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

Despite the success of deep neural networks in chest X-ray (CXR) diagnosis,supervised learning only allows the prediction of disease classes that wereseen during training. At inference, these networks cannot predict an unseendisease class. Incorporating a new class requires the collection of labeleddata, which is not a trivial task, especially for less frequently-occurringdiseases. As a result, it becomes inconceivable to build a model that candiagnose all possible disease classes. Here, we propose a multi-labelgeneralized zero shot learning (CXR-ML-GZSL) network that can simultaneouslypredict multiple seen and unseen diseases in CXR images. Given an input image,CXR-ML-GZSL learns a visual representation guided by the input's correspondingsemantics extracted from a rich medical text corpus. Towards this ambitiousgoal, we propose to map both visual and semantic modalities to a latent featurespace using a novel learning objective. The objective ensures that (i) the mostrelevant labels for the query image are ranked higher than irrelevant labels,(ii) the network learns a visual representation that is aligned with itssemantics in the latent feature space, and (iii) the mapped semantics preservetheir original inter-class representation. The network is end-to-end trainableand requires no independent pre-training for the offline feature extractor.Experiments on the NIH Chest X-ray dataset show that our network outperformstwo strong baselines in terms of recall, precision, f1 score, and area underthe receiver operating characteristic curve. Our code is publicly available at:https://github.com/nyuad-cai/CXR-ML-GZSL.git

Multi-Label Generalized Zero Shot Learning for the Classification of Disease in Chest Radiographs