IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, VOL. 60, NO.

5, MAY 2013 1345

Fetal ECG Extraction by Extended State Kalman
Filtering Based on Single-Channel Recordings
Mohammad Niknazar

, Bertrand Rivet, and Christian Jutten, Fellow, IEEE

AbstractIn this paper, we present an extended nonlinear
Bayesian ltering framework for extracting electrocardiograms
(ECGs) from a single channel as encountered in the fetal ECG
extraction from abdominal sensor. The recorded signals are mod-
eled as the summation of several ECGs. Each of them is described
by a nonlinear dynamic model, previously presented for the gen-
eration of a highly realistic synthetic ECG. Consequently, each
ECG has a corresponding term in this model and can thus be
efciently discriminated even if the waves overlap in time. The
parameter sensitivity analysis for different values of noise level,
amplitude, and heart rate ratios between fetal and maternal ECGs
shows its effectiveness for a large set of values of these parame-
ters. This framework is also validated on the extractions of fetal
ECG from actual abdominal recordings, as well as of actual twin
magnetocardiograms.
Index TermsExtended Kalman ltering (EKF), fetal electro-
cardiogram (fECG) extraction, model-based ltering, nonlinear
Bayesian ltering, twin magnetocardiogram (MCG) extraction.
I. INTRODUCTION
S
INCE the rst demonstration of the fetal electrocardiogram
(fECG) carried out in 1906 by Cremer [1], various methods
for fECG monitoring have been proposed to obtain information
about the heart status. The fECG can be measured by placing
electrodes on the mothers abdomen. However, it has very low
power and is mixed with several sources of noise and inter-
ference. Nevertheless, the main contamination is the maternal
electrocardiogram (mECG) [2]. As a result, the basic problem
is to extract the fECG signal from the mixture of mECG and
fECG signals, where the interfering mECG is a much stronger
signal. According to the review [3], existing fECG extraction
approaches in the literature can be categorized by their method-
ologies, which include linear or nonlinear decomposition and
adaptive ltering.
Linear or nonlinear decomposition methods are common
approaches, in which single- or multichannel recordings are
Manuscript received February 20, 2012; revised May 7, 2012, October 1,
2012, and November 27, 2012; accepted November 29, 2012. Date of publication
December 20, 2012; date of current version April 15, 2013. Asterisk indicates
corresponding author.

M. Niknazar is with the GIPSA-lab (UMR CNRS 5216), University of

Grenoble, Grenoble 38402, France (e-mail: mohammad.niknazar@gipsa-lab.
grenoble-inp.fr).
B. Rivet is with the GIPSA-lab (UMR CNRS 5216), University of Grenoble,
Grenoble 38402, France (e-mail: [email protected]).
C. Jutten is with the GIPSA-lab (UMR CNRS 5216), University of Grenoble,
Grenoble 38402, France, and also with the Institut Universitaire de France,
75005 Paris, France (e-mail: [email protected]).
Color versions of one or more of the gures in this paper are available online
at http://ieeexplore.ieee.org.
Digital Object Identier 10.1109/TBME.2012.2234456
decomposed into different components using suitable basis
functions. Linear decomposition methods use either xed ba-
sis functions (e.g., wavelets [4]), or data-driven basis functions
(e.g., singular vectors [5]). This limits performance of decompo-
sition in nonlinear or degenerate mixtures of signal and noise [3].
Blind or semiblind source separation, which are categorized as
linear decomposition approach, have also been used for fECG
extraction [6], [7]. These methods are based on the assumption
of independent components (or more generally independent sub-
spaces [8] or partitions [9]) for the maternal and fetal signals,
or of the existence of some temporal structure for the desired
signals [10][12]. In [13] and [14], wavelet decomposition was
also combined with blind source separation for extracting and
denoising fECGsignals. In another recent work, a newtechnique
was proposed to fasten the traditional independent component
analysis (ICA) method [15]. In blind source separation meth-
ods, it is usually assumed that signals and noises are mixed in
a stationary and linear manner. However, fECG and other inter-
ferences and noises are not always stationary mixed and linearly
separable [16].
Nonlinear transforms have been also used for mECG can-
celation and fECG extraction. In these methods, constructed
phase space of noisy signal and of its delayed versions is
smoothed using conventional or principal component analysis
(PCA) smoothers [17]. The samples are then transferred back
to the time-domain representation. Although these methods are
interesting since they are applicable to as few as one single
maternal abdominal channel, the selection of the required time
lags for constructing phase space representation is empirical and
the important interbeat variations of the cardiac signals can be
wiped-out during the state-space smoothing. Moreover, they de-
mand higher computational complexity in comparison to linear
methods, and the correct embedding dimension can change as
the noise statistics change [3].
Adaptive ltering is another common approach for mECG
cancelation and fECG extraction [18]. The conventional adap-
tive ltering is based on training an adaptive lter for either
removing the mECG using one or several maternal reference
channels [18], [19], or directly training the lter for extract-
ing the fetal QRS waves [20], [21]. However, existing adaptive
ltering methods for mECG artifact removal either require a
reference mECG channel that is morphologically similar to the
contaminating waveformor require several linearly independent
channels to roughly reconstruct any morphologic shape fromthe
references [18]. Both of these approaches are practically incon-
venient and with limiting performance, because the morphology
of the mECG contaminants highly depends on the electrode lo-
cations and it is not always possible to reconstruct the complete
0018-9294/$31.00 2012 IEEE
1346 IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, VOL. 60, NO. 5, MAY 2013
mECG morphology from a linear combination of the reference
electrodes [3]. Practically, it has been shown that for fECG ex-
traction, blind source separation methods outperform adaptive
lters [22]. An important advantage of spatial ltering over con-
ventional adaptive lters is their ability to separate mECG and
fECG with temporal overlap but it often requires more than two
sensors.
The Kalman ltering (KF) framework, which can be consid-
ered as a member of the general class of adaptive lters, is a
promising approach for both mECG cancelation and fECG en-
hancement. In [16] and [23], a set of state-space equations was
used to model the temporal dynamics of ECG signals, for de-
signing a Bayesian lter for ECGdenoising. This Bayesian lter
framework was used in [16, p. 50] to extract fECG from single-
channel mixture of mECG and fECG. However, as mentioned
in [16], the lter fails to discriminate between the maternal and
fetal components when the mECG and fECG waves fully over-
lap in time. The reason is that when mECG is being estimated,
fECGand other components are supposed to be Gaussian noises.
However, this assumption is not true, especially when mECG
and fECG waves fully overlap in time it is difcult for the lter
to follow desired ECG.
Clinical monitoring of fetal cardiac activity is usually based
on a small number of electrodes located on mothers abdomen,
and on a sound sensitive sensor. In such a context, in this study,
we wonder what performance can be obtained with only one
electrode, by using a rened model of the signal recorded on the
unique electrode: the model will explicitly take into account that
the signal is the superposition of a few ECG signals. The rest of
this paper is organized as follows. In Section II, equations and
theory supporting our proposed method including the Bayesian
ltering theory and dynamic ECG model are described. In Sec-
tion III, results of the proposed method applied on different
data and discussion about the results are presented. Finally, our
conclusion is stated in Section IV.
II. METHODOLOGY
A. Extended Kalman Filter Framework for ECG Extraction
The goal of KF is to estimate the state of a discrete-time
controlled process. Consider a state vector x
k+1
governed by
a nonlinear stochastic difference equation with measurement
vector y
k+1
at time instant k + 1:

