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

Deep learning offers potential for various healthcare applications involvingthe human skull but requires extensive datasets of curated medical images. Toovercome this challenge, we propose SkullGAN, a generative adversarial network(GAN), to create large datasets of synthetic skull CT slices, reducing relianceon real images and accelerating the integration of machine learning intohealthcare. In our method, CT slices of 38 subjects were fed to SkullGAN, aneural network comprising over 200 million parameters. The synthetic skullimages generated were evaluated based on three quantitative radiologicalfeatures: skull density ratio (SDR), mean thickness, and mean intensity. Theywere further analyzed using t-distributed stochastic neighbor embedding (t-SNE)and by applying the SkullGAN discriminator as a classifier. The results showedthat SkullGAN-generated images demonstrated similar key quantitativeradiological features to real skulls. Further definitive analysis wasundertaken by applying the discriminator of SkullGAN, where the SkullGANdiscriminator classified 56.5% of a test set of real skull images and 55.9% ofthe SkullGAN-generated images as reals (the theoretical optimum being 50%),demonstrating that the SkullGAN-generated skull set is indistinguishable fromthe real skull set - within the limits of our nonlinear classifier. Therefore,SkullGAN makes it possible to generate large numbers of synthetic skull CTsegments, necessary for training neural networks for medical applicationsinvolving the human skull. This mitigates challenges associated with preparinglarge, high-quality training datasets, such as access, capital, time, and theneed for domain expertise.

SkullGAN: Synthetic Skull CT Generation with Generative Adversarial Networks