EEG filtering based on blind source separation (BSS) for early detection of Alzheimer's disease

Exploring the frontier: Transformer-based models in EEG signal analysis for brain-computer interfaces

This review systematically explores the application of transformer-based models in EEG signal processing and brain-computer interface (BCI) development, with a distinct focus on ensuring methodological rigour and adhering to empirical validations within the existing literature. By examining various transformer architectures, such as the Temporal Spatial Transformer Network (TSTN) and EEG Conformer, this review delineates their capabilities in mitigating challenges intrinsic to EEG data, such as noise and artifacts, and their subsequent implications on decoding and classification accuracies across disparate mental tasks. The analytical scope extends to a meticulous examination of attention mechanisms within transformer models, delineating their role in illuminating critical temporal and spatial EEG features and facilitating interpretability in model decision-making processes. The discourse additionally encapsulates emerging works that substantiate the efficacy of transformer models in noise reduction of EEG signals and diversifying applications beyond the conventional motor imagery paradigm. Furthermore, this review elucidates evident gaps and propounds exploratory avenues in the applications of pre-trained transformers in EEG analysis and the potential expansion into real-time and multi-task BCI applications. Collectively, this review distils extant knowledge, navigates through the empirical findings, and puts forward a structured synthesis, thereby serving as a conduit for informed future research endeavours in transformer-enhanced, EEG-based BCI systems.

Artificial intelligence for diagnostic and prognostic neuroimaging in dementia: A systematic review

INTRODUCTION

Artificial intelligence (AI) and neuroimaging offer new opportunities for diagnosis and prognosis of dementia.

METHODS

We systematically reviewed studies reporting AI for neuroimaging in diagnosis and/or prognosis of cognitive neurodegenerative diseases.

RESULTS

A total of 255 studies were identified. Most studies relied on the Alzheimer's Disease Neuroimaging Initiative dataset. Algorithmic classifiers were the most commonly used AI method (48%) and discriminative models performed best for differentiating Alzheimer's disease from controls. The accuracy of algorithms varied with the patient cohort, imaging modalities, and stratifiers used. Few studies performed validation in an independent cohort.

DISCUSSION

The literature has several methodological limitations including lack of sufficient algorithm development descriptions and standard definitions. We make recommendations to improve model validation including addressing key clinical questions, providing sufficient description of AI methods and validating findings in independent datasets. Collaborative approaches between experts in AI and medicine will help achieve the promising potential of AI tools in practice.

HIGHLIGHTS

There has been a rapid expansion in the use of machine learning for diagnosis and prognosis in neurodegenerative disease Most studies (71%) relied on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with no other individual dataset used more than five times There has been a recent rise in the use of more complex discriminative models (e.g., neural networks) that performed better than other classifiers for classification of AD vs healthy controls We make recommendations to address methodological considerations, addressing key clinical questions, and validation We also make recommendations for the field more broadly to standardize outcome measures, address gaps in the literature, and monitor sources of bias.

Machine Learning on Visibility Graph Features Discriminates the Cognitive Event-Related Potentials of Patients with Early Alzheimer's Disease from Healthy Aging

We present a framework for electroencephalography (EEG)-based classification between patients with Alzheimer's Disease (AD) and robust normal elderly (RNE) via a graph theory approach using visibility graphs (VGs). This EEG VG approach is motivated by research that has demonstrated differences between patients with early stage AD and RNE using various features of EEG oscillations or cognitive event-related potentials (ERPs). In the present study, EEG signals recorded during a word repetition experiment were wavelet decomposed into 5 sub-bands (δ,θ,α,β,γ). The raw and band-specific signals were then converted to VGs for analysis. Twelve graph features were tested for differences between the AD and RNE groups, and t-tests employed for feature selection. The selected features were then tested for classification using traditional machine learning and deep learning algorithms, achieving a classification accuracy of 100% with linear and non-linear classifiers. We further demonstrated that the same features can be generalized to the classification of mild cognitive impairment (MCI) converters, i.e., prodromal AD, against RNE with a maximum accuracy of 92.5%. Code is released online to allow others to test and reuse this framework.

EEG Signal Complexity Measurements to Enhance BCI-Based Stroke Patients' Rehabilitation

The second leading cause of death and one of the most common causes of disability in the world is stroke. Researchers have found that brain-computer interface (BCI) techniques can result in better stroke patient rehabilitation. This study used the proposed motor imagery (MI) framework to analyze the electroencephalogram (EEG) dataset from eight subjects in order to enhance the MI-based BCI systems for stroke patients. The preprocessing portion of the framework comprises the use of conventional filters and the independent component analysis (ICA) denoising approach. Fractal dimension (FD) and Hurst exponent (Hur) were then calculated as complexity features, and Tsallis entropy (TsEn) and dispersion entropy (DispEn) were assessed as irregularity parameters. The MI-based BCI features were then statistically retrieved from each participant using two-way analysis of variance (ANOVA) to demonstrate the individuals' performances from four classes (left hand, right hand, foot, and tongue). The dimensionality reduction algorithm, Laplacian Eigenmap (LE), was used to enhance the MI-based BCI classification performance. Utilizing k-nearest neighbors (KNN), support vector machine (SVM), and random forest (RF) classifiers, the groups of post-stroke patients were ultimately determined. The findings show that LE with RF and KNN obtained 74.48% and 73.20% accuracy, respectively; therefore, the integrated set of the proposed features along with ICA denoising technique can exactly describe the proposed MI framework, which may be used to explore the four classes of MI-based BCI rehabilitation. This study will help clinicians, doctors, and technicians make a good rehabilitation program for people who have had a stroke.

Comparison of decomposition algorithms for identification of single motor units in ultrafast ultrasound image sequences of low force voluntary skeletal muscle contractions

OBJECTIVE

In this study, the aim was to compare the performance of four spatiotemporal decomposition algorithms (stICA, stJADE, stSOBI, and sPCA) and parameters for identifying single motor units in human skeletal muscle under voluntary isometric contractions in ultrafast ultrasound image sequences as an extension of a previous study. The performance was quantified using two measures: (1) the similarity of components' temporal characteristics against gold standard needle electromyography recordings and (2) the agreement of detected sets of components between the different algorithms.

