Model-based Bayesian filtering of cardiac contaminants from biomedical recordings

An open-access simultaneous electrocardiogram and phonocardiogram database

Objective.The EPHNOGRAM project aimed to develop a low-cost, low-power device for simultaneous electrocardiogram (ECG) and phonocardiogram (PCG) recording, with additional channels for environmental audio to enhance PCG through active noise cancellation. The objective was to study multimodal electro-mechanical activities of the heart, offering insights into the differences and synergies between these modalities during various cardiac activity levels.Approach.We developed and tested several hardware prototypes of a simultaneous ECG-PCG acquisition device. Using this technology, we collected simultaneous ECG and PCG data from 24 healthy adults during different physical activities, including resting, walking, running, and stationary biking, in an indoor fitness center. The data were annotated using a robust software that we developed for detecting ECG R-peaks and PCG S1 and S2 components, and overseen by a human expert. We also developed machine learning models using ECG-based, PCG-based, and joint ECG-PCG features, like R-R and S1-S2 intervals, to classify physical activities and analyze electro-mechanical dynamics.Main results.The results show a significant coupling between ECG and PCG components, especially during high-intensity exercise. Notable micro-variations in S2-based heart rate show differences in the heart's electrical and mechanical functions. The Lomb-Scargle periodogram and approximate entropy analyses confirm the higher volatility of S2-based heart rate compared to ECG-based heart rate. Correlation analysis shows stronger coupling between R-R and R-S1 intervals during high-intensity activities. Hybrid ECG-PCG features, like the R-S2 interval, were identified as more informative for physical activity classification through mRMR feature selection and SHAP value analysis.Significance.The EPHNOGRAM database, is available on PhysioNet. The database enhances our understanding of cardiac function, enabling future studies on the heart's mechanical and electrical interrelationships. The results of this study can contribute to improved cardiac condition diagnoses. Additionally, the designed hardware has the potential for integration into wearable devices and the development of multimodal stress test technologies.

Automated pipeline for EEG artifact reduction (APPEAR) recorded during fMRI

Objective.Simultaneous electroencephalography-functional magnetic resonance imaging (EEG-fMRI) recordings offer a high spatiotemporal resolution approach to study human brain and understand the underlying mechanisms mediating cognitive and behavioral processes. However, the high susceptibility of EEG to MRI-induced artifacts hinders a broad adaptation of this approach. More specifically, EEG data collected during fMRI acquisition are contaminated with MRI gradients and ballistocardiogram artifacts, in addition to artifacts of physiological origin. There have been several attempts for reducing these artifacts with manual and time-consuming pre-processing, which may result in biasing EEG data due to variations in selecting steps order, parameters, and classification of artifactual independent components. Thus, there is a strong urge to develop a fully automatic and comprehensive pipeline for reducing all major EEG artifacts. In this work, we introduced an open-access toolbox with a fully automatic pipeline for reducing artifacts from EEG data collected simultaneously with fMRI (refer to APPEAR).Approach.The pipeline integrates average template subtraction and independent component analysis to suppress both MRI-related and physiological artifacts. To validate our results, we tested APPEAR on EEG data recorded from healthy control subjects during resting-state (n= 48) and task-based (i.e. event-related-potentials (ERPs);n= 8) paradigms. The chosen gold standard is an expert manual review of the EEG database.Main results.We compared manually and automated corrected EEG data during resting-state using frequency analysis and continuous wavelet transformation and found no significant differences between the two corrections. A comparison between ERP data recorded during a so-called stop-signal task (e.g. amplitude measures and signal-to-noise ratio) also showed no differences between the manually and fully automatic fMRI-EEG-corrected data.Significance.APPEAR offers the first comprehensive open-source toolbox that can speed up advancement of EEG analysis and enhance replication by avoiding experimenters' preferences while allowing for processing large EEG-fMRI cohorts composed of hundreds of subjects with manageable researcher time and effort.

