This page provides the code for the method described in:
Class-Agnostic Weighted Normalization of Staining in Histopathology Images Using a Spatially Constrained Mixture Model by Sobhan Shafiei, Amir Safarpoor, Ahad Jamalizadeh, and H. R. Tizhoosh
This study introduces a novel approach for stain normalization based on learning a mixture of multivariate skew-normal distributions for stain clustering and parameter estimation alongside a stain transformation technique. The proposed method, labeled “Class-Agnostic Weighted Normalization” (short CLAW normalization), has the ability to normalize a source image by learning the color distribution of both source and target images within an expectation-maximization framework
The code available here contains a MATLAB implementation of the model introduced in the paper. Please refer to the paper for more details regarding the choice of parameters for the model of interest or the datasets.
This code is for academic and research applications only. If you use any part of the code, please cite:
@ARTICLE{9086617, author={S. {Shafiei} and A. {Safarpoor} and A. {Jamalizadeh} and H. R. {Tizhoosh}}, journal={IEEE Transactions on Medical Imaging}, title={Class-Agnostic Weighted Normalization of Staining in Histopathology Images Using a Spatially Constrained Mixture Model}, year={2020}, volume={39}, number={11}, pages={3355-3366}, doi={10.1109/TMI.2020.2992108}
The images included in the demo file are from “Ensemble of classifiers and wavelet transformation for improved recognition of Fuhrman grading in clear-cell renal carcinoma” paper.
To Download Code/Data visit: https://github.com/RhazesLab/claw_stain_normalization