Pneumonia Classification Using Hybrid CNN Architecture

Abstract

In this study, we propose a custom-built deep learning model for detecting pneumonia conditions by analyzing radiographs. The hybrid CNN model is trained to classify distinguishable traces of pneumonia into three (3) different categories; bacterial, normal, and viral pneumonia X-ray images. Experiments were conducted using the proposed hybrid CNN approach which is made of several convolution blocks with custom weights and multiple fully connected layers for accurate classification. The proposed deep learning model resulted in an accuracy of 92.9%, which makes it the top-ranking model in comparison to other models in this research. © 2021 IEEE.