Robust fine-grained echocardiographic view classification with supervised contrastive learning.

Preshen Naidoo¹, Patricia Fernandes², Nasim Dadashi Serej³, Catherine C Stowell⁴, Charlotte H Manisty⁵, Darrel P Francis⁶, Massoud Zolgharni⁷

¹Translational Healthcare Research Centre, University of West London, UK. Electronic address: preshen.naidoo@uwl.ac.uk.

²Translational Healthcare Research Centre, University of West London, UK. Electronic address: patricia.fernandes@uwl.ac.uk.

³Translational Healthcare Research Centre, University of West London, UK. Electronic address: nasim.dadashiserej@uwl.ac.uk.

⁴National Heart and Lung Institute, Imperial College London, UK. Electronic address: c.stowell@imperial.ac.uk.

⁵Barts Heart Centre and University College London, UK. Electronic address: c.manisty@ucl.ac.uk.

⁶National Heart and Lung Institute, Imperial College London, UK. Electronic address: d.francis@imperial.ac.uk.

⁷Translational Healthcare Research Centre, University of West London, UK; National Heart and Lung Institute, Imperial College London, UK. Electronic address: massoud.zolgharni@uwl.ac.uk.

PubMed DOI

Abstract

Accurate classification of echocardiographic views is fundamental for automated cardiac analysis. However, clinical practice relies on a large, heterogeneous set of fine-grained acquisitions that introduce substantial inter-observer variability. Existing studies have primarily focused on limited view sets, often collapsing specialised views into broad categories, which limits their clinical releva…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.