Development of a convolutional neural network to differentiate among the etiology of similar appearing pathological B lines on lung ultrasound: a deep learning study.

Journal: BMJ open
Published Date: Mar 5, 2021

Abstract

OBJECTIVES: Lung ultrasound (LUS) is a portable, low-cost respiratory imaging tool but is challenged by user dependence and lack of diagnostic specificity. It is unknown whether the advantages of LUS implementation could be paired with deep learning (DL) techniques to match or exceed human-level, diagnostic specificity among similar appearing, pathological LUS images.

Authors

  • Robert Arntfield
    Department of Critical Care Medicine, Western University, London, Ontario, Canada.
  • Blake VanBerlo
    Schulich School of Medicine, University of Western Ontario, London, Ontario, Canada.
  • Thamer Alaifan
    Division of Critical Care Medicine, Western University, London, Ontario, Canada.
  • Nathan Phelps
    Department of Computer Science, Western University, London, Ontario, Canada.
  • Matthew White
    Department of Critical Care Medicine, Western University, London, Ontario, Canada.
  • Rushil Chaudhary
    Department of Medicine, Western University, London, Ontario, Canada.
  • Jordan Ho
    Schulich School of Medicine and Dentistry, Western University, London, Ontario, Canada.
  • Derek Wu
    Google Inc, Mountain View, California.

Keywords

External Resources

Popular Topics
Recent Journals