Multichannel Electrocardiogram Signals Research Articles

A multi-channel ECG signal deep compressive sensing method using Treeshaped Autoecoder based on multiscale feature fusion

Conventionally, multi-lead Electrocardiogram (ECG) signals are recorded and stored using high sensing rates and high precision, resulting in huge data volumes and placing greater pressure on storage and transmission resources. Compressive sensing (CS) allows efficient encoding and decoding of signals through sparse representation, measurement and reconstruction for compressed storage and transmission of ECG signals. Traditional CS methods generally requires manually selecting the features or dictionaries used in sparse representations, which lacks adaptivity and flexibility, and the complexity of the reconstruction process limits the application of CS in some scenarios with high real-time requirements. In this paper, we propose a deep compressive sensing framework for processing multi-lead ECG signals by combining CS and deep learning, which is based on multi-scale feature fusion to construct a binary tree-shaped autoencoder architecture to achieve efficient compression and reconstruction of ECG signals. Experiments on the PTB diagnostic ECG database show that the proposed method achieves “very good” reconstruction quality at low sensing rates, with PRD and SNR of 1.77 % and 35.67 dB, respectively, when SR = 20 %. In addition, we investigate how the number of quantization bits affects the quality of reconstructed signals. After analysis, we found that 8-bit quantization can be used in practical applications to ensure the quality of reconstructed ECG signals, while decrease the bit rate of the data, improving the transmission efficiency, and reduce energy consumption.

MD-CardioNet: A Multi-Dimensional Deep Neural Network for Cardiovascular Disease Diagnosis from Electrocardiogram.

Automated classification of cardiovascular diseases from electrocardiogram (ECG) signals using deep learning has gained significant interest due to its wide range of applications. However, existing deep learning approaches often overlook inter-channel shared information or lose time-sequence dependent information when considering 1D and 2D ECG representations, respectively. Moreover, besides considering spatial dimension, it is necessary to understand the context of the signals from a global feature space. We propose MD-CardioNet, an efficient deep learning architecture that captures temporal, spatial, and volumetric features from multi-lead ECG signals using multidimensional (1D, 2D, and 3D) convolutions to address these challenges. Sequential feature extractors capture time-dependent information, while a 2D convolution is applied to form an image representation from the multi-channel ECG signal, extracting inter-channel features. Additionally, a volumetric feature extraction network is designed to incorporate intra-channel, inter-channel, and inter-filter global space information. To reduce computational complexity, we introduce a practical knowledge distillation framework that reduces the number of trainable parameters by up to eight times ( from 4,304,910 parameters to 94,842 parameters) while maintaining satisfactory performance compatible with the other existing approaches. The proposed architecture is evaluated on a large publicly available dataset containing ECG signals from over 10,000 patients, achieving an accuracy of 97.3% in classifying six heartbeat rhythms. Our results surpass the performance of some state-of-the-art approaches. This paper presents a novel deep-learning approach for ECG classification that addresses the limitations of existing methods. The experimental results highlight the robustness and accuracy of MD-CardioNet in cardiovascular disease classification, offering valuable insights for future research in this field.

DG-ECG: Multi-stream deep graph learning for the recognition of disease-altered patterns in electrocardiogram

Representation learning of electrocardiogram (ECG) has been an active research field for the automated detection of cardiac disease. In addition to extracting time and frequency domain features of ECG, an increasing amount of studies have adapted deep neural networks for the recognition of disease-altered ECG patterns. However, many deep learning models are deployed as blackboxes without fully exploring disease-pertinent information hidden in the signal. This, as a result, diminishes the efficacy and interpretability of the model and impedes applications in clinical practice. To address this problem, we develop a new multi-stream deep graph learning of ECG (DG-ECG) framework, which integrates multi-stream graph neural networks to uncover disease-altered ECG patterns from multifold perspectives (e.g., the morphology and rhythm of ECG signals). In each stream, visibility graphs are modeled to transform signal patterns into graph topological features, which are then mined by graph convolution. In addition, attention mechanisms are integrated into DG-ECG for multi-level information fusion to enhance its detection power and interpretability. Experimental results have demonstrated that the developed DG-ECG is better capable of gleaning disease-pertinent information from multi-channel ECG signals compared to benchmark models. The developed framework is extendable and suited for the pattern recognition of various cardiac disorders.

Developing Graph Convolutional Networks and Mutual Information for Arrhythmic Diagnosis Based on Multichannel ECG Signals.

