NC-PDNet: a Density-Compensated Unrolled Network for 2D and 3D non-Cartesian MRI Reconstruction - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Medical Imaging Année : 2022

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

Résumé

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.
Fichier principal
Vignette du fichier
TMI_Density_compensated_unrolled_networks (7).pdf (6.19 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03188997 , version 1 (02-04-2021)
hal-03188997 , version 2 (15-09-2021)
hal-03188997 , version 3 (31-01-2022)

Identifiants

Citer

Zaccharie Ramzi, Chaithya Giliyar Radhakrishna, Jean-Luc Starck, Philippe Ciuciu. NC-PDNet: a Density-Compensated Unrolled Network for 2D and 3D non-Cartesian MRI Reconstruction. IEEE Transactions on Medical Imaging, 2022, ⟨10.1109/TMI.2022.3144619⟩. ⟨hal-03188997v3⟩
538 Consultations
721 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More