RT Journal Article
SR Electronic
T1 A generative modeling approach for interpreting population-level variability in brain structure
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2020.06.04.134635
DO 10.1101/2020.06.04.134635
A1 Ran Liu
A1 Cem Subakan
A1 Aishwarya H. Balwani
A1 Jennifer Whitesell
A1 Julie Harris
A1 Sanmi Koyejo
A1 Eva Dyer
YR 2020
UL http://biorxiv.org/content/early/2020/06/05/2020.06.04.134635.abstract
AB Understanding how neural structure varies across individuals is critical for characterizing the effects of disease, learning, and aging on the brain. However, disentangling the different factors that give rise to individual variability is still an outstanding challenge. In this paper, we introduce a deep generative modeling approach to find different modes of variation across many individuals. To do this, we start by training a variational autoencoder on a collection of auto-fluorescence images from a little over 1,700 mouse brains at 25 micron resolution. To then tap into the learned factors and validate the model’s expressiveness, we developed a novel bi-directional technique to interpret the latent space–by making structured perturbations to both, the high-dimensional inputs of the network, as well as the low-dimensional latent variables in its bottleneck. Our results demonstrate that through coupling generative modeling frameworks with structured perturbations, it is possible to probe the latent space to provide insights into the representations of brain structure formed in deep neural networks.Competing Interest StatementThe authors have declared no competing interest.