Notice: Function _load_textdomain_just_in_time was called incorrectly. Translation loading for the email-encoder-bundle domain was triggered too early. This is usually an indicator for some code in the plugin or theme running too early. Translations should be loaded at the init action or later. Please see Debugging in WordPress for more information. (This message was added in version 6.7.0.) in /home/mfstmbd/www/wp-includes/functions.php on line 6114

Notice: Function _load_textdomain_just_in_time was called incorrectly. Translation loading for the participants-database domain was triggered too early. This is usually an indicator for some code in the plugin or theme running too early. Translations should be loaded at the init action or later. Please see Debugging in WordPress for more information. (This message was added in version 6.7.0.) in /home/mfstmbd/www/wp-includes/functions.php on line 6114

Notice: Function _load_textdomain_just_in_time was called incorrectly. Translation loading for the ultimate-member domain was triggered too early. This is usually an indicator for some code in the plugin or theme running too early. Translations should be loaded at the init action or later. Please see Debugging in WordPress for more information. (This message was added in version 6.7.0.) in /home/mfstmbd/www/wp-includes/functions.php on line 6114

Notice: Function _load_textdomain_just_in_time was called incorrectly. Translation loading for the updraftplus domain was triggered too early. This is usually an indicator for some code in the plugin or theme running too early. Translations should be loaded at the init action or later. Please see Debugging in WordPress for more information. (This message was added in version 6.7.0.) in /home/mfstmbd/www/wp-includes/functions.php on line 6114
Matricis.ai | Laboratoire Bernoulli

Matricis.ai

Détection des lésions d’endométriose à partir d’images d’IRM

En cours d'exécution

01/09/2022

30/09/2023

Objectifs principaux

Développer un logiciel d’IA permettant de détecter et de caractériser une endométriose sur une IRM pelvienne

Problème identifié

L’endométriose est une maladie encore mal connue et mal diagnostiquée. L’errance médicale est en moyenne de 7 ans après l’apparition des premiers symptômes et 75% des patientes reçoivent au moins un diagnostic erroné. Les erreurs de diagnostic sont en partie imputables à la difficulté de l’analyse des images d’IRM pelviennes et au manque de radiologues spécialisés, qui représentent moins d’1% des radiologues en France et sont mal répartis sur le territoire.

Méthode/Technologie utilisée

Le projet emploie un ensemble de technologies de machine learning pour reconnaitre et modéliser les organes du pelvis féminin et classifier les différents types de lésions d’endométriose, en fonction de leur localisation.

Publications

Contacts

Elise Mekkaoui () & Raphaelle Taub ()

Membres

AP-HP, Inria

Liens utiles

https://matricis.ai/