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

Classifying the various shapes and attributes of a glioma cell nucleus iscrucial for diagnosis and understanding the disease. We investigate automatedclassification of glioma nuclear shapes and visual attributes usingConvolutional Neural Networks (CNNs) on pathology images of automaticallysegmented nuclei. We propose three methods that improve the performance of apreviously-developed semi-supervised CNN. First, we propose a method thatallows the CNN to focus on the most important part of an image- the image'scenter containing the nucleus. Second, we inject (concatenate) pre-extractedVGG features into an intermediate layer of our Semi-Supervised CNN so thatduring training, the CNN can learn a set of complementary features. Third, weseparate the losses of the two groups of target classes (nuclear shapes andattributes) into a single-label loss and a multi-label loss so that the priorknowledge of inter-label exclusiveness can be incorporated. On a dataset of2078 images, the proposed methods combined reduce the error rate of attributeand shape classification by 21.54% and 15.07% respectively compared to theexisting state-of-the-art method on the same dataset.

Center-Focusing Multi-task CNN with Injected Features for Classification of Glioma Nuclear Images