• Publications
  • Influence
XPDNet for MRI Reconstruction: an application to the 2020 fastMRI challenge
TLDR
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.
Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction
TLDR
This paper hosts the second fastMRI competition targeted towards reconstructing MR images with subsampled k-space data and identifies common failure modes across the submissions, highlighting areas of need for future research in the MRI reconstruction community.
Denoising Score-Matching for Uncertainty Quantification in Inverse Problems
TLDR
This work proposes a generic Bayesian framework forsolving inverse problems, in which the use of deep neural networks are limited to learning a prior distribution on the signals to recover, and adopts recent denoisingscore matching techniques to learn this prior from data.
Benchmarking MRI Reconstruction Neural Networks on Large Public Datasets
TLDR
The main finding of this benchmark is that it is beneficial to perform more iterations between the image and the measurement spaces compared to having a deeper per-space network.
State-of-the-Art Machine Learning MRI Reconstruction in 2020: Results of the Second fastMRI Challenge
TLDR
The second fastMRI competition targeted towards reconstructing MR images with subsampled k-space data was hosted, with one team scoring best in both SSIM scores and qualitative radiologist evaluations.
Benchmarking Deep Nets MRI Reconstruction Models on the Fastmri Publicly Available Dataset
TLDR
This work provides a tool that allows the benchmark of different reconstruction deep learning models, allowing a reproducible benchmark of the different methods and ease of building new models.
Learning the sampling density in 2D SPARKLING MRI acquisition for optimized image reconstruction
TLDR
This work combines data-driven learning schemes such as LOUPE with a state-of-the-art deep neural network for image reconstruction, called XPDNet, to learn the optimal target sampling density and uses this density as an input parameter to SPARKLING to obtain 20x accelerated non-Cartesian trajectories.
Density Compensated Unrolled Networks For Non-Cartesian MRI Reconstruction
TLDR
This work introduces a novel kind of deep neural networks to tackle non-Cartesian acquisitions, namely density compensated unrolled neural networks, which rely on Density Compensation to correct the uneven weighting of the k-space.
XPDNet for MRI Reconstruction: an Application to the fastMRI 2020 Brain Challenge
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
...
...