Segmentation of the aorta in systolic phase from 4D flow MRI: multi-atlas vs. deep learning.

Journal: Magma (New York, N.Y.)
PMID: 36800143

Abstract

OBJECTIVE: In the management of the aortic aneurysm, 4D flow magnetic resonance Imaging provides valuable information for the computation of new biomarkers using computational fluid dynamics (CFD). However, accurate segmentation of the aorta is required. Thus, our objective is to evaluate the performance of two automatic segmentation methods on the calculation of aortic wall pressure.

Authors

  • Diana M Marin-Castrillon
    Imaging and Artificial Vision Laboratory, EA 7535, University of Burgundy, Dijon 21000, France.
  • Leonardo Geronzi
    University of Rome Tor Vergata, Rome, Italy.
  • Arnaud Boucher
    ImViA Laboratory, University of Burgundy, Dijon, France.
  • Siyu Lin
    Imaging and Artificial Vision Laboratory, EA 7535, University of Burgundy, Dijon 21000, France.
  • Marie-Catherine Morgant
    Imaging and Artificial Vision Laboratory, EA 7535, University of Burgundy, Dijon 21000, France; Department of cardiovascular and thoracic surgery, University Hospital of Dijon, Dijon 21000, France.
  • Alexandre Cochet
    Department of Nuclear Medicine, Centre Georges-François Leclerc, Dijon, France; LE2I UMR6306, Centre national de la recherche scientifique, Arts et Métiers, Université Bourgogne Franche-Comté, Dijon, France; MRI Unit, Centre Hospitalier Régional Universitaire, Hôpital François Mitterrand, Dijon, France.
  • Michel Rochette
    Simulation, Modelling and Engineering Software, Ansys Group, Montigny-le-Bretonneux, France.
  • Sarah Leclerc
  • Khalid Ambarki
    Siemens Healthcare SAS, Saint-Denis 93200, France.
  • Ning Jin
    National Medical Center for Major Public Health Events, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430000, China.
  • Ludwig Serge Aho
    Department of Epidemiology and Hygiene, University Hospital of Dijon, Dijon, France.
  • Alain Lalande
  • Olivier Bouchot
    Imaging and Artificial Vision Laboratory, EA 7535, University of Burgundy, Dijon 21000, France; Department of cardiovascular and thoracic surgery, University Hospital of Dijon, Dijon 21000, France.
  • Benoit Presles
    Imaging and Artificial Vision Laboratory, EA 7535, University of Burgundy, Dijon 21000, France. Electronic address: benoit.presles@u-bourgogne.fr.

Keywords

External Resources

Popular Topics
Recent Journals