Diagnosis and detection of COVID-19 infection on X-Ray and CT scans using deep learning based generative adversarial network

COVID-19 is presently one of the world's most serious health threats. However, PCR test kits are in poor supply, and the false-negative rate is significant in many countries. Patient triage is critical, and machine learning may be used to classify COVID-19 instances in chest X-ray or CT. X-rays scans will be utilised to extract and assess the pneumonia infection in the lungs caused by COVID-19. On the basis of GAN and FCN models, an image deep learning method is given that utilises these two models: GAN and FCN. First and foremost, the generator's network structure has been upgraded. With residual modules, convolutional learning can be more flexible in terms of how it responds to changes in the output. After reducing the sum of channels in the input feature by half, a larger convolution kernel is applied. Convolution and deconvolution layers are connected via a U-shaped network to prevent low-level info exchange. The GAN-FCN model achieved a CT scan accuracy of 94.32 percent and an X-ray picture accuracy of 95.62 percent, while existing deep learning models achieved a CT scan accuracy of almost 92 percent and an X-ray image accuracy of nearly 94 percent.