Gaussian filter - ORMIR-XCT

A Gaussian filter is an image-smoothing filter that reduces noise and small intensity variations by replacing each pixel or voxel with a weighted average of its neighbors, where closer neighbors receive higher weights according to a Gaussian (bell-shaped) distribution.

Function¶

To use the Gaussian filter combined with a fixed threshold, use the following commands:

from ormir_xct.core.segmentation.gauss_seg import gauss_seg

gauss_seg(
    input_image,
    lower_threshold,
    upper_threshold,
    value_in_range,
    value_outside_range,
    sigma,
    support,
    use_image_spacing)

Input settings¶

HR-pQCT

PCD-CT

µCT

input_image: Gray value input image
lower_threshold: Lower threshold for binarization
upper_threshold: Upper threshold for binarization
value_in_range: Value assigned to voxels inside the threshold range. Default = 127
value_outside_range: Value assigned to voxels inside the threshold range. Default = 0
sigma: Gaussian sigma. Default = 0.5
support: Half-width of the Gaussian kernel in voxels. Default = 1.0
use_image_spacing: Whether sigma is interpreted in physical units. Default = False

Further information about the function and its inputs can be found here (link to the API coming soon!)

Examples and workflows¶

HR-pQCT

PCD-CT

µCT

Examples of how to use the Gaussian filter:

Workflows that include the Gaussian filter:

Gaussian based segmentation

Citation¶

HR-pQCT

PCD-CT

µCT

If you use this function, please cite it as follows:

We used the Gaussian filter as implemented in ORMIR-XCT ().