x
k+1
= f(x
k
, w
k
, k + 1)
y
k+1
= h(x
k+1
, v
k+1
, k + 1)
(1)
where the random variables w
k
and v
k
represent the pro-
cess and measurement noises, with associated covariance ma-
trices Q
k
= E

w
k
w
T
k

and R
k
= E

v
k
v
T
k

. The extended
Kalman lter (EKF) is an extension of the standard KF to non-
linear systems f() and h(), which linearizes about the cur-
rent mean and covariance [24]. In order to improve the estima-
tions, EKF can be followed by a backward recursive smoothing
stage leading to the extended Kalman smoother (EKS). How-
ever, since EKS is a noncausal method, it cannot be applied
online but it is useful if a small lag in the processing is allowed.
Fig. 1. Illustration of the phase assignment approach on one ECG.
In this study, a synthetic dynamic ECG model [25] is used
to extract fECG from mixture of an mECG, one (or more)
fECG(s), and other signals considered as noises. In polar
coordinates [23], one ECG signal can be expressed as the
sum of ve Gaussian functions dened by their peak ampli-
tude, width, and center, denoted
i
, b
i
, and
i
, respectively:
z() =

iW

i
exp((
i
)
2
/(2b
2
i
)). Each Gaussian func-
tion thus models one of the ve waves W = {P, Q, R, S, T} of
a heart beat. The state vector in (1) is dened by the phase
and the amplitude z of the ECG: x
k
= [
k
, z
k
]
T
. Assuming a
small sampling period , the state noise
k
, and dening w
k
as
[0,
k
]
T
, the state process f() is