RESULTS

We found that out of these four algorithms, no algorithm significantly improved the motor unit identification success compared to stICA using spatial information, which was the best together with stSOBI using either spatial or temporal information. Moreover, there was a strong agreement of detected sets of components between the different algorithms. However, stJADE (using temporal information) provided with complementary successful detections. These results suggest that the choice of decomposition algorithm is not critical, but there may be a methodological improvement potential to detect more motor units.

Mental Workload Classification Method Based on EEG Cross-Session Subspace Alignment

Electroencephalogram (EEG) signals are sensitive to the level of Mental Workload (MW). However, the random non-stationarity of EEG signals will lead to low accuracy and a poor generalization ability for cross-session MW classification. To solve this problem of the different marginal distribution of EEG signals in different time periods, an MW classification method based on EEG Cross-Session Subspace Alignment (CSSA) is presented to identify the level of MW induced in visual manipulation tasks. The Independent Component Analysis (ICA) method is used to obtain the Independent Components (ICs) of labeled and unlabeled EEG signals. The energy features of ICs are extracted as source domains and target domains, respectively. The marginal distributions of source subspace base vectors are aligned with the target subspace base vectors based on the linear mapping. The Kullback–Leibler (KL) divergences between the two domains are calculated to select approximately similar transformed base vectors of source subspace. The energy features in all selected vectors are trained to build a new classifier using the Support Vector Machine (SVM). Then it can realize MW classification using the cross-session EEG signals, and has good classification accuracy.

Single-Channel EEG Features Reveal an Association With Cognitive Decline in Seniors Performing Auditory Cognitive Assessment

Background

Cognitive decline remains highly underdiagnosed despite efforts to find novel cognitive biomarkers. Electroencephalography (EEG) features based on machine-learning (ML) may offer a non-invasive, low-cost approach for identifying cognitive decline. However, most studies use cumbersome multi-electrode systems. This study aims to evaluate the ability to assess cognitive states using machine learning (ML)-based EEG features extracted from a single-channel EEG with an auditory cognitive assessment.

Methods

This study included data collected from senior participants in different cognitive states (60) and healthy controls (22), performing an auditory cognitive assessment while being recorded with a single-channel EEG. Mini-Mental State Examination (MMSE) scores were used to designate groups, with cutoff scores of 24 and 27. EEG data processing included wavelet-packet decomposition and ML to extract EEG features. Data analysis included Pearson correlations and generalized linear mixed-models on several EEG variables: Delta and Theta frequency-bands and three ML-based EEG features: VC9, ST4, and A0, previously extracted from a different dataset and showed association with cognitive load.

Results

MMSE scores significantly correlated with reaction times and EEG features A0 and ST4. The features also showed significant separation between study groups: A0 separated between the MMSE < 24 and MMSE ≥ 28 groups, in addition to separating between young participants and senior groups. ST4 differentiated between the MMSE < 24 group and all other groups (MMSE 24–27, MMSE ≥ 28 and healthy young groups), showing sensitivity to subtle changes in cognitive states. EEG features Theta, Delta, A0, and VC9 showed increased activity with higher cognitive load levels, present only in the healthy young group, indicating different activity patterns between young and senior participants in different cognitive states. Consisted with previous reports, this association was most prominent for VC9 which significantly separated between all level of cognitive load.

Discussion

This study successfully demonstrated the ability to assess cognitive states with an easy-to-use single-channel EEG using an auditory cognitive assessment. The short set-up time and novel ML features enable objective and easy assessment of cognitive states. Future studies should explore the potential usefulness of this tool for characterizing changes in EEG patterns of cognitive decline over time, for detection of cognitive decline on a large scale in every clinic to potentially allow early intervention.

Trial Registration

NIH Clinical Trials Registry [https://clinicaltrials.gov/ct2/show/results/NCT04386902], identifier [NCT04386902]; Israeli Ministry of Health registry [https://my.health.gov.il/CliniTrials/Pages/MOH_2019-10-07_007352.aspx], identifier [007352].

An Overview of ICA/BSS-Based Application to Alzheimer's Brain Signal Processing

Alzheimer's disease (AD) is by far the most common cause of dementia associated with aging. Early and accurate diagnosis of AD and ability to track progression of the disease is increasingly important as potential disease-modifying therapies move through clinical trials. With the advent of biomedical techniques, such as computerized tomography (CT), electroencephalography (EEG), magnetoencephalography (MEG), positron emission tomography (PET), magnetic resonance imaging (MRI), and functional magnetic resonance imaging (fMRI), large amounts of data from Alzheimer's patients have been acquired and processed from which AD-related information or "signals" can be assessed for AD diagnosis. It remains unknown how best to mine complex information from these brain signals to aid in early diagnosis of AD. An increasingly popular technique for processing brain signals is independent component analysis or blind source separation (ICA/BSS) that separates blindly observed signals into original signals that are as independent as possible. This overview focuses on ICA/BSS-based applications to AD brain signal processing.

Internet of Things and Machine Learning for Healthy Ageing: Identifying the Early Signs of Dementia

Identifying the symptoms of the early stages of dementia is a difficult task, particularly for older adults living in residential care. Internet of Things (IoT) and smart environments can assist with the early detection of dementia, by nonintrusive monitoring of the daily activities of the older adults. In this work, we focus on the daily life activities of adults in a smart home setting to discover their potential cognitive anomalies using a public dataset. After analysing the dataset, extracting the features, and selecting distinctive features based on dynamic ranking, a classification model is built. We compare and contrast several machine learning approaches for developing a reliable and efficient model to identify the cognitive status of monitored adults. Using our predictive model and our approach of distinctive feature selection, we have achieved 90.74% accuracy in detecting the onset of dementia.

