I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
6
,
No
.
6
,
Decem
b
er
201
6
,
p
p
.
281
0
~
2
8
1
7
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
6i
6
.
1
3
2
6
8
2810
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
JE
C
E
Effec
tive Co
m
pu
t
er
-
Ass
iste
d Au
tom
a
tic
Cervica
l
Ve
rtebrae
Ex
traction w
ith
Reha
bilitativ
e Ul
tr
a
so
und I
m
a
g
ing
b
y
using
K
-
m
ea
ns
Cluste
ri
ng
Hae
-
J
un
g
L
ee
1
,
Do
o
H
e
o
n So
ng
2
,
K
w
a
ng
B
a
ek
K
i
m
3
1
De
p
a
rtme
n
t
o
f
P
h
y
sic
a
l
T
h
e
ra
p
y
,
S
il
la Un
iv
e
rsity
,
Re
p
u
b
li
c
o
f
Ko
re
a
2
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter G
a
m
e
s
,
Yo
n
g
-
In
S
o
n
g
Da
m
Co
ll
e
g
e
,
Re
p
u
b
li
c
o
f
Ko
re
a
3
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter E
n
g
in
e
e
rin
g
,
S
il
la Un
iv
e
rsit
y
,
Re
p
u
b
li
c
o
f
Ko
re
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
9
,
2
0
1
6
R
ev
i
s
ed
A
u
g
2
8
,
2
0
1
6
A
cc
ep
ted
Sep
1
7
,
2
0
1
6
Ne
c
k
p
a
in
is
o
n
e
o
f
m
o
st
c
o
m
m
o
n
m
u
sc
u
lo
sk
e
let
a
l
c
o
n
d
it
io
n
r
e
su
lt
in
g
in
sig
n
if
ica
n
t
c
li
n
ica
l,
so
c
ial
a
n
d
e
c
o
n
o
m
ic
c
o
sts.
M
u
sc
les
a
ro
u
n
d
c
e
rv
ica
l
sp
in
e
in
c
lu
d
in
g
d
e
e
p
n
e
c
k
f
le
x
o
r
s
p
la
y
a
k
e
y
ro
le
to
su
p
p
o
rt
a
n
d
c
o
n
tro
l
it
s
sta
b
il
it
y
,
th
u
s
m
o
n
it
o
ri
n
g
su
c
h
m
u
sc
les
n
e
a
r
c
e
rv
ic
a
l
v
e
rteb
ra
e
is
im
p
o
rtan
t.
In
th
is
p
a
p
e
r,
w
e
p
ro
p
o
se
a
f
u
ll
y
a
u
to
m
a
ted
c
o
m
p
u
ter
a
ss
isted
m
e
th
o
d
t
o
d
e
tec
t
c
e
rv
ica
l
v
e
rteb
ra
e
w
it
h
K
-
m
e
a
n
s
p
ix
e
l
c
lu
ste
rin
g
f
ro
m
u
lt
ra
so
n
o
g
ra
p
h
y
.
T
h
e
m
e
th
o
d
a
lso
a
p
p
li
e
s
a
se
ries
o
f
i
m
a
g
e
p
ro
c
e
ss
in
g
a
lg
o
rit
h
m
s
to
re
m
o
v
e
u
n
n
e
c
e
ss
a
ry
o
rg
a
n
s
a
n
d
n
o
ise
s
in
th
e
p
r
o
c
e
ss
.
T
h
e
e
x
p
e
ri
m
e
n
t
v
e
ri
f
ies
th
a
t
o
u
r
a
p
p
ro
a
c
h
is
c
o
n
siste
n
t
w
it
h
h
u
m
a
n
m
e
d
ica
l
e
x
p
e
rts’
d
e
c
isio
n
to
lo
c
a
te
k
e
y
m
e
a
su
rin
g
p
o
i
n
t
f
o
r
m
u
sc
le
a
n
a
ly
sis
a
n
d
su
c
c
e
ss
f
u
l
in
d
e
tec
ti
n
g
c
e
rv
ica
l
v
e
rteb
ra
e
a
c
c
u
ra
tel
y
–
su
c
c
e
ss
f
u
l
in
4
8
o
u
t
o
f
5
0
tes
t
c
a
se
s (9
6
%
).
K
ey
w
o
r
d
:
C
er
v
ical
v
er
teb
r
ae
C
h
r
o
n
icle
n
ec
k
p
ain
Dee
p
ce
r
v
ical
f
le
x
o
r
K
-
m
ea
n
s
clu
s
ter
i
n
g
Ultr
aso
n
o
g
r
ap
h
y
Co
p
y
rig
h
t
©
2
0
1
6
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
K
w
a
n
g
B
ae
k
Ki
m
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
E
n
g
i
n
ee
r
in
g
,
Sil
la
Un
iv
er
s
it
y
,
1
4
0
B
ae
g
y
an
g
-
d
ae
r
o
(
B
lv
d
)
7
0
0
b
eo
n
-
g
il
(
R
d
)
,
Sas
a
n
g
-
g
u
,
B
u
s
an
-
4
6
9
5
8
,
R
ep
u
b
lic
o
f
Ko
r
ea
.
E
m
ail:
g
b
k
i
m
@
s
il
la.
ac
.
k
r
1.
I
NT
RO
D
UCT
I
O
N
Nec
k
p
ai
n
is
v
er
y
co
m
m
o
n
c
o
m
p
lai
n
t
af
f
ec
ti
n
g
u
p
to
7
0
%
o
f
i
n
d
i
v
id
u
al
s
at
s
o
m
e
p
o
i
n
t
o
f
t
h
eir
liv
es
[
1
]
.
C
lin
ical
n
ec
k
p
ai
n
is
as
s
o
ciate
d
w
it
h
i
m
p
air
m
en
t
o
f
m
u
s
cle
p
er
f
o
r
m
a
n
ce
an
d
th
e
f
u
n
ctio
n
a
l
i
m
p
air
m
e
n
t
s
ass
o
ciate
d
w
it
h
n
ec
k
p
ai
n
an
d
t
h
e
ca
u
s
e
-
e
f
f
ec
t
r
elatio
n
s
h
ip
s
b
et
w
ee
n
n
e
ck
p
ain
a
n
d
m
o
to
r
co
n
tr
o
l
ar
e
w
ell
in
v
es
tig
a
ted
[
2
]
.
A
n
te
v
er
teb
r
al
d
ee
p
ce
r
v
ical
f
le
x
o
r
(
DC
F)
m
u
s
cles
s
u
ch
as
lo
n
g
u
s
co
li
a
n
d
lo
n
g
u
s
ca
p
iti
s
d
o
k
e
y
r
o
le
to
s
tab
ilize
ce
r
v
ical
ar
ticu
latio
n
s
a
n
d
to
p
r
eser
v
e
th
e
lo
r
d
o
t
ic
cu
r
v
at
u
r
e
o
f
th
e
s
p
in
e
[
3
]
an
d
s
ter
n
o
cleid
o
m
as
to
id
m
u
s
cle
(
S
C
M)
is
r
elate
d
w
it
h
t
h
e
r
o
tatio
n
o
f
t
h
e
n
ec
k
[
4
]
.
Stre
n
g
t
h
en
in
g
o
f
th
ese
m
u
s
cles
i
s
i
m
p
o
r
tan
t
to
tr
ea
t
th
e
p
atien
ts
w
it
h
n
ec
k
p
ain
p
r
o
v
o
k
ed
b
y
v
ar
io
u
s
p
ath
o
lo
g
ies
o
f
ce
r
v
ical
s
p
in
e
[
5
]
.
Usi
n
g
u
ltra
s
o
u
n
d
i
m
ag
e
i
n
m
u
s
cle
an
al
y
s
i
s
is
ap
p
r
o
p
r
iate
f
o
r
its
n
o
n
-
i
n
v
asi
v
e,
in
e
x
p
en
s
i
v
e,
r
ea
l
ti
m
e
r
esp
o
n
s
es
[
6
]
.
Ho
w
ev
er
,
its
li
m
itatio
n
s
ar
e
o
f
te
n
p
o
in
ted
o
u
t
th
a
t
s
o
n
o
g
r
ap
h
ic
i
m
a
g
es
ar
e
d
ep
en
d
en
t
o
n
th
e
q
u
alities
o
f
eq
u
ip
m
e
n
t
a
n
d
s
k
ills
o
f
ex
p
er
ti
s
e
t
h
u
s
t
h
e
d
iag
n
o
s
is
o
f
te
n
m
is
lead
s
to
s
u
b
j
ec
tiv
e
j
u
d
g
m
e
n
t
[
7
]
.
