Exploring Variational Autoencoders for Medical Image Generation: A Comprehensive Study

TL;DR

This paper provides a comprehensive review of variational autoencoders (VAEs) in medical imaging, focusing on their architectures, ability to generate realistic synthetic images for data augmentation, and comparison with other models like GANs.

Contribution

It offers an extensive overview of VAE architectures, their applications in medical imaging, and compares their performance with GANs in terms of image quality and diversity.

Findings

VAEs can effectively generate synthetic medical images for data augmentation.

VAEs improve segmentation and classification accuracy in medical imaging.

Compared to GANs, VAEs offer advantages in diversity and stability of generated images.

Abstract

Variational autoencoder (VAE) is one of the most common techniques in the field of medical image generation, where this architecture has shown advanced researchers in recent years and has developed into various architectures. VAE has advantages including improving datasets by adding samples in smaller datasets and in datasets with imbalanced classes, and this is how data augmentation works. This paper provides a comprehensive review of studies on VAE in medical imaging, with a special focus on their ability to create synthetic images close to real data so that they can be used for data augmentation. This study reviews important architectures and methods used to develop VAEs for medical images and provides a comparison with other generative models such as GANs on issues such as image quality, and low diversity of generated samples. We discuss recent developments and applications in several medical fields highlighting the ability of VAEs to improve segmentation and classification accuracy.