a_novel_method_for_unsupervised_scanner_invariance_using_a_dual_channel_auto_encoder_encoder_model_camera_ready.pdf (2.18 MB)
Download file

A novel method for unsupervised scanner-invariance with DCAE model

Download (2.18 MB)
conference contribution
posted on 02.10.2018, 09:15 by Andrew Moyes, Kun Zhang, Liping Wang, Ming Ji, Danny Crookes, Huiyu Zhou
Automated analysis of histopathology whole-slide images is impeded by the scannerdependent variance introduced in the slide scanning process. This work presents a novel dual-channel auto-encoder based model with a multi-component loss which learns a scanner-invariant representation of histopathology images. The learned representation can be used for a number of histopathology-related applications where images are captured from different scanners such as nuclei detection and cancer segmentation. The approach is validated on a set of lung tissue sub-images extracted from whole slide images. This method achieves a 50% improvement in SSIM score on tissue masks derived from the learned representation compared to related methods. To the best of the author’s knowledge, this is the first work which explicitly learns a scanner-invariant representation of histopathology images from multiple domains simultaneously without labelled data or expensive preprocessing techniques.

History

Citation

29th British Machine Vision Conference (BMVC), 2018

Author affiliation

/Organisation/COLLEGE OF SCIENCE AND ENGINEERING/Department of Informatics

Source

29th British Machine Vision Conference (BMVC) Newcastle

Version

AM (Accepted Manuscript)

Published in

29th British Machine Vision Conference (BMVC)

Acceptance date

06/07/2018

Copyright date

2018

Available date

02/10/2018

Publisher version

http://bmvc2018.org/contents/papers/0936.pdf

Temporal coverage: start date

03/09/2015

Temporal coverage: end date

06/09/2015

Language

en

Usage metrics

Categories

Keywords

Exports