T
h
u
s
,
w
e
n
ee
d
a
n
au
to
m
atic
i
m
ag
e
s
e
g
m
e
n
tatio
n
an
d
id
e
n
t
if
icatio
n
to
o
l
f
o
r
an
ato
m
ical
l
an
d
m
ar
k
s
t
h
at
ca
n
eli
m
i
n
ate
s
u
c
h
s
u
b
j
ec
tiv
it
y
i
n
t
h
e
i
m
a
g
e
a
n
al
y
s
is
[
8
]
.
Un
f
o
r
tu
n
atel
y
,
t
h
er
e
is
al
m
o
s
t
n
o
d
ir
ec
tly
r
elate
d
r
esear
ch
f
o
r
s
u
ch
an
a
u
to
m
a
tic
n
ec
k
p
ain
r
elate
d
m
u
s
cle
e
x
tr
ac
to
r
/
an
al
y
ze
r
b
y
co
m
p
u
ter
v
i
s
io
n
y
et.
A
r
ec
en
t
s
tu
d
y
tr
ied
to
g
iv
e
a
n
au
to
m
a
tic
s
eg
m
e
n
tatio
n
o
f
ce
r
v
ical
v
er
teb
r
ae
f
r
o
m
X
-
r
a
y
s
[
9
]
b
u
t
n
o
t
r
elate
d
to
m
u
s
c
l
es
o
f
o
u
r
in
ter
est
s
.
Ou
r
co
n
ce
r
n
is
to
d
etec
t
an
d
ex
tr
ac
t
m
u
s
cles
s
u
ch
a
s
s
ter
n
o
cleid
o
m
a
s
to
id
an
d
lo
n
g
u
s
ca
p
itis
/co
lli
i
n
co
n
j
u
n
ctio
n
w
it
h
ce
r
v
ical
v
er
teb
r
ae
au
to
m
at
icall
y
f
r
o
m
u
ltra
s
o
n
o
g
r
ap
h
y
a
n
d
m
ea
s
u
r
i
n
g
t
h
e
th
i
ck
n
e
s
s
f
o
r
f
u
r
t
h
er
m
ed
ical
an
al
y
s
i
s
[
1
0
-
1
1
]
.
A
ll
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
:
2
8
1
0
–
2
8
1
7
2811
th
r
ee
v
i
s
io
n
b
ase
d
ap
p
r
o
ac
h
es
ai
m
to
lo
ca
te
m
ea
s
u
r
i
n
g
k
e
y
p
o
in
t
ac
cu
r
atel
y
to
av
o
id
m
a
n
u
al
s
u
b
j
ec
tiv
e
k
e
y
p
o
in
t setti
n
g
f
o
r
m
u
s
cle
a
n
al
y
s
is
.
I
n
o
u
r
p
r
ev
io
u
s
s
t
u
d
y
[
1
0
]
,
w
e
ap
p
lied
f
u
zz
y
s
ig
m
a
b
i
n
ar
izatio
n
to
o
v
er
co
m
e
lo
w
b
r
ig
h
t
n
es
s
co
n
tr
ast
b
y
its
ad
ap
tiv
e
th
r
es
h
o
ld
in
g
ch
ar
ac
ter
is
tic.
Ho
w
e
v
e
r
,
it
d
o
es
n
o
t
co
n
s
id
er
th
e
av
er
ag
e
b
r
ig
h
t
n
es
s
n
o
r
m
o
r
p
h
o
lo
g
ical
c
h
ar
ac
ter
is
tic
s
o
f
ce
r
v
ical
v
er
teb
r
ae
th
u
s
its
p
er
f
o
r
m
an
ce
i
s
n
o
t
s
tab
le
esp
ec
iall
y
w
h
e
n
it
f
o
r
m
s
th
e
th
ick
n
es
s
m
ea
s
u
r
in
g
k
e
y
p
o
in
ts
.
I
n
th
is
p
ap
er
,
w
e
p
r
o
p
o
s
e
a
K
-
m
ea
n
s
p
ix
el
clu
s
ter
i
n
g
[
1
1
]
ap
p
r
o
ac
h
to
f
in
d
th
e
k
e
y
p
o
in
ts
ac
cu
r
atel
y
in
d
etec
tin
g
ce
r
v
ical
v
er
teb
r
a
e.
W
ith
s
u
ch
a
clu
s
ter
in
g
ap
p
r
o
ac
h
an
d
s
u
b
s
eq
u
en
t
s
m
ea
r
in
g
tec
h
n
o
lo
g
y
to
r
esto
r
e
lo
s
t
in
f
o
r
m
atio
n
,
o
u
r
s
o
f
t
w
ar
e
is
m
o
r
e
co
n
s
i
s
ten
t
w
i
th
h
u
m
a
n
m
ed
ical
e
x
p
er
ts
’
o
p
i
n
io
n
s
i
n
d
etec
tin
g
ce
r
v
ical
v
er
teb
r
ae
an
d
lo
ca
tin
g
k
e
y
p
o
in
ts
.
2.
P
RO
CE
DUR
E
F
O
R
AUTO
M
AT
I
C
CE
RVI
CAL V
E
R
T
E
B
RAE
E
XT
RACT
I
O
N
Ob
tain
ed
d
ig
ita
l
i
m
ag
e
f
o
ll
o
w
s
DI
C
OM
(
D
ig
i
tal
i
m
a
g
i
n
g
an
d
C
o
m
m
u
n
ica
tio
n
s
i
n
m
ed
ici
n
e)
s
tan
d
ar
d
f
o
r
m
at.
I
n
th
e
m
ai
n
r
eg
io
n
o
f
in
ter
e
s
t
(
R
O
I
)
p
ar
t
o
f
th
e
i
m
ag
e
a
s
s
h
o
w
n
i
n
Fi
g
u
r
e
1
,
th
er
e
w
il
l
b
e
a
b
lo
o
d
v
ess
el
in
b
et
w
ee
n
t
w
o
i
m
p
o
r
tan
t
m
u
s
cle
s
-
th
e
s
te
r
n
o
cleid
o
m
asto
id
(
SC
M)
a
n
d
th
e
d
ee
p
ce
r
v
ical
f
le
x
o
r
s
(
DC
F).
I
ts
lo
w
er
p
ar
t h
as ir
r
eg
u
lar
c
u
r
v
e
d
u
e
to
t
h
e
b
o
r
d
er
lin
e
o
f
ce
r
v
ical
v
er
teb
r
ae
.
T
h
e
ce
r
v
ical
v
er
teb
r
ae
ar
ea
in
th
e
u
ltra
s
o
n
o
g
r
ap
h
y
is
s
h
o
wn
as
b
r
ig
h
t
r
eg
io
n
u
n
d
er
DC
F
s
in
ce
t
h
e
ar
ea
h
as
h
i
g
h
d
en
s
it
y
.
I
n
o
r
d
er
to
d
etec
t
ce
r
v
ical
v
er
teb
r
ae
,
h
o
w
ev
er
,
w
e
n
ee
d
to
r
e
m
o
v
e
o
th
er
o
r
g
an
s
u
ch
as
ca
r
tilag
e
a
n
d
s
u
b
cu
ta
n
eo
u
s
f
at
ar
ea
as
n
o
is
e
t
h
at
a
ls
o
h
av
e
r
elati
v
el
y
h
ig
h
b
r
i
g
h
t
n
es
s
.
T
h
u
s
,
w
e
n
ee
d
b
r
ig
h
t
n
es
s
en
h
an
ce
m
e
n
t p
r
o
ce
d
u
r
e
an
d
s
u
b
s
eq
u
en
t
n
o
is
e
r
e
m
o
v
al/
i
m
a
g
e
r
esto
r
atio
n
p
r
o
ce
s
s
.
Fig
u
r
e
1
.
R
OI
o
f
Ultr
aso
u
n
d
I
m
ag
e
3.
