Electrohysterography (EHG) is a noninvasive technique for monitoring uterine electrical activity. However, the presence of artifacts in the EHG signal may give rise to erroneous interpretations and make it difficult to extract useful information from these recordings. The aim of this work was to develop an automatic system of segmenting EHG recordings that distinguishes between uterine contractions and artifacts. Firstly, the segmentation is performed using an algorithm that generates the TOCO-like signal derived from the EHG and detects windows with significant changes in amplitude. After that, these segments are classified in two groups: artifacted and nonartifacted signals. To develop a classifier, a total of eleven spectral, temporal, and nonlinear features were calculated from EHG signal windows from 12 women in the first stage of labor that had previously been classified by experts. The combination of characteristics that led to the highest degree of accuracy in detecting artifacts was then determined. The results showed that it is possible to obtain automatic detection of motion artifacts in segmented EHG recordings with a precision of 92.2% using only seven features. The proposed algorithm and classifier together compose a useful tool for analyzing EHG signals and would help to promote clinical applications of this technique. 1. Introduction Monitoring uterine contractions is commonly used to estimate the time of an approaching labour. In spite of the fact that intrauterine pressure (IUP) is regarded as the gold standard in monitoring these contractions, its use in clinical practice is limited since it requires rupturing the membranes to place a catheter inside the uterus. This not only leads to delivery but may also increase the risk of intrapartum infection [1]. Hospitals often use a pressure transducer (TOCOdynamometer or TOCO) placed on the mother’s abdomen for basic noninvasive monitoring of uterine activity, thus obtaining the frequency and duration of contractions. However, the TOCO is not a reliable technique, as the measurements obtained are by no means precise and depend to a large extent on the subjective criteria of the operator [2–4]. Neither do they provide much additional information on the efficiency of contractions in order to decide whether parturition is near. However, in spite of these disadvantages, the technique is widely used in maternity clinics due to its non-invasive nature. The electrohysterogram (EHG) is the recording of uterine electrical activity from the abdominal surface. Earlier studies have shown that the EHG
References
[1]
F. A. Wilmink, F. F. Wilms, R. Heydanus, B. W. J. Mol, and D. N. M. Papatsonis, “Fetal complications after placement of an intrauterine pressure catheter: a report of two cases and review of the literature,” Journal of Maternal-Fetal and Neonatal Medicine, vol. 21, no. 12, pp. 880–883, 2008.
[2]
M. P. Vinken, C. Rabotti, M. Mischi, and S. G. Oei, “Accuracy of frequency-related parameters of the electrohysterogram for predicting preterm delivery: a review of the literature,” Obstetrical and Gynecological Survey, vol. 64, no. 8, pp. 529–541, 2009.
[3]
D. Schlembach, W. L. Maner, R. E. Garfield, and H. Maul, “Monitoring the progress of pregnancy and labor using electromyography,” European Journal of Obstetrics Gynecology and Reproductive Biology, vol. 144, supplement 1, pp. S33–S39, 2009.
[4]
A. M. Miles, M. Monga, and K. S. Richeson, “Correlation of external and internal monitoring of uterine activity in a cohort of term patients,” American Journal of Perinatology, vol. 18, no. 3, pp. 137–140, 2001.
[5]
D. Devedeux, C. Marque, S. Mansour, G. Germain, and J. Duchene, “Uterine electromyography: a critical review,” American Journal of Obstetrics and Gynecology, vol. 169, no. 6, pp. 1636–1653, 1993.
[6]
R. E. Garfield and W. L. Maner, “Physiology and electrical activity of uterine contractions,” Seminars in Cell and Developmental Biology, vol. 18, no. 3, pp. 289–295, 2007.
[7]
C. K. Marque, J. Terrien, S. Rihana, and G. Germain, “Preterm labour detection by use of a biophysical marker: the uterine electrical activity,” BMC Pregnancy and Childbirth, vol. 7, supplement 1, article S5, 2007.
[8]
M. Lucovnik, W. L. Maner, L. R. Chambliss et al., “Noninvasive uterine electromyography for prediction of preterm delivery,” American Journal of Obstetrics and Gynecology, vol. 204, no. 3, pp. 228.e1–228.e10, 2011.
[9]
T. Y. Euliano, D. Marossero, M. T. Nguyen, N. R. Euliano, J. Principe, and R. K. Edwards, “Spatiotemporal electrohysterography patterns in normal and arrested labor,” American Journal of Obstetrics and Gynecology, vol. 200, no. 1, pp. 54–57, 2009.
