Denoising AMP for MRI reconstruction: BM3D-AMP-MRI.

*(English)*Zbl 07097238Summary: There is a recurrent idea being promoted in the recent literature on iterative solvers for imaging problems, the idea being the use of an actual denoising step in each iteration. We give a brief review of some algorithms from the literature which utilize this idea, and we broadly label these algorithms as Iterative Denoising Regularization (IDR) algorithms. We extend the Denoising Approximate Message Passing (D-AMP) algorithm from this list to the magnetic resonance imaging (MRI) reconstruction problem. We utilize Block Matching 3D (BM3D) as the denoiser of choice for the introduced MRI reconstruction algorithm. The application of the denoiser for complex-valued data necessitates a special handling of the denoiser. The use of the adaptive and image-dependent BM3D image model prior together with D-AMP results in highly competitive MRI reconstruction performance.

Reviewer: Reviewer (Berlin)

##### MSC:

47A52 | Linear operators and ill-posed problems, regularization |

49M30 | Other numerical methods in calculus of variations (MSC2010) |

65J22 | Numerical solution to inverse problems in abstract spaces |

94A08 | Image processing (compression, reconstruction, etc.) in information and communication theory |

##### Keywords:

image reconstruction; magnetic resonance; message passing; block matching; compressed sensing; denoising
PDF
BibTeX
XML
Cite

\textit{E. M. Eksioglu} and \textit{A. K. Tanc}, SIAM J. Imaging Sci. 11, No. 3, 2090--2109 (2018; Zbl 07097238)

Full Text:
DOI

##### References:

[1] | S. H. Chan, X. Wang, and O. A. Elgendy, Plug-and-play ADMM for image restoration: Fixed-point convergence and applications, IEEE Trans. Comput. Imaging, 3 (2017), pp. 84–98, . |

[2] | P. Chatterjee and P. Milanfar, Is denoising dead?, IEEE Trans. Image Process., 19 (2010), pp. 895–911, . · Zbl 1371.94082 |

[3] | C. Chen and J. Huang, Exploiting the wavelet structure in compressed sensing MRI, Magnetic Resonance Imaging, 32 (2014), pp. 1377–1389, . |

[4] | S. Chen, C. Luo, B. Deng, Y. Qin, H. Wang, and Z. Zhuang, BM3D vector approximate message passing for radar coded-aperture imaging, in 2017 Progress in Electromagnetics Research Symposium - Fall (PIERS - FALL) (Singapore), IEEE, Washington, DC, 2017, pp. 2035–2038, . |

[5] | K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, Image denoising by sparse \(3\)-D transform-domain collaborative filtering, IEEE Trans. Image Process., 16 (2007), pp. 2080–2095, . |

[6] | A. Danielyan, V. Katkovnik, and K. Egiazarian, BM3D frames and variational image deblurring, IEEE Trans. Image Process., 21 (2012), pp. 1715–1728, . · Zbl 1373.94096 |

[7] | I. Daubechies, M. Defrise, and C. De Mol, An iterative thresholding algorithm for linear inverse problems with a sparsity constraint, Comm. Pure Appl. Math., 57 (2004), pp. 1413–1457, . · Zbl 1077.65055 |

[8] | D. L. Donoho, A. Maleki, and A. Montanari, Message-passing algorithms for compressed sensing, Proc. Natl. Acad. Sci. USA, 106 (2009), pp. 18914–18919, . |

[9] | M. J. Ehrhardt and M. M. Betcke, Multicontrast MRI reconstruction with structure-guided total variation, SIAM J. Imaging Sci., 9 (2016), pp. 1084–1106, . · Zbl 1346.47006 |

[10] | E. M. Eksioglu, Decoupled algorithm for MRI reconstruction using nonlocal block matching model: BM3D-MRI, J. Math. Imaging Vis., 56 (2016), pp. 430–440, . · Zbl 1386.68204 |

[11] | M. Elad, Why simple shrinkage is still relevant for redundant representations?, IEEE Trans. Inform. Theory, 52 (2006), pp. 5559–5569, . · Zbl 1309.94035 |

[12] | M. Elad, Sparse and Redundant Representations: From Theory to Applications in Signal and Image Processing, Springer, New York, 2010. · Zbl 1211.94001 |

[13] | B. K. Gunturk and X. Li, Image Restoration: Fundamentals and Advances, CRC Press, Boca Raton, FL, 2012. · Zbl 1252.68033 |

[14] | A. P. Harrison, Z. Xu, A. Pourmorteza, D. A. Bluemke, and D. J. Mollura, A multichannel block-matching denoising algorithm for spectral photon-counting CT images, Med. Phys., 44 (2017), pp. 2447–2452, . |

[15] | O. S. Jahromi, B. A. Francis, and R. H. Kwong, Relative information of multi-rate sensors, Inform. Fusion, 5 (2004), pp. 119–129, . |

[16] | J. Huang, S. Zhang, and D. Metaxas, Efficient MR image reconstruction for compressed MR imaging, Med. Image Anal., 15 (2011), pp. 670–679, . |

[17] | V. Katkovnik and K. Egiazarian, Sparse phase imaging based on complex domain nonlocal BM3D techniques, Digital Signal Process., 63 (2017), pp. 72–85, . |

[18] | V. Katkovnik, M. Ponomarenko, and K. Egiazarian, Sparse approximations in complex domain based on BM3D modeling, Signal Process., 141 (2017), pp. 96–108, . |

[19] | F. Li and T. Zeng, A universal variational framework for sparsity-based image inpainting, IEEE Trans. Image Process., 23 (2014), pp. 4242–4254, . · Zbl 1374.94201 |

[20] | F. Li and T. Zeng, A new algorithm framework for image inpainting in transform domain, SIAM J. Imaging Sci., 9 (2016), pp. 24–51, . · Zbl 1352.68274 |

[21] | L. Liu, Z. Xie, and C. Yang, A novel iterative thresholding algorithm based on plug-and-play priors for compressive sampling, Future Internet, 9 (2017), 24, . |

[22] | S. Liu, J. Cao, H. Liu, X. Shen, K. Zhang, and P. Wang, MRI reconstruction using a joint constraint in patch-based total variational framework, J. Vis. Commun. Image Represent., 46 (2017), pp. 150–164, . |

[23] | M. Lustig, D. Donoho, and J. Pauly, Sparse MRI: The application of compressed sensing for rapid MR imaging, Magnetic Resonance Med., 58 (2007), pp. 1182–1195, . |

[24] | J. Ma and L. Ping, Orthogonal AMP, IEEE Access, 5 (2017), pp. 2020–2033, . |

[25] | A. Maleki, Approximate Message Passing Algorithms for Compressed Sensing, Ph.D. thesis, Stanford University, Stanford, CA, 2011. |

[26] | C. A. Metzler, A. Maleki, and R. G. Baraniuk, BM3D-PRGAMP: Compressive phase retrieval based on BM3D denoising, in Proceedings of the IEEE International Conference on Image Processing (ICIP), IEEE, Washington, DC, 2016, pp. 2504–2508, . |

[27] | C. A. Metzler, A. Maleki, and R. G. Baraniuk, From denoising to compressed sensing, IEEE Trans. Inform. Theory, 62 (2016), pp. 5117–5144, . · Zbl 1359.94137 |

[28] | A. Perelli and M. E. Davies, Compressive computed tomography image reconstruction with denoising message passing algorithms, in Proceedings of the 23rd European Signal Processing Conference (EUSIPCO), IEEE, Washington, DC, 2015, pp. 2806–2810, . |

[29] | J. G. Proakis and D. K. Manolakis, Digital Signal Processing: Principles, Algorithms and Applications, Pearson, Upper Saddle River, NJ, 2006. |

[30] | X. Qu, Y. Hou, F. Lam, D. Guo, J. Zhong, and Z. Chen, Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator, Med. Image Anal., 18 (2014), pp. 843–856, . |

[31] | S. Ramani, T. Blu, and M. Unser, Monte-Carlo SURE: A black-box optimization of regularization parameters for general denoising algorithms, IEEE Trans. Image Process., 17 (2008), pp. 1540–1554, . |

[32] | S. Ramani, X. Wang, L. Fu, and M. Lexa, Denoising-based accelerated statistical iterative reconstruction for X-ray CT, in Proceedings of the 4th International Conference on Image Formation in X-Ray Computed Tomography, Bamberg, Germany, 2016, pp. 395–398. |

[33] | S. Rangan, P. Schniter, and A. Fletcher, On the convergence of approximate message passing with arbitrary matrices, in Proceedings of the IEEE International Symposium on Information Theory, IEEE, Washington, DC, 2014, pp. 236–240, . |

[34] | S. Rangan, P. Schniter, and A. K. Fletcher, Vector approximate message passing, in Proceedings of the IEEE International Symposium on Information Theory (ISIT), IEEE, Washington, DC, 2017, pp. 1588–1592, . |

[35] | S. Rangan, P. Schniter, E. Riegler, A. K. Fletcher, and V. Cevher, Fixed points of generalized approximate message passing with arbitrary matrices, IEEE Trans. Inform. Theory, 62 (2016), pp. 7464–7474, . · Zbl 1359.94158 |

[36] | M. Rizkinia, T. Baba, K. Shirai, and M. Okuda, Local spectral component decomposition for multi-channel image denoising, IEEE Trans. Image Process., 25 (2016), pp. 3208–3218, . · Zbl 1408.94559 |

[37] | Y. Romano, M. Elad, and P. Milanfar, The little engine that could: Regularization by denoising (RED), SIAM J. Imaging Sci., 10 (2017), pp. 1804–1844, . · Zbl 1401.62101 |

[38] | S. Sreehari, S. V. Venkatakrishnan, B. Wohlberg, G. T. Buzzard, L. F. Drummy, J. P. Simmons, and C. A. Bouman, Plug-and-play priors for bright field electron tomography and sparse interpolation, IEEE Trans. Comput. Imaging, 2 (2016), pp. 408–423, . |

[39] | H. Talebi and P. Milanfar, Asymptotic performance of global denoising, SIAM J. Imaging Sci., 9 (2016), pp. 665–683, . · Zbl 1347.94010 |

[40] | J. Tan, Y. Ma, and D. Baron, Compressive imaging via approximate message passing with image denoising, IEEE Trans. Signal Process., 63 (2015), pp. 2085–2092, . · Zbl 1394.94016 |

[41] | S. V. Venkatakrishnan, L. F. Drummy, M. Jackson, M. D. Graef, J. Simmons, and C. A. Bouman, Model-based iterative reconstruction for bright-field electron tomography, IEEE Trans. Comput. Imaging, 1 (2015), pp. 1–15, . |

[42] | J. Vila, P. Schniter, S. Rangan, F. Krzakala, and L. Zdeborov, Adaptive damping and mean removal for the generalized approximate message passing algorithm, in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, Washington, DC, 2015, pp. 2021–2025, . |

[43] | Y.-W. Wen, M. K. Ng, and W.-K. Ching, Iterative algorithms based on decoupling of deblurring and denoising for image restoration, SIAM J. Sci. Comput., 30 (2008), pp. 2655–2674, . · Zbl 1172.94333 |

[44] | M. Zibulevsky and M. Elad, L1-L2 optimization in signal and image processing, IEEE Signal Process. Mag., 27 (2010), pp. 76–88, . |

This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.