Representation based on ordinal patterns for seizure detection in EEG signals

EEG signals carry rich information about brain activity and play an important role in the diagnosis and recognition of epilepsy. Numerous algorithms using EEG signals to detect seizures have been developed in recent decades. However, most of them require well-designed features that highly depend on domain-specific knowledge and algorithm expertise. In this study, we introduce the unigram ordinal pattern (UniOP) and bigram ordinal pattern (BiOP) representations to capture the different underlying dynamics of time series, which only assumes that time series derived from different dynamics can be characterized by repeated ordinal patterns. Specifically, we first transform each subsequence in a time series into the corresponding ordinal pattern in terms of the ranking of values and consider the distribution of ordinal patterns of all subsequences as the UniOP representation. Furthermore, we consider the distribution of the cooccurrence of ordinal patterns as the BiOP representation to characterize the contextual information for each ordinal pattern. We then combine the proposed representations with the nearest neighbor algorithm to evaluate its effectiveness on three publicly available seizure datasets. The results on the Bonn EEG dataset demonstrate that this method provides more than 90% accuracy, sensitivity, and specificity in most cases and outperforms several state-of-the-art methods, which proves its ability to capture the key information of the underlying dynamics of EEG time series at healthy, seizure-free, and seizure states. The results on the second dataset are comparable with the state-of-the-art method, showing the good generalization ability of the proposed method. All performance metrics on the third dataset are approximately 89%, which demonstrates that the proposed representations are suitable for large-scale datasets.

Alpha-wave Characteristics in Psychophysiological Insomnia

Individuals with psychophysiological insomnia (Psych-Insomnia) would show raised cortical arousal through their initiating sleep. Frequent changes in the alpha activity can be indicative of visual cortical activation, even without visual stimulation or retinal input. Therefore, we aimed to investigate alpha-wave characteristics in Psych-Insomnia before and after sleep onset. In a case–control study, 11 individuals with Psych-Insomnia (age: 44.00 ± 13.27) and 11 age-, sex-, and body mass index-matched healthy individuals (age: 41.64 ± 15.89) were recruited for this study. An overnight polysomnography monitoring was performed. Alpha characteristics were calculated from wake before sleep onsets (WBSOs), wake after sleep onset, rapid eye movement, and nonrapid eye movement in the both groups. They include the alpha power and alpha frequency and their variability in the central region. In the WBSO, alpha activity and variability were higher in the Psych-Insomnia individuals compared to healthy individuals. In both groups, alpha frequency variability was observed at approximately 1 Hz. Alpha-wave synchronization in Psych-Insomnia individuals was higher than the group with normal sleep. Individuals with Psych-Insomnia have a lot of imagination in the wake before sleep, which can be caused by stress, everyday concerns, and daily concerns.

Effects of Anserine/Carnosine Supplementation on Mild Cognitive Impairment with APOE4

Background: Oral supplementation of anserine/carnosine helps preserve cognitive functions in healthy older adults. Mild cognitive impairment (MCI) is a transition between cognitive-normal and dementia. Therefore, it needs to investigate whether anserine/carnosine supplementation (ACS) has effects on subjects with MCI. Methods: A randomized, double-blind, placebo-controlled 12-week trial was performed. Fifty-four subjects with MCI were randomized to an active group ingesting 750 mg of anserine and 250 mg of carnosine per day or a placebo (1:1). Evaluation of cognitive change was conducted utilizing a psychometric test battery. Results: The score improvement in the global Clinical Dementia Rating (gloCDR) was superior in the active group than placebo (p = 0.023). No beneficial effect in the active group was detected in the other psychometric tests including the Mini-Mental State Examination (MMSE), the Wechsler Memory Scale, and the Alzheimer’s Disease Assessment Scale (ADAS). When APOE4 positive (APOE4 (+)) or negative (APOE4 (-)) subjects were separately analyzed, beneficial change in the APOE4 (+) subjects was observed in MMSE (p = 0.025) as well as in gloCDR (p = 0.026). Conclusions: The present study might suggest that protective effects against cognitive decline in APOE4 (+) MCI subjects exist.

Analysis of long range dependence in the EEG signals of Alzheimer patients

Alzheimer's disease (AD), a cognitive disability is analysed using a long range dependence parameter, hurst exponent (HE), calculated based on the time domain analysis of the measured electrical activity of brain. The electroencephalogram (EEG) signals of controls and mild cognitive impairment (MCI)-AD patients are evaluated under normal resting and mental arithmetic conditions. Simultaneous low pass filtering and total variation denoising algorithm is employed for preprocessing. Larger values of HE observed in the right hemisphere of the brain for AD patients indicated a decrease in irregularity of the EEG signal under cognitive task conditions. Correlations between HE and the neuropsychological indices are analysed using bivariate correlation analysis. The observed reduction in the values of Auto mutual information and cross mutual information in the local antero-frontal and distant regions in the brain hemisphere indicates the loss of information transmission in MCI-AD patients.

Analysis of long range dependence in the EEG signals of Alzheimer patients

Alzheimer's disease (AD), a cognitive disability is analysed using a long range dependence parameter, hurst exponent (HE), calculated based on the time domain analysis of the measured electrical activity of brain. The electroencephalogram (EEG) signals of controls and mild cognitive impairment (MCI)-AD patients are evaluated under normal resting and mental arithmetic conditions. Simultaneous low pass filtering and total variation denoising algorithm is employed for preprocessing. Larger values of HE observed in the right hemisphere of the brain for AD patients indicated a decrease in irregularity of the EEG signal under cognitive task conditions. Correlations between HE and the neuropsychological indices are analysed using bivariate correlation analysis. The observed reduction in the values of Auto mutual information and cross mutual information in the local antero-frontal and distant regions in the brain hemisphere indicates the loss of information transmission in MCI-AD patients.

Separation of P300 event-related potential using time varying time-lag blind source separation algorithm

Synchronous averaging over time locked single-trial of event-related potential (ERP) is known as the simplest scheme to extract P300 component. This method assumes the P300 features are invariant through the time while they are affected by factors like brain fatigue and habitation. In this study, a new scheme is proposed termed as time-varying time-lag blind source separation (TT-BSS) which is upon the second order statistics of signal to separate P300 waveform from the background electroencephalogram (EEG) while it captures the time variation of P300 component. The time-lag parameter for all channels is determined by maximizing the correlation (similarity) between two successive trials. As the time-lag parameter is varying by time (trial to trial), an average is taken over the time-lag covariance matrices of all two consecutive trials. TT-BSS finally estimates a transform (separating matrix) by joint diagnolization of the covariance matrix of trials and the averaged covariance matrix of the time varying time-lag. To assess the proposed scheme, synthetic and real EEGs containing P300 are used. The EEG signals were collected from twenty schizophrenic and twenty age-matched normal subjects via 20 channels through the resting state and in presence of the oddball audio stimulus. Empirical achievements over the simulated and real EEGs imply on the superiority of TT-BSS in dynamic estimation of P300 characteristics compared to state-of-the-art counterparts such as constant time-lag BSS, constrained BSS and synchronous averaging.

