EUVIMEDEUVIMED entdecken
Crossref

Unsupervised cycle‐consistent network using restricted subspace field map for removing susceptibility artifacts in EPI

Qingjia Bao iD, Weida Xie, Martins Otikovs, Liyang Xia, Han Xie iD, Xinjie Liu, Kewen Liu, Zhi Zhang, Fang Chen, Xin Zhou iD, Chaoyang Liu

Magnetic Resonance in Medicine · 2023-08 · 90 (2) · 458-472

DOI: 10.1002/mrm.29653 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, online erschienen am 13.04.2023. Verfasst von Qingjia Bao und 10 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Magnetic Resonance in Biological Systems, Innovation Academy for Precision Measurement Science and Technology, Wuhan, 430071, Peopl…. Hauptthemen laut MEDLINE: Echo-Planar Imaging, Artifacts. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: Chinese Academy of Sciences, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To design an unsupervised deep neural model for correcting susceptibility artifacts in single‐shot Echo Planar Imaging (EPI) and evaluate the model for preclinical and clinical applications.

Methods

This work proposes an unsupervised cycle‐consistent model based on the restricted subspace field map to take advantage of both the deep learning (DL) and the reverse polarity‐gradient (RPG) method for single‐shot EPI. The proposed model consists of three main components: (1) DLRPG neural network (DLRPG‐net) to obtain field maps based on a pair of images acquired with reversed phase encoding; (2) spin physical model–based modules to obtain the corrected undistorted images based on the learned field map; and (3) cycle‐consistency loss between the input images and back‐calculated images from each cycle is explored for network training. In addition, the field maps generated by DLRPG‐net belong to a restricted subspace, which is a span of predefined cubic splines to ensure the smoothness of the field maps and avoid blurring in the corrected images. This new method is trained and validated on both preclinical and clinical datasets for diffusion MRI.

Results

The proposed network could effectively generate smooth field maps and correct susceptibility artifacts in single‐shot EPI. Simulated and in vivo preclinical/clinical experiments demonstrated that our method outperforms the state‐of‐the‐art susceptibility artifact correction methods. Furthermore, the ablation experiments of the cycle‐consistent network and the restricted subspace in generating field maps did show the advantages of DLRPG‐net.

Conclusion

The proposed method (DLRPG‐net) can effectively correct susceptibility artifacts for preclinical and clinical single‐shot EPI sequences.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Echo-Planar ImagingArtifactsDiffusion Magnetic Resonance ImagingBrainImage Processing, Computer-AssistedAlgorithms

Stichwörter der Autor:innen

EPIcycle-consistentdeep learningdiffusion-weighted imagessubspace field mapsusceptibility artifacts

Autor:innen und Institutionen

  • Key Laboratory of Magnetic Resonance in Biological Systems, Innovation Academy for Precision Measurement Science and Technology, Wuhan, 430071, People's Republic of China.
  • School of Information Engineering, Wuhan University of Technology, Wuhan, People's Republic of China.
  • Weizmann Institute of Science, Rehovot, 76001, Israel.
  • University of Chinese Academy of Sciences, Beijing, 100049, People's Republic of China.
  • Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology-Optics Valley Laboratory, Hubei, 430074, People's Republic of China.

ORCID-Profile: Qingjia Bao, Han Xie, Xin Zhou

Förderung

  • Chinese Academy of Sciences
  • National Natural Science Foundation of China

Zitieren

APA

Bao, Q., Xie, W., Otikovs, M., Xia, L., Xie, H., Liu, X., Liu, K., Zhang, Z., Chen, F., Zhou, X., & Liu, C. (2023). Unsupervised cycle‐consistent network using restricted subspace field map for removing susceptibility artifacts in EPI. Magnetic Resonance in Medicine, 90(2), 458-472. https://doi.org/10.1002/mrm.29653

Vancouver

Bao Q, Xie W, Otikovs M, Xia L, Xie H, Liu X, et al. Unsupervised cycle‐consistent network using restricted subspace field map for removing susceptibility artifacts in EPI. Magnetic Resonance in Medicine. 2023;90(2):458-472. doi:10.1002/mrm.29653

BibTeX
@article{Bao2023,
  author = {Bao, Qingjia and Xie, Weida and Otikovs, Martins and Xia, Liyang and Xie, Han and Liu, Xinjie and Liu, Kewen and Zhang, Zhi and Chen, Fang and Zhou, Xin and Liu, Chaoyang},
  title = {Unsupervised cycle‐consistent network using restricted subspace field map for removing susceptibility artifacts in EPI},
  journal = {Magnetic Resonance in Medicine},
  year = {2023},
  volume = {90},
  number = {2},
  pages = {458--472},
  doi = {10.1002/mrm.29653}
}
Kostenlos starten →