COVID-19 Detection by Chest X-Ray Images through Efficient Neural Network Techniques

Abstract

This paper presents an efficient approach for detecting COVID-19 from chest X-ray images using an Enhanced Neural Network (ENN) model optimized with different optimization algorithms. The dataset used consists of X-ray images collected from Kaggle, encompassing both normal and pathological conditions, including COVID-19, pneumonia, and lung opacity. The ENN model is trained and tested using a subset of the dataset, with 10,000 chest X-rays for training and 400 images for testing. Three optimization algorithms, RMSProp, SGD, and ADAM, are employed to enhance the model's performance. The results demonstrate that the ADAM optimizer achieves the highest accuracy of 98.99% on the training set and shows promising results on the test set. The proposed method outperforms some existing approaches and achieves comparable accuracy rates to others. The novelty of this research lies in the optimization of the ENN model using different algorithms and the evaluation of its performance for COVID-19 detection. The findings highlight the potential of using machine learning and deep learning techniques for the accurate and efficient diagnosis of COVID-19 from chest X-ray images, which can aid healthcare professionals in making timely decisions and managing patients effectively.