[10]
C. Rabotti, M. Mischi, J. O. E. H. van Laar, G. S. Oei, and J. W. M. Bergmans, “Inter-electrode delay estimators for electrohysterographic propagation analysis,” Physiological Measurement, vol. 30, no. 8, pp. 745–761, 2009.
[11]
C. Rabotti and M. Mischi, “Two-dimensional estimation of the electrohysterographic conduction velocity,” in Proceedings of the 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC '10), pp. 4262–4265, September 2010.
[12]
J. Jezewski, K. Horoba, A. Matonia, and J. Wrobel, “Quantitative analysis of contraction patterns in electrical activity signal of pregnant uterus as an alternative to mechanical approach,” Physiological Measurement, vol. 26, no. 5, pp. 753–767, 2005.
[13]
T. Euliano, M. Skowronski, D. Marossero, J. Shuster, and R. Edwards, “Prediction of intrauterine pressure waveform from transabdominal electrohysterography,” Journal of Maternal-Fetal and Neonatal Medicine, vol. 19, no. 12, pp. 803–808, 2006.
[14]
T. Y. Euliano, M. T. Nguyen, D. Marossero, and R. K. Edwards, “Monitoring contractions in obese parturients: electrohysterography compared with traditional monitoring,” Obstetrics and Gynecology, vol. 109, no. 5, pp. 1136–1140, 2007.
[15]
C. Rabotti, M. Mischi, J. O. E. H. van Laar, G. S. Oei, and J. W. M. Bergmans, “Estimation of internal uterine pressure by joint amplitude and frequency analysis of electrohysterographic signals,” Physiological Measurement, vol. 29, no. 7, pp. 829–841, 2008.
[16]
T. Y. Euliano, M. T. Nguyen, S. Darmanjian et al., “Monitoring uterine activity during labor: a comparison of 3 methods,” American Journal of Obstetrics and Gynecology, vol. 208, pp. 66.e1–66.e6, 2013.
[17]
M. Hassan, S. Boudaoud, J. Terrien, B. Karlsson, and C. Marque, “Combination of canonical correlation analysis and empirical mode decomposition applied to denoising the labor electrohysterogram,” IEEE Transactions on Biomedical Engineering, vol. 58, no. 9, pp. 2441–2447, 2011.
[18]
J. Liang, J. Y. Cheung, and J. D. Z. Chen, “Detection and deletion of motion artifacts in electrogastrogram using feature analysis and neural networks,” Annals of Biomedical Engineering, vol. 25, no. 5, pp. 850–857, 1997.
[19]
M. A. M. T. Verhagen, L. J. van Schelven, M. Samsom, and A. J. P. M. Smout, “Pitfalls in the analysis of electrogastrographic recordings,” Gastroenterology, vol. 117, no. 2, pp. 453–460, 1999.
[20]
S. Conforto, T. D'Alessio, and S. Pignatelli, “Optimal rejection of movement artefacts from myoelectric signals by means of a wavelet filtering procedure,” Journal of Electromyography and Kinesiology, vol. 9, no. 1, pp. 47–57, 1999.
[21]
H. Liang, Z. Lin, and R. W. McCallum, “Artifact reduction in electrogastrogram based on empirical mode decomposition method,” Medical and Biological Engineering and Computing, vol. 38, no. 1, pp. 35–41, 2000.
[22]
W. L. Maner and R. E. Garfield, “Identification of human term and preterm labor using artificial neural networks on uterine electromyography data,” Annals of Biomedical Engineering, vol. 35, no. 3, pp. 465–473, 2007.
[23]
B. Moslem, M. Khalil, C. Marque, and M. O. Diab, “Energy distribution analysis of uterine electromyography signals,” Journal of Medical and Biological Engineering, vol. 30, no. 6, pp. 361–366, 2010.
[24]
M. Hassan, J. Terrien, C. Muszynski, A. Alexandersson, C. Marque, and B. Karlsson, “Better pregnancy monitoring using nonlinear correlation analysis of external uterine electromyography,” IEEE Transactions on Biomedical Engineering, vol. 60, pp. 1160–1166, 2013.
[25]
H. Léman, C. Marque, and J. Gondry, “Use of the electrohysterogram signal for characterization of contractions during pregnancy,” IEEE Transactions on Biomedical Engineering, vol. 46, no. 10, pp. 1222–1229, 1999.
[26]
H. Maul, W. L. Maner, G. Olson, G. R. Saade, and R. E. Garfield, “Non-invasive transabdominal uterine electromyography correlates with the strength of intrauterine pressure and is predictive of labor and delivery,” Journal of Maternal-Fetal and Neonatal Medicine, vol. 15, no. 5, pp. 297–301, 2004.
