MOSAIC (University Hospital Federation)

(Multiscale Optimised Strategy for Artificial intelligence-based Imaging biomarkers in digestive Cancer)



Collaboration type

Research structure

Main objectives

MOSAIC aims to identify prognostic and theranostic biomarkers of digestive tumors through the development of a multi-parametric multi-scale imaging approach, combining radiology (macroscopy), pathology (microscopy and molecular) and nuclear medicine (functional): IMAGOMICS. Using Artificial Intelligence (AI) methods, this project mixes the multiple facets of tumor imaging to improve tumor characterization and disease monitoring. In particular, it will allow us to highlight correlations between histology, imaging markers and tumor aggressiveness/response to therapy that remain hidden until now. Thus, we will propose non-invasive diagnostic, prognostic and theranostic modalities through virtual biopsy.

The project will focus on two types of digestive tumors: hepatocellular carcinomas (HCC) and neuroendocrine tumors (NET).


Valérie Paradis () & Kevin Mondet ()


AP-HP, Inserm, Université Paris Cité

Useful links

Other projects



US Caractérisation et prédiction de la survenue de formes graves ou létales du COVID-19 à partir des données issues de l’EDS de l’AP-HP

Names of partners involved
AP-HP, Inria & Centrale Supélec

read more