Robust fetal ECG extraction and detection from abdominal leads

Abstract

The fetal ECG derived from abdominal leads provides an alternative to standard means of fetal monitoring. Furthermore, it permits long-term and ambulant recordings, which expands the range diagnostic possibilities for evaluating the fetal health state. However, due to the temporal and spectral overlap of maternal and fetal signals, the usage of abdominal leads imposes the need for elaborated signal processing routines.In this work a modular combination of processing techniques is presented. Its core consists of two maternal ECG estimation techniques, namely the extended Kalman smoother (EKS) and template adaption (TA) in combination with an innovative detection algorithm. Our detection method employs principles of evolutionary computing to detect fetal peaks by considering the periodicity and morphological characteristics of the fetal signal. In a postprocessing phase, single channel detections are combined by means of kernel density estimation and heart rate correction.The described methodology was presented during the Computing in Cardiology Challenge 2013. The entry was the winner of the closed-source events with average scores for events 4/5 with 15.1/3.32 (TA) and 69.5/4.58 (EKS) on training set-A and 20.4/4.57 (TA) and 219/7.69 (EKS) on test set-B, respectively. Using our own clinical data (24 subjects each 20 min recordings) and statistical measures beyond the Challenge's scoring system, we further validated the proposed method. For our clinical data we obtained an average detection rate of 82.8% (TA) and 83.4% (EKS). The achieved results show that the proposed methods are able produce reliable fetal heart rate estimates from a restricted number of abdominal leads.

Non-invasive Detection and Compression of Fetal Electrocardiogram

“…For instance, the common diagnostic tool for noninvasive ECG recordings usually adopts 8-lead or 12-lead electrode placement (with symmetric electrodes) [2,20,41], which had been derived via clinical validation in a couple of periods. The FECG components in multi-lead abdominal recordings are mutually dependent with each other on the fetal position and the electrical conduction toward the maternal abdominal skin.…”

“…Due to the variations of each component, calculating linear combinations of multichannel outputs generally enhance the signal-to-noise ratio (SNR) of FECG [20]. Meanwhile, since the main electrical axis of the fetal heart position is a priori uncertain, in order to increase the possibilities that the calculated nonphysiological leads contain significant FECG components, it is often chosen to compute a set of four linear combinations for equal weights, that is, the position angles correspond with 0 ,45 ,90 , and 135 for the 8-lead placement [2,20]. Similarly, a 12-lead ECG placement (12 leads calculated using 10 electrodes, in which 6 chest electrodes provide information on the heart's horizontal plane and 4 limb electrodes on the heart's vertical plane) illustrates a more cohesive diagram on the accurate electrical activity of the heart by recording information through 12 different perspectives, where the instruction with specific details on the 12-lead placement guide was illustrated in Ref.…”

“…In this chapter, we present a general study on several categories of algorithms in the field of noninvasive FECG detection, and carry out a performance analysis via several metrics on the state-of-the-art schemes for extracting FECG using sample databases [2,19,21]. We proposed a unified approach for the dynamic system design on FECG detection, with a block diagram on noninvasive ECG extraction by collaborating data-processing techniques on weak signal detection and parameter estimation [8].…”

Sparse Coding of Cardiac Signals for Automated Component Selection after Blind Source Separation

“…The sparse representation of each component's peak detections at times t i (i ∈ [1, I], I is the number of peak detections) is obtained by coding according to the dictionary {peak -1, no peak -0} together with temporal apriori information. The cardiac refractory period ∆t R is considered as 0.3 s [10], whereas the maximum peak-topeak distance ∆t max is considered as 1.5 s (i.e. a minimum heart rate of 45 bpm [13]).…”

“…Moreover, template matching was applied in [8]. The morphological nature and periodicity of QRS waveforms of the ECG were exploited for instance in [9,10]. A combination of both approaches, primarily sorting out undesired BSS components and further selecting the (best) ECG component among the residual channels, each utilizing frequency characteristics, was proposed by our group earlier in [3].…”