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

The novel 2019 Coronavirus (COVID-19) infection has spread world widely andis currently a major healthcare challenge around the world. Chest ComputedTomography (CT) and X-ray images have been well recognized to be two effectivetechniques for clinical COVID-19 disease diagnoses. Due to faster imaging timeand considerably lower cost than CT, detecting COVID-19 in chest X-ray (CXR)images is preferred for efficient diagnosis, assessment and treatment. However,considering the similarity between COVID-19 and pneumonia, CXR samples withdeep features distributed near category boundaries are easily misclassified bythe hyper-planes learned from limited training data. Moreover, most existingapproaches for COVID-19 detection focus on the accuracy of prediction andoverlook the uncertainty estimation, which is particularly important whendealing with noisy datasets. To alleviate these concerns, we propose a noveldeep network named {\em RCoNet$^k_s$} for robust COVID-19 detection whichemploys {\em Deformable Mutual Information Maximization} (DeIM), {\em MixedHigh-order Moment Feature} (MHMF) and {\em Multi-expert Uncertainty-awareLearning} (MUL). With DeIM, the mutual information (MI) between input data andthe corresponding latent representations can be well estimated and maximized tocapture compact and disentangled representational characteristics. Meanwhile,MHMF can fully explore the benefits of using high-order statistics and extractdiscriminative features of complex distributions in medical imaging. Finally,MUL creates multiple parallel dropout networks for each CXR image to evaluateuncertainty and thus prevent performance degradation caused by the noise in thedata.

RCoNet: Deformable Mutual Information Maximization and High-order Uncertainty-aware Learning for Robust COVID-19 Detection