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

Atlas / Spain

European Innovation Council · Running

ABIGAIL4D Advancing Breast cancer Individualised Generative AI for Longitudinal Outcomes

Coordinator
Fundacio Eurecat, Spain
Runs
1 October 2026 to 31 January 2031
Status
Running
EU funding
€4.8m
Total cost
—
Partners
10 organisations in 7 countries
Type
European Innovation Council
Grant agreement
101307206

What the project is doing

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

ABIGAIL4D pioneers a new approach to personalised oncology by developing and validating a 4D Generative AI system prototype that can learn disease evolution over time and support safer, more informed treatment decisions in early breast cancer. Today, decision support tools rely on static or single-modality data and cannot estimate how an individual patient would respond to alternative therapies. This limits clinical ability to compare options and optimise outcomes.

ABIGAIL4D combines multimodal longitudinal data, including imaging, pathology, genomics, and clinical variables, into a temporal model that reconstructs and forecasts tumour response, survival and toxicity. The system introduces counterfactual analysis to estimate patient-specific benefit and risk for different treatment strategies, such as escalation and de-escalation of chemotherapy or radiotherapy. Specialised AI agents (Radiology, Pathology, Oncology and Patient) collaborate through a stateful orchestrator to generate explainable recommendations with quantified uncertainty.

Clinicians remain in control at all times, supported by transparent rationales linked to clinical concepts and guidelines. The methodology follows a staged design: requirements co-creation with clinicians; development of the GenAI backbone and multi-agent framework; trust-by-design mechanisms for traceability, reproducibility and explainability; and validation in controlled, multi-centre lab settings. Regulatory documentation aligned with EU Medical Device Regulation and the AI Act will support future certification.

ABIGAIL4D AI agents and system, aim at enabling in the future personalised treatment decisions and more efficient care pathways. Expected benefits will include better therapy selection, fewer unnecessary scans and reduced burden for patients and healthcare systems. ABIGAIL4D provides a foundation for future expansion to other solid tumours, contributing to Europe’s leadership in responsible AI driven precision medicine

Topics

Who is involved

OrganisationCityCountryRole
Fundacio EurecatCerdanyola Del Valles (Barcelona)SpainCoordinator
Aileen Health FlexcoSalzburgAustriaParticipant
Athens University of Economics and Business - Research CenterAthinaGreeceParticipant
Fundacion Para La Investigacion Del Hospital Universitario La Fe De La Comunidad ValencianaValenciaSpainParticipant
Universitat Politecnica De ValenciaValenciaSpainParticipant
Institut Gustave RoussyVillejuifFranceParticipant
UnicancerParisFranceParticipant
Intesa Sanpaolo SpATorinoItalyParticipant
Neovivum Technologies Doo Novi SadNovi SadSerbiaParticipant
University of LeicesterLeicesterUnited KingdomParticipant

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