Training and Validating a Deep Convolutional Neural Network for Computer-Aided Detection and Classification of Abnormalities on Frontal Chest Radiographs.

Journal: Investigative radiology
Published Date:

Abstract

OBJECTIVES: Convolutional neural networks (CNNs) are a subtype of artificial neural network that have shown strong performance in computer vision tasks including image classification. To date, there has been limited application of CNNs to chest radiographs, the most frequently performed medical imaging study. We hypothesize CNNs can learn to classify frontal chest radiographs according to common findings from a sufficiently large data set.

Authors

  • Mark Cicero
    From the *Department of Medical Imaging, St Michael's Hospital, and †Department of Pharmaceutical Sciences, University of Toronto, Toronto, Ontario, Canada.
  • Alexander Bilbily
  • Errol Colak
    Li Ka Shing Knowledge Institute, St. Michael's Hospital, Unity Health Toronto, Toronto, ON, Canada.
  • Tim Dowdell
  • Bruce Gray
  • Kuhan Perampaladas
  • Joseph Barfett