A new blind source separation framework for signal analysis and artifact rejection in functional Near-Infrared Spectroscopy

Published on Oct 1, 2019in NeuroImage5.812
· DOI :10.1016/j.neuroimage.2019.06.021
Alexander von Lühmann4
Estimated H-index: 4
(BU: Boston University),
Zois Boukouvalas5
Estimated H-index: 5
(UMD: University of Maryland, College Park)
+ 1 AuthorsTulay Adali56
Estimated H-index: 56
(UMBC: University of Maryland, Baltimore County)
Abstract 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 (BLISS A 2 RD). 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 10 d B , 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.
  • References (72)
  • Citations (0)
📖 Papers frequently viewed together
2017MFI: International Conference on Multisensor Fusion and Integration for Intelligent Systems
5 Authors (Gihyoun Lee, ..., Jinung An)
1 Citations
38 Citations
6 Authors (K.H. Ting, ..., F.H.Y. Chan)
78% of Scinapse members use related papers. After signing in, all features are FREE.
#1Zois Boukouvalas (UMD: University of Maryland, College Park)H-Index: 5
#2Yuri Levin-Schwartz (ISMMS: Icahn School of Medicine at Mount Sinai)H-Index: 7
Last. Tulay Adali (UMBC: University of Maryland, Baltimore County)H-Index: 56
view all 5 authors...
Independent component analysis (ICA) is one of the most popular methods for blind source separation with a diverse set of applications, such as: biomedical signal processing, video and image analysis, and communications. The success of ICA is tied to proper characterization of the probability density function (PDF) of the latent sources; information that is generally unknown. In this work, we propose a new and efficient ICA algorithm based on entropy maximization with kernels, (ICA-EMK), which u...
1 CitationsSource
Apr 1, 2018 in ICASSP (International Conference on Acoustics, Speech, and Signal Processing)
#1Qunfang Long (UMBC: University of Maryland, Baltimore County)H-Index: 2
#2Chunying Jia (UMBC: University of Maryland, Baltimore County)H-Index: 1
Last. Tulay Adali (UMBC: University of Maryland, Baltimore County)H-Index: 56
view all 6 authors...
Independent component analysis (ICA) has found wide application in a variety of areas, and analysis of functional magnetic resonance imaging (fMRI) data has been a particularly fruitful one. Maximum likelihood provides a natural formuiation for ICA and allows one to take into account multiple statistical properties of the data-forms of diversity. While use of multiple types of diversity allows for additional flexibility, it comes at a cost, leading to high variability in the solution space. In t...
6 CitationsSource
#1Jaeyoung Shin (Hanyang University)H-Index: 3
#2Alexander von Lühmann (Technical University of Berlin)H-Index: 4
Last. Klaus-Robert MüllerH-Index: 92
view all 6 authors...
15 CitationsSource
6 CitationsSource
We provide an open access dataset for hybrid brain–computer interfaces (BCIs) using electroencephalography (EEG) and near-infrared spectroscopy (NIRS). For this, we conducted two BCI experiments (left versus right hand motor imagery; mental arithmetic versus resting state). The dataset was validated using baseline signal analysis methods, with which classification performance was evaluated for each modality and a combination of both modalities. As already shown in previous literature, the capabi...
25 CitationsSource
#1Dominik Wyser (ETH Zurich)H-Index: 1
#2Olivier Lambercy (ETH Zurich)H-Index: 19
Last. Roger Gassert (ETH Zurich)H-Index: 32
view all 5 authors...
With the aim of transitioning functional near-infrared spectroscopy (fNIRS) technology from the laboratory environment to everyday applications, the field has seen a recent push toward the development of wearable/miniaturized, multiwavelength, multidistance, and modular instruments. However, it is challenging to unite all these requirements in a precision instrument with low noise, low drift, and fast sampling characteristics. We present the concept and development of a wearable fNIRS instrument...
11 CitationsSource
#1Zois Boukouvalas (UMBC: University of Maryland, Baltimore County)H-Index: 5
#2Yuri Levin-Schwartz (UMBC: University of Maryland, Baltimore County)H-Index: 7
Last. Tulay Adali (UMBC: University of Maryland, Baltimore County)H-Index: 56
view all 4 authors...
Abstract Because of its wide applicability in various disciplines, blind source separation (BSS), has been an active area of research. For a given dataset, BSS provides useful decompositions under minimum assumptions typically by making use of statistical properties—types of diversity—of the data. Two popular types of diversity that have proven useful for many applications are statistical independence and sparsity. Although many methods have been proposed for the solution of the BSS problem that...
6 CitationsSource
#1Alexander von Lühmann (Technical University of Berlin)H-Index: 4
#2Heidrun Wabnitz (German National Metrology Institute)H-Index: 30
Last. Klaus-Robert Müller (FU: Free University of Berlin)H-Index: 92
view all 4 authors...
Objective: For the further development of the fields of telemedicine, neurotechnology, and brain–computer interfaces, advances in hybrid multimodal signal acquisition and processing technology are invaluable. Currently, there are no commonly available hybrid devices combining bioelectrical and biooptical neurophysiological measurements [here electroencephalography (EEG) and functional near-infrared spectroscopy (NIRS)]. Our objective was to design such an instrument in a miniaturized, customizab...
42 CitationsSource
#1Ilias Tachtsidis (UCL: University College London)H-Index: 27
#2Felix ScholkmannH-Index: 18
We highlight a significant problem that needs to be considered and addressed when performing functional near-infrared spectroscopy (fNIRS) studies, namely the possibility of inadvertently measuring fNIRS hemodynamic responses that are not due to neurovascular coupling. These can be misinterpreted as brain activity, i.e., "false positives" (errors caused by wrongly assigning a detected hemodynamic response to functional brain activity), or mask brain activity, i.e., "false negatives" (errors caus...
106 CitationsSource
#1Theodore J. Huppert (University of Pittsburgh)H-Index: 25
Functional near-infrared spectroscopy (fNIRS) is a noninvasive neuroimaging technique that uses low levels of light to measure changes in cerebral blood oxygenation levels. In the majority of NIRS functional brain studies, analysis of this data is based on a statistical comparison of hemodynamic levels between a baseline and task or between multiple task conditions by means of a linear regression model: the so-called general linear model. Although these methods are similar to their implementatio...
30 CitationsSource
Cited By0
#1Alexander von Lühmann (BU: Boston University)H-Index: 4
#2Xinge Li (BU: Boston University)H-Index: 1
Last. Meryem A. Yücel (BU: Boston University)H-Index: 14
view all 5 authors...
Abstract For the robust estimation of evoked brain activity from functional Near Infrared Spectroscopy (fNIRS) signals, it is crucial to reduce nuisance signals from systemic physiology and motion. The current best practice incorporates short separation (SS) fNIRS measurements as regressors in a General Linear Model (GLM). However, several challenging signal characteristics such as non-instantaneous and non-constant coupling are not yet addressed by this approach and additional auxiliary signals...
1 CitationsSource
Within a decade, single trial analysis of functional Near Infrared Spectroscopy (fNIRS) signals has gained significant momentum, and fNIRS joined the set of modalities frequently used for active and passive Brain Computer Interfaces (BCI). A great variety of methods for feature extraction and classification have been explored using state-of-the-art Machine Learning methods. In contrast, signal preprocessing and cleaning pipelines for fNIRS often follow simple recipes and so far rarely incorporat...