Unsupervised Deep Learning for Stain Separation and Artifact Detection In Histopathology Images

Stain separation is an important pre-processing technique used to aid automated analysis of histopathology images. In this paper, we propose a novel, unsupervised deep learning method for stain separation (Hematoxylin and Eosin). This approach is inspired by Non-Negative Matrix Factorization (NMF) and decomposes an input image into a stain color matrix and a stain concentration matrix.In contrast to existing approaches, our method predicts stain color matrices at the pixel level rather than the image level, thus enabling implicit modelling of tissue-dependant interactions between stains. We demonstrate an 8.81% reduction in mean-squared error on a stain separation task measuring the similarity between predicted and actual hematoxylin images from a publicly available dataset of digitized tissue images. We also present a novel approach to artifact detection in histological images based on a constrained generative adversarial network which we demonstrate is able to detect a variety of artifact types with-out the use of labels.