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/

Zendy Plus

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

Zendy Tools

Zendy Open

Our contribution is a unified cross-modality feature disentagling approachfor multi-domain image translation and multiple organ segmentation. Using CT asthe labeled source domain, our approach learns to segment multi-modal(T1-weighted and T2-weighted) MRI having no labeled data. Our approach uses avariational auto-encoder (VAE) to disentangle the image content from style. TheVAE constrains the style feature encoding to match a universal prior (Gaussian)that is assumed to span the styles of all the source and target modalities. Theextracted image style is converted into a latent style scaling code, whichmodulates the generator to produce multi-modality images according to thetarget domain code from the image content features. Finally, we introduce ajoint distribution matching discriminator that combines the translated imageswith task-relevant segmentation probability maps to further constrain andregularize image-to-image (I2I) translations. We performed extensivecomparisons to multiple state-of-the-art I2I translation and segmentationmethods. Our approach resulted in the lowest average multi-domain imagereconstruction error of 1.34$\pm$0.04. Our approach produced an average Dicesimilarity coefficient (DSC) of 0.85 for T1w and 0.90 for T2w MRI formulti-organ segmentation, which was highly comparable to a fully supervised MRImulti-organ segmentation network (DSC of 0.86 for T1w and 0.90 for T2w MRI).

Unified cross-modality feature disentangler for unsupervised multi-domain MRI abdomen organs segmentation