Radiograph recognition of COVID-19 based on DenseNet

Abstract

This paper presents a neural network approach for pneumonia image classification. Utilizing thousands of actual X-ray images from both pneumonia patients and healthy individuals, a classification model is developed. This neural network model, a prevalent machine learning technique, is employed as an adjunct tool to aid pneumonia diagnosis and pre-screening. The algorithms utilized in the study are comprehensively analyzed and detailed. Through an examination of the network's architecture, several effective methods for enhancing the model are proposed, leading to improved model structure and classification performance. The novel model structure proposed in this study is demonstrated and evaluated. The final training accuracy exceeds 95%, demonstrating the model's proficiency in learning from the training data. Moreover, the test accuracy hovers around 92%, indicating the model's robust performance in generalizing to unseen data.