C
E
RV
I
CA
L
VE
R
T
E
B
RAE
DE
T
E
C
T
I
O
N
W
I
T
H
K
-
M
E
ANS
P
I
X
E
L
C
L
US
T
E
RIN
G
I
n
o
r
d
er
to
ex
tr
ac
t
th
e
ce
r
v
ical
v
er
teb
r
ae
o
b
j
ec
t
f
r
o
m
t
h
e
u
ltr
aso
u
n
d
i
m
ag
e,
w
e
s
h
o
u
ld
f
i
n
d
th
e
lo
w
er
b
o
u
n
d
o
f
D
C
F a
r
ea
t
h
at
i
s
t
h
e
u
p
p
er
b
o
u
n
d
o
f
t
h
e
ce
r
v
ica
l v
e
r
teb
r
ae
ex
is
ten
ce
.
On
ce
th
e
r
a
n
g
e
o
f
tar
g
et
o
b
j
ec
t
ex
is
te
n
ce
is
d
ec
id
ed
,
w
e
cl
u
s
ter
p
ix
els
w
it
h
K
-
m
ea
n
s
alg
o
r
ith
m
to
f
o
r
m
th
e
ce
r
v
ical
v
e
r
teb
r
ae
o
b
j
ec
t
w
it
h
r
esp
ec
t to
th
e
m
o
r
p
h
o
lo
g
ica
l li
m
itatio
n
s
s
u
ch
as
lo
n
g
o
v
al
s
h
ap
in
g
.
D
u
r
i
n
g
s
u
c
h
i
m
ag
e
p
r
o
ce
s
s
i
n
g
s
tep
s
,
th
er
e
ca
n
b
e
s
o
m
e
i
n
f
o
r
m
atio
n
lo
s
s
w
h
ic
h
m
i
g
h
t
ca
u
s
e
u
n
d
es
ir
ed
d
is
co
n
n
ec
t
io
n
s
o
f
t
h
e
o
b
j
e
cts
f
o
r
m
ed
b
y
K
-
m
ea
n
s
clu
s
ter
i
n
g
.
T
h
u
s
,
w
e
ap
p
l
y
i
m
ag
e
r
es
to
r
atio
n
p
r
o
ce
s
s
b
y
S
m
ea
r
i
n
g
al
g
o
r
ith
m
to
f
i
n
ali
ze
th
e
ex
tr
ac
tio
n
o
f
ce
r
v
ical
v
er
teb
r
ae
.
3
.
1
.
L
o
ca
t
ing
t
he
Cer
v
ica
l V
er
t
ebra
e
Ca
nd
ida
t
e
O
bje
ct
Fro
m
th
i
s
R
OI
i
m
a
g
e
th
at
co
n
tai
n
s
o
n
l
y
m
u
s
cles,
f
asciae
an
d
s
p
in
es,
w
e
tr
y
to
ex
tr
ac
t
ca
n
d
id
ate
DC
F
b
y
ap
p
l
y
i
n
g
a
s
er
ies
o
f
i
m
ag
e
p
r
o
ce
s
s
in
g
al
g
o
r
ith
m
s
.
T
h
e
f
ir
s
t
s
tep
i
s
a
n
o
r
m
aliza
ti
o
n
p
r
o
ce
s
s
k
n
o
w
n
a
s
th
e
E
n
d
s
-
i
n
Stre
tc
h
in
g
to
th
e
i
m
ag
e
p
r
o
ce
s
s
i
n
g
co
m
m
u
n
it
y
[
1
2
]
.
T
h
at
s
tr
etch
i
n
g
e
n
h
an
ce
s
t
h
e
in
te
n
s
it
y
co
n
tr
ast
to
d
i
f
f
er
e
n
tiate
t
h
e
tar
g
et
a
n
d
th
e
b
ac
k
g
r
o
u
n
d
ar
ea
m
o
r
e
c
lear
l
y
.
Fo
r
m
u
la
(
1
)
ex
p
lain
s
E
n
d
s
-
i
n
s
ea
r
c
h
s
tr
etch
i
n
g
.
M
a
x
y
x
P
M
a
x
y
x
P
M
i
n
M
i
n
y
x
P
M
i
n
M
a
x
M
i
n
y
x
P
y
x
C
)
,
(
)
,
(
)
,
(
255
)
,
(
255
0
)
,
(
(
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
E
ffective
C
o
mp
u
ter
-
A
s
s
i
s
ted
A
u
to
ma
tic
C
ervica
l V
erteb
r
a
e
E
xtra
ctio
n
w
ith
…
(
Ha
e
-
Ju
n
g
Lee
)
2812
w
h
er
e
M
in
an
d
Ma
x
d
en
o
te
t
h
e
m
a
x
i
m
u
m
a
n
d
m
i
n
i
m
u
m
i
n
ten
s
it
y
v
al
u
e
o
f
t
h
e
g
i
v
en
i
m
ag
e
a
n
d
P
(
x
,
y
)
is
th
e
in
te
n
s
i
t
y
v
al
u
e
o
f
th
e
p
i
x
el
at
(
x
,
y
)
co
o
r
d
in
ates
in
t
h
e
o
r
ig
i
n
al
i
m
ag
e
a
n
d
C
(
x
,
y
)
is
th
e
r
esu
l
tan
t
in
te
n
s
it
y
v
alu
e
a
f
ter
E
n
d
s
-
i
n
s
ea
r
ch
s
tr
etc
h
i
n
g
.
S
u
c
h
n
o
r
m
aliza
tio
n
p
r
o
ce
s
s
is
n
ec
es
s
a
r
y
to
m
i
n
i
m
ize
t
h
e
in
f
o
r
m
atio
n
lo
s
s
s
i
n
ce
t
h
er
e
m
ig
h
t b
e
a
b
lu
r
r
in
g
d
u
e
to
t
h
e
s
c
atter
in
g
ef
f
ec
t o
f
u
ltra
s
o
u
n
d
te
ch
n
iq
u
e.
Fro
m
th
at
co
n
tr
a
s
t
-
e
n
h
an
ce
d
i
m
ag
e,
w
e
ap
p
l
y
av
er
a
g
e
b
in
ar
izatio
n
a
n
d
B
lo
b
alg
o
r
ith
m
[
1
3
]
to
r
e
m
o
v
e
u
n
n
ec
e
s
s
ar
y
n
o
is
e
in
d
etec
tin
g
D
C
F
m
u
s
cle
ar
ea
.
T
h
e
B
l
o
b
alg
o
r
ith
m
w
e
ad
o
p
ted
ca
n
b
e
s
u
m
m
ar
ized
as f
o
llo
w
s
;
G
iv
en
B
in
ar
y
I
m
a
g
e
L
et
t
h
e
in
itial C
o
lo
r
[
k
]
=0
Ste
p 1
Scan
th
e
o
r
ig
i
n
al
i
m
ag
e
f
r
o
m
lef
t
to
r
ig
h
t
an
d
to
p
to
b
o
tto
m
(
r
aster
Sca
n
)
u
s
i
n
g
L
-
Sh
ap
e
te
m
p
late
Fo
r
k
=I
m
a
g
e
Size
if
I
m
a
g
e[
C
]
=2
5
5
th
en
if
I
m
a
g
e[
U]
=2
5
5
an
d
I
m
a
g
e[
L
]
=0
th
en
C
o
lo
r
[
C
]
=Co
lo
r
[
U]
if
I
m
a
g
e[
U]
=0
an
d
I
m
a
g
e[
L
]
=
2
5
5
th
en
C
o
lo
r
[
C
]
=Co
lo
r
[
L
]
if
I
m
a
g
e[
U]
=0
an
d
I
m
a
g
e[
L
]
=
0
th
en
C
o
lo
r
[
C
]
=K
++
,
n
e
w
C
o
lo
r
if
I
m
a
g
e[
U]
=2
5
5
an
d
I
m
a
g
e[
L
]
=2
5
5
th
en
if
C
o
lo
r
[
U]
is
n
o
t e
q
u
al
C
o
lo
r
[
L
]
th
e
n
R
eCo
lo
r
in
g
T
ab
le
C
o
lo
r
[
C
]
=
C
o
lo
r
[
L
]
r
ep
ea
t
Ste
p 2
Fo
r
co
u
n
t=k
C
o
lo
r
[
co
u
n
t]
=Re
C
o
lo
r
in
g
[
C
o
l
o
r
[
co
u
n
t]
]
r
ep
ea
t
w
h
er
e
U,
C
,
L
d
e
n
o
te
Up
,
C
en
ter
,
L
ef
t i
n
r
esp
ec
ti
v
el
y
.
