Abstract
An important goal in neuroscience is to elucidate the causal relationships between the brain’s different regions. This can help reveal the brain’s functional circuitry and diagnose lesions. Currently there are a lack of approaches to functional connectome estimation that leverage the state-of-the-art in deep learning architectures and training methodologies. Therefore, we propose a new framework based on a vector auto-regressive deep neural network (VARDNN) architecture. Our approach consists of a set of nodes, each with a deep neural network structure. These nodes can be mapped to any spatial sub-division based on the data to be analyzed, such as anatomical brain regions from which representative neural signals can be obtained. VARDNN learns to reproduce experimental time series data using modern deep learning training techniques. Based on this, we developed two novel directed functional connectivity (dFC) measures, namely VARDNN-DI and VARDNN-GC. We evaluated our measures against a number of existing functional connectome estimation measures, such as partial correlation and multivariate Granger causality combined with large dimensionality counter-measure techniques. Our measures outperformed them across various types of ground truth data, especially as the number of nodes increased. We applied VARDNN to fMRI data to compare the dFC between 41 healthy control vs. 32 Alzheimer’s disease subjects. Our VARDNN-DI measure detected lesioned regions consistent with previous studies and separated the two groups well in a subject-wise evaluation framework. Summarily, the VARDNN framework has powerful capabilities for whole brain dFC estimation. We have implemented VARDNN as an open-source toolbox that can be freely downloaded for researchers who wish to carry out functional connectome analysis on their own data.
Highlights
There is a rich history of structural and functional connectome analysis of neuroimaging data of the whole brain, such as those acquired from magnetic resonance imaging (MRI)
We propose a new approach for whole-brain analytics based on a vector auto-regressive deep neural network (VARDNN) architecture that can deal with a large number of time series
We defined two types of directed functional connectivity measures based on the VARDNN, namely VARDNN-directional influence (DI) (Directional Influence, our new measure) and VARDNN-Granger causality (GC)
Summary
There is a rich history of structural and functional connectome analysis of neuroimaging data of the whole brain, such as those acquired from MRI (magnetic resonance imaging). Functional connectivity (FC), which is calculated by the correlation coefficient of pairwise time-series, is the most basic measure to analyze brain region relationships. To evaluate our VARDNN approach we tested the performance of its dFC measures against 14 other analysis algorithms, including zero-lag and predictive types, and pairwise and multivariate strategies. Included in these algorithms, countermeasure techniques, such as PCA, Elastic Net (Zou and Hastie, 2005) and Partial Least Squares (PLS) (Wold et al, 2001) were combined with PC and multivariate GC. Functional connectomes estimated by the VARDNN measure was able to capture the causal relationship between brain regions and showed a significant difference between healthy control and Alzheimer’s disease data
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
