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

Machine learning‐based multi‐pool Voigt fitting of CEST , rNOE , and MTC in Z‐spectra

Sajad Mohammed Ali iD, Peter C M van Zijl, Jannik Prasuhn, Ronnie Wirestam, Linda Knutsson iD, Nirbhay N Yadav

Magnetic Resonance in Medicine · 2025

DOI: 10.1002/mrm.30460 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, 2025. Verfasst von Sajad Mohammed Ali und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Radiation Physics, Lund University, Lund, Sweden. Hauptthemen laut MEDLINE: Machine Learning, Magnetic Resonance Imaging, Brain, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NIBIB NIH HHS, NIH HHS, Cancerfonden.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Four‐pool Voigt (FPV) machine learning (ML)–based fitting for Z‐spectra was developed to reduce fitting times for clinical feasibility in terms of on‐scanner analysis and to promote larger cohort studies. The approach was compared to four‐pool Lorentzian (FPL)‐ML–based modeling to empirically verify the advantage of Voigt models for Z‐spectra.

Methods

Voigt and Lorentzian models were fitted to human 3 T Z‐spectral data using least squares (LS) to generate training data for the corresponding ML versions. Gradient boosting decision trees were trained, resulting in one Voigt and one Lorentzian ML model. Modeling accuracy was tested, and the fitting times of the ML models and LS versions were evaluated. The goodness of fits of Voigt and Lorentzian ML models were compared.

Results

The training time for each ML model (Voigt and Lorentzian) was less than 1 min, and the modeling accuracy compared to the corresponding LS versions was excellent, as indicated by a nonsignificant difference between the parameters obtained by LS and corresponding ML versions. The average fitting time was 20 μs/spectrum for both ML models compared to 0.27 and 0.82 s/spectrum for LS with FPL and FPV, respectively. The goodness of fits of FPV‐ML and FPL‐ML differed significantly ( p < 0.005), with FPV‐ML showing an improvement for all tested data.

Conclusion

Gradient boosting decision trees fitting of multi‐pool Z‐spectra significantly reduces fitting times compared to traditional LS approaches, allowing fast data processing while upholding fitting quality. Along with the short training times, this makes the method suitable for clinical settings and for large cohort research applications. The FPV‐ML approach provides a significant improvement of goodness of fit compared to FPL‐ML.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningMagnetic Resonance ImagingBrainImage Processing, Computer-AssistedHumansAlgorithmsPhantoms, ImagingLeast-Squares AnalysisReproducibility of Results

Stichwörter der Autor:innen

CESTLorentzian fittingMTCVoigt fittingmachine learningrNOE

Autor:innen und Institutionen

  • Department of Medical Radiation Physics, Lund University, Lund, Sweden.
  • Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.
  • F.M. Kirby Research Center for Functional Brain Imaging, Kennedy Krieger Institute, Baltimore, Maryland, USA.
  • Department of Neurology, University Medical Center Schleswig-Holstein, Germany.
  • Institute of Neurogenetics, University of Lübeck, Germany.
  • Center for Brain, Behavior and Metabolism, University of Lübeck, Germany.

ORCID-Profile: Sajad Mohammed Ali, Linda Knutsson

Förderung

  • NIBIB NIH HHS
  • NIH HHS
  • Cancerfonden
  • Swedish Research Council
  • NICHD NIH HHS
  • NINDS NIH HHS
  • National Institutes of Health
  • Vetenskapsrådet

Zitieren

APA

Mohammed Ali, S., van Zijl, P. C. M., Prasuhn, J., Wirestam, R., Knutsson, L., & Yadav, N. N. (2025). Machine learning‐based multi‐pool Voigt fitting of CEST , rNOE , and MTC in Z‐spectra. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.30460

Vancouver

Mohammed Ali S, van Zijl PCM, Prasuhn J, Wirestam R, Knutsson L, Yadav NN. Machine learning‐based multi‐pool Voigt fitting of CEST , rNOE , and MTC in Z‐spectra. Magnetic Resonance in Medicine. 2025. doi:10.1002/mrm.30460

BibTeX
@article{MohammedAli2025,
  author = {Mohammed Ali, Sajad and van Zijl, Peter C M and Prasuhn, Jannik and Wirestam, Ronnie and Knutsson, Linda and Yadav, Nirbhay N},
  title = {Machine learning‐based multi‐pool Voigt fitting of CEST , rNOE , and MTC in Z‐spectra},
  journal = {Magnetic Resonance in Medicine},
  year = {2025},
  doi = {10.1002/mrm.30460}
}
Kostenlos starten →