THOMAS COUDERT
Doctorant(e) (INSERM)
- Imprimer
- Partager
- Partager sur Facebook
- Share on X
- Partager sur LinkedIn
Eq B.Lemasson/T.Christen
![Profile picture for user couderth](/sites/default/files/styles/photo_user/public/pictures/2024-06/unnamed.jpg?itok=srIY-cu3)
Coordonnées
Bâtiment : Grenoble Institut des Neurosciences
Bureau : GIN
Thomas.Coudert1@univ-grenoble-alpes.fr
Réseaux sociaux :
Thèmes de recherche
The concept of MRI fingerprint (MRF) proposes to reconstruct images by directly comparing in vivo acquisitions and billions of in silico simulations that mimic brain tissue (dictionary). This approach is flexible enough to simultaneously allow access to several MRI parameters and quantify them. As we have shown in clinical and preclinical studies, when the simulations are based on the physics of NMR (magnetic field, magnetic susceptibility, diffusion, relaxations, etc.) and biophysics (cellular dimensions and vascular, flow ...), the technique allows for extraction of information on tissue microstructures. These data are particularly important for the management of patients with acute stroke. Until now, the digital representation of tissues has been based on simple shapes (cells = spheres, blood vessels = cylinders). In addition, the choice of the 4D sequence is currently based on rough nuclear magnetization trajectories and the comparison step is extremely time-consuming. During my thesis, I propose to develop realistic biophysical simulations coupled with new sensitive designed MR sequences and artificial intelligence tools integrated at different levels of the MRF frame to optimize the MRF protocol. We will thus create a tool that can be integrated into a clinical environment and capable of guiding patients more quickly to the appropriate treatments.
Disciplines scientifiques
MRI - MR Fingerprinting - MR Sequence Design - Image Analysis - Neurosciences - Deep Learning - Machine Learning - MR Reconstruction
Enseignement
- 2024 - 3 months Internship supervision Master 1 Student in Biomedical Engineering - Project: Automated optimization of MR vascular Fingerprinting bSSFP sequences.
- 2022 - Course: Introduction to Python - Grenoble National Polytechnic Institute - Preparatory class.
- 2022 - Practical class supervision: Introduction to PCR method - Grenoble National Polytechnic Institute - Preparatory class.
- 2022 - Practical session animation - Synthetic MRI Contrast Generation - AI4Health Winter School - January 14th 2022
Curriculum vitae
- 2021-now PhD in Physic for Life Sciences, Grenoble Institute Neurosciences (GIN)
- 2018-2021 Master in Engineering at Grenoble-INP Phelma school
- 2016-2018 Preparatory Classe at La Prépa Des INP Grenoble
Publications
Journals
- Thomas Coudert, Aurélien Delphin, Loïc Legris, Antoine Barrier, Jan M. Warnking, Emmanuel L. Barbier, Thomas Christen (2024). MR Fingerprinting bSSFP for the contrast-free quantification of Blood Volume, Microvascular Properties, and Relaxometry parameters. In-preparation
- Aurélien Delphin, Fabien Boux, Clément Brossard, Thomas Coudert, Jan M Warnking, Benjamin Lemasson, Emmanuel Luc Barbier, Thomas Christen (2024). Enhancing MR vascular Fingerprinting through realistic microvascular geometries. arXiv preprint arXiv:2305.17092, Imaging Neuroscience. Under review
Conference papers
- Thomas Coudert, Aurélien Delphin, Loïc Legris, Antoine Barrier, Jan M. Warnking, David Chechin, Laurent Lamalle, Peter Mazurkewitz, Peter Koken, Emmanuel L. Barbier, Mariya Doneva, Thomas Christen (2024). Contrast-free Blood Volume, Microvascular Properties, and Relaxometry mapping using bSSFP MR Fingerprinting. ISMRM Singapore (Power Pitch Oral)
