Abstract | ||
---|---|---|
Compressed sensing utilizes the sparsity of Magnetic resonance (MR) images to obtain accurate reconstructions from undersampled k-space data. In this paper, a novel nonlocal dynamic MRI reconstruction method with low-rank regularization is developed to exploit the spatiotemporal structural sparsity of a MRI sequence. The nonlocal prior and low rank prior are combined organically by grouping similar patches in both spatial and temporal domain. The low-rank regularization can be approximated by nuclear norm minimization solved by a singular value thresholding (SVT) method with adaptive thresholds estimation. The objective function is divided into several sub-problems that are easier to solve by alternative direction multiplier method (ADMM). Extensive experiments show that the new method outperforms commonly used classical dynamic MRI reconstruction algorithms. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/MMSP.2015.7340840 | 2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP) |
Keywords | Field | DocType |
patch-based nonlocal dynamic MRI reconstruction,compressed sensing,magnetic resonance imaging,low-rank regularization,MRI sequence,singular value thresholding method,nuclear norm minimization,SVT method,adaptive thresholds estimation,alternative direction multiplier method,ADMM | Iterative reconstruction,Computer vision,Pattern recognition,Computer science,Multiplier method,Minification,Regularization (mathematics),Artificial intelligence,Linear programming,Real-time MRI,Dynamic contrast-enhanced MRI,Compressed sensing | Conference |
ISSN | Citations | PageRank |
2163-3517 | 0 | 0.34 |
References | Authors | |
9 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Liyan Sun | 1 | 7 | 3.16 |
Jinchu Chen | 2 | 2 | 0.70 |
Xiao-ping Zhang | 3 | 951 | 100.51 |
Xinghao Ding | 4 | 591 | 52.95 |