Background: Chest CT is used for the assessment of the severity of patients infected\nwith novel coronavirus 2019 (COVID-19). We collected chest CT scans of 202 patients\ndiagnosed with the COVID-19, and try to develop a rapid, accurate and automatic tool\nfor severity screening follow-up therapeutic treatment.\nMethods: A total of 729 2D axial plan slices with 246 severe cases and 483 non-severe\ncases were employed in this study. By taking the advantages of the pre-trained deep\nneural network, four pre-trained off-the-shelf deep models (Inception-V3, ResNet-50,\nResNet-101, DenseNet-201) were exploited to extract the features from these CT scans.\nThese features are then fed to multiple classifiers (linear discriminant, linear SVM, cubic\nSVM, KNN and Adaboost decision tree) to identify the severe and non-severe COVID-\n19 cases. Three validation strategies (holdout validation, tenfold cross-validation and\nleave-one-out) are employed to validate the feasibility of proposed pipelines..................
Loading....