Density Compensated Unrolled Networks for Non-Cartesian MRI Reconstruction

作者: | Zaccharie Ramzi | Philippe Ciuciu | Jean-Luc Starck |

摘要: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. We assess their efficiency on the publicly available fastMRI dataset, and perform a small ablation study. We also open source our code, in particular a Non-Uniform Fast Fourier transform for TensorFlow.

论文地址

https://arxiv.org/abs/2101.01570v1

下载地址

https://arxiv.org/pdf/2101.01570v1.pdf

全部源码

https://github.com/zaccharieramzi/fastmri-reproducible-benchmark 类型: tensorflow

mri reconstruction

相关推荐

暂无评论

微信扫一扫,分享到朋友圈

Density Compensated Unrolled Networks for Non-Cartesian MRI Reconstruction