eICAB: A novel deep learning pipeline for Circle of Willis multiclass segmentation and analysis.

Journal: NeuroImage
Published Date: Oct 15, 2022

Abstract

BACKGROUND: The accurate segmentation, labeling and quantification of cerebral blood vessels on MR imaging is important for basic and clinical research, yet results are not generalizable, and often require user intervention. New methods are needed to automate this process.

Authors

  • Félix Dumais
    Department of Nuclear Medicine and Radiobiology, Faculty of Medicine and Health Science, Université de Sherbrooke, 3001 12e Avenue N, Sherbrooke, Québec J1H 5H3, Canada. Electronic address: felix.dumais@usherbrooke.ca.
  • Marco Perez Caceres
    Department of Nuclear Medicine and Radiobiology, Faculty of Medicine and Health Science, Université de Sherbrooke, 3001 12e Avenue N, Sherbrooke, Québec J1H 5H3, Canada.
  • Félix Janelle
    Department of Nuclear Medicine and Radiobiology, Faculty of Medicine and Health Science, Université de Sherbrooke, 3001 12e Avenue N, Sherbrooke, Québec J1H 5H3, Canada.
  • Kassem Seifeldine
    Department of Nuclear Medicine and Radiobiology, Faculty of Medicine and Health Science, Université de Sherbrooke, 3001 12e Avenue N, Sherbrooke, Québec J1H 5H3, Canada.
  • Noémie Arès-Bruneau
    Department of Medecine, Université de Sherbrooke, Sherbrooke, Québec, Canada.
  • Jose Gutierrez
    Department of Neurology, College of Physicians and Surgeons, Columbia University, New York, NY, USA.
  • Christian Bocti
    Université de Sherbrooke, Sherbrooke, QC.
  • Kevin Whittingstall
    Department of Radiology, Université de Sherbrooke, Sherbrooke, Québec, Canada.

Keywords

External Resources

Popular Topics
Recent Journals