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

Aortic stenosis (AS) is a degenerative valve condition that causessubstantial morbidity and mortality. This condition is under-diagnosed andunder-treated. In clinical practice, AS is diagnosed with expert review oftransthoracic echocardiography, which produces dozens of ultrasound images ofthe heart. Only some of these views show the aortic valve. To automatescreening for AS, deep networks must learn to mimic a human expert's ability toidentify views of the aortic valve then aggregate across these relevant imagesto produce a study-level diagnosis. We find previous approaches to AS detectionyield insufficient accuracy due to relying on inflexible averages acrossimages. We further find that off-the-shelf attention-based multiple instancelearning (MIL) performs poorly. We contribute a new end-to-end MIL approachwith two key methodological innovations. First, a supervised attentiontechnique guides the learned attention mechanism to favor relevant views.Second, a novel self-supervised pretraining strategy applies contrastivelearning on the representation of the whole study instead of individual imagesas commonly done in prior literature. Experiments on an open-access dataset andan external validation set show that our approach yields higher accuracy whilereducing model size.

Detecting Heart Disease from Multi-View Ultrasound Images via Supervised Attention Multiple Instance Learning