Development and testing of a deep learning-based strategy for scar segmentation on CMR-LGE images.

Journal: Magma (New York, N.Y.)
PMID: 30460430

Abstract

OBJECTIVE: The aim of this paper is to investigate the use of fully convolutional neural networks (FCNNs) to segment scar tissue in the left ventricle from cardiac magnetic resonance with late gadolinium enhancement (CMR-LGE) images.

Authors

  • Sara Moccia
    Department of Electronics, Information, and Bioengineering, Politecnico di Milano, Milan, Italy; Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy. Electronic address: sara.moccia@iit.it.
  • Riccardo Banali
    Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy.
  • Chiara Martini
    Diagnostic Department, Azienda Ospedaliera-Universitaria di Parma, Parma, Italy.
  • Giuseppe Muscogiuri
    Clinical Cardiology Unit and Department of Cardiovascular Imaging, Centro Cardiologico Monzino IRCCS, Milan, Italy.
  • Gianluca Pontone
    Department of Cardiovascular Imaging, Centro Cardiologico Monzino IRCCS, Milan, Italy.
  • Mauro Pepi
    Clinical Cardiology Unit and Department of Cardiovascular Imaging, Centro Cardiologico Monzino IRCCS, Milan, Italy.
  • Enrico Gianluca Caiani
    Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy. enrico.caiani@polimi.it.

Keywords

External Resources

Popular Topics
Recent Journals