XPDNet for MRI Reconstruction: an application to the 2020 fastMRI challenge (2020-10-15T00:00:00.000000Z)

TL;DR

A new neural network, the XPDNet, for MRI reconstruction from periodically under-sampled multi-coil data is presented, which can achieve state-of-the-art reconstruction results, as shown by its ranking of second in the fastMRI 2020 challenge.

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.

Authors

Zaccharie Ramzi

2 papers

P. Ciuciu

2 papers

J. Starck

1 papers

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

TL;DR

Abstract

Authors

References16 items

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

An Adaptive Intelligence Algorithm for Undersampled Knee MRI Reconstruction

End-to-End Variational Networks for Accelerated MRI Reconstruction

Benchmarking MRI Reconstruction Neural Networks on Large Public Datasets

On the Variance of the Adaptive Learning Rate and Beyond

fastMRI: An Open Dataset and Benchmarks for Accelerated MRI

Multi-level Wavelet-CNN for Image Restoration

Learned Primal-Dual Reconstruction

U-Net: Convolutional Networks for Biomedical Image Segmentation

ESPIRiT—an eigenvalue approach to autocalibrating parallel MRI: Where SENSE meets GRAPPA

A First-Order Primal-Dual Algorithm for Convex Problems with Applications to Imaging

Learning Fast Approximations of Sparse Coding

Sparse MRI: The application of compressed sensing for rapid MR imaging

Image quality assessment: from error visibility to structural similarity

Generalized autocalibrating partially parallel acquisitions (GRAPPA)

SENSE: Sensitivity encoding for fast MRI

Field of Study