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
,
Dec
em
b
er
201
6
,
p
p
.
3
1
6
1
~
3
1
7
3
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
6i
6
.
1
2
5
9
8
3161
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
M
o
del
-
ba
sed Au
t
o
m
a
tic
Seg
m
entat
io
n of Ascen
ding
Ao
rta fr
o
m
M
ulti
m
o
da
li
ty M
edica
l Data
No
ha
A.
Sea
da
,
Sa
f
w
a
t
H
a
m
a
d
,
M
o
s
t
a
f
a
G
.
M
.
M
o
s
t
a
f
a
S
c
ien
c
it
if
c
Co
m
p
u
ti
n
g
a
n
d
C
o
m
p
u
ter S
c
ien
c
e
De
p
a
rtm
e
n
ts
,
F
a
c
u
lt
y
o
f
Co
m
p
u
ter an
d
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
s
,
A
in
S
h
a
m
s Un
iv
e
r
sit
y
,
Eg
y
p
t
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
1
2
,
2
0
1
6
R
ev
i
s
ed
No
v
13
,
2
0
1
6
A
cc
ep
ted
No
v
27
,
2
0
1
6
A
u
to
m
a
ti
c
As
c
e
n
d
in
g
A
o
rta
S
e
g
m
e
n
tatio
n
is
o
n
e
o
f
th
e
im
p
o
rtan
t
ste
p
s
to
w
a
rd
s
a
u
to
m
a
ti
c
s
e
g
m
e
n
tatio
n
o
f
th
e
w
h
o
le
c
a
rd
iac
tree
.
T
h
is
p
a
p
e
r
p
re
se
n
ts
a
n
o
v
e
l
a
p
p
ro
a
c
h
f
o
r
th
e
a
u
to
m
a
ti
c
se
g
m
e
n
tatio
n
o
f
th
e
a
sc
e
n
d
in
g
a
o
r
ta
f
ro
m
t
w
o
i
m
a
g
in
g
m
o
d
a
li
ti
e
s:
CTA
(Co
m
p
u
ted
T
o
m
o
g
r
a
p
h
y
A
n
g
io
g
ra
p
h
y
)
a
n
d
P
C
-
M
RI
(
P
h
a
se
-
Co
n
tras
t
M
a
g
n
e
ti
c
Re
so
n
a
n
c
e
Im
a
g
e
s)
.
T
h
e
n
o
v
e
l
a
p
p
ro
a
c
h
is
a
n
a
lg
o
rit
h
m
th
a
t
w
o
rk
s
w
it
h
o
u
t
t
h
e
n
e
e
d
f
o
r
se
tt
in
g
m
a
n
u
a
l
se
e
d
p
o
in
ts
o
r
a
p
p
ly
in
g
p
re
p
ro
c
e
ss
in
g
ste
p
s
o
r
se
tt
in
g
a
re
g
io
n
o
f
in
tere
st.
In
ste
a
d
,
th
e
p
ro
p
o
se
d
a
l
g
o
rit
h
m
a
u
to
m
a
ti
c
a
ll
y
d
e
te
c
ts
a
n
d
se
g
m
e
n
ts
th
e
a
sc
e
n
d
in
g
a
o
rta
u
sin
g
a
n
a
sc
e
n
d
i
n
g
a
o
rta
m
o
d
e
l
b
u
i
lt
f
ro
m
it
s
a
n
a
to
m
ica
l
f
e
a
tu
re
s
.
T
h
e
p
ro
p
o
se
d
se
g
m
e
n
tatio
n
a
lg
o
r
it
h
m
b
e
g
in
s
w
it
h
a
o
rta
d
e
tec
ti
o
n
th
ro
u
g
h
f
e
a
tu
re
s
m
o
d
e
l
f
it
ti
n
g
a
u
g
m
e
n
ted
w
it
h
Ho
u
g
h
tran
sf
o
rm
,
w
h
e
re
th
e
a
sc
e
n
d
in
g
a
o
rta
is
id
e
n
ti
f
ied
f
ro
m
th
e
d
e
sc
e
n
d
in
g
a
o
rta
a
n
d
a
n
y
o
th
e
r
c
ircu
lar
stru
c
tu
re
s b
a
se
d
o
n
th
e
p
ro
p
o
se
d
m
o
d
e
l.
Af
ter d
e
te
c
ti
o
n
,
th
e
w
h
o
le as
c
e
n
d
in
g
a
o
rta
is
se
g
m
e
n
ted
u
p
f
ro
m
th
e
a
o
rti
c
a
rc
h
d
o
w
n
to
t
h
e
o
stia
p
o
i
n
ts
u
sin
g
a
n
o
v
e
l
a
u
to
m
a
ti
c
se
e
d
e
d
re
g
io
n
g
r
o
w
in
g
a
lg
o
rit
h
m
.
T
h
e
p
ro
p
o
se
d
a
lg
o
rit
h
m
is
f
u
ll
y
a
u
to
m
a
ti
c
,
w
o
rk
s
in
re
a
l
-
ti
m
e
a
n
d
ro
b
u
st
a
s
p
a
ra
m
e
ters
u
s
e
d
a
re
th
e
sa
m
e
f
o
r
a
ll
th
e
tes
ted
d
a
tas
e
ts.
T
h
e
d
e
tec
ti
o
n
a
n
d
se
g
m
e
n
tatio
n
o
f
th
e
a
sc
e
n
d
in
g
a
o
rta
su
c
c
e
e
d
e
d
in
a
ll
tes
t
c
a
se
s
a
c
q
u
ired
f
ro
m
th
e
t
wo
im
a
g
in
g
m
o
d
a
li
ti
e
s;
p
ro
v
in
g
th
e
ro
b
u
st
n
e
ss
o
f
th
e
p
ro
p
o
se
d
a
sc
e
n
d
in
g
a
o
rta
m
o
d
e
l
a
n
d
a
lg
o
rit
h
m
f
o
r
th
e
a
u
to
m
a
ti
c
se
g
m
e
n
tatio
n
p
ro
c
e
ss
e
v
e
n
o
n
d
a
ta
f
ro
m
d
if
fe
re
n
t
m
o
d
a
li
ti
e
s
a
n
d
d
if
f
e
r
e
n
t
sc
a
n
n
e
r
ty
p
e
s.
T
h
e
a
c
c
u
ra
c
y
o
f
th
e
se
g
m
e
n
tatio
n
h
a
s
a
m
e
a
n
Dic
e
S
im
il
a
rit
y
Co
e
ff
icie
n
t
(DSC)
o
f
9
4
.
7
2
%
f
o
r
CTA
d
a
tas
e
ts
a
n
d
9
7
.
1
3
%
f
o
r
P
C
-
M
RI
d
a
tas
e
ts.
K
ey
w
o
r
d
:
An
g
io
g
r
ap
h
y
(
C
T
A
)
Ascen
d
i
n
g
ao
r
ta
s
e
g
m
en
ta
tio
n
Au
to
m
a
tic
s
e
g
m
en
ta
tio
n
C
o
m
p
u
ted
t
o
m
o
g
r
ap
h
y
P
h
ase
-
co
n
tr
ast
m
ag
n
etic
R
eso
n
a
n
ce
i
m
ag
e
s
(
P
C
-
M
R
I
)
Seed
ed
r
eg
io
n
g
r
o
w
in
g
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
:
No
h
a
A
.
Sead
a,
Scien
cit
if
c
C
o
m
p
u
ti
n
g
a
n
d
C
o
m
p
u
ter
Scie
n
ce
Dep
ar
t
m
e
n
t
s
,
Facu
lt
y
o
f
C
o
m
p
u
ter
an
d
I
n
f
o
r
m
atio
n
Scien
ce
s
,
A
i
n
S
h
a
m
s
U
n
i
v
er
s
it
y
,
E
g
y
p
t
.
E
m
ail:
n
o
h
a_
s
ab
o
u
r
@
cis.as
u
.
ed
u
.
eg
1.
I
NT
RO
D
UCT
I
O
N
Fo
r
c
ar
d
io
lo
g
is
ts
;
in
s
p
e
ctin
g
t
h
e
v
ascu
lar
s
t
r
u
ctu
r
es
is
o
f
v
er
y
h
ig
h
i
m
p
o
r
tan
c
e
to
ass
es
s
p
ati
en
t'
s
ca
r
d
io
v
as
cu
la
r
r
is
k
.
C
u
r
r
en
t
d
ev
e
lo
p
m
en
tal
te
ch
n
iq
u
es
in
i
m
ag
in
g
m
o
d
alit
ies
in
clu
d
in
g
C
T
A
(
C
o
m
p
u
ted
T
o
m
o
g
r
a
p
h
y
A
n
g
io
g
r
ap
h
y
)
an
d
P
C
-
MR
I
(
P
h
ase
-
C
o
n
tr
ast
M
ag
n
etic
R
es
o
n
an
c
e
I
m
ag
es)
h
a
s
b
r
o
u
g
h
t
at
ten
ti
o
n
to
th
e
p
o
s
s
ib
ilit
y
f
o
r
n
o
n
-
in
v
as
iv
e
ass
ess
m
en
t
of
C
A
D
(
C
o
r
o
n
ar
y
A
r
ter
y
Dis
ea
s
e
)
p
a
tien
ts
.
T
h
is
p
a
p
e
r
f
o
cu
s
es
o
n
s
eg
m
en
tin
g
th
e
b
eg
in
n
in
g
o
f
th
e
c
ar
d
i
ac
tr
ee
w
h
ich
is
th
e
as
ce
n
d
in
g
a
o
r
ta
b
eg
in
n
in
g
f
r
o
m
th
e
ao
r
t
ic
a
r
ch
d
o
w
n
to
th
e
o
s
tia
p
o
in
ts
(
f
r
o
m
w
h
ich
th
e
co
r
o
n
a
r
ies
em
er
g
e)
,
s
ee
Fig
u
r
e
1
;
f
r
o
m
b
o
th
C
T
A
an
d
P
C
-
MRI
im
ag
es.
Ou
r
m
ain
o
b
jec
tiv
e
i
s
to
a
ch
iev
e
ac
cu
r
ate
s
eg
m
en
tati
o
n
o
f
th
e
as
ce
n
d
in
g
a
o
r
ta
to
h
el
p
in
m
u
ltip
le
f
u
r
th
er
p
r
o
ce
s
s
in
g
.
I
n
C
T
A
im
ag
es
b
ein
g
ab
le
t
o
au
t
o
m
atica
l
ly
s
eg
m
en
t
th
e
ascen
d
in
g
a
o
r
t
a
an
d
d
e
te
r
m
in
e
th
e
o
s
ti
a
l
o
ca
ti
o
n
s
th
at
r
esi
d
e
at
th
e
lat
er
al
s
i
d
es
o
f
th
e
s
eg
m
en
ted
asc
en
d
in
g
ao
r
ta
;
w
ill
lead
t
o
ef
f
icien
t
au
t
o
m
atic
s
ee
d
in
g
f
o
r
h
ea
r
t
c
o
r
o
n
ar
ies
s
eg
m
en
tatio
n
.
A
n
d
f
o
r
P
C
-
MRI
im
ag
es;
th
e
a
cc
u
r
a
t
e
s
eg
m
en
tatio
n
o
f
th
e
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
:
3
1
6
1
–
3
173
3162
ascen
d
in
g
a
o
r
ta
h
e
lp
s
q
u
an
t
if
y
b
l
o
o
d
f
l
o
w
f
o
r
ass
ess
in
g
th
e
ca
r
d
io
v
as
cu
la
r
s
y
s
tem
lo
o
k
in
g
f
o
r
s
o
m
e
d
is
e
ases
lik
e
a
o
r
tic
n
ar
r
o
w
in
g
k
n
o
w
n
as
A
o
r
t
ic
C
o
a
r
ct
ati
o
n
[
1
]
.
F
o
r
th
e
au
t
o
m
atic
s
eg
m
en
tati
o
n
p
r
o
ce
s
s
;
ascen
d
in
g
ao
r
t
a
f
e
atu
r
es
m
o
d
el
is
p
r
o
p
o
s
ed
,
th
at
is
b
u
ilt
b
ase
d
o
n
th
e
a
s
ce
n
d
in
g
a
o
r
ta
an
at
o
m
ical
f
ea
t
u
r
es.
