Automated Pneumonia Diagnosis from Chest X-Ray Images Using CNN

Abstract

Pneumonia is a serious respiratory infection that affects millions of people worldwide and remains a leading cause of mortality, particularly among children and the elderly. Early and accurate diagnosis is essential for effective treatment, yet traditional chest X-ray interpretation requires skilled radiologists and can be time-consuming, especially in resource-limited healthcare settings. To address this challenge, this project presents Pneumo Detect, an automated pneumonia detection system based on deep learning techniques. The system utilizes chest X-ray images as input and employs a Convolutional Neural Network (CNN) to classify images as either normal or pneumonia-infected, automatically extracting relevant features and reducing human error. Developed as a web-based application using Django, the platform enables healthcare professionals to upload images and receive real-time predictions through a user-friendly interface. To enhance transparency and clinical trust, the system incorporates explainable AI techniques such as Grad-CAM to highlight image regions influencing the model’s decisions. The trained model and application are deployed on Amazon Web Services (AWS), ensuring scalability, reliability, and high availability. Extensive evaluation demonstrates that Pneumo Detect provides accurate and consistent predictions, serving as a supportive diagnostic tool to assist medical professionals in faster and more efficient decision-making rather than replacing them