An Optimized LMMSE Based Method for 3D MRI Denoising
- 6 August 2014
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 12 (4) , 861-870
Abstract
Post-acquisition denoising of magnetic resonance (MR) images is an important step to improve any quantitative measurement of the acquired data. In this paper, assuming a Rician noise model, a new filtering method based on the linear minimum mean square error (LMMSE) estimation is introduced, which employs the self-similarity property of the MR data to restore the noise-less signal. This method takes into account the structural characteristics of images and the Bayesian mean square error (Bmse) of the estimator to address the denoising problem. In general, a twofold data processing approach is developed; first, the noisy MR data is processed using a patch-based L2-norm similarity measure to provide the primary set of samples required for the estimation process. Afterwards, the Bmse of the estimator is derived as the optimization function to analyze the pre-selected samples and minimize the error between the estimated and the underlying signal. Compared to the LMMSE method and also its recently proposed SNR-adapted realization (SNLMMSE), the optimized way of choosing the samples together with the automatic adjustment of the filtering parameters lead to a more robust estimation performance with our approach. Experimental results show the competitive performance of the proposed method in comparison with related state-of-the-art methods.Keywords
This publication has 42 references indexed in Scilit:
- An MRI denoising method using image data redundancy and local SNR estimationMagnetic Resonance Imaging, 2013
- A modified Rician LMMSE estimator for the restoration of magnitude MR imagesOptik, 2013
- Kernel regression based feature extraction for 3D MR image denoisingMedical Image Analysis, 2011
- Maximum likelihood estimation-based denoising of magnetic resonance images using restricted local neighborhoodsPhysics in Medicine & Biology, 2011
- Quasi-Monte Carlo Estimation Approach for Denoising MRI Data Based on Regional StatisticsIEEE Transactions on Biomedical Engineering, 2011
- A Nonlocal Maximum Likelihood Estimation Method for Rician Noise Reduction in MR ImagesIEEE Transactions on Medical Imaging, 2008
- Weighted Averaging for Denoising With Overcomplete DictionariesIEEE Transactions on Image Processing, 2007
- Adaptive principal components and image denoising2004
- Maximum likelihood estimation of signal amplitude and noise variance from MR dataMagnetic Resonance in Medicine, 2004
- Maximum-likelihood estimation of Rician distribution parametersIEEE Transactions on Medical Imaging, 1998