Conditional Cascaded Networks (Ccn) Approach for Diagnosis of Covid-19 in Chest X-Ray and Ct Images Using Transfer Learning

The COVID-19 pandemic has caused significant global health and economic damage, with over five million confirmed cases worldwide. The importance of rapid and accurate diagnosis of infected patients has been underscored. However, due to the shortage of testing kits and the time-consuming and troublesome nature of the manual RT-PCR test, an automated and efficient diagnosis system using chest medical images for early screening of COVID-19 is crucial. In this paper, we present an automated approach for rapid and accurate diagnosis of COVID-19 in chest X-ray and CT images using transfer learning. The proposed technique leverages the Conditional Cascaded Networks (CCN) approach, which employs multiple levels of networks to analyze images with high confidence. Transfer learning is employed with seven commonly used existing CNN architectures and four datasets for X-ray and CT images. Various regularization, optimization, dropout, and data augmentation techniques are examined through a series of experiments with three optimizers. Our technique is compared with other state-of-the-art techniques, and the achieved results demonstrate highly promising performance metrics. Additionally, occlusion specificity and Grad-CAM techniques are employed to better understand the network output. The proposed technique is highly adaptable and scalable and does not require manual hyperparameter tuning.