EUVIMEDEUVIMED entdecken
Crossref

Nesterov accelerated spectral conjugate gradient algorithm for magnetic resonance imaging with TV regularisation

YueHong Ding, ZhiBin Zhu, Shuo Wang, BenXin Zhang

Magnetic Resonance Imaging · 2026

DOI: 10.1016/j.mri.2025.110604 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance Imaging, 2026. Verfasst von YueHong Ding und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Engineering and Automation. Guangxi Key Laboratory of Automatic Detecting Technology and Instruments, Guilin University of Elect…. Hauptthemen laut MEDLINE: Algorithms, Magnetic Resonance Imaging, Image Processing, Computer-Assisted. Die Arbeit nennt 51 Literaturangaben. Gefördert von: Science and Technology Major Project of Guangxi, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Magnetic Resonance Imaging (MRI) as a representative of noninvasive medical imaging, it has excellent soft tissue resolution, multi-parameter imaging capability and no radiation, thus it has been widely used in the fields of disease diagnosis, treatment and drug development. However, MRI technology still has problems such as long time consuming, sensitive to motion artefacts, and difficult to balance the imaging effect and speed. In this paper, a Nesterov accelerated spectral conjugate gradient algorithm (TV_NASCG) for MRI with TV regularisation is established from optimising reconstruction algorithms based on Total Variation (TV) regularised MRI model. The algorithm is based on a set of conjugate and spectral parameters proposed in this paper, and inspired by Nesterov acceleration technique, a set of Nesterov acceleration extrapolation step and acceleration parameter are proposed. In this paper, we also use step size acceleration technique and Powell restart strategy to further improve performance of the algorithm. In addition, we give a convergence analysis of TV_NASCG algorithm, which proves that it is sufficiently descent and globally convergent. Finally, in order to verify MRI performance of TV_NASCG algorithm, it was tested in MRI experiment and compared with other algorithms, and experimental results show that TV_NASCG algorithm can improve MRI quality and shorten imaging time.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsMagnetic Resonance ImagingImage Processing, Computer-AssistedHumansArtifactsPhantoms, ImagingBrainReproducibility of Results

Stichwörter der Autor:innen

Global convergenceMagnetic resonance imagingNesterov accelerationPowell restart strategySpectral conjugate gradient methodSufficient descent property

Autor:innen und Institutionen

  • School of Electronic Engineering and Automation. Guangxi Key Laboratory of Automatic Detecting Technology and Instruments, Guilin University of Electronic Technology, Guilin, 541004, China.
  • School of Mathematics and Computing Science, Guangxi Colleges and Universities, Key Laboratory of Data Analysis and Computation, Guilin University of Electronic Technology, Guilin 541004, China; Center for Applied Mathe…
  • Guangxi Key Laboratory of Cryptography and Information Security, Guilin University of Electronic Technology, Guilin 541004, China.

Förderung

  • Science and Technology Major Project of Guangxi
  • National Natural Science Foundation of China

Zitieren

APA

Ding, Y., Zhu, Z., Wang, S., & Zhang, B. (2026). Nesterov accelerated spectral conjugate gradient algorithm for magnetic resonance imaging with TV regularisation. Magnetic Resonance Imaging. https://doi.org/10.1016/j.mri.2025.110604

Vancouver

Ding Y, Zhu Z, Wang S, Zhang B. Nesterov accelerated spectral conjugate gradient algorithm for magnetic resonance imaging with TV regularisation. Magnetic Resonance Imaging. 2026. doi:10.1016/j.mri.2025.110604

BibTeX
@article{Ding2026,
  author = {Ding, YueHong and Zhu, ZhiBin and Wang, Shuo and Zhang, BenXin},
  title = {Nesterov accelerated spectral conjugate gradient algorithm for magnetic resonance imaging with TV regularisation},
  journal = {Magnetic Resonance Imaging},
  year = {2026},
  doi = {10.1016/j.mri.2025.110604}
}
Kostenlos starten →