T
h
ese
f
ea
tu
r
es
ar
e
s
h
a
p
e
(
ci
r
cu
l
ar
/el
li
p
ti
ca
l
)
,
s
iz
e,
an
at
o
m
ical
l
o
c
ati
o
n
a
n
d
in
t
en
s
ity
.
T
h
e
s
eg
m
en
tati
o
n
a
lg
o
r
ith
m
g
o
e
s
th
r
o
u
g
h
tw
o
m
ain
s
tag
es
:
P
a
r
ti
al
an
d
Fu
ll
as
ce
n
d
in
g
ao
r
t
a
s
e
g
m
en
tatio
n
.
I
n
th
e
f
ir
s
t
s
t
ag
e;
th
e
asc
en
d
in
g
a
o
r
t
a
is
d
e
te
cte
d
an
d
i
d
en
t
if
ie
d
f
r
o
m
o
th
er
s
im
ilar
s
t
r
u
ctu
r
es
u
s
in
g
Ho
u
g
h
tr
an
s
f
o
r
m
f
o
r
d
et
ec
ti
n
g
cir
cu
l
ar
/el
li
p
ti
ca
l
s
tr
u
ctu
r
es
au
g
m
en
ted
w
ith
th
e
m
o
d
el
o
f
th
e
asc
en
d
in
g
a
o
r
ta
.
T
h
e
o
u
tp
u
t
o
f
th
e
f
i
r
s
t
s
tag
e
is
p
a
r
t
o
f
th
e
ascen
d
in
g
a
o
r
t
a
b
ein
g
s
eg
m
en
ted
(
th
is
p
a
r
t o
f
th
e
asc
en
d
in
g
a
o
r
ta
w
h
er
e
its
s
h
a
p
e
is
u
n
if
o
r
m
l
y
cir
cu
l
ar
)
.
I
n
th
e
s
ec
o
n
d
s
tag
e
,
th
e
r
em
ain
in
g
p
a
r
t
o
f
th
e
as
ce
n
d
in
g
a
o
r
ta
is
s
eg
m
en
ted
u
s
in
g
a
p
r
o
p
o
s
e
d
m
o
d
i
f
ied
v
er
s
io
n
o
f
th
e
s
ee
d
e
d
r
eg
i
o
n
g
r
o
w
in
g
alg
o
r
ith
m
;
ce
n
te
r
t
o
ed
g
e
r
ay
-
s
ea
r
ch
-
b
ase
d
p
r
o
p
ag
a
ti
o
n
r
eg
io
n
g
r
o
w
in
g
.
T
h
e
s
eg
m
en
tatio
n
o
n
b
o
th
im
ag
in
g
m
o
d
alit
ies
h
as
b
ee
n
v
a
li
d
at
ed
v
er
s
u
s
m
an
u
al
s
eg
m
en
tatio
n
an
d
d
i
ce
s
im
ila
r
ity
co
ef
f
icien
t
is
ca
l
cu
lat
e
d
.
T
h
e
p
r
o
p
o
s
e
d
s
eg
m
en
tat
i
o
n
alg
o
r
i
th
m
s
u
cc
ee
d
e
d
t
o
d
ete
ct
an
d
s
eg
m
en
t
th
e
ascen
d
in
g
ao
r
t
a,
w
ith
s
a
m
e
p
ar
am
eter
s
v
alu
e
s
et
o
v
e
r
al
l
th
e
tes
t
ca
s
es,
ev
en
o
n
d
atas
ets
w
ith
ar
tif
ac
ts
(
as
in
d
ic
ate
d
in
th
e
r
esu
lts
an
d
d
is
cu
s
s
io
n
s
ec
ti
o
n
)
.
T
h
is
p
r
o
v
es
th
e
r
o
b
u
s
tn
ess
o
f
th
e
a
lg
o
r
ith
m
,
in
ad
d
i
ti
o
n
t
o
th
e
a
cc
u
r
ac
y
at
tain
e
d
p
r
o
v
es
th
e
r
el
ia
b
ili
ty
o
f
th
e
ap
p
r
o
ac
h
f
o
r
c
lin
ic
al
u
s
e.
Seg
m
en
tatio
n
o
f
th
e
as
ce
n
d
i
n
g
ao
r
t
a
m
eth
o
d
o
lo
g
i
es
m
en
tio
n
e
d
in
l
ite
r
a
tu
r
e
v
a
r
i
es
f
r
o
m
s
em
i
-
au
to
m
atic
t
o
au
t
o
m
atic
m
eth
o
d
o
l
o
g
ies
.
Sem
i
-
au
to
m
atic
m
eth
o
d
o
l
o
g
ies
m
ain
ly
r
ely
o
n
a
m
an
u
al
s
ee
d
p
o
in
t
en
te
r
e
d
b
y
th
e
u
s
er
in
th
e
m
id
d
le
o
f
th
e
a
o
r
ta
o
r
o
n
th
e
a
o
r
ta
t
o
p
s
li
ce
.
S
o
m
e
o
th
e
r
m
eth
o
d
o
l
o
g
ies
d
ef
in
e
a
r
eg
i
o
n
o
f
in
t
er
est
o
f
v
ascu
l
ar
s
tr
u
ctu
r
es
in
o
r
d
e
r
t
o
m
in
i
m
i
ze
th
e
s
ea
r
ch
in
g
a
r
e
a
f
o
r
th
e
ao
r
t
a
s
eg
m
en
tatio
n
p
r
o
ce
s
s
.
F
r
o
m
th
e
s
em
i
-
au
t
o
m
atic
m
eth
o
d
o
l
o
g
ies
m
en
ti
o
n
e
d
in
lit
er
atu
r
e:
X
ie
e
t
al.
[
2
]
b
eg
in
th
eir
s
eg
m
en
tatio
n
b
y
s
ettin
g
a
m
an
u
al
s
ee
d
p
o
in
t in
s
i
d
e
th
e
a
o
r
ta
lu
m
en
,
th
en
u
s
ed
a
cy
lin
d
r
ica
l m
o
d
el
f
itti
n
g
in
th
e
3
D
im
ag
e
s
p
a
ce
t
o
t
r
ac
k
th
e
a
o
r
ta
c
en
te
r
lin
e.
B
o
ck
et
a
l.
[
3
]
u
s
ed
a
r
eg
io
n
g
r
o
w
in
g
alg
o
r
i
th
m
f
o
r
s
eg
m
en
tin
g
th
e
a
o
r
t
a
an
d
o
b
t
ain
e
d
i
ts
s
ee
d
b
y
m
an
u
ally
s
elec
t
in
g
a
s
in
g
le
s
ee
d
p
o
in
t
in
s
i
d
e
th
e
asc
en
d
i
n
g
ao
r
ta
a
b
o
v
e
th
e
co
r
o
n
ar
y
o
s
ti
a
lo
ca
t
io
n
s
,
w
h
ile
Hen
n
em
u
th
et
al.
[
4
]
m
an
u
ally
s
elec
t
th
e
s
ee
d
p
o
in
t
in
th
e
m
id
d
l
e
o
f
th
e
a
o
r
ta
ab
o
v
e
th
e
f
ir
s
t
c
o
r
o
n
a
r
y
ar
t
er
y
.
B
o
th
Ki
ts
la
ar
et
al.
[
5
]
an
d
B
o
u
r
ao
u
i e
t a
l.
[
6
]
is
o
l
ate
d
th
e
h
ea
r
t
r
eg
io
n
as
th
e
ir
r
eg
i
o
n
o
f
in
te
r
es
t; s
o
as t
o
m
in
im
ize
th
e
co
m
p
u
tat
io
n
al
c
o
s
t
.
Kits
la
a
r
et
a
l.
u
s
e
d
th
e
H
o
u
g
h
tr
an
s
f
o
r
m
alg
o
r
ith
m
to
d
et
ec
t
th
e
asc
en
d
in
g
a
o
r
ta
as
ci
r
cl
es
an
d
th
ey
is
o
l
ate
d
th
e
h
ea
r
t
r
eg
io
n
u
s
in
g
a2
D
b
a
ll
o
o
n
m
o
d
el
in
f
lati
o
n
.
T
h
ey
th
en
u
s
ed
g
r
a
d
i
en
t
in
f
o
r
m
atio
n
to
o
b
ta
in
h
ea
r
t
c
o
n
t
o
u
r
an
d
a
p
p
li
e
d
c
o
n
n
ec
t
e
d
c
o
m
p
o
n
en
t
an
aly
s
is
o
n
th
e
is
o
l
ate
d
h
ea
r
t
r
eg
i
o
n
an
d
c
r
ea
t
ed
a
l
is
t
o
f
v
ess
els
ca
n
d
i
d
a
te
l
is
t.
T
h
ey
u
s
ed
th
e
t
o
p
tw
o
p
o
i
n
ts
f
r
o
m
th
at
l
is
t
as
th
e
s
t
o
p
p
in
g
c
r
i
te
r
ia
f
o
r
th
e
r
eg
io
n
g
r
o
w
er
th
at
s
eg
m
en
ts
th
e
a
s
ce
n
d
in
g
ao
r
t
a.
B
o
u
r
a
o
u
i e
t
al
.
d
o
w
n
s
a
m
p
led
th
e
in
p
u
t
im
ag
es
f
o
r
c
o
s
t
r
e
d
u
ct
io
n
an
d
a
p
p
li
e
d
G
r
ay
-
lev
el
h
it
-
or
-
m
is
s
tr
an
s
f
o
r
m
(
GL
HM
T
)
i
n
co
n
j
u
n
cti
o
n
w
ith
d
if
f
er
en
t s
tr
u
ctu
r
in
g
el
em
en
ts
f
o
r
s
eg
m
en
tin
g
th
e
h
ea
r
t
r
eg
io
n
,
th
e
ao
r
t
a
an
d
th
e
c
o
r
o
n
ar
ies.
Fro
m
th
e
au
t
o
m
atic
s
eg
m
en
tatio
n
m
eth
o
d
o
l
o
g
i
es
is
th
e
o
n
e
p
r
esen
t
ed
b
y
Sau
r
et
al.
[
7
]
.
T
h
ey
b
eg
an
th
eir
s
ea
r
ch
in
x
an
d
y
d
ir
e
cti
o
n
s
in
ev
e
r
y
C
T
A
im
ag
e
s
lice
an
d
u
s
e
d
a
tw
o
-
lev
el
th
r
esh
o
l
d
t
o
f
in
d
th
e
a
o
r
ta
cir
cle
ci
r
cu
m
f
er
en
ce
.
A
lth
o
u
g
h
th
eir
w
o
r
k
s
u
c
c
ee
d
e
d
f
o
r
d
ete
ctin
g
th
e
ascen
d
in
g
a
o
r
ta
c
ir
cu
m
f
er
en
ce
,
th
eir
w
o
r
k
w
o
u
ld
h
av
e
b
e
en
m
o
r
e
ef
f
icien
t;
if
th
ey
h
av
e
r
eli
e
d
o
n
th
e
an
a
to
m
ical
f
ea
tu
r
es
o
f
t
h
e
asc
en
d
in
g
ao
r
t
a
(
lik
e
asc
en
d
in
g
a
o
r
ta
g
eo
m
etr
ic
s
h
a
p
e
,
d
iam
eter
r
an
g
e
an
d
lo
c
ati
o
n
w
ith
r
esp
ec
t
to
o
th
e
r
o
r
g
an
s
)
th
a
t
w
o
u
ld
h
av
e
h
el
p
e
d
th
em
m
in
i
m
ize
it
er
ati
o
n
s
ti
ll
f
in
d
in
g
th
e
ascen
d
in
g
a
o
r
ta
ci
r
cu
m
f
er
en
ce
.
A
ll
th
e
p
r
ev
i
o
u
s
w
o
r
k
m
en
tio
n
ed
is
a
p
p
lie
d
o
n
C
T
A
d
at
ase
ts
,
w
h
ile
Her
m
en
t
et
al.
[
8
]
an
d
A
l
-
Ag
a
m
y
at
al.
