AI for Health Imaging in cancer research

Artificial Intelligence (AI) can substantially contribute to a better diagnosis, treatment, prevention of ailments. In order to develop and test reliable AI applications in the field, access to large-volume of high- quality data is needed. To securely transfer and share health images across the border, a large interoperable repository of health images should be created which include high quality, interoperable, (pseudo) anonymised data sets of annotated cases.

Proposers should specify measures for validating AI-based solutions based upon scientific evidence establishing their safety, validity, reproducibility, usability, reliability and usefulness. AI-based solutions shall be able to report about potential failures, inaccuracies and errors that might happen or encountered. Accordingly, adequate performance metrics, monitoring and evaluation criteria and procedures should be put in place.

Data should comply with relevant ethics, security requirements and data protection legislation. Gender aspects should be considered appropriately.