A
b
lo
b
is
a
r
eg
io
n
o
f
a
n
i
m
a
g
e
in
w
h
ic
h
s
o
m
e
p
r
o
p
er
ties
ar
e
co
n
s
ta
n
t o
r
ap
p
r
o
x
i
m
atel
y
co
n
s
tan
t.
T
h
e
p
ix
els
i
n
a
b
lo
b
h
av
e
th
e
s
a
m
e
q
u
an
tized
co
lo
r
alth
o
u
g
h
t
h
e
y
m
a
y
h
av
e
d
i
f
f
er
en
t
co
lo
r
s
in
t
h
e
o
r
ig
i
n
al
i
m
a
g
e.
T
h
u
s
,
u
s
i
n
g
t
h
is
alg
o
r
it
h
m
,
w
e
ca
n
f
o
r
m
a
s
i
m
i
lar
l
y
co
lo
r
ed
o
b
j
ec
t
r
eg
io
n
s
an
d
t
h
e
n
r
e
m
o
v
e
u
n
n
ec
ess
ar
y
o
b
j
ec
ts
f
r
o
m
o
u
r
i
n
ter
es
t.
Fo
r
ex
a
m
p
le,
w
e
k
n
o
w
th
a
t o
u
r
tar
g
et
D
C
F
is
s
u
f
f
ic
ien
t
l
y
lo
n
g
i
n
th
e
o
r
ig
i
n
al
i
m
a
g
e
th
u
s
th
e
ar
ea
o
f
f
o
r
m
ed
o
b
j
ec
t
is
to
o
s
m
al
l
o
r
th
e
len
g
th
is
le
s
s
th
a
n
t
h
e
h
al
f
o
f
th
e
i
m
a
g
e
w
id
t
h
,
th
at
o
b
j
ec
t
is
u
n
n
ec
es
s
ar
y
i
n
o
u
r
i
m
ag
e
a
n
al
y
s
i
s
th
u
s
r
e
m
o
v
e
s
u
c
h
o
b
j
ec
ts
.
T
h
e
ef
f
ec
t o
f
t
h
i
s
B
lo
b
ap
p
lic
atio
n
ca
n
b
e
s
h
o
w
n
as
Fig
u
r
e
3
(
b
)
f
r
o
m
t
h
e
co
n
tr
a
s
t e
n
h
an
ce
d
i
m
a
g
e
s
h
o
w
n
as F
ig
u
r
e
2
(
a)
.
(
a)
E
n
d
s
-
i
n
Sear
ch
Stre
tch
i
n
g
(
b
)
A
v
er
ag
e
B
i
n
aiza
tio
n
&
B
lo
b
R
e
m
o
v
i
n
g
(
c)
E
x
tr
ac
tin
g
B
lo
o
d
Vess
el
(
d
)
DC
F
C
an
d
id
ate
Fig
u
r
e
2
.
P
r
o
ce
s
s
f
o
r
L
o
c
atin
g
DC
F
C
a
n
d
id
ate
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
:
2
8
1
0
–
2
8
1
7
2813
T
h
en
ex
tr
ac
tin
g
th
e
b
lo
o
d
v
ess
el
is
ea
s
y
s
i
n
ce
t
h
at
h
as
r
elat
iv
el
y
lo
w
i
n
ten
s
it
y
a
n
d
a
s
ig
n
if
ica
n
t
b
u
t
al
m
o
s
t
u
n
i
f
o
r
m
t
h
i
c
k
n
ess
a
s
s
h
o
w
n
in
Fi
g
u
r
e
2
(
c)
.
T
h
en
w
e
k
n
o
w
t
h
at
th
e
D
C
F
ar
ea
i
s
lo
ca
ted
b
elo
w
t
h
e
b
lo
o
d
v
ess
el
as s
h
o
w
n
i
n
Fi
g
u
r
e
2
(
d
)
.
T
h
en
,
o
u
r
tar
g
et
o
b
j
ec
t,
ce
r
v
ical
v
er
teb
r
ae
,
is
b
elo
w
t
h
e
lo
w
er
f
ascia
b
o
u
n
d
ar
y
li
n
es
a
n
d
h
as
a
lo
n
g
cu
r
v
ed
s
h
ap
e.
T
h
u
s
,
w
e
tr
y
t
o
f
in
d
t
h
e
r
o
u
g
h
r
an
g
e
o
f
tar
g
et
o
b
j
ec
t’
s
e
x
is
te
n
ce
b
y
s
ea
r
ch
in
g
a
n
o
b
j
ec
t
o
f
s
ig
n
i
f
ica
n
t
s
ize
f
r
o
m
t
h
e
b
o
tto
m
a
n
d
f
r
o
m
t
h
e
to
p
af
ter
r
em
o
v
i
n
g
b
lo
o
d
v
ess
el
an
d
DC
F
o
b
j
ec
t
f
r
o
m
th
e
i
m
a
g
e.
T
h
en
th
e
r
an
g
e
o
f
C
er
v
ical
v
er
teb
r
ae
’
s
e
x
is
ten
ce
i
s
g
i
v
en
a
s
Fi
g
u
r
e
3
(b
).
(
a)
L
o
w
er
b
o
u
n
d
ar
y
o
f
DC
F
(
b
)
R
an
g
e
s
ea
r
c
h
Fig
u
r
e
3
.
R
an
g
e
o
f
C
er
v
ical
V
er
teb
r
ae
C
an
d
id
ate
E
x
is
te
n
c
e
3
.
2
.
P
ix
el
Clus
t
er
ing
by
K
-
m
ea
ns
w
it
h
M
o
rpho
lo
g
ica
l In
f
o
r
m
a
t
io
n
W
ith
in
t
h
e
r
an
g
e
o
f
tar
g
et
o
b
ject
ex
i
s
ten
ce
,
w
e
tr
y
to
ap
p
l
y
p
ix
el
cl
u
s
ter
i
n
g
.
K
-
m
ea
n
s
cl
u
s
ter
in
g
is
a
w
ell
-
k
n
o
w
n
u
n
s
u
p
er
v
is
ed
lear
n
in
g
al
g
o
r
ith
m
t
h
at
h
a
s
m
a
n
y
v
ar
ian
t
s
w
it
h
r
esp
ec
t
to
th
e
ap
p
licatio
n
an
d
w
e
f
o
llo
w
a
s
p
ee
d
u
p
v
er
s
io
n
o
f
it
[
1
1
]
.
B
eg
in
I
n
itialize
n
,
k
,
μ
1
,
μ
2
,
…
,
μ
k
Do
class
i
f
y
n
s
a
m
p
les ac
co
r
d
in
g
to
n
ea
r
est
μ
i
r
ec
o
m
p
u
te
μ
i
Unt
il
n
o
ch
a
n
g
e
in
μ
i
Ret
urn
μ
1
,
μ
2
,
…,
μ
k
E
nd
T
h
e
p
r
in
cip
le
o
f
K
-
m
ea
n
s
is
as
s
i
m
p
le
as
ab
o
v
e
d
escr
ip
t
io
n
.
Fro
m
ar
b
itra
r
il
y
g
i
v
en
k
s
ets,
th
e
alg
o
r
ith
m
iter
ati
v
el
y
r
e
-
as
s
i
g
n
s
th
e
d
ata
s
ets
ac
co
r
d
in
g
to
th
e
ce
n
ter
p
o
in
t
an
d
r
e
-
co
m
p
u
tes
ce
n
ter
p
o
in
ts
a
t
ev
er
y
iter
atio
n
u
n
til
t
h
er
e
is
n
o
s
ig
n
i
f
ica
n
t
c
h
an
g
e.
I
n
o
u
r
e
x
p
er
i
m
e
n
t
k
is
g
iv
e
n
as
6
.
An
d
th
e
ef
f
ec
t
o
f
K
-
m
ea
n
s
ca
n
b
e
s
h
o
w
n
a
s
Fi
g
u
r
e
4
.
Fig
u
r
e
4
.
