A Hybrid EMD-Kurtosis Method for Estimating Fetal Heart Rate from Continuous Doppler Signals

A Robust Approach Assisted by Signal Quality Assessment for Fetal Heart Rate Estimation from Doppler Ultrasound Signal

Fetal heart rate (FHR) monitoring, typically using Doppler ultrasound (DUS) signals, is an important technique for assessing fetal health. In this work, we develop a robust DUS-based FHR estimation approach complemented by DUS signal quality assessment (SQA) based on unsupervised representation learning in response to the drawbacks of previous DUS-based FHR estimation and DUS SQA methods. We improve the existing FHR estimation algorithm based on the autocorrelation function (ACF), which is the most widely used method for estimating FHR from DUS signals. Short-time Fourier transform (STFT) serves as a signal pre-processing technique that allows the extraction of both temporal and spectral information. In addition, we utilize double ACF calculations, employing the first one to determine an appropriate window size and the second one to estimate the FHR within changing windows. This approach enhances the robustness and adaptability of the algorithm. Furthermore, we tackle the challenge of low-quality signals impacting FHR estimation by introducing a DUS SQA method based on unsupervised representation learning. We employ a variational autoencoder (VAE) to train representations of pre-processed fetal DUS data and aggregate them into a signal quality index (SQI) using a self-organizing map (SOM). By incorporating the SQI and Kalman filter (KF), we refine the estimated FHRs, minimizing errors in the estimation process. Experimental results demonstrate that our proposed approach outperforms conventional methods in terms of accuracy and robustness.

Machine learning applied in maternal and fetal health: a narrative review focused on pregnancy diseases and complications

Introduction

Machine learning (ML) corresponds to a wide variety of methods that use mathematics, statistics and computational science to learn from multiple variables simultaneously. By means of pattern recognition, ML methods are able to find hidden correlations and accomplish accurate predictions regarding different conditions. ML has been successfully used to solve varied problems in different areas of science, such as psychology, economics, biology and chemistry. Therefore, we wondered how far it has penetrated into the field of obstetrics and gynecology.

Aim

To describe the state of art regarding the use of ML in the context of pregnancy diseases and complications.

Methodology

Publications were searched in PubMed, Web of Science and Google Scholar. Seven subjects of interest were considered: gestational diabetes mellitus, preeclampsia, perinatal death, spontaneous abortion, preterm birth, cesarean section, and fetal malformations.

Current state

ML has been widely applied in all the included subjects. Its uses are varied, the most common being the prediction of perinatal disorders. Other ML applications include (but are not restricted to) biomarker discovery, risk estimation, correlation assessment, pharmacological treatment prediction, drug screening, data acquisition and data extraction. Most of the reviewed articles were published in the last five years. The most employed ML methods in the field are non-linear. Except for logistic regression, linear methods are rarely used.

Future challenges

To improve data recording, storage and update in medical and research settings from different realities. To develop more accurate and understandable ML models using data from cutting-edge instruments. To carry out validation and impact analysis studies of currently existing high-accuracy ML models.

Conclusion

The use of ML in pregnancy diseases and complications is quite recent, and has increased over the last few years. The applications are varied and point not only to the diagnosis, but also to the management, treatment, and pathophysiological understanding of perinatal alterations. Facing the challenges that come with working with different types of data, the handling of increasingly large amounts of information, the development of emerging technologies, and the need of translational studies, it is expected that the use of ML continue growing in the field of obstetrics and gynecology.

Novel Method for Fetal and Maternal Heart Rate Measurements Using 2-D Ultrasound Color Doppler Flow Images

Fetal heart rate (FHR) and maternal heart rate (MHR) are important indicators of fetal well-being during pregnancy. A common method in clinical examination is to estimate the FHR using the Doppler shift of echoes from umbilical artery blood flow based on an ultrasound pulsed-wave (PW) Doppler technique. Similarly, a sampling gate can be located at the maternal blood flow to measure MHR using PW Doppler. Ultrasound color Doppler flow imaging (CDFI) is one of the most commonly used imaging modes for clinical fetal examinations. Color coding is employed to display the blood flow velocity and direction in color grades according to the Doppler shift. Continuous CDF images contain dynamic changes characteristics of the blood flow. The periodic characteristics can be used to obtain heart rate information. Therefore, here we propose a novel method to measure FHR and MHR simultaneously using CDF images. The proposed method calculates the histogram of color similarity of CDF images to initially extract the periodic characteristics of the CDF image sequence. The histogram of color similarity function is then processed by a bandpass filter and autocorrelation operation to reduce noise and enhance periodicity. Finally, peak detection is performed on the processed signal to obtain the period and estimate the heart rate. The proposed method can measure the FHR and MHR in parallel after selecting two regions containing the umbilical artery and maternal blood flow, respectively. Thus, the method has high computational efficiency. The proposed method was evaluated on a Doppler flow phantom and clinical CDF images and then compared with the PW Doppler method. The correlation analysis and Bland-Altman plots reveal that the proposed method agrees well with the PW Doppler. It is a sanity check method for real-time clinical FHR and MHR measurements.

