Towards Automated COVID-19 Presence and Severity Classification
This incremental work aids medical professionals in capacity planning for intensive care units by providing automated predictions comparable to existing methods.
The paper tackles COVID-19 presence classification and severity prediction from thorax CT scans using an ensemble of pre-trained 3D ResNet34 and DenseNet121 models, achieving 83.7% AUC for presence classification and 79.0% AUC for severity prediction.
COVID-19 presence classification and severity prediction via (3D) thorax computed tomography scans have become important tasks in recent times. Especially for capacity planning of intensive care units, predicting the future severity of a COVID-19 patient is crucial. The presented approach follows state-of-theart techniques to aid medical professionals in these situations. It comprises an ensemble learning strategy via 5-fold cross-validation that includes transfer learning and combines pre-trained 3D-versions of ResNet34 and DenseNet121 for COVID19 classification and severity prediction respectively. Further, domain-specific preprocessing was applied to optimize model performance. In addition, medical information like the infection-lung-ratio, patient age, and sex were included. The presented model achieves an AUC of 79.0% to predict COVID-19 severity, and 83.7% AUC to classify the presence of an infection, which is comparable with other currently popular methods. This approach is implemented using the AUCMEDI framework and relies on well-known network architectures to ensure robustness and reproducibility.