volume | PIER Journals

Abstract

Compressive sensing (CS) is an effective method for reconstructing magnetic resonance imaging (MRI) image from under-determined linear system (ULS). However, how to improve the accuracy of MRI image reconstructed by CS is still a serious problem, especially in noisy conditions. To solve this problem, in this paper, we propose a novel approach, dubbed as regularized maximum entropy function (RMEF) minimization algorithm. Specifically, motivated by the entropy function in information theory, we propose a maximum entropy function (MEF) to approximate L_q-norm (0 < q < 1) as sparsity promoting objectives, and then the regularization mechanism for improving the de-noising performance is adopted. Combining the above two ideas, a new objective function of RMEF method is proposed, and the global minimum is iteratively solved. We further analyze the convergence to verify the robustness of the RMEF algorithm. Experiments demonstrate the state-of-the-art performances of the proposed RMEF algorithm and show that the RMEF achieves higher PSNR and SSIM than other widely-adopted methods in MRI image recovery.

1. Donoho, D. L., "Compressed sensing," IEEE Transactions on Information Theory, Vol. 4, 1289-1306, 2006. Google Scholar

2. Baraniuk, R. G., E. Candes, R. Nowak, and M. Vetterli, "Compressive sampling," IEEE Signal Processing Magazine, Vol. 25, 12-13, 2008. Google Scholar

3. Candés, E. J. and M. B.Wakin, "An introduction to compressive sampling," IEEE Signal Processing Magazine, Vol. 2, 21-30, 2008. Google Scholar

4. Huang, S. and T. D. Tran, "Sparse signal recovery via generalized entropy functions minimization," Eprint Arxiv, 2017. Google Scholar

5. Candés, E. J., "The restricted isometry property and its implications for compressed sensing," Comptes rendus-Math´ematique, Vol. 346, 589-592, 2008. Google Scholar

6. Natarajan, B. K., "Sparse approximate solutions to linear systems," SIAM Journal on Computing, Vol. 2, 227-234, 1995. Google Scholar

7. Wang, J., S. Kwon, P. Li, and B. Shim, "Recovery of sparse signals via generalized orthogonal matching pursuit: A new analysis," IEEE Transactions on Signal Processing, Vol. 64, 1076-1089, 2016. Google Scholar

8. Lee, J., G. T. Gil, and H. L. Yong, "Channel estimation via orthogonal matching pursuit for hybrid mimo systems in millimeter wave communications," IEEE Transactions on Communications, Vol. 64, 2370-2386, 2016. Google Scholar

9. Wen, J., Z. Zhou, J. Wang, X. Tang, and Q. Mo, "A sharp condition for exact support recovery with orthogonal matching pursuit," IEEE Transactions on Signal Processing, Vol. 6, 1370-1382, 2017. Google Scholar

10. Liu, J., C. Zhang, and C. Pan, "Priori-information hold subspace pursuit: A compressive sensing-based channel estimation for layer modulated TDS-OFDM," IEEE Trans. Broadcast., Vol. 99, 1-9, 2018. Google Scholar

11. Foucart, S. and M. J. Lai, "Sparsest solutions of underdetermined linear systems via L_p-minimization for 0 < p ≤ 1," Applied and Computational Harmonic Analysis, Vol. 3, 395-407, 2009. Google Scholar

12. Hurley, N. and S. Rickard, "Comparing measures of sparsity," IEEE Transactions on Information Theory, Vol. 10, 4723-4741, 2009. Google Scholar

13. Kose, K., O. Gunay, and A. E. Ceti, "Compressive sensing using the modified entropy functional," Digital Signal Processing, Vol. 24, 63-70, 2014. Google Scholar

14. Figueiredo, M. A. T., R. D. Nowak, and S. J.Wright, "Gradient projection for sparse reconstruction: Application to compressed sensing and other inverse problems," IEEE Journal of Selected Topics in Signal Processing, Vol. 1, 586-597, 2008. Google Scholar

15. Qiao, B., X. Zhang, C.Wang, H. Zhang, and X. Chen, "Sparse regularization for force identification using dictionaries," J. Sound Vib., Vol. 368, 71-86, 2016. Google Scholar

16. Wang, Y., S. Xie, and Z. Xie, "Fista-based papr reduction method for tone reservation’s OFDM system," IEEE Wireless Communications Letters, Vol. 7, No. 3, 300-303, 2017. Google Scholar

17. Metzler, C. A., A. Maleki, and R. G. Baraniuk, "From denoising to compressed sensing," IEEE Transactions on Information Theory, Vol. 62, 5117-5144, 2016. Google Scholar

18. Metzler, C. A., A. Mousavi, and R. G. Baraniuk, "Learned D-AMP: Principled neural network based compressive image recovery," Advances in Neural Information Processing Systems, 2017. Google Scholar

19. Chen, L. and Y. Gu, "On the null space constant for L_p minimization," IEEE Signal Processing Letters, Vol. 10, 1600-1603, 2015. Google Scholar

20. Wang, J. and B. Shim, "A simple proof of the mutual incoherence condition for orthogonal matching pursuit," Mathematics, 2011. Google Scholar

