Role of CT Imaging for the Management of COVID-19

Aim: To evaluate the role of high-resolution Computer tomography imaging in the management of COVID-19. Study design: Prospective study Place and duration of study: Jinnah Postgraduate Medical Centre Karachi from 1st December 2021 to 31st May 2022. Methodology: One hundred patients suspected to be suffering from COVID-19 were enrolled. All patients underwent Reverse transcriptase-based polymerase chain reaction tests (RT-PCR). The patients were divided into positive or negative depending upon their test results. A high-resolution computed tomography scan was followed in every patient and the results were compared with the reverse transcriptase-based polymerase chain reaction tests findings. The sensitivity and Specificity of the CT scan test were assessed. Result(s): The mean age of the patients was 59+/-6.5 years. There were 60 (60%) male and 40 (40%) female patients. Around 58% of the patients were found as positive on PCR while 42% were negative. There 75% of the cases were positive for novel coronavirus on high-resolution computed tomography scan while only 25% were negative. Conclusion(s): Chest HRCT-scan proved to be a better and more sensitive tool for the diagnosis of novel coronavirus and can be considered as an alternative screening tool for COVID-19 confirmation. Copyright © 2022 Authors. All rights reserved.

Performance Analysis of Convolutional Neural Network Architectures for the Identification of COVID-19 from Chest X-ray Images

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. © 2022 IEEE.