Functional Connectivity in Parkinson Disease Through Mixture Modelling

摘要

Functional MRI (fMRI) is one of the most important techniques to study the human brain. A relatively new problem to the analysis of fMRI data is the identification of brain networks when the brain is at rest, i.e., no external stimulus is applied to the subject. In this work, we present an advanced method to estimate the Resting State Networks (RSNs) based on a mixture of regression models. More specifically, we adopt the Maximum A Posteriori (MAP) Expectation - Maximization (EM) framework. A critical step of our approach is the use of smoothness prior to model the resting state fMRI time - series. Also, it is important to enforce spatial properties in our model due to physical properties of fMRI time series. We provide experimental results using real fMRI benchmarks that show the efficiency of our method. More specifically, our analysis on resting state fMRI time series from subjects with Parkinson Disease (PD) shows that brain connectivity could be used as a potential biomarker.