Laplacian Eigenmaps Network-Based Nonlocal Means Method for MR Image Denoising

Hongkai Yu; Mingyue Ding; Xuming Zhang

doi:10.3390/s19132918

journal article Open Access Jul 01, 2019

Laplacian Eigenmaps Network-Based Nonlocal Means Method for MR Image Denoising

Hongkai Yu

Mingyue Ding

Xuming Zhang

Sensors Vol. 19 No. 13 pp. 2918 · MDPI AG

View at Publisher Save 10.3390/s19132918

Abstract

Magnetic resonance (MR) images are often corrupted by Rician noise which degrades the accuracy of image-based diagnosis tasks. The nonlocal means (NLM) method is a representative filter in denoising MR images due to its competitive denoising performance. However, the existing NLM methods usually exploit the gray-level information or hand-crafted features to evaluate the similarity between image patches, which is disadvantageous for preserving the image details while smoothing out noise. In this paper, an improved nonlocal means method is proposed for removing Rician noise in MR images by using the refined similarity measures. The proposed method firstly extracts the intrinsic features from the pre-denoised image using a shallow convolutional neural network named Laplacian eigenmaps network (LEPNet). Then, the extracted features are used for computing the similarity in the NLM method to produce the denoised image. Finally, the method noise of the denoised image is utilized to further improve the denoising performance. Specifically, the LEPNet model is composed of two cascaded convolutional layers and a nonlinear output layer, in which the Laplacian eigenmaps are employed to learn the filter bank in the convolutional layers and the Leaky Rectified Linear Unit activation function is used in the final output layer to output the nonlinear features. Due to the advantage of LEPNet in recovering the geometric structure of the manifold in the low-dimension space, the features extracted by this network can facilitate characterizing the self-similarity better than the existing NLM methods. Experiments have been performed on the BrainWeb phantom and the real images. Experimental results demonstrate that among several compared denoising methods, the proposed method can provide more effective noise removal and better details preservation in terms of human vision and such objective indexes as peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM).

Topics

No keywords indexed for this article. Browse by subject →

References

42

[1]

Ikram, S., Shah, J.A., Zubair, S., Qureshi, I.M., and Bilal, M. (2019). Improved reconstruction of MR scanned images by using a dictionary learning scheme. Sensors, 19. 10.3390/s19081918

[2]

Sharma, A., and Chaurasia, V. (2018). A review on magnetic resonance images denoising techniques. Mach. Intell. Signal Anal., 707–715. 10.1007/978-981-13-0923-6_60

[3]

Murase "An anisotropic diffusion method for denoising dynamic susceptibility contrast-enhanced magnetic resonance images" Phys. Med. Biol. (2001) 10.1088/0031-9155/46/10/313

[4]

Ghassan "Bilateral filtering of diffusion tensor magnetic resonance images" IEEE Trans. Image Process. (2007) 10.1109/tip.2007.904964

[5]

Liu "Generalized total variation-based MRI Rician denoising model with spatially adaptive regularization parameters" Magn. Reson. Imaging (2014) 10.1016/j.mri.2014.03.004

[6]

Izlian, Y.O., Francisco, J.G., and Alfonso, A. (2019). Local complexity estimation based filtering method in wavelet domain for magnetic resonance imaging denoising. Entropy, 21. 10.3390/e21040401

[7]

Pizurica "A review of wavelet denoising in MRI and ultrasound brain imaging" Curr. Med. Imaging Rev. (2006) 10.2174/157340506776930665

[8]

Zervakis "A class of robust entropic functionals for image restoration" IEEE Trans. Image Process. (1995) 10.1109/83.388078

[9]

Hemalata "NLM based magnetic resonance image denoising-A review" Biomed. Signal Process. Control (2019) 10.1016/j.bspc.2018.08.031

[10]

Buades, A., Coll, B., and Morel, J.M. (2005, January 20–25). A non-local algorithm for image denoising. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, USA.

[11]

Lull "MRI denoising using non-local means" Med. Image Anal. (2008) 10.1016/j.media.2008.02.004

[12]

Manjon "New methods for MRI denoising based on sparseness and self-similarity" Med. Image Anal. (2012) 10.1016/j.media.2011.04.003

[13]

Manjon "MRI noise estimation and denoising using non-local PCA" Med. Image Anal. (2015) 10.1016/j.media.2015.01.004

[14]

Maggioni "Nonlocal transform-domain filter for volumetric data denoising and reconstruction" IEEE Trans. Image Process. (2013) 10.1109/tip.2012.2210725

[15]

MRI‐based prostate cancer detection with high‐level representation and hierarchical classification

Yulian Zhu, Li Wang, Mingxia Liu et al.

Medical Physics 2017 10.1002/mp.12116

[16]

Schonberger, J.L., Hardmeier, H., Sattler, T., and Pollefeys, M. (2017, January 21–26). Comparative evaluation of hand-crafted and learned local features. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA. 10.1109/cvpr.2017.736

[17]

A Fast Learning Algorithm for Deep Belief Nets

Geoffrey E. Hinton, Simon Osindero, Yee-Whye Teh

Neural Computation 2006 10.1162/neco.2006.18.7.1527

[18]

Representation Learning: A Review and New Perspectives

Y. Bengio, A. Courville, P. Vincent

IEEE Transactions on Pattern Analysis and Machine... 2013 10.1109/tpami.2013.50

[19]

Li, C., Wang, Y., Zhang, X., Gao, H., Yang, Y., and Wang, J. (2019). Deep belief network for spectral-spatial classification of hyperspectral remote sensor data. Sensors, 19. 10.3390/s19010204

[20]

Zhao, F., Liu, Y., Huo, K., Zhang, S., and Zhang, Z. (2018). Radar HRRP target recognition based on stacked autoencoder and extreme learning machine. Sensors, 18. 10.3390/s18010173

[21]

Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising

Kai Zhang, Wangmeng Zuo, Yunjin Chen et al.

