Global denoising for 3D MRI

Denoising is the primary preprocessing step before subsequent clinical diagnostic analysis of MRI data. Common patch-based denoising methods rely heavily on the degree of patch matching, which limits their performance by the necessity of finding sufficiently similar patches. In this paper, we propose a global filtering framework, in which each voxel is restored with information from the whole 3D image. This global filter is not restricted to any specific patchbased filter, as it is a low-rank approximation using the Nyström method combined with a low sampling rate and a kmeans clustering adaptive sampling scheme. Experiments demonstrate that this method utilizes information effectively from the whole image for denoising, and the framework can be applied on top of most patch-based methods to further improve the performance.

[1]  Katya Scheinberg,et al.  Efficient SVM Training Using Low-Rank Kernel Representations , 2002, J. Mach. Learn. Res..

[2]  Pierrick Coupé,et al.  An Optimized Blockwise Nonlocal Means Denoising Filter for 3-D Magnetic Resonance Images , 2008, IEEE Transactions on Medical Imaging.

[3]  A. Evans,et al.  MRI simulation-based evaluation of image-processing and classification methods , 1999, IEEE Transactions on Medical Imaging.

[4]  Peyman Milanfar,et al.  A Tour of Modern Image Filtering: New Insights and Methods, Both Practical and Theoretical , 2013, IEEE Signal Processing Magazine.

[5]  José V. Manjón,et al.  MRI denoising using Non-Local Means , 2008, Medical Image Anal..

[6]  Alessandro Foi,et al.  Noise estimation and removal in MR imaging: The variance-stabilization approach , 2011, 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[7]  Vikrant Bhateja,et al.  A Non-Local Means Filtering Algorithm for Restoration of Rician Distributed MRI , 2015 .

[8]  Jean-Michel Morel,et al.  A Review of Image Denoising Algorithms, with a New One , 2005, Multiscale Model. Simul..

[9]  Michael Elad,et al.  Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries , 2006, IEEE Transactions on Image Processing.

[10]  D. Shen,et al.  LRTV: MR Image Super-Resolution With Low-Rank and Total Variation Regularizations , 2015, IEEE Transactions on Medical Imaging.

[11]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[12]  Wufan Chen,et al.  Denoising Multi-Channel Images in Parallel MRI by Low Rank Matrix Decomposition , 2014, IEEE Transactions on Applied Superconductivity.

[13]  Ameet Talwalkar,et al.  Sampling Methods for the Nyström Method , 2012, J. Mach. Learn. Res..

[14]  Petros Drineas,et al.  Fast Monte Carlo Algorithms for Matrices II: Computing a Low-Rank Approximation to a Matrix , 2006, SIAM J. Comput..

[15]  S. D. Babacan,et al.  Denoising diffusion‐weighted magnitude MR images using rank and edge constraints , 2014, Magnetic resonance in medicine.

[16]  Ameet Talwalkar,et al.  Sampling Techniques for the Nystrom Method , 2009, AISTATS.

[17]  Xinyuan Zhang,et al.  Denoising of 3D magnetic resonance images by using higher-order singular value decomposition , 2015, Medical Image Anal..

[18]  Patrick J. Wolfe,et al.  On landmark selection and sampling in high-dimensional data analysis , 2009, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[19]  Minh N. Do,et al.  Denoising MR Spectroscopic Imaging Data With Low-Rank Approximations , 2013, IEEE Transactions on Biomedical Engineering.

[20]  D. L. Donoho,et al.  Compressed sensing , 2006, IEEE Trans. Inf. Theory.

[21]  Petros Drineas,et al.  On the Nyström Method for Approximating a Gram Matrix for Improved Kernel-Based Learning , 2005, J. Mach. Learn. Res..

[22]  D. Louis Collins,et al.  New methods for MRI denoising based on sparseness and self-similarity , 2012, Medical Image Anal..

[23]  Peyman Milanfar,et al.  Kernel Regression for Image Processing and Reconstruction , 2007, IEEE Transactions on Image Processing.

[24]  Suyash P. Awate,et al.  Feature-Preserving MRI Denoising: A Nonparametric Empirical Bayes Approach , 2007, IEEE Transactions on Medical Imaging.

[25]  Peyman Milanfar,et al.  Global Image Denoising , 2014, IEEE Transactions on Image Processing.

[26]  Carl-Fredrik Westin,et al.  Noise and Signal Estimation in Magnitude MRI and Rician Distributed Images: A LMMSE Approach , 2008, IEEE Transactions on Image Processing.

[27]  Allen Gersho,et al.  Vector quantization and signal compression , 1991, The Kluwer international series in engineering and computer science.

[28]  Peyman Milanfar,et al.  Symmetrizing Smoothing Filters , 2013, SIAM J. Imaging Sci..

[29]  Mathews Jacob,et al.  Accelerated Dynamic MRI Exploiting Sparsity and Low-Rank Structure: k-t SLR , 2011, IEEE Transactions on Medical Imaging.

[30]  Karen O. Egiazarian,et al.  Nonlocal Transform-Domain Filter for Volumetric Data Denoising and Reconstruction , 2013, IEEE Transactions on Image Processing.

[31]  Ivor W. Tsang,et al.  Improved Nyström low-rank approximation and error analysis , 2008, ICML '08.

[32]  Alessandro Foi,et al.  Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering , 2007, IEEE Transactions on Image Processing.

[33]  Ian R. Greenshields,et al.  A Nonlocal Maximum Likelihood Estimation Method for Rician Noise Reduction in MR Images , 2009, IEEE Transactions on Medical Imaging.

[34]  Jiliu Zhou,et al.  Nonlocal denoising using anisotropic structure tensor for 3D MRI. , 2013, Medical physics.

[35]  D. Louis Collins,et al.  Diffusion Weighted Image Denoising Using Overcomplete Local PCA , 2013, PloS one.

[36]  Bernhard Schölkopf,et al.  Sparse Greedy Matrix Approximation for Machine Learning , 2000, International Conference on Machine Learning.