Michel Haritopoulos

Foetal PQRST extraction from ECG recordings using cyclostationarity-based source separation method

This work proposes a novel foetal electrocardiogram (FECG) extraction approach based on the cyclostationary properties of the signal of interest. The problem of FECG extraction can easily fit in a blind source separation (BSS) framework; taking into account specific statistical nature of the signal, that one wants to extract, leads to an algorithm able to estimate the FECG contribution to ECG recordings where the maternal ECG is predominant. We show that the proposed procedure provides estimates of the FECGs PQRST complexes without incorporating any prior knowledge concerning PQRST features. Discussions about foetal heart rate variability (HRV) estimation and future works conclude this paper.

Fetal ECG subspace estimation based on cyclostationarity

In this paper, we propose a strategy to estimate a Fetal Electrocardiogram (FECG) subspace from a set of mixed ECG recordings from the thoracic and abdominal electrodes attached on a pregnant woman. The ECGs from an expectant woman contain FECG that can provide valuable information for fetal health monitoring, such as the fetal heart rate (FHR). After applying blind source separation (BSS) methods to mixed ECG, independent components are obtained. The main purpose of this paper is to classify an FECG group from all of these components which can be classified as FECG, MECG and noise according to the features of signals. Inspired by the concept of multidimensional independent component analysis (MICA) and to automate the classification task, we propose a procedure based on cyclostationarity of FECGs, in particular, an integrated Cyclic Coherence. The method is validated on real world DaISy dataset and the results are promising.

Survey on Cardiotocography Feature Extraction Algorithms for Foetal Welfare Assessment

Since its inception forty years ago as a way to control birth process, the cardiotocograph (CTG) has emerged over time and became the undisputed leader worldwide of non-invasive intrapartum foetal monitoring systems. The CTG signals conveying a lot of information, it is very difficult to interpret them and act accordingly even for specialists; hence, researchers have started looking for characteristics which could be correlated with a particular pathological state of the foetus. Thereby, many features appeared in the literature, ranging from the most common ones to artificially generated features, and computed using a wide variety of signal processing-based analysis tools: time scale, spectral or non-linear analysis, to name but a few. This survey paper, presents in a hierarchical order the most common processing steps of a CTG signal and focuses primarily on the feature extraction methods for foetal heart rate (FHR) analysis reported in the literature during the last decade. Also, some feature classification methods are reported before a brief discussion which concludes this work.

Fetal heart rate feature extraction from cardiotocographic recordings through autoregressive model's power spectral- and pole-based analysis

The main objective of this work is to perform an autoregressive model (AR)-based power spectral analysis of the fetal heart rate (FHR) signal for the extraction of significant features for fetal welfare assessment. A group of features is directly computed from the AR-based spectrum while another group is computed from the poles representation. The presented method is applied to real cardiotocographic (CTG) signals and for different frequency bands, and the obtained results are very promising as they exhibit direct correlations between the extracted features and the fetal welfare in terms of umbilical pH.

A new cyclostationarity-based blind approach for motor unit's firing rate automated detection in electromyographic signals

This work focuses on electromyographic (EMG) signal processing. We propose a new blind approach that aims at detecting the firing rates of the activated motor units. The proposed method is based on the fact that, EMGs can be modelled as second-order cyclostationary signals. After application of a Blind Source Separation (BSS) algorithm, we compute a cyclostationarity measure which is the Cyclic Spectral Density (CSD), and we show how one can use it to group the estimated components into independent subspaces and in an automated manner. The proposed classification procedure is based on the concept of subspace BSS techniques, like the Multidimensional Independent Component Analysis (MICA), the difference being that our method allows automatic classification of the estimated source signals. After discarding the subspace corresponding to the noise and computation of a modified CSD measure, the proposed procedure yields to the detection of specific cyclic frequencies corresponding to the discharge frequencies of the Motor Units Action Potential Trains (MUAPTs). Early results obtained from experiments on synthetic EMGs are presented in the paper and research perspectives conclude this work.

