Diffusion-Weighted Magnetic Resonance Brain Images Generation with Generative Adversarial Networks and Variational Autoencoders: A Comparison Study

TL;DR

This paper compares deep generative models, specifically Introspective Variational Autoencoders and Style-Based GANs, for synthesizing high-quality, diverse diffusion-weighted MRI brain images to aid data augmentation in medical imaging.

Contribution

It introduces and evaluates two advanced generative models for realistic MRI brain image synthesis, demonstrating their potential for medical data augmentation.

Findings

Generated images are high quality and diverse.

Models are validated by neuroradiologists' evaluations.

Potential for improving medical imaging datasets.

Abstract

We show that high quality, diverse and realistic-looking diffusion-weighted magnetic resonance images can be synthesized using deep generative models. Based on professional neuroradiologists' evaluations and diverse metrics with respect to quality and diversity of the generated synthetic brain images, we present two networks, the Introspective Variational Autoencoder and the Style-Based GAN, that qualify for data augmentation in the medical field, where information is saved in a dispatched and inhomogeneous way and access to it is in many aspects restricted.