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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Convolutional neural networks (CNN) are now being widely used for classifyingand detecting pulmonary abnormalities in chest radiographs. Two complementarygeneralization properties of CNNs, translation invariance and equivariance, areparticularly useful in detecting manifested abnormalities associated withpulmonary disease, regardless of their spatial locations within the image.However, these properties also come with the loss of exact spatial informationand global relative positions of abnormalities detected in local regions.Global relative positions of such abnormalities may help distinguish similarconditions, such as COVID-19 and viral pneumonia. In such instances, a globalattention mechanism is needed, which CNNs do not support in their traditionalarchitectures that aim for generalization afforded by translation invarianceand equivariance. Vision Transformers provide a global attention mechanism, butlack translation invariance and equivariance, requiring significantly moretraining data samples to match generalization of CNNs. To address the loss ofspatial information and global relations between features, while preserving theinductive biases of CNNs, we present a novel technique that serves as anauxiliary attention mechanism to existing CNN architectures, in order toextract global correlations between salient features.

Pulmonary Disease Classification Using Globally Correlated Maximum Likelihood: an Auxiliary Attention mechanism for Convolutional Neural Networks