Miyuki Endo

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

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 (p <; 0.05) across these age groups. In particular, STI, IRT, and PEP of the fetuses with 36-41 week were significantly (p <; 0.05) different from other age groups. These findings can be used as sensitive markers for evaluating the fetal cardiac performance.

Model-Based Estimation of Aortic and Mitral Valves Opening and Closing Timings in Developing Human Fetuses

Electromechanical coupling of the fetal heart can be evaluated noninvasively using doppler ultrasound (DUS) signal and fetal electrocardiography (fECG). In this study, an efficient model is proposed using K-means clustering and hybrid Support Vector Machine-Hidden Markov Model (SVM-HMM) modeling techniques. Opening and closing of the cardiac valves were detected from peaks in the high frequency component of the DUS signal decomposed by wavelet analysis. It was previously proposed to automatically identify the valve motion by hybrid SVM-HMM[1] based on the amplitude and timing of the peaks. However, in the present study, six patterns were identified for the DUS components which were actually variable on a beat-to-beat basis and found to be different for the early gestation (16-32 weeks), compared to the late gestation fetuses (36-41 weeks). The amplitude of the peaks linked to the valve motion was different across the six patterns and this affected the precision of valve motion identification by the previous hybrid SVM-HMM method. Therefore in the present study, clustering of the DUS components based on K-means was proposed and the hybrid SVM-HMM was trained for each cluster separately. The valve motion events were consequently identified more efficiently by beat-to-beat attribution of the DUS component peaks. Applying this method, more than 98.6% of valve motion events were beat-to-beat identified with average precision and recall of 83.4% and 84.2% respectively. It was an improvement compared to the hybrid method without clustering with average precision and recall of 79.0% and 79.8%. Therefore, this model would be useful for reliable screening of fetal wellbeing.

Classification of Doppler Ultrasound signal quality for the application of fetal valve motion identification

One dimensional Doppler Ultrasound (DUS) is a commonly applied technique for fetal heart rate monitoring, but it can also be used to identify the timings of fetal cardiac valve motion. These timings are required to estimate the fetal cardiac intervals, which are fundamental and clinically significant markers of fetal development and well-being. Several methods have been proposed in previous studies to automatically identify the valve movement timings using 1-D DUS and fetal Electrocardiography (fECG) as a reference. However DUS is highly susceptible to noise and variable on a beat-to-beat basis. Therefore it is crucial to assess the signal quality to ensure its validity for a reliable estimation of the valve movement timings. An automated quality assessment can provide the operator with an online feedback on the quality of DUS during data collection. This paper investigates automated classification of the DUS signal quality using Naive Bayes (NB) classifier. The quality of 345 beats of DUS signals collected from 57 fetuses was assessed by four independent annotators and used for training and validation of the classifier. Using Fleiss kappa test, a fair agreement was found between the raters with overall κ = 0.3. The performance of the classification was tested by 10-fold cross validation. Results showed an average classification accuracy of 86% on training and 84% on test data.

Intrauterine Ischemic Reperfusion Switches the Fetal Transcriptional Pattern from HIF-1α- to P53-Dependent Regulation in the Murine Brain

Ischemic reperfusion (IR) during the perinatal period is a known causative factor of fetal brain damage. So far, both morphologic and histologic evidence has shown that fetal brain damage can be observed only several hours to days after an IR insult has occurred. Therefore, to prevent fetal brain damage under these circumstances, a more detailed understanding of the underlying molecular mechanisms involved during an acute response to IR is necessary. In the present work, pregnant mice were exposed to IR on day 18 of gestation by clipping one side of the maternal uterine horn. Simultaneous fetal electrocardiography was performed during the procedure to verify that conditions resulting in fetal brain damage were met. Fetal brain sampling within 30 minutes after IR insult revealed molecular evidence that a fetal response was indeed triggered in the form of inhibition of the Akt-mTOR-S6 synthesis pathway. Interestingly, significant changes in mRNA levels for both HIF-1α and p53 were apparent and gene regulation patterns were observed to switch from a HIF-1α-dependent to a p53-dependent process. Moreover, pre-treatment with pifithrin-α, a p53 inhibitor, inhibited protein synthesis almost completely, revealing the possibility of preventing fetal brain damage by prophylactic pifithrin-α treatment.

Investigating the beat by beat phase synchronization between maternal and fetal heart rates

The development of the fetal cardiovascular system plays a crucial role in fetal health. The evolution of the relationship between fetal and maternal cardiac systems during fetal maturation is a characterizing feature for fetal cardiac development. This paper aims to evaluate this relationship by investigating the beat-to-beat synchronization between fetal and maternal heart rates and its variation at different stages of pregnancy. Synchronization epochs and phase locking patterns are analyzed at certain synchronization ratios (SRs) for three gestational age groups (16-26 weeks, 27-33 weeks, 34-40 weeks). Results show that the normalized synchronization epoch is significantly different for three age groups with the p-value of 6.72*10-6 and 2.89*10-4 at SR of 1:2 and 4:5 respectively. The variance of phase locking also shows significant difference for three groups with the p-value less than 10-7 at four SRs. Results also suggest that synchronization may be the force behind the increase in the maternal heart rate to maintain the fetal development and provide supplies for the fetus. Overall, the findings propose new clinical markers for evaluating the antenatal development.

