Deep learning based MRI reconstruction with transformer

Zhengliang Wu, Weibin Liao, Chao Yan, Mangsuo Zhao, Guowen Liu, Ning Ma*, Xuesong Li*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

14 Citations (Scopus)

Abstract

Magnetic resonance imaging (MRI) has become one of the most powerful imaging techniques in medical diagnosis, yet the prolonged scanning time becomes a bottleneck for application. Reconstruction methods based on compress sensing (CS) have made progress in reducing this cost by acquiring fewer points in the k-space. Traditional CS methods impose restrictions from different sparse domains to regularize the optimization that always requires balancing time with accuracy. Neural network techniques enable learning a better prior from sample pairs and generating the results in an analytic way. In this paper, we propose a deep learning based reconstruction method to restore high-quality MRI images from undersampled k-space data in an end-to-end style. Unlike prior literature adopting convolutional neural networks (CNN), advanced Swin Transformer is used as the backbone of our work, which proved to be powerful in extracting deep features of the image. In addition, we combined the k-space consistency in the output and further improved the quality. We compared our models with several reconstruction methods and variants, and the experiment results proved that our model achieves the best results in samples at low sampling rates. The source code of KTMR could be acquired at https://github.com/BITwzl/KTMR.

Original languageEnglish
Article number107452
JournalComputer Methods and Programs in Biomedicine
Volume233
DOIs
Publication statusPublished - May 2023

Keywords

  • Compress sensing
  • Deep learning
  • Magnetic resonance imaging (MRI)
  • Transformer

Fingerprint

Dive into the research topics of 'Deep learning based MRI reconstruction with transformer'. Together they form a unique fingerprint.

Cite this