A multi-stage 3D convolutional neural network algorithm for CT-based lung segment parcellation.

Journal: Journal of applied clinical medical physics
Published Date: Aug 1, 2025

Abstract

BACKGROUND: Current approaches to lung parcellation utilize established fissures between lobes to provide estimates of lobar volume. However, deep learning segment parcellation provides the ability to better assess regional heterogeneity in ventilation and perfusion.

Authors

  • Trishul Siddharthan
    Division of Pulmonary, Critical Care and Sleep Medicine, University of Miami (TS), USA. Electronic address: tsiddhar@miami.edu.
  • Zhoubing Xu
    Electrical Engineering, Vanderbilt University, Nashville, TN 37235, USA. Electronic address: zhoubing.xu@vanderbilt.edu.
  • Bruce Spottiswoode
    Siemens Medical Solutions USA, Inc., Knoxville, Tennessee.
  • Chris Schettino
    Department of Radiology, Miller School of Medicine, University of Miami, Miami, Florida, USA.
  • Yoel Siegel
    Department of Radiology, Miller School of Medicine, University of Miami, Miami, Florida, USA.
  • Michalis Georgiou
    Department of Nuclear Medicine, Miller School of Medicine, University of Miami, Miami, Florida, USA.
  • Thomas Eluvathingal
    Department of Nuclear Medicine, Miller School of Medicine, University of Miami, Miami, Florida, USA.
  • Bernhard Geiger
    Technology Excellence, Digital Technology & Innovation, Siemens Healthineers, Princeton, NJ, USA.
  • Sasa Grbic
  • Partha Gosh
    Siemens Medical Solutions USA, Inc., Malvern, Pennsylvania, USA.
  • Rachid Fahmi
    Department of Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio 44106.
  • Naresh Punjabi
    Division of Pulmonary, Critical Care and Sleep Medicine, University of Miami, Miami, Florida, USA.

Keywords

External Resources

Popular Topics
Recent Journals