When you use AI to studying brain tumours, there's an inherent problem with the data because abnormal brain images are, by definition, uncommon.
Now a group of boffins from Nvidia, the Mayo Clinic, and the MGH & BWH Center for Clinical Data Science are presenting a paper on their work using generative adversarial networks (GANs) to create synthetic brain MRI images.
GANs are effectively two AI systems that are pitted against each other -- one that creates synthetic results within a category, and one that identifies the fake results. Working against each other, they both improve.
GANs could help expand the data sets that doctors and researchers have to work with, especially when it comes to particularly rare brain diseases.
The research team used an Nvidia DGX-system with the cuDNN-accelerated PyTorch deep learning framework to train the GAN on data from two publicly available data sets of brain MRIs -- one with images of brains with Alzheimer's disease, and the other with images of brains with tumors.
All well and good until Nvidia's drivers shutting freezing the screen during a backup and destroying the book you have been working on and two days work. This writer will never let Nvidia near his computer again – let alone his brain.