2015
DOI: 10.1007/s13246-015-0381-2
|View full text |Cite
|
Sign up to set email alerts
|

Robust fetal QRS detection from noninvasive abdominal electrocardiogram based on channel selection and simultaneous multichannel processing

Abstract: The purpose of this study is to provide a new method for detecting fetal QRS complexes from non-invasive fetal electrocardiogram (fECG) signal. Despite most of the current fECG processing methods which are based on separation of fECG from maternal ECG (mECG), in this study, fetal heart rate (FHR) can be extracted with high accuracy without separation of fECG from mECG. Furthermore, in this new approach thoracic channels are not necessary. These two aspects have reduced the required computational operations. Co… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

1
9
0

Year Published

2016
2016
2021
2021

Publication Types

Select...
9
1

Relationship

1
9

Authors

Journals

citations
Cited by 15 publications
(10 citation statements)
references
References 29 publications
1
9
0
Order By: Relevance
“…First, based on the geometry of the inherited oscillatory structure of the cardiac activity, the diffusion-based manifold learning technique is applied to do the channel section. While other channel selection criteria mainly are based on the power spectral distribution, wave morphology entropy, root mean square error, etc, to find the clearest and most enhanced QRS complexes [15,22], our approach is different since we carefully examine the nontrivial underlying geometric structure hosting the cardiac activity by the DM and look for the linear combination that is most like a simple closed curve. Second, we apply the modern time-frequency analysis technique, the dsSTFT, and the beat tracking algorithms detailed in [50] to obtain an accurate R peak locations, and the nonlocal median, to better estimate the maternal ECG morphology and fetal ECG morphology.…”
Section: 2mentioning
confidence: 99%
“…First, based on the geometry of the inherited oscillatory structure of the cardiac activity, the diffusion-based manifold learning technique is applied to do the channel section. While other channel selection criteria mainly are based on the power spectral distribution, wave morphology entropy, root mean square error, etc, to find the clearest and most enhanced QRS complexes [15,22], our approach is different since we carefully examine the nontrivial underlying geometric structure hosting the cardiac activity by the DM and look for the linear combination that is most like a simple closed curve. Second, we apply the modern time-frequency analysis technique, the dsSTFT, and the beat tracking algorithms detailed in [50] to obtain an accurate R peak locations, and the nonlocal median, to better estimate the maternal ECG morphology and fetal ECG morphology.…”
Section: 2mentioning
confidence: 99%
“…There have been many attempts to conquer this challenge in the past decades, and we can roughly classify those attempts into three categories -(a) multiple ta-mECG channels, with or without one or more maternal thoracic ECG signals; (b) only single ta-mECG channel; (c) few (two or three) ta-mECG channels. Most attempts fall in category (a), and researchers apply algorithms like blind source separation (BSS) [18,19,20,21], semi-BSS like periodic component analysis [22,23,24], adaptive filtering like approaches [25,26,27,28,29,30,31], and others [32,33,34]. When there is only a single channel ta-mECG in category (b), researchers consider approaches like template subtraction (TS) [35,36,37,38,39,40,41,42], time-frequency analysis [43,44,45,46,47,48], sequential total variation [49], or state space reconstruction via lag map [50,51,52].…”
Section: Introductionmentioning
confidence: 99%
“…For the extraction of FECG, many sophisticated signal processing methods have been used in literature. The approaches based on the adaptive filtering which are combined with wavelet transform [2], singular value decomposition [3], cross-correlation method and orthogonal basis [4], independent component analysis and wavelet-based techniques [5,6] and so forth. These approaches can be categorized based on the principal signal processing methodologies which are adaptive filtering, linear decomposition and non-linear decomposition.…”
Section: Introductionmentioning
confidence: 99%