Multi-channel auto-encoders for learning domain invariant representations enabling superior classification of histopathology images

Andrew Moyes, Richard Gault, Kun Zhang, Ji Ming, Danny Crookes, Jing Wang

Research output: Contribution to journalArticlepeer-review

11 Citations (Scopus)
113 Downloads (Pure)

Abstract

Domain shift is a problem commonly encountered when developing automated histopathology pipelines. The performance of machine learning models such as convolutional neural networks within automated histopathology pipelines is often diminished when applying them to novel data domains due to factors arising from differing staining and scanning protocols. The Dual-Channel Auto-Encoder (DCAE) model was previously shown to produce feature representations that are less sensitive to appearance variation introduced by different digital slide scanners. In this work, the Multi-Channel Auto-Encoder (MCAE) model is presented as an extension to DCAE which learns from more than two domains of data. Experimental results show that the MCAE model produces feature representations that are less sensitive to inter-domain variations than the comparative StaNoSA method when tested on a novel synthetic dataset. This was apparent when applying the MCAE, DCAE, and StaNoSA models to three different classification tasks from unseen domains. The results of this experiment show the MCAE model out performs the other models. These results show that the MCAE model is able to generalise better to novel data, including data from unseen domains, than existing approaches by actively learning normalised feature representations.

Original languageEnglish
Article number102640
Number of pages10
JournalMedical Image Analysis
Volume83
Early online date17 Oct 2022
DOIs
Publication statusPublished - Jan 2023

Keywords

  • Domain adaptation
  • Deep learning (DL)
  • histopathology
  • representation learning
  • computer vision

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Pathology and Forensic Medicine

Fingerprint

Dive into the research topics of 'Multi-channel auto-encoders for learning domain invariant representations enabling superior classification of histopathology images'. Together they form a unique fingerprint.

Cite this