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

Nuclei classification provides valuable information for histopathology imageanalysis. However, the large variations in the appearance of different nucleitypes cause difficulties in identifying nuclei. Most neural network basedmethods are affected by the local receptive field of convolutions, and pay lessattention to the spatial distribution of nuclei or the irregular contour shapeof a nucleus. In this paper, we first propose a novel polygon-structure featurelearning mechanism that transforms a nucleus contour into a sequence of pointssampled in order, and employ a recurrent neural network that aggregates thesequential change in distance between key points to obtain learnable shapefeatures. Next, we convert a histopathology image into a graph structure withnuclei as nodes, and build a graph neural network to embed the spatialdistribution of nuclei into their representations. To capture the correlationsbetween the categories of nuclei and their surrounding tissue patterns, wefurther introduce edge features that are defined as the background texturesbetween adjacent nuclei. Lastly, we integrate both polygon and graph structurelearning mechanisms into a whole framework that can extract intra andinter-nucleus structural characteristics for nuclei classification.Experimental results show that the proposed framework achieves significantimprovements compared to the state-of-the-art methods.

Structure Embedded Nucleus Classification for Histopathology Images