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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Content-based histopathological image retrieval (CBHIR) has become popular inrecent years in the domain of histopathological image analysis. CBHIR systemsprovide auxiliary diagnosis information for pathologists by searching for andreturning regions that are contently similar to the region of interest (ROI)from a pre-established database. While, it is challenging and yet significantin clinical applications to retrieve diagnostically relevant regions from adatabase that consists of histopathological whole slide images (WSIs) for aquery ROI. In this paper, we propose a novel framework for regions retrievalfrom WSI-database based on hierarchical graph convolutional networks (GCNs) andHash technique. Compared to the present CBHIR framework, the structuralinformation of WSI is preserved through graph embedding of GCNs, which makesthe retrieval framework more sensitive to regions that are similar in tissuedistribution. Moreover, benefited from the hierarchical GCN structures, theproposed framework has good scalability for both the size and shape variationof ROIs. It allows the pathologist defining query regions using free curvesaccording to the appearance of tissue. Thirdly, the retrieval is achieved basedon Hash technique, which ensures the framework is efficient and therebyadequate for practical large-scale WSI-database. The proposed method wasvalidated on two public datasets for histopathological WSI analysis andcompared to the state-of-the-art methods. The proposed method achieved meanaverage precision above 0.857 on the ACDC-LungHP dataset and above 0.864 on theCamelyon16 dataset in the irregular region retrieval tasks, which are superiorto the state-of-the-art methods. The average retrieval time from a databasewithin 120 WSIs is 0.802 ms.

Histopathology WSI Encoding based on GCNs for Scalable and Efficient Retrieval of Diagnostically Relevant Regions