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.
9
,
No
.
6
,
Dec
em
b
er
201
9
,
p
p
.
5
2
0
5
~
5
2
1
0
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
9
i
6
.
pp
5
2
0
5
-
5210
5205
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
Auto
m
a
tic
seg
m
e
ntatio
n of w
rist b
o
ne f
ra
ctu
re area
by
K
-
m
ea
ns
pix
el clu
stering
f
ro
m
X
-
ra
y
i
m
a
g
e
K
w
a
ng
B
a
ek
K
i
m
1
,
Do
o
H
eo
n So
ng
2
,
Sa
ng
-
Seo
k
Y
un
3
1
Div
isio
n
o
f
Co
m
p
u
ter S
o
f
twa
re
En
g
in
e
e
rin
g
,
S
i
ll
a
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
Div
isio
n
o
f
M
e
c
h
a
n
ica
l
C
o
n
v
e
rg
e
n
c
e
En
g
in
e
e
rin
g
,
S
il
la Un
iv
e
rsity
,
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
A
p
r
2
0
,
2
0
1
9
R
ev
i
s
ed
J
u
l 9
,
2
0
1
9
A
cc
ep
ted
J
u
l
1
7
,
2
0
1
9
Early
d
e
te
c
ti
o
n
o
f
su
b
tl
e
f
ra
c
tu
re
is
im
p
o
rtan
t
p
a
rti
c
u
larly
f
o
r
th
e
se
n
io
r
c
it
ize
n
s’
q
u
a
li
ty
o
f
li
f
e
.
Na
k
e
d
e
y
e
e
x
a
m
in
a
ti
o
n
f
ro
m
X
-
ra
y
i
m
a
g
e
m
a
y
c
a
u
se
f
a
ls
e
n
e
g
a
ti
v
e
s
d
u
e
to
o
p
e
ra
t
o
r
su
b
jec
ti
v
it
y
th
u
s
c
o
m
p
u
ter
v
is
io
n
b
a
se
d
a
u
to
m
a
ti
c
d
e
tec
ti
o
n
so
f
tw
a
r
e
is
m
u
c
h
n
e
e
d
e
d
i
n
p
ra
c
ti
c
e
.
In
t
h
is
p
a
p
e
r,
w
e
p
ro
p
o
se
a
n
a
u
to
m
a
ti
c
e
x
trac
ti
o
n
m
e
th
o
d
f
o
r
su
s
p
i
c
io
u
s
w
ris
t
f
ra
c
tu
re
re
g
io
n
s.
W
e
a
p
p
ly
K
-
m
e
a
n
s
in
p
i
x
e
l
c
lu
ste
rin
g
to
f
o
rm
th
e
c
a
n
d
id
a
te
p
a
rt
o
f
p
o
ss
ib
le
f
ra
c
tu
re
f
ro
m
w
rist
X
-
r
a
y
ima
g
e
a
u
to
m
a
ti
c
a
ll
y
.
T
h
is
m
e
th
o
d
c
a
n
re
c
o
v
e
r
p
re
v
io
u
sly
d
e
tec
ted
p
a
tt
e
rn
e
d
f
a
lse
c
a
se
s
w
it
h
e
d
g
e
d
e
tec
ti
o
n
m
e
th
o
d
a
f
ter
f
u
z
z
y
stre
tch
in
g
.
T
h
e
p
ro
p
o
se
d
m
e
th
o
d
is
su
c
c
e
ss
f
u
l
in
1
6
o
u
t
o
f
2
0
tes
ted
c
a
se
s in
e
x
p
e
ri
m
e
n
t.
K
ey
w
o
r
d
s
:
Fu
zz
y
s
tr
etc
h
in
g
K
-
m
ea
n
s
P
ix
el
clu
s
ter
in
g
W
r
is
t b
o
n
e
f
r
ac
tu
re
X
-
r
a
y
Co
p
y
rig
h
t
©
2
0
1
9
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
,
Div
i
s
io
n
o
f
C
o
m
p
u
ter
So
f
t
w
ar
e
E
n
g
i
n
ee
r
in
g
,
S
il
la Un
iv
e
rsity
,
Bu
sa
n
4
6
9
5
8
,
Re
p
u
b
li
c
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
Fra
ctu
r
e
r
ef
er
s
to
th
e
co
m
p
le
te
o
r
in
co
m
p
lete
lo
s
s
o
f
co
n
t
in
u
it
y
o
f
b
o
n
e,
alv
eo
lar
p
late,
o
r
jo
in
t
s
u
r
f
ac
e,
o
f
ten
ac
co
m
p
a
n
ied
b
y
d
a
m
a
g
e
to
s
o
f
t
tis
s
u
es
o
r
o
r
g
an
s
ar
o
u
n
d
t
h
e
b
o
n
e.
T
h
e
f
r
ac
tu
r
e
o
f
th
e
f
o
r
ea
r
m
h
ap
p
en
s
w
h
e
n
at
least
o
n
e
o
f
th
e
t
w
o
i
m
p
o
r
tan
t
b
o
n
es
o
f
th
e
ar
ea
b
etw
ee
n
th
e
elb
o
w
an
d
th
e
w
r
is
t
-
r
ad
iu
s
an
d
u
l
n
a
–
is
b
r
o
k
en
an
d
f
r
eq
u
en
t
l
y
it
ac
co
m
p
a
n
ies
w
i
th
d
i
s
lo
ca
tio
n
.
I
t
is
ca
u
s
ed
b
y
eit
h
er
in
d
ir
ec
t
f
o
r
ce
in
f
alli
n
g
ac
cid
en
t
w
h
en
t
h
e
v
ict
i
m
p
u
t
o
n
e
’
s
h
a
n
d
o
n
th
e
f
lo
o
r
w
it
h
i
m
b
ala
n
ce
p
o
s
itio
n
o
r
t
h
e
d
ir
ec
t
f
o
r
ce
b
y
tr
af
f
ic
ac
cid
en
t
o
r
co
n
tu
s
io
n
.
I
n
d
ir
ec
t
f
o
r
ce
ca
u
s
es
an
o
b
liq
u
e
o
r
s
p
ir
al
f
r
ac
tu
r
e,
an
d
th
e
d
ir
ec
t
f
o
r
ce
ca
u
s
es
a
later
al
f
r
ac
tu
r
e
o
f
t
h
e
r
ad
ial
an
d
u
l
n
a
[
1
]
.
I
f
th
e
f
r
ac
t
u
r
e
is
n
o
t
tr
ea
ted
p
r
o
p
er
ly
s
o
th
at
th
e
m
al
u
n
io
n
o
r
h
y
p
er
k
ala
b
o
n
e
o
cc
u
r
s
,
th
e
w
r
i
s
t
is
w
ea
k
en
ed
w
i
th
p
ain
a
n
d
t
h
e
p
atien
t
m
a
y
f
ee
l
d
if
f
ic
u
lt
y
i
n
r
o
tatin
g
h
a
n
d
s
[
2
]
.
T
h
e
b
o
n
e
f
r
ac
tu
r
e
d
etec
tio
n
is
o
f
ten
th
r
o
u
g
h
v
is
u
al
in
s
p
ec
ti
o
n
o
f
a
n
X
-
r
a
y
i
m
a
g
e
to
d
et
er
m
in
e
t
h
e
p
r
esen
ce
an
d
s
ev
e
r
it
y
o
f
t
h
e
f
r
ac
tu
r
e.