k+1
= (
k
+) mod(2) (2)
z
k+1
=

iW

i,k

b
2
i
exp

2
i,k
2b
2
i

+z
k
+
k
(3)
where is the phase increment and
i,k
= (
k

i
)
mod(2). From the ECG, one can dene the observed phase

k
by a linear time wrapping of the RR time intervals into
[0, 2) (see Fig. 1). The measurement process h() is nally de-
ned as y
k+1
= x
k+1
+v
k+1
, where y
k+1
= [
k+1
, s
k+1
]
T
.
The ECGs composing the observed mixture can be estimated
by recursively applying the described EKF: at each step, one
ECGis extracted according to a deation procedure. In case of a
mixture of mECGand one fECG, the rst step extracts, fromthe
rawrecording, the dominant ECG(often the mECG) considering
the concurrent ECG (respectively, fECG) and other noises as a
unique Gaussian noise. After subtracting the dominant ECG
from the original signal, the second step is the extraction of
fECG from the residual signal. This procedure is referred to as
sequential EKF or EKS (seq-EKF or seq-EKS). In this recursive
extraction, during the rst step, the concurrent ECG(i.e., fECG)
and additional noise are modeled by Gaussian noises v
k
and w
k
,
which is not a very relevant assumption. In fact, although this
assumption may be acceptable when there are not strong artifacts
interfering with the ECG, it is no longer accurate when other
ECG artifacts are considerable (i.e., at the rst step) since the
noise is no longer normally distributed. In addition, concurrent
ECGs can be confused with dominant ECG when their waves
(especially QRS complexes) fully overlap in time. Meanwhile,
resultant inaccuracies, which are generated by the previous steps
of the ECG extraction, will propagate to the next steps while the
residuals are computed.
NIKNAZAR et al.: FETAL ECG EXTRACTION BY EXTENDED STATE KALMAN FILTERING BASED ON SINGLE-CHANNEL RECORDINGS 1347
B. Extension to Multiple ECGs: Extended State EKF
In this paper, the dynamic equations (2) and (3) are ex-
tended for simultaneously modeling N ECGs mixed in a
single observation. The related extended state vector x
k
=
[
(1)
k
, z
(1)
k
, . . . ,
(N)
k
, z
(N)
k
]
T
is thus dened by

(1)
k+1
= (
(1)
k
+
(1)
) mod(2)
z
(1)
k+1
=

iW
1

(1)
i

(1)

b
(1)
2
i

(1)
i,k
exp

(1)
2
i,k
2b
(1)
2
i

+z
(1)
k
+
(1)
k
.
.
.

(N)
k+1
= (
(N)
k
+
(N)
) mod(2)
z
(N)
k+1
=

iW
N

(N)
i

(N)

b
(N)
2
i

(N)
i,k
exp

(N)
2
i,k
2b
(N)
2
i

+z
(N)
k
+
(N)
k
where each [
(i)
k
, z
(i)
k
]
T
is related to one of the ECGs. Finally, the
measurement process leads to express the measurement vector
y
k+1
= [
(1)
k+1
, . . . ,
(N)
k+1
, s
k+1
]
T
as

(n)
k+1
=
(n)
k+1
+v
(n)
k+1
, n {1, . . . , N}
s
k+1
=
N

n=1
z
(n)
k+1
+v
(N+1)
k+1
.
(4)
This extended state Kalman ltering procedure is referred to as
parallel EKF or EKS (par-EKF, or par-EKS, respectively). As
shown in Section III, this par-EKF or par-EKS is more accurate
to extract fECG from abdominal sensors than the seq-EKF or
seq-EKF. Indeed, in the proposed method, all ECGs are jointly
modeled by dynamic states so that only the state and mea-
surement noise vectors are assumed to be normally distributed.
Moreover, the extended state par-EKF fully models overlapping
waves of several ECGs. Finally, the state and observation noises,

n
k
and v
n
k
, respectively, allow the lter to t some variabilities
of the ECG shapes. Although the model does not t too large
variations (for example, due to arrythmia), an inspection of the
residue will reveal these abnormal beats.
C. Model Parameters Estimation
The proposed par-EKF and par-EKS lie on several state pa-
rameters {
(n)
i
, b
(n)
i
,
(n)
i
}
iW
n
, n {1, . . . , N}. The proce-
dure described below is an extension of the single ECG param-
eter estimation [23].
The parameters estimation procedure rst needs the R-peak
detection for all ECGs to perform the time wrapping of the RR
intervals into [0, 2) to dene
(n)
k
. The R-peaks are found from
a peak search in windows of length T, where T corresponds to
the R-peak period calculated from approximate ECG beat-rate.
R-peaks with periods smaller than
T
2
or larger than T are not
detected. Although maternal R-peaks are easily detectable from
the mixture, fetal R-peak detection is more complex due to its
lower amplitude than mECG. Therefore, a rough estimation of
fECG is obtained by using the seq-EKF algorithm, which now
allows us to detect easily the fetal R-peaks.
1
Then, for each ECG,
each beat (dened by the signals between two consecutive R-
peaks) is time wrapped into [0, 2). The average of the ECG
waveform is obtained by the mean of all time-wrapped beats,
for all phases between 0 and 2. Finally, by using a nonlinear
least-squares approach [26], the best estimate of the parameters
in the minimum mean square error (MMSE) sense is found.
III. RESULTS AND DISCUSSIONS
Both synthetic and actual data have been used to study perfor-
mance of the proposed method. In Subsection III-A, quantitative
results coming from simulations and inuence of the main pa-
rameters of mixed ECGs on performance of the method has been
studied. They will present the conditions in which the proposed
method is efcient. In Subsection III-B, the effectiveness of the
method on actual data has been examined.
A. Experimental Performance Analysis on Synthetic Data
Since there is neither ground truth nor golden standard on
single-channel recording, it is important to provide quantitative
performance with simulations to validate the behavior of the
proposed method. In order to do so, realistic synthetic mixtures
of mECGand fECGwith white Gaussian noise have been gener-
ated for different situations, and the proposed method has been
applied on them to extract mECG and fECG.
Synthetic mECG and fECG used in this study are based on a
3-Dcanonical model of the single dipole vector of the heart, pro-
posed in [27] and inspired by the single-channel ECG dynamic
model presented in [25]. Sampling frequency is set to 500 Hz
and signals include 20 000 samples. The main parameters that
can affect the mixtures are input noise power, ratio between
amplitudes of fECG and mECG, and ratio between fetal and
maternal heart rates. In order to investigate the performance of
the proposed method, 100 trials were carried out under each
value of these parameters. In the output, estimated mECG and
fECG signals, s
m
and s
f
, are assumed to be the sum of mECG,
fECG, and noise, such that
s
m
=
1
s
m
+
2
s
f
+
3
n
s
f
=
1
s
m
+
2
s
f
+
3
n (5)
where coefcients
1
,
2
,
3
,
1
,
2
, and
3
have to be es-
timated and s
m
, s
f
, and n denote mECG, fECG, and noise,
respectively. In order to estimate the coefcients, s
m
, s
f
, and n
are assumed to be orthogonal, i.e., decorrelated. The orthogo-
nality principle states that an estimator s achieves MMSE if and
only if E

