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

With the development of convolutional neural network, deep learning has shownits success for retinal disease detection from optical coherence tomography(OCT) images. However, deep learning often relies on large scale labelled datafor training, which is oftentimes challenging especially for disease with lowoccurrence. Moreover, a deep learning system trained from data-set with one ora few diseases is unable to detect other unseen diseases, which limits thepractical usage of the system in disease screening. To address the limitation,we propose a novel anomaly detection framework termed Sparsity-constrainedGenerative Adversarial Network (Sparse-GAN) for disease screening where onlyhealthy data are available in the training set. The contributions of Sparse-GANare two-folds: 1) The proposed Sparse-GAN predicts the anomalies in latentspace rather than image-level; 2) Sparse-GAN is constrained by a novel SparsityRegularization Net. Furthermore, in light of the role of lesions for diseasescreening, we present to leverage on an anomaly activation map to show theheatmap of lesions. We evaluate our proposed Sparse-GAN on a publicly availabledataset, and the results show that the proposed method outperforms thestate-of-the-art methods.

Sparse-GAN: Sparsity-constrained Generative Adversarial Network for Anomaly Detection in Retinal OCT Image