Cardiovascular diseases, like arrhythmia, as the leading causes of death in the world, can be automatically diagnosed using an electrocardiogram (ECG). The ECG-based diagnostic has notably resulted in reducing human errors. The main aim of this study is to increase the accuracy of arrhythmia diagnosis and classify various types of arrhythmias in individuals (suffering from cardiovascular diseases) using a novel graph convolutional network (GCN) benefitting from mutual information (MI) indices extracted from the ECG leads. In this research, for the first time, the relationships of 12 ECG leads measured using MI as an adjacency matrix were illustrated by the developed GCN and included in the ECG-based diagnostic method. Cross-validation methods were applied to select both training and testing groups. The proposed methodology was validated in practice by applying it to the large ECG database, recently published by Chapman University. The GCN-MI structure with 15 layers was selected as the best model for the selected database, which illustrates a very high accuracy in classifying different types of rhythms. The classification indicators of sensitivity, precision, specificity, and accuracy for classifying heart rhythm type, using GCN-MI, were computed as 98.45%, 97.89%, 99.85%, and 99.71%, respectively. The results of the present study and its comparison with other studies showed that considering the MI index to measure the relationship between cardiac leads has led to the improvement of GCN performance for detecting and classifying the type of arrhythmias, in comparison to the existing methods. For example, the above classification indicators for the GCN with the identity adjacency matrix (or GCN-Id) were reported to be 68.24%, 72.83%, 95.24%, and 92.68%, respectively.

Dictionary Learning-Based Multichannel ECG Reconstruction Using Compressive Sensing

Multi-channel electrocardiogram (MECG) compression on lightweight wireless body area network (WBAN) is highly challenging for long-term eHealthcare monitoring. Energy consumption involved in wireless transmission poses an obstacle in the implementation of WBAN. MECG is widely used to diagnose cardiovascular diseases (CVDs), which require a considerable time to extract sufficient clinically relevant data from subjects. Since wireless MECG data transmission dominates energy cost and memory consumption of wireless sensor nodes, it is favorable to reduce the data size without any loss of diagnostic information. Compressed sensing (CS) provides efficient encoding schemes for data reduction and energy consumption in wireless transmission. We propose an adaptive multiple dictionary learning-based joint CS model for MECG compression, which exploits spatial correlation and adaptive features existing in MECG signals. We demonstrate performance of the proposed algorithm with the Physikalisch-Technische Bundesanstalt database (PTB) for MECG compression. Results from the proposed scheme can achieve excellent reconstruction quality with fewer measurements than other existing CS-based approaches. It is the most suitable technique for long-term MECG compression using lightweight WBAN devices.

Tensor-Based ECG Anomaly Detection toward Cardiac Monitoring in the Internet of Health Things.

Advanced heart monitors, especially those enabled by the Internet of Health Things (IoHT), provide a great opportunity for continuous collection of the electrocardiogram (ECG), which contains rich information about underlying cardiac conditions. Realizing the full potential of IoHT-enabled cardiac monitoring hinges, to a great extent, on the detection of disease-induced anomalies from collected ECGs. However, challenges exist in the current literature for IoHT-based cardiac monitoring: (1) Most existing methods are based on supervised learning, which requires both normal and abnormal samples for training. This is impractical as it is generally unknown when and what kind of anomalies will occur during cardiac monitoring. (2) Furthermore, it is difficult to leverage advanced machine learning approaches for information processing of 1D ECG signals, as most of them are designed for 2D images and higher-dimensional data. To address these challenges, a new sensor-based unsupervised framework is developed for IoHT-based cardiac monitoring. First, a high-dimensional tensor is generated from the multi-channel ECG signals through the Gramian Angular Difference Field (GADF). Then, multi-linear principal component analysis (MPCA) is employed to unfold the ECG tensor and delineate the disease-altered patterns. Obtained principal components are used as features for anomaly detection using machine learning models (e.g., deep support vector data description (deep SVDD)) as well as statistical control charts (e.g., Hotelling chart). The developed framework is evaluated and validated using real-world ECG datasets. Comparing to the state-of-the-art approaches, the developed framework with deep SVDD achieves superior performances in detecting abnormal ECG patterns induced by various types of cardiac disease, e.g., an F-score of 0.9771 is achieved for detecting atrial fibrillation, 0.9986 for detecting right bundle branch block, and 0.9550 for detecting ST-depression. Additionally, the developed framework with the T2 control chart facilitates personalized cycle-to-cycle monitoring with timely detected abnormal ECG patterns. The developed framework has a great potential to be implemented in IoHT-enabled cardiac monitoring and smart management of cardiac health.