( s s)
T
s

= 0. Satisfaction of this criterion leads to

1
=
E( s
T
m
s
m
)
E(s
T
m
s
m
)
,
2
=
E( s
T
m
s
f
)
E(s
T
m
s
f
)
,
3
=
E( s
T
m
n)
E(s
T
m
n)

1
=
E( s
T
f
s
m
)
E(s
T
f
s
m
)
,

2
=
E( s
T
f
s
f
)
E(s
T
f
s
f
)
,

3
=
E( s
T
f
n)
E(s
T
f
n)
. (6)
1
In practice, one could also use a sound sensor to have a reliable R-peak
detector. In this case, even if there exists a delay, it does not impact the method,
since it can be synchronized.
1348 IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, VOL. 60, NO. 5, MAY 2013
Fig. 2. Mean SNR improvement results of the EKF and EKS against input
noise power (bold lines). Upper and lower borders (thin lines) present maximum
and minimum, respectively.
In a successful estimation, contribution of desired ECG in
output should be much more than contribution of undesired ECG
and noise. In other words, in extraction of fECG, the power of

2
s
f
should be much larger than the power of
1
s
m
+
3
n,
which means the contribution of mECG and noise is very low
in the fECG estimate. In the same manner, the power of
1
s
m
should be much larger than the power of
2
s
f
+
3
n in mECG
extraction. In order to quantize contribution of the desired ECG
in the output, output signal-to-noise ratio (SNR) for maternal
and fetal ECGs are dened as
SNR
m
o u t
=

2
1
P
s
m

2
2
P
s
f
+
2
3
P
n
SNR
f
o u t
=

2
2
P
s
f

2
1
P
s
m
+

2
3
P
n
(7)
where P
s
m
, P
s
f
, and P
n
denote power of mECG, fECG, and
noise, respectively. Output SNR is now compared to input SNR
to investigate performance of desired ECG extraction. Input
SNRs are dened as
SNR
m
i n
=
P
s
m
P
s
f
+P
n
and SNR
f
i n
=
P
s
f
P
s
m
+P
n
. (8)
Input signal-to-interference ratio (SIR) and output SIR are
also dened as
SIR
m
i n
=
P
s
m
P
s
f
, SIR
f
i n
=
P
s
f
P
s
m
SIR
m
o u t
=

