An Enhanced Diagnostic and Classification Process of Covid-19 Chest X-Ray Images Using Ensemble Convolutional Neural Network (ECNN)

Abstract

Coronavirus disease 2019 (COVID-19) is an epidemic disease caused by the Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus and became a pandemic disease in 2020. Since the arrival of this health crisis, accurate prediction and efficient diagnosis of COVID-19 remains a significant challenge to medical experts due to the limitations of current detection methods, such as blood tests and chest scans, which can be cost, time-consuming and error-prone. In this context, fast and accessible diagnostic technical tools are needed. During this period, the medical Chest X-ray (CXR) image plays an important role to diagnose COVID-19 patients effectively. This current research work takes the COVID-19 affect chest X -ray and proposes a new method of image de-noising based on using Discrete Wavelet Transform (DWT) and Total Variation Regularization (TVR). Features are extracted using VGG16, InceptionV3, DenseNet and MobileNet. Optimization is performed using Grasshopper Optimization Algorithm (GOA) and Enhanced GOA (EGOA). DL-based approaches like Convolutional Neural Network (CNN) and Ensemble CNN (ECNN) are used for classifying Covid-19, normal or healthy and Pneumonia cases from X-ray images. From the outcomes, it is obvious that the proposed mechanism offers improved Precision, Accuracy, F1-Score and Recall. (ECNN) are used for classifying Covid-19, normal or healthy and Pneumonia cases from X-ray images. From the outcomes, it is obvious that the proposed mechanism offers improved Precision, Accuracy, F1-Score and Recall.