Deep Generative Models İn Medical İmaging : A Literature Review

Abstract

Deep learning has been used extensively in recent years in numerous studies across many disciplines, including medical imaging. GANs (Generative Adversarial Networks) have started to be widely used in the medical field due to their ability to generate realistic images. Recent research has concentrated on three different deep generative models for improving medical images, and a review of deep learning architectures for data augmentation has been done. In this article, other generative models are emphasized, given the dominance of GANs in the field. Studies have conducted a literature review comparing different deep generative models for medical image data augmentation, without focusing solely on GANs or traditional data augmentation methods. In contrast to variational autoencoders, generative adversarial networks (GANs) are the generative model that is most frequently employed for enhancing medical image data. Recent studies have shown that diffusion models have received more attention in recent years compared to variational autoencoders and GANs for medical image data augmentation. This trend is thought to be related to the fact that many GAN-related research directions have previously been investigated, making it more challenging to advance these architectures' current applications.