T
h
e
s
o
u
r
ce
s
o
f
d
if
f
ic
u
lt
y
i
n
v
is
u
al
d
etec
tio
n
b
y
r
ad
io
lo
g
is
t
s
m
ig
h
t
b
e
th
e
o
v
er
lap
p
in
g
o
f
s
ev
er
al
an
a
to
m
ical
s
tr
u
ct
u
r
es
o
n
an
X
-
r
a
y
i
m
a
g
e
o
r
th
e
in
co
n
s
i
s
te
n
c
y
o
f
i
m
ag
e
q
u
alit
y
ac
r
o
s
s
ex
a
m
s
.
Ho
w
ev
er
,
th
e
p
o
ten
tial
h
u
m
a
n
er
r
o
r
f
r
o
m
f
ati
g
u
e
o
r
o
p
er
ato
r
s
u
b
j
ec
t
iv
it
y
m
a
y
in
cr
e
ase
th
e
r
i
s
k
o
f
m
is
s
i
n
g
s
u
b
tle
b
o
n
e
f
r
ac
tu
r
e
s
[
3
]
.
T
h
u
s
,
au
to
m
a
ted
b
o
n
e
f
r
ac
tu
r
e
d
etec
tio
n
ca
n
ass
is
t
d
o
cto
r
s
an
d
p
ar
am
ed
ical
s
ta
f
f
to
an
al
y
ze
th
e
s
e
v
er
it
y
o
f
th
e
s
it
u
atio
n
an
d
to
ch
o
o
s
e
a
p
r
o
p
er
c
o
u
r
s
e
o
f
ac
tio
n
o
n
u
r
g
e
n
t b
asis
[
4
]
.
A
t
y
p
ic
a
l
au
to
m
a
ted
b
o
n
e
f
r
ac
tu
r
e
d
etec
tio
n
s
o
f
t
w
ar
e
co
n
s
is
ts
o
f
th
r
ee
s
ta
g
es
–
p
r
ep
r
o
ce
s
s
in
g
,
s
eg
m
e
n
tatio
n
,
a
n
d
f
r
ac
t
u
r
e
d
etec
tio
n
.
I
n
t
h
is
p
ap
er
,
w
e
p
r
o
p
o
s
e
a
co
m
p
u
ter
v
is
io
n
b
ased
m
eth
o
d
to
ex
tr
ac
t
th
e
ca
n
d
id
ate
ar
ea
o
f
w
r
i
s
t
f
r
ac
tu
r
e
au
to
m
atica
ll
y
f
r
o
m
X
-
r
a
y
i
m
ag
e.
T
h
is
s
tep
is
th
e
m
ai
n
s
o
u
r
ce
o
f
au
to
m
at
ic
f
r
ac
t
u
r
e
d
etec
tio
n
a
n
d
th
e
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
o
f
t
h
is
r
esear
c
h
is
s
i
m
i
lar
to
o
u
r
p
r
ev
io
u
s
w
o
r
k
[
5
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
201
9
:
5
2
05
-
5
2
1
0
5206
T
h
er
e
h
av
e
b
ee
n
s
ev
er
al
r
es
ea
r
ch
es
in
t
h
is
a
u
to
m
a
tic
h
a
n
d
b
o
n
e
s
eg
m
en
ta
tio
n
p
r
o
b
lem
s
.
E
ar
l
y
atte
m
p
t l
ik
e
[
6
]
ap
p
lies
r
eg
io
n
b
ased
lev
el
s
et
ap
p
r
o
ac
h
b
u
t
n
o
d
etailed
ex
p
er
i
m
en
t r
es
u
lt
w
a
s
r
ep
o
r
ted
.
I
n
[
7
]
,
it
u
s
es
an
ex
ten
d
ed
v
er
s
io
n
o
f
Ots
u
’
s
b
in
ar
izatio
n
b
u
t
th
e
co
m
p
u
tatio
n
ti
m
e
m
a
y
tak
e
u
p
s
ev
er
al
s
ec
o
n
d
s
.
Ma
n
y
s
y
s
te
m
s
u
s
ed
s
o
m
e
f
i
lte
r
in
g
al
g
o
r
ith
m
a
n
d
ed
g
e
d
etec
tio
n
in
th
e
ir
m
ai
n
p
ar
t
in
s
eg
m
en
tatio
n
[
8
-
1
0
]
b
u
t
n
o
n
e
o
f
th
e
m
s
h
o
w
s
g
o
o
d
ex
p
er
i
m
e
n
tal
s
tati
s
tic
s
in
f
r
ac
tu
r
e
d
etec
tio
n
r
ate.
So
m
e
o
t
h
er
w
o
r
k
i
n
clu
d
e
s
th
e
o
p
er
atio
n
s
lik
e
g
r
a
y
co
n
v
e
r
s
io
n
,
ac
tiv
e
co
n
to
u
r
s
eg
m
en
ta
tio
n
b
u
t
th
e
d
etec
tio
n
r
ate
w
as
r
ep
o
r
te
d
as
lo
w
as
6
9
%
an
d
s
till
,
it
lo
o
k
s
b
etter
th
an
o
t
h
er
s
i
m
p
le
m
et
h
o
d
s
u
c
h
as
r
eg
io
n
g
r
o
w
i
n
g
a
n
d
lev
el
s
et
s
eg
m
e
n
tatio
n
[
6
]
f
o
r
th
eir
i
m
p
le
m
e
n
tatio
n
[
1
1
]
.
I
n
th
is
p
ap
er
,
w
e
p
r
o
p
o
s
e
a
p
ix
el
cl
u
s
ter
in
g
b
ased
a
u
to
m
at
ic
s
eg
m
e
n
tatio
n
o
f
s
u
s
p
icio
u
s
f
r
ac
t
u
r
ed
ar
ea
.
T
h
is
s
tep
s
h
o
u
ld
b
e
d
o
n
e
ac
cu
r
atel
y
b
ef
o
r
e
d
etec
tin
g
th
e
f
r
ac
t
u
r
ed
s
p
o
t.
Ho
w
ev
e
r
,
in
m
a
n
y
m
ed
ica
l
i
m
a
g
in
g
ap
p
licatio
n
s
,
ed
g
e
-
b
a
s
ed
alg
o
r
ith
m
s
s
u
f
f
er
b
ec
au
s
e
m
ed
ical
i
m
a
g
es
co
m
m
o
n
l
y
h
av
e
p
o
o
r
c
o
n
tr
asts
,
d
if
f
er
e
n
t
t
y
p
es
o
f
n
o
is
e,
an
d
m
is
s
i
n
g
o
r
d
if
f
u
s
iv
e
b
o
u
n
d
ar
ies
[
1
2
]
.
I
n
s
tead
,
p
ix
el
clu
s
ter
i
n
g
ap
p
r
o
ac
h
es
h
a
v
e
b
ee
n
s
u
cc
e
s
s
f
u
ll
y
ap
p
lied
to
d
etec
t
th
e
tar
g
et
o
r
g
an
f
r
o
m
u
ltra
s
o
n
o
g
r
ap
h
y
o
r
X
-
r
a
y
i
m
ag
es.
