Feeding the zombies: Synthesizing brain volumes using a 3D progressive growing GAN
This addresses the challenge of small datasets for training deep learning models in neuroimaging, though it is incremental as it adapts existing GAN methods to 3D medical imaging.
The authors tackled the problem of limited neuroimaging datasets by using a 3D progressive growing GAN to synthesize MR brain volumes, achieving preliminary results in generating 3D data.
Deep learning requires large datasets for training (convolutional) networks with millions of parameters. In neuroimaging, there are few open datasets with more than 100 subjects, which makes it difficult to, for example, train a classifier to discriminate controls from diseased persons. Generative adversarial networks (GANs) can be used to synthesize data, but virtually all research is focused on 2D images. In medical imaging, and especially in neuroimaging, most datasets are 3D or 4D. Here we therefore present preliminary results showing that a 3D progressive growing GAN can be used to synthesize MR brain volumes.