Wyniki wyszukiwania - Biblioteka Nauki

1

Combined application of independent component analysis and projective filtering to fetal ECG extraction

100%

Kotas M.

Biocybernetics and Biomedical Engineering

|

2008

|

tom Vol. 28, no. 1

75-93

EN

The maternal abdominal signals contain a few components: the dominant maternal ECG, various types of noise and the signal of the primary interest - the fetal ECG. In order to obtain the fetal ECG, the maternal signal should first be suppressed. In the paper, we propose a combined application of the independent component analysis and projective filtering of the time-aligned beats to solve the problem of the fetal ECG extraction from multi channel abdominal signals, when the number of the channels is low. The independent component analysis performs spatial decomposition of the signals. It often leads to a successful separation of the maternal and the fetal ECG. When the separation is not complete, projective filtering can be applied to enhance the partially separated maternal ECG. Then the maternal ECG contained in the respective channels can be reconstructed and subtracted from the original composite signals. This operation leads to the extraction of the fetal ECG in the respective channels. The signal can still be enhanced by the second application of the independent component analysis. The developed system operation is ilIustrated, and the results of its application are compared to the results achievable by application of the independent component analysis.

2

State-space averaging for maternal ECG suppression

100%

Kotas M. , Jeżewski J. , Kupka T. , Matonia A.

Journal of Medical Informatics & Technologies

|

2009

|

tom Vol. 13

194--200

EN

In this paper a new method of maternal electrocardiogram suppression for fetal component extraction from one-channel maternal abdominal bioelectric signals is proposed. The method performs maternal ECG estimation by application of state-space averaging. The estimated signal is subtracted from the original one and this way suppressed. The method parameters allow us to balance between the precision of maternal ECG suppression and the necessity not to attenuate the fetal QRS complexes. A small database of the maternal abdominal bioelectric signals is used to investigate the developed system for fetal heart rate determination. The final assessment is based on the detection performance index. It is shown that by proper choice of the parameters we can tune the system so that it is more effective than the classical approach based on template subtraction.

3

Separation of abdominal fetal electrocardiograms in twin pregnancy

84%

Kotas M. , Jeżewski J. , Matonia A. , Kupka T.

Journal of Medical Informatics & Technologies

|

2008

|

tom Vol. 12

83--89

EN

A combined application of independent component analysis and projective filtering of the time-aligned ECG beats is proposed to solve the problem of fetal ECG extraction from multi-channel maternal abdominal electric signals. The developed method is employed to process the four-channel abdominal signals recorded during twin pregnancy. The signals are complicated mixtures of the maternal ECG, the ECGs of the fetal twins and noise of other origin. The independent component analysis cannot separate the respective signals, but the proposed combination of the methods allows to suppress the maternal ECG and when the level of noise is low it leads to an effective separation of the twins' signals.

4

Spatio-spectral independent component analysis for fetal ECG extraction from two-channel maternal abdominal signals

84%

Kotas M. P. , AlShrouf A. M.

Biocybernetics and Biomedical Engineering

|

2024

|

tom Vol. 44, no. 1

247--263

EN

Independent component analysis (ICA) is widely used to separate maternal and fetal electrocardiograms. However, it has become less effective due to the efforts to reduce the number of recording electrodes. To address this issue, we propose an extension of ICA that can extract the fetal electrocardiogram from only two maternal abdominal electric signals. We solve this problem by increasing the dimension of the observed signals using the method of delays, followed by spatio-spectral filtering to separate the source signals. By iteratively applying this approach, we can extract signals that are not separable using the original observations alone. These signals are then clustered to create signal subspaces corresponding to different sources, allowing for a rough reconstruction of signal components produced by these sources. This initial decomposition can then be refined by using the reconstructed components as new observations, extending the original ones, and applying ICA to this extended signal representation. Applied to two-channel maternal abdominal signals, the proposed method was able to extract 3 source signals (two maternal and one fetal), resulting in the achievement of the goal of over-complete blind source separation (BSS). Furthermore, the method enabled the successful detection of fetal QRS (fQRS) complexes in experiments on two datasets of real-world maternal abdominal signals. For the ADFECGDB dataset, the method reached the sensitivity, positive predictivity, and F1 score of 100%, 99.97%, and 99.98%, respectively, outperforming all reference methods. For the PREGNANCY dataset, the corresponding values were 98.95%, 98.92%, and 98.93%, second only to one reference method.

5

Sequential separation of twin pregnancy electrocardiograms

67%

Kotas M. , Leski J. M. , Wrobel J.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2016

|

tom Vol. 64, nr 1

91--101

EN

We propose to tackle the problem of maternal abdominal electric signals decomposition with a combined application of independent component analysis and projective or adaptive filtering. The developed method is employed to process the four-channel abdominal signals recorded during twin pregnancy. These signals are complicated mixtures of the maternal ECG, the ECGs of the fetal twins and noise of various origin. Although the independent component analysis cannot separate the respective signals, the proposed combination of the methods deals with this task successfully. A simulation experiment confirms high efficiency of this approach.