Automated Echocardiographic Quantification of Left Ventricular Ejection Fraction Without Volume Measurements Using a Machine Learning Algorithm Mimicking a Human Expert.

Journal: Circulation. Cardiovascular imaging
Published Date:

Abstract

BACKGROUND: Echocardiographic quantification of left ventricular (LV) ejection fraction (EF) relies on either manual or automated identification of endocardial boundaries followed by model-based calculation of end-systolic and end-diastolic LV volumes. Recent developments in artificial intelligence resulted in computer algorithms that allow near automated detection of endocardial boundaries and measurement of LV volumes and function. However, boundary identification is still prone to errors limiting accuracy in certain patients. We hypothesized that a fully automated machine learning algorithm could circumvent border detection and instead would estimate the degree of ventricular contraction, similar to a human expert trained on tens of thousands of images.

Authors

  • Federico M Asch
    MedStar Health Research Institute, Washington DC (F.M.A.).
  • Nicolas Poilvert
    Bay Labs Inc, San Francisco, CA (N.P., M.A., N.R., H.H., R.P.M.).
  • Theodore Abraham
    University of California, San Francisco, CA (T.A.).
  • Madeline Jankowski
    Northwestern Memorial Hospital, Chicago, IL (M.J.).
  • Jayne Cleve
    Duke University Medical Center, Chapel Hill, NC (J.C.).
  • Michael Adams
    Bay Labs Inc, San Francisco, CA (N.P., M.A., N.R., H.H., R.P.M.).
  • Nathanael Romano
    Bay Labs Inc, San Francisco, CA (N.P., M.A., N.R., H.H., R.P.M.).
  • Ha Hong
    Bay Labs Inc, San Francisco, CA (N.P., M.A., N.R., H.H., R.P.M.).
  • Victor Mor-Avi
    Cardiac Imaging Center, University of Chicago Medical Center, Chicago, Illinois.
  • Randolph P Martin
    Bay Labs Inc, San Francisco, CA (N.P., M.A., N.R., H.H., R.P.M.).
  • Roberto M Lang
    Cardiac Imaging Center, University of Chicago Medical Center, Chicago, Illinois.