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

With the remarkable success of representation learning for predictionproblems, we have witnessed a rapid expansion of the use of machine learningand deep learning for the analysis of digital pathology and biopsy imagepatches. However, learning over patch-wise features using convolutional neuralnetworks limits the ability of the model to capture global contextualinformation and comprehensively model tissue composition. The phenotypical andtopological distribution of constituent histological entities play a criticalrole in tissue diagnosis. As such, graph data representations and deep learninghave attracted significant attention for encoding tissue representations, andcapturing intra- and inter- entity level interactions. In this review, weprovide a conceptual grounding for graph analytics in digital pathology,including entity-graph construction and graph architectures, and present theircurrent success for tumor localization and classification, tumor invasion andstaging, image retrieval, and survival prediction. We provide an overview ofthese methods in a systematic manner organized by the graph representation ofthe input image, scale, and organ on which they operate. We also outline thelimitations of existing techniques, and suggest potential future researchdirections in this domain.

A Survey on Graph-Based Deep Learning for Computational Histopathology