Hello. I am looking for already existing tool that can help me to denoise brain mri images with nonlocal means filter. Are there any suggestions. Primarily, I use SPM12, but any other opportunities are also welcomed. Thank you in advanced.
Hi @ChrisTall , welcome to Neurostars!
This type of denoising is available through the SPM toolbox CAT
Denoising
We also use two noise reduction methods to make data processing, and the tissue segmentation in particular, more robust against noise. The first method is a spatial-adaptive Non-Local Means (SANLM) denoising filter and removes noise while maintaining edges (Manjon et al., 2010) and is implemented as a pre-processing step. The second method is a classical Markov Random Field (MRF) approach, which includes spatial information from adjacent voxels in the segmentation estimation (Rajapakse et al., 1997) and is part of the AMAP segmentation. The strength of the filters is automatically determined by estimating the residual noise in the image or can be set manually.
so you want to blur but preserve edges, essentially?
if so, you could also try AFNI’s 3danisosmooth, it works fast, well and with multiple options.
there are also non-local means denoising in the ants ecosystem, see ants, antsR or antspy for example in antspy: ants.utils.denoise_image.denoise_image()
I just try to repeat the “” recipe" from a paper and see how it works on my dataset. I am trying to enhance the images for further segmentation.