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

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…

• UD
  U.S. Department of Health and Human Services

  Awards: Task Order No. 75N91019F00129, No. 75N91019D00024, Contract No. 75N91019D00024, 75N91019D00024
• N
  Nvidia
• SF
  Société Française de Radiologie
• NI
  National Institutes of Health

  Awards: 75N91019D00024, BC011242, Contract No. 75N91019D00024, COVID-19, 75N91019F00129, CL040015
• NC
  National Cancer Institute

  Awards: Contract No. 75N91019D00024, 75N91019D00024, 75N91019F00129, CL040015