Multivariate Generative Adversarial Networks and Their Loss Functions for Synthesis of Multichannel ECGs

Access to medical data is highly regulated due to its sensitive nature, which can constrain communities’ ability to utilise these data for research or clinical purposes. Common de-identification techniques to enable the sharing of data may not provide adequate privacy in every circumstance. We investigate the ability of Generative Adversarial Networks (GANs) to generate synthetic, and more significantly, multichannel electrocardiogram signals that are representative of waveforms observed in patients to address these privacy concerns. Successful generation of high-quality synthetic time series data has the potential to act as an effective substitute for actual patient data. For the first time, we demonstrate a range of novel loss functions using our multivariate GAN architecture and analyse their effect on data quality and privacy. We also present the application of multivariate dynamic time warping as a means of evaluating generated time series. Quantitative evidence demonstrates that the inclusion of a penalisation coefficient (Dynamic Time Warping) in the loss function enables our GAN to outperform the other generative models and loss functions explored by 4.9% according to our metrics. This allows for the generation of data that is more representative of the training set and diverse across generated samples, all whilst ensuring sufficient privacy.

Automatic diagnosis of cardiovascular disorders by sub images of the ECG signal using multi-feature extraction methods and randomized neural network

Electrocardiography has been employed successfully in medicine for many years to provide vital knowledge about the cardiovascular system. Although processing and evaluation of electrocardiogram (ECG) signals provide helpful information in the detection of anomalies in the vessel, diagnosis of heart defect, and treatment of diseases, multi-channel ECG signals have been started to be employed in order to achieve higher success. Utilizing a multi-channel ECG signal instead of a one-channel ECG signal yields more adequate achievements but require higher complexity in analysis and higher computational cost. To achieve faster and accurate results in multi-channel ECG signals, an artificial intelligence-based automatic diagnosis system employing the texture features of two-dimensional images, which are constructed by projecting the ECG signal vector as a row of the image, is proposed. The hypothesis proposed in this study conjectures that these texture features in the images contain determinative indicators of various diseases (cardiovascular abnormalities/disturbance) even for the short-time intervals. Accordingly, the main contribution of this study is to expose that detection of cardiovascular defects can be done with the classical image texture methods by utilizing multi-channel biomedical signals in a sufficiently short-time-interval. The methodology has been implemented in different time intervals of a large dataset constructed from a diverse population that is labeled as one normal sinus rhythm type and eight abnormal types of ECG signals. The accuracy of this hypothesis has been proven by achieving high detection rates of identifying cardiac abnormalities and reduced the computational load of the processing system without any sacrificing accuracy.

Compressive sensing based the multi-channel ECG reconstruction in wireless body sensor networks

Compressed Sensing (CS) has been considered a very effective means of reducing energy consumption at the energy-constrained wireless body sensor networks for monitoring the multi-channel Electrocardiogram (MECG) signals. In this paper, we have used the Kronecker sparsifying bases to exploit the spatio-temporal correlations of the MECG signals for improving the compression of the signals transmitted by the sensors. Furthermore, a compressed sensing-based method with low-rank constraint is proposed for effective data acquisition and signal reconstruction in the energy-constrained wireless body sensor networks. More specifically, in the proposed algorithm, an optimization formula consisting of two constraints is defined. The sparsity constraint is presented through the minimization of the l1 norm and the low-rank constraint is specified through the minimization of the nuclear norm. Afterward, a robust and efficient alternating direction method of multipliers (ADMM) based method is developed for the reconstruction of the MECG signals that solves the resulting optimization problem more effectively. Numerical experiments verify that the proposed algorithm achieves greater reconstruction accuracy with the smaller number of required transmissions, lower computational complexity, and smaller reconstruction errors, as compared to the latest CS-based recovery methods.

