Riemannian Geometry for the Classification of Brain States with fNIRS

Abstract

BackgroundFunctional near-infrared spectroscopy (fNIRS) has recently gained momentum as a reliable and accurate tool for assessing brain states. This increase in popularity is due to its robustness to movement, non-invasive nature, portability, and user-friendly application. However, compared to functional magnetic resonance imaging (fMRI), fNIRS is less sensitive to deeper brain activity and offers less coverage. Additionally, due to fewer advancements in method development, the performance of fNIRS-based brain-state classification still lags behind more prevalent methods like fMRI. MethodsWe introduce a novel classification approach grounded in Riemannian geometry for the classification of kernel matrices, leveraging the temporal and spatial channel relationships and inherent duality of fNIRS signals--more specifically, oxygenated and deoxygenated hemoglobin. For the Riemannian geometry-based models, we compared different kernel matrix estimators and two classifiers: Riemannian Support Vector Classifier and Tangent Space Logistic Regression. These were benchmarked against four models employing traditional feature extraction methods. Our approach was tested in two brain-state classification scenarios based on the same fNIRS dataset: an 8-choice classification, which includes seven established plus an individually selected imagery task, and a 2-choice classification of all possible 28 2-task combinations. ResultsThe novel approach achieved a mean 8-choice classification accuracy of 65%, significantly surpassing the mean accuracy of 42% obtained with traditional methods. Additionally, the best-performing model achieved an average accuracy of 96% for 2-choice classification across all possible 28 task combinations, compared to 78% with traditional models. ConclusionTo our knowledge, we are the first to demonstrate that the proposed Riemannian geometry-based classification approach is both powerful and viable for fNIRS data, considerably increasing the accuracy in binary and multi-class classification of brain activation patterns.