Abstract
Timely and accurate detection of COVID-19 is essential for rapid intervention and preventing the spread of the disease, especially among vulnerable populations. This study introduces a new two-stage methodology for the detection of COVID-19 in chest X-ray images, combining an optimized preprocessing stage with a deep learning classification stage. The main contribution of this approach lies in the integration of the Maximally Stable Extremal Regions (MSER) algorithm with the Grey Wolf Optimizer (GWO) metaheuristic to enhance image preprocessing. MSER adaptively identifies candidate regions potentially associated with COVID-19, while GWO fine-tunes its parameters to maximize the relevance and stability of these regions under diverse imaging conditions. This optimized preprocessing significantly improves the visibility of key features, making them more distinguishable to the neural network. In the second stage, a deep convolutional neural network is trained to classify the enhanced images. Experimental results demonstrate that the proposed approach significantly improves classification performance, increasing accuracy from 90% to 98%, and accelerating convergence during training. Comprehensive evaluations across multiple metrics confirm the robustness and effectiveness of the method, highlighting its potential as a reliable tool for automated COVID-19 diagnosis from X-ray imagery.