So
m
e
e
x
a
m
p
le
s
o
f
s
u
ch
ap
p
r
o
ac
h
es
i
n
cl
u
d
e
d
etec
tin
g
b
r
ai
n
t
u
m
o
r
[
1
3
,
1
4
]
,
b
r
ac
h
ial
ar
ter
y
[
1
5
]
,
ce
r
v
ical
v
er
te
b
r
ae
[
1
6
]
,
lu
n
g
ca
n
ce
r
[
1
7
]
,
in
f
la
m
ed
ap
p
en
d
ix
[
1
8
]
,
g
an
g
lio
n
c
y
s
t
[
1
9
]
an
d
b
r
ea
s
t
im
a
g
e
s
eg
m
e
n
tatio
n
[
2
0
]
.
T
h
u
s
,
in
t
h
is
p
ap
er
,
w
e
tak
e
K
-
m
ea
n
s
b
ased
p
ix
el
clu
s
ter
i
n
g
ap
p
r
o
ac
h
[
1
6
,
2
1
]
t
o
th
is
au
to
m
a
tic
s
eg
m
en
tatio
n
p
r
o
b
le
m
.
Du
e
to
t
h
e
lo
w
in
te
n
s
it
y
co
n
tr
ast
b
et
w
ee
n
t
h
e
tar
g
et
ar
ea
an
d
th
e
b
ac
k
g
r
o
u
n
d
,
w
e
n
ee
d
f
u
zz
y
s
tr
etc
h
i
n
g
[
2
2
]
to
en
h
a
n
ce
th
e
co
n
tr
ast.
2.
P
I
XE
L
CL
U
ST
E
R
I
N
G
B
Y
K
-
M
E
ANS
WI
T
H
F
U
Z
Z
Y
S
T
R
E
T
CH
I
NG
I
m
ag
e
s
e
g
m
e
n
tat
io
n
r
ef
er
s
to
th
e
p
r
o
ce
s
s
o
f
p
ar
titi
o
n
in
g
an
im
a
g
e
in
to
m
u
t
u
all
y
e
x
clu
s
i
v
e
r
eg
io
n
s
.
I
t
ca
n
b
e
co
n
s
id
er
ed
as
t
h
e
m
o
s
t
es
s
en
tial
a
n
d
cr
u
cial
p
r
o
ce
s
s
f
o
r
f
ac
ili
tati
n
g
th
e
d
elin
ea
t
io
n
,
ch
ar
ac
ter
izat
io
n
,
an
d
v
is
u
aliza
tio
n
o
f
r
e
g
io
n
s
o
f
in
ter
est
i
n
an
y
m
ed
ical
i
m
a
g
e
[
1
2
]
.
C
lu
s
ter
i
n
g
ca
n
b
e
d
ef
i
n
ed
as
th
e
o
p
ti
m
al
p
ar
titi
o
n
in
g
o
f
a
g
i
v
en
s
et
o
f
n
d
ata
p
o
in
ts
in
to
c
s
u
b
g
r
o
u
p
s
,
s
u
c
h
t
h
at
d
ata
p
o
in
ts
b
elo
n
g
i
n
g
to
th
e
s
a
m
e
g
r
o
u
p
ar
e
as
s
i
m
ilar
to
ea
c
h
o
th
er
a
s
p
o
s
s
ib
le
w
h
er
ea
s
d
ata
p
o
in
t
s
f
r
o
m
t
w
o
d
i
f
f
er
e
n
t
g
r
o
u
p
s
s
h
ar
e
th
e
m
a
x
i
m
u
m
d
if
f
er
e
n
ce
.
I
m
a
g
e
s
e
g
m
en
tati
o
n
ca
n
b
e
tr
ea
ted
as
a
cl
u
s
te
r
in
g
p
r
o
b
le
m
w
h
er
e
th
e
f
ea
t
u
r
es
d
escr
ib
in
g
ea
c
h
p
ix
el
co
r
r
esp
o
n
d
to
a
p
atter
n
,
an
d
ea
ch
i
m
ag
e
r
e
g
io
n
co
r
r
esp
o
n
d
s
to
a
clu
s
ter
[
2
3
]
.
Ver
y
f
r
eq
u
e
n
tl
y
,
an
y
v
is
io
n
b
ased
o
b
j
ec
t
ex
tr
ac
tio
n
p
r
o
ce
d
u
r
e
p
r
o
v
id
es
au
x
iliar
y
i
n
te
n
s
i
t
y
s
tr
etch
i
n
g
alg
o
r
ith
m
to
ex
te
n
d
th
e
co
n
tr
a
s
t
t
o
d
if
f
er
e
n
tiate
t
h
e
tar
g
et
o
b
j
ec
t
f
r
o
m
t
h
e
b
ac
k
g
r
o
u
n
d
ef
f
e
ctiv
el
y
[
2
4
]
.
Fro
m
th
e
g
i
v
en
X
-
r
a
y
i
m
a
g
e,
s
i
n
ce
t
h
e
i
m
a
g
e
d
o
es
n
o
t
h
a
v
e
e
n
o
u
g
h
i
n
te
n
s
it
y
co
n
tr
ast
to
d
i
s
cr
i
m
i
n
ate
b
o
n
e
p
ar
t
a
n
d
o
th
er
p
ar
ts
in
t
h
e
i
m
ag
e,
w
e
h
av
e
s
i
m
ilar
s
i
tu
atio
n
an
d
t
h
u
s
ad
o
p
t
f
u
zz
y
s
tr
etch
in
g
[
2
2
]
f
o
r
th
at
p
u
r
p
o
s
e.
I
n
th
at
f
u
zz
y
s
tr
etch
i
n
g
,
th
e
d
y
n
a
m
ic
co
n
tr
o
l
o
f
f
u
zz
y
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
f
o
r
in
ten
s
it
y
s
tr
etc
h
i
n
g
i
s
th
e
p
o
w
er
o
f
q
u
al
itati
v
e
s
e
g
m
en
tatio
n
.
T
h
e
g
r
e
y
-
s
ca
le
i
n
p
u
t
i
m
a
g
e
m
a
y
n
o
t
h
av
e
e
n
o
u
g
h
b
r
ig
h
tn
e
s
s
co
n
tr
ast
b
et
w
ee
n
th
e
“
b
r
i
g
h
t
”
s
id
e
an
d
th
e
“
d
ar
k
”
s
id
e.
T
h
u
s
,
w
e
s
tr
et
ch
0
’
s
a
n
d
1
’
s
as
f
o
llo
w
s
s
o
th
at
th
e
b
r
ig
h
t c
o
n
tr
ast i
s
ef
f
ec
ti
v
el
y
e
x
a
g
g
er
ated
.
