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

One of the leading causes of blindness is glaucoma, which is challenging todetect since it remains asymptomatic until the symptoms are severe. Thus,diagnosis is usually possible until the markers are easy to identify, i.e., thedamage has already occurred. Early identification of glaucoma is generally madebased on functional, structural, and clinical assessments. However, due to thenature of the disease, researchers still debate which markers qualify as aconsistent glaucoma metric. Deep learning methods have partially solved thisdilemma by bypassing the marker identification stage and analyzing high-levelinformation directly to classify the data. Although favorable, these methodsmake expert analysis difficult as they provide no insight into the modeldiscrimination process. In this paper, we overcome this using deep generativenetworks, a deep learning model that learns complicated, high-dimensionalprobability distributions. We train a Deep Feature consistent VariationalAutoencoder (DFC-VAE) to reconstruct optic disc images. We show that asmall-sized latent space obtained from the DFC-VAE can learn thehigh-dimensional glaucoma data distribution and provide discriminatory evidencebetween normal and glaucoma eyes. Latent representations of size as low as 128from our model got a 0.885 area under the receiver operating characteristiccurve when trained with Support Vector Classifier.

Assessing glaucoma in retinal fundus photographs using Deep Feature Consistent Variational Autoencoders