Machine learning aided classification of tremor in multiple sclerosis.

BACKGROUND: Tremors are frequent and disabling in people with multiple sclerosis (MS). Characteristic tremor frequencies in MS have a broad distribution range (1-10 Hz), which confounds the diagnostic from other forms of tremors. In this study, we propose a classification method for distinguishing MS tremors from other forms of cerebellar tremors. METHODS: Electromyogram (EMG), accelerometer and clinical data were obtained from a total of 120 [40 MS, 41 essential tremor (ET) and 39 Parkinson's disease (PD)] subjects. The proposed method - Soft Decision Wavelet Decomposition (SDWD) - was used to compute power spectral densities and receiver operating characteristic (ROC) analysis was performed for the automatic classification of the tremors. Association between the spectral features and clinical features (FTM - Fahn-Tolosa-Marin scale, UPDRS - Unified Parkinson's Disease Rating Scale), was assessed using a support vector regression (SVR) model. FINDINGS: Our developed analytical framework achieved an accuracy of up to 91.67% using accelerometer data and up to 91.60% using EMG signals for the differentiation of MS tremors and the tremors from ET and PD. In addition, SVR further revealed strong significant correlations between the selected discriminators and the clinical scores. INTERPRETATION: The proposed method, with high classification accuracy and strong correlations of these features to clinical outcomes, has clearly demonstrated the potential to complement the existing tremor-diagnostic approach in MS patients. FUNDING: This work was supported by the German Research Foundation (DFG): SFB-TR-128 (to SG, MM), MU 4354/1-1(to MM) and the Boehringer Ingelheim Fonds BIF-03 (to SG, MM).

Source imaging of deep-brain activity using the regional spatiotemporal Kalman filter.

BACKGROUND AND OBJECTIVE: The human brain displays rich and complex patterns of interaction within and among brain networks that involve both cortical and subcortical brain regions. Due to the limited spatial resolution of surface electroencephalography (EEG), EEG source imaging is used to reconstruct brain sources and investigate their spatial and temporal dynamics. The majority of EEG source imaging methods fail to detect activity from subcortical brain structures. The reconstruction of subcortical sources is a challenging task because the signal from these sources is weakened and mixed with artifacts and other signals from cortical sources. In this proof-of-principle study we present a novel EEG source imaging method, the regional spatiotemporal Kalman filter (RSTKF), that can detect deep brain activity. METHODS: The regional spatiotemporal Kalman filter (RSTKF) is a generalization of the spatiotemporal Kalman filter (STKF), which allows for the characterization of different regional dynamics in the brain. It is based on state-space modeling with spatially heterogeneous dynamical noise variances, since models with spatial and temporal homogeneity fail to describe the dynamical complexity of brain activity. First, RSTKF is tested using simulated EEG data from sources in the frontal lobe, putamen, and thalamus. After that, it is applied to non-averaged interictal epileptic spikes from a presurgical epilepsy patient with focal epileptic activity in the amygdalo-hippocampal complex. The results of RSTKF are compared to those of low-resolution brain electromagnetic tomography (LORETA) and of standard STKF. RESULTS: Only RSTKF is successful in consistently and accurately localizing the sources in deep brain regions. Additionally, RSTKF shows improved spatial resolution compared to LORETA and STKF. CONCLUSIONS: RSTKF is a generalization of STKF that allows for accurate, focal, and consistent localization of sources, especially in the deeper brain areas. In contrast to standard source imaging methods, RSTKF may find application in the localization of the epileptogenic zone in deeper brain structures, such as mesial frontal and temporal lobe epilepsies, especially in EEG recordings for which no reliable averaged spike shape can be obtained due to lack of the necessary number of spikes required to reach a certain signal-to-noise ratio level after averaging.

Spatial projection as a preprocessing step for EEG source reconstruction using spatiotemporal Kalman filtering.

The reconstruction of brain sources from non-invasive electroencephalography (EEG) or magnetoencephalography (MEG) via source imaging can be distorted by information redundancy in case of high-resolution recordings. Dimensionality reduction approaches such as spatial projection may be used to alleviate this problem. In this proof-of-principle paper we apply spatial projection to solve the problem of information redundancy in case of source reconstruction via spatiotemporal Kalman filtering (STKF), which is based on state-space modeling. We compare two approaches for incorporating spatial projection into the STKF algorithm and select the best approach based on its performance in source localization with respect to accurate estimation of source location, lack of spurious sources, computational speed and small number of required optimization steps in state-space model parameter estimation. We use state-of-the-art simulated EEG data based on neuronal population models, for which the number and location of sources is known, to validate the source reconstruction results of the STKF. The incorporation of spatial projection into the STKF algorithm solved the problem of information redundancy, resulting in correct source localization with no spurious sources, and decreased the overall computational time in STKF analysis. The results help make STKF analyses of high-density EEG, MEG or simultaneous MEG-EEG data more feasible.

