Parallel factor analysis for multidimensional decomposition of functional near-infrared spectroscopy data

Abstract

Significance: Current techniques for data analysis in functional near-infrared spectroscopy (fNIRS), such as artifact correction, do not allow to integrate the information originating from both wavelengths, considering only temporal and spatial dimensions of the signal's structure. Parallel factor analysis (PARAFAC) has previously been validated as a multidimensional decomposition technique in other neuroimaging fields.Aim: We aimed to introduce and validate the use of PARAFAC for the analysis of fNIRS data, which is inherently multidimensional (time, space, and wavelength).Approach: We used data acquired in 17 healthy adults during a verbal fluency task to compare the efficacy of PARAFAC for motion artifact correction to traditional two-dimensional decomposition techniques, i.e., target principal (tPCA) and independent component analysis (ICA). Correction performance was further evaluated under controlled conditions with simulated artifacts and hemodynamic response functions.Results: PARAFAC achieved significantly higher improvement in data quality as compared to tPCA and ICA. Correction in several simulated signals further validated its use and promoted it as a robust method independent of the artifact's characteristics.Conclusions: This study describes the first implementation of PARAFAC in fNIRS and provides validation for its use to correct artifacts. PARAFAC is a promising data-driven alternative for multidimensional data analyses in fNIRS and this study paves the way for further applications.

Trends in authentication of edible oils using vibrational spectroscopic techniques

“…As a result, it can be utilized in the pre-processing stages to isolate artifacts and in the actual data analysis to extract predominant brain activations or other relevant signal characteristics. 29…”

“…As a result, it can be utilized in the pre-processing stages to isolate artifacts and in the actual data analysis to extract predominant brain activations or other relevant signal characteristics. 29 Spectral data, comprising hundreds or even thousands of absorbance values per observation, can be collected rapidly. These data can be transformed into valuable information through multivariate statistical analysis techniques; however, variable selection can be a crucial step as it improves model predictability and simplicity by eliminating non-informative variables.…”

Brain language networks and cognitive outcomes in children with frontotemporal lobe epilepsy

“…A visual inspection was also performed, and minor manual adjustments were applied. Subsequently, parallel factor analysis (PARAFAC), i.e., a multidimensional decomposition method ( Harshman, 1970 ; Bro, 1997 ) which has recently been validated for fNIRS data ( Harshman, 1970 ; Bro, 1997 ; Hüsser et al, 2022 ), was used to correct the signal during relatively isolated artifact intervals. Noisy periods that lasted for a relatively long interval and where no clear signature could be extracted were excluded.…”