TY - JOUR
T1 - A new blind source separation framework for signal analysis and artifact rejection in functional Near-Infrared Spectroscopy
AU - von Lühmann, Alexander
AU - Boukouvalas, Zois
AU - Müller, Klaus Robert
AU - Adalı, Tülay
N1 - Funding Information:
AvL acknowledges support by the Berlin International Graduate School in Model and Simulation based Research (BIMoS) . This work was also supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (No. 2017-0-00451 ). KRM acknowledges partial funding by the German Ministry for Education and Research as Berlin Big Data Centre (BBDC) ( 01IS14013A ) and Berlin Center for Machine Learning under Grant 01IS18037I and by DFG ( EXC 2046/1 , Project-ID 390685689 ). TA acknowledges support by the US National Science Foundation (grants NSF-CCF 1618551 and NSF-NCS 1631838 ). The authors thank Prof. Benjamin Blankertz, Stefan Haufe, PhD, and Andreas Ziehe, PhD for fruitful discussions of applied mathematical models, Stephanie Brandl and Daniel Miklody for help with manuscript revision, Prof. Gabriel Curio for discussing the design of the experimental paradigm and Marina González-Gómez for help with the graphical design of figures.
Funding Information:
AvL acknowledges support by the Berlin International Graduate School in Model and Simulation based Research (BIMoS). This work was also supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (No. 2017-0-00451). KRM acknowledges partial funding by the German Ministry for Education and Research as Berlin Big Data Centre (BBDC) (01IS14013A) and Berlin Center for Machine Learning under Grant 01IS18037I and by DFG (EXC 2046/1, Project-ID 390685689). TA acknowledges support by the US National Science Foundation (grants NSF-CCF 1618551 and NSF-NCS 1631838). The authors thank Prof. Benjamin Blankertz, Stefan Haufe, PhD, and Andreas Ziehe, PhD for fruitful discussions of applied mathematical models, Stephanie Brandl and Daniel Miklody for help with manuscript revision, Prof. Gabriel Curio for discussing the design of the experimental paradigm and Marina González-Gómez for help with the graphical design of figures.
Publisher Copyright:
© 2019 Elsevier Inc.
PY - 2019/10/15
Y1 - 2019/10/15
N2 - In the analysis of functional Near-Infrared Spectroscopy (fNIRS) signals from real-world scenarios, artifact rejection is essential. However, currently there exists no gold-standard. Although a plenitude of methodological approaches implicitly assume the presence of latent processes in the signals, elaborate Blind-Source-Separation methods have rarely been applied. A reason are challenging characteristics such as Non-instantaneous and non-constant coupling, correlated noise and statistical dependencies between signal components. We present a novel suitable BSS framework that tackles these issues by incorporating A) Independent Component Analysis methods that exploit both higher order statistics and sample dependency, B) multimodality, i.e., fNIRS with accelerometer signals, and C) Canonical-Correlation Analysis with temporal embedding. This enables analysis of signal components and rejection of motion-induced physiological hemodynamic artifacts that would otherwise be hard to identify. We implement a method for Blind Source Separation and Accelerometer based Artifact Rejection and Detection (BLISSA2RD). It allows the analysis of a novel n-back based cognitive workload paradigm in freely moving subjects, that is also presented in this manuscript. We evaluate on the corresponding data set and simulated ground truth data, making use of metrics based on 1st and 2nd order statistics and SNR and compare with three established methods: PCA, Spline and Wavelet-based artifact removal. Across 17 subjects, the method is shown to reduce movement induced artifacts by up to two orders of magnitude, improves the SNR of continuous hemodynamic signals in single channels by up to 10dB, and significantly outperforms conventional methods in the extraction of simulated Hemodynamic Response Functions from strongly contaminated data. The framework and methods presented can serve as an introduction to a new type of multivariate methods for the analysis of fNIRS signals and as a blueprint for artifact rejection in complex environments beyond the applied paradigm.
AB - In the analysis of functional Near-Infrared Spectroscopy (fNIRS) signals from real-world scenarios, artifact rejection is essential. However, currently there exists no gold-standard. Although a plenitude of methodological approaches implicitly assume the presence of latent processes in the signals, elaborate Blind-Source-Separation methods have rarely been applied. A reason are challenging characteristics such as Non-instantaneous and non-constant coupling, correlated noise and statistical dependencies between signal components. We present a novel suitable BSS framework that tackles these issues by incorporating A) Independent Component Analysis methods that exploit both higher order statistics and sample dependency, B) multimodality, i.e., fNIRS with accelerometer signals, and C) Canonical-Correlation Analysis with temporal embedding. This enables analysis of signal components and rejection of motion-induced physiological hemodynamic artifacts that would otherwise be hard to identify. We implement a method for Blind Source Separation and Accelerometer based Artifact Rejection and Detection (BLISSA2RD). It allows the analysis of a novel n-back based cognitive workload paradigm in freely moving subjects, that is also presented in this manuscript. We evaluate on the corresponding data set and simulated ground truth data, making use of metrics based on 1st and 2nd order statistics and SNR and compare with three established methods: PCA, Spline and Wavelet-based artifact removal. Across 17 subjects, the method is shown to reduce movement induced artifacts by up to two orders of magnitude, improves the SNR of continuous hemodynamic signals in single channels by up to 10dB, and significantly outperforms conventional methods in the extraction of simulated Hemodynamic Response Functions from strongly contaminated data. The framework and methods presented can serve as an introduction to a new type of multivariate methods for the analysis of fNIRS signals and as a blueprint for artifact rejection in complex environments beyond the applied paradigm.
KW - Artifact removal
KW - Blind source separation
KW - Entropy rate bound minimization
KW - Machine learning
KW - Multimodality
KW - Neuroimaging in motion
KW - fNIRS
UR - http://www.scopus.com/inward/record.url?scp=85067812680&partnerID=8YFLogxK
U2 - 10.1016/j.neuroimage.2019.06.021
DO - 10.1016/j.neuroimage.2019.06.021
M3 - Article
C2 - 31203024
AN - SCOPUS:85067812680
SN - 1053-8119
VL - 200
SP - 72
EP - 88
JO - NeuroImage
JF - NeuroImage
ER -