[27]
J. Terrien, T. Steingrimsdottir, C. Marque, and B. Karlsson, “Synchronization between EMG at different uterine locations investigated using time-frequency ridge reconstruction: comparison of pregnancy and labor contractions,” Eurasip Journal on Advances in Signal Processing, vol. 2010, Article ID 242493, 10 pages, 2010.
[28]
M. Lucovnik, R. J. Kuon, L. R. Chambliss et al., “Use of uterine electromyography to diagnose term and preterm labor,” Acta Obstetricia et Gynecologica Scandinavica, vol. 90, no. 2, pp. 150–157, 2011.
[29]
I. Verdenik, M. Pajntar, and B. Lesko？ek, “Uterine electrical activity as predictor of preterm birth in women with preterm contractions,” European Journal of Obstetrics Gynecology and Reproductive Biology, vol. 95, no. 2, pp. 149–153, 2001.
[30]
G. Fele-？or？, G. Kav？ek, ？. Novak-Antoli？, and F. Jager, “A comparison of various linear and non-linear signal processing techniques to separate uterine EMG records of term and pre-term delivery groups,” Medical and Biological Engineering and Computing, vol. 46, no. 9, pp. 911–922, 2008.
[31]
D. Zhu, J. Tong, and Y. Chen, “An ICA-based method for automatic eye blink artifact correction in multi-channel EEG,” in Proceedings of the 5th International Conference on Information Technology and Application in Biomedicine, in Conjunction with the 2nd International Symposium & Summer School on Biomedical and Health Engineering, pp. 338–341, May 2008.
[32]
M. Hassan, J. Terrien, C. Marque, and B. Karlsson, “Comparison between approximate entropy, correntropy and time reversibility: application to uterine electromyogram signals,” Medical Engineering and Physics, vol. 33, no. 8, pp. 980–986, 2011.
[33]
I. Guyon and A. Elisseeff, “An introduction to variable variable and feature selection,” Journal of Machine Learning Research, vol. 46, pp. 1157–1182, 2003.
[34]
A. Irimia and L. A. Bradshaw, “Artifact reduction in magnetogastrography using fast independent component analysis,” Physiological Measurement, vol. 26, no. 6, pp. 1059–1073, 2005.
[35]
M. Milanesi, N. Martini, N. Vanello, V. Positano, M. F. Santarelli, and L. Landini, “Independent component analysis applied to the removal of motion artifacts from electrocardiographic signals,” Medical and Biological Engineering and Computing, vol. 46, no. 3, pp. 251–261, 2008.
[36]
I. Daly, M. Billinger, R. Scherer, and G. Muller-Putz, “On the automated removal of artifacts related to head movement from the EEG,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 21, pp. 427–434, 2013.
[37]
Y. Ye-Lin, J. Garcia-Casado, G. Prats-Boluda, and J. L. Martinez-De-Juan, “Combined method for reduction of high frequency interferences in surface electroenterogram (EEnG),” Annals of Biomedical Engineering, vol. 38, no. 7, pp. 2358–2370, 2010.
[38]
T. Schreiber and A. Schmitz, “Surrogate time series,” Physica D, vol. 142, no. 3-4, pp. 346–382, 2000.
[39]
T. van Gestel, J. A. K. Suykens, B. Baesens et al., “Benchmarking least squares support vector machine classifiers,” Machine Learning, vol. 54, no. 1, pp. 5–32, 2004.
[40]
C. Rabotti, Characterization of Uterine Activity by Electrohysterography, Eindhoven University of Technology, Eindhoven, The Netherlands, 2010.
[41]
H. Leman and C. Marque, “Rejection of the maternal electrocardiogram in the electrohysterogram signal,” IEEE Transactions on Biomedical Engineering, vol. 47, no. 8, pp. 1010–1017, 2000.
[42]
C. Marque, C. Bisch, R. Dantas, S. Elayoubi, V. Brosse, and C. Pérot, “Adaptive filtering for ECG rejection from surface EMG recordings,” Journal of Electromyography and Kinesiology, vol. 15, no. 3, pp. 310–315, 2005.
[43]
A. Matonia, J. Jezewski, K. Horoba, A. Gacek, and P. Labaj, “The maternal ECG suppression algorithm for efficient extraction of the fetal ECG from abdominal signal,” in Proceedings of the 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS '06), vol. 1–15, pp. 296–299, September 2006.
