Computed Tomography Image Enhancement Using Super-Resolution Generative Adversarial Network

The use of generative AI in healthcare has become increasingly popular. This paper aims to enhance the quality of CT images using Super-Resolution Generative Adversarial Networks (SRGAN). We begin with an introduction to AI and its applications, followed by an overview of the building blocks of Generative Adversarial Networks (GANs). We then explore previous work on the use of generative AI in image processing, such as text-to-image and image-to-image transformations. The methods used in this domain are also discussed. Finally, we do some preprocessing in the used data set, such as normalization, we present the building blocks of SRGAN, and the results demonstrate improvements in image quality, with reduced blurriness and enhanced visibility of both white and black areas.