Deep COVID DeteCT: an international experience on COVID-19 lung detection and prognosis using chest CT

Lee, E.H. and Zheng, J. and Colak, E. and Mohammadzadeh, M. and Houshmand, G. and Bevins, N. and Kitamura, F. and Altinmakas, E. and Reis, E.P. and Kim, J.-K. and Klochko, C. and Han, M. and Moradian, S. and Mohammadzadeh, A. and Sharifian, H. and Hashemi, H. and Firouznia, K. and Ghanaati, H. and Gity, M. and Do�an, H. and Salehinejad, H. and Alves, H. and Seekins, J. and Abdala, N. and Atasoy, �. and Pouraliakbar, H. and Maleki, M. and Wong, S.S. and Yeom, K.W. (2021) Deep COVID DeteCT: an international experience on COVID-19 lung detection and prognosis using chest CT. npj Digital Medicine, 4 (1).

Preview

Text Deep-COVID-DeteCT-an-international-experience-on-COVID19-lung-detection-and-prognosis-using-chest-CT2021npj-Digital-MedicineOpen-Access.pdf Download (5MB) | Preview

Abstract

The Coronavirus disease 2019 (COVID-19) presents open questions in how we clinically diagnose and assess disease course. Recently, chest computed tomography (CT) has shown utility for COVID-19 diagnosis. In this study, we developed Deep COVID DeteCT (DCD), a deep learning convolutional neural network (CNN) that uses the entire chest CT volume to automatically predict COVID-19 (COVID+) from non-COVID-19 (COVID�) pneumonia and normal controls. We discuss training strategies and differences in performance across 13 international institutions and 8 countries. The inclusion of non-China sites in training significantly improved classification performance with area under the curve (AUCs) and accuracies above 0.8 on most test sites. Furthermore, using available follow-up scans, we investigate methods to track patient disease course and predict prognosis. © 2021, The Author(s).

Actions (login required)

View Item