[
9
]
s
eg
m
en
ted
th
e
ao
r
t
a
f
r
o
m
P
C
-
MRI
im
ag
es.
H
er
m
en
t
et
al
.
b
eg
in
s
th
e
s
eg
m
en
tat
io
n
p
r
o
c
ess
b
y
m
an
u
all
y
d
ef
in
in
g
a
r
ec
tan
g
u
la
r
r
eg
i
o
n
o
f
in
te
r
es
t
c
o
n
t
ain
in
g
th
e
a
o
r
ta
.
T
h
e
d
y
n
a
m
ic
tim
e
f
r
a
m
es
o
f
th
e
P
C
-
MRI
im
ag
es
ar
e
av
e
r
ag
ed
o
v
er
tim
e
w
ith
in
th
at
r
eg
io
n
.
T
h
ey
th
en
u
s
e
a
2
D+
t
d
ef
o
r
m
ab
le
s
u
r
f
a
ce
m
o
d
el
t
o
s
eg
m
en
t
th
e
ao
r
t
a.
A
l
-
A
g
a
m
y
at
al
.
im
p
lem
en
ts
s
em
i
-
au
to
m
ated
s
eg
m
en
tatio
n
b
y
ask
in
g
th
e
u
s
e
r
t
o
cli
ck
tw
o
p
o
in
ts
in
s
i
d
e
th
e
a
o
r
ta
.
A
f
ter
w
ar
d
s
th
ey
s
eg
m
en
t
th
e
ascen
d
in
g
an
d
d
esc
en
d
in
g
a
o
r
ta
cr
o
s
s
s
e
cti
o
n
s
u
s
in
g
a
m
o
d
if
ied
v
e
r
s
i
o
n
o
f
th
e
ac
tiv
e
co
n
t
o
u
r
m
o
d
els.
A
f
ter
an
aly
zin
g
th
e
p
r
ev
i
o
u
s
w
o
r
k
in
th
e
ar
ea
o
f
asc
en
d
in
g
ao
r
ta
s
eg
m
en
tati
o
n
,
it
w
as
o
b
s
er
ev
d
th
at
u
s
in
g
m
an
u
al
s
ee
d
p
o
i
n
ts
y
iel
d
s
a
s
o
lu
ti
o
n
th
a
t
y
et
n
ee
d
s
u
s
er
in
te
r
a
cti
o
n
an
d
th
e
r
esu
lts
o
f
th
e
a
lg
o
r
ith
m
is
h
ig
h
ly
d
ep
en
d
en
t
o
n
an
ac
cu
ar
ate
in
iti
ali
za
t
io
n
.
A
ls
o
,
s
eg
m
en
tatio
n
m
eth
o
d
o
l
o
g
ies
th
at
n
ee
d
s
a
r
eg
i
o
n
o
f
in
ter
est
(
R
O
I
)
to
b
e
s
p
ec
if
ie
d
at
th
e
b
eg
in
n
in
g
;
ad
d
s
ex
t
r
a
p
r
o
c
ess
in
g
to
th
e
s
eg
m
en
tati
o
n
p
ip
e
lin
e
an
d
als
o
th
e
r
esu
lts
w
ill
d
e
p
en
d
o
n
th
e
a
c
cu
r
a
te
R
O
I
s
p
e
cif
i
ca
ti
o
n
.
M
o
r
e
o
v
e
r
,
au
t
o
m
atic
m
eth
o
d
o
lo
g
ies
th
a
t
s
e
a
r
ch
th
e
w
h
o
le
im
ag
e
f
o
r
d
et
ec
tin
g
th
e
a
o
r
ta
r
eg
io
n
g
o
es
in
to
m
u
ltip
le
it
er
ati
o
n
s
ti
ll
f
in
d
in
g
th
e
ao
r
t
a
c
i
r
cu
m
f
er
en
ce
w
h
ich
r
esu
lts
in
t
o
l
o
n
g
p
r
o
ce
s
s
in
g
tim
es.
T
h
is
in
a
d
d
iti
o
n
t
o
u
s
in
g
m
u
ltip
le
th
r
esh
o
l
d
s
th
a
t
n
ee
d
v
alu
e
-
tu
n
in
g
f
o
r
im
ag
es
o
f
d
if
f
er
en
t
v
o
lu
m
es
an
d
a
cq
u
i
r
e
d
u
s
in
g
d
if
f
er
en
t
s
ca
n
n
er
ty
p
es;
y
eild
s
a
n
o
n
-
g
e
n
er
i
c
s
eg
m
en
tatio
n
alg
o
r
ith
m
.
I
n
th
is
p
ap
e
r
,
a
f
u
lly
au
t
o
m
atic
m
eth
o
d
o
l
o
g
y
is
p
r
esen
te
d
th
at
av
o
i
d
s
all
th
e
d
r
aw
b
ac
k
s
o
b
s
e
r
v
e
d
in
th
e
p
r
ev
i
o
u
s
w
o
r
k
.
T
h
e
asc
en
d
in
g
ao
r
t
a
is
s
eg
m
en
ted
w
ith
o
u
t
th
e
n
ee
d
o
f
an
y
m
an
u
al
s
ee
d
p
o
in
ts
,
o
r
a
r
eg
i
o
n
o
f
in
te
r
es
t t
o
b
e
d
ef
in
e
d
,
o
r
b
l
i
n
d
s
ca
n
n
in
g
o
f
th
e
im
ag
e
s
lic
e
in
all
d
i
r
e
cti
o
n
s
t
o
s
e
ar
ch
f
o
r
t
h
e
ao
r
t
a
r
eg
i
o
n
.
W
e
r
ath
er
d
ef
in
e
d
an
as
ce
n
d
in
g
a
o
r
ta
f
e
atu
r
es
m
o
d
el
th
at
is
au
g
m
en
ted
w
ith
o
u
r
p
r
o
p
o
s
ed
m
eth
o
d
o
lg
y
an
d
y
ield
s
s
u
cc
ess
f
u
l
au
t
o
m
atic
d
et
ec
t
io
n
an
d
i
d
en
t
if
ica
ti
o
n
o
f
th
e
asc
e
n
d
in
g
ao
r
t
a
in
an
ef
f
ic
ien
t
w
a
y
in
all
th
e
d
a
tase
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
Mo
d
el
-
b
a
s
ed
A
u
t
o
ma
tic
S
eg
m
en
ta
tio
n
o
f A
s
ce
n
d
in
g
A
o
r
ta
fr
o
m
Mu
ltimo
d
a
lity
....
(
N
o
h
a
A
.
S
ea
d
a
)
3163
p
r
o
v
i
d
e
d
f
r
o
m
th
e
tw
o
i
m
ag
in
g
m
o
d
al
iti
es
(
C
T
A
/
P
C
-
MR
I
)
a
n
d
th
is
is
p
r
o
v
e
d
b
y
th
e
ex
p
e
r
im
en
tal
r
esu
lts
an
d
co
m
p
a
r
is
o
n
d
o
n
e
w
ith
p
r
ev
i
o
u
s
w
o
r
k
in
t
er
m
s
o
f
ac
cu
r
ac
y
an
d
p
r
o
ce
s
s
in
g
tim
es.
T
h
e
p
a
p
er
is
o
r
g
an
i
ze
d
as
f
o
ll
o
w
s
:
Secti
o
n
2
p
r
es
en
ts
t
h
e
p
r
o
p
o
s
e
d
au
t
o
m
atic
ascen
d
in
g
a
o
r
ta
s
eg
m
en
tatio
n
m
eth
o
d
o
lo
g
y
.
Se
cti
o
n
3
p
r
es
en
ts
th
e
r
esu
l
ts
an
d
d
is
cu
s
s
i
o
n
an
d
p
er
f
o
r
m
an
ce
m
ea
s
u
r
es
(
ac
cu
r
ac
y
an
d
p
r
o
c
ess
in
g
tim
e)
.
F
in
ally
c
o
n
clu
s
i
o
n
is
p
r
esen
t
e
d
in
S
e
cti
o
n
4
.
Fig
u
r
e
1
.
T
h
e
as
c
en
d
in
g
a
o
r
ta
d
e
p
i
cte
d
f
r
o
m
th
e
a
o
r
ti
c
ar
ch
d
o
w
n
to
o
s
ti
a
p
o
in
ts
[
1
0
]
2.
P
RO
P
O
SE
D
ASC
E
ND
I
N
G
AO
RT
A
AU
T
O
M
AT
I
C
SE
G
M
E
NT
A
T
I
O
N
AP
P
RO
AC
H
I
n
t
h
is
s
ec
tio
n
,
t
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
f
o
r
th
e
au
to
m
atic
s
eg
m
e
n
tatio
n
o
f
th
e
asce
n
d
in
g
ao
r
ta
i
s
p
r
esen
ted
.
T
h
e
ascen
d
in
g
ao
r
t
a
is
cir
cu
lar
/ellip
tical
i
n
s
h
ap
e
in
m
u
ltip
le
s
eq
u
en
t
ial
i
m
a
g
es
(
b
eg
in
n
i
n
g
f
r
o
m
th
e
cr
an
ial
th
ir
d
o
f
th
e
v
o
lu
m
e)
[
7
]
,
[
1
1
]
,
an
d
th
en
its
s
h
ap
e
b
eg
in
s
to
d
ef
o
r
m
in
later
co
n
s
eq
u
e
n
t
i
m
a
g
es.
B
ased
o
n
th
is
o
b
s
er
v
atio
n
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
f
o
r
au
to
m
atica
ll
y
s
e
g
m
en
tin
g
t
h
e
f
u
ll
a
s
ce
n
d
in
g
ao
r
ta
is
d
iv
id
ed
in
to
t
w
o
m
ai
n
s
ta
g
e
s
;
p
ar
tial
an
d
f
u
ll
s
eg
m
e
n
tatio
n
,
s
ee
Fi
g
u
r
e
2
.
T
h
e
o
u
tp
u
t
o
f
th
e
f
ir
s
t
s
ta
g
e
is
p
ar
t
o
f
t
h
e
u
n
i
f
o
r
m
l
y
cir
cu
lar
asce
n
d
in
g
ao
r
ta
b
ei
n
g
s
e
g
m
en
ted
.
I
n
t
h
e
s
ec
o
n
d
s
ta
g
e
,
t
h
e
s
e
g
m
e
n
ted
p
ar
t
is
u
s
ed
a
s
a
s
ee
d
f
o
r
s
eg
m
en
t
in
g
th
e
r
e
m
ain
i
n
g
asce
n
d
in
g
ao
r
ta
p
ar
t
t
o
ac
h
iev
e
f
u
ll
s
eg
m
e
n
tatio
n
o
f
th
e
ascen
d
i
n
g
ao
r
ta
f
r
o
m
t
h
e
ao
r
tic
ar
ch
d
o
w
n
t
o
th
e
o
s
tia
p
o
in
ts
.
Mo
r
eo
v
er
to
m
in
i
m
ize
co
m
p
u
tat
io
n
s
co
m
p
le
x
it
y
a
n
d
to
s
u
cc
e
s
s
f
u
ll
y
id
e
n
ti
f
y
t
h
e
asce
n
d
in
g
ao
r
ta
f
r
o
m
o
t
h
er
s
i
m
ilar
s
t
r
u
ctu
r
e
s
in
t
h
e
i
m
ag
e,
a
n
asce
n
d
in
g
ao
r
ta
m
o
d
el
is
p
r
o
p
o
s
ed
.
T
h
e
m
o
d
el
h
elp
s
in
lo
ca
lizi
n
g
an
d
id
e
n
ti
f
y
in
g
th
e
asce
n
d
in
g
ao
r
ta
i
n
a
q
u
i
ck
m
a
n
n
er
w
it
h
n
o
n
ee
d
to
s
et
a
r
eg
io
n
o
f
in
t
er
est
o
r
d
o
an
y
p
r
ep
r
o
ce
s
s
in
g
o
n
th
e
v
o
lu
m
e
b
ef
o
r
e
t
h
e
asce
n
d
in
g
ao
r
ta
s
eg
m
e
n
tatio
n
a
n
d
p
er
f
o
r
m
an
c
e
is
y
et
r
ea
l
-
ti
m
e.
