XPDNet for MRI Reconstruction: an application to the 2020 fastMRI challenge

Code

• github.com/zaccharieramzi/fastmri-reproducible-benchmark
  OfficialIn papertf★ 161
• github.com/wdika/mridc
  pytorch★ 40
• github.com/f78bono/deep-cine-cardiac-mri
  pytorch★ 18

Abstract

We present a new neural network, the XPDNet, for MRI reconstruction from periodically under-sampled multi-coil data. We inform the design of this network by taking best practices from MRI reconstruction and computer vision. We show that this network can achieve state-of-the-art reconstruction results, as shown by its ranking of second in the fastMRI 2020 challenge.

Tasks

Benchmark Results

Reproductions