Automatic Artifact Removal in EEG of Normal and Demented Individuals Using ICA-WT during Working Memory Tasks

Characterizing dementia is a global challenge in supporting personalized health care. The electroencephalogram (EEG) is a promising tool to support the diagnosis and evaluation of abnormalities in the human brain. The EEG sensors record the brain activity directly with excellent time resolution. In this study, EEG sensor with 19 electrodes were used to test the background activities of the brains of five vascular dementia (VaD), 15 stroke-related patients with mild cognitive impairment (MCI), and 15 healthy subjects during a working memory (WM) task. The objective of this study is twofold. First, it aims to enhance the recorded EEG signals using a novel technique that combines automatic independent component analysis (AICA) and wavelet transform (WT), that is, the AICA–WT technique; second, it aims to extract and investigate the spectral features that characterize the post-stroke dementia patients compared to the control subjects. The proposed AICA–WT technique is a four-stage approach. In the first stage, the independent components (ICs) were estimated. In the second stage, three-step artifact identification metrics were applied to detect the artifactual components. The components identified as artifacts were marked as critical and denoised through DWT in the third stage. In the fourth stage, the corrected ICs were reconstructed to obtain artifact-free EEG signals. The performance of the proposed AICA–WT technique was compared with those of two other techniques based on AICA and WT denoising methods using cross-correlation XCorr and peak signal to noise ratio (PSNR) (ANOVA, p ˂ 0.05). The AICA–WT technique exhibited the best artifact removal performance. The assumption that there would be a deceleration of EEG dominant frequencies in VaD and MCI patients compared with control subjects was assessed with AICA–WT (ANOVA, p ˂ 0.05). Therefore, this study may provide information on post-stroke dementia particularly VaD and stroke-related MCI patients through spectral analysis of EEG background activities that can help to provide useful diagnostic indexes by using EEG signal processing.

Regularized Linear Discriminant Analysis of EEG Features in Dementia Patients

The present study explores if EEG spectral parameters can discriminate between healthy elderly controls (HC), Alzheimer's disease (AD) and vascular dementia (VaD) using. We considered EEG data recorded during normal clinical routine with 114 healthy controls (HC), 114 AD, and 114 VaD patients. The spectral features extracted from the EEG were the absolute delta power, decay from lower to higher frequencies, amplitude, center and dispersion of the alpha power and baseline power of the entire frequency spectrum. For discrimination, we submitted these EEG features to regularized linear discriminant analysis algorithm with a 10-fold cross-validation. To check the consistency of the results obtained by our classifiers, we applied bootstrap statistics. Four binary classifiers were used to discriminate HC from AD, HC from VaD, AD from VaD, and HC from dementia patients (AD or VaD). For each model, we measured the discrimination performance using the area under curve (AUC) and the accuracy of the cross-validation (cv-ACC). We applied this procedure using two different sets of predictors. The first set considered all the features extracted from the 22 channels. For the second set of features, we automatically rejected features poorly correlated with their labels. Fairly good results were obtained when discriminating HC from dementia patients with AD or VaD (AUC = 0.84). We also obtained AUC = 0.74 for discrimination of AD from HC, AUC = 0.77 for discrimination of VaD from HC, and finally AUC = 0.61 for discrimination of AD from VaD. Our models were able to separate HC from dementia patients, and also and to discriminate AD from VaD above chance. Our results suggest that these features may be relevant for the clinical assessment of patients with dementia.

Fuzzy-entropy threshold based on a complex wavelet denoising technique to diagnose Alzheimer disease

The presence of irregularities in electroencephalographic (EEG) signals entails complexities during the Alzheimer's disease (AD) diagnosis. In addition, the uncertainty presented on EEG raises major issues in the improvement of the classification rate. The multi-resolution analysis through an optimum threshold will likely achieve better results in distinguishing AD and normal EEG signals. Hence, a fuzzy-entropy concept defined in a complex multi-resolution wavelet has been proposed to obtain the most appropriate threshold. First, the complex coefficients are fuzzified using a Gaussian membership function. Afterwards, the ability of the proposed fuzzy-entropy threshold has been compared with traditional thresholds in complex wavelet domain. Experimental results show that the authors' methodology produces a higher signal-to-noise ratio and a lower root-mean-square error than traditional approaches. Moreover, a neural network scheme is performed along several features to classify AD from normal EEG signals obtaining a specificity of 87.5%.

Comparative Study of Wavelet-Based Unsupervised Ocular Artifact Removal Techniques for Single-Channel EEG Data

Electroencephalogram (EEG) is a technique for recording the asynchronous activation of neuronal firing inside the brain with non-invasive scalp electrodes. Artifacts, such as eye blink activities, can corrupt these neuronal signals. While ocular artifact (OA) removal is well investigated for multiple channel EEG systems, in alignment with the recent momentum toward minimalistic EEG systems for use in natural environments, we investigate unsupervised and effective removal of OA from single-channel streaming raw EEG data. In this paper, the unsupervised wavelet transform (WT) decomposition technique was systematically evaluated for the effectiveness of OA removal for a single-channel EEG system. A set of seven raw EEG data set was analyzed. Two commonly used WT methods, Discrete Wavelet Transform (DWT) and Stationary Wavelet Transform (SWT), were applied. Four WT basis functions, namely, haar, coif3, sym3, and bior4.4, were considered for OA removal with universal threshold and statistical threshold (ST). To quantify OA removal efficacy from single-channel EEG, five performance metrics were utilized: correlation coefficients, mutual information, signal-to-artifact ratio, normalized mean square error, and time-frequency analysis. The temporal and spectral analysis shows that the optimal combination could be DWT with ST with coif3 or bior4.4 to remove OA among 16 combinations. This paper demonstrates that the WT can be an effective tool for unsupervised OA removal from single-channel EEG data for real-time applications.