T
h
e
E
ffe
ct
o
f
K
-
M
ea
n
s
P
ix
el
C
l
u
s
ter
i
n
g
T
h
e
n
ex
t
s
tep
is
to
e
x
tr
ac
t
m
e
an
in
g
f
u
l
o
b
j
ec
ts
b
y
lo
ca
l
r
e
g
i
o
n
lab
elin
g
p
r
o
ce
d
u
r
e.
Sin
ce
t
h
e
ce
r
v
ica
l
v
er
teb
r
ae
ar
ea
is
r
elati
v
el
y
b
r
ig
h
t,
w
e
ap
p
l
y
th
e
lab
elin
g
t
o
o
n
l
y
h
i
g
h
l
y
b
r
ig
h
t
cl
u
s
ter
s
.
T
h
e
r
esu
lt
o
f
t
h
i
s
lab
elin
g
p
r
o
ce
d
u
r
e
is
s
h
o
w
n
a
s
Fig
u
r
e
5
.
I
n
Fi
g
u
r
e
5
,
t
h
e
e
x
tr
ac
ted
o
b
jects
co
n
tai
n
n
o
is
e
s
s
u
ch
as
ca
r
tilag
e
a
n
d
s
u
b
cu
ta
n
eo
u
s
f
a
t.
I
n
o
r
d
er
to
r
e
m
o
v
e
s
u
ch
n
o
i
s
e
o
b
j
ec
ts
,
w
e
test
th
e
cir
cle
r
ate
an
d
ex
ten
s
io
n
r
ate
o
f
o
b
j
ec
ts
in
co
n
s
id
er
ati
o
n
.
Fo
r
m
u
la
(
2
)
ex
p
lain
s
s
u
c
h
s
h
ap
e
p
ar
a
m
eter
s
.
T
h
e
s
h
ap
e
o
f
ce
r
v
ical
v
er
te
b
r
ae
is
lo
n
g
c
u
r
v
e
w
it
h
r
elati
v
el
y
co
n
s
is
te
n
t
f
o
r
m
w
h
ile
o
t
h
er
n
o
is
es
h
a
v
e
ir
r
e
g
u
lar
s
h
ap
es
t
h
u
s
s
u
c
h
m
o
r
p
h
o
lo
g
ical
c
h
ar
ac
ter
is
t
ics
ca
n
d
is
cr
i
m
i
n
ate
tar
g
et
o
b
j
ec
ts
f
r
o
m
n
o
i
s
es
w
it
h
m
ea
s
u
r
e
m
e
n
ts
e
x
p
lai
n
ed
in
f
o
r
m
u
la
(
2
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
E
ffective
C
o
mp
u
ter
-
A
s
s
i
s
ted
A
u
to
ma
tic
C
ervica
l V
erteb
r
a
e
E
xtra
ctio
n
w
ith
…
(
Ha
e
-
Ju
n
g
Lee
)
2814
Fig
u
r
e
5
.
Af
ter
L
ab
eli
n
g
P
r
o
c
e
d
u
r
e
H
e
i
g
h
t
H
e
i
g
h
t
W
i
d
t
h
E
A
P
C
,
4
2
(
2
)
As
s
h
o
w
n
i
n
f
o
r
m
u
la
(
2
)
,
th
e
cir
cle
r
ate
C
is
d
ef
in
ed
as
1
if
th
e
o
b
j
ec
t
is
a
p
er
f
ec
t
cir
cle
an
d
it
b
ec
o
m
e
s
m
o
r
e
th
a
n
1
if
th
e
o
b
j
ec
t
is
co
m
p
lex
s
in
ce
t
h
e
cir
cu
m
f
er
en
ce
(
P
)
b
ec
o
m
es
lar
g
er
.
A
is
th
e
ar
ea
o
f
th
e
r
eg
io
n
in
t
h
i
s
f
o
r
m
u
la.
T
h
e
ex
ten
s
io
n
r
ate
(
E
)
d
en
o
tes
th
e
r
ate
o
f
th
e
d
if
f
er
en
ce
b
et
w
ee
n
th
e
w
id
t
h
an
d
th
e
h
eig
h
t
d
iv
id
ed
b
y
th
e
h
ei
g
h
t
f
o
r
th
e
m
i
n
i
m
u
m
q
u
ad
r
a
n
g
le
th
at
in
c
lu
d
es
t
h
e
o
b
j
ec
t.
E
b
e
co
m
e
s
0
w
h
en
t
h
e
q
u
ad
r
an
g
le
is
a
s
q
u
ar
e
(
o
r
a
cir
cle
o
f
co
u
r
s
e)
.
A
n
y
n
o
n
-
ze
r
o
E
r
ep
r
esen
ts
th
e
d
ir
ec
tio
n
an
d
th
e
d
eg
r
ee
o
f
u
n
b
ala
n
ce
o
f
t
h
e
o
b
j
ec
t th
u
s
it
h
elp
s
to
f
i
g
u
r
e
o
u
t th
e
n
o
is
e
to
b
e
r
em
o
v
ed
.
T
h
e
ef
f
ec
t o
f
n
o
is
e
r
e
m
o
v
al
is
s
h
o
w
n
a
s
Fi
g
u
r
e
6
.
⇩
Fig
u
r
e
6
.
No
is
e
R
e
m
o
v
ed
3
.
3
.
Cer
v
ic
a
l V
er
t
ebra
e
O
bj
ec
t
Rest
o
ra
t
io
n by
S
m
ea
ring
T
h
e
r
esu
ltan
t
i
m
a
g
e
m
a
y
h
a
v
e
lo
s
t
in
f
o
r
m
atio
n
d
u
r
i
n
g
t
h
e
n
o
is
e
r
e
m
o
v
al
p
r
o
ce
s
s
s
o
t
h
at
t
h
e
lab
elled
o
b
j
ec
ts
ar
e
v
er
y
clo
s
e
b
u
t
d
is
c
o
n
n
ec
ted
.
T
h
e
h
o
r
izo
n
tal
s
m
e
ar
in
g
p
r
o
ce
s
s
[
1
3
]
is
ap
p
lied
t
o
co
m
p
en
s
ate
s
u
c
h
in
f
o
r
m
atio
n
lo
s
s
to
o
b
tai
n
t
h
e
f
in
al
o
u
tp
u
t
i
m
ag
e
f
o
r
e
x
tr
ac
ti
n
g
ce
r
v
ical
v
er
teb
r
ae
w
it
h
r
ec
o
n
n
ec
ti
n
g
p
r
o
ce
d
u
r
e
.
I
n
th
e
p
r
o
ce
s
s
m
o
r
p
h
o
lo
g
ical
o
p
er
ato
r
s
[
1
3
]
ar
e
ap
p
lied
f
o
r
i
m
a
g
e
s
m
o
o
t
h
in
g
an
d
r
esto
r
atio
n
a
n
d
th
e
r
esu
lt c
an
b
e
s
h
o
w
n
a
s
Fi
g
u
r
e
7
.
(
a)
Dis
co
n
n
ec
ted
C
er
v
ical
Ver
teb
r
ae
(
b
)
I
m
ag
e
R
es
to
r
atio
n
Fig
u
r
e
7
.
C
er
v
ical
Ver
teb
r
ae
I
m
ag
e
R
esto
r
atio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
:
2
8
1
0
–
2
8
1
7
2815
4.
E
XP
E
R
I
M
E
NT
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
is
i
m
p
le
m
en
ted
w
it
h
C
++
u
n
d
er
Mic
r
o
s
o
f
t
Vis
u
al
St
u
d
io
2
0
1
0
o
n
th
e
I
B
M
-
co
m
p
atib
le
P
C
w
it
h
I
n
te
l(
R
)
C
o
r
e(
T
M)
T
-
4
2
0
0
C
P
U
@
3
.
4
0
GHz
an
d
2
GB
R
A
M.
T
h
e
ex
p
er
i
m
e
n
t
u
s
e
s
f
i
f
t
y
t
w
o
8
0
0
x
6
0
0
s
ize
DI
C
O
M
f
o
r
m
at
li
n
ea
r
u
ltra
s
o
u
n
d
i
m
ag
es
T
h
e
ac
cu
r
ac
y
o
f
t
h
e
m
et
h
o
d
o
r
th
e
u
til
it
y
o
f
th
e
au
to
m
atic
v
is
io
n
b
ased
ce
r
v
ical
v
er
teb
r
ae
an
al
y
ze
r
ca
n
b
e
m
ea
s
u
r
ed
b
y
th
e
a
g
r
ee
m
en
t
r
ate
o
f
lo
ca
ti
n
g
D
C
F
m
u
s
cle
th
ic
k
n
es
s
m
ea
s
u
r
i
n
g
k
e
y
p
o
in
ts
w
it
h
h
u
m
a
n
ex
p
er
ts
–
p
h
y
s
ical
th
er
ap
is
ts
.