(
a)
P
a
r
tial A
s
ce
n
d
in
g
A
o
r
ta
Se
g
m
e
n
tat
io
n
(
b
)
Fu
ll Ascen
d
i
n
g
A
o
r
ta
Seg
m
en
tatio
n
Fig
u
r
e
2
.
A
s
ce
n
d
i
n
g
A
o
r
ta
Se
g
m
e
n
tat
io
n
Flo
w
C
h
ar
t
f
o
r
P
ar
tial a
n
d
Fu
ll
Se
g
m
e
n
tat
io
n
Sta
g
es
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
:
3
1
6
1
–
3
173
3164
2
.
1
.
P
ro
po
s
ed
Ascend
ing
Ao
rt
a
M
o
del
T
o
c
o
r
r
ec
tly
d
etec
t
t
h
e
asce
n
d
in
g
ao
r
ta
cr
o
s
s
s
ec
t
io
n
f
r
o
m
a
n
y
o
t
h
er
o
r
g
an
s
t
h
at
ar
e
s
i
m
ilar
i
n
s
tr
u
ct
u
r
e
m
a
k
es
b
u
ild
in
g
a
n
a
s
ce
n
d
i
n
g
ao
r
ta
m
o
d
el
an
es
s
e
n
tial
ad
d
itio
n
to
th
e
d
etec
tio
n
an
d
s
eg
m
e
n
tatio
n
p
r
o
ce
s
s
es.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
o
f
th
e
asce
n
d
in
g
ao
r
ta
i
s
b
u
ilt
b
ased
o
n
it
s
an
ato
m
i
ca
l
f
ea
t
u
r
es
.
T
h
ese
an
ato
m
ica
l
f
ea
t
u
r
es
ar
e:
g
eo
m
etr
ic
s
h
ap
e,
s
ize,
an
ato
m
ical
l
o
ca
tio
n
w
it
h
r
esp
ec
t
to
o
th
er
o
r
g
an
s
an
d
in
ten
s
it
y
v
alu
e
s
.
1.
Sh
ap
e:
T
h
e
asce
n
d
in
g
ao
r
ta
h
as
cir
c
u
lar
/ellip
tical
s
h
ap
e
[
7
]
,
[
1
2
]
f
r
o
m
t
h
e
ao
r
tic
ar
ch
d
o
w
n
to
o
s
tia
p
o
in
ts
,
s
ee
Fi
g
u
r
e
1.
2.
S
ize:
T
h
e
asce
n
d
i
n
g
ao
r
ta
d
iam
eter
i
s
b
i
g
g
er
th
a
n
th
at
o
f
t
h
e
d
esce
n
d
in
g
ao
r
ta
in
h
ea
l
th
y
p
atie
n
ts
.
T
h
e
n
o
r
m
al
d
ia
m
eter
o
f
th
e
a
s
ce
n
d
in
g
ao
r
ta
is
le
s
s
t
h
a
n
2
.
1
cm
/
m
2
an
d
th
e
n
o
r
m
al
d
ia
m
eter
o
f
th
e
d
esce
n
d
in
g
ao
r
ta
is
less
th
a
n
1
.
6
c
m
/
m
2
[
1
3
]
.
3.
A
n
ato
m
ical
L
o
ca
tio
n
:
T
h
e
asc
en
d
in
g
ao
r
ta
a
n
ato
m
ical
lo
ca
ti
o
n
w
it
h
r
esp
ec
t
to
o
th
er
o
r
g
a
n
s
;
i
s
t
h
e
n
ea
r
es
t
to
th
e
ce
n
ter
o
f
g
r
av
it
y
o
f
th
e
i
m
ag
e.
Fo
r
ev
er
y
d
etec
ted
cir
cu
lar
s
tr
u
ct
u
r
e
in
t
h
e
i
m
a
g
e,
th
e
ascen
d
i
n
g
ao
r
ta
w
ill b
e
th
e
cir
c
u
lar
s
tr
u
ct
u
r
e
w
ith
t
h
e
m
i
n
i
m
u
m
E
u
c
lid
ea
n
d
is
ta
n
ce
to
th
e
i
m
ag
e
ce
n
te
r
.
E
u
clid
ea
n
d
is
ta
n
ce
=
√
(
)
(
)
(
1
)
w
h
er
e
C
Ix
, C
Iy
an
d
C
cx
, C
cy
ar
e
th
e
ce
n
ter
p
o
in
t
s
o
f
i
m
ag
e
(
I
)
an
d
d
etec
ted
cir
cles (
c)
o
n
th
at
i
m
ag
e
s
lice.
4.
I
n
ten
s
it
y
:
I
n
C
T
A
i
m
a
g
es
t
h
e
v
es
s
els
ar
e
i
n
j
ec
ted
w
it
h
a
co
n
tr
ast
ag
e
n
t,
th
u
s
t
h
e
asce
n
d
i
n
g
ao
r
ta
i
n
te
n
s
i
t
y
h
as
a
r
an
g
e
o
f
Ho
u
n
s
f
ield
v
al
u
es
[
1
4
]
th
at
is
u
s
ed
as
a
th
r
esh
o
ld
in
th
e
s
eg
m
e
n
tatio
n
alg
o
r
ith
m
a
n
d
in
th
e
PC
-
MRI
i
m
a
g
es a
n
in
te
n
s
it
y
r
an
g
e
i
s
e
m
p
ir
icall
y
d
eter
m
in
e
d
(
af
ter
tr
ain
in
g
t
h
e
d
atasets
)
a
s
a
th
r
es
h
o
ld
f
o
r
th
e
s
e
g
m
en
ta
tio
n
as
w
el
l.
2
.
2
.
P
a
rt
ia
l A
s
ce
nd
in
g
Ao
rt
a
Seg
m
e
nta
t
io
n
Fro
m
t
h
e
a
s
ce
n
d
i
n
g
ao
r
ta
f
lo
w
c
h
ar
t
d
ep
icted
i
n
Fig
u
r
e
2
,
th
e
f
ir
s
t
s
tag
e
o
f
th
e
au
to
m
at
ic
s
eg
m
e
n
tatio
n
p
r
o
ce
s
s
is
th
e
p
ar
tial
ascen
d
in
g
ao
r
ta
s
eg
m
e
n
tatio
n
.
I
t
b
eg
in
s
w
it
h
cir
cu
lar
s
tr
u
ct
u
r
es
d
etec
tio
n
in
ea
ch
C
T
A
/P
C
-
MRI
i
m
a
g
e
s
lice,
a
n
d
th
e
n
th
e
a
s
ce
n
d
i
n
g
ao
r
ta
is
id
en
tifie
d
f
r
o
m
a
n
y
o
t
h
er
cir
cu
lar
s
tr
u
ct
u
r
e
u
s
i
n
g
th
e
a
s
ce
n
d
i
n
g
ao
r
ta
m
o
d
el.
T
h
e
d
etec
tio
n
an
d
id
en
ti
f
icatio
n
b
eg
i
n
f
r
o
m
t
h
e
cr
an
ial
th
ir
d
o
f
t
h
e
C
T
A
v
o
lu
m
e
[
1
1
]
.
I
n
th
e
b
eg
in
n
in
g
o
f
th
is
p
ar
t
o
f
th
e
v
o
l
u
m
e,
th
e
ascen
d
in
g
ao
r
ta
ap
p
ea
r
s
as
a
u
n
i
f
o
r
m
cir
cle
an
d
ac
co
r
d
in
g
l
y
co
u
ld
b
e
s
eg
m
e
n
ted
w
it
h
a
n
y
al
g
o
r
ith
m
f
o
r
d
etec
tin
g
cir
cle
s
li
k
e
t
h
e
f
a
m
o
u
s
2
D
Ho
u
g
h
T
r
an
s
f
o
r
m
,
s
ee
Fi
g
u
r
e
s
3
-
a
an
d
3
-
c.
T
h
e
s
eg
m
e
n
tatio
n
w
i
ll
p
r
o
ce
ed
to
s
eg
m
e
n
t
th
e
as
ce
n
d
in
g
ao
r
ta
f
r
o
m
co
n
s
ec
u
tiv
e
C
T
A
/P
C
-
M
R
I
i
m
ag
e
s
lice
s
an
d
w
i
ll
s
to
p
as
s
o
o
n
as
t
h
e
asce
n
d
i
n
g
ao
r
ta
s
h
ap
e
is
n
o
m
o
r
e
a
u
n
i
f
o
r
m
cir
cle.
Fi
n
all
y
,
t
h
e
o
u
tp
u
t
o
f
t
h
is
s
ta
g
e
is
a
p
ar
t
o
f
t
h
e
asce
n
d
in
g
ao
r
ta
b
ein
g
au
to
m
atica
l
l
y
s
eg
m
e
n
ted
.
2
.
2
.
1
.
H
o
ug
h T
ra
ns
f
o
r
m
f
o
r
Circ
u
la
r
Str
uct
ures De
t
ec
t
io
n
T
h
e
Ho
u
g
h
tr
a
n
s
f
o
r
m
i
s
m
ai
n
l
y
u
s
ed
f
o
r
d
etec
tin
g
cir
cu
lar
s
t
r
u
ctu
r
es i
n
t
h
e
i
m
ag
e
[
1
1
]
,
[
1
5
-
16]
.
I
t
d
etec
ts
cir
cles
w
it
h
k
n
o
w
n
r
ad
iu
s
r
a
n
g
e
a
n
d
th
u
s
it
f
it
s
to
o
u
r
p
r
o
b
lem
[
1
7
]
.
T
h
e
Ho
u
g
h
tr
a
n
s
f
o
r
m
i
s
ap
p
lied
o
n
C
T
A
/M
R
I
i
m
a
g
e
s
lice
s
b
eg
in
n
in
g
f
r
o
m
th
e
cr
a
n
ial
t
h
ir
d
o
f
th
e
C
T
A
v
o
l
u
m
e.
T
h
e
Ho
u
g
h
tr
an
s
f
o
r
m
f
it
s
in
th
is
p
ar
t o
f
t
h
e
s
e
g
m
e
n
ta
t
io
n
p
ip
elin
e;
as t
h
e
asce
n
d
in
g
ao
r
ta
is
u
n
i
f
o
r
m
l
y
c
ir
cu
lar
i
n
th
at
p
ar
t o
f
th
e
v
o
l
u
m
e,
s
ee
Fig
u
r
e
3
(
a,
c,
d
)
.
2
.
2
.
2
.
M
o
del U
t
iliza
t
io
n f
o
r
Ascendi
ng
Ao
rt
a
I
dentif
ica
t
io
n
Af
ter
ap
p
l
y
in
g
Ho
u
g
h
tr
an
s
f
o
r
m
;
all
cir
cu
lar
s
tr
u
ctu
r
es
i
n
th
e
i
m
ag
e
ar
e
d
etec
ted
.
T
h
ese
cir
cu
lar
s
tr
u
ct
u
r
es
w
o
u
ld
b
e
t
h
e
a
s
ce
n
d
in
g
ao
r
ta,
d
escen
d
i
n
g
ao
r
ta
o
r
ev
en
t
h
e
s
p
i
n
al
co
r
d
cr
o
s
s
s
e
ctio
n
.
T
h
er
ef
o
r
e
to
id
en
ti
f
y
th
e
a
s
ce
n
d
in
g
ao
r
ta
a
m
o
n
g
o
t
h
er
cir
cu
lar
s
tr
u
ct
u
r
es
,
m
o
d
el
f
itti
n
g
is
d
o
n
e
o
n
t
h
e
o
u
tp
u
t
o
f
t
h
e
Ho
u
g
h
tr
an
s
f
o
r
m
.
