Foetal phonocardiographic signal denoising based on non-negative matrix factorization
01 Jan 2012-Journal of Medical Engineering & Technology (Taylor & Francis)-Vol. 36, Iss: 1, pp 57-66
TL;DR: Using the NMF algorithm, a substantial improvement in SNR of the fPCG signals in the range of 12–30 dB has been achieved, providing a high quality assessment of foetal well-being.
Abstract: Foetal phonocardiography (fPCG) is a non-invasive, cost-effective and simple technique for antenatal care. The fPCG signals contain vital information of diagnostic importance regarding the foetal health. However, the fPCG signal is usually contaminated by various noises and thus requires robust signal processing to denoise the signal. The main aim of this paper is to develop a methodology for removal of unwanted noise from the fPCG signal. The proposed methodology utilizes the non-negative matrix factorization (NMF) algorithm. The developed methodology is tested on both simulated and real-time fPCG signals. The performance of the developed methodology has been evaluated in terms of the gain in signal-to-noise ratio (SNR) achieved through the process of denoising. In particular, using the NMF algorithm, a substantial improvement in SNR of the fPCG signals in the range of 12–30 dB has been achieved, providing a high quality assessment of foetal well-being.
Citations
More filters
TL;DR: An overview of the existing standards of fetal monitoring is provided and a comprehensive survey on Fetal Phonocardiography is provided with focus on trends in data collection, signal processing techniques and synthesis models that have been developed to date.
71 citations
TL;DR: A randomised trial for the evaluation of a new model of routine antenatal care and the results confirm the need for further research into this area.
Abstract: Summary Background We undertook a multicentre randomised controlled trial that compared the standard model of antenatal care with a new model that emphasises actions known to be effective in improving maternal or neonatal outcomes and has fewer clinic visits. Methods Clinics in Argentina, Cuba, Saudi Arabia, and Thailand were randomly allocated to provide either the new model (27 clinics) or the standard model currently in use (26 clinics). All women presenting for antenatal care at these clinics over an average of 18 months were enrolled. Women enrolled in clinics offering the new model were classified on the basis of history of obstetric and clinical conditions. Those who did not require further specific assessment or treatment were offered the basic component of the new model, and those deemed at higher risk received the usual care for their conditions; however, all were included in the new-model group for the analyses, which were by intention to treat. The primary outcomes were low birthweight (<2500 g), preeclampsia/eclampsia, severe postpartum anaemia (<90 g/L haemoglobin), and treated urinary-tract infection. There was an assessment of quality of care and an economic evaluation.
60 citations
TL;DR: A novel algorithm based on wavelet transform has been developed for denoising of fPCG signals and the performance of newly developed wavelet is found to be better when compared with the existing wavelets.
Abstract: Fetal phonocardiography (fPCG) based antenatal care system is economical and has a potential to use for long-term monitoring due to noninvasive nature of the system. The main limitation of this technique is that noise gets superimposed on the useful signal during its acquisition and transmission. Conventional filtering may result into loss of valuable diagnostic information from these signals. This calls for a robust, versatile, and adaptable denoising method applicable in different operative circumstances. In this work, a novel algorithm based on wavelet transform has been developed for denoising of fPCG signals. Successful implementation of wavelet theory in denoising is heavily dependent on selection of suitable wavelet basis function. This work introduces a new mother wavelet basis function for denoising of fPCG signals. The performance of newly developed wavelet is found to be better when compared with the existing wavelets. For this purpose, a two-channel filter bank, based on characteristics of fPCG signal, is designed. The resultant denoised fPCG signals retain the important diagnostic information contained in the original fPCG signal.
34 citations
TL;DR: The proposed approach (namely WT–FD) is a wavelet transform (WT)-based method that combines fractal dimension (FD) analysis in the WT domain for the extraction of fHSs from the underlying noise to achieve fetal heartbeat segmentation.
Abstract: Phonocardiography is a noninvasive technique for the detection of fetal heart sounds (fHS). In this study, analysis of fetal phonocardiograph signals (fPCG), in order to achieve fetal heartbeat segmentation, is proposed. The proposed approach (namely WT-FD) is a Wavelet Transform (WT)-based method that combines Fractal Dimension (FD) analysis in the WT domain for the extraction of fHSs from the underlying noise. Its adoption in this field stems from its successful use in the fields of lung and bowel sounds de-noising analysis. The efficiency of the WT-FD method in fHS extraction has been evaluated with 19 simulated fHS signals, created for the present study, with additive noise up to (3dB), along with the Simulated Fetal PCGs database available at PhysioBank. Results have shown promising performance in the identification of the correct location and morphology of the fHSs, reaching an overall accuracy of 89% justifying the efficacy of the method. The WT-FD approach effectively extracts the fHS signals from the noisy background, paving the way for testing it in real fHSs and clearly contributing to better evaluation of the fetal heart functionality.
29 citations
Cites background from "Foetal phonocardiographic signal de..."
