Automated Estimation of Fetal Cardiac Timing Events From Doppler Ultrasound Signal Using Hybrid Models

Abstract

In this paper, a new noninvasive method is proposed for automated estimation of fetal cardiac intervals from Doppler Ultrasound (DUS) signal. This method is based on a novel combination of empirical mode decomposition (EMD) and hybrid support vector machines-hidden Markov models (SVM/HMM). EMD was used for feature extraction by decomposing the DUS signal into different components (IMFs), one of which is linked to the cardiac valve motions, i.e. opening (o) and closing (c) of the Aortic (A) and Mitral (M) valves. The noninvasive fetal electrocardiogram (fECG) was used as a reference for the segmentation of the IMF into cardiac cycles. The hybrid SVM/HMM was then applied to identify the cardiac events, based on the amplitude and timing of the IMF peaks as well as the sequence of the events. The estimated timings were verified using pulsed doppler images. Results show that this automated method can continuously evaluate beat-to-beat valve motion timings and identify more than 91% of total events which is higher than previous methods. Moreover, the changes of the cardiac intervals were analyzed for three fetal age groups: 16-29, 30-35, and 36-41 weeks. The time intervals from Q-wave of fECG to Ac (Systolic Time Interval, STI), Ac to Mo (Isovolumic Relaxation Time, IRT), Q-wave to Ao (Preejection Period, PEP) and Ao to Ac (Ventricular Ejection Time, VET) were found to change significantly ( ) across these age groups. In particular, STI, IRT, and PEP of the fetuses with 36-41 week were significantly ( ) different from other age groups. These findings can be used as sensitive markers for evaluating the fetal cardiac performance.

Estimating Fetal Gestational Age Using Cardiac Valve Intervals

“…The valve intervals can be used to assess the Autonomic Nervous System (ANS) function, as an alternative to FHRV, since the cardiac mechanics are known to reflect the autonomic control [13,14]. Significant changes in the valve intervals with advancing GA were also reported in our previous studies [11]. The aim of the current paper is to use these intervals as a novel GA estimator which reflects the development of fetal ANS.…”

“…However, FHR is influenced by arrhythmias, fetal behavioral states, heart rate patterns and maternal conditions [8,9]. Fetal cardiac valve intervals are other measures which could be obtained from non-invasive, low cost and easyto-operate devices, and provide reliable markers for fetal development and wellbeing [10,11]. These intervals are based on opening and closing timings of the fetal cardiac valves and can be automatically estimated as proposed in our previous papers [11,12].…”

“…Fetal cardiac valve intervals are other measures which could be obtained from non-invasive, low cost and easyto-operate devices, and provide reliable markers for fetal development and wellbeing [10,11]. These intervals are based on opening and closing timings of the fetal cardiac valves and can be automatically estimated as proposed in our previous papers [11,12]. The valve intervals can be used to assess the Autonomic Nervous System (ANS) function, as an alternative to FHRV, since the cardiac mechanics are known to reflect the autonomic control [13,14].…”

Is Abdominal Fetal Electrocardiography an Alternative to Doppler Ultrasound for FHR Variability Evaluation?

“…Principle of operation relies on internal processing of the envelope of the US beam reflected from moving parts of fetal hearts—valves or walls, to find the episodes corresponding to consecutive heart beats. However, a complex structure and varying content of the US signal, usually caused by relocation of the fetal heart in relation to a transducer during monitoring session, make a determination of the beat-to-beat interval very difficult (Khandoker et al, 2009; Marzbanrad et al, 2014). Therefore, a correlation techniques, considering full shape of the analyzed signal, have been applied.…”

The Removal of EOG Artifacts From EEG Signals Using Independent Component Analysis and Multivariate Empirical Mode Decomposition

“…Subsequently, some investigators introduce the techniques based on the combination of wavelet transform and ICA for suppression of EOAs in EEG recordings [11][12][13]. Additionally, empirical mode decomposition (EMD) is an adaptive method for analyzing the nonlinear signal [14][15][16]. Many EMD-based methods are proposed to remove EOAs.…”