Cardiotocography in Obstetrics: New Solutions for "Routine" Technology

This work is devoted to the problems of one of the most common screening examinations used in medical practice: fetal cardiotocography (CTG). The technology of ultrasonic monitoring of fetal heart rate (HR) variations has been used for more than 70 years. During this time, it has undergone many upgrades and has been characterized several times as a hopelessly outdated routine technology. Over the past 5-7 years, many in-depth studies and review papers on cardiotocography have appeared, which revealed both the problems and prospects of the technology. Basically, hopes are associated with artificial intelligence, which should increase the accuracy of the analysis of initially inaccurate measurements obtained using ultrasonic testing. At the same time, after the introduction of pulsed operating modes and the appearance of multi-chip sensors, the quality of the original signal remains practically unchanged. This circumstance makes the prospects of the technology very problematic. However, until now, there has not been a reliable replacement for this screening, which is equally safe, non-invasive, and accessible to a wide range of specialists, medical institutions, and patients. The paper discusses and substantiates proposals for improving the technology based on original (different from traditional CTG) methods of processing information received from ultrasonic sensors, which, in the author's opinion, allow for solving the main problems of CTG: identifying the correct direction of radiation to the fetal heart and to reliably evaluate beat-to-beat heart rate.

A novel algorithm based on ensemble empirical mode decomposition for non-invasive fetal ECG extraction

Non-invasive fetal electrocardiography appears to be one of the most promising fetal monitoring techniques during pregnancy and delivery nowadays. This method is based on recording electrical potentials produced by the fetal heart from the surface of the maternal abdomen. Unfortunately, in addition to the useful fetal electrocardiographic signal, there are other interference signals in the abdominal recording that need to be filtered. The biggest challenge in designing filtration methods is the suppression of the maternal electrocardiographic signal. This study focuses on the extraction of fetal electrocardiographic signal from abdominal recordings using a combination of independent component analysis, recursive least squares, and ensemble empirical mode decomposition. The method was tested on two databases, the Fetal Electrocardiograms, Direct and Abdominal with Reference Heartbeats Annotations and the PhysioNet Challenge 2013 database. The evaluation was performed by the assessment of the accuracy of fetal QRS complexes detection and the quality of fetal heart rate determination. The effectiveness of the method was measured by means of the statistical parameters as accuracy, sensitivity, positive predictive value, and F1-score. Using the proposed method, when testing on the Fetal Electrocardiograms, Direct and Abdominal with Reference Heartbeats Annotations database, accuracy higher than 80% was achieved for 11 out of 12 recordings with an average value of accuracy 92.75% [95% confidence interval: 91.19-93.88%], sensitivity 95.09% [95% confidence interval: 93.68-96.03%], positive predictive value 96.36% [95% confidence interval: 95.05-97.17%] and F1-score 95.69% [95% confidence interval: 94.83-96.35%]. When testing on the Physionet Challenge 2013 database, accuracy higher than 80% was achieved for 17 out of 25 recordings with an average value of accuracy 78.24% [95% confidence interval: 73.44-81.85%], sensitivity 81.79% [95% confidence interval: 76.59-85.43%], positive predictive value 87.16% [95% confidence interval: 81.95-90.35%] and F1-score 84.08% [95% confidence interval: 80.75-86.64%]. Moreover, the non-invasive ST segment analysis was carried out on the records from the Fetal Electrocardiograms, Direct and Abdominal with Reference Heartbeats Annotations database and achieved high accuracy in 7 from in total of 12 records (mean values μ < 0.1 and values of ±1.96σ < 0.1).

Unsupervised hidden semi-Markov model for automatic beat onset detection in 1D Doppler ultrasound

OBJECTIVE

One dimensional (1D) Doppler ultrasound (DUS) is commonly used for fetal health assessment, during both regular prenatal visits and labor. It is used in preference to ECG and other modalities because of its simplicity and cost. To date, all analysis of such data has been confined to a smoothed, windowed heart rate estimation derived from the 1D DUS signal, reducing the potential of short-term variability information. A first step in improving the assessment of short-term variability of the fetal heart rate (FHR) is through implementing an accurate beat detector for 1D DUS signals.