- Thomas Coudert*, Antoine Barrier*, Aurélien Delphin, Benjamin Lemasson, Thomas Christen (2024). MARVEL: MR Fingerprinting with Additional micRoVascular Estimates using bidirectional LSTMs. MICCAI 2024 (under review)
- Geoffroy Oudoumanessah, Thomas Coudert, Luc Meyer, Aurélien Delphin, Thomas Christen, Carole Lartizien, Michel Dojat, Florence Forbes (2024). Cluster globally, Reduce locally: Scalable cluster-specific dimension reduction for medical imaging. MICCAI 2024 (under review)
- Liliane Daniela Talba Malla Tchamedeu, Benjamin Lambert, Thomas Coudert, Elizabeth Moyal Cohen-Jonathan, Soléakhéna Ken, Géraldine Le Duc, Michel Dojat, Fabien Boux, Benjamin Lemasson (2024). Segmentation d'IRM multimodales par réseaux de neurones : Stratégies de transfert d'apprentissage pour des ensembles de données de taille limitée. IABM24 Grenoble (Poster)
- Antoine Barrier, Thomas Coudert, Aurélien Delphin, Loïc Legris, Jan Warnking, Emmanuel Barbier, Thomas Christen (2024). Reconstructions de cartes multi-paramétriques haute dimension accélérées via LSTM bidirectionnel et IRM Fingerprint. IABM24 Grenoble (Poster)
- Aurélien Delphin, Thomas Coudert, Audrey Fan, Michael E Moseley, Greg Zaharchuk, Thomas Christen (2023). MR Vascular Fingerprinting with 3D realistic blood vessel structures and machine learning to assess oxygenation changes in human volunteers. ISMRM, Toronto (Poster).
- Thomas Coudert, Aurélien Delphin, Jan M.Warnking, Emmanuel L.Barbier, Thomas Christen (2023). Utilisation de séquences de type MR Fingerprint bSSFP pour les mesures T2* et la quantification de l’effet BOLD. SFRMBM Paris (Poster)
- Thomas Coudert, Aurélien Delphin, Jan M.Warnking, Emmanuel L.Barbier, Thomas Christen (2023). Réseaux de neurones profonds pour la simulation de signaux IRM pour l’IRM Fingerprint vasculaire. IABM23 Paris (Poster)
- Thomas Coudert, Aurelien Delphin, Jan Warnking, Benjamin Lemasson, Emmanuel L Barbier, Thomas Christen (2022). Searching for an MR Fingerprinting sequence to measure brain oxygenation without contrast agent. ISMRM, London (Poster)
- Thomas Coudert, Sophie Ancelet, Nadya Pyatigorskaya, Lucia Nichelli, Damien Ricard, Dimitri Psimaras, Marie Odile Bernier, Michel Dojat, Florence Forbes, Alan Tucholka (2021). Contribution of Transfer Learning for automatic segmentation of radiation-induced brain lesions in glioblastoma patients from a limited number of annotated MRIs. GDR Statistique&Santé (Oral)
Computer skills
- Programming: Python (Tensorflow, PyTorch), Matlab, C, SQL
- Software: Microsoft Office; Version management: GitHub, GitLab; Imaging: ImageJ, ITKSnap; OS: Linux, Ubuntu, Windows
Languages
- French (native)
- English (level C1 BULATS)
- German (level B2)
- Italian (level B1)
Side activities
- Junior organizing committee for IABM 2024, the first French conference to bring together national players in Artificial Intelligence for biomedical and medical imaging
- Active member of the “PhD students representatives” of the Grenoble Institut Neurosciences https://neurosciences.univ-grenoble-alpes.fr/fr/linstitut/vie-linstitut/neurodocs-doctorants-gin: Animation group created by Grenoble Neuroscience Institute doctoral students.
- Participation in the French-language science popularization competition "Ma thèse en 180 secondes" (My thesis in 180 seconds), during which I have to present my thesis work in less than 3 minutes to a jury and an audience, in a popular and didactic way. https://youtu.be/8e2OX-1v9OA?si=cnw0B8r2t2z9PBnW
![mybrain](/sites/default/files/2024-06/mybrain_zoom.png)
- Imprimer
- Partager
- Partager sur Facebook
- Share on X
- Partager sur LinkedIn