Artificial intelligence for the evaluation of profiles, trajectories and management of vulnerability in health: COVID-19, frailty of the elderly and cancer
EVALHEP
EValuation of Hepatic Lesion Removal by ElectroPoration
Underway
01/11/2022
-
30/11/2023
Main objectives
Irreversible electroporation is a curative treatment for cancerous lesions of the liver, performed when tumors are too deep and poorly located to be resected or destroyed by other means.
The EVALHEP project aims to develop criteria for evaluating the effectiveness of the treatment based on imaging, mathematical models and numerical simulations to assist the radiologist performing these complex procedures.
The EVALHEP project aims to develop criteria for evaluating the effectiveness of the treatment based on imaging, mathematical models and numerical simulations to assist the radiologist performing these complex procedures.

Challenge
Although it has shown promising efficacy, irreversible electroporation (IRE) remains underutilized because it is considered a complex procedure subject to many variability factors.
There is no real-time evaluation of the efficacy of the procedure and inaccuracies in needle positioning or treatment parameters will generate changes in the distribution of the electric field that may affect treatment efficacy.
Moreover, it remains difficult to evaluate the effectiveness of the treatment on post-therapeutic images whose interpretation is subject to controversy.
Methodology/Technology used
Mathematical modeling; Numerical simulations of the electric field from 3D imagery; Estimation of motion and non-rigid inter-modality registration; Biomarkers in imaging (radiomics)
Publications
Contacts
Clair Poignard (Equipe MONC – Inria Bordeaux) () & Olivier Sutter (Unité de Radiologie Interventionnelle, hôpital Avicenne, Hôpitaux Universitaires Paris-Seine-Saint-Denis) ()
Members
AP-HP, Inria
Useful links
https://www.bernoulli-lab.fr/project/nepa-2/
Other projects
Description
Learning a deep representation of patient records for event prediction and patient segmentation
Names of partners involved
AP-HP, Inria