APPROACH

This work presents an unsupervised probabilistic segmentation method enabled by a hidden semi-Markov model (HSMM). The proposed method employs envelope and spectral features for an online segmentation of fetal 1D DUS signal. The beat onsets and fetal cardiac beat-to-beat intervals are then estimated from the segmentations. For this work, two data sets were used, including 1D DUS recordings from five fetuses recorded in Germany, comprising 6521 beats and 45.06 minutes of data (dataset 1). Simultaneous fetal ECG (fECG) was used as the reference for beat timing. Dataset 2, comprising 4044 beats captured from 17 subjects in the UK was hand scored for beat location and was used as an independent held-out test set. Leave-one-out subject cross-validation was used for parameter tuning on dataset 1. No retraining was performed for dataset 2. To assess the performance of the beat onset detection, the root mean square error (RMSE), F1 score, sensitivity, positive predictivity (PPV) and the error in several standard common heart rate variability metrics were used. These metrics were evaluated on three fiducial points: (1) beat onset, (2) beat offset, and (3) middle of beat interval.

MAIN RESULTS

In dataset 1, the proposed method provided an RMSE of 20 ms, F1 score of 97.5 %, a Se of 97.6%, and a PPV of 97.3%. In dataset 2, the proposed method achieved an RMSE of 26 ms, an F1 score of 98.5 %, a Se of 98.0 % and a PPV of 98.9 %. It was also determined that the best beat-to-beat interval was derived from the onset of each beat. For the dataset 2, significant correlations were found in all short term heart rate variability metrics tested, both in the time and frequency domain. Only the proportion of successive normal-to-normal interval differences greater than 20 ms (pNN20) exhibited a significant absolute difference.

SIGNIFICANCE

This work presents the first-ever description of an algorithm to identify cardiac beats with 1D DUS, closely matching the fetal ECG-derived beats, to enable short-term heart rate variability analysis. The novel algorithm proposed requires no human labeling of data, and could have applicability beyond 1D DUS to other similar highly variable time series.

New Method for Beat-to-Beat Fetal Heart Rate Measurement Using Doppler Ultrasound Signal

The most commonly used method of fetal monitoring is based on heart activity analysis. Computer-aided fetal monitoring system enables extraction of clinically important information hidden for visual interpretation-the instantaneous fetal heart rate (FHR) variability. Today's fetal monitors are based on monitoring of mechanical activity of the fetal heart by means of Doppler ultrasound technique. The FHR is determined using autocorrelation methods, and thus it has a form of evenly spaced-every 250 ms-instantaneous measurements, where some of which are incorrect or duplicate. The parameters describing a beat-to-beat FHR variability calculated from such a signal show significant errors. The aim of our research was to develop new analysis methods that will both improve an accuracy of the FHR determination and provide FHR representation as time series of events. The study was carried out on simultaneously recorded (during labor) Doppler ultrasound signal and the reference direct fetal electrocardiogram Two subranges of Doppler bandwidths were separated to describe heart wall movements and valve motions. After reduction of signal complexity by determining the Doppler ultrasound envelope, the signal was analyzed to determine the FHR. The autocorrelation method supported by a trapezoidal prediction function was used. In the final stage, two different methods were developed to provide signal representation as time series of events: the first using correction of duplicate measurements and the second based on segmentation of instantaneous periodicity measurements. Thus, it ensured the mean heart interval measurement error of only 1.35 ms. In a case of beat-to-beat variability assessment the errors ranged from -1.9% to -10.1%. Comparing the obtained values to other published results clearly confirms that the new methods provides a higher accuracy of an interval measurement and a better reliability of the FHR variability estimation.

Independent Analysis of Decelerations and Resting Periods through CEEMDAN and Spectral-Based Feature Extraction Improves Cardiotocographic Assessment

Fetal monitoring is commonly based on the joint recording of the fetal heart rate (FHR) and uterine contraction signals obtained with a cardiotocograph (CTG). Unfortunately, CTG analysis is difficult, and the interpretation problems are mainly associated with the analysis of FHR decelerations. From that perspective, several approaches have been proposed to improve its analysis; however, the results obtained are not satisfactory enough for their implementation in clinical practice. Current clinical research indicates that a correct CTG assessment requires a good understanding of the fetal compensatory mechanisms. In previous works, we have shown that the complete ensemble empirical mode decomposition with adaptive noise, in combination with time-varying autoregressive modeling, may be useful for the analysis of those characteristics. In this work, based on this methodology, we propose to analyze the FHR deceleration episodes separately. The main hypothesis is that the proposed feature extraction strategy applied separately to the complete signal, deceleration episodes, and resting periods (between contractions), improves the CTG classification performance compared with the analysis of only the complete signal. Results reveal that by considering the complete signal, the classification performance achieved 81.7% quality. Then, including information extracted from resting periods, it improved to 83.2%.

