Deep learning algorithm in detecting intracranial hemorrhages on emergency computed tomographies.

Journal: PloS one
Published Date:

Abstract

BACKGROUND: Highly accurate detection of intracranial hemorrhages (ICH) on head computed tomography (HCT) scans can prove challenging at high-volume centers. This study aimed to determine the number of additional ICHs detected by an artificial intelligence (AI) algorithm and to evaluate reasons for erroneous results at a level I trauma center with teleradiology services.

Authors

  • Almut Kundisch
    Center for Emergency Training, BG Klinikum Unfallkrankenhaus Berlin, Berlin, Germany.
  • Alexander Hönning
    Center for Clinical Research, BG Klinikum Unfallkrankenhaus Berlin, Berlin, Germany.
  • Sven Mutze
    Department of Radiology and Neuroradiology, BG Klinikum Unfallkrankenhaus Berlin, Berlin, Germany.
  • Lutz Kreissl
    Department of Radiology and Neuroradiology, BG Klinikum Unfallkrankenhaus Berlin, Berlin, Germany.
  • Frederik Spohn
    Department of Radiology and Neuroradiology, BG Klinikum Unfallkrankenhaus Berlin, Berlin, Germany.
  • Johannes Lemcke
    Department of Neurosurgery, BG Klinikum Unfallkrankenhaus Berlin, Berlin, Germany.
  • Maximilian Sitz
    Department of Neurosurgery, BG Klinikum Unfallkrankenhaus Berlin, Berlin, Germany.
  • Paul Sparenberg
    Department of Neurology, BG Klinikum Unfallkrankenhaus Berlin, Berlin, Germany.
  • Leonie Goelz
    Department of Radiology and Neuroradiology, BG Klinikum Unfallkrankenhaus Berlin, Berlin, Germany.