Deep Learning Approaches for COVID-19 Detection from CT Scans and Chest X-Rays: A Comparative Study of VGG, ResNet, Inception, and Xception Models

Abstract Accurate diagnosis of COVID-19 is critical for patient management and disease control. In this study, we evaluate the performance of Convolutional Neural Network (CNN) models, including VGG, ResNet, Inception, and Xception, for COVID-19 detection using CT scans and chest X-ray images. Leveraging deep learning algorithms and multiple layers such as Conv2D, MaxPooling2D, Flatten, and Dense, we analyze medical images to identify COVID-19 patterns. Through comprehensive dataset training and evaluation, we assess model accuracy, sensitivity, and specificity. Our findings highlight the potential of CNN-based approaches for accurate COVID-19 diagnosis from chest radiography images, contributing to the development of advanced diagnostic tools in combating the pandemic.