EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Rosette Trajectory MRI Reconstruction with Vision Transformers

Muhammed Fikret Yalcinbas iD, Cengizhan Ozturk, Onur Ozyurt iD, Uzay E Emir iD, Ulas Bagci

Tomography · 2025

DOI: 10.3390/tomography11040041 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Tomography, 2025. Verfasst von Muhammed Fikret Yalcinbas und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Biomedical Engineering, Boğaziçi University, Istanbul 34684, Turkey. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Image Processing, Computer-Assisted. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Wellcome Trust, NCI NIH HHS, NHLBI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction: An efficient pipeline for rosette trajectory magnetic resonance imaging reconstruction is proposed, combining the inverse Fourier transform with a vision transformer (ViT) network enhanced with a convolutional layer. This method addresses the challenges of reconstructing high-quality images from non-Cartesian data by leveraging the ViT’s ability to handle complex spatial dependencies without extensive preprocessing. Materials and Methods: The inverse fast Fourier transform provides a robust initial approximation, which is refined by the ViT network to produce high-fidelity images. Results and Discussion: This approach outperforms established deep learning techniques for normalized root mean squared error, peak signal-to-noise ratio, and entropy-based image quality scores; offers better runtime performance; and remains competitive with respect to other metrics.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingImage Processing, Computer-AssistedHumansFourier AnalysisDeep LearningSignal-To-Noise RatioAlgorithmsBrain

Stichwörter der Autor:innen

MRImachine learningmedical imaging

Autor:innen und Institutionen

  • Institute of Biomedical Engineering, Boğaziçi University, Istanbul 34684, Turkey.
  • Center for Targeted Therapy Technologies (CT3), Boğaziçi University, Istanbul 34984, Turkey.
  • Wolfson Brain Imaging Centre, Department of Clinical Neurosciences, University of Cambridge, Cambridge CB2-0QQ, UK.
  • Department of Radiology, University of North Carolina at Chapel Hill, Chapel Hill, NC 27514, USA.
  • Machine and Hybrid Intelligence Lab, Northwestern University, Chicago, IL 60611, USA.

ORCID-Profile: Muhammed Fikret Yalcinbas, Onur Ozyurt, Uzay E Emir

Förderung

  • Wellcome Trust
  • NCI NIH HHS
  • NHLBI NIH HHS
  • NIH

Zitieren

APA

Yalcinbas, M. F., Ozturk, C., Ozyurt, O., Emir, U. E., & Bagci, U. (2025). Rosette Trajectory MRI Reconstruction with Vision Transformers. Tomography. https://doi.org/10.3390/tomography11040041

Vancouver

Yalcinbas MF, Ozturk C, Ozyurt O, Emir UE, Bagci U. Rosette Trajectory MRI Reconstruction with Vision Transformers. Tomography. 2025. doi:10.3390/tomography11040041

BibTeX
@article{Yalcinbas2025,
  author = {Yalcinbas, Muhammed Fikret and Ozturk, Cengizhan and Ozyurt, Onur and Emir, Uzay E and Bagci, Ulas},
  title = {Rosette Trajectory MRI Reconstruction with Vision Transformers},
  journal = {Tomography},
  year = {2025},
  doi = {10.3390/tomography11040041}
}
Kostenlos starten →