Texture enhanced generative adversarial network for stain normalisation in histopathology images

Cong Cong, Sidong Liu, Antonio Di Ieva, Maurice Pagnucco, Shlomo Berkovsky, Yang Song

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

Abstract

Digitised histopathology image analysis has drawn researchers’ attention over recent years. However, stain variation due to several factors can be a significant hurdle for the diagnosis process. Stain normalisation can be used as an effective method to address this issue but most existing methods require careful selection of a reference image. In this work, we propose a texture enhanced pix2pix generative adversarial network (TESGAN), which takes higher contrast hematoxylin components as input and includes a novel loss function to guide the generator to produce higher quality images without the need for reference images. We implement our method as a pre-processing approach for an isocitrate dehydrogenase (IDH) mutation status classification task. Evaluated on The Cancer Genome Atlas (TCGA) glioma cohorts, the proposed model achieves Area Under Curve (AUC) of 0.967, which substantially outperforms the current state-of the-art.
Original languageEnglish
Title of host publication2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)
Place of PublicationFrance
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages1949-1952
Number of pages4
ISBN (Electronic)9781665412469
ISBN (Print)9781665429474
DOIs
Publication statusPublished - 13 Apr 2021
Event18th IEEE International Symposium on Biomedical Imaging, ISBI 2021 - Nice, France
Duration: 13 Apr 202116 Apr 2021

Conference

Conference18th IEEE International Symposium on Biomedical Imaging, ISBI 2021
CountryFrance
CityNice
Period13/04/2116/04/21

Keywords

  • Conditional Generative Adversarial Networks
  • Content loss
  • IDH classification
  • Stain normalisation

Fingerprint

Dive into the research topics of 'Texture enhanced generative adversarial network for stain normalisation in histopathology images'. Together they form a unique fingerprint.

Cite this