Artifact Reduction in Simultaneous EEG-fMRI: A Systematic Review of Methods and Contemporary Usage

Simultaneous electroencephalography-functional MRI (EEG-fMRI) is a technique that combines temporal (largely from EEG) and spatial (largely from fMRI) indicators of brain dynamics. It is useful for understanding neuronal activity during many different event types, including spontaneous epileptic discharges, the activity of sleep stages, and activity evoked by external stimuli and decision-making tasks. However, EEG recorded during fMRI is subject to imaging, pulse, environment and motion artifact, causing noise many times greater than the neuronal signals of interest. Therefore, artifact removal methods are essential to ensure that artifacts are accurately removed, and EEG of interest is retained. This paper presents a systematic review of methods for artifact reduction in simultaneous EEG-fMRI from literature published since 1998, and an additional systematic review of EEG-fMRI studies published since 2016. The aim of the first review is to distill the literature into clear guidelines for use of simultaneous EEG-fMRI artifact reduction methods, and the aim of the second review is to determine the prevalence of artifact reduction method use in contemporary studies. We find that there are many published artifact reduction techniques available, including hardware, model based, and data-driven methods, but there are few studies published that adequately compare these methods. In contrast, recent EEG-fMRI studies show overwhelming use of just one or two artifact reduction methods based on literature published 15–20 years ago, with newer methods rarely gaining use outside the group that developed them. Surprisingly, almost 15% of EEG-fMRI studies published since 2016 fail to adequately describe the methods of artifact reduction utilized. We recommend minimum standards for reporting artifact reduction techniques in simultaneous EEG-fMRI studies and suggest that more needs to be done to make new artifact reduction techniques more accessible for the researchers and clinicians using simultaneous EEG-fMRI.

Temporally Nonstationary Component Analysis; Application to Noninvasive Fetal Electrocardiogram Extraction

OBJECTIVE

Mixtures of temporally nonstationary signals are very common in biomedical applications. The nonstationarity of the source signals can be used as a discriminative property for signal separation. Herein, a semi-blind source separation algorithm is proposed for the extraction of temporally nonstationary components from linear multichannel mixtures of signals and noises.

METHODS

A hypothesis test is proposed for the detection and fusion of temporally nonstationary events, by using ad hoc indexes for monitoring the first and second order statistics of the innovation process. As proof of concept, the general framework is customized and tested over noninvasive fetal cardiac recordings acquired from the maternal abdomen, over publicly available datasets, using two types of nonstationarity detectors: 1) a local power variations detector, and 2) a model-deviations detector using the innovation process properties of an extended Kalman filter.

RESULTS

The performance of the proposed method is assessed in presence of white and colored noise, in different signal-to-noise ratios.

CONCLUSION AND SIGNIFICANCE

The proposed scheme is general and it can be used for the extraction of nonstationary events and sample deviations from a presumed model in multivariate data, which is a recurrent problem in many machine learning applications.

Fetal ECG extraction from time-varying and low-rank noninvasive maternal abdominal recordings

OBJECTIVE

Noninvasive fetal electrocardiography is emerging as a low-cost and high-accuracy technology for fetal cardiac monitoring. Signal processing techniques have been used over the past fifty years in this domain. The current major challenges of this domain, addressed in this study are (1) fetal electrocardiogram (fECG) extraction from few numbers of maternal abdominal channels in low signal-to-noise ratios; (2) online fECG extraction; (3) automatic and online signal quality assessment and channel selection; and (4) accurate and robust fetal R-peak detection and ECG parameter extraction.

APPROACH

Based on the theory of cyclostationarity, auxiliary maternal ECG channel(s) are synthetically constructed and augmented with the input channels. The augmented data are used to develop a robust multichannel source separation algorithm for online/offline fECG extraction, from as few as a single channel, and an accurate fetal R-peak detector using a two-pass matched filter. Several robust signal quality indexes (SQI) and a voting strategy are also proposed for automatic fetal signal quality assessment.

MAIN RESULTS

It is shown that the fECG and the fetal R-peaks can be accurately extracted from standard online available datasets, for which classical source separation methods (requiring many channels) had previously failed. The signal quality indexes fully automate the extraction and channel selection procedure. Finally, the proposed R-peak detector is highly robust to background noise and residual maternal R-peak components.

SIGNIFICANCE

The proposed methods for fECG extraction, R-peak detection and automatic channel selection are evaluated (visually and numerically), on two online available datasets and compared with recently developed algorithms. The proposed algorithm is statistically shown to outperform the benchmarks in terms of average and standard deviation.

A template subtraction method for the removal of cardiogenic oscillations on esophageal pressure signals

Esophageal pressure (P_es) is usually measured in patients receiving mechanical ventilation and is used for the assessment of lung mechanics. However, its interpretation is complicated by the presence of cardiogenic oscillations (CGO). In this article we present a novel method for the reduction of CGO based on the identification of pressure templates. Similar approaches are known for the removal of electrocardiographic (ECG) artifacts from the electromyogram (EMG). The proposed method is tested on clinical recordings of patients under assisted spontaneous ventilation. Besides the improvement of the respiratory signals, the identified CGO templates can be used diagnostically when viewed in relation to corresponding ECG data. This approach is illustrated on a few sample datasets.

