EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Motion‐robust T2∗$$ {\mathrm{T}}_2^{\ast } $$ quantification from low‐resolution gradient echo brain MRI with physics‐informed deep learning

Hannah Eichhorn iD, Veronika Spieker iD, Kerstin Hammernik iD, Elisa Saks iD, Lina Felsner iD, Kilian Weiss iD, Christine Preibisch iD, Julia A Schnabel iD

Magnetic Resonance in Medicine · 2026

DOI: 10.1002/mrm.70050 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, 2026. Verfasst von Hannah Eichhorn und 7 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Machine Learning in Biomedical Imaging, Helmholtz Munich, Neuherberg, Germany. Hauptthemen laut MEDLINE: Brain, Deep Learning, Magnetic Resonance Imaging, Image Processing, Computer-Assisted. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose quantification from gradient echo magnetic resonance imaging is particularly affected by subject motion due to its high sensitivity to magnetic field inhomogeneities, which are influenced by motion and might cause signal loss. Thus, motion correction is crucial to obtain high‐quality maps.

Methods

We extend PHIMO, our previously introduced learning‐based physics‐informed motion correction method for low‐resolution mapping. Our extended version, PHIMO+, utilizes acquisition knowledge to enhance the reconstruction performance for challenging motion patterns and increase PHIMO's robustness to varying strengths of magnetic field inhomogeneities across the brain. We perform comprehensive evaluations regarding motion detection accuracy and image quality for data with simulated and real motion.

Results

PHIMO+ outperforms the learning‐based baseline methods both qualitatively and quantitatively with respect to line detection and image quality. Moreover, PHIMO+ performs on par with a conventional state‐of‐the‐art motion correction method for quantification from gradient echo MRI, which relies on redundant data acquisition.

Conclusion

PHIMO+'s competitive motion correction performance, combined with a reduction in acquisition time by over 40% compared to the state‐of‐the‐art method, makes it a promising solution for motion‐robust quantification in research settings and clinical routine.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BrainDeep LearningMagnetic Resonance ImagingImage Processing, Computer-AssistedHumansMotionAlgorithmsArtifactsReproducibility of ResultsMovement

Stichwörter der Autor:innen

data‐consistent image reconstructionmotion correctionmotion detectionmotion simulationself‐supervised optimization

Autor:innen und Institutionen

  • Institute of Machine Learning in Biomedical Imaging, Helmholtz Munich, Neuherberg, Germany.
  • School of Computation, Information & Technology, Technical University of Munich, Munich, Germany.
  • Department of Diagnostic and Interventional Neuroradiology, School of Medicine & Health, TUM Klinikum Rechts der Isar, Technical University of Munich, Munich, Germany.
  • TUM-Neuroimaging Center, School of Medicine & Health, TUM Klinikum Rechts der Isar, Technical University of Munich, Munich, Germany.
  • Philips GmbH Market DACH, Hamburg, Germany.
  • Clinic of Neurology, School of Medicine & Health, TUM Klinikum Rechts der Isar, Technical University of Munich, Munich, Germany.

ORCID-Profile: Hannah Eichhorn, Veronika Spieker, Kerstin Hammernik, Elisa Saks, Lina Felsner, Kilian Weiss, Christine Preibisch, Julia A Schnabel

Zitieren

APA

Eichhorn, H., Spieker, V., Hammernik, K., Saks, E., Felsner, L., Weiss, K., Preibisch, C., & Schnabel, J. A. (2026). Motion‐robust T2∗$$ {\mathrm{T}}_2^{\ast } $$ quantification from low‐resolution gradient echo brain MRI with physics‐informed deep learning. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.70050

Vancouver

Eichhorn H, Spieker V, Hammernik K, Saks E, Felsner L, Weiss K, et al. Motion‐robust T2∗$$ {\mathrm{T}}_2^{\ast } $$ quantification from low‐resolution gradient echo brain MRI with physics‐informed deep learning. Magnetic Resonance in Medicine. 2026. doi:10.1002/mrm.70050

BibTeX
@article{Eichhorn2026,
  author = {Eichhorn, Hannah and Spieker, Veronika and Hammernik, Kerstin and Saks, Elisa and Felsner, Lina and Weiss, Kilian and Preibisch, Christine and Schnabel, Julia A},
  title = {Motion‐robust T2∗$$ \mathrmT_2^\ast  $$ quantification from low‐resolution gradient echo brain MRI with physics‐informed deep learning},
  journal = {Magnetic Resonance in Medicine},
  year = {2026},
  doi = {10.1002/mrm.70050}
}
Kostenlos starten →