AngioPy Segmentation: An open-source, user-guided deep learning tool for coronary artery segmentation.

Journal: International journal of cardiology
PMID: 39341506

Abstract

BACKGROUND: Quantitative coronary angiography (QCA) typically employs traditional edge detection algorithms that often require manual correction. This has important implications for the accuracy of downstream 3D coronary reconstructions and computed haemodynamic indices (e.g. angiography-derived fractional flow reserve). We developed AngioPy, a deep-learning model for coronary segmentation that employs user-defined ground-truth points to boost performance and minimise manual correction. We compared its performance without correction with an established QCA system.

Authors

  • Thabo Mahendiran
    Cardiology Department, Lausanne University Center Hospital, Lausanne, Switzerland.
  • Dorina Thanou
    Chair of Mathematical Data Science and LTS4 laboratory, EPFL, Lausanne, Switzerland.
  • Ortal Senouf
    Chair of Mathematical Data Science and LTS4 laboratory, EPFL, Lausanne, Switzerland.
  • Yassine Jamaa
    Center for Imaging, EPFL, Lausanne, Switzerland.
  • Stephane Fournier
    Cardiology Department, Lausanne University Center Hospital, Lausanne, Switzerland stephane.fournier@chuv.ch emmanuel.abbe@epfl.ch.
  • Bernard De Bruyne
    Cardiovascular Center OLV Aalst, Belgium.
  • Emmanuel Abbe
    PACM and Department of EE, Princeton University, Princeton, NJ 08544, USA.
  • Olivier Muller
    Cardiology Department, Lausanne University Center Hospital, Lausanne, Switzerland.
  • Edward Andò
    Center for Imaging, EPFL, Lausanne, Switzerland.

Keywords

External Resources

Popular Topics
Recent Journals