IEEE Transactions on Image Processing 2017 10.1109/tip.2017.2662206

[22]

Chan "PCANet: A simple deep learning baseline for image classification?" IEEE Trans. Image Process. (2015) 10.1109/tip.2015.2475625

[23]

Laplacian Eigenmaps for Dimensionality Reduction and Data Representation

Mikhail Belkin, Partha Niyogi

Neural Computation 2003 10.1162/089976603321780317

[24]

Postma "Dimensionality reduction: A comparative review" J. Mach. Learn. Res. (2009)

[25]

Daffertshofer "PCA in studying coordination and variability: A tutorial" Clin. Biomech. (2004) 10.1016/j.clinbiomech.2004.01.005

[26]

Borg "Modern multidimensional scaling: Theory and applications" J. Educ. Meas. (2006) 10.1111/j.1745-3984.2003.tb01108.x

[27]

Portillo-Portillo, J., Leyva, R., Sanchez, V., Sanchez-Perez, G., Perez-Meana, H., Olivares-Mercado, J., and Nakano-Miyatake, M. (2017). Cross view gait recognition using joint-direct linear discriminant analysis. Sensors, 17. 10.1007/s10489-017-1043-8

[28]

Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3–6). Imagenet classification with deep convolutional neural networks. Proceedings of the 25th International Conference on Neural Information Processing Systems, Lake Tahoe, NV, USA.

[29]

Andrew, L.M., Awni, Y.H., and Andrew, Y.N. (2013, January 30). Rectifier nonlinearities improve neural network acoustic models. Proceedings of the 30th International Conference on Machine Learning, Atlanta, GA, USA.

[30]

Basu, S., Fletcher, T., and Whitaker, R. (2006, January 1–6). Rician noise removal in diffusion tensor MRI. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Copenhagen, Denmark. 10.1007/11866565_15

[31]

Nowak "Wavelet-based rician noise removal for magnetic resonance imaging" IEEE Trans. Image Process. (1999) 10.1109/83.791966

[32]

A Threshold Selection Method from Gray-Level Histograms

Nobuyuki Otsu

IEEE Transactions on Systems, Man, and Cybernetics 1979 10.1109/tsmc.1979.4310076

[33]

(2018, September 10). Available online: https://wiki.cancerimagingarchive.net/display/Public/SPIE-AAPM-NCI+PROSTATEx+Challenges.

[34]

Litjens, G., Debats, O., Barentsz, J., Karssemeijer, N., and Huisman, H. (2018, September 10). ProstateX challenge data. Available online: https://doi.org/10.7937/K9TCIA.2017.MURS5CL.

[35]

Litjens "Computer-aided detection of prostate cancer in MRI" IEEE Trans. Med. Imaging (2014) 10.1109/tmi.2014.2303821

[36]

The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository

Kenneth Clark, Bruce Vendt, Kirk Smith et al.

Journal of Digital Imaging 2013 10.1007/s10278-013-9622-7

[37]

Kervrann "Local adaptivity to variable smoothness for exemplar-based image regularization and representation" Int. J. Comput. Vis. (2008) 10.1007/s11263-007-0096-2

[38]

Zhong "A new weight for nonlocal means denoising using method noise" IEEE Signal Process. Lett. (2012) 10.1109/lsp.2012.2205566

[39]

(2018, October 15). BrainWeb: Simulated Brain Database. Available online: http://brainweb.bic.mni.mcgill.ca/brainweb/.

[40]

(2018, October 15). The Whole Brain Atlas. Available online: http://www.med.harvard.edu/aanlib/home.html.

[41]

Coupe "3D Wavelet Sub-Bands Mixing for Image Denoising" Int. J. Biomed. Imaging (2008) 10.1155/2008/590183

[42]

Kala "Adaptive hexagonal fuzzy hybrid filter for Rician noise removal in MRI images" Neural Comput. Appl. (2018) 10.1007/s00521-017-2953-4

Metrics

24

Citations

42

References

Details

Published: Jul 01, 2019
Vol/Issue: 19(13)
Pages: 2918
License: View

Authors

H

Hongkai Yu

Department of Biomedical Engineering, School of Life Science and Technology, Ministry of Education Key Laboratory of Molecular Biophysics, Huazhong University of Science and Technology, No 1037, Luoyu Road, Wuhan 430074, China; Department of Mathematics and Statistics, Hubei University of Science and Technology, No 88, Xianning Road, Xianning 437000, China

M

Mingyue Ding

Department of Biomedical Engineering, School of Life Science and Technology, Ministry of Education Key Laboratory of Molecular Biophysics, Huazhong University of Science and Technology, No 1037, Luoyu Road, Wuhan 430074, China

X

Xuming Zhang

Department of Biomedical Engineering, School of Life Science and Technology, Ministry of Education Key Laboratory of Molecular Biophysics, Huazhong University of Science and Technology, No 1037, Luoyu Road, Wuhan 430074, China

Funding

National Natural Science Foundation of China Award: 61871440

National Key Research and Development Program of China Award: 2017YFB1303100

Cite This Article

Hongkai Yu, Mingyue Ding, Xuming Zhang (2019). Laplacian Eigenmaps Network-Based Nonlocal Means Method for MR Image Denoising. Sensors, 19(13), 2918. https://doi.org/10.3390/s19132918

Laplacian Eigenmaps Network-Based Nonlocal Means Method for MR Image Denoising

You May Also Like