Source reconstruction via the spatiotemporal Kalman filter and LORETA from EEG time series with 32 or fewer electrodes.

The clinical routine of non-invasive electroencephalography (EEG) is usually performed with 8-40 electrodes, especially in long-term monitoring, infants or emergency care. There is a need in clinical and scientific brain imaging to develop inverse solution methods that can reconstruct brain sources from these low-density EEG recordings. In this proof-of-principle paper we investigate the performance of the spatiotemporal Kalman filter (STKF) in EEG source reconstruction with 9-, 19- and 32- electrodes. We used simulated EEG data of epileptic spikes generated from lateral frontal and lateral temporal brain sources using state-of-the-art neuronal population models. For validation of source reconstruction, we compared STKF results to the location of the simulated source and to the results of low-resolution brain electromagnetic tomography (LORETA) standard inverse solution. STKF consistently showed less localization bias compared to LORETA, especially when the number of electrodes was decreased. The results encourage further research into the application of the STKF in source reconstruction of brain activity from low-density EEG recordings.

The performance of the spatiotemporal Kalman filter and LORETA in seizure onset localization.

The assumption of spatial-smoothness is often used to solve the bioelectric inverse problem during electroencephalographic (EEG) source imaging, e.g., in low resolution electromagnetic tomography (LORETA). Since the EEG data show a temporal structure, the combination of the temporal-smoothness and the spatial-smoothness constraints may improve the solution of the EEG inverse problem. This study investigates the performance of the spatiotemporal Kalman filter (STKF) method, which is based on spatial and temporal smoothness, in the localization of a focal seizure's onset and compares its results to those of LORETA. The main finding of the study was that the STKF with an autoregressive model of order two significantly outperformed LORETA in the accuracy and consistency of the localization, provided that the source space consists of a whole-brain volumetric grid. In the future, these promising results will be confirmed using data from more patients and performing statistical analyses on the results. Furthermore, the effects of the temporal smoothness constraint will be studied using different types of focal seizures.

The choice of the source space and the Laplacian matrix in LORETA and the spatio-temporal Kalman filter EEG inverse methods.

The discretization of the brain and the definition of the Laplacian matrix influence the results of methods based on spatial and spatio-temporal smoothness, since the Laplacian operator is used to define the smoothness based on the neighborhood of each grid point. In this paper, the results of low resolution electromagnetic tomography (LORETA) and the spatiotemporal Kalman filter (STKF) are computed using, first, a greymatter source space with the standard definition of the Laplacian matrix and, second, using a whole-brain source space and a modified definition of the Laplacian matrix. Electroencephalographic (EEG) source imaging results of five inter-ictal spikes from a pre-surgical patient with epilepsy are used to validate the two aforementioned approaches. The results using the whole-brain source space and the modified definition of the Laplacian matrix were concentrated in a single source activation, stable, and concordant with the location of the focal cortical dysplasia (FCD) in the patient's brain compared with the results which use a grey-matter grid and the classical definition of the Laplacian matrix. This proof-of-concept study demonstrates a substantial improvement of source localization with both LORETA and STKF and constitutes a basis for further research in a large population of patients with epilepsy.

Differences in hemispherical thalamo-cortical causality analysis during resting-state fMRI.

Thalamus is a very important part of the human brain. It has been reported to act as a relay for the messaging taking place between the cortical and sub-cortical regions of the brain. In the present study, we analyze the functional network between both hemispheres of the brain with the focus on thalamus. We used conditional Granger causality (CGC) and time-resolved partial directed coherence (tPDC) to investigate the functional connectivity. Results of CGC analysis revealed the asymmetry between connection strengths of the bilateral thalamus. Upon testing the functional connectivity of the default-mode network (DMN) at low-frequency fluctuations (LFF) and comparing coherence vectors using Spearman's rank correlation, we found that thalamus is a better source for the signals directed towards the contralateral regions of the brain, however, when thalamus acts as sink, it is a better sink for signals generated from ipsilateral regions of the brain.

Multi-modal causality analysis of eyes-open and eyes-closed data from simultaneously recorded EEG and MEG.

