Citation: Tanvir Anjum, Tanzil Ebad, Shadman Sakib, Shafkat Kibria “Performance Analysis of Convolutional Neural Network Architectures for the Identification of COVID-19 from Chest X-ray Images”, in proceedings of 2022 IEEE 12th Annual Computing and Communication Workshop and Conference(CCWC), March 2022, pp. 0446-0452, doi: 10.1109/CCWC54503.2022.9720862.
URL: https://ieeexplore.ieee.org/document/9720862
Abstract: The 2019 Novel Coronavirus (COVID-19) has spread quickly over the world and continues to impact the health and well-being of people. The application of deep learning coupled with radiological images is effective for early diagnosis and prevention of the spread. In this study, we introduced a 2D Convolutional Neural Network (CNN) to automatically diagnose Chest X-ray images for multi-class classification (COVID-19 vs. Viral Pneumonia vs. Normal). The objective of the research is to maximize the accuracy of detection by altering various internal parameters of a 2D CNN architecture. A dataset consisting of 1000 COVID-19, 1000 Viral Pneumonia, and 1000 Normal images was considered, and preprocessing steps and augmentation strategies were applied. The training and evaluation of the results were performed on eight 2D CNN architectures with internal parameters changed specifically in each case, and a COVID-19 classification model was proposed. Our proposed computer-aided diagnostic tool produced a significant performance with a classification accuracy of 97.3%, a sensitivity of 97.3%, specificity of 98.7%, and precision of 97.4% on test datasets. These results suggest that it can reliably detect COVID-19 cases and expedite treatment to those in the most need.