Abstract
Medical imaging techniques play a very important role in modern life. However, due to the technique limitation, the random noise often degrades the quality of acquired medical images, which seriously affects the medical image analysis. A denoising scheme that combines sparse dictionary learning with cluster ensemble is proposed in our paper, which exploits both the inherent self-similarity in images and sparsity of image patches. Firstly, construct image feature set by using steering kernel regression. Then, the effective cluster ensemble method is utilized to gain the class label of image feature set. Finally, for each cluster, an adaptive dictionary was trained by the sparse dictionary learning algorithm. The trained dictionary is more adaptive and stable, which is beneficial to improve the quality of recovered image. The experiment validates the superiorities of our proposed method and has a satisfactory speed.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Aharon M, Elad M, Bruckstein A (2006) k-svd: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans Signal Process 54(11):4311–4322
Binh NT, Khare A (2010) Adaptive complex wavelet technique for medical image denoising. IFMBE Proc 27:196C199
Buades A, Coll B, Morel J M (2005) Computer vision and pattern recognition. In: IEEE computer society conference on. IEEE 2005, p 60C65
Cai N, Zhou Y, Wang S, Weng XW (2016) Image denoising via patch-based adaptive Gaussian mixture prior method. Signal Image Video Process 10(6):993C999
Chatterjee P, Milanfar P (2009) Clustering-based denoising with locally learned dictionaries. IEEE Trans Image Process A Publ IEEE Signal Process Soc 18(7):1438–51
Do MN, Vetterli M (2005) The contourlet transform:an effcient directional multiresolution image representation. IEEE Trans Image Process A Publ IEEE Signal Process Soc 14(12):2091–2106
Drapaca CS (2009) A nonlinear total variation-based denoising method with two regularization parameters. IEEE Trans Biomed Eng 56(3):582–6
Elad M, Aharon M (2007) Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans Image Process A Publ IEEE Signal Process Soc 15(12):3736–45
Engan K, Aase SO, Hakon Husoy J (1999) Method of optimal directions for frame design. icassp. IEEE Comput Soc 5:2443–2446
Hadian A, Shahrivari S (2014) High performance parallel k-means clustering for disk-resident datasets on multi-core CPUs. J Supercomput 69(2):845–863
Irofti P (2016) Efficient dictionary learning implementation on the GPU using OpenCL. UPB Sci Bull Ser C Electr Eng 78(3):39–50
Kuncheva LI, Vetrov DP (2006) Evaluation of stability of k-means cluster ensembles with respect to random initialization. IEEE Trans Pattern Anal Mach Intell 28(11):1798–808
Li Q, Qian ZH, Sun Y, Wang X (2012) Medical CT image denoising method based on the correlation property of directional coefficients. Recent Adv Comput Sci Inf Eng 128:127–132
Li S, Yin H, Fang L (2012) Group-sparse representation with dictionary learning for medical image denoising and fusion. IEEE Trans. Biomed Eng 59(12):3450–9
Malik M, Ahsan F, Mohsin S (2016) Adaptive image denoising using cuckoo algorithm. Soft Comput 20:925
Meng Y (2012) Medical image denoising based on improved anisotropic diffusion. Adv Autom Robot 1:233–239
Phophalia A, Mitra SK, Rajwade AK (2013) Medical image denoising from similar patches derived by Rough Set. In: 2013 IEEE second international conference on, pp 586–591
Rabbani H, Nezafat R, Gazor S (2009) Wavelet-domain medical image denoising using bivariate laplacian mixture model. IEEE Trans Biomed Eng 56(12):2826–37
Rubinstein R, Zibulevsky M, Elad M (2010) Double sparsity: learning sparse dictionaries for sparse signal approximation. IEEE Trans Signal Process 58(3):1553–1564
Rubinstein R, Zibulevsky M, Elad M (2008) Effcient implementation of the k-svd algorithm using batch orthogonal matching pursuit. Technical report, CS Technion
Shechtman E, Irani M (2007) Matching Local Self-Similarities across Images and Videos. In: IEEE conference on computer vision and pattern recognition, pp 1–8
Takeda H, Farsiu S, Milanfar P (2007) Kernel regression for image processing and reconstruction. IEEE Trans Image Process A Publ IEEE Signal Process Soc 16(2):349–366
Yang AF, Lu M, Teng SH, Sun JX (2013) Local sparse representation for astronomical image denoising. J Central South Univ 20(10):2720–2727
Yue Y, Croitoru MM, Bidani A, Zwischenberger JB, Clark J Jr (2006) Nonlinear multiscale wavelet diffusion for speckle suppression and edge enhancement in ultrasound images. IEEE Trans Med Imaging 25(3):297–311
Zhang L, Zhou WD, Wu CL, Huo JT, Zou HS, Jiao LC (2009) Center matching scheme for k-means cluster ensembles. In: Proceedings of SPIE—the international society for optical engineering, pp 749614–749614-6
Acknowledgements
The authors would like to thank all those who have helped us during the writing of the paper and the anonymous reviewers for their constructive comments. This work was funded by the International Postdoctoral Exchange Fellowship Program 2013 by the Office of China Postdoctoral Council (No. 20130026), the China Postdoctoral Science Foundation Special funded project (No. 2012T50799) and the Open Research Fund of Key Laboratory of Spectral Imaging Technology by Chinese Academy of Sciences.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Additional information
Communicated by M. Anisetti.
Rights and permissions
About this article
Cite this article
Bai, J., Song, S., Fan, T. et al. Medical image denoising based on sparse dictionary learning and cluster ensemble. Soft Comput 22, 1467–1473 (2018). https://doi.org/10.1007/s00500-017-2853-7
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-017-2853-7