FLUTE: Federate Learning and mUlti-party computation Techniques for prostatE cancer


Basic info:


The goal of the multi-disciplinary FLUTE project is to advance and scale up data-driven healthcare by developing novel methods for privacy-preserving cross-border utilization of data hubs. Advanced research will be performed to push the performance envelope of secure multi-party computation in Federated Learning, including the associated AI models and secure execution environments.

The technical innovations of the project will be integrated in a privacy-enforcing platform that will provide innovators with a provenly secure environment for federated healthcare AI solution development, testing and deployment, including the integration of real world health data from the data hubs and the generation and utilization of synthetic data (categorical, numerical and images).

To maximize the impact, adoption and replicability of the results, the project will contribute to the global HL7 FHIR standard development, and create novel guidelines for GDPR-compliant cross-border Federated Learning in healthcare.

To demonstrate the practical use and impact of the results, the project will integrate the FLUTE platform with health data hubs located in three different countries, use their data to develop a novel federated AI toolset for diagnosis of clinically significant prostate cancer and perform a multi-national clinical validation study of its efficacy, which will help to improve predictions of aggressive prostate cancer while avoiding unnecessary biopsies, thus improving the welfare of patients and significantly reducing the associated costs.

The FLUTE project will boost the competitiveness of European SMEs and research organizations in the digital age, and increase the productivity and efficiency of the healthcare industry.


1Institut National de recherche en informatique et automatiqueINRIARTOFR
2Fundación Centro Tecnolóxico de Telecomunicacións de GaliciaGRADRTOES
3Arteevo Technologies Ltd.AVOSMEIL
4Istituto Romagnolo per lo studio dei tumori dino amadori - IRSTIRSTMEDIT
5Technovative Solutions LtdTVSSMEUK
7Centre Hospitalier Universitaire de LiègeCHUMEDBE
8Universitat Politècnica de CatalunyaUPCUNIES
9Fundacio Hospital Universitari Vall d'Hebron - Institut De RecercaVHIRMEDES
10HL7 Europe FoundationHL7SDOBE
11 Quibim Sociedad Limitada QBIMSMEES

INRIA contribution

INRIA is the coordinator of this project.
An important technical contribution will concern improving scalability of multi-party protocols in the context of machine learning, e.g., exploiting data sparsity.

People and related projects

This is a project of the MAGNET team.
Project members include: Most of the algorithms developed by INRIA-MAGNET will be included in the TAILED open source library.


We are looking for For applying, please read the general guidelines and send email to Jan (dot) Ramon (at) inria (dot) fr.
There are also open positions on related projects.

Project website