Af
ter
ap
p
l
y
in
g
t
h
i
s
co
m
b
in
at
io
n
b
et
w
ee
n
t
h
e
Ho
u
g
h
tr
a
n
s
f
o
r
m
an
d
t
h
e
a
s
ce
n
d
in
g
ao
r
ta
m
o
d
el
o
n
co
n
s
ec
u
tiv
e
C
T
A
/P
C
-
M
R
I
i
m
ag
e
s
lice
s
;
t
h
e
asce
n
d
in
g
a
o
r
ta
cr
o
s
s
s
ec
tio
n
i
s
s
u
cc
ess
f
u
ll
y
id
en
ti
f
ied
an
d
f
i
n
all
y
a
p
ar
t o
f
t
h
e
asce
n
d
in
g
ao
r
ta
is
s
eg
m
en
ted
in
a
co
m
p
u
tatio
n
a
ll
y
ef
f
icie
n
t
m
a
n
n
er
,
s
e
e
Fig
u
r
e
3
(
d
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
Mo
d
el
-
b
a
s
ed
A
u
t
o
ma
tic
S
eg
m
en
ta
tio
n
o
f A
s
ce
n
d
in
g
A
o
r
ta
fr
o
m
Mu
ltimo
d
a
lity
....
(
N
o
h
a
A
.
S
ea
d
a
)
3165
(
a)
(
c)
(
d
)
(
f
)
(
b)
(
e
)
Fig
u
r
e
3
.
(
a)
A
s
ce
n
d
i
n
g
A
o
r
ta
A
p
p
ea
r
s
as a
Un
if
o
r
m
C
ir
cle,
(
b
)
A
s
ce
n
d
i
n
g
A
o
r
ta
S
h
ap
e
Ap
p
ea
r
s
No
n
-
U
n
i
f
o
r
m
,
(
c)
Sag
i
ttal
Vie
w
f
o
r
th
e
Hea
r
t S
h
o
w
in
g
t
h
e
F
u
ll
A
s
ce
n
d
i
n
g
A
o
r
ta
S
h
ap
e
,
(
d
)
T
h
e
Un
i
f
o
r
m
C
ir
cu
lar
P
ar
t
o
f
th
e
A
s
ce
n
d
i
n
g
A
o
r
ta
Seg
m
e
n
ted
in
First
Sta
g
e
,
(
e)
T
h
e
R
em
a
in
i
n
g
(
No
n
-
Un
i
f
o
r
m
)
P
ar
t o
f
th
e
A
s
ce
n
d
in
g
A
o
r
ta
Se
g
m
e
n
t
ed
in
S
tag
e
2
,
(
f
)
F
u
ll
A
s
ce
n
d
i
n
g
A
o
r
ta
Se
g
m
en
ted
A
l
g
o
r
i
t
h
m
1
:
P
a
r
t
i
a
l
A
sce
n
d
i
n
g
A
o
r
t
a
S
e
g
me
n
t
a
t
i
o
n
In
p
u
t
:
C
TA
v
o
l
u
me
w
i
t
h
si
z
e
N
sl
i
c
e
s
F
o
r
i
=
1
t
o
N
B
e
g
i
n
R
e
a
d
i
mag
e
I
i
w
i
t
h
si
z
e
5
1
2
2
S
e
t
N
C
i
r
c
l
e
s =
A
p
p
l
y
H
o
u
g
h
T
r
a
n
sf
o
r
m t
o
d
e
t
e
c
t
c
i
r
c
l
e
s i
n
I
i
If
N
C
i
r
c
l
e
s >
0
/
/
n
o
.
o
f
c
i
r
c
l
e
s d
e
t
e
c
t
e
d
w
i
t
h
c
e
n
t
e
r
C
x,
y
a
n
d
r
a
d
i
u
s
R
B
e
g
i
n
F
o
r
j
=
1
t
o
N
C
i
r
c
l
e
s
B
e
g
i
n
C
a
l
c
u
l
a
t
e
Eu
c
l
i
d
e
a
n
d
i
s
t
a
n
c
e
b
e
t
w
e
e
n
i
mag
e
I
i
c
e
n
t
e
r
a
n
d
c
i
r
c
l
e
c
c
e
n
t
e
r
Ed
=
√
(
)
(
)
a
c
=
Fi
nd
c
i
r
c
l
e
c
w
i
t
h
m
i
n
E
d
a
n
d
max
R
E
n
d
a
sce
n
d
i
n
g
_
a
o
r
t
a
=
a
c
/
/
t
h
i
s
i
s
t
h
e
a
sce
n
d
i
n
g
a
o
r
t
a
c
r
o
ss se
c
t
i
o
n
d
e
t
e
c
t
e
d
w
i
t
h
c
e
n
t
e
r
C
x,
y
.
me
a
n
I
n
t
=
c
a
l
c
u
l
a
t
e
me
a
n
i
n
t
e
n
s
i
t
y
v
a
l
u
e
o
f
t
h
e
a
sce
n
d
i
n
g
_
a
o
r
t
a
c
r
o
ss s
e
c
t
i
o
n
se
e
d
P
o
si
t
i
o
n
=
a
sce
n
d
i
n
g
_
a
o
r
t
a
c
e
n
t
e
r
C
x,
y
se
e
d
R
a
d
i
u
s =
a
s
c
e
n
d
i
n
g
_
a
o
r
t
a
R
se
e
d
I
n
t
e
n
i
st
y
=
me
a
n
I
n
t
t
h
r
e
sh
o
l
d
D
e
l
t
a
=
c
a
l
c
u
l
a
t
e
mi
n
i
n
t
e
n
si
t
y
v
a
l
u
e
o
f
t
h
e
a
sce
n
d
i
n
g
_
a
o
r
t
a
c
r
o
ss se
c
t
i
o
n
E
l
se
e
n
d
S
t
a
g
e
1
=
i
/
/
sl
i
c
e
n
o
.
a
t
w
h
i
c
h
st
a
g
e
1
h
a
l
t
s
e
x
i
t
s
t
a
g
e
1
E
n
d
E
n
d
Fig
u
r
e
4
.
P
s
eu
d
o
C
o
d
e
f
o
r
P
ar
tial A
s
ce
n
d
in
g
A
o
r
ta
Seg
m
e
n
t
atio
n
Sta
g
e
2
.
3
.
F
ull
Ascen
din
g
Ao
rt
a
Seg
m
e
nta
t
io
n
T
h
e
au
to
m
atic
s
e
g
m
e
n
tat
io
n
o
f
th
e
r
e
m
ain
in
g
p
ar
t
o
f
th
e
asc
en
d
in
g
ao
r
ta
b
eg
in
s
b
y
ta
k
i
n
g
th
e
o
u
tp
u
t
o
f
th
e
f
ir
s
t
s
ta
g
e
as
a
s
ee
d
f
o
r
th
e
s
e
g
m
e
n
tat
io
n
p
r
o
ce
s
s
.
W
h
en
t
h
e
asce
n
d
in
g
ao
r
ta
s
h
ap
e
b
eg
in
s
to
d
ef
o
r
m
an
d
is
n
o
m
o
r
e
cir
cu
lar
,
s
ee
F
ig
u
r
e
3(
b
)
;
t
h
e
f
ir
s
t
s
ta
g
e
h
a
lt
s
s
i
n
ce
t
h
e
Ho
u
g
h
tr
a
n
s
f
o
r
m
i
s
s
e
n
s
i
tiv
e
to
s
h
ap
e
d
ev
iatio
n
an
d
n
o
i
s
e
[
1
5
]
an
d
f
ailed
to
d
etec
t
th
e
ascen
d
in
g
ao
r
ta
cr
o
s
s
s
ec
tio
n
s
i
n
th
at
c
ase.
So
,
th
e
s
ec
o
n
d
s
tag
e
b
e
g
in
s
to
s
e
g
m
e
n
t
t
h
e
r
e
m
ai
n
in
g
a
s
ce
n
d
i
n
g
ao
r
ta
p
ar
t
u
p
to
th
e
o
s
tia
lo
ca
tio
n
s
.
I
n
th
e
s
ec
o
n
d
s
tag
e
a
m
o
d
i
f
ied
v
er
s
io
n
o
f
th
e
s
ee
d
e
d
r
eg
io
n
g
r
o
w
i
n
g
ap
p
r
o
ac
h
is
p
r
o
p
o
s
ed
.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
i
th
m
i
s
ca
l
led
ce
n
ter
to
ed
g
e
r
a
y
-
s
ea
r
ch
-
b
ased
p
r
o
p
ag
atio
n
r
eg
io
n
g
r
o
w
i
n
g
ap
p
r
o
ac
h
.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
ta
k
es
t
h
e
s
ee
d
p
o
s
itio
n
an
d
in
te
n
s
it
y
o
f
t
h
e
ascen
d
i
n
g
ao
r
ta
f
r
o
m
t
h
e
f
ir
s
t
s
tag
e
an
d
b
eg
i
n
s
s
ea
r
c
h
i
n
g
e
v
er
y
n
e
w
u
n
v
i
s
ited
U
n
i
f
o
r
m
c
i
r
c
u
l
a
r
a
o
r
t
a
p
a
r
t
d
e
t
e
c
t
e
d
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
:
3
1
6
1
–
3
173
3166
s
lice
f
o
r
th
e
asce
n
d
in
g
ao
r
ta
cr
o
s
s
s
ec
tio
n
b
ased
o
n
th
e
s
ee
d
p
o
s
itio
n
a
n
d
in
ten
s
it
y
(
r
e
g
io
n
g
r
o
w
i
n
g
th
r
es
h
o
ld
)
.
I
n
ea
ch
i
m
a
g
e
s
l
ic
e,
th
e
s
ea
r
ch
b
eg
i
n
s
f
r
o
m
t
h
e
s
ee
d
p
o
s
itio
n
(
ce
n
ter
p
o
in
t)
an
d
p
r
o
p
ag
ates
as
a
r
ay
c
h
ec
k
in
g
ev
er
y
p
i
x
el
alo
n
g
t
h
at
r
a
y
w
h
eth
er
it
b
elo
n
g
s
to
th
e
asce
n
d
in
g
ao
r
ta
o
r
n
o
t.
T
h
e
r
ay
s
to
p
s
p
r
o
p
ag
atin
g
w
h
e
n
it
h
its
a
n
e
d
g
e
(
th
e
asce
n
d
i
n
g
ao
r
ta
ed
g
e
)
.
T
h
e
r
ay
s
m
o
v
e
i
n
a
cir
c
u
lar
f
as
h
io
n
to
s
ca
n
th
e
w
h
o
le
ascen
d
i
n
g
ao
r
ta
cr
o
s
s
s
ec
tio
n
f
r
o
m
0
o
to
3
6
0
o
,
s
ee
Fig
u
r
e
5
.
T
h
e
s
ee
d
p
o
s
itio
n
an
d
in
ten
s
it
y
ar
e
th
e
n
u
p
d
ated
to
b
e
u
s
ed
b
y
t
h
e
r
eg
i
o
n
g
r
o
w
i
n
g
al
g
o
r
ith
m
i
n
t
h
e
c
o
n
s
ec
u
tiv
e
s
lice.
T
h
is
p
r
ese
n
ts
a
k
i
n
d
o
f
lear
n
in
g
f
r
o
m
th
e
v
o
lu
m
e
its
el
f
to
h
el
p
in
ac
cu
r
atel
y
s
e
g
m
en
t
in
g
th
e
ascen
d
in
g
ao
r
ta.
T
h
e
s
ee
d
t
ak
en
f
r
o
m
th
e
f
ir
s
t
s
tag
e
h
elp
ed
s
i
m
p
li
f
y
th
e
r
e
g
i
o
n
g
r
o
w
in
g
al
g
o
r
ith
m
w
o
r
k
f
l
o
w
an
d
r
aise
s
th
e
co
m
p
u
tatio
n
ef
f
i
cie
n
c
y
o
f
th
e
s
eg
m
e
n
tatio
n
p
r
o
ce
s
s
.
Fig
u
r
e
5
.
R
eg
io
n
Gr
o
w
i
n
g
R
a
y
s
P
r
o
p
ag
ate
f
r
o
m
C
e
n
ter
See
d
P
o
s
itio
n
T
ill Hittin
g
an
E
d
g
e
w
it
h
a
Ma
x
R
a
y
L
e
n
g
t
h
o
f
(
R
+
r
)
,
m
o
v
in
g
i
n
a
C
ir
cle
f
r
o
m
A
n
g
le
0
o
to
3
6
0
o
2
.
3
.
1
.
