Automatic characterization of myocardial perfusion imaging polar maps employing deep learning and data augmentation.

Journal: Hellenic journal of nuclear medicine
Published Date:

Abstract

OBJECTIVE: To investigate a deep learning technique, more specifically state-of-the-art convolutional neural networks (CNN), for automatic characterization of polar maps derived from myocardial perfusion imaging (MPI) studies for the diagnosis of coronary artery disease.

Authors

  • Ioannis D Apostolopoulos
    Department of Medical Physics, School of Medicine, University of Patras, 26504, Patras, Greece. ece7216@upnet.gr.
  • Nikolaos D Papathanasiou
  • Trifon Spyridonidis
  • Dimitris J Apostolopoulos