Unlocking COVID-19 patterns: Exploring deep learning models for precise recognition and classification of CT images

Abstract

Coronavirus is a pestilence sickness that truly affects old individuals and patients with persistent illnesses and causes life threatening diseases. Preventing the entire world from this epidemic, quick and accurate detection of COVID-19 plays a crucial role. To contain the advancement of Covid, it is important to build up a dependent and fast technique to recognize the individuals who are influenced and segregate them until full recovery is made. In this study, we introduce a groundbreaking deep CNN model, leveraging the latest advancements in the field, to accomplish precise categorization of COVID-19 CT images. We employ the publicly available HUST-19 dataset, encompassing an impressive collection of 13,980 CT scan images. By harnessing the power of this extensive dataset, our model aims to improve the precision and reliability of COVID-19 classification. In our research, we propose three innovative architectures for deep convolutional neural networks (CNNs), known as AlexNet, Inception V3 and VGG19 models, to get the accurate diagnosis of COVID-19 patients based on images obtained from a CT scan. In order to assess the effectiveness of CNN-based models in a quantitative manner, we employ several key metrics, including Accuracy, Precision, Recall and F-score. The findings of our study indicate that all these three architectures gave remarkable results but InceptionV3 came on the top with testing accuracy of 99.95% with precision, recall and f1-score of 1, 1, and 1 respectively. The results underscore the potential of our suggested method in accurately diagnosing COVID-19 cases utilizing CT scan images.