Delay of cognitive gamma responses in Alzheimer's disease

Event-related oscillations (EROs) reflect cognitive brain dynamics, while sensory-evoked oscillations (SEOs) reflect sensory activities. Previous reports from our lab have shown that those with Alzheimer's disease (AD) or mild cognitive impairment (MCI) have decreased activity and/or coherence in delta, theta, alpha and beta cognitive responses. In the current study, we investigated gamma responses in visual SEO and ERO in 15 patients with AD and in 15 age-, gender- and education-matched healthy controls. The following parameters were analyzed over the parietal-occipital regions in both groups: (i) latency of the maximum gamma response over a 0-800 ms time window; (ii) the maximum peak-to-peak amplitudes for each participant's averaged SEO and ERO gamma responses in 3 frequency ranges (25-30, 30-35, 40-48 Hz); and (iii) the maximum peak-to-peak amplitudes for each participant's averaged SEO and ERO gamma responses over a 0-800 ms time block containing four divided time windows (0-200, 200-400, 400-600, and 600-800 ms). There were main group effects in terms of both latency and peak-to-peak amplitudes of gamma ERO. However, peak-to-peak gamma ERO amplitude differences became noticeable only when the time block was divided into four time windows. SEO amplitudes in the 25-30 Hz frequency range of the 0-200 ms time window over the left hemisphere were greater in the healthy controls than in those with AD. Gamma target ERO latency was delayed up to 138 ms in AD patients when compared to healthy controls. This finding may be an effect of lagged neural signaling in cognitive circuits, which is reflected by the delayed gamma responses in those with AD. Based on the results of this study, we propose that gamma responses should be examined in a more detailed fashion using multiple frequency and time windows.

Towards Semi-Automatic Artifact Rejection for the Improvement of Alzheimer's Disease Screening from EEG Signals

A large number of studies have analyzed measurable changes that Alzheimer's disease causes on electroencephalography (EEG). Despite being easily reproducible, those markers have limited sensitivity, which reduces the interest of EEG as a screening tool for this pathology. This is for a large part due to the poor signal-to-noise ratio of EEG signals: EEG recordings are indeed usually corrupted by spurious extra-cerebral artifacts. These artifacts are responsible for a consequent degradation of the signal quality. We investigate the possibility to automatically clean a database of EEG recordings taken from patients suffering from Alzheimer's disease and healthy age-matched controls. We present here an investigation of commonly used markers of EEG artifacts: kurtosis, sample entropy, zero-crossing rate and fractal dimension. We investigate the reliability of the markers, by comparison with human labeling of sources. Our results show significant differences with the sample entropy marker. We present a strategy for semi-automatic cleaning based on blind source separation, which may improve the specificity of Alzheimer screening using EEG signals.

EEG Spectral Features Discriminate between Alzheimer's and Vascular Dementia

Alzheimer's disease (AD) and vascular dementia (VaD) present with similar clinical symptoms of cognitive decline, but the underlying pathophysiological mechanisms differ. To determine whether clinical electroencephalography (EEG) can provide information relevant to discriminate between these diagnoses, we used quantitative EEG analysis to compare the spectra between non-medicated patients with AD (n = 77) and VaD (n = 77) and healthy elderly normal controls (NC) (n = 77). We use curve-fitting with a combination of a power loss and Gaussian function to model the averaged resting-state spectra of each EEG channel extracting six parameters. We assessed the performance of our model and tested the extracted parameters for group differentiation. We performed regression analysis in a multivariate analysis of covariance with group, age, gender, and number of epochs as predictors and further explored the topographical group differences with pair-wise contrasts. Significant topographical differences between the groups were found in several of the extracted features. Both AD and VaD groups showed increased delta power when compared to NC, whereas the AD patients showed a decrease in alpha power for occipital and temporal regions when compared with NC. The VaD patients had higher alpha power than NC and AD. The AD and VaD groups showed slowing of the alpha rhythm. Variability of the alpha frequency was wider for both AD and VaD groups. There was a general decrease in beta power for both AD and VaD. The proposed model is useful to parameterize spectra, which allowed extracting relevant clinical EEG key features that move toward simple and interpretable diagnostic criteria.

Recognizing mild cognitive impairment based on network connectivity analysis of resting EEG with zero reference

The diagnosis of mild cognitive impairment (MCI) is very helpful for early therapeutic interventions of Alzheimer's disease (AD). MCI has been proven to be correlated with disorders in multiple brain areas. In this paper, we used information from resting brain networks at different EEG frequency bands to reliably recognize MCI. Because EEG network analysis is influenced by the reference that is used, we also evaluate the effect of the reference choices on the resting scalp EEG network-based MCI differentiation. The conducted study reveals two aspects: (1) the network-based MCI differentiation is superior to the previously reported classification that uses coherence in the EEG; and (2) the used EEG reference influences the differentiation performance, and the zero approximation technique (reference electrode standardization technique, REST) can construct a more accurate scalp EEG network, which results in a higher differentiation accuracy for MCI. This study indicates that the resting scalp EEG-based network analysis could be valuable for MCI recognition in the future.

Signal-to-noise ratio of the MEG signal after preprocessing

BACKGROUND

Magnetoencephalography (MEG) provides a direct measure of brain activity with high combined spatiotemporal resolution. Preprocessing is necessary to reduce contributions from environmental interference and biological noise.

NEW METHOD

The effect on the signal-to-noise ratio of different preprocessing techniques is evaluated. The signal-to-noise ratio (SNR) was defined as the ratio between the mean signal amplitude (evoked field) and the standard error of the mean over trials.

RESULTS

Recordings from 26 subjects obtained during and event-related visual paradigm with an Elekta MEG scanner were employed. Two methods were considered as first-step noise reduction: Signal Space Separation and temporal Signal Space Separation, which decompose the signal into components with origin inside and outside the head. Both algorithm increased the SNR by approximately 100%. Epoch-based methods, aimed at identifying and rejecting epochs containing eye blinks, muscular artifacts and sensor jumps provided an SNR improvement of 5-10%. Decomposition methods evaluated were independent component analysis (ICA) and second-order blind identification (SOBI). The increase in SNR was of about 36% with ICA and 33% with SOBI.