21. Barnett, A. G., J. Beyersmann, and A. Allignol, "The time-dependent bias and its effect on extra length of stay due to nosocomial infection," Value in Health, Vol. 2, 381-386, 2011. Google Scholar

22. Bolyog, B. and G. Pap, "On conditional least squares estimation for affine diffusions based on continuous time observations," Statistical Inference for Stochastic Processes, Vol. 4, 1-35, 2017. Google Scholar

23. Abgrall, R., D. Amsallem, and R. Crisonovan, "Robust model reduction of hyperbolic problems by L₁-norm minimization and dictionary approximation," Advanced Modeling and Simulation in Engineering Sciences, Vol. 1, 1, 2016. Google Scholar

24. Zhao, Y., Z. Liu, and Y. Wang, "Sparse coding algorithm with negentropy and weighted L₁-norm for signal reconstruction," Entropy, Vol. 1, 599, 2017. Google Scholar

25. Zheng, L., A. Maleki, H. Weng, X. Wang, and T. Long, "Does l_p-minimization outperform l₁-minimization," IEEE Transactions on Information Theory, Vol. 63, 6896-6935, 2017. Google Scholar

26. Saab, R, R. Chartrand, and O. Yilmaz, "Stable sparse approximations via nonconvex optimization," Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., 3885-3888, 2008. Google Scholar

27. Pant, J. K., W. Lu, and A. Antoniou, "Unconstrained regularized L_p norm based algorithm for the reconstruction of sparse signals," IEEE International Symposium on Circuits & Systems, 1740-1743, 2011. Google Scholar

28. Pant, J. K., W. Lu, and A. Antoniou, "New improved algorithms for compressive sensing based on L_p-norm," IEEE Trans. Circuits and Systems II: Express Briefs, Vol. 3, 198-202, 2014. Google Scholar

29. Boyd, S., N. Parikh, E. Chu, B. Peleato, and J. Eckstein, "Distributed optimization and statistical learning via the alternating direction method of multipliers," Found. Trends Mach. Learn., Vol. 1, 1-122, 2011. Google Scholar

30. Xie, Q., C. Ma, and C. Guo, "Image fusion based on the △¹-TV energy function," Entropy, Vol. 16, 6099-6115, 2014. Google Scholar

31. Du, S. and M. Chen, "A new smoothing modified three-term conjugate gradient method for L₁-norm minimization problem," Journal of Inequalities and Applications, Vol. 1, 105, 2018. Google Scholar

32. Lai, M. J., Y. Xu, and W. Yin, "Improved iteratively reweighted least squares for unconstrained smoothed L_q minimization," SIAM Journal on Numerical Analysis, Vol. 51, 927-957, 201. Google Scholar

33. Li, Q., S. Y. Liang, and Q. Li, "Incipient fault diagnosis of rolling bearings based on impulse-step impact dictionary and re-weighted minimizing nonconvex penalty L_q regular technique," Entropy, Vol. 19, 2017. Google Scholar

34. Wipf, D. and S. Nagarajan, "Iterative reweighted L₁ and L₂ methods for finding sparse solutions," IEEE Journal of Selected Topics in Signal Processing, Vol. 4, 317-329, 2013. Google Scholar

35. Ye, X., W. Zhu, and A. Zhang, "Sparse channel estimation of MIMO-OFDM systems with unconstrained smoothed L₀-norm-regularized least squares compressed sensing," EURASIP Journal on Wireless Communications and Networking, Vol. 1, 282, 2013. Google Scholar

36. Arias-Castro, E. and Y. C. Eldar, "Noise folding in compressed sensing," IEEE Signal Processing Letters, Vol. 18, 478-481, 2011. Google Scholar

37. Yang, X., Q. Cui, E. Dutkiewicz, and X. Huang, "Anti-noise-folding regularized subspace pursuit recovery algorithm for noisy sparse signals," Proceeding of the IEEE Wireless Communications and Networking Conference, 275-280, Istanbul, Turkey, April 6-9, 2014. Google Scholar

38. Lu, Z., "Iterative reweighted minimization methods for l_p regularized unconstrained nonlinear programming," Mathematical Programming, Vol. 147, 277-307, 2014. Google Scholar

39. Mourad, N., J. P. Reilly, and T. Kirubarajan, "Majorization-minimization for blind source separation of sparse sources," Signal Processing, Vol. 131, 120-133, 2017. Google Scholar

40. Oh, J. and N. Kwak, "Generalized mean for robust principal component analysis," Pattern Recognition, Vol. 54, 116-127, 2016. Google Scholar

41. Zhou, W., Y. B. Sun, Q. S. Liu, and W. U. Min, "L₀ group sparse RPCA model and algorithm for moving object detection," Acta Electronica Sinica, Vol. 44, No. 3, 627-632, 2016. Google Scholar

42. Xu, D., X. Gao, X. Fan, D. Zhao, and W. Gao, "ODD: An algorithm of online directional dictionary learning for sparse representation," Proceedings of the Pacific Rim Conference on Multimedia, Vol. 10736, 939-947, Harbin, China, September 28-29, 2017. Google Scholar

Dr. Huihui Yue

Dr. Xiangjun Yin