To FID or not to FID: Applying GANs for MRI Image Generation in HPC

Abstract

<jats:title>Abstract</jats:title><jats:p>With the rapid growth of Deep Learning models and neural networks, the medical data available for training – which is already significantly less than other types of data – is becoming scarce. For that purpose, Generative Adversarial Networks (GANs) have received increased attention due to their ability to synthesize new realistic images. Our preliminary work shows promising results for brain MRI images; however, there is a need to distribute the workload, which can be supported by High-Performance Computing (HPC) environments. In this paper, we generate 256<jats:italic>×</jats:italic>256 MRI images of the brain in a distributed setting. We obtained an FID<jats:sub>RadImageNet</jats:sub>of 10.67 for the DCGAN and 23.54 for the WGAN-GP, which are consistent with results reported in several works published in this scope. This allows us to conclude that distributing the GAN generation process is a viable option to overcome the computational constraints imposed by these models and, therefore, facilitate the generation of new data for training purposes.</jats:p>