Metadata-Conditioned Generative Models to Synthesize Anatomically-Plausible 3D Brain MRIs
This work addresses the need for neuroimaging research to have synthetic data that captures real anatomical properties, though it is incremental in extending generative models with metadata conditioning and anatomical evaluation.
The authors tackled the problem of generating synthetic brain MRIs that are both visually high-quality and anatomically plausible, proposing BrainSynth to synthesize metadata-conditioned MRIs and developing a novel evaluation procedure. Results showed that over half of brain regions were anatomically accurate, and the synthetic MRIs improved training for identifying accelerated aging effects.
Generative AI models hold great potential in creating synthetic brain MRIs that advance neuroimaging studies by, for example, enriching data diversity. However, the mainstay of AI research only focuses on optimizing the visual quality (such as signal-to-noise ratio) of the synthetic MRIs while lacking insights into their relevance to neuroscience. To gain these insights with respect to T1-weighted MRIs, we first propose a new generative model, BrainSynth, to synthesize metadata-conditioned (e.g., age- and sex-specific) MRIs that achieve state-of-the-art visual quality. We then extend our evaluation with a novel procedure to quantify anatomical plausibility, i.e., how well the synthetic MRIs capture macrostructural properties of brain regions, and how accurately they encode the effects of age and sex. Results indicate that more than half of the brain regions in our synthetic MRIs are anatomically accurate, i.e., with a small effect size between real and synthetic MRIs. Moreover, the anatomical plausibility varies across cortical regions according to their geometric complexity. As is, our synthetic MRIs can significantly improve the training of a Convolutional Neural Network to identify accelerated aging effects in an independent study. These results highlight the opportunities of using generative AI to aid neuroimaging research and point to areas for further improvement.