基于扩展卡尔曼滤波和奇异值分解算法的单通道胎儿心电提取方法

提出一种将扩展卡尔曼滤波(EKF)算法和奇异值分解(SVD)算法相结合的单通道胎儿心电提取方法。首先,建立母体心电的动态模型,利用该模型通过扩展卡尔曼滤波或扩展卡尔曼平滑(EKS),从孕妇的单通道腹部信号中估计出母体心电成分,然后与单通道腹部信号相减得到胎儿心电信号的初步估计,随后再利用奇异值分解算法,对初步估计出的胎儿心电信号进行去噪处理,以期得到高信噪比的胎儿心电信号。另外,针对胎儿心律不齐的情况,在奇异值分解算法中提出一种改进的心电信号重构矩阵构造方法。对合成腹部信号和实际腹部信号(源于DaISy数据库和PhysioNet中的非侵入式胎儿心电数据库,共计49个腹部通道的数据),进行胎儿心电提取实验。结果表明,使用EKF+SVD或EKS+SVD的算法比单独使用EKF或EKS的算法,提取出的胎儿心电信号的信噪比提高约5 dB,胎儿心电提取的准确性分别达95.60%和95.94%。结合EKF和SVD算法的单通道胎儿心电提取方法,可以有效地提高胎儿心电信号的信噪比和提取的准确性,并且适用于母体或胎儿心律不齐的情况。     

用平均法进行胎儿ECG的测量

胎儿心电图(FECG)已广泛得到应用,目前不仅能精确地测量胎儿的心率,而且PR间期、ST段形态和QRS波宽等与胎儿状况有关的参数也受到临床的重视。FECG测量的难点在于信噪比太低,母亲心电(MECG)和FECG同时发生的儿率较大及信号和噪声的频谱混叠在一起。本文介绍了一种用相干函数和FFT算法求得平均的FECG     

结合快速独立成分分析算法和卷积神经网络的胎儿心电信号提取与分析方法

胎儿心电信号为胎儿异常情况的早期诊断和干预提供了重要的临床信息，本文提出一种胎儿心电信号提取与分析的新方法。首先，将改进的快速独立成分分析（FastICA）法和奇异值分解（SVD）算法结合，来提取高质量胎儿心电信号并解决波形缺失问题。其次，运用一种新的卷积神经网络（CNN）模型识别胎儿心电信号QRS复合波，并有效解决波形重叠问题。最终，实现胎儿心电信号的高质量提取与胎儿QRS复合波的智能识别。以复杂生理信号研究资源网2013年心脏病学计算挑战赛（PhysioNet2013）数据库资料对本文所提方法进行验证，结果表明该提取算法平均灵敏度与阳性预测值为98.21%和99.52%;QRS复合波识别算法平均灵敏度与阳性预测值为94.14%和95.80%，相较于其他研究成果均有较好的提升。综上，本文提出的算法与模型具有一定的实践意义，今后或可为临床医学决策提供理论依据。     

基于移动智能终端的单通道胎儿心电监护系统

目的 设计基于移动智能终端的单通道胎儿心电监护系统,以实现扩展卡尔曼滤波(extended Kalman filtering,EKF)和奇异值分解(singular value decomposition,SVD)相结合的单通道胎儿心电提取算法,实时获取高信噪比的胎儿心电信号,完成胎心监护的远程移动医疗.方法 利用STM32单片机控制24位采样芯片ADS1298,对单通道的孕妇腹部信号进行采集,并将采集后的数据经蓝牙传送给移动智能终端,在基于Android的移动智能终端上实现EKF和SVD相结合的单通道胎儿心电提取算法,完成对胎儿心电的实时提取、显示、存储与分析,计算心律变异率,实现对整个监护系统进行控制等功能.结果 测试结果表明,该系统可从单通道孕妇腹部信号中准确提取出胎儿心电信号,准确度为95.60％,阳性预测率为98.71％,系统工作稳定,连续处理5个胎心周期的数据用时约为70μs,小于一个母体心动周期(约0.8 s)的时间,适于临床对胎儿心电的实时监护.结论 该系统实时性强、准确率高、工作稳定、操作简单、便于携带,实现了对胎心监护的可穿戴式远程移动医疗,适合社区医院和家庭使用.     

