EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Pushing the limits of low‐cost ultra‐low‐field MRI by dual‐acquisition deep learning 3D superresolution

Vick Lau iD, Linfang Xiao, Yujiao Zhao iD, Shi Su iD, Ye Ding iD, Christopher Man iD, Xunda Wang, Anderson Tsang iD, Peng Cao iD, Gary K K Lau iD, Gilberto K K Leung iD, Alex T L Leong iD und 1 weitere

Magnetic Resonance in Medicine · 2023-08 · 90 (2) · 400-416

DOI: 10.1002/mrm.29642 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, online erschienen am 03.04.2023. Verfasst von Vick Lau und 12 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory of Biomedical Imaging and Signal Processing, The University of Hong Kong, SAR, Hong Kong, China. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 76-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Recent development of ultra‐low‐field (ULF) MRI presents opportunities for low‐power, shielding‐free, and portable clinical applications at a fraction of the cost. However, its performance remains limited by poor image quality. Here, a computational approach is formulated to advance ULF MR brain imaging through deep learning of large‐scale publicly available 3T brain data.

Methods

A dual‐acquisition 3D superresolution model is developed for ULF brain MRI at 0.055 T. It consists of deep cross‐scale feature extraction, attentional fusion of two acquisitions, and reconstruction. Models for T 1 ‐weighted and T 2 ‐weighted imaging were trained with 3D ULF image data sets synthesized from the high‐resolution 3T brain data from the Human Connectome Project. They were applied to 0.055T brain MRI with two repetitions and isotropic 3‐mm acquisition resolution in healthy volunteers, young and old, as well as patients.

Results

The proposed approach significantly enhanced image spatial resolution and suppressed noise/artifacts. It yielded high 3D image quality at 0.055 T for the two most common neuroimaging protocols with isotropic 1.5‐mm synthetic resolution and total scan time under 20 min. Fine anatomical details were restored with intrasubject reproducibility, intercontrast consistency, and confirmed by 3T MRI.

Conclusion

The proposed dual‐acquisition 3D superresolution approach advances ULF MRI for quality brain imaging through deep learning of high‐field brain data. Such strategy can empower ULF MRI for low‐cost brain imaging, especially in point‐of‐care scenarios or/and in low‐income and mid‐income countries.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningHumansReproducibility of ResultsMagnetic Resonance ImagingImaging, Three-DimensionalNeuroimagingBrain

Stichwörter der Autor:innen

3D superresolutionMRIbraindeep learningultralow-field MRI

Autor:innen und Institutionen

  • Laboratory of Biomedical Imaging and Signal Processing, The University of Hong Kong, SAR, Hong Kong, China.
  • Department of Electrical and Electronic Engineering, The University of Hong Kong, SAR, Hong Kong, China.
  • Department of Surgery, LKS Faculty of Medicine, The University of Hong Kong, SAR, Hong Kong, China.
  • Department of Diagnostic Radiology, LKS Faculty of Medicine, The University of Hong Kong, SAR, Hong Kong, China.
  • Department of Medicine, LKS Faculty of Medicine, The University of Hong Kong, SAR, Hong Kong, China.

ORCID-Profile: Vick Lau, Yujiao Zhao, Shi Su, Ye Ding, Christopher Man, Anderson Tsang, Peng Cao, Gary K K Lau, Gilberto K K Leung, Alex T L Leong, Ed X Wu

Zitieren

APA

Lau, V., Xiao, L., Zhao, Y., Su, S., Ding, Y., Man, C., Wang, X., Tsang, A., Cao, P., Lau, G. K. K., Leung, G. K. K., Leong, A. T. L., & Wu, E. X. (2023). Pushing the limits of low‐cost ultra‐low‐field MRI by dual‐acquisition deep learning 3D superresolution. Magnetic Resonance in Medicine, 90(2), 400-416. https://doi.org/10.1002/mrm.29642

Vancouver

Lau V, Xiao L, Zhao Y, Su S, Ding Y, Man C, et al. Pushing the limits of low‐cost ultra‐low‐field MRI by dual‐acquisition deep learning 3D superresolution. Magnetic Resonance in Medicine. 2023;90(2):400-416. doi:10.1002/mrm.29642

BibTeX
@article{Lau2023,
  author = {Lau, Vick and Xiao, Linfang and Zhao, Yujiao and Su, Shi and Ding, Ye and Man, Christopher and Wang, Xunda and Tsang, Anderson and Cao, Peng and Lau, Gary K K and Leung, Gilberto K K and Leong, Alex T L and Wu, Ed X},
  title = {Pushing the limits of low‐cost ultra‐low‐field MRI by dual‐acquisition deep learning 3D superresolution},
  journal = {Magnetic Resonance in Medicine},
  year = {2023},
  volume = {90},
  number = {2},
  pages = {400--416},
  doi = {10.1002/mrm.29642}
}
Kostenlos starten →