Federated Learning and mUlti-party computation Techniques for prostatE cancer

Type Start End
European May 2023 Apr 2026
Responsible URL
Cecilio Angulo (GREC-IDEAI) - Veronica Vilaplana (GPI-IDEAI) FLUTE




Call: HORIZON-HLTH-2022-IND-13-02

Grant Agreement: 101095382


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. 


The consortium driving the FLUTE project comprises an interdisciplinary team of 11 partners. This includes three clinical and data partners from distinct countries, three technology SMEs, three technology research partners, a legal/ethics partner, and a standards organization. The diverse expertise of the consortium members will ensure comprehensive and effective project implementation. The partners of FLUTE are: Inria Lille - Nord Europe (France), with the role of project coordinator, Arteevo Technologies Ltd (Israel), Centre Hospitalier Universitaire De Liege (Belgium), Fundacio Hospital Universitari Vall D'Hebron - Institut De Recerca (Spain), Gradiant (Spain), HL7 International Foundation, Istituto Romagnolo Per Lo Studio Dei Tumori Dino Amadori - Irst Srl (Italy), Quibim (Spain), Technovative Solutions Ltd (UK), Time.Lex (Belgium), Universitat Politecnica De Catalunya (Spain).


Improve prediction of aggressive prostate cancer, minimizing unnecessary biopsies.

The FLUTE project is set to revolutionize healthcare data utilization through a privacy-preserving approach, ensuring patient data does not need to leave the secure hospital databases where they are stored. With a focus on secure multi-party computation in Federated Learning and the integration of advanced AI models, FLUTE will pioneer technical innovations that enhance data privacy and security in healthcare. This innovative approach will improve predictions of aggressive prostate cancer while minimizing unnecessary biopsies, ultimately benefiting patients and reducing associated costs. The project will integrate these technical advancements into a cutting-edge platform designed to provide a secure environment for the development, testing, and deployment of healthcare AI solutions. By leveraging real-world health data from data hubs and the generation of synthetic data, the FLUTE platform will foster innovation in the healthcare industry. 

The incidence of Prostate Cancer worldwide

Prostate cancer is the second most commonly diagnosed cancer in men, with approximately 1.4 million diagnoses worldwide in 2020. Studies have shown that the prevalence of prostate cancer increases with age, ranging from 5% at age <30 to 59% at age >79. The frequency of prostate cancer varies among different ethnic backgrounds and geographical areas. The incidence of prostate cancer diagnosis is influenced by factors such as PSA (prostate specific antigen) testing rates and screening recommendations. Incidence rates are highest in Australia/New Zealand, Northern America, Western Europe, and Northern Europe, while rates are low in Eastern and South-Central Asia. Mortality rates worldwide show relatively less variation, with higher rates observed in populations of African descent and lower rates in Asia. Overall, mortality due to prostate cancer has decreased in most Western nations, but the extent of reduction varies between countries. Hence, the importance of developing tools which help physicians in the diagnose process is crucial


The FLUTE project: contributing to the HL7 FHIR standard and GDPR policy

A key aspect of the FLUTE project is its commitment to the global development of the HL7 FHIR standard, a next-generation interoperability standard designed to enable quick and efficient exchange of health data, including clinical and administrative data. The aim is to contribute to the enhancement and widespread adoption of the FHIR standard. Additionally, the project will establish novel guidelines for GDPR-compliant cross-border Federated Learning in healthcare, ensuring regulatory compliance and data protection.


Giardina C, Vilaplana V, Pardàs M, Guardia O. Synthesis of Prostate MRI Scans: A Comparison of StyleGAN2-ADA and Latent Diffusion Models . In: Conferencia de la Asociación Española para la Inteligencia Artificial, IABioMed workshop. Conferencia de la Asociación Española para la Inteligencia Artificial, IABioMed workshop. ; In Press.