N
M
i
i
m
N
M
X
X
0
1
(
1
)
L
et
X
m
b
e
th
e
a
v
er
ag
e
b
r
ig
h
t
n
ess
v
a
lu
e
o
f
t
h
e
i
m
a
g
e
w
it
h
M
×
N
s
ize,
t
h
e
d
is
ta
n
ce
f
r
o
m
t
h
e
b
r
ig
h
test
p
ix
el
an
d
th
e
d
ar
k
e
s
t p
ix
el
ar
e
d
ef
in
ed
as
(
2
)
.
l
m
m
h
X
X
D
X
X
D
m
i
n
m
a
x
,
(
2
)
T
h
e
b
r
ig
h
tn
e
s
s
ad
j
u
s
t
m
en
t v
al
u
e
is
co
m
p
u
ted
as s
h
o
w
n
i
n
(
3
)
.
m
m
m
m
m
X
a
d
j
u
s
t
m
e
n
t
e
l
s
e
D
a
d
j
u
s
t
m
e
n
t
D
X
e
l
s
e
i
f
D
a
d
j
u
s
t
m
e
n
t
D
X
e
l
s
e
i
f
X
a
d
j
u
s
t
m
e
n
t
X
if
m
a
x
m
a
x
m
i
n
m
i
n
)
(
)
(
255
)
128
(
(
3
)
T
h
u
s
,
th
e
m
ax
i
m
u
m
,
m
i
n
i
m
u
m
,
an
d
th
e
ce
n
ter
p
o
in
t
o
f
th
e
b
r
ig
h
t
n
es
s
w
h
ic
h
w
ill
f
o
r
m
t
h
e
f
u
zz
y
m
e
m
b
er
s
h
ip
tr
ian
g
le
ar
e
d
ef
in
ed
as
f
o
llo
w
s
;
a
d
j
u
s
t
m
e
n
t
X
I
a
d
j
u
s
t
m
e
n
t
X
I
m
m
m
i
n
m
a
x
,
(
4
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
A
u
to
ma
tic
s
eg
men
ta
tio
n
o
f wr
is
t b
o
n
e
fr
a
ctu
r
e
a
r
ea
b
y
K
-
m
ea
n
s
…
(
K
w
a
n
g
B
a
ek
K
im
)
5207
2
m
in
m
a
x
I
I
I
m
id
(
5
)
T
h
e
m
e
m
b
er
s
h
ip
f
u
n
ct
io
n
is
t
h
en
d
ef
i
n
ed
as Fi
g
u
r
e
1.
Fig
u
r
e
1
.
Fu
zz
y
m
e
m
b
er
s
h
ip
f
u
n
ct
io
n
f
o
r
b
r
ig
h
t
n
ess
e
n
h
an
c
e
m
en
t
T
h
e
cu
t p
o
in
t (
c
u
t
)
in
Fig
u
r
e
2
is
co
m
p
u
ted
as
f
o
llo
w
s
;
5
.
0
/
)
0
(
m
a
x
m
i
n
m
i
n
c
u
t
e
l
s
e
I
I
c
u
t
I
if
(
5
)
X
X
n
e
w
255
(
6
)
T
h
e
u
p
p
er
lim
it
v
al
u
e
(
α
-
cu
t
)
an
d
th
e
lo
w
er
li
m
it
v
al
u
e
(
α
)
ar
e
d
ef
in
ed
as
th
e
h
ig
h
e
s
t
an
d
lo
w
est
X
i
a
m
o
n
g
p
i
x
els
th
at
h
a
v
e
h
i
g
h
er
m
e
m
b
er
s
h
ip
d
e
g
r
ee
th
a
n
th
e
c
u
t
p
o
in
t
α
-
cu
t
.
T
h
en
,
t
h
e
f
i
n
al
s
tr
etc
h
i
n
g
eq
u
atio
n
f
o
r
th
e
p
ix
el
b
r
ig
h
t
n
e
s
s
is
d
e
f
in
ed
as
f
o
llo
w
s
;
Af
ter
s
u
c
h
f
u
zz
y
s
tr
etc
h
in
g
,
w
it
h
i
n
t
h
e
r
an
g
e
o
f
tar
g
et
o
b
j
ec
t
ex
is
ten
ce
,
w
e
tr
y
to
a
p
p
ly
p
i
x
el
c
lu
s
ter
i
n
g
.
K
-
m
ea
n
s
cl
u
s
ter
i
n
g
is
a
w
ell
-
k
n
o
w
n
u
n
s
u
p
er
v
i
s
ed
lear
n
in
g
alg
o
r
it
h
m
t
h
at
h
as
m
an
y
v
ar
ia
n
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 [
2
0
]
as su
m
m
ar
ized
in
A
l
g
o
r
ith
m
1
.
A
l
g
o
r
ith
m
1
.
K
-
m
ea
n
s
p
r
o
ce
s
s
: a
s
p
ee
d
u
p
v
er
s
io
n
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
i
s
as
s
i
m
p
le
as
ab
o
v
e
d
escr
ip
tio
n
.
Fro
m
ar
b
itra
r
il
y
g
i
v
e
n
k
s
ets,
th
e
alg
o
r
ith
m
iter
ati
v
el
y
r
e
-
a
s
s
i
g
n
s
th
e
d
ata
s
ets
ac
co
r
d
i
n
g
to
th
e
ce
n
ter
p
o
in
t
an
d
r
e
-
co
m
p
u
te
s
ce
n
ter
p
o
in
ts
at
ev
er
y
iter
atio
n
u
n
t
il
th
er
e
is
n
o
s
i
g
n
i
f
ican
t
ch
a
n
g
e.
T
h
e
ty
p
ical
r
es
u
lt
o
f
K
-
m
e
an
s
p
ix
e
l
clu
s
ter
in
g
is
s
h
o
w
n
as F
ig
u
r
e
2.
Fro
m
th
e
K
-
m
ea
n
s
cl
u
s
ter
i
n
g
r
esu
lt
as
s
h
o
w
n
in
Fi
g
u
r
e
3
(
a)
,
w
e
n
ee
d
n
o
is
e
r
e
m
o
v
al
p
r
o
ce
s
s
b
ased
o
n
th
e
d
o
m
ai
n
k
n
o
w
led
g
e
s
u
ch
t
h
at
t
h
e
f
r
ac
tu
r
ed
ar
ea
d
o
es
n
o
t
h
a
v
e
ex
tr
e
m
e
in
te
n
s
it
y
v
alu
e
s
a
n
d
th
e
n
w
e
ap
p
ly
lab
elli
n
g
p
r
o
ce
d
u
r
e
[
2
5
]
to
f
o
r
m
an
d
r
em
o
v
e
th
e
co
n
to
u
r
o
f
th
e
w
r
is
t
b
o
n
e
as
s
h
o
w
n
in
Fig
u
r
e
3
(
b
)
.
T
h
en
th
e
r
eg
io
n
lab
eli
n
g
p
r
o
ce
d
u
r
e
is
ap
p
lied
to
m
ak
e
t
h
e
tar
g
et
s
u
s
p
icio
u
s
f
r
ac
tu
r
e
r
ep
ea
ted
ly
s
u
c
h
th
at
th
e
s
u
s
p
icio
u
s
r
eg
io
n
s
ar
e
co
n
n
ec
ted
an
d
f
o
r
m
a
m
ea
n
i
n
g
f
u
l
s
ize
o
f
o
b
j
ec
t
w
h
ile
r
e
m
o
v
i
n
g
s
m
all
o
r
d
is
co
n
n
ec
ted
n
o
is
es
as
s
h
o
w
n
in
Fi
g
u
r
e
3
(
c)
.
T
h
at
co
m
p
letes
o
u
r
au
to
m
atic
s
eg
m
e
n
tatio
n
p
r
o
ce
s
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
201
9
:
5
2
05
-
5
2
1
0
5208
Fig
u
r
e
2
.
