Generative-AI based Agents to Revolutionize Medical Diagnosis and Treatment of Cancer

The grant opportunity titled "Generative-AI based Agents to Revolutionize Medical Diagnosis and Treatment of Cancer" is part of the EIC Pathfinder Challenges for 2025 under the Horizon Europe program. This initiative targets early-stage research aimed at developing and validating innovative applications of Generative AI to enhance medical imaging and health data integration specifically for cancer diagnosis and treatment.

Eligible applicants include universities, research institutions, small and medium-sized enterprises (SMEs), startups, and natural persons, while mid-cap and larger companies cannot act as single beneficiaries. Applications can be submitted by individual entities or consortia, with specific consortium requirements where groups must consist of independent legal entities from different EU Member States or Associated Countries.

Funding for this grant ranges from €500,000 to €4 million per project under a lump-sum grant model. The total budget for the call is €120 million, with a competitive success rate indicated to be below 10%. The application process is structured as a single stage, with a submission deadline set for October 29, 2025.

The project specifically focuses on the pivotal areas of technological and clinical innovation. Technologically, proposals are expected to explore the creation of GenAI algorithms that integrate multimodal health data, develop models for medical data augmentation, and enhance medical knowledge representation. Clinically, they will address predictive diagnosis and personalized treatment pathways for various cancer types, including breast, cervical, ovarian, prostate, lung, brain, stomach, and colorectal cancers.

Successful projects should contribute to the overarching goals of improving patient care and addressing current barriers in cancer treatment through advanced AI solutions that integrate diverse data sources while adhering to EU regulations on Trustworthy AI, data privacy, and security. Collaborative efforts are encouraged to enhance the potential for groundbreaking advancements in healthcare.

In summary, this grant aims to support high-risk, interdisciplinary research that leverages Generative AI for practical applications in oncology, ultimately driving innovation and improving health outcomes in Europe.

The EU Funding Opportunity: Generative-AI based Agents to Revolutionize Medical Diagnosis and Treatment of Cancer

This is a call for proposals under the Horizon Europe program, specifically within the EIC Pathfinder Challenges 2025. The call, titled "Generative-AI based Agents to Revolutionize Medical Diagnosis and Treatment of Cancer," aims to support early-stage research projects focused on developing and validating novel approaches for integrating and interpreting multimodal medical imaging and health data using Generative AI (GenAI). The goal is to create interactive GenAI autonomous agents, or super-agents, that can provide clinicians with a holistic view of patient care throughout the entire clinical pathway, enhancing pattern identification, reducing diagnostic errors, and improving cancer treatment.

The scope of this challenge addresses the limitations of current medical imaging and AI applications in cancer care. It acknowledges the difficulties clinicians face in combining diverse data sources for a comprehensive understanding of patient conditions, disease progression, and treatment efficacy. Existing AI applications often operate on single data modalities, lack sufficient data training, and suffer from a lack of interpretability, hindering their adoption in clinical settings.

The specific objectives of this call require project proposals to focus on one of the following cancers: breast cancer, cervical cancer, ovarian cancer, prostate cancer, lung cancer, brain cancer, stomach cancer, or colorectal cancer. Each proposal must address both a technological area (Area 1) and a clinical area (Area 2), with at least one sub-objective from each.

Area 1: Technological Area

GenAI-based tools for Integrating Multidimensional Multimodal health Data: Proposals should investigate techniques for developing GenAI algorithms that combine multidimensional and multimodal data from various sources, including multiple imaging modalities (MRI, CT, PET, X-ray), clinical data (electronic health records, lab results, structured and unstructured clinical data, pathology results, genetics and – omics data, videos, knowledge databases, and other resources). The goal is to create unified and actionable datasets for AI tool development.

Medical Data Augmentation: Proposals should develop GenAI models based on groundbreaking techniques in the conceptual or initial experimental phase for medical data augmentation. These models should be capable of creating highly realistic synthetic medical data (images, genomics data, etc.) and generating complementary data from existing sources (e.g., synthetic CT images from MRI images) to support iterative model training.

