Reducing inter-observer variability and interaction time of MR liver volumetry by combining automatic CNN-based liver segmentation and manual corrections.

Journal: PloS one
Published Date: May 20, 2019

Abstract

PURPOSE: To compare manual corrections of liver masks produced by a fully automatic segmentation method based on convolutional neural networks (CNN) with manual routine segmentations in MR images in terms of inter-observer variability and interaction time.

Authors

  • Grzegorz Chlebus
    Fraunhofer Institute for Medical Image Computing MEVIS, Bremen, Germany. grzegorz.chlebus@mevis.fraunhofer.de.
  • Hans Meine
    Fraunhofer Institute for Medical Image Computing MEVIS, Bremen, Germany.
  • Smita Thoduka
    Department of Radiology, Städtisches Klinikum Dresden, Dresden, Germany.
  • Nasreddin Abolmaali
    Department of Radiology, Städtisches Klinikum Dresden, Dresden, Germany.
  • Bram van Ginneken
    Diagnostic Image Analysis Group, Department of Radiology and Nuclear Medicine, Radboud University Medical Center, Nijmegen, The Netherlands; Fraunhofer Mevis, Bremen, Germany.
  • Horst Karl Hahn
    Fraunhofer Institute for Medical Image Computing MEVIS, Bremen, Germany.
  • Andrea Schenk
    Fraunhofer Institute for Medical Image Computing MEVIS, Bremen, Germany.

Keywords

External Resources

Popular Topics
Recent Journals