Fast MR signal simulations of microvascular and diffusion contributions using histogram‐based approximation and recurrent neural networks
Magnetic Resonance in Medicine · 2025
DOI: 10.1002/mrm.30629 ↗Kurz gefasst
Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, 2025. Verfasst von Thomas Coudert und 9 weiteren Autor:innen. Beteiligte Einrichtung: Université Grenoble Alpes, INSERM, U1216, Grenoble Institute Neurosciences, GIN, Grenoble, France. Hauptthemen laut MEDLINE: Microvessels, Magnetic Resonance Imaging, Brain, Image Processing, Computer-Assisted. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Agence Nationale de la Recherche.
Abstract (Originalsprache)
Purpose
Accurate MR signal simulation, including microvascular structures and water diffusion, is crucial for MRI techniques like fMRI BOLD modeling and MR vascular Fingerprinting (MRF), which use susceptibility effects on MR signals for tissue characterization. However, integrating microvascular features and diffusion remains computationally challenging, limiting the accuracy of the estimates. Using advanced modeling and deep neural networks, we propose a novel simulation tool that efficiently accounts for susceptibility and diffusion effects.
Methods
We used dimension reduction of magnetic field inhomogeneity matrices combined with deep learning methodology to accelerate the simulations while maintaining their accuracy. We validated our results through an in silico study against a reference method and in vivo MRF experiments.
Results
This approach accelerates MR signal generation by a factor of almost 13 000 compared to previously used simulation methods while preserving accuracy.
Conclusion
The MR‐WAVES method allows fast generation of MR signals accounting for microvascular structures and water‐diffusion contribution.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Université Grenoble Alpes, INSERM, U1216, Grenoble Institute Neurosciences, GIN, Grenoble, France.
- Université Grenoble Alpes, INSERM, US17, CNRS, UAR3552, CHU Grenoble Alpes, IRMaGe, Grenoble, France.
- Stroke Unit, Department of Neurology, Université Grenoble Alpes, CHU Grenoble Alpes, Grenoble, France.
ORCID-Profile: Thomas Coudert
Förderung
- Agence Nationale de la Recherche
Zitieren
APA
Coudert, T., Silva Martins Marçal, M., Delphin, A., Barrier, A., Cunge, L., Legris, L., Warnking, J. M., Lemasson, B., Barbier, E. L., & Christen, T. (2025). Fast MR signal simulations of microvascular and diffusion contributions using histogram‐based approximation and recurrent neural networks. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.30629
Vancouver
Coudert T, Silva Martins Marçal M, Delphin A, Barrier A, Cunge L, Legris L, et al. Fast MR signal simulations of microvascular and diffusion contributions using histogram‐based approximation and recurrent neural networks. Magnetic Resonance in Medicine. 2025. doi:10.1002/mrm.30629
BibTeX
@article{Coudert2025,
author = {Coudert, Thomas and Silva Martins Marçal, Maitê and Delphin, Aurélien and Barrier, Antoine and Cunge, Lila and Legris, Loïc and Warnking, Jan M and Lemasson, Benjamin and Barbier, Emmanuel L and Christen, Thomas},
title = {Fast MR signal simulations of microvascular and diffusion contributions using histogram‐based approximation and recurrent neural networks},
journal = {Magnetic Resonance in Medicine},
year = {2025},
doi = {10.1002/mrm.30629}
}
EUVIMED