numpyradiomics.glszm#

numpyradiomics.glszm(image, mask, binWidth=25, levels=None, connectivity=None)[source]#

Compute 16 Pyradiomics-style GLSZM (Gray Level Size Zone Matrix) features.

GLSZM quantifies gray level zones in an image. A gray level zone is defined as a number of connected voxels that share the same gray level intensity.

Parameters:

  • image (np.ndarray) – 3D image array containing voxel intensities.

  • mask (np.ndarray) – 3D mask array (same shape as image), where non-zero values indicate the ROI.

  • binWidth (float, optional) – Width of bins for discretization. Default is 25.

  • levels (int, optional) – Number of levels for discretization. If None, calculated from binWidth.

  • connectivity (int, optional) – Connectivity kernel (e.g., 6, 18, 26 for 3D). Default is None (26-connected in 3D, 8-connected in 2D).

Returns:

Dictionary containing the 16 GLSZM features:

  • SmallAreaEmphasis: Measures the distribution of small zones.

  • LargeAreaEmphasis: Measures the distribution of large zone sizes.

  • GrayLevelNonUniformity: Measures the variability of gray-level values in the image.

  • GrayLevelNonUniformityNormalized: Normalized version of GLN.

  • ZoneSizeNonUniformity: Measures the variability of zone size values.

  • ZoneSizeNonUniformityNormalized: Normalized version of ZSN.

  • ZonePercentage: Measures the coarseness of the texture.

  • LowGrayLevelZoneEmphasis: Measures the distribution of lower gray-level values.

  • HighGrayLevelZoneEmphasis: Measures the distribution of higher gray-level values.

  • SmallAreaLowGrayLevelEmphasis: Emphasis on small zones with low gray levels.

  • SmallAreaHighGrayLevelEmphasis: Emphasis on small zones with high gray levels.

  • LargeAreaLowGrayLevelEmphasis: Emphasis on large zones with low gray levels.

  • LargeAreaHighGrayLevelEmphasis: Emphasis on large zones with high gray levels.

  • GrayLevelVariance: Variance of gray level intensities in the zones.

  • ZoneSizeVariance: Variance of zone size volumes.

  • ZoneEntropy: Uncertainty/Randomness in the distribution of zone sizes and gray levels.

Return type:

dict

Example

>>> import numpyradiomics as npr
>>> # Generate a noisy ellipsoid
>>> img, mask = npr.dro.noisy_ellipsoid(radii_mm=(15, 15, 15), intensity_range=(0, 100))
>>>
>>> # Compute GLSZM features
>>> feats = npr.glszm(img, mask, binWidth=10)
>>>
>>> print(f"ZonePercentage: {feats['ZonePercentage']:.4f}")
ZonePercentage: 0.8912
On this page

This Page