Implementation of Generative Adversarial Network (GAN) Method for Pneumonia Dataset Augmentation

Abstract

As a communicable disease, the majority of pneumonia cases are brought on by bacteria or viruses, which cause the lungs' alveoli to swell with fluid or mucus. Pneumonia may arise from this and further making breathing challenging since the lungs' air sacs are unable to contain enough oxygen for the body. Pneumonia may generally be diagnosed clinically (by a physician based on physical symptoms) as well as through a photo chest radiograph, CT scan, and MRI. In this case, the lower cost of a chest radiograph examination making it as one of the most popular medical imaging tests. However, chest radiograph photo readings have a disadvantage, where it takes a long time for medical staff or physicians to identify the patient's illness since it is difficult to detect the condition. Therefore, an identification of chest radiograph imagery into various forms using machine learning becomes one way to address this issue. This research focuses on building a deep neural network model using techniques from the Generative Adversarial Network algorithm. GAN is a category of machine learning techniques using two models to be trained simultaneously, one is a generator model to generated fake data and the other is a discriminator model used to separate the raw data from the real data set images. The dataset used is Chest X-Ray images obtained from repo GitHub and repo Kaggle totaling 5,863 with normal data 1583 images and pneumonia data 4273 imagesThe results showed that the use of the Generative Adevrsarial Network method as augmentation data proved to be more effective in improving the generalization of neural networks, this can be seen from the results the result of the accuracy value obtained is 97%.