Abstract
Identifying brain effective connectivity (EC) networks from neuroimaging data has become an effective tool that can evaluate normal brain functions and the injuries associated with neurodegenerative diseases. So far, there are many methods used to identify EC networks. However, most of the research currently focus on learning EC networks from single modal imaging data such as functional magnetic resonance imaging (fMRI) data. This paper proposes a new method, called ACOEC-FD, to learn EC networks from fMRI and diffusion tensor imaging (DTI) using ant colony optimization (ACO). First, ACOEC-FD uses DTI data to acquire some positively correlated relations among regions of interest (ROI), and takes them as anatomical constraint information to effectively restrict the search space of candidate arcs in an EC network. ACOEC-FD then achieves multi-modal imaging data integration by incorporating anatomical constraint information into the heuristic function of probabilistic transition rules to effectively encourage ants more likely to search for connections between structurally connected regions. Through simulation studies on generated datasets and real fMRI-DTI datasets, we demonstrate that the proposed approach results in improved inference results on EC compared to some methods that only used fMRI data.
Highlights
As an important method in brain science, brain imaging reveals the anatomic structure and function of a brain through images and imaging techniques such as functional MRI, electroencephalography, magnetoencephalography, structural MRI and diffusion tensor imaging (DTI), and provides a powerful technical tool to understand the working mechanisms of the brain
To illustrate the application potential of ACO for Learning Brain Effective Connectivity (ACOEC)-FD, we apply it to real Alzheimer’s disease (AD) datasets to discriminate effective connectivity (EC) differences between four subject groups
By allowing stronger structural connectivity to lead to a greater probability of non-zero functional or effective connectivity, structural information has been incorporated into some studies to identify functional connectivity (FC) and EC
Summary
As an important method in brain science, brain imaging reveals the anatomic structure and function of a brain through images and imaging techniques such as functional MRI (fMRI), electroencephalography, magnetoencephalography, structural MRI and diffusion tensor imaging (DTI), and provides a powerful technical tool to understand the working mechanisms of the brain. Multimodal analysis from multiple imaging data provides new insights for the progress of learning EC studies This is because many studies have produced evidence, that FC based on fMRI is positively correlated with structural connectivity (SC) between brain regions based on DTI in the brain network (Rykhlevskaia et al, 2008; Sui et al, 2012; Zhu et al, 2013). The experimental results on generated data and real fMRI-DTI datasets show that the new algorithm is more effective and efficient in identifying EC, and greatly enhances the convergence speed and learning quality compared to ACOEC and some other methods that only use single modality data
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have