Laboratory of Mathematics in Imaging
3D Slicer License
Yes
Brigham and Women's Hospital
NITRC
Fast Nonlocal Means for MRI denoising
MacOS, Microsoft, Linux, Other UNIX-like
Yes
C++
This is a fast and robust implementation of the popular Nonlocal Means for MRI-Rician denoising. It works by computing the non-local weights based on distances in a features space comprising the local mean value and gradients of the image.
It can reach an acceleration factor of 20x over the original implementation, with an improved performance for medium-low SNR images.
We use a bias correction step for Rician noise based on the well-known Conventional Approach.
This software can be compiled either as a Slicer module or a stand-alone:
http://www.nitrc.org/snapshots.php?group_id=518
For diffusion MRI volumes, see also: http://www.nitrc.org/projects/jalmmse_dwi
Key words: nonlocal (non-local) means, NLM, C++, ITK
2013-10-24
5 - Production/Stable/Mature
Whole package with source code, pre-compiled binaries, Matlab/Octave code, and test data
2013-10-24
5 - Production/Stable/Mature
Beta 1.0 for Windows only (MinGW compilation)
2013-9-29
5 - Production/Stable/Mature
Matlab code v1.1
2013-9-28
5 - Production/Stable/Mature
Matlab code
2013-2-09
5 - Production/Stable/Mature
Beta 1.0
Fast Nonlocal Means for MRI denoising
Filtering, Quality Metrics, Intensity Non-uniformity Correction, Artifact Removal, 5 - Production/Stable/Mature, MR, Other Environment, Console (Text Based), End Users, 3D Slicer License, English, MacOS, Microsoft, Linux, Other UNIX-like, C++, NIfTI-1, ANALYZE, Nrrd, Other Format, MINC
http://www.nitrc.org/projects/unlmeans/, http://www.nitrc.org/projects/unlmeans/