2
1
P
s
m

2
2
P
s
f
, SIR
f
o u t
=

2
2
P
s
f

2
1
P
s
m
. (9)
1) SNR Analysis: Fig. 2 shows SNR improvement results of
EKF and EKS over a wide range of input noise power. The SNR
improvement in decibels is dened as the output SNR of the
lter minus the input SNR. In all trials, power of mECG signals
is normalized to 1 (0 dB) and the ratio of amplitudes of fECG
and mECG is 0.3. Maternal and fetal heart rates are set to 1.1
Fig. 3. Mean SIRimprovement results of the EKF and EKS against amplitude
ratio (bold lines). Upper and lower borders (thin lines) present maximum and
minimum, respectively.
and 2 Hz, respectively. Moreover, in order to have more realistic
signals, mECG and fECG are allowed to have slight random
uctuations (5%) in amplitude and duration at each beat. More-
over, initial phases of ECGs are random. As can be seen in
Fig. 2, both EKF and EKS successfully improved the SNR for
all ranges of the input SNRs. When the mixture is rather noise
free (noise power 30 dB), the minimum SNR improvement of
fECG is 40 dB, which means efcient cancelation of mECG.
Nevertheless, even for very noisy mixtures (noise power 20 dB),
the SNR improvement of fECG remains over 20 dB. According
to this gure, EKF is more effective when a rather clean sig-
nal is available. On the contrary, as power of noise increases,
EKS signicantly outperforms EKF. As it has been explained
in the previous section, the EKS algorithm consists of a for-
ward EKF stage followed by a backward recursive smoothing
stage. Therefore, if a rather clean signal is available, the recur-
sive smoothing stage will deteriorate EKF output, because the
output is smooth enough and recursive smoothing leads to over-
ltering. Conversely, if the signal is very noisy, EKF output is
not denoised enough yet. Therefore, recursive smoothing stage
can be successfully used to cancel more noise from the signal.
2) Amplitude Ratio Analysis: The basic problem of fECG
monitoring is to extract the fECG signal from the mixture of
mECG and fECG signals, where the interfering mECG is a
stronger signal. Therefore, it is necessary to evaluate the perfor-
mance of the method for different ratios of fECG and mECG
amplitudes. For this purpose, SIRimprovement of output signals
have been calculated in the range of 0.11 of amplitude ratio
of fECG and mECG. Fig. 3 shows SIR improvement results
of the EKF and EKS for different values of amplitude ratios.
Power of mECG signals are normalized to 1 (0 dB) with 5%
random uctuation, input SNR with respect to (w.r.t.) mECG is
10 dB, and average maternal and fetal heart rates are 1.1 and
2 Hz, respectively. As is seen in Fig. 3, although the fetal SIR
improvements of both EKF and EKS remain over 30 dB for all
ranges of the amplitude ratios, results of EKS are slightly better.
NIKNAZAR et al.: FETAL ECG EXTRACTION BY EXTENDED STATE KALMAN FILTERING BASED ON SINGLE-CHANNEL RECORDINGS 1349
Fig. 4. Mean SIR improvement results of the EKF and EKS against heart rate
ratio (bold lines). Upper and lower borders (thin lines) present maximum and
minimum, respectively.
3) Heart Rate Ratio Analysis: Since fetal heart rate may vary
in a wide range [28], the performance of the method was studied
on a wide range of 0.33.6 Hz of fetal heart rate. Fig. 4 shows
SIR improvement results of EKF and EKS. Power of mECG
signals are normalized to 1 (0 dB) with 5% random uctuation
and the ratio of amplitudes of fECG and mECG is 0.3. Input
SNR w.r.t. mECG is 10 dB, and maternal heart rate is set to
1.1 Hz. In this section, heart rate uctuations are slighter (1%)
to study harmonic issues more accurately. As expected, SIR
improvement diagram has three deep local minima at ratios 1,
2, and 3. The reason is that when main frequencies of mECG
and fECG are proportional, the signals overlap more closely
in the frequency domain. Therefore, discrimination of mECG
and fECG is more difcult for these ratios. Nevertheless, these
situations are unlikely happening because the heart rate ratio is
usually more than 1 and less than 2. Even in these cases, fetal
SIRimprovement remains over 20 dB. Here again, EKS slightly
outperforms EKF.
B. Fetal ECG Extraction on Actual Data
In Subsection III-A, efciency of the proposed method in
fECG extraction for a wide range of possible congurations has
been examined using synthetic data. In this section, the results of
application of the proposed method on actual data are presented.
1) DaISy Database: The DaISy fetal ECG database [29]
consists of a single dataset of cutaneous potential recording of
a pregnant woman. A total of eight channels (ve abdominal
and three thoracic) are available, sampled at 250 Hz and lasting
10 s.
Fig. 5 presents the results of par-EKS and seq-EKS using the
rst channel of the dataset. Moreover, the periodic component
analysis (CA) [8] using the eight channels, which is a multi-
channel method, is also included as the golden standard. Results
of CAmethod are then postprocessed via EKS on the best ECG
estimate [23]. As already mentioned, unlike seq-EKS, par-EKS
does not fail when mECG and fECG fully overlap in time. This
Fig. 5. Comparison of fECG extraction by par-EKS, seq-EKS and CA on
the rst channel of DaISy data.
is particularly noticed between t = 6 s and t = 7 s in Fig. 5, in
which some parts of fECG signal have been deteriorated during
mECG extraction by the seq-EKS method. On the contrary, the
proposed par-EKS jointly models the fECG and mECG, result-
ing in a better estimate of fECG than seq-EKS. Since par-EKS
estimates a single component while CA can estimate several
components (typically one or two), the cosine between sub-
spaces is used and is equal to 0.92 in this experiment. With a
value close to 1, these estimates are quite similar. Finally, Fig. 6
shows the results of fECG extraction using par-EKS applied on
the other abdominal channels of the DaISy dataset. It experi-
mentally proves that par-EKS is able to extract fECG even in
ill-conditioned mixtures, such as channels 4 or 5.
2) Noninvasive fECG Database: This database consists of
a series of 55 multichannel abdominal fECG recordings, taken
from a single subject between 21 and 40 weeks of pregnancy.
The recordings include two thoracic signals and three or four