COMPARISON WITH EXISTING METHODS

No previous systematic evaluation of the effect of the typical preprocessing steps in the SNR of the MEG signal has been performed.

CONCLUSIONS

The application of either SSS or tSSS is mandatory in Elekta systems. No significant differences were found between the two. While epoch-based methods have been routinely applied the less often considered decomposition methods were clearly superior and therefore their use seems advisable.

Suppression of translucent elongated structures: applications in chest radiography

Projection images, such as those routinely acquired in radiological practice, are difficult to analyze because multiple 3-D structures superimpose at a single point in the 2-D image. Removal of particular superimposed structures may improve interpretation of these images, both by humans and by computers. This work therefore presents a general method to isolate and suppress structures in 2-D projection images. The focus is on elongated structures, which allows an intensity model of a structure of interest to be extracted using local information only. The model is created from profiles sampled perpendicular to the structure. Profiles containing other structures are detected and removed to reduce the influence on the model. Subspace filtering, using blind source separation techniques, is applied to separate the structure to be suppressed from other structures. By subtracting the modeled structure from the original image a structure suppressed image is created. The method is evaluated in four experiments. In the first experiment ribs are suppressed in 20 artificial radiographs simulated from 3-D lung computed tomography (CT) images. The proposed method with blind source separation and outlier detection shows superior suppression of ribs in simulated radiographs, compared to a simplified approach without these techniques. Additionally, the ability of three observers to discriminate between patches containing ribs and containing no ribs, as measured by the area under the receiver operating characteristic curve (AUC), reduced from 0.99-1.00 on original images to 0.75-0.84 on suppressed images. In the second experiment clavicles are suppressed in 253 chest radiographs. The effect of suppression on clavicle visibility is evaluated using the clavicle contrast and border response, showing a reduction of 78% and 34%, respectively. In the third experiment nodules extracted from CT were simulated close to the clavicles in 100 chest radiographs. It was found that after suppression contrast of the nodules was higher than of the clavicles (1.35 and 0.55, respectively) than on original images (1.83 and 2.46, respectively). In the fourth experiment catheters were suppressed in chest radiographs. The ability of three observers to discriminate between patches originating from 36 images with and 21 images without catheters, as measured by the AUC, reduced from 0.98-0.99 on original images to 0.64-0.74 on suppressed images. We conclude that the presented method can markedly reduce the visibility of elongated structures in chest radiographs and shows potential to enhance diagnosis.

Prediction of P300 BCI aptitude in severe motor impairment

Brain-computer interfaces (BCIs) provide a non-muscular communication channel for persons with severe motor impairments. Previous studies have shown that the aptitude with which a BCI can be controlled varies from person to person. A reliable predictor of performance could facilitate selection of a suitable BCI paradigm. Eleven severely motor impaired participants performed three sessions of a P300 BCI web browsing task. Before each session auditory oddball data were collected to predict the BCI aptitude of the participants exhibited in the current session. We found a strong relationship of early positive and negative potentials around 200 ms (elicited with the auditory oddball task) with performance. The amplitude of the P2 (r  =  −0.77) and of the N2 (r  =  −0.86) had the strongest correlations. Aptitude prediction using an auditory oddball was successful. The finding that the N2 amplitude is a stronger predictor of performance than P3 amplitude was reproduced after initially showing this effect with a healthy sample of BCI users. This will reduce strain on the end-users by minimizing the time needed to find suitable paradigms and inspire new approaches to improve performance.

Diagnosis of Alzheimer's disease from EEG by means of synchrony measures in optimized frequency bands

Several clinical studies have reported that EEG synchrony is affected by Alzheimer's disease (AD). In this paper a frequency band analysis of AD EEG signals is presented, with the aim of improving the diagnosis of AD using EEG signals. In this paper, multiple synchrony measures are assessed through statistical tests (Mann-Whitney U test), including correlation, phase synchrony and Granger causality measures. Moreover, linear discriminant analysis (LDA) is conducted with those synchrony measures as features. For the data set at hand, the frequency range (5-6 Hz) yields the best accuracy for diagnosing AD, which lies within the classical theta band (4-8 Hz). The corresponding classification error is 4.88% for directed transfer function (DTF) Granger causality measure. Interestingly, results show that EEG of AD patients is more synchronous than in healthy subjects within the optimized range 5-6 Hz, which is in sharp contrast with the loss of synchrony in AD EEG reported in many earlier studies. This new finding may provide new insights about the neurophysiology of AD. Additional testing on larger AD datasets is required to verify the effectiveness of the proposed approach.

Prediction of auditory and visual p300 brain-computer interface aptitude

OBJECTIVE

Brain-computer interfaces (BCIs) provide a non-muscular communication channel for patients with late-stage motoneuron disease (e.g., amyotrophic lateral sclerosis (ALS)) or otherwise motor impaired people and are also used for motor rehabilitation in chronic stroke. Differences in the ability to use a BCI vary from person to person and from session to session. A reliable predictor of aptitude would allow for the selection of suitable BCI paradigms. For this reason, we investigated whether P300 BCI aptitude could be predicted from a short experiment with a standard auditory oddball.

METHODS

Forty healthy participants performed an electroencephalography (EEG) based visual and auditory P300-BCI spelling task in a single session. In addition, prior to each session an auditory oddball was presented. Features extracted from the auditory oddball were analyzed with respect to predictive power for BCI aptitude.

RESULTS

Correlation between auditory oddball response and P300 BCI accuracy revealed a strong relationship between accuracy and N2 amplitude and the amplitude of a late ERP component between 400 and 600 ms. Interestingly, the P3 amplitude of the auditory oddball response was not correlated with accuracy.

CONCLUSIONS

Event-related potentials recorded during a standard auditory oddball session moderately predict aptitude in an audiory and highly in a visual P300 BCI. The predictor will allow for faster paradigm selection.

SIGNIFICANCE

Our method will reduce strain on patients because unsuccessful training may be avoided, provided the results can be generalized to the patient population.

