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

This study explores the use of the Dirichlet Variational Autoencoder (DirVAE)for learning disentangled latent representations of chest X-ray (CXR) images.Our working hypothesis is that distributional sparsity, as facilitated by theDirichlet prior, will encourage disentangled feature learning for the complextask of multi-label classification of CXR images. The DirVAE is trained usingCXR images from the CheXpert database, and the predictive capacity ofmulti-modal latent representations learned by DirVAE models is investigatedthrough implementation of an auxiliary multi-label classification task, with aview to enforce separation of latent factors according to class-specificfeatures. The predictive performance and explainability of the latent spacelearned using the DirVAE were quantitatively and qualitatively assessed,respectively, and compared with a standard Gaussian prior-VAE (GVAE). Weintroduce a new approach for explainable multi-label classification in which weconduct gradient-guided latent traversals for each class of interest. Studyfindings indicate that the DirVAE is able to disentangle latent factors intoclass-specific visual features, a property not afforded by the GVAE, andachieve a marginal increase in predictive performance relative to GVAE. Wegenerate visual examples to show that our explainability method, when appliedto the trained DirVAE, is able to highlight regions in CXR images that areclinically relevant to the class(es) of interest and additionally, can identifycases where classification relies on spurious feature correlations.

Learning disentangled representations for explainable chest X-ray classification using Dirichlet VAEs