Cent
er
t
o
E
dg
e
Ra
y
-
Sea
rc
h
-
B
a
s
ed
P
ro
pa
g
a
t
i
o
n Re
g
io
n
G
ro
w
ing
Alg
o
rit
h
m
S
ee
d
ed
r
eg
io
n
g
r
o
w
in
g
i
s
a
r
o
b
u
s
t
a
n
d
co
m
p
u
tatio
n
ef
f
icie
n
t
tech
n
iq
u
e
u
s
ed
f
o
r
s
e
g
m
e
n
tin
g
a
r
e
g
io
n
o
f
in
ter
e
s
t
f
r
o
m
an
i
m
a
g
e
a
n
d
th
e
ac
cu
r
ac
y
o
f
t
h
e
r
es
u
lt
s
ar
e
b
ased
o
n
th
e
r
ig
h
t
c
h
o
ice
o
f
t
h
e
s
ee
d
(
s
)
[
1
8
]
.
Fo
r
s
atis
f
y
in
g
t
h
e
in
te
n
s
it
y
a
n
d
co
n
n
ec
t
iv
i
t
y
cr
iter
ia;
t
h
e
s
ee
d
ed
r
eg
io
n
g
r
o
w
i
n
g
al
g
o
r
ith
m
r
eq
u
ir
es
s
ee
d
p
o
s
itio
n
,
s
ee
d
in
te
n
s
it
y
,
a
n
d
ex
p
an
s
io
n
an
d
ter
m
i
n
atio
n
cr
i
ter
ia.
All
t
h
ese
i
n
p
u
t
s
f
o
r
th
e
r
eg
io
n
g
r
o
w
i
n
g
alg
o
r
it
h
m
ar
e
tak
en
f
r
o
m
t
h
e
o
u
tp
u
t o
f
t
h
e
f
i
r
s
t stag
e
a
s
f
o
llo
w
s
:
1.
Seed
p
o
s
itio
n
: c
en
te
r
C
x,
y
o
f
t
h
e
to
p
d
etec
ted
ascen
d
in
g
ao
r
ta
cr
o
s
s
s
ec
tio
n
r
es
u
lti
n
g
f
r
o
m
s
t
ag
e1
.
2.
Seed
in
ten
s
it
y
:
m
ea
n
in
te
n
s
i
t
y
m
ea
n
[
A
c
]
o
f
th
e
to
p
d
etec
ted
ascen
d
in
g
ao
r
ta
cr
o
s
s
s
ec
tio
n
r
esu
ltin
g
f
r
o
m
s
tag
e1
.
3.
E
x
p
an
s
io
n
cr
iter
ia
o
n
a
n
e
w
l
y
g
iv
e
n
i
m
a
g
e
s
lice:
r
e
g
io
n
g
r
o
w
i
n
g
r
a
y
s
p
r
o
p
ag
ate
f
r
o
m
ce
n
ter
s
ee
d
p
o
s
itio
n
till
h
it
tin
g
a
n
ed
g
e,
m
o
v
in
g
i
n
a
cir
cle
f
r
o
m
an
g
le
0
o
to
3
6
0
o
.
4.
T
er
m
in
at
io
n
cr
iter
ia:
m
ax
r
a
y
len
g
th
i
s
(
R
+
r
)
,
w
h
er
e
R
is
t
h
e
r
ad
iu
s
o
f
t
h
e
to
p
d
etec
ted
ascen
d
i
n
g
ao
r
ta
cr
o
s
s
s
ec
tio
n
r
es
u
lt
in
g
f
r
o
m
s
t
ag
e
1
an
d
r
is
a
p
ar
a
m
eter
b
eg
i
n
n
i
n
g
w
it
h
v
alu
e
1
a
n
d
in
cr
e
m
en
ted
w
h
i
le
th
e
in
te
n
s
it
y
v
alu
e
o
f
th
e
v
is
ited
p
ix
el
is
le
s
s
t
h
a
n
a
s
p
ec
if
ied
t
h
r
esh
o
ld
.
2
.
3
.
2
.
T
he
ce
nte
r
t
o
edg
e
ra
y
-
s
ea
rc
h
-
ba
s
ed
pro
pa
g
a
t
io
n r
eg
io
n g
ro
w
ing
a
lg
o
rit
hm
w
o
rks
a
s
f
o
llo
w
s
:
L
et
I
b
e
th
e
i
m
ag
e
s
lice
u
n
d
er
in
s
p
ec
tio
n
an
d
A
c
r
ep
r
esen
t t
h
e
s
et
o
f
p
ix
el
v
alu
e
s
o
f
t
h
e
to
p
d
etec
ted
ascen
d
i
n
g
ao
r
ta
cir
cle
w
ith
ce
n
ter
C
x,
y
an
d
r
ad
iu
s
R
,
th
e
n
:
Seed
I
n
ten
s
it
y
=
m
ea
n
[
A
c
]
,
S
ee
d
p
o
s
itio
n
=
C
x,
y
.
1.
T
h
e
s
ee
d
p
o
s
itio
n
(
C
x,
y
)
an
d
s
ee
d
in
ten
s
it
y
(
m
ea
n
[
A
c
]
)
ar
e
tak
en
f
r
o
m
t
h
e
to
p
d
etec
ted
ascen
d
in
g
ao
r
ta
cr
o
s
s
s
ec
tio
n
r
es
u
lti
n
g
f
r
o
m
t
h
e
p
ar
tial seg
m
e
n
tat
io
n
s
ta
g
e.
2.
Fo
r
s
ea
r
ch
in
g
in
a
n
e
w
co
n
s
ec
u
ti
v
e
C
T
A
i
m
ag
e
s
lice,
a
g
r
o
u
p
o
f
r
a
y
s
(
3
6
0
r
ay
s
m
o
v
in
g
i
n
a
cir
cu
lar
f
as
h
io
n
w
i
th
a
n
g
le
θ
A
=
(0
o
-
360
o
)
)
p
r
o
p
ag
ate
s
f
r
o
m
t
h
e
s
ee
d
p
o
s
itio
n
till
h
itti
n
g
a
n
ed
g
e,
s
e
e
Fig
u
r
e
5
.
3.
Sin
ce
t
h
e
s
ea
r
ch
i
s
in
a
cir
cu
l
ar
f
ash
io
n
,
ev
er
y
n
e
w
p
ix
el
P
x
,
y
p
o
s
itio
n
(
th
e
p
ix
el
to
b
e
test
ed
f
o
r
b
ein
g
an
ascen
d
i
n
g
ao
r
ta
p
ix
el)
is
f
o
u
n
d
b
y
t
h
e
cir
cle
eq
u
atio
n
:
(
(
)
(
)
)
(
2
)
(
(
)
(
)
)
(
3
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
Mo
d
el
-
b
a
s
ed
A
u
t
o
ma
tic
S
eg
m
en
ta
tio
n
o
f A
s
ce
n
d
in
g
A
o
r
ta
fr
o
m
Mu
ltimo
d
a
lity
....
(
N
o
h
a
A
.
S
ea
d
a
)
3167
4.
E
v
er
y
p
i
x
el
v
i
s
ited
b
y
t
h
e
r
a
y
is
te
s
ted
f
o
r
b
ein
g
a
n
asce
n
d
in
g
ao
r
ta
p
ix
el
(
co
m
p
ar
i
n
g
it
w
it
h
th
e
s
ee
d
in
te
n
s
it
y
p
r
o
v
id
ed
)
.
T
h
e
n
e
w
p
ix
el
P
x,
y
is
ad
d
ed
to
th
e
s
et
A
c
o
f
t
h
e
n
e
w
a
s
ce
n
d
i
n
g
ao
r
ta
cr
o
s
s
s
ec
t
io
n
i
f
i
t
s
in
te
n
s
it
y
(
)
s
atis
f
ies t
h
e
f
o
llo
w
i
n
g
co
n
d
itio
n
s
:
(
)
*
+
{
(
)
|
(
)
,
-
|
(
4
)
T
h
e
f
ir
s
t
co
n
d
itio
n
(
)
is
es
s
en
tia
l
f
o
r
a
v
o
id
in
g
lea
k
ag
e
o
u
t
s
id
e
th
e
ed
g
e
o
f
t
h
e
asce
n
d
i
n
g
ao
r
ta
r
eg
io
n
(
as
t
h
e
h
o
u
n
s
f
ield
u
n
i
t
[
1
4
]
v
alu
es
o
f
p
ix
el
s
at
t
h
e
o
u
ter
s
id
e
o
f
t
h
e
ed
g
e
ar
e
n
eg
ativ
e)
.
A
ls
o
,
t
h
e
p
ix
el
is
an
ao
r
ta
p
ix
el
i
f
th
e
d
if
f
er
en
ce
b
et
w
ee
n
i
ts
i
n
te
n
s
i
t
y
an
d
t
h
at
o
f
t
h
e
m
ea
n
in
te
n
s
it
y
,
-
is
g
r
ea
ter
th
an
d
elta
,
w
h
er
e
is
a
th
r
esh
o
ld
i
n
g
p
ar
a
m
eter
r
ep
r
esen
ti
n
g
th
e
m
in
i
m
u
m
h
o
u
n
s
f
ield
v
al
u
e
ca
lcu
lated
f
r
o
m
t
h
e
to
p
d
etec
t
ed
ascen
d
i
n
g
ao
r
ta
cr
o
s
s
s
ec
ti
o
n
r
es
u
lti
n
g
f
r
o
m
s
ta
g
e
1.
T
h
e
s
e
t
w
o
in
te
n
s
it
y
co
n
d
itio
n
s
s
ec
u
r
e
t
h
at
th
e
n
e
w
p
ix
el
ad
d
ed
lies
in
s
id
e
th
e
ao
r
ta
cr
o
s
s
s
ec
tio
n
.
5.
I
f
th
e
p
ix
e
l is a
n
ascen
d
i
n
g
ao
r
ta
p
ix
el,
it’s a
d
d
ed
to
th
e
s
et
*
+
th
at
w
ill co
n
s
tit
u
te
t
h
e
n
e
w
s
eg
m
en
ted
ascen
d
i
n
g
ao
r
ta
cr
o
s
s
s
ec
tio
n
.
6.
F
in
all
y
t
h
e
ce
n
ter
C
x,
y
an
d
s
ee
d
in
ten
s
it
y
(
m
ea
n
[
A
c
]
)
ar
e
u
p
d
ated
f
o
r
co
n
s
ec
u
ti
v
e
s
lice
s
s
e
ar
ch
.
T
h
e
p
r
o
p
o
s
ed
r
ay
p
r
o
p
ag
atio
n
ap
p
r
o
ac
h
g
u
ar
a
n
tees
t
h
at
n
o
p
ix
el
i
s
v
is
i
ted
o
r
tes
ted
m
o
r
e
th
a
n
o
n
ce
a
n
d
th
is
en
h
a
n
ce
s
th
e
p
er
f
o
r
m
a
n
ce
.
Mo
r
eo
v
er
it
s
u
cc
ee
d
s
to
g
iv
e
u
s
s
i
g
n
if
ican
t
r
esu
lts
f
o
r
t
h
e
asce
n
d
in
g
ao
r
ta
s
eg
m
e
n
tatio
n
,
s
ee
R
e
s
u
l
ts
s
ec
tio
n
.
A
ls
o
,
t
h
e
ap
p
r
o
ac
h
is
p
r
o
m
is
i
n
g
f
o
r
s
e
g
m
en
t
in
g
t
h
e
a
s
ce
n
d
i
n
g
ao
r
ta
w
it
h
d
is
s
ec
tio
n
o
r
an
eu
r
y
s
m
;
t
h
r
o
u
g
h
co
n
tr
o
lli
n
g
th
e
p
ar
a
m
eter
r
.
A
lth
o
u
g
h
an
y
alg
o
r
it
h
m
i
s
ch
alle
n
g
ed
b
y
th
e
n
u
m
b
er
o
f
p
ar
a
m
eter
s
to
t
u
n
e;
o
u
r
ap
p
r
o
ac
h
h
av
e
o
n
l
y
o
n
e
p
ar
am
eter
;
r
to
co
n
tr
o
l
an
d
it
's
n
o
t
e
m
p
ir
ical
b
u
t
r
ath
er
co
n
tr
o
lled
b
y
th
e
ap
p
r
o
x
i
m
ate
r
ad
iu
s
v
al
u
e
o
f
th
e
a
s
c
e
n
d
in
g
ao
r
ta,
an
d
is
i
n
cr
ea
s
ed
in
i
n
cr
e
m
e
n
tal
s
tep
s
an
d
ter
m
i
n
ated
w
i
th
t
h
e
co
n
d
itio
n
s
i
n
E
q
u
at
io
n
4
.
