Abstract: Accurate and quick diagnosis of COVID-19 remains a global challenge, as conventional RT-PCR testing suffers from high false-negative rates, delays, and limited availability. Chest X-ray imaging, while more accessible, requires expert interpretation and is prone to human error. Although several deep learning methods have been applied, many face issues of overfitting, insufficient feature selection, and reduced reliability. In order to overcome these constraints, we suggest a hybrid framework, COVID-19-DSCNN-XISSP, which integrates a Deep Spatial Convolutional Neural Network (DSCNN) for robust spatial excision of features with the Exponential Incremental Social Ski Driver with Sine Cosine Algorithm (XISSP) for optimal feature selection. This strategy enhances classification accuracy while reducing computational overhead. Extensive experiments on benchmark COVID-19 chest X-ray datasets demonstrate that the proposed model outperforms existing approaches in terms of accuracy, precision, and robustness. The findings highlight the potential of COVID-19-DSCNN-XISSP as an economical, automated, and expandable tool for assisting radiologists in early and reliable detection of COVID-19,

Key words: Bayesian boundary trend filtering')">Bayesian boundary trend filtering, COVID-19, Shape–texture discriminative convolutional neural network, Lung area specific COVID-19 Xray dataset, Multi‐hypothesis fuzzy‐matching radon transform, Snow ablation optimizer