Determining effective connectivity from FMRI data using a gaussian dynamic bayesian network

  • Authors:

  • Xia Wu;Juan Li;Li Yao

  • Affiliations:

  • State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University, Beijing, China,College of Information Science and Technology, Beijing Normal University, Beijing, China;State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University, Beijing, China;State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University, Beijing, China,College of Information Science and Technology, Beijing Normal University, Beijing, China

  • Venue:
  • ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part I
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Two techniques that are based on the Bayesian network, Gaussian Bayesian network (BN) and discrete dynamic Bayesian network (DBN), have recently been used to determine the effective connectivity from functional magnetic resonance imaging (fMRI) data in an exploratory manner and provide a new method for the interactions among brain regions. However, Gaussian BN ignores the temporal relationships of interactions among brain regions, while discrete DBN loses a great of information by discretizing data. In this study, we proposed Gaussian DBN, which is based on Gaussian assumptions, to capture the temporal characteristics of connectivity with less associated loss of information. Synthetic data were generated to validate the effectiveness of this method, and the results were compared with discrete DBN. The result demonstrated that our method is both more robust than discrete DBN and an improvement over BN.