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

In this work, we exploit the unsupervised domain adaptation problem forradiology image interpretation across domains. Specifically, we study how toadapt the disease recognition model from a labeled source domain to anunlabeled target domain, so as to reduce the effort of labeling each newdataset. To address the shortcoming of cross-domain, unpaired image-to-imagetranslation methods which typically ignore class-specific semantics, we proposea task-driven, discriminatively trained, cycle-consistent generativeadversarial network, termed TUNA-Net. It is able to preserve 1) low-leveldetails, 2) high-level semantic information and 3) mid-level featurerepresentation during the image-to-image translation process, to favor thetarget disease recognition task. The TUNA-Net framework is general and can bereadily adapted to other learning tasks. We evaluate the proposed framework ontwo public chest X-ray datasets for pneumonia recognition. The TUNA-Net modelcan adapt labeled adult chest X-rays in the source domain such that they appearas if they were drawn from pediatric X-rays in the unlabeled target domain,while preserving the disease semantics. Extensive experiments show thesuperiority of the proposed method as compared to state-of-the-art unsuperviseddomain adaptation approaches. Notably, TUNA-Net achieves an AUC of 96.3% forpediatric pneumonia classification, which is very close to that of thesupervised approach (98.1%), but without the need for labels on the targetdomain.

TUNA-Net: Task-oriented UNsupervised Adversarial Network for Disease Recognition in Cross-Domain Chest X-rays