2021/01/09 by Axel Wismüller, Wismuller, Axel, M. Ali Vosoughi +1
Medicine · Neuroscience · #Advanced MRI Techniques and Applications #Advanced Neuroimaging Techniques and Applications #FOS: Biological sciences #FOS: Computer and information sciences #FOS: Electrical engineering #Functional Brain Connectivity Studies #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Neurons and Cognition (q-bio.NC) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2101.09354
openalex publication_date 2021/01/09 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
We introduce large-scale Augmented Granger Causality (lsAGC) as a method for\nconnectivity analysis in complex systems. The lsAGC algorithm combines\ndimension reduction with source time-series augmentation and uses predictive\ntime-series modeling for estimating directed causal relationships among\ntime-series. This method is a multivariate approach, since it is capable of\nidentifying the influence of each time-series on any other time-series in the\npresence of all other time-series of the underlying dynamic system. We\nquantitatively evaluate the performance of lsAGC on synthetic directional\ntime-series networks with known ground truth. As a reference method, we compare\nour results with cross-correlation, which is typically used as a standard\nmeasure of connectivity in the functional MRI (fMRI) literature. Using\nextensive simulations for a wide range of time-series lengths and two different\nsignal-to-noise ratios of 5 and 15 dB, lsAGC consistently outperforms\ncross-correlation at accurately detecting network connections, using Receiver\nOperator Characteristic Curve (ROC) analysis, across all tested time-series\nlengths and noise levels. In addition, as an outlook to possible clinical\napplication, we perform a preliminary qualitative analysis of connectivity\nmatrices for fMRI data of Autism Spectrum Disorder (ASD) patients and typical\ncontrols, using a subset of 59 subjects of the Autism Brain Imaging Data\nExchange II (ABIDE II) data repository. Our results suggest that lsAGC, by\nextracting sparse connectivity matrices, may be useful for network analysis in\ncomplex systems, and may be applicable to clinical fMRI analysis in future\nresearch, such as targeting disease-related classification or regression tasks\non clinical data.\n