abdominal signals. The signals were recorded at 1 kHz, 16-bit
resolution with a bandpass lter (0.01100 Hz) and a main notch
lter (50 Hz) [30]. Fig. 7 shows results of seq-EKS and par-EKS
using channel 3, and CA using all channels of the rst 20s of
namely the ecgca771 dataset. To show the effectiveness of the
proposed method in extraction of the fECG at different periods
of pregnancy, and from different channel locations, the rst
20s of the mixtures and fetal par-EKS outputs of the datasets
ecgca274 channel 5, ecgca748 channel 4, and ecgca997 channel
3 are plotted in Fig. 8.
3) Twin Magnetocardiograms Extraction: The proposed
method has been principally designed for ECG signals. Nev-
ertheless, due to the morphological similarity of the ECG and
the magnetocardiogram (MCG), it is also directly applicable
to MCG recordings. In this section, twin fetal cardiac mag-
1350 IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, VOL. 60, NO. 5, MAY 2013
Fig. 6. Results of fECG extraction using par-EKS applied on channels 25
of the DaISy dataset (up to down). Note differences of scales, according to the
channels and the fetal estimates.
Fig. 7. Comparison of fECG extraction by par-EKS, seq-EKS, and CA on
ecgca771 of the PhysioNet database.
netic signals recorded by a SQUID Biomagnetometer system
are extracted. The dataset has been recorded in the Biomagnetic
Center of the Department of Neurology (Friedrich Schiller Uni-
versity, Jena, Germany) and it consists of 208 channels sampled
at 1025 Hz over 30 min.
Fig. 8. ECG mixtures of the datasets ecgca274 channel 5, ecgca748 channel
4, and ecgca997 channel 3, and their fetal par-EKS outputs.
Fig. 9. Results of the seq-EKS, par-EKS, and CA on twin MCG data.
Fig. 9 presents the results of the proposed par-EKS to ex-
tract the two fetal MCG signals from a single sensor. A typical
channel (indexed 92) of namely the q00002252 dataset has been
selected. Even though the multichannel CA method provides
better results in this case than single-channel methods (par-EKS
NIKNAZAR et al.: FETAL ECG EXTRACTION BY EXTENDED STATE KALMAN FILTERING BASED ON SINGLE-CHANNEL RECORDINGS 1351
Fig. 10. MCG mixtures of the channels 126, 152, and 160, and their fetal
par-EKS outputs.
or seq-EKS), the proposed par-EKS succeeds to extract the two
fetal MCG (fMCG), while seq-EKS fails to discriminate cor-
rectly the two fMCGs when they overlap (see highlighted signal
parts in Fig. 9). In order to show the good behavior of par-EKS
in several congurations, par-EKS is applied on other sensors
(see Fig. 10). One can note that the proposed par-EKS succeeds
to extract the two fetal MCGs.
Finally, it is worth noting that the crucial part of the proposed
par-EKSis the R-peak detection. Although this detection is quite
direct when a single fetus is present (see Subsection II-C), some
words should be added on twin data. Indeed, on such data, the
detection of the mothers R-peaks is still direct since it is the
dominant signal. On the contrary, the discrimination between the
two fetal R-peaks is much more difcult. Even though in this
study, the oracle is obtained using several sensors and applying
an ICA algorithm (here, we used Fast-ICA), it can be replaced
in practice by a sound sensor located on the mothers abdomen.
IV. CONCLUSION
In this paper, a synthetic dynamic ECG model within a KF
framework has been extended to jointly model several ECGs to
extract desired ECGs from a unique mixture (i.e., one channel
recording) of maternal and fetal ECGs and noise. Although the
proposed method only uses a single channel to separate dif-
ferent ECGs, since each ECG has a corresponding term in the
model, the proposed model can efciently discriminate ECGs
even if desired and undesired ECG waves overlap in time. As
proved on synthetic data and illustrated on actual data (single
and multiple fetal pregnancy), the main merit of the proposed
algorithm relies on its performance in a large class of situations.
Performance of the proposed method on extraction of fECG
from one mixture of mECG and fECG was examined according
to noise level, amplitude ratio, and heart rate ratio parameters:
results show that the proposed method can be successfully em-
ployed in many scenarios. According to the obtained results,
as long as R-peaks are correctly detected, the proposed model
achieves good results. Although a reliable R-peak detection is
a straight forward procedure in a single fetal pregnancy (which
most likely happens) even with a single sensor, it is much more
difcult in multiple fetal pregnancy (twin or more). Nonethe-
less, in these situations, the R-peak detection can be provided
by other modalities such as echocardiography.
Finally, the proposed method compares favorably with ef-
cient multisensor methods such as CA (which also requires
reliable R-peak detection), while it requires only one sensor. The
latter criterion is of high interest, since using a single channel
does not only mean less electronic components (such as analog
to digital converters or ampliers) and thus a cheaper device,
but also a more convenient and portable device for a long-term
monitoring system or at home since only a single electrode has
to be placed on the mothers abdomen.
Perspectives include extension of the proposed method to
apply on multichannel (but with a small number of channels,
e.g., up to 3 or 4) mixtures of mECG and fECG. Moreover,
synchronous echocardiography data can also be used in future
works, especially for a reliable R-peak detection.
ACKNOWLEDGMENT
The authors would like to thank Dr. R. Sameni for his support
and assistance in this study, and Dr. D. Hoyer for providing the
twin MCG dataset.
REFERENCES
[1] H. M. Jenkins, Technical progress in fetal electrocardiographyA re-
view, J. Perinat. Med., vol. 14, no. 6, pp. 365370, 1986.
[2] G. Camps, M. Martinez, and E. Soria, Fetal ECG extraction using an r
neural network, in Proc. Comput. Cardiol., 2001, pp. 249252.
[3] R. Sameni and G. D. Clifford, A review of fetal ECG signal processing;
Issues and promising directions, Open Pacing, Electrophysiol. Ther. J.,
vol. 3, pp. 420, 2010.
[4] A. Khamene and S. Negahdaripour, A new method for the extraction of
fetal ECG from the composite abdominal signal, IEEE Trans. Biomed.
