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 Factorisation (NMF) and decomposes an input image into a stain colour matrix and a stain concentration matrix. In contrast to existing approaches, our method predicts stain colour 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 digitised 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 without the use of labels.
|Title of host publication||Medical Image Understanding and Analysis - 24th Annual Conference, MIUA 2020, Proceedings|
|Editors||Bartlomiej W. Papiez, Ana I.L. Namburete, Mohammad Yaqub, J. Alison Noble, Mohammad Yaqub|
|Number of pages||14|
|Publication status||Published - 08 Jul 2020|
|Event||24th Annual Conference on Medical Image Understanding and Analysis, MIUA 2020 - Oxford, United Kingdom|
Duration: 15 Jul 2020 → 17 Jul 2020
|Name||Communications in Computer and Information Science|
|Conference||24th Annual Conference on Medical Image Understanding and Analysis, MIUA 2020|
|Period||15/07/2020 → 17/07/2020|
Bibliographical noteFunding Information:
This work was financially supported by Invest NI, the Natural Science Foundation of Jiangsu Province, China under Grant No. BK20170443 and the Natural Science Foundation of the Higher Education Institutions of Jiangsu Province, China under Grant No. 17KJB520030.
© 2020, Springer Nature Switzerland AG.
Copyright 2020 Elsevier B.V., All rights reserved.
- Artifact detection
- Stain separation
ASJC Scopus subject areas
- Computer Science(all)