基于平稳小波变换的胎儿心电提取方法

胎儿心电信号的提取对孕期胎儿健康状况的检测具有重要意义。本文提出一种基于平稳小波变换的单/多通道胎儿心电提取方法。多通道环境下输入信号包括腹部混合信号和母体心电信号,单通道环境下母体心电信号采用对腹部混合信号进行窗口平均法获得,然后对信号进行平稳小波变换与阈值去噪,继而提取胎儿心电信号。Physio Net数据测试实验表明,该方法在单/多通道的环境下均能成功提取到清晰的胎儿心电信号,并且能有效地消除噪声。     

心率变异信号的非均匀采样问题研究

心率变异性研究是目前的一个研究热点,心率变异性研究的主要对象-R-R间期时间序列是一个非均匀采样序列,这种非均匀性导致了许多问题,本文提出了一种基于三次样条的序列均匀重采样算法。并构造了一种新的更直观的R-R间期信号模型。实验结果表明新算法确实可以改善谱估计的结果和波形的形态,消除二次伪谐波峰,并在大多数情况下减少偏差。更重要的是,该算法使得R-R间期序列的物理意义更明确,从而使不同信号间的比较和运算成为可能。     

基于BP神经网络的胎儿心电提取算法研究

目的针对胎儿心电不易提取的问题,提出一种从孕妇腹部混合心电信号和胸部心电信号中提取胎儿心电的方法。方法采用反向传播(BP)神经网络预测孕妇腹部混合心电信号中母体心电的真实形态,从腹部混合信号中减去预测的母体心电信号便得到胎儿心电信号。与小波阈值去燥算法和自适应滤波算法比较,评价BP神经网络算法可行性。结果相比小波阈值去燥算法和自适应滤波算法,该算法准确度为94.12%,灵敏度为96.97%。这两项指标均优于小波阈值去燥算法的80.52%、93.94%和自适应滤波算法的87.88%、87.88%。结论基于BP神经网络的方法可以提取到纯净的胎儿心电信号,对于胎儿心电监护有一定的应用价值。     

应用改进的时序自适应噪声消除法作胎儿心电信号的处理

采用时序自适应噪声消除法作胎儿心电信号处理,适应了信号的非平稳特性,但是难以实现微计算机的实时处理,主要问题在于计算量大,占内存多,我们通过分析信号和算法的特点,在应用中进行了改进.初步处理结果表明,改进后的时序自适应算法,在处理结果相同的前提下大大减少了内存和计算量,可以用于微计算机作实时处理.取自母腹体表电极的胎儿心电信号具有三个特点:(1)信噪比低,作为干扰出现的母亲心电比胎儿心电强得多.(2)信号与噪声频谱交迭(3)随机性,胎儿心电与母亲心电均为非平稳非各态遍历的随机过程.胎儿心电信号的处理,关键是要消除母亲心电干扰.本文主要探讨改进时序自适应噪声消除法来处理腹部胎儿心电信号,使处理结果能够满足胎儿心率检测的要求,算法适于微计算机的实时处理,以便实现胎儿监护.     

