GCTI-SN is a Geometry-inspired Chemical-invariant and Tissue Invariant Stain Normalization method. The proposed GCTI-SN method corrects for illumination variation, stain chemical, and stain quantity variation in a unified framework by exploiting the underlying color vector space’s geometry. While existing stain normalization methods have demonstrated their results on a single tissue and stain type, GCTI-SN is benchmarked on three cancer datasets of three cell/tissue types prepared with two different stain chemicals. the utility and the efficacy of the GCTI-SN stain normalization method is demonstrated diagnostically in the application of breast cancer detection via a CNN-based classifier. The dataset used is publicly available at [TCIA]. The article is available [here], and the code is available [here]. The BibTeX citation of the article is as follows:
title = "GCTI-SN: Geometry-inspired chemical and tissue invariant stain normalization of microscopic medical images",
journal = "Medical Image Analysis",
volume = "65",
pages = "101788",
year = "2020",
issn = "1361-8415",
doi = "https://doi.org/10.1016/j.media.2020.101788",
url = "http://www.sciencedirect.com/science/article/pii/S1361841520301523",
author = "Anubha Gupta and Rahul Duggal and Shiv Gehlot and Ritu Gupta and Anvit Mangal and Lalit Kumar and Nisarg Thakkar and Devprakash Satpathy", }