I
n
o
r
d
er
to
av
o
id
h
u
m
a
n
s
u
b
j
ec
tiv
it
y
,
o
u
r
g
r
o
u
n
d
tr
u
t
h
s
o
f
m
e
asu
r
i
n
g
p
o
in
ts
ar
e
o
b
tain
ed
b
y
t
w
o
p
h
y
s
ical
t
h
e
r
ap
is
ts
’
ag
r
ee
m
e
n
ts
.
E
x
tr
ac
ti
n
g
ce
r
v
ical
v
er
teb
r
ae
w
h
ic
h
i
s
th
e
th
e
m
e
o
f
t
h
is
p
ap
er
is
r
eq
u
ir
ed
in
o
r
d
er
to
an
al
y
ze
t
h
o
s
e
i
m
p
o
r
tan
t
m
u
s
cle
s
(
DC
F a
n
d
S
C
M)
f
o
r
n
ec
k
p
a
in
m
a
n
ag
e
m
e
n
t.
As
d
escr
ib
ed
in
T
a
b
le
1
,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
s
h
o
w
ed
9
6
%
ag
r
ee
m
e
n
t
r
ate
w
it
h
m
u
lt
ip
le
h
u
m
a
n
ex
p
er
ts
’
ag
r
ee
m
e
n
ts
.
T
ab
le
1
.
Mu
s
cle
T
h
ick
n
e
s
s
M
ea
s
u
r
i
n
g
K
e
y
P
o
in
ts
E
x
tr
ac
tio
n
P
r
o
p
o
se
d
M
e
t
h
o
d
K
e
y
P
o
i
n
t
s
4
8
/
5
0
(
9
6
%
)
I
n
o
u
r
p
r
o
p
o
s
ed
m
eth
o
d
,
k
e
y
p
o
in
t
is
s
et
to
b
e
th
e
lo
w
e
s
t
p
o
in
t
o
f
t
h
e
f
ir
s
t
ce
r
v
ical
v
er
te
b
r
ae
o
b
j
ec
t
an
d
th
e
r
a
n
g
e
o
f
m
ea
s
u
r
e
m
e
n
t
is
w
it
h
in
1
c
m
le
f
t
a
n
d
r
ig
h
t
o
f
t
h
at
k
e
y
p
o
in
t.
T
h
e
th
ick
n
e
s
s
o
f
t
h
e
DC
F
m
u
s
cle
is
t
h
e
n
co
m
p
u
ted
as th
e
av
er
ag
e
le
n
g
t
h
o
f
v
er
tical
li
n
es
w
ith
in
t
h
at
m
ea
s
u
r
in
g
r
an
g
e
.
I
n
o
u
r
p
r
e
v
io
u
s
atte
m
p
t
[
1
0
]
,
w
e
u
s
ed
f
u
zz
y
s
i
g
m
a
b
in
ar
izat
io
n
to
co
n
tr
o
l
lo
w
b
r
i
g
h
t
n
es
s
co
n
tr
ast
b
y
its
ad
ap
tiv
e
th
r
es
h
o
ld
in
g
c
h
ar
ac
ter
is
tic
i
n
s
tead
o
f
K
-
m
ea
n
s
p
ix
el
cl
u
s
ter
i
n
g
t
h
at
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
o
f
f
er
s
.
Ho
w
e
v
er
,
th
e
p
r
ev
io
u
s
ap
p
r
o
ac
h
d
o
es
n
o
t
co
n
s
id
er
t
h
e
av
er
ag
e
b
r
ig
h
tn
e
s
s
n
o
r
m
o
r
p
h
o
lo
g
ical
ch
ar
ac
ter
is
tic
s
o
f
ce
r
v
ical
v
er
teb
r
ae
th
u
s
its
p
er
f
o
r
m
a
n
ce
is
n
o
t
s
tab
le
esp
e
ciall
y
w
h
e
n
it
f
o
r
m
s
t
h
e
t
h
ic
k
n
es
s
m
ea
s
u
r
in
g
k
e
y
p
o
in
ts
.
T
h
u
s
,
th
e
p
r
o
p
o
s
ed
m
e
th
o
d
u
ti
l
izes
m
o
r
p
h
o
lo
g
ical
i
n
f
o
r
m
atio
n
o
f
ce
r
v
ical
v
er
teb
r
a
e
in
n
o
is
e
r
e
m
o
v
a
l
p
r
o
ce
s
s
.
Fig
u
r
e
8
s
h
o
w
s
t
h
e
d
if
f
er
en
ce
o
f
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
an
d
p
r
ev
io
u
s
a
tte
m
p
t
[
1
0
]
in
d
etec
ti
n
g
m
ea
s
u
r
in
g
k
e
y
p
o
in
t
s
.
(
a)
E
x
tr
ac
tin
g
C
er
v
ica
l V
er
t
eb
r
ae
[
1
0
]
(
b
)
E
x
tr
ac
tin
g
C
er
v
ical
Ve
r
teb
r
ae
(
P
r
o
p
o
s
ed
)
(
a)
Key
P
o
in
ts
[
1
0
]
(
b
)
Key
P
o
i
n
t (
P
r
o
p
o
s
ed
)
Fig
u
r
e
8
.
P
er
f
o
r
m
a
n
ce
Co
m
p
a
r
is
o
n
As
s
h
o
w
n
i
n
Fi
g
u
r
e
9
,
th
e
r
esu
lt
s
f
r
o
m
t
h
e
p
r
o
p
o
s
ed
m
e
th
o
d
is
co
n
s
is
te
n
t
w
it
h
t
h
o
s
e
o
f
h
u
m
a
n
ex
p
er
ts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
E
ffective
C
o
mp
u
ter
-
A
s
s
i
s
ted
A
u
to
ma
tic
C
ervica
l V
erteb
r
a
e
E
xtra
ctio
n
w
ith
…
(
Ha
e
-
Ju
n
g
Lee
)
2816
(
a)
Ma
n
u
al
Ke
y
P
o
in
t
De
tecti
o
n
(
b
)
P
r
o
p
o
s
ed
Me
th
o
d
Fig
u
r
e
9
.
P
er
f
o
r
m
a
n
ce
co
m
p
ar
is
o
n
2
: H
u
m
a
n
ex
p
er
ts
v
s
P
r
o
p
o
s
ed
m
et
h
o
d
5.
CO
NCLU
SI
O
N
I
n
th
i
s
p
ap
er
,
w
e
p
r
o
p
o
s
e
a
m
et
h
o
d
to
ex
tr
ac
t
ce
r
v
ical
v
er
teb
r
ae
au
to
m
atica
ll
y
b
y
u
s
i
n
g
v
ar
io
u
s
i
m
a
g
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
e
s
an
d
K
-
m
ea
n
s
p
ix
el
clu
s
ter
in
g
to
f
o
r
m
t
h
e
tar
g
et
ce
r
v
ical
v
er
teb
r
ae
o
b
j
ec
t
f
r
o
m
u
ltra
s
o
n
o
g
r
ap
h
y
.
Fo
r
tech
n
ic
al
co
n
ce
r
n
s
,
o
u
r
m
et
h
o
d
c
o
n
s
is
t
s
o
f
th
r
ee
p
ar
ts
in
th
i
s
au
to
m
at
ic
ex
tr
ac
tio
n
.
Firstl
y
,
w
e
s
h
o
u
ld
f
i
n
d
t
h
e
l
o
w
er
b
o
u
n
d
o
f
D
C
F
ar
ea
th
at
is
th
e
u
p
p
er
b
o
u
n
d
o
f
t
h
e
ce
r
v
ical
v
er
teb
r
ae
ex
is
te
n
ce
.
