Deep Learning Assistance Closes the Accuracy Gap in Fracture Detection Across Clinician Types.

Journal: Clinical orthopaedics and related research
Published Date:

Abstract

BACKGROUND: Missed fractures are the most common diagnostic errors in musculoskeletal imaging and can result in treatment delays and preventable morbidity. Deep learning, a subfield of artificial intelligence, can be used to accurately detect fractures by training algorithms to emulate the judgments of expert clinicians. Deep learning systems that detect fractures are often limited to specific anatomic regions and require regulatory approval to be used in practice. Once these hurdles are overcome, deep learning systems have the potential to improve clinician diagnostic accuracy and patient care.

Authors

  • Pamela G Anderson
    Imagen Technologies, New York, NY, USA.
  • Graham L Baum
    Imagen Technologies, New York, NY, USA.
  • Nora Keathley
    Imagen Technologies, New York, NY, USA.
  • Serge Sicular
    Imagen Technologies, New York, NY 10012.
  • Srivas Venkatesh
    Imagen Technologies, New York, NY, USA.
  • Anuj Sharma
    Department of Civil, Construction and Environmental Engineering, Iowa State University, United States.
  • Aaron Daluiski
    Imagen Technologies, New York, NY 10012.
  • Hollis Potter
    Imagen Technologies, New York, NY 10012.
  • Robert Hotchkiss
    Imagen Technologies, New York, NY 10012.
  • Robert V Lindsey
    Imagen Technologies, New York, NY, USA.
  • Rebecca M Jones
    Center for Autism and the Developing Brain, Weill Cornell Medicine, New York, USA.