2020
DOI: 10.1016/j.mri.2020.08.013
|View full text |Cite
|
Sign up to set email alerts
|

A multi-scale residual network for accelerated radial MR parameter mapping

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
18
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
6

Relationship

1
5

Authors

Journals

citations
Cited by 12 publications
(18 citation statements)
references
References 52 publications
0
18
0
Order By: Relevance
“…This may be due to the challenge of obtaining fully sampled multi-contrast CMR for supervised training as it may require breath-hold that is intolerable or scan time that is prohibitively long. A recent study has used the reconstruction by conventional CS as ground truth to train a multi-contrast reconstruction network, showing that the trained network may outperform CS [83]. But still, possible residual aliasing artefacts in the CS reconstructed reference images may influence the network performance.…”
Section: Discussionmentioning
confidence: 99%
See 4 more Smart Citations
“…This may be due to the challenge of obtaining fully sampled multi-contrast CMR for supervised training as it may require breath-hold that is intolerable or scan time that is prohibitively long. A recent study has used the reconstruction by conventional CS as ground truth to train a multi-contrast reconstruction network, showing that the trained network may outperform CS [83]. But still, possible residual aliasing artefacts in the CS reconstructed reference images may influence the network performance.…”
Section: Discussionmentioning
confidence: 99%
“…Several deep learning undersampled MR reconstruction techniques have been proposed in the last several years, from standalone neural network mapping undersampled images/k-space to fully sampled images/k-space [91][92][93], to unrolled cascaded networks [88,94] emulating iterative steps of conventional CS. Inspired by the breakthrough of single-contrast DL reconstruction, several multi-contrast DL reconstruction methods have recently been developed to reconstruct high-quality contrast-weighted images [79,81,83,85] or parametric maps [75,77,78]. Most of these methods have been validated in brain and/or knee MRI, whereas few DL techniques exist for multi-contrast CMR.…”
Section: Discussionmentioning
confidence: 99%
See 3 more Smart Citations