I
n
th
i
s
p
ar
t,
w
e
ap
p
ly
a
v
er
ag
e
b
in
ar
izatio
n
an
d
B
lo
b
alg
o
r
ith
m
f
r
o
m
i
n
ten
s
it
y
en
h
a
n
ce
d
i
m
a
g
e
to
r
e
m
o
v
e
u
n
n
ec
es
s
ar
y
p
ar
t
an
d
lo
ca
te
o
n
l
y
th
e
r
e
g
io
n
t
h
at
t
h
e
tar
g
et
o
b
j
ec
t
ca
n
ap
p
ea
r
.
On
ce
th
e
r
an
g
e
o
f
tar
g
e
t
o
b
j
ec
t
ex
is
ten
ce
i
s
d
ec
id
ed
,
w
e
clu
s
ter
p
ix
el
s
w
ith
K
-
m
ea
n
s
alg
o
r
ith
m
to
f
o
r
m
th
e
ce
r
v
ic
al
v
er
teb
r
ae
o
b
j
ec
t
w
it
h
r
esp
ec
t
to
th
e
m
o
r
p
h
o
lo
g
ic
al
li
m
itat
io
n
s
s
u
c
h
as
lo
n
g
o
v
al
s
h
ap
i
n
g
.
L
a
s
tl
y
,
w
e
ap
p
ly
i
m
ag
e
r
esto
r
atio
n
p
r
o
ce
s
s
b
y
S
m
ea
r
in
g
alg
o
r
it
h
m
to
co
m
p
e
n
s
ate
p
o
s
s
ib
le
o
b
j
ec
t
d
is
co
n
n
ec
tio
n
o
r
o
th
er
in
f
o
r
m
atio
n
lo
s
s
th
a
t
w
a
s
ca
u
s
ed
f
r
o
m
p
r
ev
io
u
s
i
m
a
g
e
p
r
o
ce
s
s
in
g
s
tep
s
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
is
ev
al
u
ated
b
y
th
e
ag
r
ee
m
e
n
t
r
ate
w
it
h
h
u
m
a
n
ex
p
er
ts
in
lo
ca
tin
g
m
ea
s
u
r
i
n
g
k
e
y
p
o
in
t
s
f
o
r
r
elate
d
m
u
s
cle
an
al
y
s
is
.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
w
a
s
s
u
cc
ess
f
u
l
i
n
4
8
o
u
t
if
5
0
test
ca
s
es.
Ho
w
e
v
er
,
as sh
o
w
n
i
n
Fi
g
u
r
e
1
0
,
tw
o
ca
s
e
s
ar
e
f
ailed
d
u
e
to
i
m
p
er
f
ec
t
n
o
is
e
r
e
m
o
v
al.
(
a)
No
is
e
R
e
m
o
v
al
Failed
(
b
)
Ov
er
lap
p
ed
O
b
j
ec
ts
Fig
u
r
e
1
0
.
Failed
C
er
v
ical
Ver
teb
r
ae
E
x
tr
a
ctio
n
I
n
ca
s
e
Fig
u
r
e
1
0
(
a)
,
th
e
f
als
e
p
o
s
itiv
e
n
o
is
e
w
as
n
o
t
r
e
m
o
v
ed
s
in
ce
it
h
as
s
i
g
n
i
f
ica
n
t
s
ize
an
d
i
n
Fig
u
r
e
1
0
(
b
)
,
ce
r
v
ical
v
er
teb
r
ae
o
b
j
ec
ts
ar
e
n
o
t
s
ep
ar
ated
d
u
e
to
in
co
r
r
ec
t
r
e
m
o
v
al
o
f
r
elate
d
ca
r
tilag
e
a
n
d
s
u
b
cu
tan
eo
u
s
f
at
ex
p
lai
n
ed
i
n
s
ec
tio
n
3
.
2
.
I
n
o
r
d
e
r
to
o
v
er
co
m
e
s
u
c
h
i
m
p
er
f
ec
tio
n
,
we
m
a
y
n
ee
d
m
o
r
e
co
m
p
le
x
lear
n
i
n
g
p
r
o
ce
d
u
r
e
t
o
d
elim
ita
te
u
n
n
ec
e
s
s
ar
y
o
b
j
ec
ts
f
r
o
m
tar
g
et
o
b
j
ec
t.
Oth
er
w
i
s
e,
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
is
ef
f
ec
ti
v
e
an
d
s
tab
le
w
it
h
r
esp
ec
t to
m
a
n
u
al
d
etec
ti
o
n
o
f
m
ea
s
u
r
i
n
g
k
e
y
p
o
in
ts
f
o
r
r
elate
d
m
u
s
cle
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
:
2
8
1
0
–
2
8
1
7
2817
RE
F
E
R
E
NC
E
S
[1
]
R.
F
e
jer
,
e
t
a
l.
,
“
T
h
e
p
re
v
a
len
c
e
o
f
n
e
c
k
p
a
in
in
th
e
w
o
rld
p
o
p
u
lat
io
n
:
a
sy
ste
m
a
ti
c
c
r
it
ica
l
re
v
i
e
w
o
f
th
e
li
tera
tu
re
”
,
Eu
ro
p
e
a
n
s
p
in
e
jo
u
rn
a
l
,
v
o
l.
15
,
n
o
.
6
,
p
p
.
8
3
4
-
8
4
8
,
2
0
0
6
.
[2
]
D.
F
a
ll
a
a
n
d
D.
F
a
ri
n
a
,
“
Ne
u
ra
l
a
n
d
m
u
sc
u
lar
f
a
c
to
rs
a
ss
o
c
iate
d
w
it
h
m
o
to
r
im
p
a
ir
m
e
n
t
in
n
e
c
k
p
a
in
”
,
C
u
rr
e
n
t
rh
e
u
ma
t
o
lo
g
y
re
p
o
rts
,
v
o
l.
9
,
n
o
.
6
,
p
p
.
4
9
7
-
5
0
2
,
2
0
0
7
.
[3
]
M
.
A
.
M
a
y
o
u
x
-
Be
n
h
a
m
o
u
,
e
t
a
l.
,
“
L
o
n
g
u
s
c
o
ll
i
h
a
s
a
p
o
st
u
ra
l
f
u
n
c
ti
o
n
o
n
c
e
rv
ica
l
c
u
rv
a
tu
re
”
,
S
u
r
g
ica
l
a
n
d
Ra
d
i
o
lo
g
ic A
n
a
t
o
my
,
v
o
l.
16
,
n
o
.
4
,
p
p
.
3
6
7
-
3
7
1
,
1
9
9
4
.
[4
]
A
.
M
id
d
led
it
c
h
a
n
d
J.
Oliv
e
r,
Fu
n
c
ti
o
n
a
l
a
n
a
t
o
my
o
f
th
e
sp
in
e
,
2
n
d
e
d
it
i
o
n
.
C
h
a
p
ter
3
,
Bu
tt
e
rw
o
rth
-
He
in
e
m
a
n
n
,
2
0
0
2
.
[5
]
J.
Ylin
e
n
,
e
t
a
l.
,
“
S
tretc
h
in
g
e
x
e
rc
ise
s
v
s
m
a
n
u
a
l
th
e
ra
p
y
in
tr
e
a
t
m
e
n
t
o
f
c
h
ro
n
ic
n
e
c
k
p
a
in
:
a
ra
n
d
o
m
ize
d
,
c
o
n
tro
ll
e
d
c
ro
ss
-
o
v
e
r
tri
a
l
”
,
J
o
u
rn
a
l
o
f
re
h
a
b
il
it
a
ti
o
n
me
d
icin
e
,
v
o
l
.
39
,
n
o
.
2
,
p
p
.
1
2
6
-
1
3
2
,
2
0
0
7
.
[6
]
É.
Ca
rd
in
a
l
,
e
t
a
l.
,
“
Ro
le
o
f
u
lt
ra
so
u
n
d
in
m
u
sc
u
lo
sk
e
leta
l
in
f
e
c
ti
o
n
s
”
,
Ra
d
io
lo
g
ic
c
li
n
ics
o
f
n
o
rth
A
me
ric
a
,
v
o
l.
39
,
n
o
.
2
,
p
p
.
1
9
1
-
2
0
1
,
2
0
0
1
.
[7
]
R.
J.
M
a
so
n
,
e
t
a
l.
,
M
u
rr
a
y
a
n
d
N
a
d
e
l’s
T
e
x
tb
o
o
k
o
f
re
sp
ira
to
ry
me
d
icin
e
,
5
th
e
d
it
i
o
n
.