Fi
n
all
y
t
o
co
v
er
all
co
n
d
itio
n
s
,
it
is
i
m
p
o
r
tan
t
to
m
en
t
io
n
th
at
i
f
t
h
e
r
i
g
h
t
s
ee
d
p
o
in
t
is
n
o
t
p
r
o
v
id
ed
f
r
o
m
s
ta
g
e
1
(
in
ca
s
e
s
ta
g
e
1
f
ailed
to
d
etec
t
a
n
y
cir
cu
lar
asce
n
d
in
g
ao
r
ta
cr
o
s
s
s
ec
tio
n
)
;
t
h
e
u
s
er
w
i
ll
b
e
p
r
o
m
p
ted
to
s
elec
t
a
s
ee
d
p
o
in
t
to
b
e
u
s
ed
b
y
t
h
e
r
eg
io
n
g
r
o
w
i
n
g
alg
o
r
ith
m
.
Fi
g
u
r
e
6
s
h
o
w
s
p
s
e
u
d
o
co
d
e
f
o
r
f
u
ll a
s
ce
n
d
in
g
ao
r
ta
s
eg
m
en
ta
tio
n
s
tag
e
A
l
g
o
r
i
t
h
m
2
:
F
u
l
l
A
sce
n
d
i
n
g
A
o
r
t
a
S
e
g
me
n
t
a
t
i
o
n
In
p
u
t
:
F
r
o
m st
a
g
e
1
:
se
e
d
P
o
si
t
i
o
n
,
se
e
d
I
n
t
e
n
i
st
y
,
me
a
n
I
n
t
,
se
e
d
R
a
d
i
u
s,
t
h
r
e
sh
o
l
d
D
e
l
t
a
If
se
e
d
P
o
si
t
i
o
n
=
0
/
/
me
a
n
s
n
o
a
sce
n
d
i
n
g
a
o
r
t
a
c
r
o
ss se
c
t
i
o
n
d
e
t
e
c
t
e
d
a
u
t
o
ma
t
i
c
a
l
l
y
i
n
s
t
a
g
e
1
B
e
g
i
n
A
sk
u
se
r
t
o
e
n
t
e
r
se
e
d
P
o
si
t
i
o
n
f
o
r
t
h
e
t
o
p
a
sce
n
d
i
n
g
a
o
r
t
a
c
r
o
ss se
c
t
i
o
n
me
a
n
I
n
t
=
c
a
l
c
u
l
a
t
e
me
a
n
i
n
t
e
n
s
i
t
y
v
a
l
u
e
o
f
t
h
e
a
sce
n
d
i
n
g
_
a
o
r
t
a
c
r
o
ss se
c
t
i
o
n
se
e
d
P
o
si
t
i
o
n
=
a
sce
n
d
i
n
g
_
a
o
r
t
a
c
e
n
t
e
r
C
x,
y
se
e
d
I
n
t
e
n
i
st
y
=
me
a
n
I
n
t
t
h
r
e
sh
o
l
d
D
e
l
t
a
=
c
a
l
c
u
l
a
t
e
mi
n
i
n
t
e
n
s
i
t
y
v
a
l
u
e
o
f
t
h
e
a
s
c
e
n
d
i
n
g
_
a
o
r
t
a
c
r
o
ss se
c
t
i
o
n
E
n
d
S
e
t
r
e
g
i
o
n
o
f
i
n
t
e
r
e
st
:
c
e
n
t
e
r
=
se
e
d
P
o
si
t
i
o
n
(
C
x
,
y
)
a
n
d
r
a
d
i
u
s
=
se
e
d
R
a
d
i
u
s (R)
Fo
r
k
=
e
n
d
S
t
a
g
e
1
t
o
N
B
e
g
i
n
R
e
a
d
i
m
a
g
e
I
k
w
i
t
h
s
i
z
e
5
1
2
2
S
e
t
r
a
y
r
a
n
g
e
r
=
0
t
o
1
0
/
/
r
e
g
i
o
n
r
a
n
g
e
w
i
l
l
b
e
R
+
r
.
F
o
r
θ
A
=
0
o
t
o
3
6
0
o
B
e
g
i
n
C
a
l
c
u
l
a
t
e
n
e
w
p
i
x
e
l
p
o
si
t
i
o
n
a
l
o
n
g
t
h
e
r
a
y
p
r
o
p
a
g
a
t
i
n
g
u
si
n
g
c
i
r
c
l
e
e
q
u
a
t
i
o
n
(
(
)
(
)
)
(
(
)
(
)
)
/
/
C
h
e
c
k
i
f
p
i
x
e
l
P
x,
y
i
s a
n
a
sce
n
d
i
n
g
a
o
r
t
a
p
i
x
e
l
If
I
(
P
x
,P
y
)
>
0
a
n
d
I
(
P
x
,P
y
)
-
se
e
d
I
n
t
e
n
i
s
t
y
>
t
h
r
e
sh
o
l
d
D
e
l
t
a
B
e
g
i
n
I
(
P
x
,P
y
)
i
s a
n
a
s
c
e
n
d
i
n
g
a
o
r
t
a
p
i
x
e
l
E
n
d
E
n
d
U
p
d
a
t
e
se
e
d
P
o
si
t
i
o
n
,
se
e
d
R
a
d
i
u
s
,
se
e
d
I
n
t
e
n
i
st
y
,
t
h
r
e
sh
o
l
d
D
e
l
t
a
E
n
d
Fig
u
r
e
6
.
P
s
eu
d
o
C
o
d
e
f
o
r
Fu
ll Ascen
d
i
n
g
A
o
r
ta
Se
g
m
en
ta
ti
o
n
Stag
e
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
:
3
1
6
1
–
3
173
3168
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
Da
t
a
s
et
s
T
h
e
p
r
o
p
o
s
ed
au
to
m
at
ic
asce
n
d
in
g
ao
r
ta
s
e
g
m
e
n
tatio
n
a
lg
o
r
i
th
m
is
ap
p
lied
o
n
t
w
o
d
ata
s
ets
f
r
o
m
t
w
o
i
m
a
g
in
g
m
o
d
ali
ties
:
C
T
A
an
d
P
C
-
MRI.
1.
C
o
m
p
u
ted
T
o
m
o
g
r
ap
h
y
An
g
i
o
g
r
ap
h
y
(
C
T
A
)
:
ca
r
d
iac
C
T
A
d
atab
ase
p
r
o
v
id
ed
b
y
th
e
R
o
tt
er
d
am
C
o
r
o
n
ar
y
A
r
ter
y
A
l
g
o
r
ith
m
E
v
al
u
atio
n
Fra
m
e
w
o
r
k
[
1
9
]
.
T
h
e
d
atab
ase
in
cl
u
d
es
4
8
d
atasets
w
it
h
a
m
i
n
i
m
u
m
o
f
2
5
3
s
lices
u
p
to
a
m
a
x
i
m
u
m
o
f
6
4
0
s
lices
f
o
r
a
v
o
lu
m
e.
T
h
e
C
T
A
d
atase
ts
w
e
r
e
ac
q
u
ir
ed
in
t
h
e
E
r
as
m
u
s
M
C
,
Un
i
v
er
s
it
y
Me
d
ical
C
e
n
ter
R
o
tter
d
a
m
,
i
n
Net
h
er
lan
d
s
.
So
m
e
o
f
t
h
e
d
ata
s
ets
w
er
e
ac
q
u
ir
ed
w
it
h
a
6
4
-
s
lice
C
T
s
ca
n
n
er
an
d
s
o
m
e
w
it
h
a
d
u
al
-
s
o
u
r
ce
C
T
s
ca
n
n
er
.
2.
P
h
ase
C
o
n
tr
as
t
–
Ma
g
n
etic
R
eso
n
a
n
ce
I
m
a
g
i
n
g
(
P
C
-
MRI
)
:
d
atab
ase
o
f
8
d
atasets
ac
q
u
ir
ed
u
s
i
n
g
1
.
5
T
esla
–
MRI
s
ca
n
n
er
s
[
9
]
.
3
.
2
.
Co
m
pu
t
ing
Reso
urce
s
T
h
e
i
m
p
le
m
e
n
tatio
n
is
d
o
n
e
o
n
an
I
n
tel
co
r
e
i5
m
ac
h
i
n
e
w
it
h
2
.
5
0
GHz
C
P
U,
6
GB
R
A
M
a
n
d
an
NVid
ia
GeFo
r
ce
GT
6
3
5
M
g
r
ap
h
ics
ca
r
d
.
T
h
e
v
is
u
aliza
tio
n
an
d
r
en
d
er
in
g
f
o
r
th
e
3
D
s
e
g
m
e
n
ted
asce
n
d
in
g
ao
r
ta
is
d
o
n
e
u
s
i
n
g
I
m
ag
eV
is
3
D
v
er
s
io
n
3
.
1
.
0
[
2
0
]
.
3
.
3
.
P
a
rt
ia
l A
s
ce
nd
ing
Ao
rt
a
Seg
m
e
nta
t
io
n:
T
h
e
f
ir
s
t
s
tag
e
o
f
t
h
e
au
to
m
at
ic
s
eg
m
en
ta
tio
n
al
g
o
r
ith
m
b
e
g
in
s
w
it
h
Ho
u
g
h
tr
an
s
f
o
r
m
f
o
r
C
ir
cu
lar
Stru
ct
u
r
es
De
tectio
n
.
T
h
e
Ho
u
g
h
tr
an
s
f
o
r
m
i
s
ap
p
lied
o
n
e
v
e
r
y
C
T
A/P
C
-
M
R
I
i
m
a
g
e
s
lice
b
eg
in
n
i
n
g
f
r
o
m
t
h
e
cr
an
ial
t
h
ir
d
o
f
th
e
i
n
p
u
t
v
o
l
u
m
e.
T
h
e
r
ad
iu
s
r
an
g
e
s
p
ec
i
f
ie
d
f
o
r
th
e
Ho
u
g
h
tr
an
s
f
o
r
m
is
s
et
o
v
er
all
tes
ted
d
atasets
b
ased
o
n
th
e
m
ed
i
ca
l
ascen
d
i
n
g
ao
r
ta
d
ia
m
ete
r
r
an
g
e
m
e
n
tio
n
ed
i
n
[
1
3
]
.
First
w
h
e
n
H
o
ugh
T
r
an
s
f
o
r
m
is
ap
p
lied
w
ith
in
th
e
s
p
ec
if
ied
r
ad
iu
s
r
an
g
e,
b
o
th
th
e
ascen
d
i
n
g
a
n
d
d
escen
d
in
g
ao
r
ta
cr
o
s
s
s
ec
tio
n
s
ar
e
d
etec
ted
s
ee
Fi
g
u
r
e
7(
a
)
,
7
(
d
)
.
T
o
id
en
tify
t
h
e
ascen
d
in
g
ao
r
ta
f
r
o
m
t
h
e
d
escen
d
i
n
g
ao
r
ta,
th
e
p
r
o
p
o
s
ed
ascen
d
in
g
ao
r
ta
m
o
d
el
is
f
itted
to
t
h
e
d
etec
ted
cir
cles
an
d
t
h
e
asce
n
d
in
g
a
o
r
ta
is
s
u
c
ce
s
s
f
u
ll
y
id
en
ti
f
ied
,
s
ee
Fi
g
u
r
e
7(
b
)
,
7
(
c
)
.
T
h
e
d
etec
ted
ascen
d
in
g
ao
r
ta
cr
o
s
s
s
ec
tio
n
is
t
h
e
n
s
eg
m
e
n
ted
an
d
th
e
d
etec
tio
n
p
r
o
ce
s
s
co
n
tin
u
es
w
it
h
ev
er
y
co
n
s
ec
u
ti
v
e
i
m
a
g
e
s
lice,
w
h
ile
th
e
asce
n
d
in
g
ao
r
ta
s
h
ap
e
is
s
till
u
n
i
f
o
r
m
l
y
cir
c
u
lar
.
