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

Semi-supervised image classification has shown substantial progress inlearning from limited labeled data, but recent advances remain largely untestedfor clinical applications. Motivated by the urgent need to improve timelydiagnosis of life-threatening heart conditions, especially aortic stenosis, wedevelop a benchmark dataset to assess semi-supervised approaches to two tasksrelevant to cardiac ultrasound (echocardiogram) interpretation: viewclassification and disease severity classification. We find that astate-of-the-art method called MixMatch achieves promising gains in heldoutaccuracy on both tasks, learning from a large volume of truly unlabeled imagesas well as a labeled set collected at great expense to achieve betterperformance than is possible with the labeled set alone. We further pursuepatient-level diagnosis prediction, which requires aggregating across hundredsof images of diverse view types, most of which are irrelevant, to make acoherent prediction. The best patient-level performance is achieved by newmethods that prioritize diagnosis predictions from images that are predicted tobe clinically-relevant views and transfer knowledge from the view task to thediagnosis task. We hope our released Tufts Medical Echocardiogram Dataset andevaluation framework inspire further improvements in multi-task semi-supervisedlearning for clinical applications.

A New Semi-supervised Learning Benchmark for Classifying View and Diagnosing Aortic Stenosis from Echocardiograms