NGLDM

class zrad.radiomics.ngldm.NGLDM(aggr_dim, slice_weight=False, slice_median=False)

Neighbouring grey level dependence matrix features.

NGLDM features count neighbouring voxels that depend on the centre voxel’s discretized grey level. They describe local homogeneity, dependence counts, and grey-level emphasis patterns.

Parameters:

• aggr_dim ({"2D", "2.5D", "3D"}) – Spatial dimensionality used to count neighbouring dependencies.

• slice_weight (bool, default=False) – Weight 2D slice-wise averages by slice ROI voxel count.

• slice_median (bool, default=False) – Aggregate 2D slice-wise values by median instead of mean.

Methods

calculate_features(discretized_image_array)	Calculate NGLDM features for a prepared discretized intensity array.
get_feature_names()	Return the NGLDM feature names produced by this calculator.
get_params()	Return the configuration parameters of this NGLDM calculator.

NGLDM.calculate_features(discretized_image_array)

Calculate NGLDM features for a prepared discretized intensity array.

Parameters:

discretized_image_array (numpy.ndarray) – Prepared discretized intensity array with voxels outside the ROI set to NaN.

Returns:

Mapping of NGLDM feature names to calculated values.

Return type:

dict

NGLDM.get_feature_names()

Return the NGLDM feature names produced by this calculator.

Returns:

Feature names defined for the NGLDM family.

Return type:

list of str

NGLDM.get_params()

Return the configuration parameters of this NGLDM calculator.

Returns:

Parameter names mapped to their configured values.

Return type:

dict