Neural network-based strategies for automatically diagnosing of COVID-19 from X-ray images utilizing different feature extraction algorithms

This study aims to introduce neural network-based strategies for classifying and detecting COVID-19 early through image processing utilizing X-ray images. Despite the extensive use of directly fed X-ray images into the classifier, there is a lack of comparative analysis between the feature-based system and the direct imaging system in the classification of COVID-19 to evaluate the efficiency of feature extraction methods. Therefore, the proposed system represents introductory experiments of feature-based system using image Feature Extraction Algorithms [Texture, Grey-Level Co-occurrence Matrix (GLCM), Grey-Level Dependence Matrix (GLDM), Fast Fourier Transform (FFT), and Discrete Wavelet Transform (DWT)], Dimensionality Reduction Algorithms (Principal Component Analysis (PCA), Kernel Principal Component Analysis (KPCA), Sparse Autoencoder, and Stacked Autoencoder), Feature Selection Algorithms (Anova F-measure, Chi-square Test, and Random Forest), and Neural Networks [Feed-Forward Neural Network (FFNN) and Convolutional Neural Network (CNN)] on generated datasets consisting of Normal, COVID-19, and Pneumonia-infected chest X-ray images. Tenfold Cross-Validations are implemented during the classification process. A baseline model is created where no Feature Extraction Algorithm is implemented. Accuracy, sensitivity, specificity, precision, and F-measure metrics are utilized to assess classification performance. Finally, a comprehensive comparison of the success of the Feature-...

Source: Network Modeling Analysis in Health Informatics and Bioinformatics - July 4, 2023 Category: Bioinformatics Source Type: research