Automated localization of the medial clavicular epiphyseal cartilages using an object detection network: a step towards deep learning-based forensic age assessment.

Journal: International journal of legal medicine
PMID: 36729183

Abstract

BACKGROUND: Deep learning is a promising technique to improve radiological age assessment. However, expensive manual annotation by experts poses a bottleneck for creating large datasets to appropriately train deep neural networks. We propose an object detection approach to automatically annotate the medial clavicular epiphyseal cartilages in computed tomography (CT) scans.

Authors

  • Philipp Wesp
    From the Department of Radiology, University Hospital, LMU Munich.
  • Bastian Oliver Sabel
    From the Department of Radiology, University Hospital, LMU Munich.
  • Andreas Mittermeier
    Department of Radiology, University Hospital, LMU Munich, Marchioninistraße 15, 81377, Munich, Germany.
  • Anna Theresa Stüber
    Department of Radiology, University Hospital, LMU Munich, Marchioninistraße 15, 81377, Munich, Germany.
  • Katharina Jeblick
    Department of Radiology, University Hospital, LMU Munich, Marchioninistraße 15, 81377, Munich, Germany.
  • Patrick Schinke
    Institute of Informatics, LMU Munich, Oettingenstraße 67, 80538, Munich, Germany.
  • Marc Mühlmann
    Department of Radiology, University Hospital, LMU Munich, Marchioninistraße 15, 81377, Munich, Germany.
  • Florian Fischer
    Institute of Forensic Medicine, LMU Munich, Nußbaumstraße 26, 80336, Munich, Germany.
  • Randolph Penning
    Institute of Forensic Medicine, LMU Munich, Nußbaumstraße 26, 80336, Munich, Germany.
  • Jens Ricke
    Department of Radiology, University Hospital Munich, Germany. Electronic address: jens.ricke@med.uni-muenchen.de.
  • Michael Ingrisch
    Department of Radiology, Ludwig-Maximilians-University Munich, Munich, Germany.
  • Balthasar Maria Schachtner
    Department of Radiology, University Hospital, LMU Munich, Marchioninistraße 15, 81377, Munich, Germany.

Keywords

External Resources

Popular Topics
Recent Journals