Compressed sensing (CS) has produced promising results on dynamic cardiac MR imaging by exploiting the sparsity in image series. In this paper, we propose a new method to improve the CS reconstruction for dynamic cardiac MRI based on the theory of structured sparse representation. The proposed method user the PCA subdictionaries for adaptive sparse representation and suppresses the sparse coding noise to obtain good reconstructions. An accelerated iterative shrinkage algorithm is used to solve the optimization problem and achieve a fast convergence rate. Experimental results demonstrate that the proposed method improves the reconstruction quality of dynamic cardiac cine MRI over the state-of-the-art CS method. 1. Introduction Dynamic cardiac cine MR imaging aims at simultaneously providing a series of dynamic magnetic resonance image in spatial and temporal domains ( space) at a high frame rate. It usually acquires the -space at each time frame and collects the raw data in the spatial frequency and temporal domain, the so called space. Therefore, it is necessary to reconstruct each time frame and get a series of dynamic images. However, the relatively low acquisition speed of the dynamic MRI is an important factor to limit its application in clinics. How to accelerate -space sampling for each time frame and reconstruct them without sacrificing spatial resolution is a challenging problem. In recent years, many advanced techniques [1–10] were proposed to effectively address this issue and can be divided into two categories. One is based on compressed sensing (CS) theory [11, 12] utilizing the sparsity in dynamic images to be reconstructed, and the other is based on the partial separable theory [13] exploiting the low-rank property of images in space. The application of CS in dynamic MRI has drawn a lot of attention, since this theory demonstrates that the signal can be accurately reconstructed from a small amount of linear undersampled measurements by exploiting the inherent sparsity in signal. For example, Jung et al. [7, 9] uncovered an intriguing link between the compressed sensing and BLAST/SENSE and proposed the FOCUSS algorithm to achieve high spatiotemporal resolution in cardiac cine imaging. Liang et al. [5] developed iterative support detection ( ISD) method to further utilize the detected partial support information besides the sparsity in cardiac cine images. Recently, image restoration with patch-based sparse representations has attracted a lot of attention. The similarity of works in this topic is seeking for a more appropriate way to
References
[1]
A. Majumdar, R. K. Ward, and T. Aboulnasr, “Compressed sensing based Real-Time dynamic MRI reconstruction,” IEEE Transactions on Medical Imaging, vol. 31, no. 12, pp. 2253–2266, 2012.
[2]
B. Zhao, J. P. Haldar, C. Brinegar, and Z.-P. Liang, “Low rank matrix recovery for real-time cardiac MRI,” in Proceedings of the 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro (ISBI '10), pp. 996–999, Rotterdam, The Netherlands, April 2010.
[3]
J. P. Haldar and Z.-P. Liang, “Low-rank approximations for dynamic imaging,” in Proceedings of the 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro (ISBI '11), pp. 1052–1055, Chicago, Ill, USA, April 2011.
[4]
S. G. Lingala, Y. Hu, E. Dibella, and M. Jacob, “Accelerated dynamic MRI exploiting sparsity and low-rank structure: k-t SLR,” IEEE Transactions on Medical Imaging, vol. 30, no. 5, pp. 1042–1054, 2011.
[5]
D. Liang, E. V. R. Dibella, R.-R. Chen, and L. Ying, “k-t ISD: dynamic cardiac MR imaging using compressed sensing with iterative support detection,” Magnetic Resonance in Medicine, vol. 68, no. 1, pp. 41–53, 2012.
[6]
M. Lustig, J. M. Santos, D. L. Donoho, and J. M. Pauly, “k-t SPARSE: high frame rate dynamic MRI exploiting spatio-temporal sparsity,” in Proceedings of the 14th Annual Meeting of ISMRM, p. 2420, Seattle, Wash, USA, 2006.
[7]
H. Jung, J. C. Ye, and E. Y. Kim, “Improved k-t BLAST and k-t SENSE using FOCUSS,” Physics in Medicine and Biology, vol. 52, no. 11, article 018, pp. 3201–3226, 2007.
