Effect of electrode configuration on recognizing uterine contraction with electrohysterogram: Analysis using a convolutional neural network

This paper aimed to evaluate the effect of various electrode configurations on applying a convolutional neural network (CNN) to recognize uterine contraction (UC) with Electrohysterogram (EHG) signals. Seven 8‐electrode configurations and thirteen 4‐electrode configurations were selected from the 4 × 4 electrode grid in the Icelandic 16‐electrode EHG database. EHG signals were divided into UC and non‐UC sections of 45 seconds and saved as images. Each 8‐electrode configuration with 7152 images and 4‐electrode configuration with 3576 images were applied to train CNN to recognize UCs. A scoring method was proposed based on the area under the curve (AUC) and the accuracy to evaluate the effect of electrode configurations on recognizing UCs. The EHG signals from the 4 electrodes on the upper left of the uterus showed the best classification performance (AUC = 0.79, Accuracy = 0.72, Score = 2.30).

[1]  B. Moslem,et al.  Classification of multichannel uterine EMG signals using a reduced number of channels , 2012, 2012 8th International Symposium on Mechatronics and its Applications.

[2]  M. Fejgin,et al.  A comparison of surface acquired uterine electromyography and intrauterine pressure catheter to assess uterine activity. , 2012, American journal of obstetrics and gynecology.

[3]  G. Fele-Zorz,et al.  A comparison of various linear and non-linear signal processing techniques to separate uterine EMG records of term and pre-term delivery groups , 2008, Medical & Biological Engineering & Computing.

[4]  Marta Borowska,et al.  Early diagnosis of threatened premature labor by electrohysterographic recordings – The use of digital signal processing , 2016 .

[5]  Javier Garcia-Casado,et al.  Feasibility and Analysis of Bipolar Concentric Recording of Electrohysterogram with Flexible Active Electrode , 2014, Annals of Biomedical Engineering.

[6]  Brynjar Karlsson,et al.  Better Pregnancy Monitoring Using Nonlinear Correlation Analysis of External Uterine Electromyography , 2013, IEEE Transactions on Biomedical Engineering.

[7]  Charles X. Ling,et al.  AUC: A Better Measure than Accuracy in Comparing Learning Algorithms , 2003, Canadian Conference on AI.

[8]  Charles X. Ling,et al.  Using AUC and accuracy in evaluating learning algorithms , 2005, IEEE Transactions on Knowledge and Data Engineering.

[9]  M. Lucovnik,et al.  Noninvasive uterine electromyography for prediction of preterm delivery. , 2011, American journal of obstetrics and gynecology.

[10]  R. Young,et al.  Myocytes, Myometrium, and Uterine Contractions , 2007, Annals of the New York Academy of Sciences.

[11]  Nigel H. Lovell,et al.  Erratum to “Optimisation of a Generic Ionic Model of Cardiac Myocyte Electrical Activity” , 2013, Comput. Math. Methods Medicine.

[12]  Catherine Marque,et al.  Parameters extraction and monitoring in uterine EMG signals. Detection of preterm deliveries , 2013 .

[13]  G. Prats-Boluda,et al.  Comparison of non-invasive electrohysterographic recording techniques for monitoring uterine dynamics. , 2013, Medical engineering & physics.

[14]  Catherine Marque,et al.  Comparison of Different EHG Feature Selection Methods for the Detection of Preterm Labor , 2013, Comput. Math. Methods Medicine.

[15]  P. Steer,et al.  Physiology and management of normal labour , 1999, BMJ.

[16]  Catherine Marque,et al.  Source localization of uterine activity using maximum entropy on the mean approach , 2018, 2018 IEEE 4th Middle East Conference on Biomedical Engineering (MECBME).

[17]  Yiyao Ye-Lin,et al.  Evaluation of Bipolar, Tripolar, and Quadripolar Laplacian Estimates of Electrocardiogram via Concentric Ring Electrodes , 2019, Sensors.