A multi-step method with signal quality assessment and fine-tuning procedure to locate maternal and fetal QRS complexes from abdominal ECG recordings

Non-invasive monitoring of fetal electrocardiogram (fECG) plays an important role in detecting and diagnosing fetal diseases. This study aimed to develop a multi-step method for locating both maternal and fetal QRS complexes from abdominal ECG (aECG) recordings. The proposed method included four major steps: abdominal ECG pre-processing, maternal QRS complex locating, maternal ECG cancellation and fetal QRS complex locating. Signal quality assessment (SQA) and fine-tuning for maternal ECG (FTM) were implemented in the first and third steps, respectively. The method was then evaluated using 75 non-invasive 4-channel aECG recordings provided by the PhysioNet/Computing in Cardiology Challenge 2013. The F1 measure, which is a new index introduced by Behar et al (2013 Proc. Comput. Cardiol. 40 297-300), was used to assess the locating accuracy. The other two indices, mean squared error of heart rate (MSE_HR) between the fetal HR signals estimated from the reference and our method (MSE_HR in bpm(2)) and root mean squared difference between the corresponding fetal RR intervals (MSE_RR in ms) were also used to assess the locating accuracy. Overall, for the maternal QRS complex, the F1 measure was 98.4% from the method without the implementation of SQA, and it was improved to 99.8% with SQA. For the fetal QRS complex, the F1 measure, MSE_HR and MSE_RR were 84.9%, 185.6 bpm(2) and 19.4 ms for the method without both SQA and FTM procedures. They were improved to 93.9%, 47.5 bpm(2) and 7.6 ms with both SQA and FTM procedures. These improvements were observed from each individual subject. It can be concluded that implementing both SQA and FTM procedures could achieve better performance for locating both maternal and fetal QRS complexes.

Morphological modeling of cardiac signals based on signal decomposition

In this paper a general framework is presented for morphological modeling of cardiac signals from a signal decomposition perspective. General properties of a desired morphological model are presented and special cases of the model are studied in detail. The presented approach is studied for modeling the morphology of electrocardiogram (ECG) signals. Specifically, three types of ECG modeling techniques, including polynomial spline models, sinusoidal model and a model previously presented by McSharry et al., are studied within this framework. The proposed method is applied to datasets from the PhysioNet ECG database for compression and modeling of normal and abnormal ECG signals. Quantitative and qualitative results of these applications are also presented and discussed.

Application of artificial neural networks for versatile preprocessing of electrocardiogram recordings

The electrocardiogram (ECG) is the most widely used method for diagnosis of heart diseases, where a good quality of recordings allows the proper interpretation and identification of physiological and pathological phenomena. However, ECG recordings often have interference from noises including thermal, muscle, baseline and powerline noises. These signals severely limit ECG recording utility and, hence, have to be removed. To deal with this problem, the present paper proposes an artificial neural network (ANN) as a filter to remove all kinds of noise in just one step. The method is based on a growing ANN which optimizes both the number of nodes in the hidden layer and the coefficient matrices, which are optimized by means of the Widrow-Hoff delta algorithm. The ANN has been trained with a database comprising all kinds of noise, both from synthesized and real ECG recordings, in order to handle any noise signal present in the ECG. The proposed system improves results yielded by conventional techniques of ECG filtering, such as FIR-based systems, adaptive filtering and wavelet filtering. Therefore, the algorithm could serve as an effective framework to substantially reduce noise in ECG recordings. In addition, the resulting ECG signal distortion is notably more reduced in comparison with conventional methodologies. In summary, the current contribution introduces a new method which is able to suppress all ECG interference signals in only one step with low ECG distortion and a high noise reduction.

ECG denoising using angular velocity as a state and an observation in an Extended Kalman Filter framework

In this paper an efficient filtering procedure based on Extended Kalman Filter (EKF) has been proposed. The method is based on a modified nonlinear dynamic model, previously introduced for the generation of synthetic ECG signals. The proposed method considers the angular velocity of ECG signal, as one of the states of an EKF. We have considered two cases for observation equations, in one case we have assumed a corresponding observation to angular velocity state and in the other case, we have not assumed any observations for it. Quantitative evaluation of the proposed algorithm on the MIT-BIH Normal Sinus Rhythm Database (NSRDB) shows that an average SNR improvement of 8 dB is achieved for an input signal of -4 dB.

