Automated pneumothorax triaging in chest X-rays in the New Zealand population using deep-learning algorithms.

Journal: Journal of medical imaging and radiation oncology
Published Date:

Abstract

INTRODUCTION: The primary aim was to develop convolutional neural network (CNN)-based artificial intelligence (AI) models for pneumothorax classification and segmentation for automated chest X-ray (CXR) triaging. A secondary aim was to perform interpretability analysis on the best-performing candidate model to determine whether the model's predictions were susceptible to bias or confounding.

Authors

  • Sijing Feng
    Department of Radiology, Dunedin Hospital, Dunedin, New Zealand.
  • Qixiu Liu
    Counties Manukau Health, Auckland, New Zealand.
  • Aakash Patel
    Dunedin School of Medicine, Dunedin Hospital, Dunedin, New Zealand.
  • Sibghat Ullah Bazai
    School of Natural and Computational Sciences, Massey University, Palmerston North, New Zealand.
  • Cheng-Kai Jin
    Auckland District Health Board, Auckland, New Zealand.
  • Ji Soo Kim
    Auckland District Health Board, Auckland, New Zealand.
  • Mikal Sarrafzadeh
    Auckland District Health Board, Auckland, New Zealand.
  • Damian Azzollini
    Eastern Health, Melbourne, Victoria, Australia.
  • Jason Yeoh
    Auckland District Health Board, Auckland, New Zealand.
  • Eve Kim
    Auckland District Health Board, Auckland, New Zealand.
  • Simon Gordon
    Waikato District Health Board, Hamilton, New Zealand.
  • Julian Jang-Jaccard
    School of Natural and Computational Sciences, Massey University, Palmerston North, New Zealand.
  • Martin Urschler
    a Ludwig Boltzmann Institute for Clinical Forensic Imaging , Graz , Austria .
  • Stuart Barnard
    Middlemore Hospital, Auckland, New Zealand.
  • Amy Fong
    Department of Radiology, Dunedin Hospital, Dunedin, New Zealand.
  • Cameron Simmers
    Department of Radiology, Dunedin Hospital, Dunedin, New Zealand.
  • Gregory P Tarr
    Auckland City Hospital, Auckland, New Zealand.
  • Ben Wilson
    Department of Radiology, Dunedin Hospital, Dunedin, New Zealand.