MacenkoExtractor¶

tiatoolbox . tools . stainextract . MacenkoExtractor

class MacenkoExtractor(luminosity_threshold=0.8, angular_percentile=99)[source]¶

Macenko stain extractor.

Get the stain matrix as defined in:

Macenko, Marc, et al. “A method for normalizing histology slides for quantitative analysis.” 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro. IEEE, 2009.

This class contains code inspired by StainTools [https://github.com/Peter554/StainTools] written by Peter Byfield.

Parameters:

luminosity_threshold (float) – Threshold used for tissue area selection
angular_percentile (int) – Percentile of angular coordinates to be selected with respect to the principle, orthogonal eigenvectors.

Examples

>>> from tiatoolbox.tools.stainextract import MacenkoExtractor
>>> from tiatoolbox.utils import imread
>>> extractor = MacenkoExtractor()
>>> img = imread('path/to/image')
>>> stain_matrix = extractor.get_stain_matrix(img)

Initialize MacenkoExtractor.

Methods

get_stain_matrix

Stain matrix estimation.

get_stain_matrix(img)[source]¶

Stain matrix estimation.

Parameters:

img (numpy.ndarray) – Input image used for stain matrix estimation.
self (MacenkoExtractor)

Returns:

Estimated stain matrix.

Return type:

numpy.ndarray