够聚合具有隐私保护特性的多中心数据而引起了医学图像分析领域越来越多的兴趣。已经发布了大量的联合培训方案，我们将其分为全局（一个最终模型）、个性化（每个机构一个模型）或混合（每个机构集群一个模型）方法。然而，它们在最近发布的 2022 年联合脑肿瘤分割数据集上的适用性尚未得到探索。我们针对此任务提出了来自所有三个类别的联邦学习算法的广泛基准。虽然标准 FedAvg 已经表现得很好，但我们表明每个类别中的一些方法可以带来轻微的性能改进，并可能限制最终模型对联邦主要数据分布的偏差。此外，我们通过在机构之间分配汇集数据集的替代方式，即独立相同分布式（IID）设置和有限数据设置，更深入地理解了联邦学习在该任务中的行为。我们的代码位于 (https://github.com/MatthisManthe/Benchmark_FeTS2022)。