Rapid identification of COVID-19 severity in CT scans through classification of deep features

Abstract

Background Chest CT is used for the assessment of the severity of patients infected with novel coronavirus 2019 (COVID-19). We collected chest CT scans of 202 patients diagnosed with the COVID-19, and try to develop a rapid, accurate and automatic tool for severity screening follow-up therapeutic treatment. Methods A total of 729 2D axial plan slices with 246 severe cases and 483 non-severe cases were employed in this study. By taking the advantages of the pre-trained deep neural network, four pre-trained off-the-shelf deep models (Inception-V3, ResNet-50, ResNet-101, DenseNet-201) were exploited to extract the features from these CT scans. These features are then fed to multiple classifiers (linear discriminant, linear SVM, cubic SVM, KNN and Adaboost decision tree) to identify the severe and non-severe COVID-19 cases. Three validation strategies (holdout validation, tenfold cross-validation and leave-one-out) are employed to validate the feasibility of proposed pipelines. Results and conclusion The experimental results demonstrate that classification of the features from pre-trained deep models shows the promising application in COVID-19 severity screening, whereas the DenseNet-201 with cubic SVM model achieved the best performance. Specifically, it achieved the highest severity classification accuracy of 95.20% and 95.34% for tenfold cross-validation and leave-one-out, respectively. The established pipeline was able to achieve a rapid and accurate identification of the severity of COVID-19. This may assist the physicians to make more efficient and reliable decisions.

Early Prediction of COVID-19 Ventilation Requirement and Mortality from Routinely Collected Baseline Chest Radiographs, Laboratory, and Clinical Data with Machine Learning

“…For example, several studies have used CT scans to assess the severity of COVID-19 disease. 54 , 55 Although CT scan shows the COVID-19 pneumonia presentations of ground-glass opacity and pulmonary consolidation and has a better sensitivity than CXR; 56 , 57 however, it is not the standard of care for COVID-19 diagnosis in many countries. 57 , 58 Among other reasons, it is preferable to avoid CT scan as a first-line imaging method to limit unnecessary extra radiation exposure, prevent CT device shortages, and minimize cross-infection by using portable X-ray machines.…”

Diagnostic Techniques for COVID-19: A Mini-review of Early Diagnostic Methods

“…Recently, a 3D deep scan framework applied to diagnosing the pathological change of the diagnosed SARS-CoV-2 patients was reported, with 96% specificity and 90% sensitivity when evaluation of SARS-CoV-2 infected samples [ 110 , 111 ]. However, a CT scan cannot diagnose the causes of viral pneumonia, only reveal the radiological change of lungs, and shows lower sensitivity than RT-PCR [ 112 ]. Therefore, RT-PCR-based techniques are remaining as the recommended techniques in the diagnostic of COVID-19, while the combination of RT-PCR and CT scan or other techniques are proved to be more effective tools in enhancing the sensitivity of COVID-19 diagnosis [ 113 ].…”

Automatic Detection of Coronavirus (COVID-19) from Chest CT Images using VGG16-Based Deep-Learning

“…Yu, et al [13] used four pre-trained deep network models (ResNet-50, ResNet-101, Inception-V3, and DenseNet-201) with multiple classifiers (linear discriminant, linear SVM, cubic SVM, KNN, and Adaboost decision tree) to discriminate between severe and non-severe COVID-19 cases. The methods were applied on a dataset of 729 2D axial CT images (246 severe and 483 non-severe cases).…”