medpy.features.intensity.local_mean_gauss

medpy.features.intensity.local_mean_gauss(image, sigma=5, voxelspacing=None, mask=slice(None, None, None))

Takes a simple or multi-spectral image and returns the approximate mean over a small region around each voxel. A multi-spectral image must be supplied as a list or tuple of its spectra.

Optionally a binary mask can be supplied to select the voxels for which the feature should be extracted.

For this feature a Gaussian smoothing filter is applied to the image / each spectrum and then the resulting intensity values returned. Another name for this function would be weighted local mean.

Parameters:

imagearray_like or list/tuple of array_like

A single image or a list/tuple of images (for multi-spectral case).

sigmanumber or sequence of numbers

Standard deviation for Gaussian kernel. The standard deviations of the Gaussian filter are given for each axis as a sequence, or as a single number, in which case it is equal for all axes. Note that the voxel spacing of the image is taken into account, the given values are treated as mm.

voxelspacingsequence of floats

The side-length of each voxel.

maskarray_like

A binary mask for the image.

Returns:

local_mean_gaussndarray

The weighted mean intensities over a region around each voxel.