T
h
e
f
ir
s
t
s
tag
e
h
a
lts
w
h
e
n
th
e
s
h
ap
e
o
f
th
e
asce
n
d
in
g
ao
r
ta
d
ef
o
r
m
s
.
T
h
e
o
u
tp
u
t
o
f
t
h
i
s
s
tag
e
i
s
p
ar
t o
f
th
e
asc
e
n
d
in
g
a
o
r
ta
b
ein
g
s
eg
m
e
n
ted
; see
F
ig
u
r
e
7
(
c)
.
3
.
3
.
1
.
CT
A
R
es
ults
T
h
e
p
ar
tial
ascen
d
i
n
g
ao
r
ta
s
e
g
m
e
n
tat
io
n
al
g
o
r
ith
m
a
s
s
h
o
wn
i
n
F
ig
u
r
e
8
is
ap
p
lied
o
n
t
h
e
4
8
C
T
A
d
atasets
a
n
d
s
u
cc
ee
d
ed
i
n
al
l
th
e
ca
s
e
s
to
p
ar
tiall
y
s
e
g
m
e
n
t
t
h
e
asce
n
d
in
g
ao
r
ta,
a
s
s
h
o
w
n
i
n
tab
le
.
T
h
e
n
u
m
b
er
o
f
s
lices
s
e
g
m
e
n
ted
d
if
f
er
s
p
er
d
ataset.
A
s
o
b
s
er
v
e
d
f
r
o
m
tab
le,
t
h
e
n
u
m
b
er
o
f
s
lices
s
e
g
m
en
ted
in
s
o
m
e
d
atasets
i
s
lar
g
er
th
a
n
o
th
er
s
b
ased
o
n
th
e
v
o
lu
m
e
s
ize
an
d
th
e
s
p
atial
r
eso
lu
tio
n
p
er
s
ca
n
n
er
(
s
in
ce
d
atasets
ar
e
co
llected
f
r
o
m
d
if
f
er
en
t
s
ca
n
n
er
s
)
.
(
a)
(
b
)
(
c)
(
d)
(
e)
Fig
u
r
e
7.
(
a)
A
s
ce
n
d
i
n
g
Ao
r
ta
an
d
Descen
d
i
n
g
A
o
r
ta
ar
e
B
o
t
h
Dete
cte
d
o
n
a
C
T
A
I
m
ag
e
S
lic
e,
(
b
)
A
s
ce
n
d
i
n
g
A
o
r
ta
is
I
d
en
tifie
d
,
(
c)
I
s
o
lated
A
s
ce
n
d
in
g
A
o
r
ta,
(
d
)
3
D
R
en
d
er
in
g
f
o
r
th
e
Ascen
d
i
n
g
A
o
r
ta
an
d
Descen
d
i
n
g
A
o
r
ta
Dete
cted
in
a
,
(
e)
3
D
R
en
d
er
in
g
f
o
r
th
e
A
s
ce
n
d
i
n
g
A
o
r
ta
af
ter
Au
g
m
en
tin
g
t
h
e
Ascen
d
i
n
g
A
o
r
ta
Mo
d
el
w
ith
t
h
e
Ho
u
g
h
T
r
an
s
f
o
r
m
A
l
g
o
r
ith
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
Mo
d
el
-
b
a
s
ed
A
u
t
o
ma
tic
S
eg
m
en
ta
tio
n
o
f A
s
ce
n
d
in
g
A
o
r
ta
fr
o
m
Mu
ltimo
d
a
lity
....
(
N
o
h
a
A
.
S
ea
d
a
)
3169
Fig
u
r
e
8
.
P
ar
tial a
s
ce
n
d
in
g
ao
r
ta
s
eg
m
e
n
tatio
n
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
s
u
cc
ee
d
ed
to
id
en
ti
f
y
a
n
d
d
etec
t
th
e
asce
n
d
in
g
ao
r
ta
in
all
4
8
test
ed
d
atasets
3
.
3
.
2
.
PC
-
M
RI
R
esu
lt
s
T
h
e
P
C
-
MRI
d
atasets
co
n
s
i
s
t
o
f
t
w
o
i
m
a
g
e
t
y
p
e
s
:
m
ag
n
it
u
d
e
an
d
p
h
ase
i
m
ag
e
s
.
Ma
g
n
it
u
d
e
i
m
ag
e
s
d
eter
m
in
e
t
h
e
a
n
ato
m
ical
in
f
o
r
m
at
io
n
(
p
r
esen
t
s
th
e
s
p
atial
r
eso
lu
tio
n
)
,
w
h
ile
t
h
e
p
h
ase
i
m
a
g
es
e
n
co
d
e
th
e
v
elo
cit
y
y
o
f
b
lo
o
d
f
lo
w
i
n
t
h
e
v
e
s
s
el
s
(
p
r
esen
t
s
th
e
te
m
p
o
r
al
r
eso
lu
tio
n
)
[
2
1
]
.
W
h
en
ap
p
ly
i
n
g
th
e
p
ar
tia
l
ascen
d
i
n
g
ao
r
ta
s
e
g
m
en
ta
tio
n
alg
o
r
ith
m
o
n
t
h
e
P
C
-
M
R
I
d
at
a,
it
s
u
cc
ee
d
ed
to
d
etec
t
th
e
as
ce
n
d
in
g
ao
r
ta
cr
o
s
s
s
ec
tio
n
n
o
t
o
n
l
y
f
r
o
m
th
e
m
a
g
n
i
tu
d
e
i
m
ag
e
s
,
b
u
t
also
f
r
o
m
p
h
ase
i
m
a
g
es
a
s
i
n
d
icate
d
in
Fi
g
u
r
e
9(
a
)
-
9(
b
)
.
Mo
r
eo
v
er
th
e
a
lg
o
r
it
h
m
s
u
cc
ee
d
ed
in
d
etec
ti
n
g
t
h
e
a
s
ce
n
d
in
g
ao
r
ta
in
i
m
a
g
es
w
it
h
ar
t
if
ac
ts
a
n
d
d
if
f
er
en
t
r
eso
lu
tio
n
s
s
ee
Fi
g
u
r
e
9(
c
)
-
9(
d
)
.
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
9
.
(
a)
A
s
ce
n
d
i
n
g
A
o
r
ta
Det
ec
ted
in
P
C
-
M
R
I
Ma
g
n
it
u
d
e
I
m
a
g
e,
(
b
)
P
h
ase
I
m
a
g
e,
(
c)
I
m
a
g
e
w
it
h
d
if
f
er
e
n
t
R
e
s
o
lu
t
io
n
,
(
d
)
I
m
a
g
e
w
it
h
A
r
ti
f
ac
ts
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
:
3
1
6
1
–
3
173
3170
3
.
4
.
F
ull
Ascen
din
g
Ao
rt
a
Seg
m
e
nta
t
io
n
W
h
en
th
e
ao
r
ta
cr
o
s
s
s
ec
tio
n
s
h
ap
e
is
n
o
m
o
r
e
u
n
i
f
o
r
m
l
y
cir
cu
lar
an
d
Ho
u
g
h
tr
an
s
f
o
r
m
f
ailed
to
d
etec
t
it,
th
e
p
r
o
p
o
s
ed
r
ay
-
s
e
a
r
ch
-
b
ased
p
r
o
p
ag
atio
n
r
eg
io
n
g
r
o
w
i
n
g
al
g
o
r
ith
m
i
s
ap
p
lied
to
s
eg
m
e
n
t
t
h
e
r
e
m
ain
in
g
p
ar
t
o
f
th
e
asce
n
d
i
n
g
ao
r
ta.
T
h
e
s
eg
m
en
ted
p
ar
t
o
f
th
e
asce
n
d
in
g
ao
r
ta
tak
e
n
f
r
o
m
f
ir
s
t
s
tag
e
w
i
ll
r
ese
m
b
le
t
h
e
s
ee
d
f
o
r
th
e
r
eg
i
o
n
g
r
o
w
in
g
al
g
o
r
ith
m
.
T
h
e
p
r
o
p
o
s
ed
r
eg
io
n
g
r
o
w
in
g
al
g
o
r
ith
m
ta
k
es
t
h
e
s
ee
d
p
o
s
itio
n
an
d
in
ten
s
it
y
to
s
ea
r
ch
w
it
h
f
r
o
m
t
h
e
s
e
g
m
e
n
ted
asc
en
d
in
g
ao
r
ta
p
ar
t.
3
.
4
.
1
.
CT
A
Res
ults
T
h
e
f
u
ll a
s
ce
n
d
i
n
g
ao
r
ta
alg
o
r
i
th
m
is
ap
p
lied
o
n
th
e
r
e
m
a
in
i
n
g
u
n
v
is
ited
s
l
ices o
f
t
h
e
C
T
A
v
o
lu
m
es
an
d
it su
cc
e
s
s
f
u
ll
y
s
e
g
m
e
n
t
s
t
h
e
f
u
ll a
s
ce
n
d
i
n
g
ao
r
ta
f
r
o
m
t
h
e
ao
r
tic
ar
ch
d
o
w
n
to
o
s
tia
p
o
in
ts
as i
n
d
icate
d
in
Fig
u
r
e
1
0
.
T
h
e
th
r
es
h
o
ld
u
s
ed
f
o
r
th
e
r
eg
io
n
g
r
o
w
i
n
g
i
s
s
et
i
n
all
test
ca
s
es to
(
)
.
Fig
u
r
e
10.
Fu
ll
A
s
ce
n
d
in
g
A
o
r
ta
Seg
m
en
ta
tio
n
R
e
s
u
lts
f
o
r
4
C
T
A
D
ataset
s
3
.
4
.
2
.
PC
-
M
RI
R
esu
lt
s
W
h
en
ap
p
l
y
i
n
g
t
h
e
f
u
ll
asce
n
d
in
g
ao
r
ta
s
e
g
m
en
ta
tio
n
al
g
o
r
ith
m
o
n
P
C
-
M
R
I
i
m
a
g
e
s
at
d
if
f
er
en
t
ti
m
e
f
r
a
m
e
s
,
it
s
u
cc
ee
d
ed
to
s
e
g
m
en
t
t
h
e
a
s
ce
n
d
in
g
ao
r
ta
cr
o
s
s
s
ec
tio
n
,
al
th
o
u
g
h
its
s
h
ap
e
d
if
f
er
s
f
r
o
m
f
r
a
m
e
to
an
o
th
er
,
s
ee
Fi
g
u
r
e
11(
b
)
.
(
a)
(
b
)
Fig
u
r
e
11
.
(
a)
P
C
-
MRI
Im
a
g
e
s
at
d
if
f
er
en
t
T
i
m
e
Fra
m
es,
(
b
)
A
s
ce
n
d
i
ng
A
o
r
ta
Det
ec
ted
as
R
ed
C
i
r
cle
3
.
5
.
P
er
f
o
r
m
a
nce
M
ea
s
ures
3
.
5
.
1
.
Acc
ura
cy
M
ea
s
u
re
T
o
m
ea
s
u
r
e
t
h
e
ac
c
u
r
ac
y
o
f
th
e
s
eg
m
e
n
tatio
n
r
es
u
lt
s
,
t
h
e
au
t
o
m
a
ticall
y
s
e
g
m
en
ted
a
s
ce
n
d
i
n
g
ao
r
ta
i
s
v
alid
ated
v
er
s
u
s
a
m
a
n
u
al
l
y
s
eg
m
e
n
ted
ascen
d
i
n
g
ao
r
ta
cr
o
s
s
s
ec
tio
n
s
;
u
s
i
n
g
Dice
Si
m
ilar
it
y
C
o
e
f
f
icien
t
(
DSC
)
,
to
m
ea
s
u
r
e
th
e
d
eg
r
ee
o
f
o
v
er
lap
b
et
w
ee
n
b
o
th
cr
o
s
s
s
ec
tio
n
s
i
n
all
t
h
e
v
o
l
u
m
e
s
lic
es,
s
ee
Fi
g
u
r
e
12.
D
i
ce
C
oe
f
f
i
c
i
en
t
=
(
5
)
Evaluation Warning : The document was created with Spire.PDF for Python.