Building an Otoscopic screening prototype tool using deep learning.

Journal: Journal of otolaryngology - head & neck surgery = Le Journal d'oto-rhino-laryngologie et de chirurgie cervico-faciale
Published Date:

Abstract

BACKGROUND: Otologic diseases are often difficult to diagnose accurately for primary care providers. Deep learning methods have been applied with great success in many areas of medicine, often outperforming well trained human observers. The aim of this work was to develop and evaluate an automatic software prototype to identify otologic abnormalities using a deep convolutional neural network.

Authors

  • Devon Livingstone
    Division of Otolaryngology-Head and Neck Surgery, Department of Surgery, University of Calgary, Calgary, Alberta, Canada.
  • Aron S Talai
    Department of Radiology, Hotchkiss Brain Institute, University of Calgary, Calgary, Canada.
  • Justin Chau
  • Nils D Forkert
    Department of Radiology, University of Calgary, Calgary, Canada. nils.forkert@ucalgary.ca.