Fetal cardiotocography monitoring using Legendre neural networks
-
Abdulaziz Alsayyari
Abstract
A new technique for electronic fetal monitoring (EFM) using an efficient structure of neural networks based on the Legendre series is presented in this paper. Such a structure is achieved by training a Legendre series-based neural network (LNN) to classify the different fetal states based on recorded cardiotocographic (CTG) data sets given by others. These data sets consist of measurements of fetal heart rate (FHR) and uterine contraction (UC). The applied LNN utilizes a Legendre series expansion for the input vectors and, hence, has the capability to produce explicit equations describing multi-input multi-output systems. Simulations of the proposed technique in EFM demonstrate its high efficiency. Training the LNN requires a few number of iterations (5–10 epochs). The applied technique makes the classification of the fetal state available through equations combining the trained LNN weights and the current measured CTG record. A comparison of performance between the proposed LNN and other popular neural network techniques such as the Volterra neural network (VNN) in EFM is provided. The comparison shows that, the LNN outperforms the VNN in case of less computational requirements and fast convergence with a lower mean square error.
Author Statement
Research funding: The author states no funding involved.
Conflict of interest: The author states no conflict of interest.
Informed consent: Informed consent is not applicable.
Ethical approval: The conducted research is not related to either human or animal use.
References
[1] Ayres-de-Campos D, Spong CY, Chandraharan E, Panel FIFMEC. FIGO consensus on intrapartum fetal monitoring: cardiotocography. Int J Gynaecol Obstet 2015;131:13–24.10.1016/j.ijgo.2015.06.020Suche in Google Scholar PubMed
[2] Chudáček V, Spilka J, Huptych M, Georgoulas G, Lhotská L, Stylios C, et al. Linear and non-linear features for intrapartum cardiotocography evaluation. Comput Cardiol 2010;999–1002.Suche in Google Scholar
[3] Oliveira Fernandes JN, Cortez PC, Lobo Marques JA, Lucena Feitosa FE. A fuzzy intelligent agent for analysis and classification of fetuses cardiac signals. IEEE Latin Am Trans 2016;14:2052–8.10.1109/TLA.2016.7530394Suche in Google Scholar
[4] Chudáček V, Andén J, Mallat S, Abry P, Doret M. Scattering transform for intrapartum fetal heart rate variability fractal analysis: a case-control study. IEEE Trans Biomed Eng 2014;61:1100–8.10.1109/TBME.2013.2294324Suche in Google Scholar PubMed
[5] Pinas A, Chandraharan E. Continuous cardiotocography during labor: analysis, classification and management. Best Pract Res Clin Obstet Gynaecol 2016;30:33–47.10.1016/j.bpobgyn.2015.03.022Suche in Google Scholar PubMed
[6] Czabanski R, Jezewski M, Wrobel J, Horoba K, Jezewski J. A Neuro-fuzzy approach to the classification of fetal cardiotocograms. In: Katashev A, Dekhtyar Y, Spigulis J, editors. 14th Nordic Baltic Conference on Biomedical Engineering and Medical Physics. IFMBE Proceedings, vol. 20. Berlin, Heidelberg: Springer 2008:446–9.10.1007/978-3-540-69367-3_120Suche in Google Scholar
[7] Bonow RO, Carabello BA, Chatterjee K, De Leon Jr AC, Faxon DP. ACC/AHA 2006 guidelines for the management of patients with valvular heart disease. Circulation 2006;114:84–231.10.1161/CIRCULATIONAHA.106.176857Suche in Google Scholar PubMed
[8] MacOnes GA, Hankins GD, Spong CY, Hauth J, Moore T. The 2008 National Institute of Child Health and Human Development workshop report on electronic fetal monitoring. Obstet Gynecol 2008;112:661–6.10.1097/AOG.0b013e3181841395Suche in Google Scholar PubMed
