The pig brain model is an important translational model due to its similarity to the human brain anatomy and physiology. However, a lack of a priori information required for common functional analysis techniques dictates that new techniques are required to explore the connectivity of the pig brain. Here we present two new, unsupervised forms of analysis to find functional connectivity in healthy and ischemic stroke pigs using sparse deep convolutional neural networks and dynamic time warping with spectral clustering that yield complementary results.
This abstract and the presentation materials are available to members only; a login is required.