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

Convolutional neural networks can be trained to perform histology slideclassification using weak annotations with multiple instance learning (MIL).However, given the paucity of labeled histology data, direct application of MILcan easily suffer from overfitting and the network is unable to learn richfeature representations due to the weak supervisory signal. We propose toovercome such limitations with a two-stage semi-supervised approach thatcombines the power of data-efficient self-supervised feature learning viacontrastive predictive coding (CPC) and the interpretability and flexibility ofregularized attention-based MIL. We apply our two-stage CPC + MILsemi-supervised pipeline to the binary classification of breast cancerhistology images. Across five random splits, we report state-of-the-artperformance with a mean validation accuracy of 95% and an area under the ROCcurve of 0.968. We further evaluate the quality of features learned via CPCrelative to simple transfer learning and show that strong classificationperformance using CPC features can be efficiently leveraged under the MILframework even with the feature encoder frozen.

Semi-Supervised Histology Classification using Deep Multiple Instance Learning and Contrastive Predictive Coding