C
an
d
id
ate
f
r
ac
t
u
r
ed
ar
ea
ex
tr
ac
tio
n
b
y
K
-
m
ea
n
s
,
(
a)
I
m
a
g
e
af
ter
f
u
zz
y
s
tr
etc
h
i
n
g
,
(
b
)
C
an
d
id
ate
f
r
ac
tu
r
ed
ar
ea
af
ter
K
-
m
ea
n
s
Fig
u
r
e
3
.
Fra
ctu
r
e
ar
ea
ex
tr
ac
t
io
n
af
ter
k
-
m
ea
n
s
,
(
a)
A
f
ter
K
-
m
ea
n
s
,
(
b
)
C
an
d
id
ate
f
r
ac
tu
r
e
,
(
c)
Fra
ctu
r
e
ar
ea
3.
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
l
e
m
en
ted
in
C
#
u
n
d
er
Vis
u
a
l
Stu
d
io
2
0
1
7
en
v
ir
o
n
m
e
n
t
w
it
h
I
n
tel(
R
)
Du
al
C
o
r
e(
T
M)
i3
-
5
0
0
5
U
C
PU
@
2
.
0
GHz
an
d
4
GB
R
A
M
P
C
.
T
w
en
t
y
(
2
0
)
X
-
R
a
y
i
m
ag
es
co
n
tain
i
n
g
h
an
d
b
o
n
e
s
k
eleto
n
w
i
th
f
r
ac
tu
r
e
i
n
s
o
m
e
p
lace
o
f
1
2
0
8
x
1
5
0
2
s
ize
w
er
e
u
s
ed
in
t
h
is
e
x
p
er
i
m
en
t.
I
n
ex
p
er
i
m
en
t,
o
u
r
co
o
p
er
ated
p
ath
o
lo
g
is
t
e
v
alu
a
te
i
f
t
h
e
r
es
u
lt
co
m
e
o
u
t
o
f
th
e
s
o
f
t
w
ar
e
is
s
u
f
f
ici
en
tl
y
m
ea
n
i
n
g
f
u
l.
T
h
e
p
ath
o
lo
g
is
t
ag
r
ee
s
w
it
h
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
’
s
r
es
u
lts
i
n
1
6
o
u
t
o
f
2
0
ca
s
es.
Fig
u
r
e
4
d
em
o
n
s
tr
ates
b
o
th
th
e
s
u
cc
es
s
f
u
l e
x
tr
ac
tio
n
ca
s
e
(
Fig
u
r
e
4
(
a)
)
an
d
f
ailed
ex
tr
ac
tio
n
(
Fig
u
r
e
4
(
b
)
)
.
(
a)
(
b
)
Fig
u
r
e
4
.
Fra
ctu
r
e
ar
ea
ex
tr
ac
t
io
n
s
u
cc
e
s
s
a
n
d
f
ailed
ca
s
e
s
,
(
a)
Su
cc
ess
f
u
l
e
x
tr
ac
tio
n
(
b
)
Failed
ex
tr
ac
tio
n
I
n
r
etr
o
s
p
ec
tiv
e
an
al
y
s
is
,
f
a
i
led
ex
tr
ac
tio
n
ca
s
e
s
r
ep
r
esen
t
eit
h
er
in
s
u
f
f
icie
n
t
d
is
cr
i
m
in
atio
n
o
f
f
r
ac
tu
r
ed
ar
ea
f
r
o
m
n
o
r
m
al
s
t
ate
in
in
te
n
s
it
y
o
r
u
n
i
n
ten
d
ed
r
e
m
o
v
al
o
f
s
m
all
b
u
t
m
ea
n
i
n
g
f
u
l
f
r
ac
tu
r
ed
p
ar
t
in
r
eg
io
n
lab
elli
n
g
p
r
o
ce
s
s
.
T
h
e
f
o
r
m
er
ca
s
e
n
ee
d
s
ca
r
ef
u
l
f
i
l
m
i
n
g
o
r
b
etter
in
ten
s
it
y
s
tr
et
ch
in
g
p
r
o
ce
d
u
r
e
in
th
e
f
u
tu
r
e.
Fo
r
t
h
e
lat
ter
ca
s
e,
it is
p
ar
tl
y
attr
ib
u
ted
to
th
e
i
n
t
r
in
s
ic
d
i
s
ad
v
a
n
tag
e
o
f
K
-
m
ea
n
s
th
a
t it
n
ee
d
s
p
r
io
r
d
eter
m
in
at
io
n
o
f
t
h
e
n
u
m
b
e
r
o
f
cl
u
s
ter
s
b
ef
o
r
e
p
r
o
ce
s
s
in
g
.
T
h
at
i
s
,
t
h
e
al
g
o
r
ith
m
r
eq
u
ir
e
s
a
g
o
o
d
in
itial
izatio
n
f
r
o
m
t
h
e
ex
p
er
ie
n
ce
o
f
t
h
e
en
v
ir
o
n
m
en
t c
h
ar
ac
ter
is
tics
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
A
u
to
ma
tic
s
eg
men
ta
tio
n
o
f wr
is
t b
o
n
e
fr
a
ctu
r
e
a
r
ea
b
y
K
-
m
ea
n
s
…
(
K
w
a
n
g
B
a
ek
K
im
)
5209
4.
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
th
at
e
x
tr
ac
ts
t
h
e
s
u
s
p
icio
u
s
f
r
ac
tu
r
ed
ar
ea
s
u
to
m
a
ti
ca
ll
y
f
r
o
m
X
-
r
a
y
i
m
a
g
es.
S
u
ch
a
u
to
m
at
ic
s
eg
m
en
ta
tio
n
is
cr
u
c
ial
to
b
u
ild
a
h
ig
h
l
y
tib
u
s
t
an
d
ac
cu
r
ate
f
r
ac
tu
r
e
d
etec
tio
n
s
o
f
t
w
ar
e.
L
i
k
e
m
a
n
y
o
th
er
p
r
i
o
r
s
tu
d
ies,
o
u
r
p
r
ev
io
u
s
s
tu
d
y
[
5
]
u
s
ed
ca
n
n
y
ed
g
e
al
g
o
r
it
h
m
to
tak
e
t
h
e
f
r
ac
t
u
r
e
p
ar
t
ar
o
u
n
d
th
e
w
r
i
s
t
ar
ea
.
Ho
w
e
v
er
,
th
e
r
esu
lt
s
h
o
w
s
t
h
at
th
er
e
w
er
e
a
p
atter
n
ed
f
ailu
r
e
in
d
etec
tin
g
th
e
tar
g
et
f
r
ac
t
u
r
e
lo
ca
tio
n
.
T
h
u
s
,
w
e
ta
k
e
K
-
m
ea
n
s
p
i
x
el
clu
s
ter
in
g
as t
h
e
an
s
w
er
o
f
s
u
ch
p
r
o
b
lem
.
W
h
ile
t
h
is
p
ix
el
c
lu
s
ter
in
g
ap
p
r
o
ac
h
is
m
o
r
e
r
o
b
u
s
t
t
h
an
ed
g
e
d
etec
tio
n
s
c
h
e
m
es,
it
s
ti
l
l
n
ee
d
s
to
b
e
i
m
p
r
o
v
ed
d
u
e
to
its
s
tatic
in
it
ializatio
n
p
r
o
b
lem
.
