DeepAI AI Chat
Log In Sign Up

XPDNet for MRI Reconstruction: an Application to the fastMRI 2020 Brain Challenge

by   Zaccharie Ramzi, et al.

We present a modular cross-domain neural network the XPDNet and its application to the MRI reconstruction task. This approach consists in unrolling the PDHG algorithm as well as learning the acceleration scheme between steps. We also adopt state-of-the-art techniques specific to Deep Learning for MRI reconstruction. At the time of writing, this approach is the best performer in PSNR on the fastMRI leaderboards for both knee and brain at acceleration factor 4.


page 1

page 2

page 3

page 4


Joint Calibrationless Reconstruction and Segmentation of Parallel MRI

The volume estimation of brain regions from MRI data is a key problem in...

Is good old GRAPPA dead?

We perform a qualitative analysis of performance of XPDNet, a state-of-t...

Towards Ultrafast MRI via Extreme k-Space Undersampling and Superresolution

We went below the MRI acceleration factors (a.k.a., k-space undersamplin...

DuDoRNeXt: A hybrid model for dual-domain undersampled MRI reconstruction

Undersampled MRI reconstruction is crucial for accelerating clinical sca...

State-of-the-art Machine Learning MRI Reconstruction in 2020: Results of the Second fastMRI Challenge

Accelerating MRI scans is one of the principal outstanding problems in t...