Abstract Until recently, many studies have been achieved for the sake of automatically segmentation of the Electrohysterogram (EHG) in order to identify the efficient uterine contractions but the most of them encountered the presence of other events such as motion artifacts and other kind of contractions despite of the use of efficient filtering methods. In this study, we apply an online method which is developed previously and known by Dynamic Cumulative Sum (DCS) on monopolar EHG signals acquired through a 4x4 electrodes matrix with and without Canonical Correlation Analysis and Empirical Mode Decomposition (CCA-EMD) denoising method, then on monopolar EHG after wavelet decomposition. The detected segments are driven through an automatic concatenation technique of detected event time from all channels in order to reduce the unwanted segments, the obtained segments then undergo to implemented Margin validation test in order to classify among them. Sensitivity of detected contractions and other detected events rate referring to identified contractions by expert have been calculated in order to track the efficiency of the fully automated multichannel segmentation method. Additional EHG filtering techniques like CCA-EMD method seems to be better but effective time cost. Further studies should be achieved in order to decreasing the other events rate for the sake of fully identifying the uterine contractions.

References

[1] Alamedine D., Diab A., Muszynski C., Karlsson B., Khalil M., and Marque C., “Selection Algorithm for Parameters to Characterize Uterine EHG Signals for the Detection of Preterm Labor,” Signal Image Video Process, vol. 8, no. 6, pp. 1169-1178, 2014.

[2] Basseville M. and Benveniste M., “Sequential Segmentation of Non-Stationary Digital Signals using Spectral Analysis,” Information Sciences, vol. 29, no. 1, pp. 57-73, 1983.

[3] Basseville M. and Benveniste M., “Sequential Detection of Abrupt Changes in Spectral Characteristics of Digital Signals,” IEEE Transaction Information Theory, vol. 29, no. 5, pp. 709-724, 1983.

[4] Basseville M. and Nikiforov I., Detection of Abrupt Changes: Theory and Application, Prentice-Hall, 1993.

[5] Brandt A., “Detecting and Estimating Parameters Jumps using Ladder Algorithms and Likelihood Ratio Test,” in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Boston, pp. 1017-1020, 1983.

[6] Diab M., Marque C., and Khalil M., “Une approche de classification des contractions utérines basée sur la théorie des ondelettes et la statistique,” Lebanese Science Journal, vol. 7, no. 1, pp. 91-101, 2006.

[7] Diab A., “Study of The Nonlinear Properties And Propagation Characteristics of The Uterine Electrical Activity During Pregnancy And Labor,” Phd Thesis, University of technology of Compiegne and Reykjavik University, 2014.

[8] Eadie W., Statistical Methods in Experimental Physics, North-Holland, 1971.

[9] Hassan M., Boudaoud S., Terrien J., Karlsson B., and Marque C., “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. 2441-2247, 2011.

[10] Karlsson B., Terrien J., Gudmundsson V., Steingrimsdottir T., and Marque C., “Abdominal EHG on a 4 By 4 Grid: Mapping and Presenting the Propagation of Uterine Contractions,” in Proceedings of the 11th Mediterranean Conference on Medical and Biological Engineering and Computing, Ljubljana, pp.139-143, 2007.

[11] Khalil M. and Duchêne J., “Uterine EMG Analyzing: A Dynamic Approach for Change Detection and Classification,” IEEE Transactions on Biomedical Engineering, vol. 46, no. 6, pp. 748-756, 2000.

[12] Liu L., Oza D., Hogan Y., Chu J., Perin, J., and Zhu J., “Global, Regional, and National Causes of under Mortality in 2000-15: an Updated Systematic Analysis with Implications for the Sustainable Development Goals,” The Lancet, vol. 388, no. 10063, pp. 3027-3035, 2016.

[13] Miles A., Monga M., and Richeson K., “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.

