Nonlinear dynamics of the EEG separated by independent component analysis after sound and light stimulation

Jin, Songwan; Jeong, Jaeseung; Jeong, Dong-Gyu; Kim, Daijin; Kim, Soo Yong

doi:10.1007/s00422-001-0304-z

Cited by 20 publications

(21 citation statements)

References 38 publications

(37 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In order to compare components from different MEG epochs and subjects and to decide which are more sensitive to AD, an order or criterion must be established [12][13][14]. For this reason, MEG signals were decomposed with the algorithm for multiple unknown signals extraction (AMUSE) [15,25], which provides an order for the components [12].…”

Section: Blind Source Separation (Bss) Algorithmmentioning

confidence: 99%

“…Nevertheless, it is desirable to develop novel strategies to help in AD detection from the analysis of the electromagnetic brain activity [9,11,12]. Techniques based on spatial filtering can help to achieve this goal, as these algorithms offer additional perspectives to examine EEG and MEG signals [11][12][13][14]. For instance, common spatial patterns (CSP) have been recently applied to enhance characteristics of EEG recordings in mild cognitive impairment (MCI) patients who eventually developed AD [11].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Blind source separation to enhance spectral and non-linear features of magnetoencephalogram recordings. Application to Alzheimer's disease

Escudero¹,

Hornero²,

Abásolo³

et al. 2009

Medical Engineering & Physics

View full text Add to dashboard Cite

This work studied whether a blind source separation (BSS) and component selection procedure could increase the differences between Alzheimer's disease (AD) patients and control subjects' spectral and non-linear features of magnetoencephalogram (MEG) recordings. MEGs were acquired with a 148-channel whole-head magnetometer from 62 subjects (36 AD patients and 26 controls), who were divided randomly into training and test sets. MEGs were decomposed using the algorithm for multiple unknown signals extraction (AMUSE). The extracted AMUSE components were characterised with two spectral -median frequency and spectral entropy (SpecEn) -and two non-linear features: Lempel-Ziv complexity (LZC) and sample entropy (SampEn). One-way analyses of variance with age as a covariate were applied to the training set to decide which components had the most significant differences between groups. Then, partial reconstructions of the MEGs were computed with these significant components. In the test set, the accuracy and area under the ROC curve (AUC) associated with each partial reconstruction of the MEGs were compared with the case where no BSS-preprocessing was applied. This preprocessing increased the AUCs between 0.013 and 0.227, while the accuracy for SpecEn, LZC and SampEn rose between 6.4% and 22.6%, improving the separation between AD patients and control subjects.

show abstract

Section: Blind Source Separation (Bss) Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Blind source separation to enhance spectral and non-linear features of magnetoencephalogram recordings. Application to Alzheimer's disease

Escudero¹,

Hornero²,

Abásolo³

et al. 2009

Medical Engineering & Physics

View full text Add to dashboard Cite

show abstract

“…A technique that may improve the subject classification based on features extracted from EEG and MEG data is blind source separation (BSS) [28,29], since this methodology allows us to examine these signals from another point of view [27,30].…”

mentioning

confidence: 99%

“…Moreover, BSS methods can be applied to brain recordings using another approach. Considering the intrinsic complexity of the brain recordings, some BSS components may have certain features that could make them more sensitive to particular brain states, such as AD [27] or audiovisual stimulation [30]. Hence, the most relevant components may be selected and the brain recordings may be partially reconstructed using only these components [27].…”

mentioning

confidence: 99%

Assessment of classification improvement in patients with Alzheimer's disease based on magnetoencephalogram blind source separation

Escudero

Hornero

Poza

et al. 2008

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

2 SummaryObjectives: In this pilot study, we intended to assess whether a procedure based on blind source separation (BSS) and subsequent partial reconstruction of magnetoencephalogram (MEG) recordings might enhance the differences between MEGs from Alzheimer's disease (AD) patients and elderly control subjects. Materials and methods:We analysed MEG background activity recordings acquired with a 148-channel whole-head magnetometer from 21 AD patients and 21 control subjects. Artefact-free epochs of 20 s were blindly decomposed using the algorithm for multiple unknown signals extraction (AMUSE), which arranges the extracted components by decreasing linear predictability. Thus, the components of diverse epochs and subjects could be easily compared. Every component was characterised with its median frequency and spectral entropy (denoted by f median and SpecEn, respectively). The differences between subject groups in these variables were statistically evaluated to find out which components could improve the subject classification. Then, these significant components were used to partially reconstruct the MEG recordings.Results: The statistical analysis showed that the AMUSE components which provided the largest differences between demented patients and control subjects were ordered together. Considering this analysis, we defined two subsets, denoted by BSS-{15,35} and BSS-{20,30}, which included 21 components (15 to 35) and 11 components (20 to 30), respectively. We 3 partially reconstructed the MEGs with these subsets. Then, the classification performance was computed with a leave-one-out cross-validation procedure for the case where no BSS was applied and for the partial reconstructions BSS-{15,35} and BSS-{20,30}. The BSS and component selection procedure improved the classification accuracy from 69.05% to 83.33% using f median with BSS-{15,35} and from 61.91% to 73.81% using SpecEn with BSS-{20,30}. Conclusion:These preliminary results lead us to think that the proposed procedure based on BSS and selection of significant components may improve the classification of AD patients using straightforward features from MEG recordings.