Signal subspace integration for improved seizure localization

A subspace signal processing approach is proposed for improved scalp EEG-based localization of broad-focus epileptic seizures, and estimation of the directions of source arrivals (DOA). Ictal scalp EEGs from adult and pediatric patients with broad-focus seizures were first decomposed into dominant signal modes, and signal and noise subspaces at each modal frequency, to improve the signal-to-noise ratio while preserving the original data correlation structure. Transformed (focused) modal signals were then resynthesized into wideband signals from which the number of sources and DOA were estimated. These were compared to denoised signals via principal components analysis (PCA). Coherent subspace processing performed better than PCA, significantly improved the localization of ictal EEGs and the estimation of distinct sources and corresponding DOAs.

Optimization of EEG frequency bands for improved diagnosis of Alzheimer disease

Many clinical studies have shown that electroencephalograms (EEG) of Alzheimer patients (AD) often have an abnormal power spectrum. In this paper a frequency band analysis of AD EEG signals is presented, with the aim of improving the diagnosis of AD from EEG signals. Relative power in different EEG frequency bands is used as features to distinguish between AD patients and healthy control subjects. Many different frequency bands between 4 and 30 Hz are systematically tested, besides the traditional frequency bands, e.g., theta band (4-8 Hz). The discriminative power of the resulting spectral features is assessed through statistical tests (Mann-Whitney U test). Moreover, linear discriminant analysis is conducted with those spectral features. The optimized frequency ranges (4-7 Hz, 8-15 Hz, 19-24 Hz) yield substantially better classification performance than the traditional frequency bands (4-8 Hz, 8-12 Hz, 12-30 Hz); the frequency band 4-7 Hz is the optimal frequency range for detecting AD, which is similar to the classical theta band. The frequency bands were also optimized as features through leave-one-out crossvalidation, resulting in error-free classification. The optimized frequency bands may improve existing EEG based diagnostic tools for AD. Additional testing on larger AD datasets is required to verify the effectiveness of the proposed approach.

Interactions between occlusion and human brain function activities

There are few review articles in the area of human research that focus on the interactions between occlusion and brain function. This systematic review discusses the effect of occlusion on the health of the entire body with a focus on brain function. Available relevant articles in English from 1999 to 2011 were assessed in an online database and as hard copies in libraries. The selected 19 articles were classified into the following five categories: chewing and tongue movements, clenching and grinding, occlusal splints and occlusal interference, prosthetic rehabilitation, and pain and stimulation. The relationships between the brain activity observed in the motor and sensory cortices and movements of the oral and maxillofacial area, such as those produced by gum chewing, tapping and clenching, were investigated. It was found that the sensorimotor cortex was also affected by the placement of the occlusal interference devices, splints and implant prostheses. Brain activity may change depending on the strength of the movements in the oral and maxillofacial area. Therefore, mastication and other movements stimulate the activity in the cerebral cortex and may be helpful in preventing degradation of a brain function. However, these findings must be verified by evidence gathered from more subjects.

Multiway array decomposition analysis of EEGs in Alzheimer's disease

Methods for the extraction of features from physiological datasets are growing needs as clinical investigations of Alzheimer's disease (AD) in large and heterogeneous population increase. General tools allowing diagnostic regardless of recording sites, such as different hospitals, are essential and if combined to inexpensive non-invasive methods could critically improve mass screening of subjects with AD. In this study, we applied two state of the art multiway array decomposition (MAD) methods to extract unique features from electroencephalograms (EEGs) of AD patients obtained from multiple sites. In comparison to MAD, spectral-spatial average filter (SSFs) of control and AD subjects were used as well as a common blind source separation method, algorithm for multiple unknown signal extraction (AMUSE), and singular value decomposition (SVD) coupled to tensor unfolding. We trained a feed-forward multilayer perceptron (MLP) to validate and optimize AD classification from two independent databases. Using a third EEG dataset, we demonstrated that features extracted from MAD outperformed features obtained from SSFs AMUSE in terms of root mean squared error (RMSE) and reaching up to 100% of accuracy in test condition. We propose that MAD maybe a useful tool to extract features for AD diagnosis offering great generalization across multi-site databases and opening doors to the discovery of new characterization of the disease.

Improving Alzheimer's disease diagnosis with machine learning techniques

There is not a specific test to diagnose Alzheimer's disease (AD). Its diagnosis should be based upon clinical history, neuropsychological and laboratory tests, neuroimaging and electroencephalography (EEG). Therefore, new approaches are necessary to enable earlier and more accurate diagnosis and to follow treatment results. In this study we used a Machine Learning (ML) technique, named Support Vector Machine (SVM), to search patterns in EEG epochs to differentiate AD patients from controls. As a result, we developed a quantitative EEG (qEEG) processing method for automatic differentiation of patients with AD from normal individuals, as a complement to the diagnosis of probable dementia. We studied EEGs from 19 normal subjects (14 females/5 males, mean age 71.6 years) and 16 probable mild to moderate symptoms AD patients (14 females/2 males, mean age 73.4 years. The results obtained from analysis of EEG epochs were accuracy 79.9% and sensitivity 83.2%. The analysis considering the diagnosis of each individual patient reached 87.0% accuracy and 91.7% sensitivity.

Improving the specificity of EEG for diagnosing Alzheimer's disease

Objective. EEG has great potential as a cost-effective screening tool for Alzheimer's disease (AD). However, the specificity of EEG is not yet sufficient to be used in clinical practice. In an earlier study, we presented preliminary results suggesting improved specificity of EEG to early stages of Alzheimer's disease. The key to this improvement is a new method for extracting sparse oscillatory events from EEG signals in the time-frequency domain. Here we provide a more detailed analysis, demonstrating improved EEG specificity for clinical screening of MCI (mild cognitive impairment) patients. Methods. EEG data was recorded of MCI patients and age-matched control subjects, in rest condition with eyes closed. EEG frequency bands of interest were θ (3.5–7.5 Hz), α₁ (7.5–9.5 Hz), α₂ (9.5–12.5 Hz), and β (12.5–25 Hz). The EEG signals were transformed in the time-frequency domain using complex Morlet wavelets; the resulting time-frequency maps are represented by sparse bump models. Results. Enhanced EEG power in the θ range is more easily detected through sparse bump modeling; this phenomenon explains the improved EEG specificity obtained in our previous studies. Conclusions. Sparse bump modeling yields informative features in EEG signal. These features increase the specificity of EEG for diagnosing AD.

