Artificial intelligence for the detection of COVID-19 pneumonia on chest CT using multinational datasets
Stephanie A. Harmon, Thomas Sanford, Sheng Xu, Evrim Türkbey, Holger R. Roth, Ziyue Xu, Dong Yang, Andriy Myronenko, Victoria Anderson, Amel Amalou, Maxime Blain, Michael Kassin, Dilara J. Long, Nicole Varble, Stephanie M. Walker, Ulaş Bağcı, Anna Maria Ierardi, Elvira Stellato, Guido Giovanni Plensich, Giuseppe Franceschelli, Cristiano Girlando, Giovanni Irmici, Dominic LaBella, Dima A. Hammoud, Ashkan A. Malayeri, Elizabeth C. Jones, Ronald M. Summers, Peter L. Choyke, Daguang Xu, Mona G. Flores, Kaku Tamura, Hirofumi Obinata, Hitoshi Mori, Francesca Patella, Maurizio Cariati, Gianpaolo Carrafiello, Peng An, Bradford J. Wood, Barış Türkbey
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.