[9] Gonçalves H, Rocha AP, Ayres-de-Campos D, Bernardes J. Linear and nonlinear fetal heart rate analysis of normal and acidemic fetuses in the minutes preceding delivery. Med Biol Eng Comput 2006;44:847–55.10.1007/s11517-006-0105-6Suche in Google Scholar PubMed
[10] Alfirevic Z, Devane D, Gyte GM. Continuous cardiotocography (CTG) as a form of electronic fetal monitoring (EFM) for fetal assessment during labour. Cochrane Database Syst Rev 2013.10.1002/14651858.CD006066.pub2Suche in Google Scholar PubMed
[11] Da Poian G, Bernardini R, Rinaldo R. Separation and analysis of fetal ECG signals from compressed sensed abdominal ECG Recordings. IEEE Trans Biomed Eng 2016;63:1269–79.10.1109/TBME.2015.2493726Suche in Google Scholar PubMed
[12] Yu L, Guo Y, Wang Y, Yu J, Chen P. Segmentation of fetal left ventricle in echocardiographic sequences based on dynamic convolutional neural networks. IEEE Trans Biomed Eng 2017;64:1886–95.10.1109/TBME.2016.2628401Suche in Google Scholar PubMed
[13] Devyatykh DV, Gerget OM. Extraction of the fetal electrocardiogram using dynamic neural networks. Biomed Eng 2017;50:371–5.10.1007/s10527-017-9658-ySuche in Google Scholar
[14] Yılmaz E. Fetal state assessment from cardiotocogram data using artificial neural networks. J Med Biol Eng 2016;36:820–32.10.1007/s40846-016-0191-3Suche in Google Scholar
[15] Pao YH. Adaptive pattern recognition and neural networks. Reading, MA: Addison-Wesley; 1989.Suche in Google Scholar
[16] Ali HH, Haweel MT. Legendre neural networks with multi input multi output system equations. In: IEEE International Conference on Computer Engineering and Systems (ICCES), Egypt 2012;92–7.10.1109/ICCES.2012.6408490Suche in Google Scholar
[17] Ali HH, Haweel MT. Legendre based equalization for nonlinear wireless communication channels. In: The Second Saudi International Electronics, Communications and Photonics Conference (SIECPC), Riyadh, KSA 2013:1–4.10.1109/SIECPC.2013.6550776Suche in Google Scholar
[18] Mansor W, Crowe JA, Woolfson M, Hayes-Gill BR, Blanchfield P, Bister M. Simulation of the generation and processing of Doppler ultrasound fetal heart signals to obtain directional motion information. In: 2006 International Conference of the IEEE Engineering in Medicine and Biology Society 2006;1383–86.10.1109/IEMBS.2006.260428Suche in Google Scholar PubMed
[19] Zhou X, Xiong X. An improved auto-correlation algorithm and its application in fetal heart rate detection. In: 2nd International Conference on Biomedical Engineering and Informatics 2009:1–5.10.1109/BMEI.2009.5304972Suche in Google Scholar
[20] Cömert Z, Kocamaz AF. Using wavelet transform for cardiotocography signals classification. In: 25th Signal Processing and Communications Applications Conference (SIU) 2017:1–4.10.1109/SIU.2017.7960152Suche in Google Scholar
[21] Banerjee S, Mitra M. Application of cross wavelet transform for ECG pattern analysis and classification. IEEE Trans Instrument Measur 2014;63:326–33.10.1109/TIM.2013.2279001Suche in Google Scholar
[22] Lima-Herrera SL, Alvarado-Serrano C. Fetal ECG extraction based on adaptive filters and Wavelet Transforms. In: 13th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE) 2016;1–6.Suche in Google Scholar
[23] Cömert Z, Kocamaz AF. A comparison of machine learning techniques for fetal heart rate classification. In: 3rd International Conference on Computational and Experimental Science and Engineering (ICCESEN-2016), Antalya, Turkey 2016.10.12693/APhysPolA.132.451Suche in Google Scholar
