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 models tend to underperform in the presence of domain shifts.Domain transfer has recently emerged as a promising approach wherein imagesexhibiting a domain shift are transformed into other domains for augmentationor adaptation. However, with the absence of paired and annotated images, modelsmerely learned by adversarial loss and cycle consistency loss could result inpoor consistency of anatomy structures during the translation. Additionally,the complexity of learning multi-domain transfer could significantly increasewith the number of target domains and source images. In this paper, we proposea multi-domain transfer network, named MDT-Net, to address the limitationsabove through perceptual supervision. Specifically, our model consists of asingle encoder-decoder network and multiple domain-specific transfer modules todisentangle feature representations of the anatomy content and domain variance.Owing to this architecture, the model could significantly reduce the complexitywhen the translation is conducted among multiple domains. To demonstrate theperformance of our method, we evaluate our model qualitatively andquantitatively on RETOUCH, an OCT dataset comprising scans from three differentscanner devices (domains). Furthermore, we take the transfer results asadditional training data for fluid segmentation to prove the advantage of ourmodel indirectly, i.e., in the task of data adaptation and augmentation.Experimental results show that our method could bring universal improvement inthese segmentation tasks, which demonstrates the effectiveness and efficiencyof MDT-Net in multi-domain transfer.

MDT-Net: Multi-domain Transfer by Perceptual Supervision for Unpaired Images in OCT Scan