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

Medical image segmentation is routinely performed to isolate regions ofinterest, such as organs and lesions. Currently, deep learning is the state ofthe art for automatic segmentation, but is usually limited by the need forsupervised training with large datasets that have been manually segmented bytrained clinicians. The goal of semi-superised and unsupervised imagesegmentation is to greatly reduce, or even eliminate, the need for trainingdata and therefore to minimze the burden on clinicians when trainingsegmentation models. To this end we introduce a novel network architecture forcapable of unsupervised and semi-supervised image segmentation calledTricycleGAN. This approach uses three generative models to learn translationsbetween medical images and segmentation maps using edge maps as an intermediatestep. Distinct from other approaches based on generative networks, TricycleGANrelies on shape priors rather than colour and texture priors. As such, it isparticularly well-suited for several domains of medical imaging, such asultrasound imaging, where commonly used visual cues may be absent. We presentexperiments with TricycleGAN on a clinical dataset of kidney ultrasound imagesand the benchmark ISIC 2018 skin lesion dataset.

TricycleGAN: Unsupervised Image Synthesis and Segmentation Based on Shape Priors