Open Consortium for Decentralized Medical Artificial Intelligence

Informations projet

ODELIA

N° de convention de subvention: 101057091

DOI

10.3030/101057091

Date de signature de la CE 17 Novembre 2022

Date de début 1 Janvier 2023

Date de fin 31 Decembre 2027

Financé au titre de

• Health

Coût total

€ 8 691 755,75

Contribution de l’UE

€ 8 691 755,00

Coordonné par

EIBIR GEMEINNUTZIGE GMBH ZUR FORDERUNG DER ERFORSCHUNG DER BIOMEDIZINISCHEN BILDGEBUNG
Austria

Periodic Reporting for period 2 - ODELIA (Open Consortium for Decentralized Medical Artificial Intelligence)

Période du rapport: 2024-07-01 au 2025-12-31

Résumé du contexte et des objectifs généraux du projet

In the rapidly advancing field of healthcare, innovation is the driving force behind improving patient outcomes and expanding medical knowledge. The Open Consortium for Decentralized Medical Artificial Intelligence (ODELIA) is an EU-funded project poised to significantly advance healthcare through the use of Swarm Learning (SL). ODELIA is dedicated to harnessing the power of SL to develop artificial intelligence (AI) solutions for breast cancer detection in MRI screenings while prioritizing data privacy and fostering collaboration.

In an age where data privacy is paramount, ODELIA offers a groundbreaking approach to AI development. By uniting institutions in a pan-European SL Network, ODELIA facilitates secure and collaborative AI development without the need to share sensitive patient data. This ensures that patient privacy remains intact—a crucial ethical consideration in healthcare AI.

ODELIA’s primary objective is to build the first open-source software framework for SL, providing an assembly line for the streamlined development of AI solutions. Similar to federated learning, SL is a decentralized approach that enables machine learning models to learn on distributed data without sharing raw patient data. SL however does not require a central hub or server, which is typically required for federated learning that involves aggregating federated models to update a global model.

The project partners collaborate to develop a clinically useful AI algorithm for the detection of breast cancer in MRI, using a distributed database. Breast cancer is a leading cause of mortality among women, and early diagnosis is pivotal for improving survival rates. Using SL, ODELIA aims to enhance diagnostic performance, accelerate AI development, and create robust, generalizable solutions for better healthcare outcomes.

The ODELIA project’s success is expected to have far-reaching impact. It will not only deliver a useful medical application for the detection of breast cancer but also serve as a model for similar initiatives in other medical fields. By fostering secure, collaborative AI development and protecting patient data, ODELIA paves the way for a new era of healthcare innovation, thereby promoting and fostering transparency and trust in AI solutions in healthcare.

Travail effectué depuis le début du projet jusqu’à la fin de la période considérée dans le rapport et principaux résultats atteints jusqu’à présent

During the second reporting period, ODELIA moved from prototyping to operational deployment of its decentralized Swarm Learning (SL) infrastructure. The consortium strengthened the minimum viable product through expanded technical documentation, updated best‑practice guidelines, and support for partner‑site setup.

A major milestone was the creation and roll‑out of MediSwarm, the open‑source NVFLARE‑based SL platform. All eight partner sites reached operational readiness, enabling the first multi‑centre open‑source SL training run in December 2025.

In the breast‑cancer MRI use case, partners completed data curation, trained local baseline models, and performed joint SL experiments. A public MRI dataset was released, and the ODELIA public challenge successfully attracted high‑performing external solutions.

Front‑end development advanced with a fully functional, open‑source viewer supporting structured data collection, visualization of AI results, explainability heatmaps, and expert‑feedback workflows.

Regulatory and quality‑assurance work progressed through IEC‑62304‑aligned documentation, improved software‑development processes, and new tools for data‑quality and anomaly detection. Dissemination intensified through publications, conference presentations, and internal and external Summer Schools.

Overall, the period marked a decisive shift toward operational SL in real‑world clinical environments, strengthening the technical and regulatory foundation for the final phase of the project.

Progrès au-delà de l’état des connaissances et impact potentiel prévu (y compris l’impact socio-économique et les conséquences sociétales plus larges du projet jusqu’à présent)

In the second reporting period, ODELIA advanced from feasibility to operational validation of Swarm Learning (SL). The launch of the first multi‑centre training run on the MediSwarm platform, combined with harmonised data curation and the release of a public MRI dataset, confirmed that SL can function reliably across diverse clinical environments. Initial results indicate that SL‑trained models show improved generalisability compared to locally trained ones, supported by enhanced explainability and structured expert‑feedback tools developed within the new front‑end viewer.
ODELIA’s progress strengthens the case for decentralised, privacy‑preserving AI in medical imaging and prepares the pathway for expanding SL to other modalities and clinical tasks. Work on data‑quality assessment, anomaly detection, and regulatory‑aligned documentation further contributes to developing trustworthy and certifiable AI.
To enable broader uptake, continued research is needed to refine the models, expand datasets, and execute the upcoming multi‑site reader study. Demonstration at non‑partner sites, stronger links to industrial partners, and support for market readiness, IPR, and certification will be essential. Sustained investment in deployment‑ready infrastructure, quality assurance, and alignment with emerging regulatory frameworks will help ensure successful long‑term adoption of ODELIA’s SL ecosystem across European healthcare.

ODELIA Logo

ODELIA Social Media Card with Slogan