[18]  Chelsea Dobbins,et al.  Advanced artificial neural network classification for detecting preterm births using EHG records , 2016, Neurocomputing.

[19]  Sung Bum Pan,et al.  A study on user recognition using 2D ECG based on ensemble of deep convolutional neural networks , 2019, Journal of Ambient Intelligence and Humanized Computing.

[20]  Brynjar Karlsson,et al.  The Icelandic 16-electrode electrohysterogram database , 2015, Scientific Data.

[21]  Melvyn Dunstall BSc MSc Pgcea Rm Rgn,et al.  Anatomy and Physiology for Midwives , 2001 .

[22]  Graham Brooker,et al.  The Identification and Tracking of Uterine Contractions Using Template Based Cross-Correlation , 2017, Annals of Biomedical Engineering.

[23]  M. Khalil,et al.  Channel combination selection for EHG bivariate analysis , 2016, 2016 3rd Middle East Conference on Biomedical Engineering (MECBME).

[24]  W. Maner,et al.  Physiology and electrical activity of uterine contractions. , 2007, Seminars in cell & developmental biology.

[25]  G. Prats-Boluda,et al.  Electrohysterography in the diagnosis of preterm birth: a review , 2018, Physiological measurement.

[26]  L. Kinzl,et al.  Length and torsion of the lower limb. , 1997, The Journal of bone and joint surgery. British volume.

[27]  Catherine Marque,et al.  Multichannel EHG segmentation for automatically identifying contractions and motion artifacts , 2017, 2017 Fourth International Conference on Advances in Biomedical Engineering (ICABME).

[28]  Ahmad Diab,et al.  Selection algorithm for parameters to characterize uterine EHG signals for the detection of preterm labor , 2014, Signal Image Video Process..

[29]  I. Verdenik,et al.  Uterine electrical activity as predictor of preterm birth in women with preterm contractions. , 2001, European journal of obstetrics, gynecology, and reproductive biology.

[30]  Yann LeCun,et al.  What is the best multi-stage architecture for object recognition? , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[31]  U. Raghavendra,et al.  Automated identification of shockable and non-shockable life-threatening ventricular arrhythmias using convolutional neural network , 2018, Future Gener. Comput. Syst..

[32]  M. Mischi,et al.  Propagation of electrical activity in uterine muscle during pregnancy: a review , 2015, Acta physiologica.

[33]  W. Lammers,et al.  The Electrical Activities of the Uterus During Pregnancy , 2013, Reproductive Sciences.

[34]  C. Rabotti,et al.  Clinical Use of Electrohysterography During Term Labor: A Systematic Review on Diagnostic Value, Advantages, and Limitations. , 2018, Obstetrical & gynecological survey.

[35]  Massimo Mischi,et al.  Study protocol: PoPE-Prediction of Preterm delivery by Electrohysterography , 2014, BMC Pregnancy and Childbirth.

[36]  Moncef Gabbouj,et al.  Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks , 2016, IEEE Transactions on Biomedical Engineering.

[37]  Ying Liu,et al.  A Comparison of 1-D and 2-D Deep Convolutional Neural Networks in ECG Classification , 2018, Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference.

[38]  S. Steigrad.  Torsion of the Gravid Uterus , 1987, The Australian & New Zealand journal of obstetrics & gynaecology.

[39]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[40]  C Marque,et al.  Uterine electromyography: a critical review. , 1993, American journal of obstetrics and gynecology.

[41]  Yiyao Ye-Lin,et al.  Automatic Identification of Motion Artifacts in EHG Recording for Robust Analysis of Uterine Contractions , 2014, Comput. Math. Methods Medicine.

[42]  William L. Maner,et al.  Identification of Human Term and Preterm Labor using Artificial Neural Networks on Uterine Electromyography Data , 2007, Annals of Biomedical Engineering.

[43]  D. Zheng,et al.  Comparison of electrohysterogram signal measured by surface electrodes with different designs: A computational study with dipole band and abdomen models , 2017, Scientific Reports.