Description
Date depot: 28 septembre 2023
Titre: Transformers for etiological diagnosis in multi-modal medical data
Directeur de thèse:
Nicolas THOME (ISIR (EDITE))
Domaine scientifique: Sciences et technologies de l'information et de la communication
Thématique CNRS : Intelligence artificielle
Resumé: This PhD is founded by the ORCHID ANR project (2023-2027). The main objective in ORCHID is to perform etiological diagnosis, i.e. to predict the origin of a given pathology, by combining multi-modal and heterogeneous input data.
We are interested in combining diverse sources of information, from raw echography image sequences, times series representing the evolution of cardiac features, and
patient data (e.g. age, gender, various medical histories).
The objective of this project is to develop rigorous and explainable cardiac disease prediction models
based on artificial intelligence (AI). The main challenge is to model complex interactions between high-
quality image-based measurements extracted from echocardiograms and relevant patient data to
automatically predict etiological diagnosis of cardiac diseases.
Doctorant.e: Stym-Popper Jérémie