Ch
a
p
ter
2
0
,
S
a
u
n
d
e
rs
,
2
0
1
0
.
[8
]
E.
T
.
En
ik
o
v
a
n
d
R.
A
n
to
n
,
“
Im
a
g
e
S
e
g
m
e
n
tatio
n
a
n
d
A
n
a
ly
sis
o
f
F
lex
io
n
-
Ex
ten
sio
n
Ra
d
i
o
g
ra
p
h
s
o
f
Ce
rv
ica
l
S
p
in
e
s
”
,
J
o
u
rn
a
l
o
f
M
e
d
ica
l
En
g
i
n
e
e
rin
g
,
2
0
1
4
.
[9
]
X
.
Xu
,
e
t
a
l.
,
“A
u
to
m
a
ti
c
se
g
m
e
n
tatio
n
o
f
c
e
rv
ica
l
v
e
rteb
ra
e
in
X
-
ra
y
i
m
a
g
e
s
”
,
In
Ne
u
ra
l
Ne
two
rk
s
(
IJ
CNN),
T
h
e
2
0
1
2
I
n
ter
n
a
ti
o
n
a
l
J
o
i
n
t
Co
n
fer
e
n
c
e
o
n
,
p
p
.
1
-
8
,
Ju
n
e
2
0
1
2
.
[1
0
]
K.B.
Kim
,
e
t
a
l.
,
“
Ex
trac
ti
o
n
o
f
S
tern
o
c
leid
o
m
a
sto
id
a
n
d
L
o
n
g
u
s
Ca
p
it
is/Co
l
li
M
u
sc
le
Us
in
g
Ce
rv
ica
l
V
e
rteb
ra
e
Ultras
o
u
n
d
Im
a
g
e
s
”
,
Cu
rr
e
n
t
M
e
d
ica
l
Im
a
g
i
n
g
Rev
iews
,
v
o
l.
10
,
n
o
.
2
,
p
p
.
95
-
1
0
4
,
2
0
1
4
.
[1
1
]
T
.
Hiten
d
ra
S
a
rm
a
,
e
t
a
l.
,
“
A
h
y
b
rid
a
p
p
r
o
a
c
h
t
o
sp
e
e
d
-
u
p
th
e
k
-
m
e
a
n
s
c
lu
ste
rin
g
m
e
th
o
d
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
M
a
c
h
i
n
e
L
e
a
r
n
in
g
a
n
d
Cy
b
e
rn
e
ti
c
s
, v
ol
.
4
,
n
o
.
2
,
p
p
.
1
0
7
-
1
1
7
,
2
0
1
2
.
[1
2
]
E.
Da
v
ies
,
M
a
c
h
in
e
Vi
si
o
n
:
T
h
e
o
ry
,
Al
g
o
rit
h
ms
a
n
d
Pra
c
ti
c
a
li
ti
e
s
,
A
c
a
d
e
m
ic
P
re
ss
,
1
9
9
0
.
[1
3
]
R.
C.
G
o
n
z
a
lez
a
n
d
R.
E.
W
o
o
d
s,
Dig
it
a
l
Ima
g
e
Pro
c
e
ss
in
g
,
T
h
ird
Ed
it
i
o
n
,
P
re
n
ti
c
e
-
Ha
ll
,
2
0
0
7
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
H
a
e
j
u
n
g
Le
e
Ha
e
ju
n
g
L
e
e
is
a
n
a
ss
o
c
iate
p
ro
f
e
ss
o
r
a
t
th
e
d
e
p
a
rtm
e
n
t
o
f
P
h
y
sic
a
l
T
h
e
ra
p
y
in
S
il
la
Un
iv
e
rsity
,
S
o
u
t
h
K
o
re
a
.
S
h
e
f
in
ish
e
d
h
e
r
M
A
p
p
S
c
i
a
n
d
P
h
D
a
t
t
h
e
Un
iv
e
rsity
o
f
S
y
d
n
e
y
,
A
u
stra
li
a
.
He
r
re
se
a
rc
h
in
tere
sts
a
r
e
m
u
sc
u
lo
sk
e
leta
l
c
o
n
d
it
i
o
n
s
f
o
c
u
sin
g
o
n
f
u
n
c
ti
o
n
a
l
a
c
ti
v
it
ies
,
e
sp
e
c
iall
y
n
e
c
k
p
a
in
a
n
d
/
o
r
sh
o
u
l
d
e
r
p
a
i
n
w
it
h
re
late
d
f
u
n
c
ti
o
n
s.
S
h
e
is
c
u
r
re
n
tl
y
a
n
e
d
it
o
rial
m
e
m
b
e
r
f
o
r
th
e
Jo
u
r
n
a
l
o
f
P
h
y
sic
a
l
T
h
e
ra
p
y
S
c
ien
c
e
(Ja
p
a
n
)
a
n
d
W
o
rl
d
Jo
u
rn
a
l
o
f
Orth
o
p
e
d
ics
(Ch
i
n
a
).
Do
o
H
e
o
n
S
o
n
g
Do
o
He
o
n
S
o
n
g
re
c
e
iv
e
d
a
B.
S
.
d
e
g
re
e
in
S
tatisti
c
s
&
Co
m
p
u
ter
S
c
ien
c
e
f
ro
m
S
e
o
u
l
Na
ti
o
n
a
l
Un
iv
e
rsit
y
a
n
d
M
.
S
.
d
e
g
re
e
Co
m
p
u
ter
S
c
ien
c
e
f
ro
m
th
e
Ko
re
a
A
d
v
a
n
c
e
d
In
stit
u
te
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
in
1
9
8
3
.
He
re
c
e
iv
e
d
h
is
P
h
.
D.
Ce
rti
f
ica
te
in
Co
m
p
u
ter
S
c
ien
c
e
f
ro
m
th
e
Un
iv
e
rsit
y
o
f
Ca
li
f
o
rn
ia
in
1
9
9
4
.
F
o
rm
1
9
8
3
-
1
9
8
6
,
h
e
w
a
s
a
re
se
a
rc
h
sc
ien
ti
st
a
t
th
e
Ko
re
a
In
stit
u
te
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
.
He
h
a
s
b
e
e
n
a
p
ro
f
e
ss
o
r
a
t
th
e
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
G
a
m
e
s,
Yo
n
g
-
in
S
o
n
g
d
a
m
Co
ll
e
g
e
,
Ko
re
a
,
sin
c
e
1
9
9
7
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
IT
S
,
m
a
c
h
in
e
lea
rn
in
g
,
a
rti
f
icia
l
in
telli
g
e
n
c
e
,
m
e
d
ica
l
i
m
a
g
e
p
ro
c
e
ss
in
g
,
c
o
g
n
it
iv
e
,
a
n
d
g
a
m
e
in
telli
g
e
n
c
e
.
K
w
a
n
g
B
a
e
k
K
i
m
Kw
a
n
g
Ba
e
k
Ki
m
re
c
e
iv
e
d
h
is
M
.
S
.
a
n
d
P
h
.
D.
d
e
g
re
e
s
f
ro
m
th
e
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
P
u
sa
n
Na
ti
o
n
a
l
Un
iv
e
rsity
,
Bu
sa
n
,
Ko
re
a
,
in
1
9
9
3
a
n
d
1
9
9
9
,
re
sp
e
c
ti
v
e
ly
.
F
ro
m
1
9
9
7
t
o
th
e
p
re
se
n
t,
h
e
is
a
p
r
o
f
e
ss
o
r
a
t
th
e
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
E
n
g
in
e
e
rin
g
,
S
il
la
U
n
iv
e
rsity
,
Ko
re
a
.
He
is
c
u
rre
n
tl
y
a
n
a
ss
o
c
i
a
te
e
d
it
o
r
f
o
r
Jo
u
rn
a
l
o
f
In
telli
g
e
n
c
e
a
n
d
In
f
o
rm
a
ti
o
n
S
y
ste
m
s
a
n
d
T
h
e
Op
e
n
C
o
m
p
u
ter
S
c
ien
c
e
Jo
u
rn
a
l
(USA
).
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
f
u
z
z
y
n
e
u
ra
l
n
e
tw
o
rk
a
n
d
a
p
p
li
c
a
ti
o
n
s,
b
i
o
in
f
o
rm
a
ti
c
s,
a
n
d
im
a
g
e
p
ro
c
e
ss
in
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.