一种基于R-R间期的改进型模板匹配法在心电图自动诊断中的应用

目的探讨R-R间期的改进型模板匹配法在心电图(ECG)自动诊断中的应用。方法选择26例受试者ECG数据作为研究对象,分为3组。10例心律失常患者数据作为实验组,其中男性7例,女性3例,年龄24~75岁,平均年龄58.4岁。再选取10例正常人数据作为对照组,其中男性3例,女性7例,年龄26~45岁,平均年龄32.2岁。另选取6例ECG时间大于6 h的长时间病例数据用以证实算法的稳定性,其中男性3例,女性3例,年龄42~63岁,平均年龄56.6岁。使用改进型的信号模板匹配算法检测R波并进而利用计算机程序计算出诊断心率变异性(HRV)的多个因素,借用美国麻省理工学院生理数据库(MIT/BIH)中数据进行测试,对测试结果分组进行统计学检验。结果所选数据组间R-R间期标准差(SDNN)、相邻R-R间期差值的均方根值(RNSSD)、正常窦性心搏间期的平均值(NNVGR)、相邻R-R间期差值大于50 ms的个数占所有R-R间期个数的百分比(PNN50)的计算结果在实验组与对照组之间差异存在统计学意义(P<0.05)。根据改进型模板匹配法得到的6例长时间病例心律失常患者均值都高于对照组。结论该方法可以用来初步筛选ECG心律失常患者,可作为心电预警自动诊断的一种检测参考方法。     

一种改进的FastICA算法在胎儿心电提取中的应用

目的为了改进传统FastICA算法对初始权值较敏感的问题,本文提出一种基于超松弛因子改进的FastICA算法来提取胎儿心电。方法首先对Da ISy数据库中的母体腹部混合信号进行中心化和白化处理,去除信号间的相关性;然后在牛顿迭代算法中引入超松弛因子对随机产生的初始权值进行处理,再用改进FastICA算法提取胎儿心电;最后对胎儿心电信号的提取结果通过可视化的波形和量化指标进行评估。结果实验结果显示该算法平均迭代次数由改进前的55次降到15次,信噪比也得到提高,并且改进后算法提取出来的胎儿心电几乎不掺杂母体心电。结论基于超松弛因子改进的FastICA算法,在保持收敛速度的同时,放宽了对初始权值的要求,避免了收敛不平衡,减少了迭代次数,可以提取出比较清晰的胎儿心电。     

The influence of coincidence of fetal and maternal QRS complexes on fetal heart rate reliability

Bioelectrical fetal heart activity being recorded from maternal abdominal surface contains more information than mechanical heart activity measurement based on the Doppler ultrasound signals. However, it requires extraction of fetal electrocardiogram from abdominal signals where the maternal electrocardiogram is dominant. The simplest technique for maternal component suppression is a blanking procedure, which relies upon the replacement of maternal QRS complexes by isoline values. Although, in case of coincidence of fetal and maternal QRS complexes, it causes a loss of information on fetal heart activity. Its influence on determination of fetal heart rate and the variability analysis depends on the sensitivity of the heart-beat detector used. The sensitivity is defined as an ability to detect the incomplete fetal QRS complex. The aim of this work was to evaluate the influence of the maternal electrocardiogram suppression method used on the reliability of FHR signal being calculated.     

A Comparison of Single Channel Fetal ECG Extraction Methods

The abdominal electrocardiogram (ECG) provides a non-invasive method for monitoring the fetal cardiac activity in pregnant women. However, the temporal and frequency overlap between the fetal ECG (FECG), the maternal ECG (MECG) and noise results in a challenging source separation problem. This work seeks to compare temporal extraction methods for extracting the fetal signal and estimating fetal heart rate. A novel method for MECG cancelation using an echo state neural network (ESN) based filtering approach was compared with the least mean square (LMS), the recursive least square (RLS) adaptive filter and template subtraction (TS) techniques. Analysis was performed using real signals from two databases composing a total of 4 h 22 min of data from nine pregnant women with 37,452 reference fetal beats. The effects of preprocessing the signals was empirically evaluated. The results demonstrate that the ESN based algorithm performs best on the test data with an F1 measure of 90.2% as compared to the LMS (87.9%), RLS (88.2%) and the TS (89.3%) techniques. Results suggest that a higher baseline wander high pass cut-off frequency than traditionally used for FECG analysis significantly increases performance for all evaluated methods. Open source code for the benchmark methods are made available to allow comparison and reproducibility on the public domain data.     

