EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Fast MR signal simulations of microvascular and diffusion contributions using histogram‐based approximation and recurrent neural networks

Thomas Coudert iD, Maitê Silva Martins Marçal, Aurélien Delphin, Antoine Barrier, Lila Cunge, Loïc Legris, Jan M Warnking, Benjamin Lemasson, Emmanuel L Barbier, Thomas Christen

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.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

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)

MicrovesselsMagnetic Resonance ImagingBrainImage Processing, Computer-AssistedNeural Networks, ComputerHumansComputer SimulationAlgorithmsDeep LearningDiffusionDiffusion Magnetic Resonance ImagingRecurrent Neural Networks

Stichwörter der Autor:innen

BOLDRNNcerebral blood volume (CBV)magnetic resonance fingerprinting (MRF)numerical simulationsvascularization

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}
}
Kostenlos starten →