| Summary: | Pneumonia stands as a critical respiratory infection, exerting a significant impact on a global scale. With its ability to affect millions of individuals across various age groups and regions, the urgency surrounding this medical concern becomes clear. Early and accurate diagnosis emerges as a crucial factor in effectively addressing this health challenge. Timely identification of pneumonia enables medical professionals to promptly initiate appropriate treatments, thereby minimizing potential complications and improving patient outcomes. Given the potential severity of the infection, the importance of swift and precise diagnosis cannot be overstated, underscoring the vital role it plays in combating the spread and impact of this respiratory ailment. This study presents a pneumonia detection system to aid in timely diagnosis based on chest X-ray images using the Convolutional Neural Network (CNN) algorithm. The study demonstrates impressive performance with F1-Score of 95.82% and accuracy of 95.19%, demonstrating high reliability and accuracy. The system prototype integrates the trained model with Flask as the back-end and HTML, CSS, and JavaScript for the front-end, providing users with real-time predictions and confidence scores. By leveraging the capabilities of CNN and a user-friendly interface, this pneumonia detection system enables medical professionals to make informed decisions, potentially leading to better treatment outcomes. It also presents as a valuable tool for healthcare practices. © 2024 IEEE.
|
|---|