Abstract
Functional near-infrared spectroscopy (fNIRS) is suitable for noninvasive mapping of relative changes in regional cortical activity but is limited for quantitative comparisons among cortical sites, subjects, and populations. We have developed a convolutional neural network (CNN) analysis method that learns feature vectors for accurate identification of group differences in fNIRS responses. In this study, subject gender was classified using CNN analysis of fNIRS data. fNIRS data were acquired from male and female subjects during a visual number memory task performed in a white noise environment because previous studies had revealed that the pattern of cortical blood flow during the task differed between males and females. A learned classifier accurately distinguished males from females based on distinct fNIRS signals from regions of interest (ROI) including the inferior frontal gyrus and premotor areas that were identified by the learning algorithm. These cortical regions are associated with memory storage, attention, and task motor response. The accuracy of the classifier suggests stable gender-based differences in cerebral blood flow during this task. The proposed CNN analysis method can objectively identify ROIs using fNIRS time series data for machine learning to distinguish features between groups.
Highlights
Functional near-infrared spectroscopy (f NIRS) estimates regional cortical activity by measuring local changes in hemoglobin concentration. This neuroimaging modality has numerous advantages including the capacity to measure cortical hemodynamics associated with activity in real time with higher temporal resolution than functional magnetic resonance imaging and positron emission tomography (PET). fMRI measures the hemodynamic response associated with neuronal activity based on nuclear magnetic resonance
As the convolution is performed in the sliding window manner, the feature extraction process of convolutional neural network (CNN) retains the temporal information of the time series data obtained by f NIRS, which is novel among analysis methods for group trends in f NIRS studies
We have performed a preliminary evaluation of a CNN-based method for automatic determination of the regions of interest (ROI) for f NIRS group analysis
Summary
Functional near-infrared spectroscopy (f NIRS) estimates regional cortical activity by measuring local changes in hemoglobin concentration. Extensive preprocessing of f NIRS data is required, including correction for motion artifacts and baseline drift (low-frequency fluctuations) Setting parameters for these processes is difficult or arbitrary because the optimal settings differ for each individual subject and task. FCA is a form of seed-based analysis or independent component analysis In this case, it is necessary to determine the most appropriate region of interest (ROI) as the seed; this decision is highly subjective. It is necessary to determine the most appropriate region of interest (ROI) as the seed; this decision is highly subjective Resolution of these analytical problems is necessary to fully realize the potential of f NIRS as a noninvasive, safe, and accessible alternative to fMRI for human studies. We verify that CNN analysis can identify an ROI (seed region) to distinguish males from females based on differences in the hemodynamic response pattern during the task
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
