Deep convolutional neural networks computer-aided diagnosis of identifying Pneumonia types

Abstract

Radiology is one of the most important area in western medicine practice. It has been used to diagnose very important health issues and diseases. Generally, the disease are often diagnosed from chest X-ray images by an expert radiologist. Also early diagnosis is an important factor for a successful treatment process. But the diagnoses can be subjective and the process of detection by reading X-ray images can be time-consuming for some reasons such as the appearance of disease which can be unclear in chest X-ray images or are often confused with other diseases. Therefore, computer-aided diagnosis systems are needed to guide the radiologist. In this study, I expect to develop a system for detecting the presence of pneumonia(sub types) in the lungs. Convolutional neural network model is constructed using deep learning approaches and extract features from a given chest X-ray image and classify it to determine if a person is infected with pneumonia.