Fully Automated Segmentation of Connective Tissue Compartments for CT-Based Body Composition Analysis: A Deep Learning Approach.

Journal: Investigative radiology
Published Date: Jun 1, 2020

Abstract

OBJECTIVE: Body composition comprises prognostic information in patients with various malignancies and can be opportunistically determined from routine computed tomography (CT) scans. However, accurate assessment of patients with alterations, for example, due to ascites or anasarca, and accurate identification of intermuscular fat remain challenging. In this study, we aimed to develop a fully automated and highly accurate segmentation tool for connective tissue compartments from abdominal CT scans using the open-source Convolutional Neural Network (CNN) DeepMedic.

Authors

  • Sebastian Nowak
    From the Quantitative Imaging Lab, Department of Radiology.
  • Anton Faron
    Department of Radiology, University Hospital Bonn, Sigmund-Freud-Str. 25, 53127, Bonn, Germany. Anton.Faron@ukbonn.de.
  • Julian A Luetkens
    Department of Radiology, University Hospital Bonn, Sigmund-Freud-Str. 25, 53127, Bonn, Germany.
  • Helena L Geißler
    From the Quantitative Imaging Lab, Department of Radiology.
  • Michael Praktiknjo
    Department of Internal Medicine I, University of Bonn, Venusberg-Campus, Bonn, Germany.
  • Wolfgang Block
    From the Quantitative Imaging Lab, Department of Radiology.
  • Daniel Thomas
    From the Quantitative Imaging Lab, Department of Radiology.
  • Alois M Sprinkart
    From the Quantitative Imaging Lab, Department of Radiology.

Keywords

External Resources

Popular Topics
Recent Journals