Multichannel Electrocardiogram Decomposition Using Periodic Component Analysis

Sameni, Reza; Jutten, Christian; Shamsollahi, Mohammad Bagher

doi:10.1109/tbme.2008.919714

Cited by 179 publications

(149 citation statements)

References 13 publications

Supporting

Mentioning

148

Contrasting

Unclassified

Order By: Relevance

“…We present here two multi-lead approaches [104], one based on πCA (multi-πCA) [105] and another one based on PCA (multi-PCA) [89]. Both approaches follow a general scheme whose main stages are: preprocessing, signal transformation, TWA detection, signal reconstruction and TWA estimation (Fig.…”

Section: Ecg Markers For Characterization Of Spatio-temporal Repolmentioning

confidence: 99%

Techniques for Ventricular Repolarization Instability Assessment From the ECG

2016

View full text Add to dashboard Cite

Abstract-Instabilities in ventricular repolarization have been documented to be tightly linked to arrhythmia vulnerability. Translation of the information contained in the repolarization phase of the ECG into valuable clinical decision-making tools remains challenging. This work aims at providing an overview of the last advances in the proposal and quantification of ECG-derived indices that describe repolarization properties and whose alterations are related with threatening arrhythmogenic conditions. A review of the state-of-the-art is provided, spanning from the electrophysiological basis of ventricular repolarization to its characterization on the surface ECG through a set of temporal and spatial risk markers.Index Terms-Electrophysiological basis of the ECG, ECG waves, ECG intervals, repolarization instabilities, spatial and temporal ventricular repolarization dispersion, cardiac arrhythmias, biophysical modeling of the ECG, ECG signal processing, repolarization risk markers, T wave alternans, QT variability.

show abstract

Section: Ecg Markers For Characterization Of Spatio-temporal Repolmentioning

confidence: 99%

Techniques for Ventricular Repolarization Instability Assessment From the ECG

2016

View full text Add to dashboard Cite

show abstract

“…where R X 0 is defined in (5) and A X 0 ðmÞ is the spatial correlation of ðX ðmÞ 0 À X 0 Þ; which can be estimated as T6 T5 T3 T2 T1 T4 T7 T8 T6 T5 T3 T2 T1 T4 I II V6 V5 V3 V2 V1 V4 8 9 10 The weight w that minimizes (9) is given by the generalized eigenvector corresponding to the smallest generalized eigenvalue of the matrix pair ðA X 0 ðmÞ; R X 0 Þ: 24,25 The transformation matrix W is chosen as the generalized eigenvector matrix of ðA X 0 ðmÞ; R X 0 Þ; with the eigenvectors (columns) sorted according to the corresponding eigenvalues in ascending order of magnitude. In this way, the transformation Y ¼ W T X projects the most periodic component into the first row of Y; i.e., TWA, if present, is projected into the first transformed lead.…”

Section: Periodic Component Analysismentioning

confidence: 99%

“…This improvement, however, was limited by the fact that PCA uses a maximumvariance criterion to separate signal and noise into orthogonal subspaces, which may not be the best way of differentiating between the constituent sources of an ECG signal, particularly if they are not orthogonal. 4 In this study, we present a new multilead scheme based on periodic component analysis (pCA), a technique that was first proposed in Saul and Allen 25 and later applied to ECG signals in Sameni et al 24 With this technique, the variance criterion of PCA is replaced by a periodical structure criterion to separate TWA from non-alternant components, which is a more reasonable assumption from a physiological point of view because periodicity is the defining characteristic of TWA. In this study, two multilead schemes, one based on pCA and the other based on PCA, are combined with the LLR method, and are compared to a conventional single-lead approach, in which each ECG lead is analyzed independently.…”

Section: Introductionmentioning

confidence: 99%

A Multilead Scheme Based on Periodic Component Analysis for T-Wave Alternans Analysis in the ECG

et al. 2010

View full text Add to dashboard Cite

Abstract-T-wave alternans (TWA) is a cardiac phenomenon that appears in the electrocardiogram (ECG) and is associated with the mechanisms leading to sudden cardiac death (SCD). In this study, we propose the use of a multilead TWA analysis scheme that combines the Laplacian likelihood ratio (LLR) method and periodic component analysis (pCA), an eigenvalue decomposition technique whose aim is to extract the most periodic sources of the signal. The proposed scheme is evaluated in different scenarios-from synthetic signals to stress test ECGs-and is compared to other reported schemes based on the LLR method. Results demonstrate that the pCA-based scheme provides a superior ability to detect TWA than previously reported schemes, and has the potential to improve the prognostic value of testing for TWA.

show abstract

“…The results on ECG and MCG data have been compared with the results of πCA [26] and FastICA [33] methods. The GCP and WCP labels denote results of the first and second proposed approaches for tensor decomposition without Kalman filtering stage.…”

Section: Resultsmentioning

confidence: 99%

“…Furthermore, contrary to the previous tensorbased approaches, it permits to extract the original time courses of the signals, which are not identical for all realizations, using Kalman filtering. Among several methods in the literature for multichannel fetal ECG (fECG) extraction, one can name blind source separation [22], semi-blind source separation [23], adaptive filtering [24,25], and periodic component analysis (πCA) [26]. All these methods exploit the redundancy of the multichannel ECG recordings to reduce maternal ECG (mECG) and other interference sources.…”

Section: Introductionmentioning

confidence: 99%

Blind source separation of underdetermined mixtures of event-related sources

Niknazar¹,

Becker²,

Rivet³

et al. 2014

Signal Processing

View full text Add to dashboard Cite

This paper addresses the problem of blind source separation for underdetermined mixtures (i.e., more sources than sensors) of event-related sources that include quasi-periodic sources (e.g., electrocardiogram (ECG)), sources with synchronized trials (e.g., event-related potentials (ERP)), and amplitude-variant sources. The proposed method is based on two steps: (i) tensor decomposition for underdetermined source separation and (ii) signal extraction by Kalman filtering to recover the source dynamics. A tensor is constructed for each source by synchronizing on the "event" period of the corresponding signal and stacking different periods along the second dimension of the tensor. To cope with the interference from other sources that impede on the extraction of weak signals, two robust tensor decomposition methods are proposed and compared. Then, the state parameters used within a nonlinear dynamic model for the extraction of event-related sources from noisy mixtures are estimated from the loading matrices provided by the first step. The influence of different parameters on the robustness to outliers of the proposed method is examined by numerical simulations. Applied to clinical electroencephalogram (EEG), ECG and magnetocardiogram (MCG), the proposed method exhibits a significantly higher performance in terms of expected signal shape than classical source separation methods such as πCA and FastICA.

show abstract

Multichannel Electrocardiogram Decomposition Using Periodic Component Analysis

Cited by 179 publications

References 13 publications

Techniques for Ventricular Repolarization Instability Assessment From the ECG

Techniques for Ventricular Repolarization Instability Assessment From the ECG

A Multilead Scheme Based on Periodic Component Analysis for T-Wave Alternans Analysis in the ECG

Blind source separation of underdetermined mixtures of event-related sources

Contact Info

Product

Resources

About