Explainable DCNN based chest X-ray image analysis and classification for COVID-19 pneumonia detection

Sci Rep. 2021 Aug 9;11(1):16071. doi: 10.1038/s41598-021-95680-6.

Abstract

To speed up the discovery of COVID-19 disease mechanisms by X-ray images, this research developed a new diagnosis platform using a deep convolutional neural network (DCNN) that is able to assist radiologists with diagnosis by distinguishing COVID-19 pneumonia from non-COVID-19 pneumonia in patients based on chest X-ray classification and analysis. Such a tool can save time in interpreting chest X-rays and increase the accuracy and thereby enhance our medical capacity for the detection and diagnosis of COVID-19. The explainable method is also used in the DCNN to select instances of the X-ray dataset images to explain the behavior of training-learning models to achieve higher prediction accuracy. The average accuracy of our method is above 96%, which can replace manual reading and has the potential to be applied to large-scale rapid screening of COVID-9 for widely use cases.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms*
  • COVID-19 / complications
  • COVID-19 / prevention & control*
  • COVID-19 / virology
  • Deep Learning*
  • Diagnosis, Differential
  • Humans
  • Neural Networks, Computer*
  • Pneumonia / complications
  • Pneumonia / diagnosis*
  • Radiography, Thoracic / methods
  • SARS-CoV-2 / physiology
  • Sensitivity and Specificity
  • X-Rays