2015/02/08 by Ricardo Pio Monti, Monti, Ricardo Pio, Romy Lorenz +7
Medicine · Neuroscience · #Advanced MRI Techniques and Applications #EEG and Brain-Computer Interfaces #FOS: Computer and information sciences #Functional Brain Connectivity Studies #Machine Learning (stat.ML)
paper · pdf · doi:10.48550/arxiv.1502.02309
openalex publication_date 2015/02/08 · openalex created_date 2022/10/02 · openalex updated_date 2026/07/28
There has been an explosion of interest in functional Magnetic Resonance\nImaging (MRI) during the past two decades. Naturally, this has been accompanied\nby many major advances in the understanding of the human connectome. These\nadvances have served to pose novel challenges as well as open new avenues for\nresearch. One of the most promising and exciting of such avenues is the study\nof functional MRI in real-time. Such studies have recently gained momentum and\nhave been applied in a wide variety of settings; ranging from training of\nhealthy subjects to self-regulate neuronal activity to being suggested as\npotential treatments for clinical populations. To date, the vast majority of\nthese studies have focused on a single region at a time. This is due in part to\nthe many challenges faced when estimating dynamic functional connectivity\nnetworks in real-time. In this work we propose a novel methodology with which\nto accurately track changes in functional connectivity networks in real-time.\nWe adapt the recently proposed SINGLE algorithm for estimating sparse and\ntemporally homo- geneous dynamic networks to be applicable in real-time. The\nproposed method is applied to motor task data from the Human Connectome Project\nas well as to real-time data ob- tained while exploring a virtual environment.\nWe show that the algorithm is able to estimate significant task-related changes\nin network structure quickly enough to be useful in future brain-computer\ninterface applications.\n