[24] Martinek R, Skutova H, Kahankova R, Koudelka P, Bilik P, Koziorek J. Fetal ECG extraction based on adaptive neuro-fuzzy ECG interface system. In: 10th International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP) 2016:1–6.10.1109/CSNDSP.2016.7573973Suche in Google Scholar
[25] Kumar P, Sharma SK, Prasad S. Detection of fetal electrocardiogram through OFDM, neuro-fuzzy logic and wavelets systems for telemetry. In: 10th International Conference on Intelligent Systems and Control (ISCO) 2016;1–4.10.1109/ISCO.2016.7726970Suche in Google Scholar
[26] Bae M, Park SB and Kwon SJ. Fast minimum variance beamforming based on Legendre polynomials. IEEE Trans Ultrason Ferroelectr Freq Control 2016;63:1422–31.10.1109/TUFFC.2016.2591623Suche in Google Scholar PubMed
[27] Haweel TI, Bangash JI. Volterra neural analysis of fetal cardiotocographic signals. In: 1st International Conference on Communications, Signal Processing, and their Applications (ICCSPA) 2013:1–5.10.1109/ICCSPA.2013.6487321Suche in Google Scholar
[28] Ficko BW, Liebl M, Knopke C, Phan MQ, Steinhoff U, Wiekhorst F, et al. Nonlinear spectroscopic characterization and Volterra series inspired modeling of magnetic nanoparticles. IEEE Trans Magnet 2017;53:5000112.10.1109/TMAG.2016.2628341Suche in Google Scholar
[29] Despotovic V, Goertz N, Peric Z. Nonlinear long-term prediction of speech based on truncated Volterra series. IEEE Trans Audio Speech Lang Process 2012;20:1069–73.10.1109/TASL.2011.2169788Suche in Google Scholar
[30] Frank A, Asuncion A. UCI Machine Repository 2010. Available at: http://archive.ics.uci.edu/ml.Suche in Google Scholar
©2019 Walter de Gruyter GmbH, Berlin/Boston
Artikel in diesem Heft
- Frontmatter
- Review
- Regression analysis for detecting epileptic seizure with different feature extracting strategies
- Research articles
- Assessment of CSP-based two-stage channel selection approach and local transformation-based feature extraction for classification of motor imagery/movement EEG data
- A step forward in the quest for a mobile EEG-designed epoch for psychophysiological studies
- Fetal cardiotocography monitoring using Legendre neural networks
- Wireless power transmission in endoscopy capsules
- Iris recognition under the influence of diabetes
- Sonographic visibility of cannulas using convex ultrasound transducers
- A wavelet-based method for MRI liver image denoising
- Mathematical morphology-based imaging of gastrointestinal cancer cell motility and 5-aminolevulinic acid-induced fluorescence
- Comparison of bone biomechanical properties after bone marrow mesenchymal stem cell or alendronate treatment in an osteoporotic animal model
- ESLMT: a new clustering method for biomedical document retrieval
Artikel in diesem Heft
- Frontmatter
- Review
- Regression analysis for detecting epileptic seizure with different feature extracting strategies
- Research articles
- Assessment of CSP-based two-stage channel selection approach and local transformation-based feature extraction for classification of motor imagery/movement EEG data
- A step forward in the quest for a mobile EEG-designed epoch for psychophysiological studies
- Fetal cardiotocography monitoring using Legendre neural networks
- Wireless power transmission in endoscopy capsules
- Iris recognition under the influence of diabetes
- Sonographic visibility of cannulas using convex ultrasound transducers
- A wavelet-based method for MRI liver image denoising
- Mathematical morphology-based imaging of gastrointestinal cancer cell motility and 5-aminolevulinic acid-induced fluorescence
- Comparison of bone biomechanical properties after bone marrow mesenchymal stem cell or alendronate treatment in an osteoporotic animal model
- ESLMT: a new clustering method for biomedical document retrieval
