Abstract: COVID-19, a deadly disease originated in 2019 is still affecting millions across the globe and has become a global pandemic. The virus is continuously mutating and Omicron being the latest mutated variant (2022). Most nations had to take measures to react to the sudden and rapid outbreak of COVID-19 within a relatively short period of time. Because radiographs such as X-rays and computed tomography (CT) scans are cost-effective and widely available at public health facilities, hospital emergency rooms (ERs), and even at rural clinics, they could be used for rapid detection of possible COVID-19-induced lung infections. Therefore, toward automating the COVID-19 detection, in this paper, we propose a viable and efficient deep learning-based chest radiograph classification (DL-CRC) framework to distinguish the COVID-19 cases with high accuracy from other abnormal (e.g., pneumonia) and normal cases. A unique dataset is prepared from four publicly available sources containing the posteroanterior (PA) chest view of X-ray data for COVID-19, pneumonia, and normal cases. Our proposed DL-CRC framework leverages a data augmentation of radiograph images (DARI) algorithm for the COVID-19 data by adaptively employing the generative adversarial network (GAN) and generic data augmentation methods to generate synthetic COVID-19 infected chest X-ray images to train a robust model. The training data consisting of actual and synthetic chest X-ray images are fed into our customized convolutional neural network (CNN) model in DL-CRC, which achieves COVID-19 detection accuracy of 98.94% compared to 54.55% for the scenario without data augmentation (i.e., when only a few actual COVID-19 chest X-ray image samples are available in the original dataset). Furthermore, we justify our customized CNN model by extensively comparing it with widely adopted CNN architectures in the literature, namely ResNet, Inception-ResNet v2, and DenseNet that represent depth-based, multi-path-based, and hybrid CNN paradigms. The encouragingly high classification accuracy of our proposal implies that it can efficiently automate COVID-19 detection from radiograph images to provide a fast and reliable evidence of COVID-19 infection in the lung that can complement existing COVID-19 diagnostics modalities. H5 model in Convolutional Neural Networks (CNN) is a new innovation done by us. CNN (Convolutional Neural Network) is a popular NN algorithm and it clearly outperforms Artificial Neural Networks (ANN) and Recurrent Neural Networks (RNN) in this project. Inception V3, ResNet50, MobileNet and Xception [1] are the existing CNN models but are found to be less accurate and more time consuming. In our R&D lab we have developed a new CNN model called the H5 model. It is the best fit after the output is obtained from Haar Cascade Classifiers. A model which was developed for facial detection and distinction is now used for all objects detection with more accuracy focusing on five regions with different pixel Intensity scheme. The encouragingly high classification accuracy of our proposal implies that it can efficiently automate COVID-19 detection from radiograph images to provide a fast and reliable evidence of COVID-19 infection in the lung that can complement existing COVID-19 diagnostics modalities. In our previous paper on CNN we had exhibited one channel output. In this paper we will deploy the designed model onto heroku cloud. We prefer our model to be deployed in the cloud platform, for global access of our AI application.
|
DOI:
10.17148/IJARCCE.2022.11155
