Deep neural networks have recently been thoroughly investigated as a powerful tool for MRI reconstruction. There is a lack of research, however, regarding their use for a specific setting of MRI, namely non-Cartesian acquisitions. In this work, we introduce a novel kind of deep neural networks to tackle this problem, namely density compensated unrolled neural networks, which rely on Density Compensation to correct the uneven weighting of the k-space. We assess their efficiency on the publicly available fastMRI dataset, and perform a small ablation study. Our results show that the density-compensated unrolled neural networks outperform the different baselines, and that all parts of the design are needed. We also open source our code, in particular a Non-Uniform Fast Fourier transform for TensorFlow.
@article{arxiv.2101.01570,
title = {Density Compensated Unrolled Networks for Non-Cartesian MRI Reconstruction},
author = {Zaccharie Ramzi and Jean-Luc Starck and Philippe Ciuciu},
journal= {arXiv preprint arXiv:2101.01570},
year = {2021}
}