Slowing and Loss of Complexity in Alzheimer's EEG: Two Sides of the Same Coin?

Medical studies have shown that EEG of Alzheimer's disease (AD) patients is "slower" (i.e., contains more low-frequency power) and is less complex compared to age-matched healthy subjects. The relation between those two phenomena has not yet been studied, and they are often silently assumed to be independent. In this paper, it is shown that both phenomena are strongly related. Strong correlation between slowing and loss of complexity is observed in two independent EEG datasets: (1) EEG of predementia patients (a.k.a. Mild Cognitive Impairment; MCI) and control subjects; (2) EEG of mild AD patients and control subjects. The two data sets are from different patients, different hospitals and obtained through different recording systems. The paper also investigates the potential of EEG slowing and loss of EEG complexity as indicators of AD onset. In particular, relative power and complexity measures are used as features to classify the MCI and MiAD patients versus age-matched control subjects. When combined with two synchrony measures (Granger causality and stochastic event synchrony), classification rates of 83% (MCI) and 98% (MiAD) are obtained. By including the compression ratios as features, slightly better classification rates are obtained than with relative power and synchrony measures alone.

A hierarchical Bayesian approach for learning sparse spatio-temporal decompositions of multichannel EEG

Multichannel electroencephalography (EEG) offers a non-invasive tool to explore spatio-temporal dynamics of brain activity. With EEG recordings consisting of multiple trials, traditional signal processing approaches that ignore inter-trial variability in the data may fail to accurately estimate the underlying spatio-temporal brain patterns. Moreover, precise characterization of such inter-trial variability per se can be of high scientific value in establishing the relationship between brain activity and behavior. In this paper, a statistical modeling framework is introduced for learning spatio-temporal decompositions of multiple-trial EEG data recorded under two contrasting experimental conditions. By modeling the variance of source signals as random variables varying across trials, the proposed two-stage hierarchical Bayesian model is able to capture inter-trial amplitude variability in the data in a sparse way where a parsimonious representation of the data can be obtained. A variational Bayesian (VB) algorithm is developed for statistical inference of the hierarchical model. The efficacy of the proposed modeling framework is validated with the analysis of both synthetic and real EEG data. In the simulation study we show that even at low signal-to-noise ratios our approach is able to recover with high precision the underlying spatio-temporal patterns and the dynamics of source amplitude across trials; on two brain-computer interface (BCI) data sets we show that our VB algorithm can extract physiologically meaningful spatio-temporal patterns and make more accurate predictions than other two widely used algorithms: the common spatial patterns (CSP) algorithm and the Infomax algorithm for independent component analysis (ICA). The results demonstrate that our statistical modeling framework can serve as a powerful tool for extracting brain patterns, characterizing trial-to-trial brain dynamics, and decoding brain states by exploiting useful structures in the data.

Sensory evoked and event related oscillations in Alzheimer's disease: a short review

Diagnosis and treatment of Alzheimer's disease (AD) depend on clinical evaluation and there is a strong need for an objective tool as a biomarker. Our group has investigated brain oscillatory responses in a small group of AD subjects. We found that the de novo (untreated) AD group differs from both the cholinergically-treated AD group and aged-matched healthy controls in theta and delta responses over left frontal-central areas after cognitive stimulation. On the contrary, the difference observed in AD groups upon a sensory visual stimulation includes response increase over primary or secondary visual sensorial areas compared to controls. These findings imply at least two different neural networks, depending on type of stimulation (i.e. cognitive or sensory). The default mode defined as activity in resting state in AD seems to be affected electrophysiologically. Coherences are also very valuable in observing the group differences, especially when a cognitive stimulus is applied. In healthy controls, higher coherence values are elicited after a cognitive stimulus than after a sensory task. Our findings support the notion of disconnectivity of cortico-cortical connections in AD. The differences in comparison of oscillatory responses upon sensory and cognitive stimulations and their role as a biomarker in AD await further investigation in series with a greater number of subjects.

Reference estimation in EEG recordings

This work aims to analyze the reference (montage) problem in electroencephalographic (EEG) recordings. It is well accepted that EEG signals are a mixture of cerebral and extracerebral sources, and the solution to the reference problem depends on the hypothesized mixing model. We focus here on an acquisition model using a distant reference electrode and propose a method for determining and eliminating the reference signal which develops and improves Hu et al. work from [1]. The obtained solution, based on a constrained blind source separation (BSS) algorithm, outperforms the cited method on simulated noisy EEG signals for all noise levels.

Quantifying statistical interdependence by message passing on graphs-part II: multidimensional point processes

Stochastic event synchrony is a technique to quantify the similarity of pairs of signals. First, events are extracted from the two given time series. Next, one tries to align events from one time series with events from the other. The better the alignment, the more similar the two time series are considered to be. In Part I, the companion letter in this issue, one-dimensional events are considered; this letter concerns multidimensional events. Although the basic idea is similar, the extension to multidimensional point processes involves a significantly more difficult combinatorial problem and therefore is nontrivial. Also in the multidimensional case, the problem of jointly computing the pairwise alignment and SES parameters is cast as a statistical inference problem. This problem is solved by coordinate descent, more specifically, by alternating the following two steps: (1) estimate the SES parameters from a given pairwise alignment; (2) with the resulting estimates, refine the pairwise alignment. The SES parameters are computed by maximum a posteriori (MAP) estimation (step 1), in analogy to the one-dimensional case. The pairwise alignment (step 2) can no longer be obtained through dynamic programming, since the state space becomes too large. Instead it is determined by applying the max-product algorithm on a cyclic graphical model. In order to test the robustness and reliability of the SES method, it is first applied to surrogate data. Next, it is applied to detect anomalies in EEG synchrony of mild cognitive impairment (MCI) patients. Numerical results suggest that SES is significantly more sensitive to perturbations in EEG synchrony than a large variety of classical synchrony measures.

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

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 analysis of variance with age as a covariate was 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.