COVID-19 is a deadly and fast-spreading disease that makes early death by affectinghuman organs, primarily the lungs. The detection of COVID in the earlystages is crucial as it may help restrict the spread of the progress. The traditionaland trending tools are manual, time-inefficient, and less accurate. Hence, an automateddiagnosis of COVID is needed to detect COVID in the early stages.Recently, several methods for exploiting computed tomography (CT) scan picturesto detect COVID have been developed; however, none are effective in detectingCOVID at the preliminary phase. We propose a method based on twodimensionalvariational mode decomposition in this work. This proposedapproach decomposes pre-processed CT scan pictures into sub-bands. The texturebasedGabor filter bank extracts the relevant features, and the student's t-value isused to recognize robust traits. After that, linear discriminative analysis (LDA)reduces the dimensionality of features and provides ranks for robust features. Onlythe first 14 LDA features are qualified for classification. Finally, the least squaresupportvector machine (SVM) (radial basis function) classifier distinguishesbetween COVID and non-COVID CT lung images. The results of the trial showedthat our model outperformed cutting-edge methods for COVID classification.Using tenfold cross-validation, this model achieved an improved classificationaccuracy of 93.96, a specificity of 95.59, and an F1 score of 93. To validate ourproposed methodology, we conducted different relative experiments with deeplearning and traditional machine learning-based models like random forest,K-nearest neighbor, SVM, convolutional neural network, and recurrent neuralnetwork. The proposed model is ready to help radiologists identify diseases daily.
展开▼
