A multi-scale residual network for accelerated radial MR parameter mapping
Keerthivasan, Mahesh B
Martin, Diego R
Altbach, Maria I
AffiliationUniv Arizona, Dept Elect & Comp Engn
Univ Arizona, Dept Med Imaging
Univ Arizona, Dept Biomed Engn
KeywordsConvolutional neural networks
MetadataShow full item record
PublisherELSEVIER SCIENCE INC
CitationFu, Z., Mandava, S., Keerthivasan, M. B., Li, Z., Johnson, K., Martin, D. R., ... & Bilgin, A. (2020). A multi-scale residual network for accelerated radial MR parameter mapping. Magnetic Resonance Imaging, 73, 152-162.
JournalMAGNETIC RESONANCE IMAGING
RightsCopyright © 2020 Elsevier Inc. All rights reserved.
Collection InformationThis item from the UA Faculty Publications collection is made available by the University of Arizona with support from the University of Arizona Libraries. If you have questions, please contact us at firstname.lastname@example.org.
AbstractA deep learning MR parameter mapping framework which combines accelerated radial data acquisition with a multi-scale residual network (MS-ResNet) for image reconstruction is proposed. The proposed supervised learning strategy uses input image patches from multi-contrast images with radial undersampling artifacts and target image patches from artifact-free multi-contrast images. Subspace filtering is used during pre-processing to denoise input patches. For each anatomy and relaxation parameter, an individual network is trained. in vivo T1 mapping results are obtained on brain and abdomen datasets and in vivo T2 mapping results are obtained on brain and knee datasets. Quantitative results for the T2 mapping of the knee show that MS-ResNet trained using either fully sampled or undersampled data outperforms conventional model-based compressed sensing methods. This is significant because obtaining fully sampled training data is not possible in many applications. in vivo brain and abdomen results for T1 mapping and in vivo brain results for T2 mapping demonstrate that MS-ResNet yields contrast-weighted images and parameter maps that are comparable to those achieved by model-based iterative methods while offering two orders of magnitude reduction in reconstruction times. The proposed approach enables recovery of high-quality contrast-weighted images and parameter maps from highly accelerated radial data acquisitions. The rapid image reconstructions enabled by the proposed approach makes it a good candidate for routine clinical use.
Note12 month embargo; available online 1 September 2020
VersionFinal accepted manuscript
- Magnetic resonance parameter mapping using model-guided self-supervised deep learning.
- Authors: Liu F, Kijowski R, El Fakhri G, Feng L
- Issue date: 2021 Jan 19
- High-performance rapid MR parameter mapping using model-based deep adversarial learning.
- Authors: Liu F, Kijowski R, Feng L, El Fakhri G
- Issue date: 2020 Dec
- High-dimensionality undersampled patch-based reconstruction (HD-PROST) for accelerated multi-contrast MRI.
- Authors: Bustin A, Lima da Cruz G, Jaubert O, Lopez K, Botnar RM, Prieto C
- Issue date: 2019 Jun
- MANTIS: Model-Augmented Neural neTwork with Incoherent k-space Sampling for efficient MR parameter mapping.
- Authors: Liu F, Feng L, Kijowski R
- Issue date: 2019 Jul
- Improving subspace constrained radial fast spin echo MRI using block matching driven non-local low rank regularization.
- Authors: Mandava S, Keerthivasan MB, Martin DR, Altbach MI, Bilgin A
- Issue date: 2020 Dec 17