Deep-learning model for prenatal congenital heart disease screening generalizes to community setting and outperforms clinical detection.

Journal: Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology
Published Date:

Abstract

OBJECTIVES: Despite nearly universal prenatal ultrasound screening programs, congenital heart defects (CHD) are still missed, which may result in severe morbidity or even death. Deep machine learning (DL) can automate image recognition from ultrasound. The main aim of this study was to assess the performance of a previously developed DL model, trained on images from a tertiary center, using fetal ultrasound images obtained during the second-trimester standard anomaly scan in a low-risk population. A secondary aim was to compare initial screening diagnosis, which made use of live imaging at the point-of-care, with diagnosis by clinicians evaluating only stored images.

Authors

  • C Athalye
    Division of Cardiology, Department of Medicine, University of California, San Francisco, San Francisco, CA, USA.
  • A van Nisselrooij
    Department of Obstetrics, Division of Fetal Medicine, Leiden University Medical Center, Leiden, The Netherlands.
  • S Rizvi
    Division of Cardiology, Department of Medicine, University of California, San Francisco, San Francisco, CA, USA.
  • M C Haak
    Department of Obstetrics, Division of Fetal Medicine, Leiden University Medical Center, Leiden, The Netherlands.
  • A J Moon-Grady
    Department of Pediatrics, Division of Cardiology, University of California, San Francisco, San Francisco, CA, USA.
  • R Arnaout
    Division of Cardiology, Department of Medicine, University of California, San Francisco, San Francisco, CA, USA.