Benchmarking 3D multi-coil NC-PDNET MRI reconstruction - Institut des Sciences du Vivant Frédéric JOLIOT
Pré-Publication, Document De Travail Année : 2024

Benchmarking 3D multi-coil NC-PDNET MRI reconstruction

Résumé

Deep learning has shown great promise for MRI reconstruction from undersampled data, yet there is a lack of research on validating its performance in 3D parallel imaging acquisitions with non-Cartesian undersampling. In addition, the artifacts and the resulting image quality depend on the under-sampling pattern. To address this uncharted territory, we extend the Non-Cartesian Primal-Dual Network (NC-PDNet), a state-of-the-art unrolled neural network, to a 3D multi-coil setting. We evaluated the impact of channel-specific versus channel-agnostic training configurations and examined the effect of coil compression. Finally, we benchmark four distinct non-Cartesian undersampling patterns, with an acceleration factor of six, using the publicly available Calgary-Campinas dataset. Our results show that NC-PDNet trained on compressed data with varying input channel numbers achieves an average PSNR of 42.98 dB for 1 mm isotropic 32 channel whole-brain 3D reconstruction. With an inference time of 4.95sec and a GPU memory usage of 5.49 GB, our approach demonstrates significant potential for clinical research application.
Fichier principal
Vignette du fichier
Template_ISBI_latex.pdf (1.83 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04771143 , version 1 (07-11-2024)

Licence

Identifiants

  • HAL Id : hal-04771143 , version 1

Citer

Asma Tanabene, Chaithya Giliyar Radhakrishna, Aurélien Massire, Mariappan S. Nadar, Philippe Ciuciu. Benchmarking 3D multi-coil NC-PDNET MRI reconstruction. 2024. ⟨hal-04771143⟩
31 Consultations
28 Téléchargements

Partager

More