HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

NC-PDNet: a Density-Compensated Unrolled Network for 2D and 3D non-Cartesian MRI Reconstruction

Abstract : Deep Learning has become a very promising avenue for magnetic resonance image (MRI) reconstruction. In this work, we explore the potential of unrolled networks for the non-Cartesian acquisition setting. We design the NC-PDNet, the first density-compensated unrolled network and validate the need for its key components via an ablation study. Moreover, we conduct some generalizability experiments to test our network in out-of-distribution settings, for example training on knee data and validating on brain data. The results show that the NC-PDNet outperforms the baseline models visually and quantitatively in the 2D settings. Additionally, in the 3D settings, it outperforms them visually. In particular, in the 2D multi-coil acquisition scenario, the NC-PDNet provides up to a 1.2 dB improvement in peak signal-to-noise ratio (PSNR) over baseline networks, while also allowing a gain of at least 1 dB in PSNR in generalization settings. We provide the opensource implementation of our network, and in particular the Non-uniform Fourier Transform in TensorFlow, tested on 2D multi-coil and 3D data.
Complete list of metadata

Contributor : Zaccharie Ramzi Connect in order to contact the contributor
Submitted on : Friday, April 2, 2021 - 4:09:21 PM
Last modification on : Thursday, April 7, 2022 - 1:58:32 PM
Long-term archiving on: : Saturday, July 3, 2021 - 6:45:38 PM


  • HAL Id : hal-03188997, version 1


Zaccharie Ramzi, Chaithya G.R., Jean-Luc Starck, Philippe Ciuciu. NC-PDNet: a Density-Compensated Unrolled Network for 2D and 3D non-Cartesian MRI Reconstruction. 2021. ⟨hal-03188997v1⟩



Record views


Files downloads