The recent pandemic caused by Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) has highlighted the importance of early detection of infections, especially when RT-PCR testing equipment is scarce. This study introduces a machine learning algorithm using CT scan imaging for rapid COVID-19 identification. The algorithm, designed as a computer-aided detection model, analyzed 536 CT images (32x32 pixels) categorized into COVID-19 infected and non-infected groups. The model preprocesses images using the Prewitt filter and discrete cosine transform, then extracts features through various statistical methods and the histogram of oriented gradients (HOG). Out of 32 analyzed features, 29 showed high significance (p-value < 0.05), effectively distinguishing normal and abnormal cases. These features were classified using support vector machine (SVM) and k-nearest neighbor (KNN) methods. Performance metrics like sensitivity, specificity, and accuracy were used to evaluate the classifiers. The results of metrics showed that the classifiers of KNN-1, KNN-3, KNN-5, and SVM-Linear could distinguish between normal and abnormal images perfectly (100%) when it was applied to the proposed model on the tested ROIs images. Also, the SVM-RBF had less performance than other classifiers with 98.38% of accuracy but was still at a high-performance level. These results indicate that physicians can utilize the proposed model as an assisted tool for detecting COVID-19.
Read full abstract