Medical Knowledge Representation and Integration: Proposals should create an initial prototype GenAI model for medical knowledge representation and integration. This model should aim to develop a comprehensive and dynamic medical knowledge base, to identify discrete medical imaging features associated with demographic information and systemic conditions, to improve the interpretability of AI-based models and extract new knowledge.

Area 2: Clinical Area

Predictive Diagnosis: Proposals should develop an interactive autonomous agent capable of assessing the likelihood of a patient developing cancer by analysing their medical history, imaging data, and genetic information. The agent should provide personalised health risk predictions, enabling early detection and preventive measures.

Enhance Personalized Treatment Selection: Proposals should develop novel AI algorithms and architectures that leverage multidimensional and multimodal data integration, along with synthetic data generation, to predict the optimal treatment pathway for specific patient conditions, as well as to forecast disease progression and treatment efficacy.

Across both areas, appropriate performance metrics should be used for continuous evaluation and testing of the scientific and technical robustness of developed algorithms and architectures. Rigorous testing against diverse datasets is essential to ensure reliable model performance across various patient demographics and conditions. Projects should also conduct proof-of-concept studies to demonstrate improved diagnosis and treatment compared to current clinical practice. The focus should be on enhancing the interpretability of AI models/agents, and the AI models developed are expected to comply with the EU concept for Trustworthy AI, relevant ethical principles, and the AI Act, with careful attention to data quality, transparency, privacy, and security.

Proposers are encouraged to leverage the data and tools available in the Cancer Image Europe platform and contribute datasets, AI tools, and models to the platform. All datasets produced should be described with metadata records in the EU dataset catalogue of the European Health Data Space (EHDS) using the Health DCAT-AP metadata standard. Projects addressing only one area or other cancer types will be considered out of scope.

Expected outcomes and impacts include supporting the European AI Strategy and the Cancer Plan for Europe and the Cancer Mission by developing next-generation models for cancer diagnosis and treatment with Generative AI. The challenge aims to create a collaborative environment with diverse expertise to address the complexities of developing autonomous agents for holistic patient care. It aspires to improve patient care, reduce pressure on the healthcare system, enhance the quality and reliability of medical services, and foster innovation in Europe.

The portfolio of selected projects will deliver a set of agents/models for improved diagnosis and personalized treatment, collaborating to create a shared database of synthetically generated images, compare the use of agent combinations, benchmark agents, define innovative clinical pathways, validate agents at clinical premises, and develop standardized methods for evaluating AI-Act and Medical Device Regulation (MDR)-compliant generative AI models.

The portfolio of projects will be composed to address all cancers mentioned in the call, apply different technologies, and provide access to relevant clinical facilities and research infrastructures, categorized by type of cancer, type of technology, and access to infrastructure data and ecosystem integration.

Specific conditions include restrictions for applications concerning the evolution of European communication networks (5G, post-5G). Proposals must meet general eligibility requirements and specific requirements for the challenge. The EIC Pathfinder Challenges support collaborative or individual research and innovation from consortia or single legal entities established in a Member State or an Associated Country. Consortia of two entities must be comprised of independent legal entities from two different Member States or Associated Countries. Consortia of three or more entities must include at least three legal entities, independent from each other and each established in a different country. Legal entities may be universities, research organisations, SMEs, start-ups, or natural persons. Mid-caps and larger companies will not be permitted as single beneficiaries.

The proposal page limit for sections 1 to 3 of Part B is 30 A4 pages.

The call documents include the EIC Work Programme 2025, FAQs, standard application and evaluation forms, a challenge guide, model grant agreements, call-specific instructions, a detailed budget table, information on clinical studies, and guidance on lump sums. Additional documents include the HE Programme Guide, HE Framework Programme, HE Specific Programme Decision, EU Financial Regulation, rules for legal entity validation, the EU Grants AGA, and the Funding & Tenders Portal Online Manual.

