We will have two student seminar presentations on Friday, April 29. Feedback and encouragement are appreciated!
Sourabh Palande presents:
Correlating Brain Network Topology to Autism Severity
In this talk I will present a method for analyzing the relationship between functional brain networks and behavioral scores quantifying severity of Autism. A functional brain network is derived from resting state fMRI as pairwise correlations between brain regions and represented as a connectivity matrix. We use persistent homology to extract topological features from this connectivity matrix. These features are encoded in persistence diagrams. Since these features are not Euclidean vectors, we cannot use linear statistical models directly. But we can define a kernel between two persistence diagrams and use kernel partial least squares (kPLS) to regress the topological features against behavioral scores. I will briefly describe what brain networks are, how the topological features are extracted and what they represent. Then I will present the experiments and results which show that combining the pairwise correlations with topological features gives better prediction of autism severity than using correlations alone.
Krishna Gaurav presents:
Empirical Studies in Information Visualization: Seven Scenarios. Heidi Lam, Enrico Bertini, Petra Isenberg, Catherine Plaisant, and Sheelagh Carpendale. IEEE TVCG 18(9), 2012.