Towards tailoring non-invasive brain stimulation using real-time fMRI and Bayesian optimization

TY - CHAP

T1 - Towards tailoring non-invasive brain stimulation using real-time fMRI and Bayesian optimization

AU - Lorenz, Romy

AU - Monti, Ricardo P.

AU - Hampshire, Adam

AU - Koush, Yury

AU - Anagnostopoulos, Christoforos

AU - Faisal, Aldo A.

AU - Sharp, David

AU - Montana, Giovanni

AU - Leech, Robert

AU - Violante, Ines R.

PY - 2016/8/24

Y1 - 2016/8/24

N2 - Non-invasive brain stimulation, such as transcranial alternating current stimulation (tACS) provides a powerful tool to directly modulate brain oscillations that mediate complex cognitive processes. While the body of evidence about the effect of tACS on behavioral and cognitive performance is constantly growing, those studies fail to address the importance of subjectspecific stimulation protocols. With this study here, we set the foundation to combine tACS with a recently presented framework that utilizes real-time fRMI and Bayesian optimization in order to identify the most optimal tACS protocol for a given individual. While Bayesian optimization is particularly relevant to such a scenario, its success depends on two fundamental choices: the choice of covariance kernel for the Gaussian process prior as well as the choice of acquisition function that guides the search. Using empirical (functional neuroimaging) as well as simulation data, we identified the squared exponential kernel and the upper confidence bound acquisition function to work best for our problem. These results will be used to inform our upcoming realtime experiments.

AB - Non-invasive brain stimulation, such as transcranial alternating current stimulation (tACS) provides a powerful tool to directly modulate brain oscillations that mediate complex cognitive processes. While the body of evidence about the effect of tACS on behavioral and cognitive performance is constantly growing, those studies fail to address the importance of subjectspecific stimulation protocols. With this study here, we set the foundation to combine tACS with a recently presented framework that utilizes real-time fRMI and Bayesian optimization in order to identify the most optimal tACS protocol for a given individual. While Bayesian optimization is particularly relevant to such a scenario, its success depends on two fundamental choices: the choice of covariance kernel for the Gaussian process prior as well as the choice of acquisition function that guides the search. Using empirical (functional neuroimaging) as well as simulation data, we identified the squared exponential kernel and the upper confidence bound acquisition function to work best for our problem. These results will be used to inform our upcoming realtime experiments.

KW - Bayesian optimization

KW - fMRI

KW - non-invasive brain stimulation

KW - transcranial alternating current stimulation

UR - http://www.scopus.com/inward/record.url?scp=84988908340&partnerID=8YFLogxK

U2 - 10.1109/PRNI.2016.7552338

DO - 10.1109/PRNI.2016.7552338

M3 - Conference paper

AN - SCOPUS:84988908340

BT - PRNI 2016 - 6th International Workshop on Pattern Recognition in Neuroimaging

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 6th International Workshop on Pattern Recognition in Neuroimaging, PRNI 2016

Y2 - 22 June 2016 through 24 June 2016

ER -