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

Dongmei Hao; Xiaoxiao Song; Qian Qiu; Xin Xin; Lin Yang; Xiaohong Liu; Hongqing Jiang; Dingchang Zheng

doi:10.1002/ima.22505

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

Dongmei Hao, Xiaoxiao Song, Qian Qiu, Xin Xin, Lin Yang, Xiaohong Liu, Hongqing Jiang, Dingchang Zheng

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

441 Downloads (Pure)

Abstract

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).

Original language	English
Pages (from-to)	972-980
Number of pages	9
Journal	International Journal of Imaging Systems and Technology
Volume	31
Issue number	2
Early online date	27 Oct 2020
DOIs	https://doi.org/10.1002/ima.22505
Publication status	Published - Jun 2021

Bibliographical note

This is the peer reviewed version of the following article: Hao, D, Song, X, Qiu, Q, Xin, X, Yang, L, Liu, X, Jiang, H & Zheng, D 2021, 'Effect of electrode configuration on recognizing uterine contraction with electrohysterogram: Analysis using a convolutional neural network', International Journal of Imaging Systems and Technology, vol. 31, no. 2, pp. 972-980, which has been published in final form at https://doi.org/10.1002/ima.22505. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Self-Archiving.

Funder

National Key R&D Program of China (2019YFC0119700), Bill & Melinda Gates Foundation (OPP1148910), Beijing Natural Science Foundation (7172015), Beijing Science and Technology Project (Z161100000116005).

Funding

Beijing Science and Technology Project, Grant/Award Number: Z161100000116005; Bill and Melinda Gates Foundation, Grant/Award Number: OPP1148910; National Key R&D Program of China, Grant/Award Number: 2019YFC0119700; Natural Science Foundation of Beijing Municipality, Grant/Award Number: 7172015 Funding information This research was funded by National Key R&D Program of China (2019YFC0119700), Bill & Melinda Gates Foundation (OPP1148910), Beijing Natural Science Foundation (7172015), Beijing Science and Technology Project (Z161100000116005).

Funders	Funder number
Bill and Melinda Gates Foundation	OPP1148910
Natural Science Foundation of Beijing Municipality	7172015
National Key Research and Development Program of China	2019YFC0119700
Beijing Science and Technology Planning Project	Z161100000116005

Keywords

convolutional neural network
electrode configuration
electrohysterogram
uterine contraction

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Software
Computer Vision and Pattern Recognition
Electrical and Electronic Engineering

Access to Document

10.1002/ima.22505

Post-PrintAccepted author manuscript, 1.39 MB

Cite this

@article{a7b47320cdbc45f39c298a0deca4113b,

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

abstract = "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).",

keywords = "convolutional neural network, electrode configuration, electrohysterogram, uterine contraction",

author = "Dongmei Hao and Xiaoxiao Song and Qian Qiu and Xin Xin and Lin Yang and Xiaohong Liu and Hongqing Jiang and Dingchang Zheng",

note = "This is the peer reviewed version of the following article: Hao, D, Song, X, Qiu, Q, Xin, X, Yang, L, Liu, X, Jiang, H & Zheng, D 2021, 'Effect of electrode configuration on recognizing uterine contraction with electrohysterogram: Analysis using a convolutional neural network', International Journal of Imaging Systems and Technology, vol. 31, no. 2, pp. 972-980, which has been published in final form at https://doi.org/10.1002/ima.22505. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Self-Archiving.",

year = "2021",

month = jun,

doi = "10.1002/ima.22505",

language = "English",

volume = "31",

pages = "972--980",

journal = "International Journal of Imaging Systems and Technology",

issn = "0899-9457",

publisher = "Wiley",

number = "2",

}

TY - JOUR

T1 - Effect of electrode configuration on recognizing uterine contraction with electrohysterogram

T2 - Analysis using a convolutional neural network

AU - Hao, Dongmei

AU - Song, Xiaoxiao

AU - Qiu, Qian

AU - Xin, Xin

AU - Yang, Lin

AU - Liu, Xiaohong

AU - Jiang, Hongqing

AU - Zheng, Dingchang

N1 - This is the peer reviewed version of the following article: Hao, D, Song, X, Qiu, Q, Xin, X, Yang, L, Liu, X, Jiang, H & Zheng, D 2021, 'Effect of electrode configuration on recognizing uterine contraction with electrohysterogram: Analysis using a convolutional neural network', International Journal of Imaging Systems and Technology, vol. 31, no. 2, pp. 972-980, which has been published in final form at https://doi.org/10.1002/ima.22505. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Self-Archiving.

PY - 2021/6

Y1 - 2021/6

N2 - 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).

AB - 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).

KW - convolutional neural network

KW - electrode configuration

KW - electrohysterogram

KW - uterine contraction

UR - http://www.scopus.com/inward/record.url?scp=85093943993&partnerID=8YFLogxK

U2 - 10.1002/ima.22505

DO - 10.1002/ima.22505

M3 - Article

AN - SCOPUS:85093943993

SN - 0899-9457

VL - 31

SP - 972

EP - 980

JO - International Journal of Imaging Systems and Technology

JF - International Journal of Imaging Systems and Technology

IS - 2

ER -

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

Abstract

Bibliographical note

Funder

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this