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

Digital pathology tasks have benefited greatly from modern deep learningalgorithms. However, their need for large quantities of annotated data has beenidentified as a key challenge. This need for data can be countered by usingunsupervised learning in situations where data are abundant but access toannotations is limited. Feature representations learned from unannotated datausing contrastive predictive coding (CPC) have been shown to enable classifiersto obtain state of the art performance from relatively small amounts ofannotated computer vision data. We present a modification to the CPC frameworkfor use with digital pathology patches. This is achieved by introducing analternative mask for building the latent context and using a multi-directionalPixelCNN autoregressor. To demonstrate our proposed method we learn featurerepresentations from the Patch Camelyon histology dataset. We show that ourproposed modification can yield improved deep classification of histologypatches.

Unsupervised Representation Learning from Pathology Images with Multi-directional Contrastive Predictive Coding