show abstract

“…The nonlinear analysis method used here, recurrence analysis (22), encompasses other quantifiers in addition to %R and %D, and other nonlinear processing methods have been described (27)(28)(29). The relative sensitivity and utility of other quantifiers and processing approaches have not been determined.…”

Section: Discussionmentioning

confidence: 99%

Simulated MR magnetic field induces steady‐state changes in brain dynamics: Implications for interpretation of functional MR studies

Marino

Carrubba

Frilot

et al. 2010

Magnetic Resonance in Med

View full text Add to dashboard Cite

We examined whether a magnetic field comparable to one of the fields produced during MRI induced steady-state changes in brain electrical activity while the field was applied (called a presence effect to distinguish it from evoked potentials). The electroencephalogram was measured from standard scalp locations in the presence and absence of 100-200 mT, 60 Hz, and the effect of the field was evaluated by nonlinear (recurrence analysis) and linear techniques; individual subjects served as their own controls. Using recurrence analysis, changes in brain activity lasting 1 sec (the longest interval considered) were found in 21 of 22 subjects (P < 0.05 for each subject). The presence effect was not detected using linear analysis and was reversible, as indicated by a return of brain activity to baseline levels in all subjects within 2 sec of field offset. The possible role of artifacts or systematic errors was ruled out by studies using electrical phantoms and by analyses of electroencephalograms recorded during sham exposure. It is reasonable to expect that actual scanner magnetic fields also produce nonlinear steady-state perturbations of brain dynamical activity. The effect may influence the picture of brain connectivity inferred in some functional MR studies. Magn Reson Med 64:349-357, 2010. V C 2010 Wiley-Liss, Inc.Key words: nonlinear analysis; brain electrical activity; limitation on fMRI; electric fields; magnetic fields Cognitive activity is mediated by temporal-spatial interactions involving specialized regions of the brain (1). The interactions are commonly studied using functional MRI (fMRI) employing blood-oxygen-level-dependent (BOLD) contrast imaging (2).Averaged images obtained when subjects were and were not performing particular tasks are typically used to identify brain regions that mediated task-related cognitive processing (3,4). This strategy is based on some problematical assumptions and has neuropsychological drawbacks (5), but it affords good statistical power for detecting BOLD signals (6).In MRI, static (0 Hz) magnetic fields of 1-9 T align nuclear spins, high-frequency magnetic fields (10-400 MHz) of about 0.2 mT induce transitions between spin states, and low-frequency magnetic fields (100-1000 Hz) of about 50 mT produce imaging gradients (7); in fMRI, gradient parameters produce additional magnetic fields. Physical law and physiologic conditions in the brain (blood flow, tissue motion, cell movement, motion of the head) result in the simultaneous presence of electric fields (8).Human subjects can detect magnetic fields, as evidenced by their ability to trigger onset and offset evoked potentials (9). We were interested in whether, in addition to these transient changes in brain electrical activity, magnetic fields relevant to those used in MRI also produced continuous changes during the time the field was applied (''presence effect''). Depending on the dynamical nature of the effect (see below), such a finding would enhance the possibility that BOLD data obtained during functional imaging c...

show abstract

Nonlinear dynamics of the EEG separated by independent component analysis after sound and light stimulation

Cited by 20 publications

References 38 publications

Blind source separation to enhance spectral and non-linear features of magnetoencephalogram recordings. Application to Alzheimer's disease

Blind source separation to enhance spectral and non-linear features of magnetoencephalogram recordings. Application to Alzheimer's disease

Assessment of classification improvement in patients with Alzheimer's disease based on magnetoencephalogram blind source separation

Simulated MR magnetic field induces steady‐state changes in brain dynamics: Implications for interpretation of functional MR studies

Contact Info

Product

Resources

About