Name
Abstract | ||
|---|---|---|
We propose a new compressed sensing MRI approach that uses the discrete nonseparable shearlet transform (DNST) as a sparsifying transform and the fast iterative soft thresholding algorithm (FISTA) for reconstruction. FISTA has a simple design and has shown good convergence behavior. The DNST transform has excellent localization properties within the space domain and excellent directional selectivity. We utilize the frequency representation of the DNST canonical dual filters to obtain a memory efficient modified FISTA based algorithm with a simple and efficient way of calculating the update, tuned to the non tight frame DNST transform. The proposed approach shows improved performance and similar execution time when compared with other state of the art reconstruction approaches. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1109/LSP.2015.2414443 | Signal Processing Letters, IEEE |
Keywords | Field | DocType |
biomedical mri,compressed sensing,discrete wavelet transforms,image filtering,image representation,iterative methods,medical image processing,dnst canonical dual filter,dnst transform,fista based algorithm,compressed sensing mri approach,directional selectivity,discrete nonseparable shearlet transform,fast iterative soft thresholding algorithm,frequency representation,space domain,fista,mri,discrete nonseparable shearlet transform (dnst),memory management,image reconstruction,vectors,magnetic resonance imaging,algorithm design and analysis | Iterative reconstruction,Convergence (routing),Mathematical optimization,Algorithm design,Pattern recognition,Shearlet transform,Memory management,Artificial intelligence,Execution time,Mathematics,Tight frame,Compressed sensing | Journal |
Volume | Issue | ISSN |
22 | 10 | 1070-9908 |
Citations | PageRank | References |
4 | 0.43 | 12 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Slavche Pejoski | 1 | 34 | 5.25 |
| Venceslav Kafedziski | 2 | 22 | 4.85 |
| Gleich, D. | 3 | 34 | 3.25 |