Transfer Learning-Based Deep Learning Models for Screening Covid-19 Infection from Chest CT Images

Authors: Dr. S. Malliga, Dr. S. V. Kogilavani, R. Deepti, S. Gowtham Krishnan, G. J. Adhithiya

Abstract: As the global prevalence of Covid-19 rises, accurate diagnosis of Covid-19 patients is critical. The biggest issue in diagnosing people who test positive is the non-availability or scarcity of testing kits, as Covid-19 spreads rapidly in the community. To prevent Covid-19 from spreading among humans as an alternative quick diagnostic method, an automatic detection system is required. We propose in this study to employ Convolution Neural Networks to detect corona virus-infected patients using Computed Tomography (CT) images. In addition, we look into the transfer learning of deep convolutional neural networks like VGG16, inceptionV3, and Xception for detecting infection in CT scans.To find the best values for hyper-parameters, we use Bayesian optimization. The study comprises of comparing and analysing the employed pre-trained CNN models. According to the data, all trained models are more than 93 percent correct. Pretrained models such as VGG16, InceptionV3, and Xception have attained more than 97 percent precision. Furthermore, our method introduces novel methods for classifying CT scans in order to detect the Covid-19 infection.

Pages: 32-44

DOI: 10.46300/9107.2022.16.7

International Journal of Communications, E-ISSN: 1998-4480, Volume 16, 2022, Art. #7