CHAIMELEON: 4 datalakes for 4 cancers

CHAIMELEON aims to set up a structured repository for health imaging data to be openly reused in AI experimentation for cancer management, with the creation of four datalakes for four cancers: lung, breast, colorectal, prostate.

Medexprim Global Technical Coordinator

As a contributor to the winning consortium, our unique expertise —combining scientific sensitivity, maturity on technical platforms, a legal and regulatory knowledge and a collaborative spirit— allows us to cover legal, interoperability, platform architecture and internal consulting for data integration.









0 year


Project stages

Clinical partners and external collaborators will populate the repository with multimodality imaging and related clinical data for historic and newly diagnosed cancer patients.

AI-powered pipelines will automate data de-identification, curation, annotation, integrity securing and image harmonization, enabling reproducibility of Radiomics with large image datasets.

Analytical data engine will interpret, extract and exploit the right information stored at the Repository.

Early in-silico validation of selected AI tools will be conducted in observational clinical studies coordinated by leading experts: San Donato (breast), Sapienza (colorectal), La Fe (prostate).

I am very proud and excited to take part to this ambitious EU project. It follows the Primage project in which we were already involved. It’s a big challenge, but it’s 100% in line with Medexprim’s core mission and expertise.

Karine Seymour, Technical Leader