Efficient lossless compression scheme for multi-channel ECG signal processing

Electrocardiogram (ECG) represents the recording of the heart’s electrical activity and is used to diagnose heart disease nowadays. The diagnosis requires huge time consumption for acquiring enough multi-channel data. The storage and transmission of 12 lead ECG data results in massive cost. In this work, we propose a multi-channel ECG lossless compression which uses the adaptive linear prediction for intra and inter channel decorrelation. We also use the adaptive Golomb-Rice codec for entropy coding. The proposed technique for adaptive linear prediction and Golomb-Rice codec is based on the performance of passed samples. Thus, the coefficient of linear prediction and Golomb-Rice codec will make self-adjustments during the process. We evaluate the proposed algorithm with MIT-BIH Arrhythmia database for single-channel compression, and Physikalisch-Technische Bundesanstalt database (PTB) for multi-channel compression. The overall compression scheme is also implemented in embedded system with an ARM Cortex-M4 processor for real-time demonstration.

Compressive Sensing of Multichannel Electrocardiogram Signals in Wireless Telehealth System

Due to the capacity of compressing and recovering signal with low energy consumption, compressive sensing (CS) has drawn considerable attention in wireless telemonitoring of electrocardiogram (ECG) signals. However, most existing CS methods are designed for reconstructing single channel signal, and hence difficult to reconstruct multichannel ECG signals. In this paper, a spatio-temporal sparse model-based algorithm is proposed for the reconstruction of multichannel ECG signals by not only exploiting the temporal correlation in each individual channel signal, but also the spatial correlation among signals from different channels. In addition, a dictionary learning (DL) approach is developed to enhance the performance of the proposed reconstruction algorithm by using the sparsity of ECG signals in some transformed domain. The approach determines a dictionary by learning local dictionaries for each channel and merging them to form a global dictionary. Extensive simulations were performed to validate the proposed algorithms. Simulation results show that the proposed reconstruction algorithm has a better performance in recovering multichannel ECG signals as compared to the benchmarking methods. Moreover, the reconstruction performance of the algorithm can be further improved by using a dictionary matrix, which is obtained from the proposed DL algorithm.

Exploiting multi-scale signal information in joint compressed sensing recovery of multi-channel ECG signals

Abstract Computational complexity and power consumption are prominent issues in wireless telemonitoring applications involving physiological signals. Compressed sensing (CS) has emerged as a promising framework to address these challenges because of its energy-efficient data reduction procedure. In this work, a CS-based approach is studied for joint compression/reconstruction of multi-channel electrocardiogram (MECG) signals. The MECG signals share spatially correlated cardiac information across the channels, which is exploited in a joint CS framework for improved signal recovery. Weighted mixed-norm minimization (WMNM)-based joint sparse recovery algorithms are proposed, which can successfully recover the signals from all the channels simultaneously by utilizing the joint sparsity of MECG signals in wavelet domain. The proposed algorithms exploit multi-scale signal information through a multi-scale weighting approach. Under this strategy, weights are designed based on the diagnostic information contents of each wavelet subband/scale. In particular, clinically relevant information is captured in the form of subband energy, entropy, and amplitude decay, and based on this weighting rules are defined at each wavelet scale. Such a weighting approach emphasizes nonzero wavelet coefficients having high diagnostic importance during joint CS reconstruction. Insignificant coefficients are deemphasized simultaneously, resulting in a sparser solution. Simulation results using Physikalisch-Technische Bundesanstalt (PTB), Common Standards for Electrocardiography (CSE) and Massachusetts Institute of Technology-Boston's Beth Israel Hospital (MIT-BIH) MECG databases show that the proposed methods can achieve superior reconstruction quality with a lower number of measurements compared to their non-weighted counterpart and other existing CS-based methods. Reduction in the required number of measurements reduces computational burden and directly translates into higher compression efficiency, resulting in low energy consumption in CS-based telemonitoring systems. The diagnostic reconstruction quality of the algorithm is validated using diagnostic distortion measures like wavelet energy-based diagnostic distortion (WEDD) and with a post-reconstruction classification task. It achieves a classification accuracy of 73.2% even when MECG signals are jointly reconstructed using only about 10% of compressed measurements, validating the diagnosability of the reconstructed signals even at very low data rates.