[Optimal template selecting combined with non-liner template matching for Doppler fetal heart rate extraction]

The ultrasound Doppler fetal heart rate measurement is the gold standard of fetal heart rate counting. However, the existing fetal heart rate extraction algorithms are not designed specifically to suppress the high maternal interference during the second stage of labor, and false detection occurrences are common during labor. With this background, a method combining time-frequency frame template library optimal selecting and non-linear template matching is proposed. The method contributes a template library, and the optimal template can be selected to match the signal frame. After the short-time Fourier transform of the signal, the difference between the signal and the template is optimized by leaky rectified linear unit (LReLU) function frame by frame. The heart rate was calculated from the peak of the matching curve and the heart rate was calculated. By comparing the proposed method with the autocorrelation method, the results show that the detection accuracy of the proposed method is improved by 20% on average, and the non-linear template matching of 23% samples is at least 50% higher than the autocorrelation method. This paper designs the algorithm by analyzing the characteristics of the interference and signal mixing. We hope that this paper will provide a new idea for fetal heart rate extraction which not only focuses on the original signal.

An open source autocorrelation-based method for fetal heart rate estimation from one-dimensional Doppler ultrasound

OBJECTIVE

Open research on fetal heart rate (FHR) estimation is relatively rare, and evidence for the utility of metrics derived from Doppler ultrasound devices has historically remained hidden in the proprietary documentation of commercial entities, thereby inhibiting its assessment and improvement. Nevertheless, recent studies have attempted to improve FHR estimation; however, these methods were developed and tested using datasets composed of few subjects and are therefore unlikely to be generalizable on a population level. The work presented here introduces a reproducible and generalizable autocorrelation (AC)-based method for FHR estimation from one-dimensional Doppler ultrasound (1D-DUS) signals.

APPROACH

Simultaneous fetal electrocardiogram (fECG) and 1D-DUS signals generated by a hand-held Doppler transducer in a fixed position were captured by trained healthcare workers in a European hospital. The fECG QRS complexes were identified using a previously published fECG extraction algorithm and were then over-read to ensure accuracy. An AC-based method to estimate FHR was then developed on this data, using a total of 721 1D-DUS segments, each 3.75 s long, and parameters were tuned with Bayesian optimization. The trained FHR estimator was tested on two additional (independent) hand-annotated Doppler-only datasets recorded with the same device but on different populations: one composed of 3938 segments (from 99 fetuses) acquired in rural Guatemala, and another composed of 894 segments (from 17 fetuses) recorded in a hospital in the UK.

MAIN RESULTS

The proposed AC-based method was able to estimate FHR within 10% of the reference FHR values 96% of the time, with an accuracy of 97% for manually identified good quality segments in both of the independent test sets.

SIGNIFICANCE

This is the first work to publish open source code for FHR estimation from 1D-DUS data. The method was shown to satisfy estimations within 10% of the reference FHR values and it therefore defines a minimum accuracy for the field to match or surpass. Our work establishes a basis from which future methods can be developed to more accurately estimate FHR variability for assessing fetal wellbeing from 1D-DUS signals.

Fetal Cardiac Doppler Signal Processing Techniques: Challenges and Future Research Directions

The fetal Doppler Ultrasound (DUS) is commonly used for monitoring fetal heart rate and can also be used for identifying the event timings of fetal cardiac valve motions. In early-stage fetuses, the detected Doppler signal suffers from noise and signal loss due to the fetal movements and changing fetal location during the measurement procedure. The fetal cardiac intervals, which can be estimated by measuring the fetal cardiac event timings, are the most important markers of fetal development and well-being. To advance DUS-based fetal monitoring methods, several powerful and well-advanced signal processing and machine learning methods have recently been developed. This review provides an overview of the existing techniques used in fetal cardiac activity monitoring and a comprehensive survey on fetal cardiac Doppler signal processing frameworks. The review is structured with a focus on their shortcomings and advantages, which helps in understanding fetal Doppler cardiogram signal processing methods and the related Doppler signal analysis procedures by providing valuable clinical information. Finally, a set of recommendations are suggested for future research directions and the use of fetal cardiac Doppler signal analysis, processing, and modeling to address the underlying challenges.