Abstract
Aim: The aim of the present study is to assess the diagnostic accuracy of a computer vision-based system for the identification of radiological changes in the lungs of COVID-19 patients.
Materials and Methods: A total of two hundred and seventy-eight (278) images of chest X-rays have been assessed by applying ResNet-50 convolutional neural network architectures in the present study.
Results: A pre-trained ResNet-50 architecture was used to diagnose the cases of COVID-19 patients. The analysis of the data revealed that a computer vision-based program achieved a diagnostic accuracy of 98.18 %, and F1-score of 98.19.
Discussion: The radiological assessment of lung has got paramount importance in the case of COVID-19 patients particularly when these patients are severely ill. The computer vision-based programs may identify and differentiate among the subtle changes in the digital images which may not be detectable or visible to the human eye. Due to the better-automated feature extraction capability, the convolutional neural networks, which have been trained on natural images, turned out to be very successful in the classification of images. In the present study, ResNet-50 convolutional neural network architectures have been applied to the digital images of chest X-rays of COVID-19 patients and it yielded an accuracy of 98.18 % and F1-score of 98.19. The result of the present study is very encouraging and in the near future, it could be a very useful adjunct tool for the assessment of chest X-rays in the case of suspected patients of COVID-19.
Conclusion: The performance of a convolutional neural network regarding the differentiation of pulmonary changes in cases of COVID-19 from the other types of pneumonia on digital images of the chest X-rays is excellent. It could be a very useful adjunct tool for the evaluation of chest x-rays which may be quite helpful for health professionals in patient care.