The Identiﬁcation and Tracking of Uterine Contractions Using Template
RPA Women and Babies, Royal Prince Alfred Hospital, Missenden Rd, Camperdown, NSW 2050, Australia; and
Engineering, The University of Sydney, Sydney, NSW 2006, Australia
(Received 8 November 2016; accepted 13 June 2017; published online 28 June 2017)
Associate Editor Michael R. Torry oversaw the review of this article.
Abstract—The purpose of this paper is to outline a novel
method of using template based cross-correlation to identify
and track uterine contractions during labour. A purpose built
six-channel Electromyography (EMG) device was used to
collect data from consenting women during labour and birth.
A range of templates were constructed for the purpose of
identifying and tracking uterine activity when cross-corre-
lated with the EMG signal. Peak ﬁnding techniques were
applied on the cross-correlated result to simplify and
automate the identiﬁcation and tracking of contractions.
The EMG data showed a unique pattern when a woman was
contracting with key features of the contraction signal
remaining consistent and identiﬁable across subjects. Con-
traction proﬁles across subjects were automatically identiﬁed
using template based cross-correlation. Synthetic templates
from a rectangular function with a duration of between 5 and
10 s performed best at identifying and tracking uterine
activity across subjects. The successful application of this
technique provides opportunity for both simple and accurate
real-time analysis of contraction data while enabling inves-
tigations into the application of techniques such as machine
learning which could enable automated learning from con-
traction data as part of real-time monitoring and post
Keywords—Electromyography, Parturition, Uterine contrac-
tion, Pregnancy, Uterine monitoring, Intrapartum monitor-
Labour and childbirth are still poorly understood
and subject to a myriad of dubious hypotheses and
unproven theories. While these events are remarkable
they are still in essence biomechanical processes, cap-
able of being quantiﬁed and analyzed given suit-
able tools and methods.
To date frequency of cervix dilatation and con-
traction frequency remain the primary measures of
Measurement of cervix dilatation is done
via vaginal examination while contraction frequency is
often a mix of manually timed durations, palpations of
the abdomen and measured readings using internal and
external monitoring tools.
The uterus is a pear shaped organ located in the
pelvic cavity between the bladder and rectum. This
organ acts as the housing for a fetus during preg-
nancy and is comprised majority of smooth muscle
bundles joined by connective tissue, known as the
To date little is understood surrounding
the exact nature of uterine contractions however
uterine activity has long been seen to increase until a
fetus is delivered
and the frequency of uterine con-
traction is a measure used to assist in determining both
normal activity and progression of labour.
Overall thorough quantiﬁcation and analysis of la-
bour and childbirth have been hindered by a combi-
nation of social and technological factors.
Socially, labour and childbirth are viewed as being
over medicalised for a range of reasons, resulting in a
push to reduce intervention. This includes reserving the
use of electronic fetal monitoring for high risk pregnan-
There is also a strong focus on achieving a natural
birth within supporting literature relied on by women in
preparation of labour.
These socialfactors result in little
support or reason to conduct long term monitoring of the
labour process on otherwise healthy women.
In addition to this, the technology widely used to
monitor labour and childbirth has not provided an
accurate method capable of long term monitoring.
Cardiotocography (CTG) remains a standard for
Address correspondence to Sarah C. McDonald, RPA Women
and Babies, Royal Prince Alfred Hospital, Missenden Rd, Camper-
down, NSW 2050, Australia. Electronic mail: smcd6737@uni.
Annals of Biomedical Engineering, Vol. 45, No. 9, September 2017 (
2017) pp. 2196–2210
2017 Biomedical Engineering Society