A qualitative dynamical model for cardiotocography simulation

The purpose of this work is to present a new mathematical model for fetal monitoring simulation. It involves the simultaneous generation of fetal heart rate and maternal uterine contraction signals through a parametrical model. This model allows the generation of the main fetal monitoring dynamics including fetal movements, acceleration and deceleration of the heart rate and the dynamical adjustment of fetal heart rate following an uterine contraction. Simulated tracings were analyzed by specialists and evaluated in terms of signal realism and dynamics. Results show no significant differences between real and computer-generated signals.

Cyclostationary analysis of ECG signals acquired inside an ultra-high field MRI scanner

In this paper, a strategy is proposed to estimate the R-peaks in ECG signals recorded inside a 7 T magnetic resonance imaging (MRI) scanner in order to reduce the disturbances due to the magnetohydrodynamic (MHD) effect and to finally obtain high quality cardiovascular magnetic resonance (CMR) images. We first show that the cyclostationarity property of the ECG signal disturbed by the MHD effect can be quantified by means of cyclic spectral analysis. Then, this information is forwarded as input to a cyclostationary source extraction algorithm applied to a set of ECG recordings acquired inside the MRI scanner in a Feet first (Ff) and a Head first (Hf) positions. Finally, detection of the R-peaks in the estimated cyclostationary signal completes the proposed procedure. Validation of the method is performed by comparing the estimated with clinical R-peaks annotations provided with the real world dataset. The obtained results are promising and future research directions are discussed.

Decomposition of Multi-Channel Intramuscular EMG Signals by Cyclostationary-Based Blind Source Separation

We propose a novel decomposition method for electromyographic signals based on blind source separation. Using the cyclostationary properties of motor unit action potential trains (MUAPt), it is shown that the MUAPt can be decomposed by joint diagonalization of the cyclic spatial correlation matrix of the observations. After modeling the source signals, we provide the proof of orthogonality of the sources and of their delayed versions in a cyclostationary context. We tested the proposed method on simulated signals and showed that it can decompose up to six sources with a probability of correct detection and classification >95%, using only eight recording sites. Moreover, we tested the method on experimental multi-channel signals recorded with thin-film intramuscular electrodes, with a total of 32 recording sites. The rate of agreement of the decomposed MUAPt with those obtained by an expert using a validated tool for decomposition was >93%.

Estimation of Foetal Contribution to ECG Recordings Using Oblique Projection Technique Exploiting Cyclostationary Properties of the Heartbeat Signals

In this paper, the authors propose to estimate the contribution of the electrical activity of the foetal heart to each component of cutaneous electrocardiogram (ECG) recordings using an oblique projection technique. To date, related research work reported in the literature using Blind Source Separation (BSS) or Independent Component Analysis (ICA) methods rely on a widely used projection techniques family, which is the orthogonal projection. More recently, reported work in other areas of biomedical research is based on the use of oblique projection techniques in order to remove the artifacts from the available recordings and to estimate the contribution of the Signal of Interest (SoI) to the data set. The novel approach presented in this paper is tailored to the problem of foetal ECG (FECG) contribution estimation. The optimal steering vector’s computation procedure for the oblique projection is based on the use of the cyclostationary properties of the SoI and on the concept of Multidimensional Independent Component Analysis (MICA). The latter is used to gather into independent subspaces the components estimated using a BSS/ICA method and corresponding to the foetus’ heartbeats, the mother’s heartbeats and various artifacts and noise sources. Early comparative results with the orthogonal approach obtained after application of both methods to synthetic non-invasive FECG recordings illustrate the reliability as well as the effectiveness of the proposed method. A discussion and perspectives for future research conclude this work.

Extraction of foetal contribution to ECG recordings using cyclostationarity-based source separation method

In this paper we propose a cyclostationary approach to the problem of the foetal electrocardiogram (FECG) extraction from a set of cutaneous potential recordings of an expectant mother. We adopted a semi-blind source separation (BSS) method for which the only necessary prior knowledge is that of the fundamental cyclic frequency of the cyclostationary process to be estimated. Using this technique, the estimated cyclostationary FECG source of interest is found to be free from any interferences with the mothers ECG (MECG) signal. Experimental results and perspectives for future research conclude this paper.