FatSegNet: A fully automated deep learning pipeline for adipose tissue segmentation on abdominal dixon MRI.

Journal: Magnetic resonance in medicine
Published Date: Oct 21, 2019

Abstract

PURPOSE: Introduce and validate a novel, fast, and fully automated deep learning pipeline (FatSegNet) to accurately identify, segment, and quantify visceral and subcutaneous adipose tissue (VAT and SAT) within a consistent, anatomically defined abdominal region on Dixon MRI scans.

Authors

  • Santiago Estrada
    Image Analysis, German Center for Neurodegenerative Diseases (DZNE), Bonn, Germany.
  • Ran Lu
    Population Health Sciences, German Center for Neurodegenerative Diseases (DZNE), Bonn, Germany.
  • Sailesh Conjeti
    Chair for Computer Aided Medical Procedures, Fakultät für Informatik, Technische Universität München, Germany. Electronic address: sailesh.conjeti@tum.de.
  • Ximena Orozco-Ruiz
    Population Health Sciences, German Center for Neurodegenerative Diseases (DZNE), Bonn, Germany.
  • Joana Panos-Willuhn
    Population Health Sciences, German Center for Neurodegenerative Diseases (DZNE), Bonn, Germany.
  • Monique M B Breteler
    Population Health Sciences, German Center for Neurodegenerative Diseases (DZNE), Bonn, Germany.
  • Martin Reuter
    Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA; Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA; German Centre for Neurodegenerative Diseases (DZNE), Department of Image Analysis, Bonn, Germany.

Keywords

External Resources

Popular Topics
Recent Journals