EUVIMEDEUVIMED entdecken
Crossref

K-space and image domain collaborative energy-based model for parallel MRI reconstruction

Zongjiang Tu, Chen Jiang, Yu Guan, Jijun Liu, Qiegen Liu

Magnetic Resonance Imaging · 2023-06 · 99 · 110-122

DOI: 10.1016/j.mri.2023.02.004 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance Imaging, 2023-06. Verfasst von Zongjiang Tu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronic Information Engineering, Nanchang University, Nanchang 330031, China. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Magnetic Resonance Imaging. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key Research and Development Program of Jiangxi Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Decreasing magnetic resonance (MR) image acquisition times can potentially make MR examinations more accessible. Prior arts including the deep learning models have been devoted to solving the problem of long MRI imaging time. Recently, deep generative models have exhibited great potentials in algorithm robustness and usage flexibility. Nevertheless, none of existing schemes can be learned from or employed to the k-space measurement directly. Furthermore, how do the deep generative models work well in hybrid domain is also worth being investigated. In this work, by taking advantage of the deep energy-based models, we propose a k-space and image domain collaborative generative model to comprehensively estimate the MR data from under-sampled measurement. Equipped with parallel and sequential orders, experimental comparisons with the state-of-the-arts demonstrated that they involve less error in reconstruction accuracy and are more stable under different acceleration factors.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedMagnetic Resonance ImagingAlgorithmsTimeAcceleration

Stichwörter der Autor:innen

Energy-based modelHybrid domainImage reconstructionParallel magnetic resonance imaging

Autor:innen und Institutionen

  • Department of Electronic Information Engineering, Nanchang University, Nanchang 330031, China.
  • Department of Mathematics and Computer Sciences, Nanchang University, Nanchang 330031, China.
  • Department of Mathematics, Southeast University, Nanjing 210096, China; Nanjing Center for Applied Mathemtics, Nanjing, 211135,China.
  • Department of Electronic Information Engineering, Nanchang University, Nanchang 330031, China. Electronic address: liuqiegen@ncu.edu.cn.

Förderung

  • National Natural Science Foundation of China
  • Key Research and Development Program of Jiangxi Province

Zitieren

APA

Tu, Z., Jiang, C., Guan, Y., Liu, J., & Liu, Q. (2023). K-space and image domain collaborative energy-based model for parallel MRI reconstruction. Magnetic Resonance Imaging, 99, 110-122. https://doi.org/10.1016/j.mri.2023.02.004

Vancouver

Tu Z, Jiang C, Guan Y, Liu J, Liu Q. K-space and image domain collaborative energy-based model for parallel MRI reconstruction. Magnetic Resonance Imaging. 2023;99:110-122. doi:10.1016/j.mri.2023.02.004

BibTeX
@article{Tu2023,
  author = {Tu, Zongjiang and Jiang, Chen and Guan, Yu and Liu, Jijun and Liu, Qiegen},
  title = {K-space and image domain collaborative energy-based model for parallel MRI reconstruction},
  journal = {Magnetic Resonance Imaging},
  year = {2023},
  volume = {99},
  pages = {110--122},
  doi = {10.1016/j.mri.2023.02.004}
}
Kostenlos starten →