Artificial intelligence for the evaluation of profiles, trajectories and management of vulnerability in health: COVID-19, frailty of the elderly and cancer
APPRIMAGE
Large-scale validation of a machine learning method for diagnostic support from brain MRI data
Underway
01/11/2018
Main objectives
The ARAMIS team is developing machine learning algorithms to help diagnose neurological diseases from brain magnetic resonance imaging data.
The present study aims to:
i) evaluate these algorithms on a very large scale on routine clinical data;
ii) evaluate the influence of the training sample size on the performance of the algorithms;
iii) compare different machine learning approaches.
The present study aims to:
i) evaluate these algorithms on a very large scale on routine clinical data;
ii) evaluate the influence of the training sample size on the performance of the algorithms;
iii) compare different machine learning approaches.

Acquisition d'images cérébrales (IRM) - © Inria / Photo C. Morel
Publications
Contacts
Olivier Colliot () & Ninon Burgos () & Didier Dormont ()
Members
Equipe-projet ARAMIS, Inria, CNRS, Inserm, Sorbonne Université, Institut du Cerveau
Service de neuroradiologie diagnostique et fonctionnelle, DMU DIAMENT, Hôpital de la Pitié-Salpêtrière, AP-HP.
Service de neurologie, IM2A, DMU Neurosciences, Hôpital de la Pitié-Salpêtrière, AP-HP.
Other projects
Description
Learning a deep representation of patient records for event prediction and patient segmentation
Names of partners involved
AP-HP, Inria