EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

q3-MuPa: Quick, quiet, quantitative multi-parametric MRI using physics-informed diffusion models

Shishuai Wang, Florian Wiesinger, Noemi Sgambelluri, Carolin Pirkl, Stefan Klein, Juan A Hernandez-Tamames, Dirk H J Poot

Magnetic Resonance Imaging · 2026-09 · 131 · 110699

DOI: 10.1016/j.mri.2026.110699 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance Imaging, 2026-09. Verfasst von Shishuai Wang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Erasmus University Medical Center, Dr. Molewaterplein 40, Rotterdam, 3015 GD, The Netherlands. Electronic address: s.wang@erasmusmc.nl. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Brain, Magnetic Resonance Imaging, Diffusion Magnetic Resonance Imaging. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: GE Healthcare, Dutch Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

MuPa-ZTE is a novel multi-parametric quantitative MRI protocol that enables fast and nearly silent scanning. However, accelerating multi-parametric acquisitions to meet clinical time constraints makes the reconstruction of accurate and clean qMRI maps increasingly challenging, particularly under severe undersampling and noise. In this work, we propose a physics-informed diffusion model for MuPa-ZTE qMRI mapping. A denoising diffusion probabilistic model is trained to map MuPa-ZTE weighted image series to T1, T2, and proton density maps, while the MuPa-ZTE forward model is incorporated as an explicit data consistency constraint during inference. The proposed method is trained entirely on synthetic data and evaluated on both synthetic data and real data under the nominal (∼4min) and fourfold-accelerated (∼1min) MuPa-ZTE acquisitions. Compared with dictionary matching and a purely data-driven diffusion model, the proposed approach yields accurate and less noisy 3D qMRI maps with improved structural fidelity. The integration of MuPa-ZTE acquisition with a physics-informed diffusion model, termed q3-MuPa, provides an acquisition-consistent framework for quick, quiet, and quantitative multi-parametric MRI.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedBrainMagnetic Resonance ImagingDiffusion Magnetic Resonance ImagingAlgorithmsHumansModels, StatisticalPhantoms, ImagingSignal-To-Noise RatioComputer SimulationImaging, Three-DimensionalDiffusion

Stichwörter der Autor:innen

Deep generative modelsDiffusion modelsMulti-parametric mappingQuantitative MRI

Autor:innen und Institutionen

  • Erasmus University Medical Center, Dr. Molewaterplein 40, Rotterdam, 3015 GD, The Netherlands. Electronic address: s.wang@erasmusmc.nl.
  • GE HealthCare, Oskar-Schlemmer-Straße 11, Munich, 80807, Germany.
  • Erasmus University Medical Center, Dr. Molewaterplein 40, Rotterdam, 3015 GD, The Netherlands.

Förderung

  • GE Healthcare
  • Dutch Research Council

Zitieren

APA

Wang, S., Wiesinger, F., Sgambelluri, N., Pirkl, C., Klein, S., Hernandez-Tamames, J. A., & Poot, D. H. J. (2026). q3-MuPa: Quick, quiet, quantitative multi-parametric MRI using physics-informed diffusion models. Magnetic Resonance Imaging, 131, 110699. https://doi.org/10.1016/j.mri.2026.110699

Vancouver

Wang S, Wiesinger F, Sgambelluri N, Pirkl C, Klein S, Hernandez-Tamames JA, et al. q3-MuPa: Quick, quiet, quantitative multi-parametric MRI using physics-informed diffusion models. Magnetic Resonance Imaging. 2026;131:110699. doi:10.1016/j.mri.2026.110699

BibTeX
@article{Wang2026,
  author = {Wang, Shishuai and Wiesinger, Florian and Sgambelluri, Noemi and Pirkl, Carolin and Klein, Stefan and Hernandez-Tamames, Juan A and Poot, Dirk H J},
  title = {q3-MuPa: Quick, quiet, quantitative multi-parametric MRI using physics-informed diffusion models},
  journal = {Magnetic Resonance Imaging},
  year = {2026},
  volume = {131},
  pages = {110699},
  doi = {10.1016/j.mri.2026.110699}
}
Kostenlos starten →