EUVIMEDEUVIMED entdecken
Crossref

MEDL‐Net: A model‐based neural network for MRI reconstruction with enhanced deep learned regularizers

Xiaoyu Qiao iD, Yuping Huang, Weisheng Li

Magnetic Resonance in Medicine · 2023

DOI: 10.1002/mrm.29575 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, 2023. Verfasst von Xiaoyu Qiao und 2 weiteren Autor:innen. Beteiligte Einrichtung: Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing, China. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Neural Networks, Computer. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Natural Science Foundation of Chongqing.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To improve the MRI reconstruction performance of model‐based networks and to alleviate their large demand for GPU memory.

Methods

A model‐based neural network with enhanced deep learned regularizers (MEDL‐Net) was proposed. The MEDL‐Net is separated into several submodules, each of which consists of several cascades to mimic the optimization steps in conventional MRI reconstruction algorithms. Information from shallow cascades is densely connected to latter ones to enrich their inputs in each submodule, and additional revising blocks (RB) are stacked at the end of the submodules to bring more flexibility. Moreover, a composition loss function was designed to explicitly supervise RBs.

Results

Network performance was evaluated on a publicly available dataset. The MEDL‐Net quantitatively outperforms the state‐of‐the‐art methods on different MR image sequences with different acceleration rates (four‐fold and six‐fold). Moreover, the reconstructed images showed that the detailed textures are better preserved. In addition, fewer cascades are required when achieving the same reconstruction results compared with other model‐based networks.

Conclusion

In this study, a more efficient model‐based deep network was proposed to reconstruct MR images. The experimental results indicate that the proposed method improves reconstruction performance with fewer cascades, which alleviates the large demand for GPU memory.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedNeural Networks, ComputerMagnetic Resonance ImagingAlgorithmsAcceleration

Stichwörter der Autor:innen

MRI reconstructioncompressed sensingdeep learningmodel based

Autor:innen und Institutionen

  • Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing, China.

ORCID-Profile: Xiaoyu Qiao

Förderung

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

Zitieren

APA

Qiao, X., Huang, Y., & Li, W. (2023). MEDL‐Net: A model‐based neural network for MRI reconstruction with enhanced deep learned regularizers. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.29575

Vancouver

Qiao X, Huang Y, Li W. MEDL‐Net: A model‐based neural network for MRI reconstruction with enhanced deep learned regularizers. Magnetic Resonance in Medicine. 2023. doi:10.1002/mrm.29575

BibTeX
@article{Qiao2023,
  author = {Qiao, Xiaoyu and Huang, Yuping and Li, Weisheng},
  title = {MEDL‐Net: A model‐based neural network for MRI reconstruction with enhanced deep learned regularizers},
  journal = {Magnetic Resonance in Medicine},
  year = {2023},
  doi = {10.1002/mrm.29575}
}
Kostenlos starten →