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

While deep learning approaches have shown remarkable performance in manyimaging tasks, most of these methods rely on availability of large quantitiesof data. Medical image data, however, is scarce and fragmented. GenerativeAdversarial Networks (GANs) have recently been very effective in handling suchdatasets by generating more data. If the datasets are very small, however, GANscannot learn the data distribution properly, resulting in less diverse orlow-quality results. One such limited dataset is that for the concurrent gainof 19 and 20 chromosomes (19/20 co-gain), a mutation with positive prognosticvalue in Glioblastomas (GBM). In this paper, we detect imaging biomarkers forthe mutation to streamline the extensive and invasive prognosis pipeline. Sincethis mutation is relatively rare, i.e. small dataset, we propose a novelgenerative framework - the Sequential Attribute GEnerator (SAGE), thatgenerates detailed tumor imaging features while learning from a limiteddataset. Experiments show that not only does SAGE generate high quality tumorswhen compared to standard Deep Convolutional GAN (DC-GAN) and Wasserstein GANwith Gradient Penalty (WGAN-GP), it also captures the imaging biomarkersaccurately.

SAGE: Sequential Attribute Generator for Analyzing Glioblastomas using Limited Dataset