Utility of a Deep-Learning Algorithm to Guide Novices to Acquire Echocardiograms for Limited Diagnostic Use.

Journal: JAMA cardiology
Published Date: Jun 1, 2021

Abstract

IMPORTANCE: Artificial intelligence (AI) has been applied to analysis of medical imaging in recent years, but AI to guide the acquisition of ultrasonography images is a novel area of investigation. A novel deep-learning (DL) algorithm, trained on more than 5 million examples of the outcome of ultrasonographic probe movement on image quality, can provide real-time prescriptive guidance for novice operators to obtain limited diagnostic transthoracic echocardiographic images.

Authors

  • Akhil Narang
    Cardiac Imaging Center, University of Chicago Medical Center, Chicago, Illinois.
  • Richard Bae
    Division of Cardiology, Minneapolis Heart Institute, Minneapolis, Minnesota.
  • Ha Hong
    Bay Labs Inc, San Francisco, CA (N.P., M.A., N.R., H.H., R.P.M.).
  • Yngvil Thomas
    Caption Health, Brisbane, California.
  • Samuel Surette
    Caption Health Inc, San Francisco, CA (S.S., A.C., N.P., H.H., R.P.M.).
  • Charles Cadieu
    Caption Health, Brisbane, California.
  • Ali Chaudhry
    Caption Health Inc, San Francisco, CA (S.S., A.C., N.P., H.H., R.P.M.).
  • Randolph P Martin
    Bay Labs Inc, San Francisco, CA (N.P., M.A., N.R., H.H., R.P.M.).
  • Patrick M McCarthy
    Division of Cardiology Bluhm Cardiovascular InstituteNorthwestern University Chicago IL.
  • David S Rubenson
    Division of Cardiology, Scripps Health, San Diego, California.
  • Steven Goldstein
    MedStar Washington Hospital Center, DC (S.G., C.P.).
  • Stephen H Little
    Houston Methodist, Houston, Texas.
  • Roberto M Lang
    Cardiac Imaging Center, University of Chicago Medical Center, Chicago, Illinois.
  • Neil J Weissman
    MedStar Health Research Institute, Washington, DC.
  • James D Thomas
    Bluhm Cardiovascular Institute, Department of Cardiology, Northwestern University, Chicago, Illinois. Electronic address: Jthomas8@nm.org.

Keywords

External Resources

Popular Topics
Recent Journals