Menu
The idea of the RadioVal project is to develop and implement a very comprehensive validation of artificial intelligence solutions in the breast cancer treatment.
We hope our projects promotes precision medicine with tools that will help clinicians to perform more precise medicine, individualised to the patient’s need.
RadioVal will help clinicians help patients.
RadioVal implements the first international, clinical validation study of radiomics-based prediction of neoadjuvant chemotherapy treatment response from breast MRI. The project will develop a comprehensive and standardised methodological framework for multi-faceted radiomics evaluation based on the FUTURE-AI Guidelines, to assess Fairness, Universality, Traceability, Usability, Robustness and Explainability. Furthermore, the project will introduce new tools to enable transparent and continuous evaluation and monitoring of the radiomics tools over time. The RadioVal study will be implemented through a multi-stakeholder approach, taking into account clinical and healthcare needs, as well as socio-ethical and regulatory requirements from day one.
Project name: International Clinical Validation of Radiomics Artificial Intelligence for Breast Cancer Treatment Planning
Project acronym: RadioVal
Start Date: September 1, 2022
End Date: August 31, 2026
Coordinator: University of Barcelona
Consortium: 16 partners from 13 countries
Funding: € 5,838,576
Breast cancer is now the most common cancer worldwide, surpassing lung cancer in 2020 for the first time. It is responsible for almost 30% of all cancers in women and current trends show its increasing incidence. Neoadjuvant chemotherapy (NAC) has shown promise in reducing mortality for advanced cases, but the therapy is associated with a high rate of over-treatment, as well as with significant side effects for the patients. For predicting NAC respondents and improving patient selection, artificial intelligence (AI) approaches based on radiomics have shown promising preclinical evidence, but existing studies have mostly focused on evaluating model accuracy, all-too often in homogeneous populations.
RadioVal is the first multi-centre, multi-continental and multi-faceted clinical validation of radiomics driven estimation of NAC response in breast cancer. The project builds on the repositories, tools and results of five EU-funded projects from the AI for Health Imaging (AI4HI) Network, including a large multi-centre cancer imaging dataset on NAC treatment in breast cancer.
To test applicability as well as transferability, the validation will take place in eight clinical centres from three high-income EU countries (Sweden, Austria, Spain), two emerging EU countries (Poland, Croatia), and three countries from South America (Argentina), North Africa (Egypt) and Eurasia (Türkiye). RadioVal will develop a comprehensive and standardised methodological framework for multi-faceted radiomics evaluation. Furthermore, the project will introduce new tools to enable transparent and continuous evaluation and monitoring of the radiomics tools over time. The RadioVal study will be implemented through a multi-stakeholder approach, taking into account clinical and healthcare needs, as well as socio-ethical and regulatory requirements from day one.
We will evaluate multiple dimensions of performance, including accuracy, robustness, fairness, usability, confidence and productivity.
The first half of the project is dedicated to a dialogue with clinicians, patients, AI developers and ethicolegal experts to design the evaluation study and understand the exact needs of all stakeholders. During the second half, we will perform the evaluation study on real-world data from eight hospitals all over the world.
We want to involve a multidisciplinary group of stakeholders and understand that it’s very important that clinicians, patients and developers understand the project, and that they are involved in it.
Ultimately, we want to establish AI tools that provide insights into the decision-making (explainability), how certain or uncertain they are (uncertainty) and provide traceability tools to track AI performance through time.
RadioVal is a research project, but it focuses on research very close to clinical practice.
We noticed a lot of AI tools were of very good quality with interesting results, but not sufficiently translated into clinical practice because there was a lack of evidence they could be trusted in the real world
Dr. Karim Lekadir is a Senior/Tenure Track Researcher at the University of Barcelona and coordinator of RadioVal. He holds a Master’s Degree in Computer Science from the University of Montpellier II (France) and a PhD in Medical Image Computing from Imperial College London (UK).
Dr. Oliver Diaz is an Assistant Professor at UB and the co-coordinator of RadioVal. He holds a Ph.D. in Medical Imaging/Physics from the Centre for Vision, Speech, and Signal Processing at the University of Surrey (UK).
Jamilia Arykbaeva is the Project Manager of RadioVal. She holds a Master’s degree in Political Science and in Political and Electoral Analysis from the University of Granada and Pontificia Universidad Católica Mater Maestra (PUCMM).