English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The examination of histopathology images is considered to be the goldstandard for the diagnosis and stratification of cancer patients. A keychallenge in the analysis of such images is their size, which can run into thegigapixels and can require tedious screening by clinicians. With the recentadvances in computational medicine, automatic tools have been proposed toassist clinicians in their everyday practice. Such tools typically processthese large images by slicing them into tiles that can then be encoded andutilized for different clinical models. In this study, we propose a novelgenerative framework that can learn powerful representations for such tiles bylearning to plausibly expand their visual field. In particular, we developed aprogressively grown generative model with the objective of visual fieldexpansion. Thus trained, our model learns to generate different tissue typeswith fine details, while simultaneously learning powerful representations thatcan be used for different clinical endpoints, all in a self-supervised way. Toevaluate the performance of our model, we conducted classification experimentson CAMELYON17 and CRC benchmark datasets, comparing favorably to otherself-supervised and pre-trained strategies that are commonly used in digitalpathology. Our code is available at https://github.com/jcboyd/cdpath21-gan.

Self-Supervised Representation Learning using Visual Field Expansion on Digital Pathology