DePIcT

Deep-Learning Data Processing of spectral PC-CT longitudinal Studies to Design and Optimize combined Immuno-Anticancer Treatments in Liver Cancer Mouse Models



Résumé
The PIXSCAN-FLI prototype is a spectral micro PC-CT scanner developed at CPPM. Recently, a collaborative research between IBDM and CPPM illustrated its capability to perform unprecedented longitudinal studies to track spontaneous liver tumors in mouse models, highlighting dynamics features throughout the tumorigenic program. This project aims at exploiting deep learning for processing PIXSCAN-FLI spectral data and to explore the effectiveness of an immuno-therapy approach designed to remodel the tumor microenvironment while targeting cancer cells with drugs. First, we will develop strategies for acquisition and processing of spectral PC-CT data using different contrast agents for qualitative/quantitative evaluation and 3D reconstructions of tumors, their microenvironment their vascularization. Second, based on knowledge gathered through marker analyses, we will assess the effects of treatments combining agents acting on the immune checkpoint pathway with those targeting cancer cells.

Mots-clés
spectral Photon Counting CT, Deep Learning, immuno-anticancer treatment, hepatocellular carcinoma, in vivo longitudinal imaging

Partenaires du projet

IN2P3
BOURSIER Yannick
(UMR7346) Marseille France
INSB
MAINA Flavio
Institut de Biologie du Développement de Marseille (UMR7288) France
Yannick BOURSIER
Crédit photo : Yannick BOURSIER

Pour plus d’informations http://imxgam.in2p3.fr/depict.php