I
n
ex
p
er
i
m
en
t,
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
ex
h
ib
it
s
a
r
esp
ec
tab
le
b
u
t
i
m
p
r
o
v
ab
le
s
u
cc
e
s
s
f
u
l
ex
t
r
ac
tio
n
r
ate
(
h
u
m
a
n
p
at
h
o
lo
g
i
s
t
ag
r
ee
s
w
it
h
t
h
e
s
o
f
t
w
ar
e
(
1
6
o
u
t
o
f
2
0
ca
s
es
o
r
8
0
%
ac
cu
r
ate
b
ased
o
n
t
h
e
h
u
m
a
n
e
x
p
er
t’
s
d
ec
is
io
n
as
t
h
e
g
r
o
u
n
d
tr
u
t
h
)
.
W
e
n
ee
d
m
o
r
e
ca
r
ef
u
l
in
ten
s
it
y
s
tr
etch
i
n
g
m
et
h
o
d
an
d
m
o
r
e
s
tab
le
p
ix
el
cl
y
s
ter
in
g
al
g
o
r
tith
m
s
i
n
o
r
d
er
to
d
ev
elo
p
b
etter
au
to
m
at
ic
f
r
ac
t
u
r
e
d
etec
tio
n
s
o
f
t
w
ar
e.
ACK
NO
WL
E
D
G
M
E
NT
T
h
is
w
o
r
k
w
as
s
u
p
p
o
r
ted
b
y
th
e
T
ec
h
n
o
lo
g
y
I
n
n
o
v
atio
n
P
r
o
g
r
a
m
(
2
0
0
0
0
5
1
5
,
I
o
T
b
ased
A
s
s
is
t
iv
e
R
o
b
o
t
Sy
s
te
m
s
f
o
r
P
er
s
o
n
alize
d
Hea
lth
ca
r
e)
f
u
n
d
ed
B
y
t
h
e
Min
is
tr
y
o
f
T
r
ad
e,
I
n
d
u
s
tr
y
&
E
n
er
g
y
(
M
OT
I
E
,
Ko
r
ea
)
.
RE
F
E
R
E
NC
E
S
[1
]
K.
Ok
a
d
a
,
Vi
su
a
l
Na
v
i
Or
t
h
o
p
e
d
i
c
s
,
(L
e
e
,
HS,
Ki
m
,
TG
.
T
r
a
n
sl.)
S
e
o
u
l,
Ha
n
s
o
le M
e
d
ica
l
Bo
o
k
s.
2
0
1
4
.
[2
]
S
.
Y.
P
a
rk
,
e
t
a
l
.
,
“
S
u
rg
ica
l
o
r
n
o
n
s
u
rg
ica
l
trea
tme
n
t
o
f
o
ste
o
p
o
ro
ti
c
f
ra
c
tu
re
s,”
J
Ko
re
a
n
M
e
d
Asso
c
,
v
o
l.
5
9
,
n
o
.
1
1
,
p
p
.
8
5
7
-
8
6
5
,
2
0
1
6
.
[3
]
Y.
Ca
o
,
e
t
a
l.
,
“
F
ra
c
tu
re
d
e
tec
ti
o
n
i
n
x
-
ra
y
i
m
a
g
e
s
th
ro
u
g
h
sta
c
k
e
d
ra
n
d
o
m
f
o
re
sts
f
e
a
tu
re
f
u
sio
n
,
”
In
Pro
c
.
o
f
Bi
o
me
d
ica
l
Ima
g
in
g
,
2
0
1
5
I
EE
E
1
2
t
h
In
tern
a
ti
o
n
a
l
S
y
m
p
o
siu
m
o
n
IEE
E,
N.Y.
,
USA
,
p
p
.
8
0
1
-
8
0
5
,
2
0
1
5
.
[4
]
O.
Ba
n
d
y
o
p
a
d
h
y
a
y
,
e
t
a
l.
,
“
L
o
n
g
-
b
o
n
e
f
ra
c
tu
re
d
e
tec
ti
o
n
i
n
d
i
g
it
a
l
X
-
ra
y
im
a
g
e
s
b
a
se
d
o
n
d
i
g
it
a
l
-
g
e
o
m
e
tri
c
tec
h
n
iq
u
e
s,”
Co
mp
u
ter
me
t
h
o
d
s a
n
d
p
ro
g
ra
ms
in
b
i
o
me
d
icin
e
,
v
o
l.
1
2
3
,
p
p
.
2
-
1
4
,
2
0
1
6
.
[5
]
K.
B.
Kim
a
n
d
D.
H.
S
o
n
g
,
“
A
u
to
m
a
ti
c
Ha
n
d
Bo
n
e
S
e
g
m
e
n
tatio
n
w
it
h
F
u
z
z
y
S
tretc
h
in
g
f
ro
m
X
-
ra
y
I
m
a
g
e
,
”
Fa
r E
a
st
J
o
u
r
n
a
l
o
f
El
e
c
tro
n
ics
a
n
d
C
o
mm
u
n
ica
ti
o
n
s
,
v
o
l.
1
8
,
n
o
.
1
,
p
p
.
1
4
7
-
1
5
7
,
2
0
1
8
.
[6
]
L
in
,
P
,
e
t
a
l
.
,
“
X
-
ra
y
c
a
rp
a
l
-
b
o
n
e
im
a
g
e
b
o
u
n
d
a
ry
f
e
a
tu
re
a
n
a
l
y
s
is
u
sin
g
re
g
io
n
sta
ti
stica
l
f
e
a
tu
re
b
a
se
d
lev
e
l
se
t
m
e
th
o
d
f
o
r
sk
e
leta
l
a
g
e
a
ss
e
ss
m
e
n
t
a
p
p
li
c
a
ti
o
n
,
”
Op
t
ica
A
p
p
li
c
a
ta
,
v
o
l.
3
5
,
n
o
.
2
,
p
p
.
2
8
3
-
2
9
4
,
2
0
0
5
.
[7
]
A
.
A
.
T
iro
d
k
a
r,
“
A
m
u
lt
i
-
sta
g
e
a
lg
o
rit
h
m
f
o
r
e
n
h
a
n
c
e
d
x
-
ra
y
im
a
g
e
se
g
m
e
n
tatio
n
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
En
g
i
n
e
e
rin
g
S
c
ien
c
e
T
e
c
h
n
o
l
o
g
y
(
IJ
ES
E),
v
o
l.
3
,
n
o
.
9
,
p
p
.
7
0
5
6
-
7
0
6
5
,
2
0
1
1
.
[8
]
S
.
Ha
o
,
e
t
a
l
.,
“
A
u
to
m
a
ti
c
Iso
latio
n
o
f
Ca
rp
a
l
-
B
o
n
e
in
Ha
n
d
X
-
Ra
y
M
e
d
ica
l
I
m
a
g
e
,
”
In
:
Du
W
.
Ed
it
o
r
In
fo
rm
a
t
ics
a
n
d
M
a
n
a
g
e
me
n
t
S
c
ien
c
e
I.
L
e
c
tu
re
No
tes
i
n
El
e
c
tr
ica
l
En
g
i
n
e
e
rin
g
,
L
o
n
d
o
n
,
S
p
rin
g
e
r
.
v
o
l.
2
0
4
,
p
p
.
6
5
7
-
6
6
2
,
2
0
1
3
.
[9
]
M
.
A
l
-
Ay
y
o
u
b
,
e
t
a
l
.
