Hybrid quantum-classical convolutional neural network model for COVID-19 prediction using chest X-ray images. Issue 2 (25th February 2022)

• Record Type: Journal Article
• Authors: Houssein, Essam H; Abohashima, Zainab; Elhoseny, Mohamed; Mohamed, Waleed M
• Is Part Of: Journal of computational design and engineering. Volume 9:Issue 2(2022)
• Page Start: 343
• Page End: 363
• Publication Date: 2022-02-25
• Subjects: COVID-19 -- medical image classification -- deep neural networks -- quanvolutional neural networks -- quantum computing -- image processing; Engineering -- Data processing -- Periodicals; Computer-aided design -- Periodicals; Computer-aided design; Engineering -- Data processing; Electronic journals; Electronic journals; Periodicals; 620.0042
• DOI: 10.1093/jcde/qwac003
• Languages: English
• ISSNs: 2288-4300

Abstract

Abstract: Despite the great efforts to find an effective way for coronavirus disease 2019 (COVID-19) prediction, the virus nature and mutation represent a critical challenge to diagnose the covered cases. However, developing a model to predict COVID-19 via chest X-ray images with accurate performance is necessary to help in early diagnosis. In this paper, a hybrid quantum-classical convolutional neural network (HQ-CNN) model using random quantum circuits as a base to detect COVID-19 patients with chest X-ray images is presented. A collection of 5445 chest X-ray images, including 1350 COVID-19, 1350 normal, 1345 viral pneumonia, and 1400 bacterial pneumonia images, were used to evaluate the HQ-CNN. The proposed HQ-CNN model has achieved higher performance with an accuracy of 98.6% and a recall of 99% on the first experiment (COVID-19 and normal cases). Besides, it obtained an accuracy of 98.2% and a recall of 99.5% on the second experiment (COVID-19 and viral pneumonia cases). Also, it obtained 98% and 98.8% for accuracy and recall, respectively, on the third dataset (COVID-19 and bacterial pneumonia cases). Lastly, it achieved accuracy and recall of 88.2% and 88.6%, respectively, on the multiclass dataset cases. Moreover, the HQ-CNN model is assessed with the statistical analysis (i.e. Cohen's Kappa and Matthew correlation coefficients). The experimental results revealed that the proposed HQ-CNN model is able to predict the positive COVID-19 cases. Graphical Abstract: