Realistic generation of diffusion-weighted magnetic resonance brain images with deep generative models

We study two state of the art deep generative networks, the Introspective Variational Autoencoder and the StyleBased Generative Adversarial Network, for the generation of new diffusion-weighted magnetic resonance images. We show that high quality, diverse and realistic-looking images, as evaluated by external neuroradiologists blinded to the whole study, can be synthesized using these deep generative models. We evaluate diverse metrics with respect to quality and diversity of the generated synthetic brain images. These findings show that generative models could qualify as a method for data augmentation in the medical field, where access to large image database is in many aspects restricted.

Automated summary

By using the Introspective Variational Autoencoder and the StyleBased Generative Adversarial Network, high quality, diverse, and realistic magnetic resonance images can be generated, evaluated by neuroradiologists blinded to the study as being of superior quality. These findings demonstrate that generative models can serve as a method for data augmentation in the medical field.