EUVIMEDEUVIMED entdecken
Crossref

A cross-domain complex convolution neural network for undersampled magnetic resonance image reconstruction

Tengfei Yuan, Jie Yang, Jieru Chi, Teng Yu, Feng Liu

Magnetic Resonance Imaging · 2024-05 · 108 · 86-97

DOI: 10.1016/j.mri.2024.02.004 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance Imaging, 2024-05. Verfasst von Tengfei Yuan und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Electronics and Information, Qingdao University, Qingdao, Shandong, China. Hauptthemen laut MEDLINE: Algorithms, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: Australian Research Council, Shandong Province Natural Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To introduce a new cross-domain complex convolution neural network for accurate MR image reconstruction from undersampled k-space data. Most reconstruction methods utilize neural networks or cascade neural networks in either the image domain and/or the k-space domain. However, these methods encounter several challenges: 1) Applying neural networks directly in the k-space domain is suboptimal for feature extraction; 2) Classic image-domain networks have difficulty in fully extracting texture features; and 3) Existing cross-domain methods still face challenges in extracting and fusing features from both image and k-space domains simultaneously. In this work, we propose a novel deep-learning-based 2-D single-coil complex-valued MR reconstruction network termed TEID-Net. TEID-Net integrates three modules: 1) TE-Net, an image-domain-based sub-network designed to enhance contrast in input features by incorporating a Texture Enhancement Module; 2) ID-Net, an intermediate-domain sub-network tailored to operate in the image-Fourier space, with the specific goal of reducing aliasing artifacts realized by leveraging the superior incoherence property of the decoupled one-dimensional signals; and 3) TEID-Net, a cross-domain reconstruction network in which ID-Nets and TE-Nets are combined and cascaded to boost the quality of image reconstruction further. Extensive experiments have been conducted on the fastMRI and Calgary-Campinas datasets. Results demonstrate the effectiveness of the proposed TEID-Net in mitigating undersampling-induced artifacts and producing high-quality image reconstructions, outperforming several state-of-the-art methods while utilizing fewer network parameters. The cross-domain TEID-Net excels in restoring tissue structures and intricate texture details. The results illustrate that TEID-Net is particularly well-suited for regular Cartesian undersampling scenarios.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsImage Processing, Computer-AssistedNeural Networks, ComputerMagnetic Resonance ImagingArtifacts

Stichwörter der Autor:innen

Complex convolution neural networksCross-domain deep learningImage reconstructionMRI acceleration

Autor:innen und Institutionen

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

Förderung

  • Australian Research Council
  • Shandong Province Natural Science Foundation

Zitieren

APA

Yuan, T., Yang, J., Chi, J., Yu, T., & Liu, F. (2024). A cross-domain complex convolution neural network for undersampled magnetic resonance image reconstruction. Magnetic Resonance Imaging, 108, 86-97. https://doi.org/10.1016/j.mri.2024.02.004

Vancouver

Yuan T, Yang J, Chi J, Yu T, Liu F. A cross-domain complex convolution neural network for undersampled magnetic resonance image reconstruction. Magnetic Resonance Imaging. 2024;108:86-97. doi:10.1016/j.mri.2024.02.004

BibTeX
@article{Yuan2024,
  author = {Yuan, Tengfei and Yang, Jie and Chi, Jieru and Yu, Teng and Liu, Feng},
  title = {A cross-domain complex convolution neural network for undersampled magnetic resonance image reconstruction},
  journal = {Magnetic Resonance Imaging},
  year = {2024},
  volume = {108},
  pages = {86--97},
  doi = {10.1016/j.mri.2024.02.004}
}
Kostenlos starten →