Pneumonia Detection using Dense Convolutional Network (DenseNet) Architecture

Abstract

Pneumonia is a dangerous disease that attacks the respiratory system, causing pain in the chest when breathing. The disease killed more than two million people in one year in 2017. Photo the resulting chest X-ray will be checked manually and require proper lighting by a doctor to get the type of pneumonia. Therefore, we need a method to automatically classify pneumonia of the Chest X-ray image. Pneumonia classification systems have been developed but still, produce low accuracy. This research developed a classification system using DenseNet and compared its accuracy with previous studies using ResNet. The results show a 9% performance using DenseNet is better than using ResNet.