Explicit and automatic ejection fraction assessment on 2D cardiac ultrasound with a deep learning-based approach.

Journal: Computers in biology and medicine
Published Date:

Abstract

BACKGROUND: Ejection fraction (EF) is a key parameter for assessing cardiovascular functions in cardiac ultrasound, but its manual assessment is time-consuming and subject to high inter and intra-observer variability. Deep learning-based methods have the potential to perform accurate fully automatic EF predictions but suffer from a lack of explainability and interpretability. This study proposes a fully automatic method to reliably and explicitly evaluate the biplane left ventricular EF on 2D echocardiography following the recommended modified Simpson's rule.

Authors

  • Olivier Moal
    DESKi, Bordeaux, France. Electronic address: olivier.moal@deski.io.
  • Emilie Roger
    DESKi, Bordeaux, France. Electronic address: emilie.roger@deski.io.
  • Alix Lamouroux
    DESKi, Bordeaux, France. Electronic address: alix.lamouroux@deski.io.
  • Chloe Younes
    DESKi, Bordeaux, France. Electronic address: chloe.younes.v@gmail.com.
  • Guillaume Bonnet
    Hôpital Cardiologique Haut Lévêque, CHU de Bordeaux, CIC 0005, Pessac, France. Electronic address: unbonnet@gmail.com.
  • Bertrand Moal
    DESKi, Bordeaux, France. Electronic address: bertrand.moal@deski.io.
  • Stephane Lafitte
    Hôpital Cardiologique Haut Lévêque, CHU de Bordeaux, CIC 0005, Pessac, France. Electronic address: stephane.lafitte@chu-bordeaux.fr.