An Introduction to Variational Methods for Graphical Models
Machine Learning
A probabilistic framework to infer brain functional connectivity from anatomical connections
IPMI'11 Proceedings of the 22nd international conference on Information processing in medical imaging
Hi-index | 0.00 |
We propose a novel approach to identify the foci of a neurological disorder based on anatomical and functional connectivity information. Specifically, we formulate a generative model that characterizes the network of abnormal functional connectivity emanating from the affected foci. We employ the variational EM algorithm to fit the model and to identify both the afflicted regions and the differences in connectivity induced by the disorder. We demonstrate our method on a population study of schizophrenia.