CDLX: An Efficient novel approach for COVİD detection lung x-rays throw transfer learning based on State of the art deep learning image classification models

Abstract

When compared to the general population, lung cancer patients have a higher incidence of COVID-19 infection, pulmonary problems, and poorer survival results. As a reference for prioritising cancer care issues during the epidemic, the world's main professional organisations issued new recommendations for the diagnosis, treatment, and follow-up of lung cancer patients. In today's world, we are fighting one of the greatest pandemics in human history, known as COVID-2019, which is caused by a coronavirus. The patient can be treated promptly if the infection is detected early (before it enters the lower respiratory tract). To observe ground-glass opacity in the chest X-ray due to fibrosis in the lungs once the virus has reached the lungs. Artificial intelligence techniques can be utilised to detect the presence and degree of illness based on the major discrepancies between X-ray images of an infected and non-infected person. For this study, I employed feature extraction from Transfer Learning, which entails importing a pre-trained CNN model, such as Distributed Deep Convolutional VGGNet or Distributed Deep Convolutional with ResNet Model, and changing the last layer to meet my needs.