Synthetic ECG generation and Bayesian filtering using a Gaussian wave-based dynamical model

In this paper, we describe a Gaussian wave-based state space to model the temporal dynamics of electrocardiogram (ECG) signals. It is shown that this model may be effectively used for generating synthetic ECGs as well as separate characteristic waves (CWs) such as the atrial and ventricular complexes. The model uses separate state variables for each CW, i.e. P, QRS and T, and hence is capable of generating individual synthetic CWs as well as realistic ECG signals. The model is therefore useful for generating arrhythmias. Simulations of sinus bradycardia, sinus tachycardia, ventricular flutter, atrial fibrillation and ventricular tachycardia are presented. In addition, discrete versions of the equations are presented for a model-based Bayesian framework for denoising. This framework, together with an extended Kalman filter and extended Kalman smoother, was used for denoising the ECG for both normal rhythms and arrhythmias. For evaluating the denoising performance, the signal-to-noise ratio (SNR) improvement of the filter outputs and clinical parameter stability were studied. The results demonstrate superiority over a wide range of input SNRs, achieving a maximum 12.7 dB improvement. Results indicate that preventing clinically relevant distortion of the ECG is sensitive to the number of model parameters. Models are presented which do not exhibit such distortions. The approach presented in this paper may therefore serve as an effective framework for synthetic ECG generation and model-based filtering of noisy ECG recordings.

Robust detection of premature ventricular contractions using a wave-based Bayesian framework

Detection and classification of ventricular complexes from the ECG is of considerable importance in Holter and critical care patient monitoring, being essential for the timely diagnosis of dangerous heart conditions. Accurate detection of premature ventricular contractions (PVCs) is particularly important in relation to life-threatening arrhythmias. In this paper, we introduce a model-based dynamic algorithm for tracking the ECG characteristic waveforms using an extended Kalman filter. The algorithm can work on single or multiple leads. A "polargram"--a polar representation of the signal--is introduced, which is constructed using the Bayesian estimations of the state variables. The polargram allows the specification of a polar envelope for normal rhythms. Moreover, we propose a novel measure of signal fidelity by monitoring the covariance matrix of the innovation signals throughout the filtering procedure. PVCs are detected by simultaneous tracking the signal fidelity and the polar envelope. Five databases, including 40 records from MIT-BIH arrhythmia database, are used for differentiating normal, PVC, and other beats. Performance evaluation results show that the proposed method has an average detection accuracy of 99.10%, aggregate sensitivity of 98.77%, and aggregate positive predictivity of 97.47%. Furthermore, the method is capable of 100% accuracy for records that contain only PVCs and normal sinus beats. The results illustrate that the method can contribute to, and enhance the performance of clinical PVC detection.

A Review of Fetal ECG Signal Processing; Issues and Promising Directions

The field of electrocardiography has been in existence for over a century, yet despite significant advances in adult clinical electrocardiography, signal processing techniques and fast digital processors, the analysis of fetal ECGs is still in its infancy. This is, partly due to a lack of availability of gold standard databases, partly due to the relatively low signal-to-noise ratio of the fetal ECG compared to the maternal ECG (caused by the various media between the fetal heart and the measuring electrodes, and the fact that the fetal heart is simply smaller), and in part, due to the less complete clinical knowledge concerning fetal cardiac function and development. In this paper we review a range of promising recording and signal processing techniques for fetal ECG analysis that have been developed over the last forty years, and discuss both their shortcomings and advantages. Before doing so, however, we review fetal cardiac development, and the etiology of the fetal ECG. A selection of relevant models for the fetal/maternal ECG mixture is also discussed. In light of current understanding of the fetal ECG, we then attempt to justify recommendations for promising future directions in signal processing, and database creation.

A model-based Bayesian framework for ECG beat segmentation

The study of electrocardiogram (ECG) waveform amplitudes, timings and patterns has been the subject of intense research, for it provides a deep insight into the diagnostic features of the heart's functionality. In some recent works, a Bayesian filtering paradigm has been proposed for denoising and compression of ECG signals. In this paper, it is shown that this framework may be effectively used for ECG beat segmentation and extraction of fiducial points. Analytic expressions for the determination of points and intervals are derived and evaluated on various real ECG signals. Simulation results show that the method can contribute to and enhance the clinical ECG beat segmentation performance.