Artificial intelligence for the detection of COVID-19 pneumonia on chest CT using multinational datasets

Nat Commun. 2020 Aug 14;11(1):4080. doi: 10.1038/s41467-020-17971-2.

Abstract

Chest CT is emerging as a valuable diagnostic tool for clinical management of COVID-19 associated lung disease. Artificial intelligence (AI) has the potential to aid in rapid evaluation of CT scans for differentiation of COVID-19 findings from other clinical entities. Here we show that a series of deep learning algorithms, trained in a diverse multinational cohort of 1280 patients to localize parietal pleura/lung parenchyma followed by classification of COVID-19 pneumonia, can achieve up to 90.8% accuracy, with 84% sensitivity and 93% specificity, as evaluated in an independent test set (not included in training and validation) of 1337 patients. Normal controls included chest CTs from oncology, emergency, and pneumonia-related indications. The false positive rate in 140 patients with laboratory confirmed other (non COVID-19) pneumonias was 10%. AI-based algorithms can readily identify CT scans with COVID-19 associated pneumonia, as well as distinguish non-COVID related pneumonias with high specificity in diverse patient populations.

Publication types

  • Research Support, N.I.H., Intramural
  • Research Support, Non-U.S. Gov't

MeSH terms

  • Adolescent
  • Adult
  • Aged
  • Aged, 80 and over
  • Algorithms
  • Artificial Intelligence*
  • Betacoronavirus / isolation & purification
  • COVID-19
  • COVID-19 Testing
  • Child
  • Child, Preschool
  • Clinical Laboratory Techniques / methods*
  • Coronavirus Infections / diagnosis
  • Coronavirus Infections / diagnostic imaging*
  • Coronavirus Infections / virology
  • Deep Learning
  • Female
  • Humans
  • Imaging, Three-Dimensional / methods
  • Lung / diagnostic imaging
  • Male
  • Middle Aged
  • Pandemics
  • Pneumonia, Viral / diagnostic imaging*
  • Pneumonia, Viral / virology
  • Radiographic Image Interpretation, Computer-Assisted / methods
  • SARS-CoV-2
  • Tomography, X-Ray Computed / methods*
  • Young Adult