Benchmarking MRI Reconstruction Neural Networks on Large Public Datasets - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Applied Sciences Year : 2020

Benchmarking MRI Reconstruction Neural Networks on Large Public Datasets

Abstract

Deep learning is starting to offer promising results for reconstruction in MRI. A lot of networks are being developed, but the comparisons remain hard because the frameworks used are not the same among studies, the networks are not properly retrained and the datasets used are not the same among comparisons. The recent release of a public dataset, fastMRI, consisting of raw k-space data, encouraged us to write a consistent benchmark of several deep neural networks for MR image reconstruction. This paper shows the results obtained for this benchmark allowing to compare the networks and links the open source implementation of all these networks in Keras. The main finding of this benchmark is that it is beneficial to perform more iterations between the image and the measurement spaces compared to having a deeper per-space network.
Fichier principal
Vignette du fichier
benchmark_paper (1).pdf (2.68 Mo) Télécharger le fichier
benchmark_paper.pdf (2.67 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Origin : Files produced by the author(s)

Dates and versions

hal-03028066 , version 1 (27-11-2020)

Identifiers

  • HAL Id : hal-03028066 , version 1

Cite

Zaccharie Ramzi, Philippe Ciuciu, Jean-Luc Starck. Benchmarking MRI Reconstruction Neural Networks on Large Public Datasets. Applied Sciences, 2020. ⟨hal-03028066⟩
149 View
231 Download

Share

Gmail Facebook X LinkedIn More