Figure 1
From: Assessing clinical applicability of COVID-19 detection in chest radiography with deep learning
Summary of the types of deep learning architecture (left), ratio of studied COVID-19 CXRs (center) and performance of automatic COVID-19 diagnosis in CXR up to July 2020 (right). Performance metrics: AUC - area under the ROC curve; Acc. - accuracy; F1 - F1 score; Prec. - precision; Sens. - sensitivity; Spec. - specificity (number of works).