,
“
De
tec
ti
n
g
Ha
n
d
B
o
n
e
F
ra
c
tu
re
s
i
n
X
-
Ra
y
Im
a
g
e
s,”
J
o
u
rn
a
l
o
f
M
u
lt
ime
d
ia
Pro
c
e
ss
in
g
a
n
d
T
e
c
h
n
o
l
o
g
ies
,
v
o
l.
4
,
n
o
.
3
,
p
p
.
1
5
5
-
1
6
8
,
2
0
1
3
.
[1
0
]
A
.
K.
O.
S
u
d
a
n
a
a
n
d
S
.
Ko
m
,
“
Bo
n
e
F
ra
c
tu
re
De
tec
ti
o
n
u
sin
g
Op
e
n
CV,”
J
o
u
rn
a
l
o
f
T
h
e
o
re
ti
c
a
l
a
n
d
Ap
p
li
e
d
In
fo
rm
a
t
io
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
6
4
,
p
p
.
2
4
9
-
2
5
4
,
2
0
1
4
.
[1
1
]
M
.
U.
Jo
s
h
i
a
n
d
S
.
T
.
G
a
n
d
h
e
,
“
Bo
n
e
f
ra
c
tu
re
d
e
tec
ti
o
n
u
si
n
g
a
c
ti
v
e
c
o
n
to
u
r
se
g
m
e
n
tatio
n
,
”
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
A
p
p
li
e
d
E
n
g
i
n
e
e
rin
g
Res
e
a
rc
h
,
v
o
l.
1
1
,
n
o
.
6
,
p
p
.
4
2
3
0
-
4
2
3
4
,
2
0
1
6
.
[1
2
]
A
.
Ch
ien
,
e
t
a
l
.
,
“
F
ra
m
e
-
b
a
se
d
se
g
m
e
n
tatio
n
f
o
r
m
e
d
ica
l
ima
g
e
s,”
Co
mm
u
n
ic
a
ti
o
n
s
in
M
a
th
e
m
a
ti
c
a
l
S
c
ien
c
e
s
,
v
o
l.
9
,
n
o
.
2
,
p
p
.
5
5
1
-
5
5
9
,
2
0
1
1
.
[1
3
]
E.
A
b
d
e
l
-
M
a
k
so
u
d
,
e
t
a
l
.
,
“
Bra
in
tu
m
o
r
se
g
m
e
n
tatio
n
b
a
se
d
o
n
a
h
y
b
rid
c
lu
ste
rin
g
tec
h
n
i
q
u
e
,
”
Eg
y
p
ti
a
n
In
fo
rm
a
t
ics
J
o
u
rn
a
l
,
v
o
l.
1
6
,
n
o
.
1
,
p
p
.
7
1
-
8
1
,
2
0
1
5
.
[1
4
]
V
.
P
.
A
n
a
n
t
h
i,
e
t
a
l
.
,
“
A
n
e
w
f
u
z
z
y
c
lu
ste
rin
g
a
lg
o
rit
h
m
f
o
r
th
e
se
g
m
e
n
tatio
n
o
f
b
ra
in
t
u
m
o
r,
”
S
o
ft
Co
mp
u
ti
n
g
,
v
o
l.
2
0
,
n
o
.
1
2
,
p
p
.
4
8
5
9
-
4
8
7
9
,
2
0
1
6
.
[1
5
]
J.
P
a
rk
,
e
t
a
l
.
,
“
A
u
to
m
a
ti
c
S
e
g
m
e
n
tatio
n
o
f
Bra
c
h
ial
A
rt
e
r
y
b
a
se
d
o
n
F
u
z
z
y
C
-
M
e
a
n
s
P
ix
e
l
Clu
ste
rin
g
f
ro
m
Ultras
o
u
n
d
Im
a
g
e
s,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
8
,
n
o
.
2
,
p
p
.
6
3
8
-
6
4
3
,
2
0
1
8
.
[1
6
]
H.
J.
L
e
e
,
e
t
a
l
.
,
“
Ef
f
e
c
ti
v
e
Co
m
p
u
ter
-
A
ss
i
ste
d
A
u
to
m
a
ti
c
Ce
rv
ica
l
V
e
rteb
ra
e
Ex
trac
ti
o
n
w
it
h
Re
h
a
b
il
it
a
ti
v
e
Ultras
o
u
n
d
Im
a
g
in
g
b
y
u
sin
g
K
-
m
e
a
n
s
Clu
ste
rin
g
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
ter
En
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
6
,
n
o
.
6
,
p
p
.
2
8
1
0
-
2
8
1
7
,
2
0
1
6
.
[1
7
]
M
.
A
.
Hu
ss
a
in
,
e
t
a
l
.
,
“
L
u
n
g
c
a
n
c
e
r
d
e
tec
ti
o
n
u
sin
g
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
&
f
u
z
z
y
c
lu
ste
rin
g
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
Res
e
a
rc
h
in
Co
mp
u
ter
a
n
d
Co
mm
u
n
ica
ti
o
n
E
n
g
i
n
e
e
rin
g
,
v
o
l.
4
,
n
o
.
3
,
p
p
.
3
6
0
-
3
6
3
,
2
0
1
5
.
[1
8
]
K.
B.
Kim
,
e
t
a
l
.
,
“
A
u
to
m
a
ti
c
Ex
t
ra
c
ti
o
n
o
f
A
p
p
e
n
d
ix
f
ro
m
Ultras
o
n
o
g
ra
p
h
y
w
it
h
S
e
lf
-
Org
a
n
izin
g
M
a
p
a
n
d
S
h
a
p
e
-
Brig
h
tn
e
ss
P
a
tt
e
rn
L
e
a
rn
in
g
,
”
Bi
o
M
e
d
re
se
a
rc
h
in
ter
n
a
ti
o
n
a
l
,
2
0
1
6
.
[1
9
]
A
.
S
u
ry
a
d
ib
ra
ta
a
n
d
K.
B.
Kim
,
“
G
a
n
g
li
o
n
Cy
st
Re
g
io
n
Ex
trac
ti
o
n
f
ro
m
Ultras
o
u
n
d
Im
a
g
e
s
Us
i
n
g
P
o
ss
ib
il
isti
c
C
-
M
e
a
n
s
Clu
ste
rin
g
M
e
th
o
d
,
”
J
o
u
rn
a
l
o
f
in
fo
rm
a
t
io
n
a
n
d
c
o
mm
u
n
ica
ti
o
n
c
o
n
v
e
rg
e
n
c
e
e
n
g
in
e
e
rin
g
,
v
o
l.
5
,
n
o
.
1
,
p
p
.
4
9
-
5
2
,
2
0
1
7
.
[2
0
]
H.
M
.
M
o
f
tah
,
e
t
a
l
.
,
“
A
d
a
p
ti
v
e
k
-
me
a
n
s
c
lu
ste
rin
g
a
lg
o
rit
h
m
f
o
r
M
R
b
re
a
st
ima
g
e
se
g
m
e
n
tatio
n
,
”
Ne
u
ra
l
Co
mp
u
t
in
g
a
n
d
Ap
p
li
c
a
t
io
n
s
,
v
o
l.
2
4
,
n
o
.
7
-
8
,
p
p
.
1
9
1
7
-
1
9
2
8
,
2
0
1
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
201
9
:
5
2
05
-
5
2
1
0
5210
[2
1
]
T
.
