Blind source separation of multichannel neuromagnetic responses

Tang, Akaysha C.; Pearlmutter, Barak A.; Zibulevsky, Michael; Carter, Scott A.

doi:10.1016/s0925-2312(00)00286-1

Cited by 32 publications

(22 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Figures 2 and 3, by applying SOBI to MEG data we achieved excellent separation of noise (Tang et al, 2000a), resulting in signal-to-noise improvement sufficient to perform single trial onset detection (Tang et al, 2000b), and we showed that neuronal components can be separated from each other and localized in a robust (across modalities, tasks, and subject) fashion . These results are surveyed by .…”

Section: Separationsupporting

confidence: 59%

Progress in blind separation of magnetoencephalographic data

Pearlmutter

Jaramillo

2003

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

Section: Separationsupporting

confidence: 59%

Progress in blind separation of magnetoencephalographic data

Pearlmutter

Jaramillo

2003

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…BSS of MEG data segregates noise from signal [Sander et al, 2002;Tang et al, 2000a;Vigário et al, 2000], raising the SNR sufficiently to allow single-trial analysis [Tang et al, 2000b]. Although the sensor attenuation vectors of BSS-separated components can be localized well to equivalent current dipoles [Tang et al, 2002;Vigário et al, 2000], the recovered field maps can be quite noisy.…”

Section: Localization On Real Meg Signals and Comparison With Commercmentioning

confidence: 99%

“…One such technique that we have used is blind source separation (BSS). BSS has been shown to segregate neuronal from nonneuronal signals, and neuronal signals from each other, in both EEG [Jung et al, 2000a, b;Makeig et al, 1997Makeig et al, , 1999 and MEG [Cao et al, 2000;Tang et al, 2000aTang et al, ,b, 2002Tang and Pearlmutter, 2003;Vigário et al, 1998Vigário et al, , 1999Vigário et al, , 2000Wü bbeler et al, 2000;Ziehe et al, 2000]. For these reasons, despite its limitations, it seems feasible to use the localizer proposed above as a stage in a practical robust real-time MEG processing pipeline.…”

Section: Figure 12mentioning

confidence: 99%

Fast robust subject‐independent magnetoencephalographic source localization using an artificial neural network

Jun

Pearlmutter

2004

Human Brain Mapping

View full text Add to dashboard Cite

Abstract:We describe a system that localizes a single dipole to reasonable accuracy from noisy magnetoencephalographic (MEG) measurements in real time. At its core is a multilayer perceptron (MLP) trained to map sensor signals and head position to dipole location. Including head position overcomes the previous need to retrain the MLP for each subject and session. The training dataset was generated by mapping randomly chosen dipoles and head positions through an analytic model and adding noise from real MEG recordings. After training, a localization took 0.7 ms with an average error of 0.90 cm. A few iterations of a Levenberg-Marquardt routine using the MLP output as its initial guess took 15 ms and improved accuracy to 0.53 cm, which approaches the natural limit on accuracy imposed by noise. We applied these methods to localize single dipole sources from MEG components isolated by blind source separation and compared the estimated locations to those generated by standard manually assisted commercial software. Hum Brain Mapp 24:21-34, 2005.

show abstract

“…Superconducting QUantum Interference Device (SQUID) sensors used in the latter technology are susceptible to magnetic coupling due to geometry and must be shielded carefully against magnetic noise. Deconvolution techniques are used to separate different noise sources and ameliorate the effect of electrical and magnetic coupling in these devices [6][7][8][9].…”

Section: Introductionmentioning

confidence: 99%

A Critical Survey of Deconvolution Methods for Separating Cell Types in Complex Tissues

Mohammadi

Zuckerman²,

Goldsmith

et al. 2017

Proc. IEEE

View full text Add to dashboard Cite

Abstract-Identifying properties and concentrations of components from an observed mixture, known as deconvolution, is a fundamental problem in signal processing. It has diverse applications in fields ranging from hyperspectral imaging to denoising readings from biomedical sensors. This paper focuses on in-silico deconvolution of signals associated with complex tissues into their constitutive cell-type specific components, along with a quantitative characterization of the celltypes. Deconvolving mixed tissues/cell-types is useful in the removal of contaminants (e.g., surrounding cells) from tumor biopsies, as well as in monitoring changes in the cell population in response to treatment or infection. In these contexts, the observed signal from the mixture of cell-types is assumed to be a convolution, using a linear instantaneous (LI) mixing process, of the expression levels of genes in constitutive celltypes. The goal is to use known signals corresponding to individual celltypes along with a model of the mixing process to cast the deconvolution problem as a suitable optimization problem.In this paper, we present a survey and in-depth analysis of models, methods, and assumptions underlying deconvolution techniques. We investigate the choice of the different loss functions for evaluating estimation error, constraints on solutions, preprocessing and data filtering, feature selection, and regularization to enhance the quality of solutions, along with the impact of these choices on the performance of commonly used regression-based methods for deconvolution. We assess different combinations of these factors and use detailed statistical measures to evaluate their effectiveness. Some of these combinations have been proposed in the literature, whereas others represent novel algorithmic choices for deconvolution. We identify shortcomings of current methods and avenues for further investigation. For many of the identified shortcomings, such as normalization issues and data filtering, we provide new solutions. We summarize our findings in a prescriptive step-bystep process, which can be applied to a wide range of deconvolution problems.

show abstract

Blind source separation of multichannel neuromagnetic responses

Cited by 32 publications

References 8 publications

Progress in blind separation of magnetoencephalographic data

Progress in blind separation of magnetoencephalographic data

Fast robust subject‐independent magnetoencephalographic source localization using an artificial neural network

A Critical Survey of Deconvolution Methods for Separating Cell Types in Complex Tissues

Contact Info

Product

Resources

About