Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem.

Journal: European radiology experimental
Published Date: Aug 20, 2020

Abstract

BACKGROUND: Automated segmentation of anatomical structures is a crucial step in image analysis. For lung segmentation in computed tomography, a variety of approaches exists, involving sophisticated pipelines trained and validated on different datasets. However, the clinical applicability of these approaches across diseases remains limited.

Authors

  • Johannes Hofmanninger
    Universitätsklinik für Radiologie und Nuklearmedizin, Computational Imaging Research Lab, Medizinische Universität Wien, Währinger Gürtel 18-20, 1090, Wien, Österreich.
  • Forian Prayer
    Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Waehringer Guertel, 18-20, Vienna, Austria.
  • Jeanny Pan
    Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Waehringer Guertel, 18-20, Vienna, Austria.
  • Sebastian Röhrich
    Universitätsklinik für Radiologie und Nuklearmedizin, Computational Imaging Research Lab, Medizinische Universität Wien, Währinger Gürtel 18-20, 1090, Wien, Österreich.
  • Helmut Prosch
    Universitätsklinik für Radiologie und Nuklearmedizin, Computational Imaging Research Lab, Medizinische Universität Wien, Währinger Gürtel 18-20, 1090, Wien, Österreich.
  • Georg Langs
    Department of Biomedical Imaging and Image-guided Therapy Computational Imaging Research Lab, Medical University of Vienna Vienna Austria.

Keywords

External Resources

Popular Topics
Recent Journals