Introducing FUTURE-AI: Best practices for trustworthy AI in medical imaging

Published on: February 16, 2022
Categories: News

ProCAncer -I Project is part of the five H2020 projects that share the same vision, principles and challenges. These projects are funded under the same Action Line: AI for Health Imaging (Call: H2020-SC1-FA-DTS-2019-1): CHAIMELEON (chaimeleon.eu), EuCanImage (eucanimage.eu), INCISIVE (incisive-project.eu) and PRIMAGE (primageproject.eu). We believe that AI in medical imaging will achieve its full potential only once it has gained the trust of clinicians, patients, and policymakers, so we have established the FUTURE – AI initiative.

Taking part in the FUTURE – AI initiative will help build the trust among all interested parties. What is FUTURE-AI? It is an international, multi-stakeholder initiative for defining and maintaining concrete guidelines that will facilitate the design, development, validation and deployment of trustworthy AI solutions in medical imaging based on six guiding principles: Fairness, Universality, Traceability, Usability, Robustness and Explainability.

The FUTURE-AI assessment checklist consists of concrete and actionable questions that will guide developers, evaluators and other stakeholders in delivering imaging AI tools that are trustworthy and optimised for real-world practice. Each element of the FUTURE-AI checklist is provided with examples to illustrate potential mitigation measures for minimising the risks of imaging AI algorithms based on the FUTURE-AI guiding principles. While not all questions of the FUTURE-AI checklist are applicable in every application and scenario, we encourage the AI teams to build on as many elements as possible to produce imaging AI algorithms with solid foundations towards their trustworthiness and adoption.

The initiative has the potential to provide long-term foundations for regulators to build on in the future. What does this mean? It means that organizations, regulators, individuals, governments and healthcare organizations will have a reliable source of tools that are trustworthy and optimised regarding health imaging AI tools, and alongside improve the healthcare for all people around the world

LEARN MORE

 

 

Highlights

AI in PCa imaging : The current status and future perspectives

AI in PCa imaging : The current status and future perspectives

Ιn recent years, magnetic resonance imaging (MRI) has transformed the prostate cancer (PCa) diagnostic pathway, based on the evidence of multiple high-level evidence studies (refs 4M, MRI first, and PROMIS). Taken together, the evidence indicates that prostate MRI...

Open Call To Include New Beneficiaries Into The EUCAIM Consortium

Open Call To Include New Beneficiaries Into The EUCAIM Consortium

The EUCAIM project is launching an open call for new beneficiaries to join the consortium. The objective of the EUCAIM open call is to: i) onboard new cancer image data holders, increasing the geographic dimensions, data modalities or cancer targets, and  ii) include...

Third Dissemination Event of the ProCAncer-I Project in Athens

Third Dissemination Event of the ProCAncer-I Project in Athens

ProCAncer-I will be organising the 3rd Dissemination Event at the 21st IEEE International Symposium on Biomedical Imaging, which will be held in Athens, Greece, May 27-30, 2024. ProCAncer-I will organise the Workshop “Integrating imaging Data and AI models for...

ProCAncer-I at the ECR 2024 in Vienna

ProCAncer-I at the ECR 2024 in Vienna

A great congress once more! Artificial Intelligence (AI) took the spotlight at the European Radiology Congress (ECR) held at the Austria Center Vienna from February 28 to March 3. Under the theme of 'Next Generation Radiology,' cutting-edge technologies were...

Stay in touch!