Analyze Chest X-Ray images to detect Covid-19 using CNN

Abstract

The rapid and accurate detection of COVID-19 remains a crucial step in controlling its spread and providing timely medical care. This study proposes a Convolutional Neural Network (CNN)-based approach for the automatic detection of COVID-19 infection from chest X-ray (CXR) images. The model leverages deep learning techniques to extract discriminative features from CXR scans, distinguishing COVID-19 cases from normal and pneumonia-affected lungs. A preprocessed dataset consisting of labeled X-ray images was utilized for training, validation, and testing. Data augmentation techniques were applied to enhance model generalization and address class imbalance. The proposed CNN architecture achieved high accuracy, precision, and recall, demonstrating its reliability as a diagnostic support tool. The model’s performance was also compared with other deep learning architectures to evaluate its effectiveness. The results confirm that CNN-based methods can serve as a rapid, cost-effective, and non-invasive screening solution, assisting healthcare professionals in early COVID-19 diagnosis, particularly in resource-limited environments.