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

Large amounts of unlabelled data are commonplace for many applications incomputational pathology, whereas labelled data is often expensive, both in timeand cost, to acquire. We investigate the performance of unsupervised andsupervised deep learning methods when few labelled data are available. Threemethods are compared: clustering autoencoder latent vectors (unsupervised), asingle layer classifier combined with a pre-trained autoencoder(semi-supervised), and a supervised CNN. We apply these methods on hematoxylinand eosin (H&E) stained prostatectomy images to classify tumour versusnon-tumour tissue. Results show that semi-/unsupervised methods have anadvantage over supervised learning when few labels are available. Additionally,we show that incorporating immunohistochemistry (IHC) stained data provides anincrease in performance over only using H&E.

Dealing with Label Scarcity in Computational Pathology: A Use Case in Prostate Cancer Classification