An Automated Lightweight Deep Neural Network for Diagnosis of COVID-19 from Chest X-ray Images

Abstract

Coronavirus (COVID-19) is an epidemic that is rapidly spreading and causing a severe healthcare crisis resulting in more than 40 million confirmed cases across the globe. There are many intensive studies on AI-based technique, which is time consuming and troublesome by considering heavyweight models in terms of more training parameters and memory cost, which leads to higher time complexity. To improve diagnosis, this paper is aimed to design and establish a unique lightweight deep learning-based approach to perform multi-class classification (normal, COVID-19, and pneumonia) and binary class classification (normal and COVID-19) on X-ray radiographs of chest. This proposed CNN scheme includes the combination of three CBR blocks (convolutional batch normalization ReLu) with learnable parameters and one global average pooling (GP) layer and fully connected layer. The overall accuracy of the proposed model achieved 98.33% and finally compared with the pre-trained transfer learning model (DenseNet-121, ResNet-101, VGG-19, and XceptionNet) and recent state-of-the-art model. For validation of the proposed model, several parameters are considered such as learning rate, batch size, number of epochs, and different optimizers. Apart from this, several other performance measures like tenfold cross-validation, confusion matrix, evaluation metrics, sarea under the receiver operating characteristics, kappa score and Mathew’s correlation, and Grad-CAM heat map have been used to assess the efficacy of the proposed model. The outcome of this proposed model is more robust, and it may be useful for radiologists for faster diagnostics of COVID-19.

A multimodal AI-based non-invasive COVID-19 grading framework powered by deep learning, manta ray, and fuzzy inference system from multimedia vital signs

“…(2) CXR-based classification: The DenseNet201 reports 98.55%, 97.13%, 97.07%, 99.04%, 97.10%, and 98.05% respectively. The accuracy achieved in this study is comparable to the accuracies reported in other studies that used CXR images, such as Ahmadian et al [9] , Ardakani et al [33] , Khan et al [34] , Rajawat et al [35] , Swarup and Anupam [10] , and Ranjan et al [39] . The study also used a CNN-based model, which is a commonly used model for image classification tasks.…”

“…The average accuracy of the ensemble CNN of 96.51% was recorded. Ranjan et al [39] introduced a lightweight DL LW-CBRGPNet model for COVID-19 multi-class and binary classification using CXR images. The proposed model used CNN architecture and training from scratch without feature extraction.…”

Deep Neural Networks for Optimal Selection of Features Related to Flu

“…e majority of young people, slightly more than half, become infected with IAV and develop respiratory tract symptoms; the other half either does not develop symptoms or does not get infected at all when given a controlled IAV exposure [6][7][8]. e fact that in uenza has such a substantial in uence on the economy and peoples' health [9][10][11] makes it imperative to predict who will become ill and when. If IAV-infected people are not identi ed and treated promptly, the number of deaths will rise as a result of increased viral transmission and, possibly, worsening of sickness [12,13].…”

Stacked ensemble modeling for improved tuberculosis treatment outcome prediction in pediatric cases

“…The use of ML methods has witnessed a significant rise in health science, particularly in areas such as diagnosis, predicting mortality and case numbers during pandemics, and more. [18][19][20][21][22][23][24] The application of ML algorithms in the health sector has become imperative for health organizations in terms of patient interventions and public warnings. A growing body of recent research reflects the increasing interest in ML within healthcare.…”

“…The study by Nayak et al 19 focuses on adopting a deep feedforward NN method for diagnosing COVID‐19 using chest x‐ray images. Medeiros et al 25 utilize deep learning (DL) methods to predict glaucoma, a disease leading to blindness.…”