Owing to the recent advances in multi-modal data analysis, the aim of the present study was to analyze the functional network of the brain which remained the same during the eyes-open (EO) and eyes-closed (EC) resting task. The simultaneously recorded electroencephalogram (EEG) and magnetoencephalogram (MEG) were used for this study, recorded from five distinct cortical regions of the brain. We focused on the 'alpha' functional network, corresponding to the individual peak frequency in the alpha band. The total data set of 120 seconds was divided into three segments of 18 seconds each, taken from start, middle, and end of the recording. This segmentation allowed us to analyze the evolution of the underlying functional network. The method of time-resolved partial directed coherence (tPDC) was used to assess the causality. This method allowed us to focus on the individual peak frequency in the 'alpha' band (7-13 Hz). Because of the significantly higher power in the recorded EEG in comparison to MEG, at the individual peak frequency of the alpha band, results rely only on EEG. The MEG was used only for comparison. Our results show that different regions of the brain start to `disconnect' from one another over the course of time. The driving signals, along with the feedback signals between different cortical regions start to recede over time. This shows that, with the course of rest, brain regions reduce communication with each another.

Comparison of causality analysis on simultaneously measured fMRI and NIRS signals during motor tasks.

Brain activity can be measured using different modalities. Since most of the modalities tend to complement each other, it seems promising to measure them simultaneously. In to be presented research, the data recorded from Functional Magnetic Resonance Imaging (fMRI) and Near Infrared Spectroscopy (NIRS), simultaneously, are subjected to causality analysis using time-resolved partial directed coherence (tPDC). Time-resolved partial directed coherence uses the principle of state space modelling to estimate Multivariate Autoregressive (MVAR) coefficients. This method is useful to visualize both frequency and time dynamics of causality between the time series. Afterwards, causality results from different modalities are compared by estimating the Spearman correlation. In to be presented study, we used directionality vectors to analyze correlation, rather than actual signal vectors. Results show that causality analysis of the fMRI correlates more closely to causality results of oxy-NIRS as compared to deoxy-NIRS in case of a finger sequencing task. However, in case of simple finger tapping, no clear difference between oxy-fMRI and deoxy-fMRI correlation is identified.

DBS artifact suppression using a time-frequency domain filter.

Electroencephalogram (EEG) is a useful tool for brain research. However, during Deep-Brain Stimulation (DBS), there are large artifacts that obscure the physiological EEG signals. In this paper, we aim at suppressing the DBS artifacts by means of a time-frequency-domain filter. As a pre-processing step, Empirical-Mode Decomposition (EMD) is applied to detrend the raw data. The detrended signals are then filtered iteratively until, by visual inspection, the quality is good enough for interpretation. The proposed algorithm is demonstrated by an application to a clinical DBS-EEG data set in resting state and in finger-tapping condition. Moreover, a comparison with a Low-Pass filter (LPF) is provided, by visual inspection and by a quantitative measure.

Muscle artifact suppression using independent-component analysis and state-space modeling.

In this paper, we aim at suppressing the muscle artifacts present in electroencephalographic (EEG) signals with a technique based on a combination of Independent Component Analysis (ICA) and State-Space Modeling (SSM). The novel algorithm uses ICA to provide an initial model for SSM which is further optimized by the maximum-likelihood approach. This model is fitted to artifact-free data. Then it is applied to data with muscle artifacts. The state space is augmented by extracting additional components from the data prediction errors. The muscle artifacts are well separated in the additional components and, hence, a suppression of them can be performed. The proposed algorithm is demonstrated by application to a clinical epilepsy EEG data set.

A new diagnostic test to distinguish tremulous Parkinson's disease from advanced essential tremor.

BACKGROUND: Clinical distinction between advanced essential tremor and tremulous Parkinson's disease can be difficult. METHODS: In selected power spectra of accelerometric postural tremor recordings on the more affected side of 41 patients with essential tremor and 39 patients with tremulous Parkinson's disease being indistinguishable by tremor frequency, peak power or number of harmonic peaks, waveform asymmetry (autocorrelation decay), and mean peak power of all harmonic peaks were computed. Cutoff for essential tremor-Parkinson's disease distinction was determined by receiver operating characteristics. Diagnostic yield was tested in 12 clinically unclear patients with monosymptomatic tremor, subsequently definitively diagnosed with essential tremor (n = 2) or Parkinson's disease (n = 10) by 123-I FP-CIT-single-photon emission computed tomography, fluorodopa-positron emission tomography, or clinical course. RESULTS: By autocorrelation decay 64%, by mean harmonic peak power 94% (Parkinson's disease > essential tremor) of patients with a definite clinical diagnosis, and 11 of 12 clinically unclear patients were classified correctly. CONCLUSIONS: Mean harmonic power is a useful measure to separate clinically difficult cases of advanced essential tremor from tremulous Parkinson's disease.