EUVIMEDEUVIMED entdecken
Crossref

Deep‐ DSP 2 : Cross‐Domain Deep Learning Direct MR Signal Prediction for RF Shielding‐Free MRI

Jiahao Hu, Yujiao Zhao iD, Alex T L Leong, Ed X Wu iD

Magnetic Resonance in Medicine · 2027-01 · 97 (1) · 351-364

DOI: 10.1002/mrm.70583 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, online erschienen am 25.08.2026. Verfasst von Jiahao Hu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory of Biomedical Imaging and Signal Processing, The University of Hong Kong, Hong Kong SAR, People's Republic of China. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Deep Learning, Brain, Image Processing, Computer-Assisted. Die Arbeit nennt 64 Literaturangaben. Gefördert von: Hong Kong Research Grant Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To develop a deep learning approach to electromagnetic interference (EMI) elimination in the presence of dynamically varying electromagnetic coupling relationships (i.e., spectral domain transfer functions) between MRI receive and EMI sensing coils for RF shielding‐free ultra‐low‐field (ULF) MRI.

Methods

Following the recently developed active EMI sensing and deep learning direct MR signal prediction (Deep‐DSP), the proposed approach, named Deep‐DSP 2 , utilizes both time and spectral domains to form a cross‐domain framework to enhance the exploitation of signal characteristics, thus providing better differentiation of MR and EMI signals. Deep‐DSP 2 also utilizes a transformer‐based U‐Net architecture that integrates transformer blocks for global modeling and convolution blocks for local feature extraction. Deep‐DSP 2 was quantitatively evaluated using both simulated and experimental data sets from a shielding‐free 0.055T brain MRI scanner where the transfer functions were varied during scanning due to subject motion or arbitrarily changing EMI source location.

Results

The Deep‐DSP 2 consistently outperformed Deep‐DSP, CNN, and analytical transfer function methods for retrospective elimination of strong narrowband or broadband EMI signals. More importantly, Deep‐DSP 2 removed EMI signals most effectively when the subject motioned or EMI source location changed dynamically during scanning.

Conclusion

Deep‐DSP 2 provides more robust EMI elimination than the original Deep‐DSP and other existing methods, especially when the transfer functions dynamically vary. In point‐of‐care MRI, patient motion and EMI source location change during scanning can alter the intrinsic transfer functions between MRI receive and EMI sensing coils. Therefore, Deep‐DSP 2 is expected to be more suitable for portable ULF MRI applications in diverse settings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingDeep LearningBrainImage Processing, Computer-AssistedHumansRadio WavesAlgorithmsPhantoms, ImagingConvolutional Neural NetworksSignal Processing, Computer-AssistedComputer SimulationElectromagnetic Fields

Stichwörter der Autor:innen

EMIRF shieldingdeep learningportable MRIultra‐low‐field

Autor:innen und Institutionen

  • Laboratory of Biomedical Imaging and Signal Processing, The University of Hong Kong, Hong Kong SAR, People's Republic of China.
  • Department of Electrical and Computer Engineering, The University of Hong Kong, Hong Kong SAR, People's Republic of China.

ORCID-Profile: Yujiao Zhao, Ed X Wu

Förderung

  • Hong Kong Research Grant Council

Zitieren

APA

Hu, J., Zhao, Y., Leong, A. T. L., & Wu, E. X. (2027). Deep‐ DSP 2 : Cross‐Domain Deep Learning Direct MR Signal Prediction for RF Shielding‐Free MRI. Magnetic Resonance in Medicine, 97(1), 351-364. https://doi.org/10.1002/mrm.70583

Vancouver

Hu J, Zhao Y, Leong ATL, Wu EX. Deep‐ DSP 2 : Cross‐Domain Deep Learning Direct MR Signal Prediction for RF Shielding‐Free MRI. Magnetic Resonance in Medicine. 2027;97(1):351-364. doi:10.1002/mrm.70583

BibTeX
@article{Hu2027,
  author = {Hu, Jiahao and Zhao, Yujiao and Leong, Alex T L and Wu, Ed X},
  title = {Deep‐ DSP 2 : Cross‐Domain Deep Learning Direct MR Signal Prediction for RF Shielding‐Free MRI},
  journal = {Magnetic Resonance in Medicine},
  year = {2027},
  volume = {97},
  number = {1},
  pages = {351--364},
  doi = {10.1002/mrm.70583}
}
Kostenlos starten →