An Optimized Blockwise Nonlocal Means Denoising Filter for 3-D Magnetic Resonance Images

By Pierrick Coupé, Pierre Yger, S. Prima, P. Hellier, Charles Kervrann, C. Barillot. IEEE Transactions on Medical Imaging, 2008

1,201 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/d37203cabf15a176d2d99617960af5348e4f9282

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

MIND: Modality independent neighbourhood descriptor for multi-modal deformable registration (2012, neutral): “in D’Agostino et al. (2003), 536 Glocker et al.”
Objective Evaluation of Multiple Sclerosis Lesion Segmentation using a Data Management and Processing Infrastructure (2018, neutral): “• Denoising of each modality using the non local means algorithm [36]”
From Heuristic Optimization to Dictionary Learning: A Review and Comprehensive Comparison of Image Denoising Algorithms (2014, methodology): “2) Improvement of Quantitative and Qualitative Results: Tuning the smoothing parameters was proposed in [16].”
A supervised patch-based approach for human brain labeling (2011, positive): “As suggested in [9], it is possible to speed-up the algorithm by considering a subset of the image domain with the constraint that there is at least one label estimate for each voxel.”
Review of automatic segmentation methods of multiple sclerosis white matter lesions on conventional magnetic resonance imaging (2013, methodology): “Several noise reduction methods in the literature (Bao and Zhang, 2003; Coupé et al., 2008; Gerig et al., 1992) have been applied to MR data from patients with MS.”
Denoising of Dynamic Contrast-Enhanced MR Images Using Dynamic Nonlocal Means (2010, methodology): “Methods to address this issue include the selective comparison of similarity windows [ 32 ], [38] and Laplacian Pyramids [39].”
Cortical thickness and central surface estimation (2013, methodology): “…388) for SPM8 5 (Ashburner and Friston, 2005) (re- 192 vision 4290) for segmentation of all T1 images, which includes an 193 optimized Rician non-local mean (ORNLM) (Coupe et al., 2008) and 194 a Gaussian Hidden Markov Random Field (GHMRF) (Cuadra et al., 195 2005) filter for noise reduction (NR).”
Image Denoising Methods. A New Nonlocal Principle (2010, neutral): “Improvements or adaptations of NL-means have been proposed in cryon microscopy [29], fluorescence microscopy [9], magnetic resonance imaging (MRI) [61], [26], [91], [68], multispectral MRI [62], [12], and diffusion tensor MRI (DT-MRI) [90].”
Diffusion Weighted Image Denoising Using Overcomplete Local PCA (2013, methodology): “This method is an adaptation of Optimized blockwise NLM method [40] to deal with Rician noise.”
A survey on the magnetic resonance image denoising methods (2014, methodology): “The optimized blockwise nonlocal mean filtering method [29], Bhattacharyya coefficient (BC) and mutual information (MI) are used as the performance metrics.”
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.”
Medical image processing on the GPU - Past, present and future (2013, background): “…algorithms include anisotropic diffusion (Perona and Malik, 1990; Weickert, 1998), bilateral filtering (Tomasi and Manduchi, 1998; Elad, 2002), adaptive filtering (Knutsson et al., 1983; Granlund and Knutsson, 1995; Westin et al., 2001) and non-local means (Buades et al., 2005; Coupe et al., 2008).”
Nonlocal Transform-Domain Filter for Volumetric Data Denoising and Reconstruction (2013, methodology): “The OB-NLM3D, OB-NLM3D-WM, ODCT3D, and PRI-NLM3D algorithms exist in separate implementations developed for Gaussian-and Rician-distributed noise, thus we decorate their names with a subscript " N " (Gaussian) and " R " (Rician) to denote the noise distribution addressed by the specific algorithm im”
Group-Sparse Representation With Dictionary Learning for Medical Image Denoising and Fusion (2012, neutral): “Many denoising approaches have been proposed, such as adaptive filters [1]–[3], wavelet-based methods [4]–[6], total variation-based method [7], etc.”