Eng., vol. 47, no. 4, pp. 507516, Apr. 2000.
[5] P.P. Kanjilal, S. Palit, and G. Saha, Fetal ECG extraction from single-
channel maternal ECG using singular value decomposition, IEEE Trans.
Biomed. Eng., vol. 44, no. 1, pp. 5159, Jan. 1997.
[6] J.-F. Cardoso, Multidimensional independent component analysis, in
Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., May 1998, vol. 4,
pp. 19411944.
[7] L. de Lathauwer, B. de Moor, and J. Vandewalle, Fetal electrocardiogram
extraction by blind source subspace separation, IEEE Trans. Biomed.
Eng., vol. 47, no. 5, pp. 567572, May 2000.
[8] R. Sameni, C. Jutten, and M. B. Shamsollahi, Multichannel electrocar-
diogram decomposition using periodic component analysis, IEEE Trans.
Biomed. Eng., vol. 55, no. 8, pp. 19351940, Aug. 2008.
[9] J. L. Camargo-Olivares, R. Marti-Clemente, S. Hornillo-Mellado,
M. M. Elena, and I. Roman, The maternal abdominal ECG as input to
MICA in the fetal ECG extraction problem, IEEE Signal Process. Lett.,
vol. 18, no. 3, pp. 161164, Mar. 2011.
[10] A. K. Barros and A. Cichocki, Extraction of specic signals with tem-
poral structure, Neural Comput., vol. 13, no. 9, pp. 19952003, Sep.
2001.
1352 IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, VOL. 60, NO. 5, MAY 2013
[11] Z. Yi and Z. Zhang, Extraction of temporally correlated sources with
its application to non-invasive fetal electrocardiogram extraction, Neu-
rocomputing, vol. 69, no. 79, pp. 894899, 2006.
[12] Y. Li and Z. Yi, An algorithm for extracting fetal electrocardiogram,
Neurocomputing, vol. 71, no. 79, pp. 15381542, 2008.
[13] V. Vigneron, A. Paraschiv-Ionescu, A. Azancot, O. Sibony, and C. Jutten,
Fetal electrocardiogram extraction based on non-stationary ICA and
wavelet denoising, in Proc. 7th Int. Signal Process. Appl. Symp., 2003,
vol. 2, pp. 6972.
[14] M. G. Jafari and J. A. Chambers, Fetal electrocardiogram extraction by
sequential source separation in the wavelet domain, IEEE Trans. Biomed.
Eng., vol. 52, no. 3, pp. 390400, Mar. 2005.
[15] R. Martin-Clemente, J. L. Camargo-Olivares, S. Hornillo-Mellado,
M. Elena, and I. Roman, Fast technique for noninvasive fetal ECG ex-
traction, IEEE Trans. Biomed. Eng., vol. 58, no. 2, pp. 227230, Feb.
2011.
[16] R. Sameni. (2008, Jul.) Extraction of fetal cardiac signals from an ar-
ray of maternal abdominal recordings, Ph.D. thesis, Sharif University
of TechnologyInstitut National Polytechnique de Grenoble, [Online].
Available:http://www.sameni.info/Publications/Thesis/PhDThesis.pdf
[17] M. Kotas, Projective ltering of time-aligned ECG beats, IEEE Trans.
Biomed. Eng., vol. 51, no. 7, pp. 11291139, Jul. 2004.
[18] B. Widrow, Jr, J. R. Glover, J. M. McCool, J. Kaunitz, C. S. Williams,
R. H. Hearn, J. R. Zeidler, Jr, E. Dong, and R. C. Goodlin, Adaptive
noise cancelling: Principles and applications, Proc. IEEE, vol. 63, no. 12,
pp. 16921716, Dec. 1975.
[19] N. J. Outram, E. C. Ifeachor, P. W. J. Van Eetvelt, and J. S. H. Curnow,
Techniques for optimal enhancement and feature extraction of fetal elec-
trocardiogram, IEE Proc.Sci., Meas. Technol., vol. 142, no. 6, pp. 482
489, 1995.
[20] A. G. Favret, Computer matched lter location of fetal R-waves, Med.
Biol. Eng., vol. 6, no. 5, pp. 467475, Sep. 1968.
[21] Y. C. Park, K. Y. Lee, D. H. Youn, N. H. Kim, W. K. Kim, and S. H. Park,
On detecting the presence of fetal R-wave using the moving averaged
magnitude difference algorithm, IEEETrans. Biomed. Eng., vol. 39, no. 8,
pp. 868871, Aug. 1992.
[22] V. Zarzoso and A. K. Nandi, Noninvasive fetal electrocardiogram extrac-
tion: blind separation versus adaptive noise cancellation, IEEE Trans.
Biomed. Eng., vol. 48, no. 1, pp. 1218, Jan. 2001.
[23] R. Sameni, M. B. Shamsollahi, C. Jutten, and G. D. Clifford, Anonlinear
Bayesian ltering framework for ECG denoising, IEEE Trans. Biomed.
Eng., vol. 54, no. 12, pp. 21722185, Dec. 2007.
[24] G. Welch and G. Bishop, An introduction to the Kalman lter, Dept.
Comput. Sci., Univ. North Carolina, Chapel Hill, Tech. Rep. TR 95-041,
1995.
[25] P. E. McSharry, G. D. Clifford, L. Tarassenko, and L. A. Smith, A dy-
namical model for generating synthetic electrocardiogram signals, IEEE
Trans. Biomed. Eng., vol. 50, no. 3, pp. 289294, Mar. 2003.
[26] G. D. Clifford, A. Shoeb, P. E. McSharry, and B. A. Janz, Model-based
ltering, compression and classication of the ECG, Int. J. Bioelectro-
mag., vol. 7, no. 1, pp. 158161, 2005.
[27] R. Sameni, G. D. Clifford, C. Jutten, and M. B. Shamsollahi, Multichan-
nel ECG and noise modeling: Application to maternal and fetal ECG
signals, EURASIP J. Adv. Signal Process., vol. 2007, p. 43407, 2007.
[28] T. J. DuBose, J. A. Cunyus, and L. F. Johnson, Embryonic heart rate and
age, J. Diagnost. Med. Sonogr., vol. 6, no. 3, pp. 151157, 1990.
[29] B. De Moor, P. De Gersem, B. De Schutter, and W. Favoreel, DAISY: A
database for identication of systems, J. A, Spec. Issue Comput. Aided
Control Systems Design, vol. 38, no. 3, pp. 45, Sep. 1997.
[30] A. L. Goldberger, L. A. N. Amaral, L. Glass, J. M. Hausdorff, P. Ch.
Ivanov, R. G. Mark, J. E. Mietus, G. B. Moody, C.-K. Peng, and H. E.
Stanley, PhysioBank, PhysioToolkit, and PhysioNet: Components of a
new research resource for complex physiologic signals, Circulation, vol.
101, no. 23, pp. e215e220, Jun. 13, 2000, Circulation Electronic Pages,
[Online]. Available:http://circ.ahajournals.org/cgi/content/full/101/23/
e215
Mohammad Niknazar was born in Tehran, Iran, in
1985. He received his B.Sc. degree in electrical elec-
tronic engineering from the University of Semnan,
Semnan, Iran, in 2007, and the M.Sc. degree in elec-
trical biomedical engineering fromthe Sharif Univer-
sity of Technology, Tehran, Iran, in 2010. As a mem-
ber of GIPSA-lab, he is currently working toward the
Ph.D. degree in signal, image and speech processing
and telecommunications at Joseph Fourier Univer-
sity, Grenoble, France.
His research interests include signal and image
processing, nonlinear (chaos) analysis, blind source separation, and pattern
recognition. Current areas of application include fetal ECG extraction and ECG
processing. Previous areas of application include epileptic seizure detection and
prediction.
Bertrand Rivet was graduated from the

