Pneumonia Image Classification Using CNN with Max Pooling and Average Pooling

Abstract

Pneumonia is still a frequent cause of death in hundreds of thousands of children in most developing countries and is generally detected clinically through chest radiographs. This method is still difficult to detect the disease and requires a long time to produce a diagnosis. To simplify and shorten the detection process, we need a faster method and more precise diagnosis of pneumonia. This study aims to classify chest x-ray images using the CNN method to diagnose pneumonia. The proposed CNN model will be tested using max & average pooling. The proposed model is developed in previous studies by adding batch normalization, dropout layer, and the number of epochs used. The dataset used will be optimized with oversampling & data augmentation techniques to maximize model performance. The dataset used in this study is "Chest X-Ray Images (Pneumonia)," with 5,856 data divided into two classes, namely Normal and Pneumonia. The proposed model gets 98% results using average pooling, where the results increase by 9-13% better than the previous study. This is because the overall pixel value of the image is highly considered to classify normal lungs and pneumonia.

Keywords

• pneumonia
• image classification
• convolutional neural network