SOURCE-LINKED INTELLIGENCE
From Magnetic Resonance Imaging to Molecular Signatures: Generative AI for Virtual Biopsy in Gliomas
From Magnetic Resonance Imaging to Molecular Signatures: Generative AI for Virtual Biopsy in Gliomas 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 insig
Read original source ↗ Open in workspace
- recordType
- award
- status
- SIGNED
- region
- EU
- value
- 3996043.38
- unit
- EUR
Evidence & attribution
European Commission, CORDIS Horizon Europe project dataset. Metadata adapted.
License: CORDIS reuse policy
First collected: 2026-09-20T05:31:32.981Z. This is not the publication date.