[14] Muszynski C., Happillon T., Azudin K., Tylcz J., Istrate D., and Marque C., “Automated Electrohysterographic Detection of Uterine Contractions for Monitoring of Pregnancy: Feasibility and Prospects,” BMC Pregnancy and Childbirth, vol. 18, no. 1, pp. 136, 2018.

[15] Zaylaa A., Diab A., Khalil M., and Marque C., “Multichannel EHG Segmentation for automatically identifying contractions and motion artifacts,” in Proceedings of 4th International Conference on Advances in Biomedical Engineering, Lebanon, Beirut, pp. 1-4, 2017. Catherine Marque is presently Professor at Compiègne University, Compiègne, France, in the UMR 7338 Biomechanics and Bioengineering (BMBI) lab. After a graduation in mechanical engineering from ENSAM (Paris, France), and a Master degree in Biomedical Engineering from the EcolePolytechnique de Montréal (Canada), she received the Ph.D. degree and the “Habilitation à diriger des recherches” (HDR) from Compiègne University. Her research focuses on biomedical signal processing and modeling. She is interested in the study of uterine contractility, by processing the uterine electrical activity recorded on the mother’s abdomen (electrohysterogram, EHG) in order to detect preterm labor. Since she integrated the BMBI research lab, she has been developing an international team that works on processing and modeling the EHG. Her aim is to understand the links existing between EHG characteristics and the physiological phenomena controlling uterine contraction efficiency (cell excitability, uterine synchronization) for clinical diagnosis purpose. She has recently developed a multi-scale electrical (cell, tissue, organ, abdomen) Automatic Monodimensional EHG Contractions’ Segmentation 615 and multi-physics (electrical, mechanical) model that permits to link EHG characteristics to the uterine muscle behavior (channel dynamics, electrical diffusion, sensitivity to stretching, mechano- transduction), as well as specific processing tools to investigate the EHG connectivity. These recent results permit to evidence that the uterine synchronization is the consequence not only from a simple electrical diffusion process, but also from an electromechanical coupling related to tissue stretching, a new hypothesis recently presented by physiologists. She has been coordinator of many national and international research projects that permitted her to develop various collaborations and to supervise 22 PhD and about 30 Masters thesis. She has taken the responsibility for administrative tasks, related either to teaching (engineer, Master, Doctoral education) or to research management (research unit, Regional research group…). Mohamad Khalil is currently professor, teacher and researcher at Lebanese University, faculty of engineering. He received the DEA in biomedical engineering from the University of Technology of Compiegne (UTC) in France in 1996. He received his Ph.D from the University of Technology of Troyes in France in 1999. He received his HDR (Habilitation adiriger des recherches) from UTC in 2006... He is the chair of the EMBS chapter in Lebanon, chair of ICABME international Conference. His current interests are the signal and image processing problems: detection, classification, analysis, representation and modeling of non stationary signals, with application to biomedical signals and images. Ahmad Diab received the degree in Biomedical Engineering from the Islamic University of Lebanon, Khaldeh, Lebanon, in 2010. And the M.Sc. degree in Medical and Industrial Processing and System from the Lebanese University, Tripoli, Lebanon, in 2011. Also he received his Ph.D. degree from the University of Technology of Compiègne, Compiègne, France and Reykjavik University, Reykjavik, Iceland in 2014. He was a Research Engineer at Azm center for research in biotechnology and its application, Lebanese University between 2014 and 2017. He is currently an Assistant Professor at the Lebanese University and many private universities. His current research interests include signal processing problems: characterization, classification, nonlinear analysis, source localization, with application to biomedical signals. Amer Zaylaa received the degree in Biomedical Engineering from the Islamic University of Lebanon, Khaldeh, Lebanon, in 2008, the Master of research degree in Medical and Industrial Processing and System from the Lebanese University, Tripoli, Lebanon, in 2015. He is currently a PhD candidate in final year at University of Technology of Compiègne, section: Biomechanics and Bioengineering. He is currently the chair of biomedical engineering department at koura hospital since January 2009.