/DeepMRI

The code for paper 'DeepMRI: Exploiting deep residual network for fast parallel MR imaging with complex convolution'

Primary LanguagePythonGNU General Public License v3.0GPL-3.0

DeepMRI

DeepMRI: Exploiting deep residual network for fast parallel MR imaging with complex convolution

By Shanshan Wang, Huitao Cheng, Leslie Ying, Taohui Xiao, Ziwen Ke, Xin Liu, Hairong Zheng*, Dong Liang*

This repository contains the implementation of DeepMRI for parallel MR imaging using Tensorflow-gpu. Test code for Matlab and test data are also included. For a quick test, the trained weights can be used.

The architecture of DeepMRI for parallel MR imaging

The architecture of DeepMRI

Reconstruction Results by classical SPIRiT/L1-SPIRiT and the proposed method

Reconstruction

More results can be found in the paper.

Dependencies

  • Python3
  • Tensorflow
  • numpy scipy