COLLIOT Olivier

Olivier Colliot is Research Director at CNRS and the co-head of the ARAMIS Lab, a joint team between CNRS, Inria, Inserm and Sorbonne University at the Paris Brain Institute. ARAMIS gathers about 35 people dedicated to AI and data science for brain disorders. Olivier Colliot’s research field is machine learning for healthcare, in particular medical imaging. His current topics of interests include benchmarking and validation of medical AI methods and machine learning from multimodal medical data. He is on the board of leading medical imaging AI journals: a Senior Area Editor of IEEE Transactions on Medical Imaging, an Associate Editor of Medical Image Analysis and an Associate Editor of the SPIE Journal of Medical Imaging. He is a member of the board of the special interest group for biomedical challenges of the MICCAI Society. He was Conference Chair at SPIE Medical Imaging from 2022 to 2025. He was a Program Committee member at MICCAI 2024 and received the Oustanding Area Chair Award. He co-created, with other colleagues from AI clusters, the French Congress on AI for Biomedical Imaging (IABM), in 2023, which has been a growing success ever since and recently led to the creation of a learned society. He has edited a reference book on Machine Learning for Brain Disorders (Springer, 2023).

Informations

Institutions: CNRS – Paris Brain Institute

Thematics: Machine learning for healthcare

Topic of interest: Machine learning, benchmarking, validation, multimodal medical data, medical imaging

olivier.colliot@cnrs.fr

Personal website

Project in Prairie

His research is dedicated to the creation and validation of reliable, trustworthy and patient-benefiting medical AI systems. The main research threads are: i) the design novel approaches for integrating multimodal medical data, ii) foundational principles of validation of medical AI systems, iii) benchmarking in the context of medical AI. The main applications concern the improvement of brain health, in particular diagnosis, prognosis, disease understanding and biomarker discovery.

Brain imaging is a domain in which AI hold major promises. However, current systems are not interpretable and too narrow. These are major barriers to their adoption by clinicians. I firmly believe that fundamental research advances are needed to make systems more interpretable and generic. I hope that these ultimately lead to better diagnosis and care of patients. I am really excited to conduct this project within PRAIRIE, which will open new fruitful collaborations with academic and industrial partners. I also believe we have a major role to play in training in AI the next generation of engineers but also clinicians, that our country needs.