H.
S
a
rm
a
,
e
t
a
l
.
,
“
A
h
y
b
rid
a
p
p
ro
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
,
”
I
n
ter
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
M
a
c
h
in
e
L
e
a
r
n
in
g
a
n
d
Cy
b
e
rn
e
ti
c
s
,
v
o
l.
4
,
n
o
.
2
,
p
p
.
1
0
7
-
1
1
7
,
2
0
1
3
.
[2
2
]
K.
B.
Kim
a
n
d
D.
H.
S
o
n
g
,
“
D
e
fe
c
t
d
e
tec
ti
o
n
m
e
th
o
d
u
sin
g
f
u
z
z
y
stre
tch
in
g
a
n
d
A
RT
2
lea
rn
in
g
f
ro
m
c
e
ra
m
i
c
im
a
g
e
s,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
S
o
f
twa
re
En
g
i
n
e
e
rin
g
a
n
d
Its
A
p
p
li
c
a
ti
o
n
s
,
v
o
l.
8
,
n
o
.
9
,
p
p
.
2
9
-
3
8
,
2
0
1
4
.
[2
3
]
A
.
K.
Ja
in
,
e
t
a
l
.
,
“
Da
ta clu
ste
rin
g
:
a
re
v
ie
w
,
”
ACM
c
o
mp
u
ti
n
g
su
rv
e
y
s
,
v
o
l.
3
1
,
n
o
.
3
,
p
p
.
2
6
4
-
3
2
3
,
1
9
9
9
.
[2
4
]
K.
B.
Kim
a
n
d
D.
H.
S
o
n
g
,
“
A
u
to
m
a
ti
c
D
e
f
e
c
t
In
sp
e
c
ti
o
n
w
it
h
Ad
a
p
ti
v
e
Bin
a
riza
ti
o
n
a
n
d
Bre
se
n
h
a
m
'
s
a
lg
o
rit
h
m
f
o
r
S
p
e
c
tac
le
L
e
n
s
P
ro
d
u
c
ts,
”
J
o
u
rn
a
l
o
f
th
e
Ko
re
a
In
stit
u
te
o
f
In
f
o
rm
a
ti
o
n
a
n
d
Co
mm
u
n
ica
t
io
n
E
n
g
i
n
e
e
rin
g
,
v
o
l.
2
1
,
n
o
.
7
,
p
p
.
1
4
2
9
-
1
4
3
4
,
2
0
1
7
.
[2
5
]
R.
C.
G
o
n
z
a
les
a
n
d
R.
E.
W
o
o
d
s,
Dig
it
a
l
Ima
g
e
p
ro
c
e
ss
in
g
(
3
td
E
d
.
)
,
P
re
n
ti
c
e
Ha
ll
,
NJ
,
USA
,
2
0
0
7
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
K
w
a
n
g
B
a
e
k
K
i
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
t
h
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
U
n
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
ro
f
e
ss
o
r
a
t
th
e
Div
isio
n
o
f
C
o
m
p
u
ter
a
n
d
I
n
f
o
rm
a
ti
o
n
En
g
i
n
e
e
rin
g
,
S
il
la
Un
iv
e
rsit
y
,
Ko
re
a
.
He
is
c
u
rre
n
tl
y
a
n
a
ss
o
c
iate
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
I
n
f
o
rm
a
ti
o
n
S
y
st
e
m
s
a
n
d
T
h
e
Jo
u
rn
a
l
o
f
In
f
o
rm
a
ti
o
n
a
n
d
C
o
m
m
u
n
ica
ti
o
n
Co
n
v
e
rg
e
n
c
e
En
g
in
e
e
rin
g
.
His
re
se
a
r
c
h
in
tere
sts
in
c
lu
d
e
m
a
c
h
in
e
lea
rn
in
g
,
f
u
z
z
y
c
lu
ste
rin
g
a
n
d
f
u
z
z
y
c
o
n
tro
l
sy
ste
m
,
d
a
ta
m
in
in
g
,
ima
g
e
p
ro
c
e
ss
in
g
,
a
n
d
b
i
o
in
f
o
rm
a
ti
c
s.
Do
o
H
e
o
n
S
o
n
g
re
c
e
iv
e
d
h
is
B.
S
.
f
ro
m
S
e
o
u
l
Na
ti
o
n
a
l
U
n
iv
e
rsit
y
in
1
9
8
1
a
n
d
M
.
S
.
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
l
o
gy
in
1
9
8
3
i
n
Co
m
p
u
ter
S
c
ien
c
e
.
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
a
t
Irv
in
e
in
1
9
9
4
.
He
h
a
s
b
e
e
n
a
p
r
o
f
e
ss
o
r
a
t
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
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
ter
e
sts
in
c
lu
d
e
a
rti
f
icia
l
in
telli
g
e
n
c
e
,
f
u
z
z
y
s
y
ste
m
s,
im
a
g
e
p
ro
c
e
ss
in
g
,
a
n
d
c
o
m
p
u
ter
g
a
m
e
d
e
sig
n
.
He
is
c
u
rre
n
tl
y
th
e
a
ss
o
c
iate
e
d
it
o
r
o
f
Jo
u
rn
a
l
o
f
In
f
o
rm
a
ti
o
n
a
n
d
Co
m
u
n
ica
ti
o
n
C
o
n
v
e
rg
e
n
c
e
En
g
in
e
e
in
g
.
S
a
n
g
-
S
e
o
k
Y
u
n
re
c
e
iv
e
d
th
e
B
.
S
.
in
M
e
c
h
a
n
ica
l
En
g
in
e
e
ri
n
g
f
ro
m
In
je
Un
iv
e
rsit
y
in
2
0
0
2
,
a
n
d
h
is
M
.
S
.
i
n
M
e
c
h
a
tro
n
ics
En
g
i
n
e
e
rin
g
f
ro
m
Gw
a
n
g
ju
In
stit
u
te
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
(G
IS
T
),
Ko
re
a
,
in
2
0
0
5
.
He
re
c
e
iv
e
d
h
is
P
h
.
D.
i
n
M
e
c
h
a
n
i
c
a
l
En
g
in
e
e
rin
g
f
ro
m
Ko
re
a
Un
iv
e
rsit
y
in
2
0
1
3
.
He
w
a
s
a
re
se
a
rc
h
e
r
a
t
th
e
Ko
re
a
I
n
stit
u
te
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
(KIST
)
f
ro
m
2
0
0
5
to
2
0
1
7
.
He
is
c
u
rre
n
tl
y
a
n
a
ss
istan
t
p
r
o
f
e
ss
o
r
a
t
th
e
Di
v
isio
n
o
f
M
e
c
h
a
n
ica
l
Co
n
v
e
rg
e
n
c
e
En
g
in
e
e
rin
g
,
S
il
la
Un
iv
e
rsity
,
Ko
re
a
.
His
c
u
rre
n
t
re
se
a
rc
h
in
tere
sts
in
c
l
u
d
e
c
o
g
n
it
iv
e
c
o
n
tr
o
l
sy
ste
m
,
h
u
m
a
n
–
ro
b
o
t
i
n
tera
c
ti
o
n
,
a
n
d
so
c
ially
a
ss
isti
v
e
ro
b
o
ts.
Evaluation Warning : The document was created with Spire.PDF for Python.