Validation of a deep learning model for traumatic brain injury detection and NIRIS grading on non-contrast CT: a multi-reader study with promising results and opportunities for improvement.

Journal: Neuroradiology
PMID:

Abstract

PURPOSE: This study aimed to assess and externally validate the performance of a deep learning (DL) model for the interpretation of non-contrast computed tomography (NCCT) scans of patients with suspicion of traumatic brain injury (TBI).

Authors

  • Bin Jiang
    Department of Urology, Chinese People's Liberation Army General Hospital, Beijing, 100039 China.
  • Burak Berksu Ozkara
    Department of Neuroradiology, MD Anderson Cancer Center, Houston, TX, USA.
  • Sean Creeden
    Deparment of Neuroradiology, University of Illinois College of Medicine Peoria, Peoria, IL, USA.
  • Guangming Zhu
    1 Department of Radiology, Neuroradiology Division, Stanford University School of Medicine, 300 Pasteur Dr, Stanford, CA 94305.
  • Victoria Y Ding
    Department of Medicine, Stanford University, Stanford, CA, USA.
  • Hui Chen
    Xiangyang Central HospitalAffiliated Hospital of Hubei University of Arts and Science Xiangyang 441000 China.
  • Bryan Lanzman
    Department of Radiology, Neuroradiology Division, Stanford University, Stanford, CA, USA.
  • Dylan Wolman
    Department of Neuroimaging and Neurointervention, Stanford University, Stanford, CA, USA.
  • Sara Shams
    Department of Radiology, Neuroradiology Division, Stanford University, Stanford, CA, USA.
  • Austin Trinh
    Department of Neuroimaging and Neurointervention, Stanford University, Stanford, CA, USA.
  • Ying Li
    School of Information Engineering, Chang'an University, Xi'an 710010, China.
  • Alexander Khalaf
    University of Pittsburgh School of Medicine, PA, USA.
  • Jonathon J Parker
    Department of Neurosurgery, Stanford University School of Medicine, United States.
  • Casey H Halpern
    Departments of1Neurosurgery and.
  • Max Wintermark
    Department of Radiology, Stanford University, Stanford, California, USA.