Ankolekar Anshu, Boie Sebastian, Abdollahyan Maryam, Gadaleta Emanuela, Hasheminasab Seyed Alireza, Yang Guang, Beauville Charles, Dikaios Nikolaos, Kastis George Anthony, Bussmann Michael, Chelala Claude, Khalid Sara, Kruger Hagen, Lambin Philippe, Papanastasiou Giorgos
Department of Precision Medicine, GROW Research Institute for Oncology and Reproduction, Maastricht University, Maastricht, the Netherlands.
Pfizer Pharma GmbH, Berlin, Germany.
NPJ Digit Med. 2025 May 27;8(1):314. doi: 10.1038/s41746-025-01591-5.
Federated learning (FL) is advancing cancer research by enabling privacy-preserving collaborative training of machine learning (ML) models on diverse, multi-centre data. This systematic review synthesises current knowledge on state-of-the-art FL in oncology, focusing on breast, lung, and prostate cancer. Unlike previous surveys, we critically evaluate FL's real-world implementation and impact, demonstrating its effectiveness in enhancing ML generalisability and performance in clinical settings. Our analysis reveals that FL outperformed centralised ML in 15 out of 25 studies, spanning diverse models and clinical applications, including multi-modal integration for precision medicine. Despite challenges identified in reproducibility and standardisation, FL demonstrates substantial potential for advancing cancer research. We propose future research focus on addressing these limitations and investigating advanced FL methods to fully harness data diversity and realise the transformative power of cutting-edge FL in cancer care.
联邦学习（FL）通过在多样的多中心数据上进行隐私保护的机器学习（ML）模型协作训练，推动了癌症研究。本系统综述综合了当前关于肿瘤学中最先进的联邦学习的知识，重点关注乳腺癌、肺癌和前列腺癌。与以往的调查不同，我们严格评估了联邦学习在现实世界中的实施情况和影响，证明了其在提高机器学习在临床环境中的泛化能力和性能方面的有效性。我们的分析表明，在25项研究中的15项中，联邦学习的表现优于集中式机器学习，涵盖了各种模型和临床应用，包括用于精准医学的多模态整合。尽管在可重复性和标准化方面存在挑战，但联邦学习在推进癌症研究方面显示出巨大潜力。我们建议未来的研究集中在解决这些限制，并研究先进的联邦学习方法，以充分利用数据多样性，实现前沿联邦学习在癌症治疗中的变革力量。