Multi-channel ECG data compression using compressed sensing in eigenspace

In recent years, compressed sensing (CS) has emerged as a potential alternative to traditional data compression techniques for resource-constrained telemonitoring applications. In the present work, a CS framework of data reduction is proposed for multi-channel electrocardiogram (MECG) signals in eigenspace. The sparsity of dimension-reduced eigenspace MECG signals is exploited to apply CS. First, principal component analysis (PCA) is applied over the MECG data to retain diagnostically important ECG features in a few principal eigenspace signals based on maximum variance. Then, the significant eigenspace signals are randomly projected over a sparse binary sensing matrix to obtain the reduced dimension compressive measurement vectors. The compressed measurements are quantized using a uniform quantizer and encoded by a lossless Huffman encoder. The signal recovery is carried out by an orthogonal matching pursuit (OMP) algorithm. The proposed method is evaluated on the MECG signals from PTB and CSE multilead measurement library databases. The average value of percentage root mean square difference (PRD) across the PTB database is found to be 5.24% at a compression ratio (CR)=17.76 in Lead V3 of PTB database. The visual signal quality of the reconstructed MECG signals is validated through mean opinion score (MOS), found to be 6.66%, which implies very good quality signal reconstruction.

Weighted mixed-norm minimization based joint compressed sensing recovery of multi-channel electrocardiogram signals

Computational complexity and power consumption are prominent issues in wireless telemonitoring applications involving physiological signals. Because of its energy-efficient data reduction procedure, compressed sensing (CS) emerged as a promising framework to address these challenges. In this work, a multi-channel CS framework is explored for multi-channel electrocardiogram (MECG) signals. The work focuses on the successful joint recovery of the MECG signals using a low number of measurements by exploiting the correlated information across the channels. A CS recovery algorithm based on weighted mixed-norm minimization (WMNM) is proposed that exploits the joint sparsity of MECG signals in the wavelet domain and recovers signals from all the channels simultaneously. The proposed WMNM algorithm follows a weighting strategy to emphasize the diagnostically important MECG features. Experimental results on various MECG databases show that the proposed method can achieve superior reconstruction quality with high compression efficiency as compared to its non-weighted counterpart and other existing CS-based ECG compression techniques.

Fusion of detected multi-channel maternal electrocardiogram (ECG) R-wave peak locations.

BackgroundAlmost all promising non-invasive foetal ECG extraction methods involve accurately determining maternal ECG R-wave peaks. However, it is not easy to robustly detect accurate R-wave peaks of the maternal ECG component in an acquired abdominal ECG since it often has a low signal-to-noise ratio (SNR), sometimes containing a large foetal ECG component or other noises and interferences. This paper discusses, under the condition of acquiring multi-channel abdominal ECG signals, how to improve the robustness of maternal ECG R-wave peak detection.MethodsOn the basis of summarising the current single channel ECG R-wave peak detection methods, the paper proposed a specific fusion algorithm of detected multi-channel maternal ECG R-wave peak locations. The proposed entire algorithm was then tested using two databases; one database, created by us, was composed of 343 groups of 8-channel data collected from 78 pregnant women, and the other one, called the challenge database, was from the Physionet/Computing in Cardiology Challenge 2013, including 175 groups of 4-channel data. When using these databases, each group of data was classified into two parts, called the training part and the validation test part respectively; the training part was the first 8.192 s of each group of data and the validation test part was the next 8.192 s.ResultsTo show the results, three evaluation parameters—sensitivity (Se), positive predictive value (PPV) and F1—are used. The validation test results for the database we collected are Se = 99.93 %, PPV = 99.98 %, and F1 = 99.95 %, while the results for the challenge database are Se = 99.91 %, PPV = 99.86 %, and F1 = 99.88 %.ConclusionThe results of the test show that the robustness of our proposed whole fusion algorithm was superior to that of other outstanding algorithms for maternal R-wave detection, and is much better than that of single channel maternal R-wave detection algorithms.

Genetic algorithm and wavelet hybrid scheme for ECG signal denoising

This paper introduces an effective hybrid scheme for the denoising of electrocardiogram (ECG) signals corrupted by non-stationary noises using genetic algorithm (GA) and wavelet transform (WT). We first applied a wavelet denoising in noise reduction of multi-channel high resolution ECG signals. In particular, the influence of the selection of wavelet function and the choice of decomposition level on efficiency of denoising process was considered. Selection of a suitable wavelet denoising parameters is critical for the success of ECG signal filtration in wavelet domain. Therefore, in our noise elimination method the genetic algorithm has been used to select the optimal wavelet denoising parameters which lead to maximize the filtration performance. The efficiency performance of our scheme is evaluated using percentage root mean square difference (PRD) and signal to noise ratio (SNR). The experimental results show that the introduced hybrid scheme using GA has obtain better performance than the other reported wavelet thresholding algorithms as well as the quality of the denoising ECG signal is more suitable for the clinical diagnosis.