nCREANN: Nonlinear Causal Relationship Estimation by Artificial Neural Network; applied for autism connectivity study

Nasibeh Talebi | Ali Motie-Nasrabadi | Iman Mohammad-Rezazadeh | Robert Coben

---

URL :   http://research.shahed.ac.ir/WSR/WebPages/Report/PaperView.aspx?PaperID=116696
Date :  2019/07/27
Publish in :    IEEE Transactions on Medical Imaging
DOI :  https://doi.org/10.1109/TMI.2019.2916233
Link :  https://ieeexplore.ieee.org/abstract/document/8713538
Keywords :Relationship, Network

Abstract :

---

Abstract— Quantifying causal (effective) interactions between different brain regions is very important in neuroscience research. Many of conventional methods estimate effective connectivity based on linear models. However, using linear connectivity models may oversimplify functions and dynamics of the brain. In the present study, we propose a causal relationship estimator called “nCREANN” (nonlinear Causal Relationship Estimation by Artificial Neural Network) that identifies both linear and nonlinear components of effective connectivity in the brain. Furthermore, it can distinguish between these two types of connectivity components by calculating the linear and nonlinear parts of the network input-output mapping. The nCREANN performance has been verified using synthesized data and then it has been applied on EEG data collected during rest in children with autism spectrum disorder (ASD) and Typically Developing (TD) children. Results show that overall linear connectivity in TD subjects is higher, while the nonlinear connectivity component is more dominant in ASDs. We suggest that our findings may represent different underlying neural activation dynamics in ASD and TD subjects. The results of nCREANN may provide new insight into the connectivity between the interactive brain regions.