Efficient Detection of COVID-19 and Pneumonia from Chest X-ray Images Using Deep Learning Techniques

Respiratory diseases such as COVID-19 and pneumonia remain a significant global health challenge, particularly in developing regions where access to experienced radiologists is limited. Chest X-ray (CXR) imaging is one of the most widely used diagnostic tools, but manual interpretation is time-consuming and prone to inconsistencies. This paper presents an integrated offline deep-learning system for automatic classification of CXR images into three categories—COVID-19, Pneumonia, and Normal. The proposed framework combines a lightweight Convolutional Neural Network (CNN) for classification and a U-Net architecture for lung segmentation to enhance interpretability. A desktop-based Tkinter GUI is designed to display the prediction, confidence scores, lung mask overlay, and diagnostic suggestions, along with a text-to-speech feature. Experiments on a publicly available Mendeley dataset demonstrate that the model achieves an accuracy of approximately 90%. The system functions entirely offline, making it suitable for rural healthcare environments and emergency screening applications.