EUVIMEDEUVIMED entdecken
Crossref

GL-mamba-net: A magnetic resonance imaging restoration network with global-local mamba

Ke Liang, Zhijin Lin, Jie Yang, Teng Yu, Jieru Chi, Feng Liu

Magnetic Resonance Imaging · 2026-02 · 126 · 110574

DOI: 10.1016/j.mri.2025.110574 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance Imaging, 2026-02. Verfasst von Ke Liang und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Electronics and Information, Qingdao University, Qingdao 266071, China. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Image Processing, Computer-Assisted, Deep Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: Australian Research Council, Shandong Province Natural Science Foundation, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In clinical practice, magnetic resonance imaging is essential for disease diagnosis and evaluation, although it generally requires a prolonged scanning duration. Recently, several deep learning-based restoration techniques have been introduced to accelerate MRI acquisition. However, most existing MRI restoration methods struggle to fully capture local texture features and have limitations in fusing global and local features. To address this issue, the paper introduces a dual path Mamba network. This method uses a strategy of multi-scale local feature and global feature fusion for under-sampled single-coil image domain data, significantly improving both the quality and efficiency of image restoration. Specifically, 1) A multi-scale local Mamba block is proposed, which extracts local information from different regions through a multi-scale window mechanism, capturing diverse local features. 2) A new feature fusion block is proposed, which fuses global and local information to enhance the completeness of feature expression. 3) A dual path Mamba network architecture is proposed. This dual-path design significantly improves feature extraction capability and adaptability in complex and dynamic data environments. Through comprehensive experiments on the NAMIC, fastMRI and BraTS datasets, it is shown that the proposed network surpasses current leading methods across various evaluation metrics, particularly excelling in restoring texture details and tissue structures.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingImage Processing, Computer-AssistedDeep LearningHumansAlgorithmsBrainNeural Networks, Computer

Stichwörter der Autor:innen

Feature fusionIn-depth learningMRI restorationMamba

Autor:innen und Institutionen

  • College of Electronics and Information, Qingdao University, Qingdao 266071, China.
  • College of Mechanical and Electrical Engineering, Qingdao University, Qingdao 266071, China.
  • College of Electronics and Information, Qingdao University, Qingdao 266071, China. Electronic address: chijieru@qdu.edu.cn.
  • School of Electrical Engineering and Computer Science, University of Queensland, Brisbane, QLD 4072, Australia.

Förderung

  • Australian Research Council
  • Shandong Province Natural Science Foundation
  • National Natural Science Foundation of China

Zitieren

APA

Liang, K., Lin, Z., Yang, J., Yu, T., Chi, J., & Liu, F. (2026). GL-mamba-net: A magnetic resonance imaging restoration network with global-local mamba. Magnetic Resonance Imaging, 126, 110574. https://doi.org/10.1016/j.mri.2025.110574

Vancouver

Liang K, Lin Z, Yang J, Yu T, Chi J, Liu F. GL-mamba-net: A magnetic resonance imaging restoration network with global-local mamba. Magnetic Resonance Imaging. 2026;126:110574. doi:10.1016/j.mri.2025.110574

BibTeX
@article{Liang2026,
  author = {Liang, Ke and Lin, Zhijin and Yang, Jie and Yu, Teng and Chi, Jieru and Liu, Feng},
  title = {GL-mamba-net: A magnetic resonance imaging restoration network with global-local mamba},
  journal = {Magnetic Resonance Imaging},
  year = {2026},
  volume = {126},
  pages = {110574},
  doi = {10.1016/j.mri.2025.110574}
}
Kostenlos starten →