[8]
U. Gamper, P. Boesiger, and S. Kozerke, “Compressed sensing in dynamic MRI,” Magnetic Resonance in Medicine, vol. 59, no. 2, pp. 365–373, 2008.
[9]
H. Jung, K. Sung, K. S. Nayak, E. Y. Kim, and J. C. Ye, “K-t FOCUSS: a general compressed sensing framework for high resolution dynamic MRI,” Magnetic Resonance in Medicine, vol. 61, no. 1, pp. 103–116, 2009.
[10]
L. Feng, M. B. Srichai, R. P. Lim et al., “Highly accelerated real-time cardiac cine MRI using kt SPARSE-SENSE,” Magnetic Resonance in Medicine, vol. 70, no. 1, pp. 64–74, 2013.
[11]
D. L. Donoho, “Compressed sensing,” IEEE Transactions on Information Theory, vol. 52, no. 4, pp. 1289–1306, 2006.
[12]
E. J. Candès, J. Romberg, and T. Tao, “Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information,” IEEE Transactions on Information Theory, vol. 52, no. 2, pp. 489–509, 2006.
[13]
Z.-P. Liang, “Spatiotemporal imaging with partially separable functions,” in Proceedings of the 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro (ISBI '07), pp. 988–991, Arlington, Va, USA, April 2007.
[14]
X. Qu, D. Guo, B. Ning et al., “Undersampled MRI reconstruction with patch-based directional wavelets,” Magnetic Resonance Imaging, vol. 30, no. 7, pp. 964–977, 2012.
[15]
X. B. Qu, Y. K. Hou, F. Lam, D. Guo, J. H. Zhong, and Z. Chen, “Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator,” Medical Image Analysis, 2013.
[16]
M. Aharon, M. Elad, and A. Bruckstein, “K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation,” IEEE Transactions on Signal Processing, vol. 54, no. 11, pp. 4311–4322, 2006.
[17]
S. Ravishankar and Y. Bresler, “MR image reconstruction from highly undersampled k-space data by dictionary learning,” IEEE Transactions on Medical Imaging, vol. 30, no. 5, pp. 1028–1041, 2011.
[18]
Q. G. Liu, S. S. Wang, L. Ying, X. Peng, Y. J. Zhu, and D. Liang, “Adaptive dictionary learning in sparse gradient domain for image recovery,” IEEE Transactions on Image Processing, vol. 22, no. 12, pp. 4652–4663, 2013.
[19]
Q. G. Liu, S. S. Wang, K. Yang, J. H. Luo, Y. M. Zhu, and D. Liang, “Highly undersampled magnetic resonance imaging reconstruction using two-level Bregman method with dictionary updating,” IEEE Transactions on Medical Imaging, vol. 32, no. 7, pp. 1290–1301, 2013.
[20]
G. Yu, G. Sapiro, and S. Mallat, “Solving inverse problems with piecewise linear estimators: from gaussian mixture models to structured sparsity,” IEEE Transactions on Image Processing, vol. 21, no. 5, pp. 2481–2499, 2012.
[21]
D. Zoran and Y. Weiss, “From learning models of natural image patches to whole image restoration,” in Proceedings of the IEEE International Conference on Computer Vision (ICCV '11), pp. 479–486, Barcelona, Spain, November 2011.
[22]
W. Dong, L. Zhang, G. Shi, and X. Li, “Nonlocally centralized sparse representation for image restoration,” IEEE Transactions on Image Processing, vol. 22, no. 4, pp. 1620–1630, 2013.
[23]
I. Daubechies, M. Defrise, and C. de Mol, “An iterative thresholding algorithm for linear inverse problems with a sparsity constraint,” Communications on Pure and Applied Mathematics, vol. 57, no. 11, pp. 1413–1457, 2004.
[24]
K. Khare, C. J. Hardy, K. F. King, P. A. Turski, and L. Marinelli, “Accelerated MR imaging using compressive sensing with no free parameters,” Magnetic Resonance in Medicine, vol. 68, no. 5, pp. 1450–1457, 2012.
