Workshop #3: Big data and artificial intelligence in cancer imaging

Organisers: Prof. Karim Lekadir, Universitat de Barcelona, Spain; Prof. Luis Martí-Bonmatí, La Fe University, Spain; Prof. Manolis Tsiknakis, FORTH, Greece; Mrs. Gianna Tsakou, Athens R&D Lab of Maggioli S.P.A., Italy

Short Description: Artificial Intelligence (AI) offers substantial opportunities for healthcare, supporting better diagnosis, treatment, prevention and personalised care. Analysis of health images is one of the most promising fields for applying AI in healthcare, contributing to better prediction, diagnosis and treatment of cancer. In order to develop and test reliable AI applications in the field, access to large-volume of high- quality data is needed.

The organizers of the workshop are the coordinators of the four projects that have recently been funded by the EC in the context of a relevant H2020 call (H2020-SC1-FA-DTS-2019-1 – AI for Health Imaging) CHAIMELEON (https://chaimeleon.eu/), EuCanImage (https://eucanimage.eu/), INCISIVE (https://incisive-project.eu/), ProCancer-I (https://www.procancer-i.eu/) and the PRIMAGE (https://www.primageproject.eu/) a relevant R&D project funded in a previous H2020 call.

The projects are seeking to establish large interoperable repositories of health images, enabling the development, testing and validation of AI–based health imaging solutions to improve diagnosis, disease prediction and follow-up of the most common forms of cancer. The ongoing collaboration and information exchange among the projects so far has highlighted several areas where common approaches and consensus building should be seeked by the five projects and even beyond by the wider scientific community, in order to achieve interoperability. Similarly, it has led to the identification of significant technical and methodological challenges that need to be addressed in designing and exploiting such interoperable cancer imaging data spaces.

The workshop will provide a detailed report of the collaboration opportunities and challenges identified so far; it will also present current approaches towards consensus building and critically discuss alternatives.  Particular emphasis will be given to the issues related to the evaluation of AI-based diagnostic imaging algorithms including robustness, trust and explainability.