A Smart Approach to Pneumonia Detection Using Deep Learning

Pneumonia is an infection that results in swelling and the buildup of pus or fluid in the air sacs of one or both lungs. Bacteria, viruses, and fungi are among the infectious organisms that can cause this illness. Depending on the causative organism, the patient’s general health, and any underlying diseases, pneumonia can vary greatly in severity and treatment. Different kinds of pneumonia exist, such as community-acquired pneumonia (CAP) and hospital-acquired pneumonia (HAP). Diagnosing usually requires a physical examination and imaging exams, with treatment depending on the cause—antibiotics are used for bacterial pneumonia, while supportive care is given for viral pneumonia. Prevention involves getting vaccinated and practicing good hygiene habits. Prompt diagnosis and treatment are crucial for vulnerable populations to avoid serious complications from pneumonia. This study seeks a method to detect pneumonia by using Deep Learning (DL) techniques that concentrate on the behavior and attributes of proposed chest x-ray images. The aim of this work is to implement various deep learning models such as Convolutional neural network (CNN), VGG-19, MobilenetV2 etc., for classifying a chest X-ray image as either pneumonia or normal case. The results demonstrate that CNN achieves the highest accuracy of 99.77%.