Recovery of the fetal electrocardiogram for morphological analysis from two trans-abdominal channels via optimal shrinkage

Su, Pei-Chun; Miller, Stephen G.; Idriss, Salim F.; Barker, Piers; Wu, Hau‐Tieng

doi:10.1088/1361-6579/ab4b13

Cited by 18 publications

(16 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• In [45], optimal shrinkage was used to determine fHR with accuracy of 79.25±31.75% for (semi)-real records and with 93.21 ± 14.31% for synthetic records. In both cases, these are worse results than we have achieved.…”

Section: Discussionmentioning

confidence: 99%

“…• The authors of [45] used an algorithm based on the optimal-shrinkage under the wave-shape manifold model to extract fECG. Both fHR and signal morphology (PR, QT and ST intervals) were analyzed during the experiments on a dataset including real and simulated signals indicating the physiological and pathological condition of fetuses (e.g.…”

Section: A Morphological Analysismentioning

confidence: 99%

See 1 more Smart Citation

Non-Invasive Fetal Electrocardiogram Extraction Based on Novel Hybrid Method for Intrapartum ST Segment Analysis

et al. 2021

View full text Add to dashboard Cite

This study focuses on non-invasive fetal electrocardiogram extraction based on a novel hybrid method, which combines the advantages of non-adaptive and adaptive approaches for non-invasive fetal electrocardiogram morphological analysis. Besides estimating fetal heart rate, which is the main parameter used in the clinical practice, this study provides non-invasive ST segment analysis on data from Abdominal and Direct Fetal Electrocardiogram Database consisting of simultaneous traditionalgold standard invasive fetal scalp electrode and non-invasive fetal electrocardiogram recorded during delivery. This innovative approach utilizing the combination of independent component analysis and recursive least squares algorithms has the potential to extract valuable information from non-invasive fetal electrocardiogram in order to identify eventual sign of fetal distress. This was a prospective observational study of non-invasive fetal electrocardiogram, using 4 abdominally sited electrodes, against the traditional fetal scalp electrode on 8 patients. In terms of fetal heart rate estimation, the accuracy was high for all 8 tested patients with average value equaled 0.20 beats per minute and average value of 1.96 standard deviation equaled 5.80 beats per minute. In 7 patients, it was possible to perform the ST segment analysis with high accuracy in determining T/QRS in comparison with the reference fetal scalp electrode signal with average values and 1.96 standard deviation equaled 0.008 and 0.031 respectively. This study thus demonstrates that ST segment analysis is feasible using non-invasive fECG using the proposed hybrid method. INDEX TERMS Non-invasive fetal electrocardiography (NI-fECG), fetal heart rate (fHR), ST segment analysis (ST-analysis), hybrid method (HM), independent component analysis and recursive least squares (ICA-RLS), electronic fetal monitoring (EFM), fetal distress (FD), fetal scalp electrode (FSE).

show abstract

Section: Discussionmentioning

confidence: 99%

Section: A Morphological Analysismentioning

confidence: 99%

Non-Invasive Fetal Electrocardiogram Extraction Based on Novel Hybrid Method for Intrapartum ST Segment Analysis

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In our previous work, the effects of noise robustness and morphology recovery by optimal shrinkage and other template estimation algorithms had been compared for the purpose of extracting fetal ECG from the trans-abdominal maternal ECG [27] over the Physionet CinC Challenge 2013 database [39]. These methods included independent component analysis (ICA), principal component analysis (PCA), least mean square (LMS), recursive least square (RLS), echo state neural network (ESN), and extended Kalman filter (EKF).…”

Section: Discussionmentioning

confidence: 99%

“…Second, we applied a recently developed denoise technique called optimal shrinkage (OS) [26]. In our previous publication [27], we have demonstrated that a better and more adaptive template for each cardiac cycle is obtained through OS, which helps recover ECG morphology from noisy signals. However, we observed a morphology distortion after the application of OS on clean signals, where "clean" means the noise is dominated by the beat to beat variation.…”

Section: Introductionmentioning

confidence: 99%

Robust T-End Detection via T-End Signal Quality Index and Optimal Shrinkage

Soliman

2020

Sensors

Self Cite

View full text Add to dashboard Cite

An automatic accurate T-wave end (T-end) annotation for the electrocardiogram (ECG) has several important clinical applications. While there have been several algorithms proposed, their performance is usually deteriorated when the signal is noisy. Therefore, we need new techniques to support the noise robustness in T-end detection. We propose a new algorithm based on the signal quality index (SQI) for T-end, coined as tSQI, and the optimal shrinkage (OS). For segments with low tSQI, the OS is applied to enhance the signal-to-noise ratio (SNR). We validated the proposed method using eleven short-term ECG recordings from QT database available at Physionet, as well as four 14-day ECG recordings which were visually annotated at a central ECG core laboratory. We evaluated the correlation between the real-world signal quality for T-end and tSQI, and the robustness of proposed algorithm to various additive noises of different types and SNR’s. The performance of proposed algorithm on arrhythmic signals was also illustrated on MITDB arrhythmic database. The labeled signal quality is well captured by tSQI, and the proposed OS denoising help stabilize existing T-end detection algorithms under noisy situations by making the mean of detection errors decrease. Even when applied to ECGs with arrhythmia, the proposed algorithm still performed well if proper metric is applied. We proposed a new T-end annotation algorithm. The efficiency and accuracy of our algorithm makes it a good fit for clinical applications and large ECG databases. This study is limited by the small size of annotated datasets.

show abstract

“…r Number of Input Channels Su et al [84] introduced a very promising single channel blind source separation (scBSS) algorithm. The algorithm contained three steps.…”

Section: R Thresholding Rules and Parametersmentioning

confidence: 99%

A Review of Signal Processing Techniques for Non-Invasive Fetal Electrocardiography

Kahánková

Martínek

Jaroš

et al. 2020

IEEE Rev. Biomed. Eng.

View full text Add to dashboard Cite

Fetal electrocardiography (fECG) is a promising alternative to cardiotocography continuous fetal monitoring. Robust extraction of the fetal signal from the abdominal mixture of maternal and fetal electrocardiograms presents the greatest challenge to effective fECG monitoring. This is mainly due to the low amplitude of the fetal versus maternal electrocardiogram and to the non-stationarity of the recorded signals. In this review, we highlight key developments in advanced signal processing algorithms for non-invasive fECG extraction and the available open access resources (databases and source code). In particular, we highlight the advantages and limitations of these algorithms as well as key parameters that must be set to ensure their optimal performance. Improving or combining the current or developing new advanced signal processing methods may enable morphological analysis of the fetal electrocardiogram, which today is only possible using the invasive scalp electrocardiography method.

show abstract

Recovery of the fetal electrocardiogram for morphological analysis from two trans-abdominal channels via optimal shrinkage

Cited by 18 publications

References 70 publications

Non-Invasive Fetal Electrocardiogram Extraction Based on Novel Hybrid Method for Intrapartum ST Segment Analysis

Non-Invasive Fetal Electrocardiogram Extraction Based on Novel Hybrid Method for Intrapartum ST Segment Analysis

Robust T-End Detection via T-End Signal Quality Index and Optimal Shrinkage

A Review of Signal Processing Techniques for Non-Invasive Fetal Electrocardiography

Contact Info

Product

Resources

About