The budget for the call is EUR 120,000,000, with contributions ranging from EUR 500,000 to EUR 4,000,000. The indicative number of grants is 8888. The planned opening date is 24 July 2025, and the deadline is 29 October 2025, at 17:00:00 Brussels time.

In summary, this EU funding opportunity seeks to revolutionize cancer diagnosis and treatment by fostering the development of advanced GenAI-based agents. It encourages collaborative and innovative research projects that integrate diverse medical data, enhance AI interpretability, and comply with ethical and regulatory standards, ultimately aiming to improve patient care and establish Europe as a leader in AI-driven healthcare.

Eligible Applicant Types: The eligible applicant types include universities, research organisations, SMEs, start-ups, and natural persons. Mid-caps and larger companies are not permitted as single beneficiaries. The call supports collaborative or individual research and innovation from consortia or from single legal entities established in a Member State or an Associated Country. In the case of a consortium, the proposal must be submitted by the coordinator on behalf of the consortium. Consortia of two entities must be comprised of independent legal entities from two different Member States or Associated Countries. Consortia of three or more entities must include as beneficiaries at least three legal entities, independent from each other and each established in a different country.

Funding Type: The funding type is a grant, specifically a HORIZON EIC Grant, utilizing a Lump Sum Model Grant Agreement (MGA).

Consortium Requirement: Both single applicants and consortia are eligible. For consortia, specific requirements apply based on the number of entities involved. Consortia of two entities must be comprised of independent legal entities from two different Member States or Associated Countries. Consortia of three or more entities must include as beneficiaries at least three legal entities, independent from each other and each established in a different country.

Beneficiary Scope (Geographic Eligibility): The geographic eligibility includes entities established in a Member State or an Associated Country. The standard admissibility and eligibility conditions and the eligibility of applicants from third countries are detailed in Annex 2 of the EIC Work Programme 2025.

Target Sector: The target sector is health, specifically focusing on the development of Generative AI (GenAI) based solutions for medical diagnosis and treatment of cancer. It also encompasses ICT, biotech/medtech, pharma/healthcare, artificial intelligence, and DeepTech.

Mentioned Countries: The opportunity mentions Member States and Associated Countries of the European Union.

Project Stage: The project stage is early-stage groundbreaking research projects that will develop and validate novel approaches and concepts. The GenAI models should be based on groundbreaking techniques that are in the conceptual or initial experimental phase for medical data augmentation. Proof of concept studies in controlled settings are expected.

Funding Amount: The funding range is between €500,000 to €4,000,000 per grant.

Application Type: The application type is a single-stage call.

Nature of Support: Beneficiaries will receive money in the form of a grant.

Application Stages: The application process is a single-stage process.

Success Rates: The indicative number of grants is 8, and the total budget is 120,000,000 EUR.

Co-funding Requirement: The text does not explicitly mention a co-funding requirement.

Summary:

This EIC Pathfinder Challenge aims to revolutionize medical diagnosis and treatment of cancer by creating interactive GenAI autonomous agents. The challenge supports early-stage research projects focused on integrating and interpreting multimodal medical imaging and health data, as well as generating reliable synthetic medical data. Project proposals should focus on one of the following cancers: breast, cervical, ovarian, prostate, lung, brain, stomach, or colorectal cancer. Proposals must address both a technological area (developing GenAI algorithms, medical data augmentation, medical knowledge representation) and a clinical area (predictive diagnosis, personalized treatment selection). The goal is to develop AI models that comply with EU standards for Trustworthy AI and contribute to the Cancer Image Europe platform. The expected outcomes include improved patient care, reduced pressure on the healthcare system, and the establishment of Europe as a leader in AI-driven cancer treatment. Eligible applicants include universities, research organizations, SMEs, and start-ups from EU Member States and Associated Countries, with funding ranging from €500,000 to €4,000,000 per project. The call follows a single-stage application process with a deadline of October 29, 2025.