EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Transformer‐based deep learning denoising of single and multi‐delay 3D arterial spin labeling

Qinyang Shou iD, Chenyang Zhao iD, Xingfeng Shao iD, Kay Jann, Hosung Kim, Karl G Helmer, Hanzhang Lu, Danny J J Wang iD

Magnetic Resonance in Medicine · 2024

DOI: 10.1002/mrm.29887 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, 2024. Verfasst von Qinyang Shou und 7 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory of Functional MRI Technology (LOFT), Stevens Neuro Imaging and Informatics Institute, University of Southern California, Los Angeles, Cali…. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Deep Learning. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NIBIB NIH HHS, NINDS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To present a Swin Transformer‐based deep learning (DL) model (SwinIR) for denoising single‐delay and multi‐delay 3D arterial spin labeling (ASL) and compare its performance with convolutional neural network (CNN) and other Transformer‐based methods.

Methods

SwinIR and CNN‐based spatial denoising models were developed for single‐delay ASL. The models were trained on 66 subjects (119 scans) and tested on 39 subjects (44 scans) from three different vendors. Spatiotemporal denoising models were developed using another dataset (6 subjects, 10 scans) of multi‐delay ASL. A range of input conditions was tested for denoising single and multi‐delay ASL, respectively. The performance was evaluated using similarity metrics, spatial SNR and quantification accuracy of cerebral blood flow (CBF), and arterial transit time (ATT).

Results

SwinIR outperformed CNN and other Transformer‐based networks, whereas pseudo‐3D models performed better than 2D models for denoising single‐delay ASL. The similarity metrics and image quality (SNR) improved with more slices in pseudo‐3D models and further improved when using M0 as input, but introduced greater biases for CBF quantification. Pseudo‐3D models with three slices achieved optimal balance between SNR and accuracy, which can be generalized to different vendors. For multi‐delay ASL, spatiotemporal denoising models had better performance than spatial‐only models with reduced biases in fitted CBF and ATT maps.

Conclusions

SwinIR provided better performance than CNN and other Transformer‐based methods for denoising both single and multi‐delay 3D ASL data. The proposed model offers flexibility to improve image quality and/or reduce scan time for 3D ASL to facilitate its clinical use.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingDeep LearningHumansBrainSpin LabelsArteriesCerebrovascular CirculationImage Processing, Computer-Assisted

Stichwörter der Autor:innen

Swin Transformerarterial spin labelingdeep learningquantification

Substanzen

Spin Labels

Autor:innen und Institutionen

  • Laboratory of Functional MRI Technology (LOFT), Stevens Neuro Imaging and Informatics Institute, University of Southern California, Los Angeles, California, USA.
  • Laboratory of Neuro Imaging (LONI), Stevens Neuroimaging and Informatics Institute, University of Southern California, Los Angeles, California, USA.
  • Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, USA.
  • Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, Massachusetts, USA.
  • Department of Radiology, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA.

ORCID-Profile: Qinyang Shou, Chenyang Zhao, Xingfeng Shao, Danny J J Wang

Förderung

  • NIBIB NIH HHS
  • NINDS NIH HHS

Zitieren

APA

Shou, Q., Zhao, C., Shao, X., Jann, K., Kim, H., Helmer, K. G., Lu, H., & Wang, D. J. J. (2024). Transformer‐based deep learning denoising of single and multi‐delay 3D arterial spin labeling. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.29887

Vancouver

Shou Q, Zhao C, Shao X, Jann K, Kim H, Helmer KG, et al. Transformer‐based deep learning denoising of single and multi‐delay 3D arterial spin labeling. Magnetic Resonance in Medicine. 2024. doi:10.1002/mrm.29887

BibTeX
@article{Shou2024,
  author = {Shou, Qinyang and Zhao, Chenyang and Shao, Xingfeng and Jann, Kay and Kim, Hosung and Helmer, Karl G and Lu, Hanzhang and Wang, Danny J J},
  title = {Transformer‐based deep learning denoising of single and multi‐delay 3D arterial spin labeling},
  journal = {Magnetic Resonance in Medicine},
  year = {2024},
  doi = {10.1002/mrm.29887}
}
Kostenlos starten →