MRI denoising using Non-Local Means

By José Vicente Manjón, José Carbonell, Juan José Lull, Gracián García-Martí, Luis Martí-Bonmatí, Montserrat Robles. Medical Image Anal., 2008

602 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/d84fdab5de680193f154854c137b6c3cd256615f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

A survey on the magnetic resonance image denoising methods (2014, methodology): “UNLM [27] 29.”
Denoising of diffusion MRI using random matrix theory (2016, positive): “…similarity in terms of their structure, which is based on weighted averages of voxels, where the voxels (and weights) are selected by metric similarity of patches (Buades et al., 2005; Coupé et al., 2006; Manjón et al., 2008, 2010; Orchard et al., 2008; Rajan et al., 2011, 2012; Foi, 2011).”
Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator (2014, methodology): “Besides the image reconstruction, making use of the pattern redundancy also shows great advantages in denoising (Bao et al., 2013; Manjón et al., 2008, 2012) and super-resolution (Manjón et al., 2012).”
Denoising of Dynamic Contrast-Enhanced MR Images Using Dynamic Nonlocal Means (2010, methodology): “Several different levels of simulated Rician noise were imposed [ 34 ] on these images as shown in thefirst column of Table I. The MAV estimator was found to yield biased, although linearly related, estimates”
Denoising of 3D magnetic resonance images by using higher-order singular value decomposition (2015, methodology): “The NLM filter has been adapted to denoise MR images and demonstrated better performance than the above mentioned gradient and wavelet-based filters (Coupe et al., 2008; Manjon et al., 2008; Wiest-Daessle et al., 2008).”
Compressed Sensing MRI Reconstruction Using a Generative Adversarial Network With a Cyclic Loss (2017, methodology): “Many classical priors can be used for J ( s ) , such as Tikhonov regularization (IID Gaussian prior) [39], edge-preserving regularization [40], total variation (TV) [41], non-local mean ﬁlter (NLM) [42], wavelets [43], curvelets [44], etc.”
BEaST: Brain extraction based on nonlocal segmentation technique (2012, methodology): “A recent framework inspired by nonlocal means MRI denoising (Buades et al., 2005; Coupe et al., 2008; Manjon et al., 2008) has been introduced to achieve the label fusion segmentation task.”
Computer-Aided Detection and diagnosis for prostate cancer based on mono and multi-parametric MRI: A review (2015, background): “Briefly, a Rician distribution can be characterized as follows: in low-SI region (low SNR), it can be approximated with a Rayleigh distributionwhile in high-SI region (high SNR), it is similar to a Gaussian distribution [95].”
Group-Sparse Representation With Dictionary Learning for Medical Image Denoising and Fusion (2012, methodology): “Among the methods used in the experiments of the Gaussian noise, only the NLM can be implemented with bias subtraction for Rician noise.”
Rician Noise Removal by Non-Local Means Filtering for Low Signal-to-Noise Ratio MRI: Applications to DT-MRI (2008, neutral): “[19] have recently derived another formula to denoise Rician-corrupted data while removing the bias.”