Fed-BioMed: Open, transparent and trusted federated learning for real-world healthcare applications

Cremonesi, Francesco; Vesin, Marc; Cansiz, Sergen; Bouillard, Yannick; Balelli, Irene; Innocenti, Lucia; Taiello, Riccardo; Silva, Santiago; Ayed, Samy-Safwan; Önen, Melek; et al.
Chapter book in "Federated Learning Systems", Studies in Computational Intelligence 832, Springer, 2nd ed.


The real-world implementation of federated learning (FL) is complex and requires research and development actions at the crossroad between different domains ranging from data science, to software programming, networking, and security. While today several FL libraries are proposed to data scientists and users, most of these frameworks are not designed to find seamless application in medical use-cases, due to the specific challenges and requirements of working with medical data and hospital infrastructures.
Moreover, governance, design principles, and security assumptions of these frameworks are generally not clearly illustrated, thus preventing the adoption in sensitive applications. Motivated by the current technological landscape of FL in healthcare, in this document we present Fed-BioMed: a research and development initiative aiming at translating FL into real-world medical research applications. We describe our design space, targeted users, domain constraints, and how these factors affect our software architecture.

Type:
Book
Date:
2025-02-13
Department:
Digital Security
Eurecom Ref:
8109
Copyright:
© Springer. Personal use of this material is permitted. The definitive version of this paper was published in Chapter book in "Federated Learning Systems", Studies in Computational Intelligence 832, Springer, 2nd ed.
 and is available at :
See also:

PERMALINK : https://www.eurecom.fr/publication/8109