Ecole
Normale Sup erieure de Cachan, France. He received
the Agr egation de Physique Appliqu ee in 2002, the
Masters degree from the University of Paris-XI,
France, in 2003, and the Ph.D. degree from Grenoble
Institute of Technology (GIT), Grenoble, France, in
2006.
He is currently an Associate Professor in signal
processing with PHELMA and a member of GIPSA-
lab, GIT. His research interests include biomedical
signal processing, audiovisual speech processing, and
blind source separation.
Christian Jutten (F08) received the Ph.D. degree
and the Docteur ` es Sciences degree from the Insti-
tut National Polytechnique of Grenoble, Grenoble,
France, in 1981 and 1987, respectively.
From1982 to 1989, he was an Associate Professor
in the Department of Electrical Engineering, Institut
National Polytechnique de Grenoble. Since 1989, he
has been a full Professor at University Joseph Fourier,
Grenoble. He was a Visiting Professor in the Swiss
Federal Polytechnic Institute in Lausanne in 1989
and in Campinas University (Brazil) in 2010. He has
been the Deputy Director of the Grenoble images, speech, signal, and control
laboratory (GIPSA, 300 people) and Director of the Department Images-Signal
(DIS, 100 people) from 2007 to 2010. For 30 years, his research interests are
blind source separation, independent component analysis, and learning in neu-
ral networks, including theoretical aspects (separability, source separation in
nonlinear mixtures, sparsity) and applications in signal processing (biomedical,
seismic, hyperspectral imaging, speech). He is an author or co-author of more
than 65 papers in international journals, four books, 22 invited plenary talks,
and 150 communications in international conferences.
Dr. Jutten was an Associate Editor of the IEEE TRANSACTIONS ON CIRCUITS
AND SYSTEMS in 19941995, and co-organizer the 1st International Conference
on Blind Signal Separation and Independent Component Analysis (Aussois,
France, January 1999). He has been a scientic advisor for signal and images
processing at the French Ministry of Research from 1996 to 1998 and for the
French National Research Center (CNRS) from 2003 to 2006. He is currently
Deputy Director of the Institute for Information Sciences and Technologies of
CNRS. He received the Medal Blondel in 1997 from SEE (French Electrical
Engineering Society) for his contributions in source separation and independent
component analysis, and became a Senior Member of the Institut Universitaire
de France in 2008.