Abstract | ||
---|---|---|
Compressive Sensing (CS) is an effective approach for fast Magnetic Resonance Imaging (MRI). It aims at reconstructing MR image from a small number of under-sampled data in k-space, and accelerating the data acquisition in MRI. To improve the current MRI system in reconstruction accuracy and computational speed, in this paper, we propose a novel deep architecture, dubbed ADMM-Net. ADMM-Net is defined over a data flow graph, which is derived from the iterative procedures in Alternating Direction Method of Multipliers (ADMM) algorithm for optimizing a CS-based MRI model. In the training phase, all parameters of the net, e.g., image transforms, shrinkage functions, etc., are discriminatively trained end-to-end using L-BFGS algorithm. In the testing phase, it has computational overhead similar to ADMM but uses optimized parameters learned from the training data for CS-based reconstruction task. Experiments on MRI image reconstruction under different sampling ratios in k-space demonstrate that it significantly improves the baseline ADMM algorithm and achieves high reconstruction accuracies with fast computational speed. |
Year | Venue | Field |
---|---|---|
2016 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 29 (NIPS 2016) | Iterative reconstruction,Training set,Overhead (computing),Computer science,Data acquisition,Data-flow analysis,Artificial intelligence,Sampling (statistics),Compressed sensing,Machine learning,Magnetic resonance imaging |
DocType | Volume | ISSN |
Conference | 29 | 1049-5258 |
Citations | PageRank | References |
14 | 0.49 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yan Yang | 1 | 121 | 22.47 |
Jian Sun | 2 | 839 | 42.32 |
Huibin Li | 3 | 63 | 3.79 |
Zongben Xu | 4 | 3203 | 198.88 |