Fetal heart rate monitoring based on independent component analysis

In this paper, an algorithm based on independent component analysis (ICA) for extracting the fetal heart rate (FHR) from maternal abdominal electrodes is presented. Three abdominal ECG channels are used to extract the FHR in three steps: first preprocessing procedures such as DC cancellation and low-pass filtering are applied to remove noise. Then the algorithm for multiple unknown source extraction (AMUSE) algorithm is fed to extract the sources from the observation signals include fetal ECG (FECG). Finally, FHR is extracted from FECG. The method is shown to be capable of completely revealing FECG R-peaks from observation leads even with a SNR=-200dB using semi-synthetic data.     

基于快速定点独立分量分析算法的母胎心电信号分离

研究快速定点独立分量分析方法在母胎心电信号分离中的应用。采用此算法,在胎儿心电信号与母体心电信号可以视为相互独立的信号源的前提下,对来源于同一孕妇的观测信号进行独立分量分离。快速定点独立分量算法可以有效地分离出单个独立分量,得到的胎儿心电信号(FECG)较理想。采用独立分量分析方法,实现母胎心电信号分离,是一种值得尝试的信号处理方法。     

基于独立成分分析和量子粒子群算法的胎儿心电提取

胎儿心电图(FECG)是反映胎儿心脏电生理活动的一项客观指标,获取的FECG受到母体心电图(MECG)的干扰,如何快捷、有效的提取FECG成为重要的研究课题。在非侵入方式下,FECG的提取算法中独立成分分析(ICA)算法被认为是效果最好的方法,但现有求解其分解矩阵的算法收敛性能都不太高。量子粒子群(QPSO)算法是一种收敛于全局的智能优化算法。因此,提出了一种结合QPSO的ICA方法。研究结果表明,与其他在非侵入方式下的主要提取算法相比,这种方法能更清晰准确地提取出有用信号,为胎儿的健康检测提供了更好的方法。     

Ultra-low-noise instrumentation and computer-based data acquisition and processing system for obtaining a noninvasive and intrauterine catheter fetal electrocardiogram

A fetal electrocardiogram (FECG) from the abdominal surface will be from 20 microVpp to unmeasurable. The intrauterine catheter signal will be from 50 microVpp to unmeasureable and will be corrupted with a significant direct current component of 10 to 200 microV. For electrophysiological information to be obtained from the abdominal and intrauterine catheter signals, the signals must be in a 0.05 to 100.0 Hz bandwidth. Because typical adult electrocardiogram systems have a noise specification of 5 to 10 microVpp from instrumentation, these systems are unacceptable for obtaining a FECG via the intrauterine catheter or noninvasively. Therefore, custom instrumentation has been developed with a noise specification of approximately 1.5 microVpp in a 0.05 to 100.0 Hz bandwidth. Design details of the custom instrumentation will be presented along with a laptop computer based data acquisition and signal processing system using LabVIEW. In addition, clinical data from the intrauterine catheter and noninvasive abdominal wall are presented to determine the feasibility of obtaining a FECG via the custom instrumentation. Clinical data obtained and documented indicates that after maternal electrocardiogram cancellation, a FECG with a good signal-to-noise ratio can be obtained in a diagnostic bandwidth of 0.05 to 100.0 Hz. Because the diagnostic bandwidth is preserved, electrophysiological information can be determined along with heart rate.     

