AI-Echo: automatic interpretation of echocardiograms for congenital heart disease and beyond

Echocardiography is central to diagnosing and monitoring congenital heart disease, but expert interpretation and quantitative measurement are time-consuming and unevenly available. Our AI-Echo work develops deep learning methods that help clinicians identify congenital heart disease and automate clinically meaningful measurements from echocardiograms.

Study design and EchoFocus-CHD model architecture, from Lukyanenko et al., <i>Circulation</i> (2026).
Study design and EchoFocus-CHD model architecture, from Lukyanenko et al., Circulation (2026).

Code

  • EchoFocus

    • Selected Papers

    Automated Echocardiographic Detection of Congenital Heart Disease Using Artificial Intelligence
    Platon Lukyanenko, Sunil J. Ghelani, Yuting Yang, Bohan Jiang, Timothy A. Miller, David Harrild, Nao Sasaki, Francesca Sperotto, Danielle Sganga, John K. Triedman, Andrew J. Powell, Tal Geva, William G. La Cava, Joshua Mayourian (2026)
    Circulation
    ahajournals.org  |  PubMed  |  pdf
    Deep Learning-Based Automated Echocardiographic Measurements in Pediatric and Congenital Heart Disease
    Platon Lukyanenko, Sunil Ghelani, Yuting Yang, Bohan Jiang, Timothy Miller, Peter Higgins, Manouk Kirakosian, Kaitlyn Tracy, Janet Kane, David Harrild, John Triedman, Andrew J. Powell, Tal Geva, William La Cava, Joshua Mayourian (2026)
    Preprint
    medrxiv.org  |  pdf  |  code