Vaginal LPS changed gene transcriptional regulation response to ischemic reperfusion and increased vulnerability of fetal brain hemorrhage

During pregnancy, both ischemic reperfusion and bacterial agent LPS are known risk factors for fetal brain damage. However, there is a lack of evidence to explain whether vaginal LPS affects the fetus response to ischemic reperfusion. Here we reported that there was more than 2 folds higher vulnerability of fetal brain hemorrhage response to ischemic reperfusion when mother mouse was treated with vaginal LPS. As our previously reported, ischemic reperfusion induces P53-dependent fetal brain damage was based on a molecular mechanism: the transcriptional pattern was changed from HIF-1alpha-dependent to P53-dependent immediately. In the present work, only with vaginal LPS precondition, phosphorylation of activated transcriptional factor (ATF) 2 at Thr71 appeared in response to ischemic reperfusion. Moreover, this phosphorylation was completely blocked by pre-treatment with a P53 inhibitor, pifithrin-α. We concluded that vaginal LPS precondition trigged the p53-dependent phosphorylation of ATF2 in response to ischemic reperfusion, which played an important role of increasing vulnerability to hemorrhage in fetus.

A multi-dimensional Hidden Markov Model approach to automated identification of fetal cardiac valve motion

Fetal cardiac assessment techniques are aimed to identify fetuses at risk of intrauterine compromise or death. Evaluation of the electromechanical coupling as a fundamental part of the fetal heart physiology, provides valuable information about the fetal wellbeing during pregnancy. It is based on the opening and closing time of the cardiac valves and the onset of the QRS complex of the fetal electrocardiogram (fECG). The focus of this paper is on the automated identification of the fetal cardiac valve opening and closing from Doppler Ultrasound signal and fECG as a reference. To this aim a novel combination of Emprical Mode Decomposition (EMD) and multi-dimensional Hidden Markov Models (MD-HMM) was employed which provided beat-to-beat estimation of cardiac valve event timings with improved precision (82.9%) compared to the one dimensional HMM (77.4%) and hybrid HMM-Support Vector Machine (SVM) (79.8%) approaches.

Molecular patterns of neurodevelopmental preconditioning: a study of the effects of antenatal steroid therapy in a protein-restriction mouse model.

Introduction. Prenatal programming secondary to maternal protein restriction renders an inherent susceptibility to neural compromise in neonates and any addition of glucocorticosteroids results in further damage. This is an investigation of consequent global gene activity due to effects of antenatal steroid therapy on a protein restriction mouse model. Methods. C57BL/6N pregnant mice were administered control or protein restricted diets and subjected to either 100 μg/Kg of dexamethasone sodium phosphate with normosaline or normosaline alone during late gestation (E10–E17). Nontreatment groups were also included. Brain samples were collected on embryonic day 17 and analyzed by mRNA microarray analysis. Results. Microarray analyses presented 332 significantly regulated genes. Overall, neurodevelopmental genes were overrepresented and a subset of 8 genes allowed treatment segregation through the hierarchical clustering method. The addition of stress or steroids greatly affected gene regulation through glucocorticoid receptor and stress signaling pathways. Furthermore, differences between dexamethasone-administered treatments implied a harmful effect during conditions of high stress. Microarray analysis was validated using qPCR. Conclusion. The effects of antenatal steroid therapy vary in fetuses according to maternal-fetal factors and environmental stimuli. Defining the key regulatory networks that signal either beneficial or damaging corticosteroid action would result in valuable adjustments to current treatment protocols.

Analysis of maternal-fetal heart rate coupling directions with partial directed coherence

Abstract Maternal psycho-physiological activities affect the fetal heart rate and heart rate variability. However, directions and patterns of maternal and fetal heartbeat coupling are still poorly understood. The aim of this study was to quantify the direction of short-term maternal–fetal cardiac coupling in early, mid and late gestation fetuses by using partial directed coherence (PDC) analysis approach. The analysis was based on fetal electrocardiograms (fECGs) of 66 healthy fetuses; 22 from early gestation 16–25 weeks, 22 from mid gestation 26–30 weeks and 22 from late gestation 32–41 weeks. Results of analyzing PDC demonstrated a causal influence of fetal on maternal heart rate in the early gestation, while it significantly decreased from early to mid gestation along with a significant increase of maternal to fetal coupling strength. The causal influence of maternal on fetal heart rate was the strongest in the mid gestation and remained dominant in the late gestation. In conclusion, the application of PDC revealed detailed information about short-term maternal–fetal cardiac couplings and regulatory mechanisms (patterns) of developing autonomic nervous system function.

Transfer entropy analysis of maternal and fetal heart rate coupling

Although evidence of the short term relationship between maternal and fetal heart rates has been found in previous model-based studies, knowledge about the mechanism and patterns of the coupling during gestation is still limited. In this study, a model-free method based on Transfer Entropy (TE) was applied to quantify the maternal-fetal heart rate couplings in both directions. Furthermore, analysis of the lag at which TE was maximum and its changes throughout gestation, provided more information about the mechanism of coupling and its latency. Experimental results based on fetal electrocardiograms (fECGs) and maternal ECG showed the evidence of coupling for 62 out of 65 healthy mothers and fetuses in each direction, by statistically validating against the surrogate pairs. The fetuses were divided into three gestational age groups: early (16-25 weeks), mid (26-31 weeks) and late (32-41 weeks) gestation. The maximum TE from maternal to fetal heart rate significantly increased from early to mid gestation, while the coupling delay on both directions decreased significantly from mid to late gestation. These changes occur concomitant with the maturation of the fetal sensory and autonomic nervous systems with advancing gestational age. In conclusion, the application of TE with delays revealed detailed information about the changes in fetal-maternal heart rate coupling strength and latency throughout gestation, which could provide novel clinical markers of fetal development and well-being.