The fetal electrocardiogram by independent component analysis and wavelets

Once the fetal electrocardiogram (FECG) waveforms from ECG on the maternal abdomen are detected, the fetal P wave and T wave cannot always be identified by using continuous wavelet transform (CWT). We took noninvasive FECG from the maternal abdomen, extracted it from the maternal electrocardiogram waveforms after an Independent Component Analysis (ICA), and identified the features of those waveforms by using CWT. We also simultaneously analyzed the observed signals by Primary Component Analysis (PCA). FECG has been extracted by ICA from 25 of 30 pregnant women. The fetal P wave and T wave could be identified in 21 of the 25 cases. FECG was extracted by PCA in only one case. ICA is superior to PCA, whose separation quality highly depends on the careful positioning of the electrodes. We believe that after ICA, FECG obtained by the wavelet theory based method will become a powerful tool for the differential diagnosis of fetal arrhythmias.     

Single-lead fetal electrocardiogram estimation by means of combining R-peak detection,resampling and comb filter

Minimal detecting electrodes are preferred to miniaturise fetal electrocardiogram (fECG) monitoring devices for application in non-clinical environments. In this paper, a new method to estimate the fECG using a single-lead abdominal signal is introduced. In this method, for a preprocessed abdominal ECG recording, we follow a multi-step procedure to estimate the fECG signal. First, the locations of the maternal R-peaks are detected. Each R–R interval in the abdominal signal is resampled to have the same number of samples by changing its corresponding sampling frequency. A comb filter, which has teeth that coincide with the harmonics of the maternal electrocardiogram (mECG), is applied to the resampled signal. Each R–R interval in the filtered signal is resampled again to recover its original sampling frequency, and the mECG signal is obtained. This mECG signal is subtracted from the abdominal signal, and the residual signal is considered to be a primary estimate of the fECG signal. The same procedure can be applied to the residual signal to enhance the fECG signal. Compared to two other single-lead-based methods, singular value decomposition and nonlinear state-space projection, the proposed method has shown improved robustness and fidelity in restoration of the fECG during testing with synthetic ECG signals and a real fetal ECG database from MIT-BIH PhysioBank.     

Compact long-term recorder for the transabdominal foetal and maternal electrocardiogram

Foetal heart rate (FHR) monitoring is a proven means of assessing foetal health during the antenatal period. Currently, the only widely available instrumentation for producing these data is based on Doppler ultrasound, a technology that is unsuitable for long-term use. For nearly a century, it has been known that the foetal electrocardiogram (FECG) can be detected using electrodes placed on the maternal abdomen. Although these signals suggest an alternative means of FHR derivation, their use has been limited owing to problems of poor signal-to-noise ratio. However, the eminent suitability of the transabdominal FECG for long-term FHR monitoring has suggested that perseverance with the technique would be worthwhile. The paper describes the design, construction and use of a compact, long-term recorder of three channels of 24 h antenatal transabdominal data. Preliminary use of the recorder in around 400 short recording sessions demonstrates that FHR records of equivalent quality to those from Doppler ultrasound-based instruments can be extracted from such data. The success of FHR derivation is, on average, around 65% of the recording period from around 20 weeks gestation (although this figure is reduced from around 28–32 weeks, and the success rates exhibit a wide range when individual subjects are considered). These results demonstrate that the technique offers, not only a means of acquiring long-term FHR data that are problematic to obtain by other means, but also a more patient-friendly alternative to the Doppler ultrasound technique.     

Quantification of the fetal electrocardiogram using averaging technique

A signal analysis procedure is described for obtaining time intervals parameters of the fetal electrocardiogram as recorded from the maternal abdomen. Applying averaging to the fetal electrocardiogram quantification of the PR interval, QRS duration and QT interval were measured. This technique which includes the subtraction of an averaged maternal ECG waveform using cross-correlation function and fast Fourier transform algorithm, enables the detection of all the fetal QRS complexes in spite of their coincidence with the maternal ECGs. Results that were obtained from 21 pregnant women at the gestational age of 32-41 weeks and an example of a recording with fetal premature ventricular contractions are presented. This method shows an important improvement with respect to detection of fetal heart rate and detection of arrhythmia disturbances in the fetal ECG. The averaging procedure can be used to evaluate long-lived alterations in the fetal ECG.