...Throughout the years, various signal processing approaches for de-noising the fPCG signal have been examined and proposed (Unser and Aldroubi, 1996; Messer et al., 2001; Várady et al., 2003; Xiu-Min and Gui-Tao, 2009; Chourasia and Mittra, 2010; Chourasia et al., 2011, 2014)....
[...]
01 Apr 1984
TL;DR: This management of common problems in obstetrics and gynecology, it will really give you the good idea to be successful.
Abstract: By reading, you can know the knowledge and things more, not only about what you get from people to people. Book will be more trusted. As this management of common problems in obstetrics and gynecology, it will really give you the good idea to be successful. It is not only for you to be success in certain life you can be successful in everything. The success can be started by knowing the basic knowledge and do actions.
25 citations
References
More filters
TL;DR: An algorithm for non-negative matrix factorization is demonstrated that is able to learn parts of faces and semantic features of text and is in contrast to other methods that learn holistic, not parts-based, representations.
Abstract: Is perception of the whole based on perception of its parts? There is psychological and physiological evidence for parts-based representations in the brain, and certain computational theories of object recognition rely on such representations. But little is known about how brains or computers might learn the parts of objects. Here we demonstrate an algorithm for non-negative matrix factorization that is able to learn parts of faces and semantic features of text. This is in contrast to other methods, such as principal components analysis and vector quantization, that learn holistic, not parts-based, representations. Non-negative matrix factorization is distinguished from the other methods by its use of non-negativity constraints. These constraints lead to a parts-based representation because they allow only additive, not subtractive, combinations. When non-negative matrix factorization is implemented as a neural network, parts-based representations emerge by virtue of two properties: the firing rates of neurons are never negative and synaptic strengths do not change sign.
11,500 citations
"Foetal phonocardiographic signal de..." refers methods in this paper
...Non-negative matrix factorization (NMF) is a multivariate analysis method, which has high potential in pattern recognition and machine learning [19, 20]....
[...]
01 Jan 1999
TL;DR: In this article, non-negative matrix factorization is used to learn parts of faces and semantic features of text, which is in contrast to principal components analysis and vector quantization that learn holistic, not parts-based, representations.
Abstract: Is perception of the whole based on perception of its parts? There is psychological and physiological evidence for parts-based representations in the brain, and certain computational theories of object recognition rely on such representations. But little is known about how brains or computers might learn the parts of objects. Here we demonstrate an algorithm for non-negative matrix factorization that is able to learn parts of faces and semantic features of text. This is in contrast to other methods, such as principal components analysis and vector quantization, that learn holistic, not parts-based, representations. Non-negative matrix factorization is distinguished from the other methods by its use of non-negativity constraints. These constraints lead to a parts-based representation because they allow only additive, not subtractive, combinations. When non-negative matrix factorization is implemented as a neural network, parts-based representations emerge by virtue of two properties: the firing rates of neurons are never negative and synaptic strengths do not change sign.
9,604 citations
Proceedings Article•
01 Jan 2000TL;DR: Two different multiplicative algorithms for non-negative matrix factorization are analyzed and one algorithm can be shown to minimize the conventional least squares error while the other minimizes the generalized Kullback-Leibler divergence.
Abstract: Non-negative matrix factorization (NMF) has previously been shown to be a useful decomposition for multivariate data. Two different multiplicative algorithms for NMF are analyzed. They differ only slightly in the multiplicative factor used in the update rules. One algorithm can be shown to minimize the conventional least squares error while the other minimizes the generalized Kullback-Leibler divergence. The monotonic convergence of both algorithms can be proven using an auxiliary function analogous to that used for proving convergence of the Expectation-Maximization algorithm. The algorithms can also be interpreted as diagonally rescaled gradient descent, where the rescaling factor is optimally chosen to ensure convergence.
7,345 citations
"Foetal phonocardiographic signal de..." refers background in this paper
...These non-negativity constraints allow only additive combination of bases, hence NMF provides parts-based representation of the original dataset [28]....
[...]
TL;DR: It is shown that TIGIT is expressed by all human NK cells, that it binds PVR and PVRL2 but not PVRL3 and that it inhibits NK cytotoxicity directly through its ITIM, providing an “alternative self” mechanism for MHC class I inhibition.
Abstract: NK cell cytotoxicity is controlled by numerous NK inhibitory and activating receptors. Most of the inhibitory receptors bind MHC class I proteins and are expressed in a variegated fashion. It was recently shown that TIGIT, a new protein expressed by T and NK cells binds to PVR and PVR-like receptors and inhibits T cell activity indirectly through the manipulation of DC activity. Here, we show that TIGIT is expressed by all human NK cells, that it binds PVR and PVRL2 but not PVRL3 and that it inhibits NK cytotoxicity directly through its ITIM. Finally, we show that TIGIT counter inhibits the NK-mediated killing of tumor cells and protects normal cells from NK-mediated cytoxicity thus providing an “alternative self” mechanism for MHC class I inhibition.
3,538 citations