European
Journal
of
Radiology
83 (2014) e1–
e7
Contents
lists
available
at
ScienceDirect
European
Journal
of
Radiology
jo
ur
nal
ho
me
page:
www.elsevier.com/locate/ejrad
Computer-assisted
assessment
of
ultrasound
real-time
elastography:
Initial
experience
in
145
breast
lesions
Xue
Zhang
a,1
,
Yang
Xiao
a,1
,
Jie
Zeng
b
,
Weibao
Qiu
a
,
Ming
Qian
a
,
Congzhi
Wang
a
,
Rongqin
Zheng
b,∗
,
Hairong
Zheng
a,∗
a
Shenzhen
Key
Lab
for
Molecular
Imaging,
Paul
C.
Lauterbur
Research
Center
for
Biomedical
Imaging,
Institute
of
Biomedical
and
Health
Engineering,
Shenzhen
Institutes
of
Advanced
Technology,
Chinese
Academy
of
Sciences,
Shenzhen,
China
b
Department
of
Medical
Ultrasonics,
Third
Affiliated
Hospital
of
Sun
Yat-Sen
University,
Guangzhou,
China
a
r
t
i
c
l
e
i
n
f
o
Article
history:
Received
19
April
2013
Received
in
revised
form
20
August
2013
Accepted
9
September
2013
Keywords:
Real-time
elastography
Breast
lesion
Computer-assisted
Elasticity
score
a
b
s
t
r
a
c
t
Purpose:
To
develop
and
evaluate
a
computer-assisted
method
of
quantifying
five-point
elasticity
scoring
system
based
on
ultrasound
real-time
elastography
(RTE),
for
classifying
benign
and
malignant
breast
lesions,
with
pathologic
results
as
the
reference
standard.
Materials
and
methods:
Conventional
ultrasonography
(US)
and
RTE
images
of
145
breast
lesions
(67
malignant,
78
benign)
were
performed
in
this
study.
Each
lesion
was
automatically
contoured
on
the
B-
mode
image
by
the
level
set
method
and
mapped
on
the
RTE
image.
The
relative
elasticity
value
of
each
pixel
was
reconstructed
and
classified
into
hard
or
soft
by
the
fuzzy
c-means
clustering
method.
According
to
the
hardness
degree
inside
lesion
and
its
surrounding
tissue,
the
elasticity
score
of
the
RTE
image
was
computed
in
an
automatic
way.
Visual
assessments
of
the
radiologists
were
used
for
comparing
the
diagnostic
performance.
Histopathologic
examination
was
used
as
the
reference
standard.
The
Student’s
t
test
and
receiver
operating
characteristic
(ROC)
curve
analysis
were
performed
for
statistical
analysis.
Results:
Considering
score
4
or
higher
as
test
positive
for
malignancy,
the
diagnostic
accuracy,
sensitivity,
specificity,
positive
predictive
value
(PPV)
and
negative
predictive
value
(NPV)
were
93.8%
(136/145),
92.5%
(62/67),
94.9%
(74/78),
93.9%
(62/66),
and
93.7%
(74/79)
for
the
computer-assisted
scheme,
and
89.7%
(130/145),
85.1%
(57/67),
93.6%
(73/78),
92.0%
(57/62),
and
88.0%
(73/83)
for
manual
assess-
ment.
Area
under
ROC
curve
(A
z
value)
for
the
proposed
method
was
higher
than
the
A
z
value
for
visual
assessment
(0.96
vs.
0.93).
Conclusion:
Computer-assisted
quantification
of
classical
five-point
scoring
system
can
significantly
elim-
inate
the
interobserver
variability
and
thereby
improve
the
diagnostic
confidence
of
classifying
the
breast
lesions
to
avoid
unnecessary
biopsy.
© 2013 Elsevier Ireland Ltd. All rights reserved.
1.
Introduction
Ultrasound
real-time
elastography
(RTE)
has
recently
been
explored
to
evaluate
the
relative
elasticity
distribution
between
a
lesion
and
the
surrounding
normal
tissue
and
has
become
a
valu-
able
tool
for
breast
lesion
characterization
[1,2].
Malignant
lesions
are
mostly
shown
to
be
harder
and
produce
areas
on
RTE
images
larger
than
the
greyscale
abnormality
on
corresponding
B-mode
images,
whereas
benign
lesions
tend
to
appear
similar
or
slightly
smaller
on
RTE
images
than
on
the
B-mode
images
[3].
This
prop-
erty
serves
as
the
basis
for
RTE
in
classifying
benign
and
malignant
∗
Corresponding
authors
at:
Paul
C.
Lauterbur
Research
Center
for
Biomedical
Imaging,
SIAT,
Chinese
Academy
of
Sciences,
1068
Xueyuan
Avenue,
SZ
University
Town,
Shenzhen
518055,
China.
Tel.:
+86
755
86392244;
fax:
+86
755
86392299.
E-mail
addresses:
zhengronggin@hotmail.com
(R.
Zheng),
hr.zheng@siat.ac.cn
(H.
Zheng).
1
These
authors
contributed
equally
to
this
work
and
are
co-first
authors.
breast
lesions.
Several
clinical
studies
have
been
reported
in
the
literature
[4–7]
and
some
elasticity
features,
such
as
strain
ratio
[8],
strain
difference
[9],
softness
degree
[10],
hard
area
ratio
[11]
and
length
ratio
[12]
have
proven
to
be
useful
in
clinical
diagnosis.
One
of
these
methods
termed
five-point
scale
visual
scoring
sys-
tem
and
first
proposed
by
Itoh
et
al.
[13],
according
to
the
degree
and
distribution
of
strain
induced
by
light
compression,
is
the
most
widely
long-established
and
recognized
method
with
RTE
images
and
it
show
satisfactory
results
in
differentiating
benign
and
malig-
nant
lesions
of
breast,
pancreas
and
thyroid
[13–16].
However,
the
elasticity
scores
are
generally
assigned
by
the
examiners
and
are
not
yet
automated,
resulting
in
significant
interobserver
variabil-
ity
[16,5].
Quantitative
assessment
of
RTE
images
by
computer
has
the
potential
to
improve
the
diagnostic
accuracy
in
order
to
avoid
unnecessary
biopsy.
The
purpose
of
this
study
was
to
propose
a
computer-assisted
method
for
quantifying
five-point
scale
scoring
system
and
apply
it
to
classifying
benign
and
malignant
breast
lesions.
To
evaluate
0720-048X/$
–
see
front
matter ©
2013 Elsevier Ireland Ltd. All rights reserved.
http://dx.doi.org/10.1016/j.ejrad.2013.09.009