Unsupervised deep learning model for correcting Nyquist ghosts of single‐shot spatiotemporal encoding
Magnetic Resonance in Medicine · 2024-04 · 91 (4) · 1368-1383
DOI: 10.1002/mrm.29925 ↗Kurz gefasst
Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, online erschienen am 10.12.2023. Verfasst von Qingjia Bao und 9 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Magnetic Resonance in Biological Systems, Innovation Academy for Precision Measurement Science and Technology, Wuhan, China. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Deep Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: Chinese Academy of Sciences, National Major Scientific Research Equipment Development Project of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
Purpose
To design an unsupervised deep learning (DL) model for correcting Nyquist ghosts of single‐shot spatiotemporal encoding (SPEN) and evaluate the model for real MRI applications.
Methods
The proposed method consists of three main components: (1) an unsupervised network that combines Residual Encoder and Restricted Subspace Mapping (RERSM‐net) and is trained to generate a phase‐difference map based on the even and odd SPEN images; (2) a spin physical forward model to obtain the corrected image with the learned phase difference map; and (3) cycle‐consistency loss that is explored for training the RERSM‐net.
Results
The proposed RERSM‐net could effectively generate smooth phase difference maps and correct Nyquist ghosts of single‐shot SPEN. Both simulation and real in vivo MRI experiments demonstrated that our method outperforms the state‐of‐the‐art SPEN Nyquist ghost correction method. Furthermore, the ablation experiments of generating phase‐difference maps show the advantages of the proposed unsupervised model.
Conclusion
The proposed method can effectively correct Nyquist ghosts for the single‐shot SPEN sequence.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Key Laboratory of Magnetic Resonance in Biological Systems, Innovation Academy for Precision Measurement Science and Technology, Wuhan, China.
- University of Chinese Academy of Sciences, Beijing, China.
- School of Information Engineering, Wuhan University of Technology, Wuhan, China.
- Weizmann Institute of Science, Rehovot, Israel.
- Optics Valley Laboratory, Wuhan, China.
ORCID-Profile: Qingjia Bao, Xin Zhou
Förderung
- Chinese Academy of Sciences
- National Major Scientific Research Equipment Development Project of China
- National Natural Science Foundation of China
- National key of R&D Program of China
Zitieren
APA
Bao, Q., Liu, X., Xu, J., Xia, L., Otikovs, M., Xie, H., Liu, K., Zhang, Z., Zhou, X., & Liu, C. (2024). Unsupervised deep learning model for correcting Nyquist ghosts of single‐shot spatiotemporal encoding. Magnetic Resonance in Medicine, 91(4), 1368-1383. https://doi.org/10.1002/mrm.29925
Vancouver
Bao Q, Liu X, Xu J, Xia L, Otikovs M, Xie H, et al. Unsupervised deep learning model for correcting Nyquist ghosts of single‐shot spatiotemporal encoding. Magnetic Resonance in Medicine. 2024;91(4):1368-1383. doi:10.1002/mrm.29925
BibTeX
@article{Bao2024,
author = {Bao, Qingjia and Liu, Xinjie and Xu, Jingyun and Xia, Liyang and Otikovs, Martins and Xie, Han and Liu, Kewen and Zhang, Zhi and Zhou, Xin and Liu, Chaoyang},
title = {Unsupervised deep learning model for correcting Nyquist ghosts of single‐shot spatiotemporal encoding},
journal = {Magnetic Resonance in Medicine},
year = {2024},
volume = {91},
number = {4},
pages = {1368--1383},
doi = {10.1002/mrm.29925}
}
EUVIMED