Novel Crow Swarm Optimization Algorithm and Selection ApproachforOptimalDeepLearningCOVID-19DiagnosticModel

Abstract

: Due to the COVID-19 epidemic, the number of computerized COVID-19 diagnosis studies is growing rapidly. The diversity of COVID-19 models raises the questions of which COVID-19 diagnostic model should be selected and which performance criteria should be considered by decision-makers of healthcare organizations. Because of this, a selection scheme is a necessity to address all the above issues. This study proposes an integrated method for selecting the optimal Deep learning model based on a novel Crow Swarm Optimization (CSO) algorithm for COVID-19 diagnosis. The CSO is employed to find an optimal set of coefficients using a designed fitness function for evaluating the performance of the deep learning models. The CSO is modified to obtain a good distribution of selected coefficients by considering the best average fitness. We have utilized two datasets that include 746 CT images, 349 of them have confirmed COVID-19 cases, whereas the other 397 CT images with healthy persons and the second dataset are composed of unimproved CT images of the lung for 632 positive cases of COVID-19 with 15 trained, and pre-trained deep learning models with nine evaluation metrics are used to evaluate the developed methodology. The ResNet50 algorithm is the optimal deep learning model is selected as the ideal identification approach for COVID-19 for the first dataset, while VGG16 algorithm is the optimal deep learning model is selected as the ideal identification approach for COVID-19 for the second dataset. InceptionV3 algorithm came last for both datasets as it got the worst overall performance. The proposed evaluation methodology acts as a helpful tool to assist healthcare managers in selecting and evaluating the optimal COVID-19 diagnosis models based on Deep learning