An effective COVID-19 classification in X-ray images using a new deep learning framework

• Published in: Journal of X-ray science and technology Vol. 33; no. 2; pp. 297 - 316
• Main Authors: Thilagavathi, P., Geetha, R., Jothi Shri, S., Somasundaram, K.
• Format: Journal Article
• Language: English
• Published: London, England SAGE Publications 01.03.2025
• Subjects: Classification Algorithms; COVID-19 - diagnosis; COVID-19 - pathology; Deep Learning; Humans; Radiography, Thoracic; COVID-19; Sparse Auto-encoder; optimized features; Adaptive Optimization; adaptive filtering; hybrid deep learning; feature extraction process; loss function optimization; Multi-head Attention
• ISSN: 0895-3996; 1095-9114; 1095-9114
• DOI: 10.1177/08953996241290893

Background The global concern regarding the diagnosis of lung-related diseases has intensified due to the rapid transmission of coronavirus disease 2019 (COVID-19). Artificial Intelligence (AI) based methods are emerging technologies that help to identify COVID-19 in chest X-ray images quickly. Method In this study, the publically accessible database COVID-19 Chest X-ray is used to diagnose lung-related disorders using a hybrid deep-learning approach. This dataset is pre-processed using an Improved Anisotropic Diffusion Filtering (IADF) method. After that, the features extraction methods named Grey-level Co-occurrence Matrix (GLCM), uniform Local Binary Pattern (uLBP), Histogram of Gradients (HoG), and Horizontal-vertical neighbourhood local binary pattern (hvnLBP) are utilized to extract the useful features from the pre-processed dataset. The dimensionality of a feature set is subsequently reduced through the utilization of an Adaptive Reptile Search Optimization (ARSO) algorithm, which optimally selects the features for flawless classification. Finally, the hybrid deep learning algorithm, Multi-head Attention-based Bi-directional Gated Recurrent unit with Deep Sparse Auto-encoder Network (MhA-Bi-GRU with DSAN), is developed to perform the multiclass classification problem. Moreover, a Dynamic Levy-Flight Chimp Optimization (DLF-CO) algorithm is applied to minimize the loss function in the hybrid algorithm. Results The whole simulation is performed using the Python language in which the 0.001 learning rate accomplishes the proposed method's higher classification accuracy of 0.95%, and 0.98% is obtained for a 0.0001 learning rate. Overall, the performance of the proposed methodology outperforms all existing methods employing different performance parameters. Conclusion The proposed hybrid deep-learning approach with various feature extraction, and optimal feature selection effectively diagnoses disease using Chest X-ray images demonstrated through classification accuracy.