Comparison of reconstruction algorithm for compressive sensing magnetic resonance imaging
Compressed sensing can reconstruct the undersampled image. The combination of compressed sensing and magnetic resonance imaging is a potential future fast imaging method in hospitals. This study investigated five state-of-the-art reconstruction approaches: iterative shrinkage/threshold algorithm (ISTA), fast ISTA, subband-adaptive ISTA, exponential wavelet transform ISTA, and exponential wavelet ISTA with random search (EWISTARS). The simulation results compared the five algorithms over hand image and shoulder image. Finally, we can observe the EWISTARS obtains the best result.
Keywordscompressed sensing magnetic resonance imaging iterative shrinkage/threshold algorithm exponential wavelet transform
This work has been supported by National Natural Science Foundation of China (61401200). Moreover, the authors would also like to thank those anonymous reviewers for their helpful comments to improve this paper.
- 9.Chen Y, et al. (2016) Wavelet energy entropy and linear regression classifier for detecting abnormal breasts. Multimed Tools ApplGoogle Scholar
- 14.Deng, H.T., et al. (2015) Investigating the Stability of Fast Iterative Shrinkage Thresholding Algorithm for MR Imaging Reconstruction using Compressed Sensing. In: 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD), pp. 1296–1300. IEEEGoogle Scholar
- 24.Kowalski, M. (2014) Thresholding rules and iterative shrinkage/thresholding algorithm: a convergence study. In: International Conference on Image Processing, pp. 4151–4155. IEEEGoogle Scholar
- 26.Liu G, Yuan T-F (2016) Detection of Alzheimer's Disease by Three-Dimensional Displacement Field Estimation in Structural Magnetic Resonance Imaging. J Alzheimers Dis 50:233–248Google Scholar
- 31.Peterson BS (2014) Energy Preserved Sampling for Compressed Sensing MRI. Comput Math Method Med. Article ID: 546814Google Scholar
- 36.Wang S et al (2016) Wavelet entropy and directed acyclic graph support vector machine for detection of patients with unilateral hearing loss in MRI scanning. Front Comput Neurosci 10:160Google Scholar
- 37.Yamagishi, M., Yamada, I. (2011) Overrelaxation of the fast iterative shrinkage/thresholding algorithm for fast signal recovery. In: Statistical Signal Processing Workshop (SSP), pp. 697–700. IEEEGoogle Scholar
- 40.Yang JF, Sun P (2016) A novel compressed sensing method for magnetic resonance imaging: exponential wavelet iterative shrinkage-thresholding algorithm with random shift. Int J Biomed Imaging. Article ID: 9416435Google Scholar
- 42.Yu CX et al (2017) Separation and imaging diffractions by a sparsity-promoting model and subspace trust-region algorithm. Geophys J Int 208:1756–1763Google Scholar