Effective connectivity between superior temporal gyrus and Heschl’s gyrus during white noise listening: linear versus non-linear models
- Author:
Hamid KA
;
Yusoff AN
;
Rahman MZA
;
Mohamad M
;
Hamid AIA
- Publication Type:Journal Article
- Keywords:
fMRI, dynamic causal modelling (DCM), Bayesian Model Selection (BMS), non-linear DCM.
- From:Biomedical Imaging and Intervention Journal
2012;8(2):1-13
- CountryMalaysia
- Language:English
-
Abstract:
Purpose: This fMRI study is about modelling the effective connectivity between Heschl’s gyrus (HG) and the
superior temporal gyrus (STG) in human primary auditory cortices.
Materials & methods: Ten healthy male participants were required to listen to white noise stimuli during
functional magnetic resonance imaging (fMRI) scans. Statistical parametric mapping (SPM) was used to generate
individual and group brain activation maps. For input region determination, two intrinsic connectivity models
comprising bilateral HG and STG were constructed using dynamic causal modelling (DCM). The models were estimated
and inferred using DCM while Bayesian Model Selection (BMS) for group studies was used for model comparison and
selection. Based on the winning model, six linear and six non-linear causal models were derived and were again
estimated, inferred, and compared to obtain a model that best represents the effective connectivity between HG and the STG, balancing accuracy and complexity.
Results: Group results indicated significant asymmetrical activation (puncorr < 0.001) in bilateral HG and STG.
Model comparison results showed strong evidence of STG as the input centre. The winning model is preferred by 6 out
of 10 participants. The results were supported by BMS results for group studies with the expected posterior probability,r = 0.7830 and exceedance probability, φ = 0.9823. One-sample t-tests performed on connection values obtained from the winning model indicated that the valid connections for the winning model are the unidirectional parallel connections from STG to bilateral HG (p < 0.05). Subsequent model comparison between linear and non-linear models using BMS prefers non-linear connection (r = 0.9160, φ = 1.000) from which the connectivity between STG and the ipsi- and contralateral HG is gated by the activity in STG itself.
Conclusion: We are able to demonstrate that the effective connectivity between HG and STG while listening to
white noise for the respective participants can be explained by a non-linear dynamic causal model with the activity in STG influencing the STG-HG connectivity non-linearly.
- Full text:W020150914556712580381.pdf
