EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Quantifying physiological variability and improving reproducibility in 4D ‐flow MRI cerebrovascular measurements with self‐supervised deep learning

Brock W Jolicoeur iD, Zaynab S Yardim, Grant S Roberts iD, Leonardo A Rivera-Rivera, Laura B Eisenmenger, Kevin M Johnson iD

Magnetic Resonance in Medicine · 2025

DOI: 10.1002/mrm.30634 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, 2025. Verfasst von Brock W Jolicoeur und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, University of Wisconsin, Madison, Wisconsin, USA. Hauptthemen laut MEDLINE: Deep Learning, Cerebrovascular Circulation, Magnetic Resonance Imaging, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NIH HHS, NIA NIH HHS, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To assess the efficacy of self‐supervised deep learning (DL) denoising in reducing measurement variability in 4D‐Flow MRI, and to clarify the contributions of physiological variation to cerebrovascular hemodynamics.

Methods

A self‐supervised DL denoising framework was trained on 3D radially sampled 4D‐Flow MRI data. The model was evaluated in a prospective test–retest imaging study in which 10 participants underwent multiple 4D‐Flow MRI scans. This included back‐to‐back scans and a single scan interleaved acquisition designed to isolate noise from physiological variations. The effectiveness of DL denoising was assessed by comparing pixelwise velocity and hemodynamic metrics before and after denoising.

Results

DL denoising significantly enhanced the reproducibility of 4D‐Flow MRI measurements, reducing the 95% confidence interval of cardiac‐resolved velocity from 215 to 142 mm/s in back‐to‐back scans and from 158 to 96 mm/s in interleaved scans, after adjusting for physiological variation. In derived parameters, DL denoising did not significantly improve integrated measures, such as flow rates, but did significantly improve noise sensitive measures, such as pulsatility index. Physiologic variation in back‐to‐back time‐resolved scans contributed 26.37% ± 0.08% and 32.42% ± 0.05% of standard error before and after DL.

Conclusion

Self‐supervised DL denoising enhances the quantitative repeatability of 4D‐Flow MRI by reducing technical noise; however, variations from physiology and post‐processing are not removed. These findings underscore the importance of accounting for both technical and physiological variability in neurovascular flow imaging, particularly for studies aiming to establish biomarkers for neurodegenerative diseases with vascular contributions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningCerebrovascular CirculationMagnetic Resonance ImagingImage Processing, Computer-AssistedHumansReproducibility of ResultsMaleFemaleAdultProspective StudiesSignal-To-Noise RatioImaging, Three-DimensionalBrainBlood Flow VelocityAlgorithmsMiddle AgedHemodynamics

Stichwörter der Autor:innen

4D‐flow MRIdeep learningdenoisingneurodegenerative diseasesphysiological variation

Autor:innen und Institutionen

  • Department of Biomedical Engineering, University of Wisconsin, Madison, Wisconsin, USA.
  • Department of Radiology, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, USA.
  • Department of Physics, University of Wisconsin, Madison, Wisconsin, USA.
  • Department of Medical Physics, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, USA.
  • Department of Medicine, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, USA.

ORCID-Profile: Brock W Jolicoeur, Grant S Roberts, Kevin M Johnson

Förderung

  • NIH HHS
  • NIA NIH HHS
  • National Institutes of Health

Zitieren

APA

Jolicoeur, B. W., Yardim, Z. S., Roberts, G. S., Rivera-Rivera, L. A., Eisenmenger, L. B., & Johnson, K. M. (2025). Quantifying physiological variability and improving reproducibility in 4D ‐flow MRI cerebrovascular measurements with self‐supervised deep learning. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.30634

Vancouver

Jolicoeur BW, Yardim ZS, Roberts GS, Rivera-Rivera LA, Eisenmenger LB, Johnson KM. Quantifying physiological variability and improving reproducibility in 4D ‐flow MRI cerebrovascular measurements with self‐supervised deep learning. Magnetic Resonance in Medicine. 2025. doi:10.1002/mrm.30634

BibTeX
@article{Jolicoeur2025,
  author = {Jolicoeur, Brock W and Yardim, Zaynab S and Roberts, Grant S and Rivera-Rivera, Leonardo A and Eisenmenger, Laura B and Johnson, Kevin M},
  title = {Quantifying physiological variability and improving reproducibility in 4D ‐flow MRI cerebrovascular measurements with self‐supervised deep learning},
  journal = {Magnetic Resonance in Medicine},
  year = {2025},
  doi = {10.1002/mrm.30634}
}
Kostenlos starten →