article · PeerJ Computer Science
Chest X-ray imaging serves as a key diagnostic tool for early detection of COVID-19 infections. A deep learning framework named Chest X-Ray COVID Network, or CXRVN, evaluates grayscale chest X-ray scans across three distinct datasets. The design incorporates a lightweight architecture relying on a single fully connected layer, which lowers total memory usage and processing requirements compared to established pre-trained networks. By processing images directly in grayscale, CXRVN achieves diagnostic assessments within milliseconds using either mini-batch gradient descent or Adam optimisers. Performance benchmarks against architectures such as GoogleNet, ResNet, and AlexNet demonstrate high diagnostic capability. Following data augmentation via generative adversarial networks, CXRVN attained 96.7 per cent accuracy for two-class classification and 93.07 per cent accuracy for three-class classification, yielding an overall average accuracy of 94.5 per cent.
Rapid screening during respiratory pandemics requires automated tools that are both accurate and resource efficient. Because the network processes scans in milliseconds with minimal computational overhead, it demonstrates that accurate medical image classification does not necessarily require complex, resource-heavy models. This offers a path toward deploying automated diagnostic support in environments with limited computing hardware.
The lightweight model could support automated triage software for healthcare providers and radiology clinics seeking rapid COVID-19 screening from digital X-ray scans. Its low memory and processing demands make it suitable for integration into point-of-care medical devices or standard hospital computers without high-end graphics processing units. Currently at the stage of applied research tested on benchmark datasets, the system requires clinical validation before deployment in diagnostic workflows.
AI-generated from the published abstract. Always read the original work before citing.
Chest X-ray (CXR) imaging is one of the most feasible diagnosis modalities for early detection of the infection of COVID-19 viruses, which is classified as a pandemic according to the World Health Organization (WHO) report in December 2019. COVID-19 is a rapid natural mutual virus that belongs to the coronavirus family. CXR scans are one of the vital tools to early detect COVID-19 to monitor further and control its virus spread. Classification of COVID-19 aims to detect whether a subject is infected or not. In this article, a model is proposed for analyzing and evaluating grayscale CXR images called Chest X-Ray COVID Network (CXRVN) based on three different COVID-19 X-Ray datasets. The proposed CXRVN model is a lightweight architecture that depends on a single fully connected layer representing the essential features and thus reducing the total memory usage and processing time verse pre-trained models and others. The CXRVN adopts two optimizers: mini-batch gradient descent and Adam optimizer, and the model has almost the same performance. Besides, CXRVN accepts CXR images in grayscale that are a perfect image representation for CXR and consume less memory storage and processing time. Hence, CXRVN can analyze the CXR image with high accuracy in a few milliseconds. The consequences of the learning process focus on decision making using a scoring function called SoftMax that leads to high rate true-positive classification. The CXRVN model is trained using three different datasets and compared to the pre-trained models: GoogleNet, ResNet and AlexNet, using the fine-tuning and transfer learning technologies for the evaluation process. To verify the effectiveness of the CXRVN model, it was evaluated in terms of the well-known performance measures such as precision, sensitivity, <i>F</i>1-score and accuracy. The evaluation results based on sensitivity, precision, recall, accuracy, and F1 score demonstrated that, after GAN augmentation, the accuracy reached 96.7% in experiment 2 (Dataset-2) for two classes and 93.07% in experiment-3 (Dataset-3) for three classes, while the average accuracy of the proposed CXRVN model is 94.5%.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.7717/peerj-cs.358
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
