Real-Time Fetal Heart Monitoring in Biomagnetic Measurements Using Adaptive Real-Time ICA

Abstract

Abstract-Electrophysiological signals of the developing fetal brain and heart can be investigated by fetal magnetoencephalography (fMEG). During such investigations, the fetal heart activity and that of the mother should be monitored continuously to provide an important indication of current well-being. Due to physical constraints of an fMEG system, it is not possible to use clinically established heart monitors for this purpose. Considering this constraint, we developed a real-time heart monitoring system for biomagnetic measurements and showed its reliability and applicability in research and for clinical examinations. The developed system consists of real-time access to fMEG data, an algorithm based on Independent Component Analysis (ICA), and a graphical user interface (GUI). The algorithm extracts the current fetal and maternal heart signal from a noisy and artifact-contaminated data stream in real-time and is able to adapt automatically to continuously varying environmental parameters. This algorithm has been named Adaptive Real-time ICA (ARICA) and is applicable to real-time artifact removal as well as to related blind signal separation problems.

QRS classification and spatial combination for robust heart rate detection in low-quality fetal ECG recordings

“…In [6] it is already shown that PBSS outperforms other widely used blind source separation techniques, such as independent component analysis [5], in particular for the noninvasive fECG recordings that exhibit a low SNR. Therefore, this study only compares the performance of the developed PBSSa algorithm to the original PBSS technique.…”

“…Several techniques have been proposed to exploit this spatial correlation to enhance the SNR of the fECG [4], [5], [6]. Of these techniques, [4], [5] are so called blind source separation (BSS) techniques, that require no a priori knowledge of the physiology of the fetal cardiac electrical system.…”

“…Of these techniques, [4], [5] are so called blind source separation (BSS) techniques, that require no a priori knowledge of the physiology of the fetal cardiac electrical system. However, this lack of physiological basis reduces the efficiency of the BSS techniques to separate the fECG from the noise in case of low SNR [6], as is typical for non-invasive fECG recordings.…”

Intelligent Surveillance System Based on Stereo Vision for Level Crossings Safety Applications

“…The main disadvantage is that the fast variations cannot be accurately modeled. Delfosse & Loubaton (1995), speech and image recognition Cardoso (1997), data communication Oja et al (1991), sensor signal processing Cvejic et al (2007) and biomedical signal processing Dun et al (2007)Waldert (2007.…”

A study of fetal sympatho-vagal balance at various gestational periods using the length transform on magnetocardiographic data

“…Many efforts have been placed in studying fetal heart rate (HR) variability, in particular time and frequency domain variables that are important markers for fetal well-being [3]- [5]. Assessments of fetal HR and fetal behavior are nowadays cornerstones of clinical fetal evaluation and neurodevelopmental research.Fetal magnetocardiography (fMCG) is an excellent signal source for assessment of fetal HR, providing a precise signal that can be detected throughout the last half of pregnancy and often earlier [6]. It is generally believed that clinical fetal HR monitors based on Doppler ultrasound lack the precision required to accurately assess beat-tobeat variations.…”