From research to clinic: A sensor reduction method for high-density EEG neurofeedback systems. Issue 3 (March 2019)

• Record Type: Journal Article
• Authors: Pal, Prasanta; Theisen, Daniel L.; Datko, Michael; van Lutterveld, Remko; Roy, Alexandra; Ruf, Andrea; Brewer, Judson A.
• Is Part Of: Clinical neurophysiology. Volume 130:Issue 3(2019:Mar.)
• Page Start: 352
• Page End: 358
• Publication Date: 2019-03
• Subjects: Monte Carlo -- EEG montage -- Sensor reduction -- Neurofeedback -- Translational -- Source localization; NF neurofeedback -- l-EEG low-density EEG -- h-EEG high density EEG -- PCC Posterior Cingulate Cortex -- MC Monte Carlo; Neurophysiology -- Periodicals; Electroencephalography -- Periodicals; Electromyography -- Periodicals; Neurology -- Periodicals; 612.8
• DOI: 10.1016/j.clinph.2018.11.023
• Languages: English
• ISSNs: 1388-2457

Abstract

Highlights: Introduces an adaptable method for targeted EEG sensor reduction using Monte Carlo sampling. Reliably reduced a 128-sensors source-space EEG neurofeedback system to 32-sensors. Reduced-sensors montages could reproduce 128-sensors feedback with high accuracy and design goals. Abstract: Objective: To accurately deliver a source-estimated neurofeedback (NF) signal developed on a 128-sensors EEG system on a reduced 32-sensors EEG system. Methods: A linearly constrained minimum variance beamformer algorithm was used to select the 64 sensors which contributed most highly to the source signal. Monte Carlo-based sampling was then used to randomly generate a large set of reduced 32-sensors montages from the 64 beamformer-selected sensors. The reduced montages were then tested for their ability to reproduce the 128-sensors NF. The high-performing montages were then pooled and analyzed by a k-means clustering machine learning algorithm to produce an optimized reduced 32-sensors montage. Results: Nearly 4500 high-performing montages were discovered from the Monte Carlo sampling. After statistically analyzing this pool of high performing montages, a set of refined 32-sensors montages was generated that could reproduce the 128-sensors NF with greater than 80% accuracy for 72% of the test population. Conclusion: Our Monte Carlo reduction method was used to create reliable reduced-sensors montages which could be used to deliver accurate NF in clinical settings. Significance: A translational pathway is now available by which high-density EEG-based NF measures can be delivered using clinically accessible low-density EEG systems.