The College of Computer Science and Information Technology at University of Basrah organized a scientific lecture on "Deep Learning for Denoising Medical Images: An Approach Based on Generative Adversarial Networks."
The lecture aimed to design and develop an effective model for denoising medical images using deep learning techniques, specifically generative adversarial networks (GANs). The model consists of a generator based on the UNet architecture, along with an additional discriminator and refinement network to improve the quality of the resulting images. The lecture, delivered by Zahraa Makki Hussein, a graduate student in the Department of Computer Information Systems, included the use of a set of evaluation functions, such as SSIM and PSNR, to accurately measure the model's performance. An interactive web interface was also developed to facilitate the display of pre- and post-processing images, which contributes to supporting the model's application in the medical field.
