Seminal
The magazine and atlas of EU-funded researchA new publication from the web and AI team at Scott Charnley

Atlas / Italy

European Innovation Council · Running

GLIOGEN-X From Magnetic Resonance Imaging to Molecular Signatures: Generative AI for Virtual Biopsy in Gliomas

Coordinator
Siena Imaging s.r.l., Italy
Runs
1 October 2026 to 30 September 2030
Status
Running
EU funding
€4.0m
Total cost
—
Partners
5 organisations in 3 countries
Type
European Innovation Council
Grant agreement
101307322

What the project is doing

In the project's own words, from its summary on CORDIS.

GLIOGEN-X pioneers a new paradigm in neuro-oncology. It is a novel generative AI modality designed to test whether brain MRI truly encodes recoverable molecular information about gliomas. While current radiogenomic approaches assume that deep networks can implicitly learn tumour biology from images, this project transforms that assumption into a falsifiable hypothesis, experimentally probing the informational limits of MRI and its capacity to support virtual biopsy.

The project builds on three synergistic, high-risk/high-gain pillars. First, generative experimentation will use controlled diffusion models to synthesise realistic, biomarker-aware glioma MRIs, testing whether molecular conditioning injects measurable and reproducible phenotypic structure. Second, interpretable and uncertainty-aware prediction will translate these generative insights into transparent virtual-biopsy models, capable of identifying key molecular signatures from imaging alone.

Third, a federated research infrastructure will ensure privacy-preserving, GDPR-compliant collaboration across hospitals, enabling robust validation without data sharing and fostering reproducibility. Beyond its scientific objectives, GLIOGEN-X establishes the methodological and ethical foundations for AI Act–ready medical AI: explainable, auditable, and human-centred by design. Its outputs, a pathology-aware generative engine, hybrid datasets, interpretable predictors and an experimental research platform, will form a reusable European asset for trustworthy AI in healthcare.

Whether confirming or refuting the central hypothesis, GLIOGEN-X will deliver transformative knowledge by defining how far imaging can reveal tumour biology and paving the way for non-invasive, personalised oncology guided by trustworthy artificial intelligence.

Topics

Who is involved

OrganisationCityCountryRole
Siena Imaging s.r.l.SienaItalyCoordinator
Fundacio per a La Universitat Oberta De CatalunyaBarcelonaSpainParticipant
Fondazione Toscana Life SciencesSienaItalyParticipant
Northern Care Alliance Nhs Foundation TrustSalfordUnited KingdomThird party
The University of ManchesterManchesterUnited KingdomParticipant

Source: CORDIS, European Commission. Data of 5 Nov 2026, reused under the Commission's reuse policy. View on CORDIS · Grant DOI