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.
11
,
No
.
3
,
J
u
n
e
2
0
2
1
,
p
p
.
2613
~
2
6
2
0
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
1
1
i
3
.
pp
2
6
1
3
-
2
6
2
0
2613
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Co
m
pa
riso
n of
mutua
l inf
o
r
m
a
tion
and its
po
int
si
m
i
la
rity
i
m
pl
e
m
entatio
n
f
o
r i
m
a
g
e r
eg
istra
t
io
n
Wa
s
s
i
m
E
l H
a
j
j
Cheha
de
1
,
P
et
er
Ro
g
elj
2
1
M
a
th
e
m
a
ti
c
s a
n
d
Co
m
p
u
ter S
c
ien
c
e
De
p
a
rtme
n
t,
Be
iru
t
A
ra
b
Un
i
v
e
rsit
y
,
Leb
a
n
o
n
2
F
a
c
u
lt
y
o
f
M
a
th
e
m
a
ti
c
s,
Na
tu
ra
l
S
c
ien
c
e
s a
n
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
ies
,
Un
iv
e
rsity
o
f
P
rim
o
rsk
a
,
S
lo
v
e
n
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l 1
2
,
2
0
2
0
R
ev
i
s
ed
Dec
2
2
,
2
0
2
0
A
cc
ep
ted
J
an
8
,
2
0
2
1
M
u
tu
a
l
in
f
o
rm
a
ti
o
n
(M
I)
is
o
n
e
o
f
th
e
m
o
st
p
o
p
u
lar
a
n
d
w
id
e
ly
u
se
d
sim
il
a
rit
y
m
e
a
su
re
s
in
i
m
a
g
e
re
g
istratio
n
.
In
trad
it
io
n
a
l
re
g
istratio
n
p
ro
c
e
ss
e
s,
M
I
is
c
o
m
p
u
ted
in
e
a
c
h
o
p
ti
m
iza
ti
o
n
ste
p
to
m
e
a
su
re
th
e
sim
il
a
rit
y
b
e
t
w
e
e
n
th
e
re
f
e
re
n
c
e
i
m
a
g
e
a
n
d
th
e
m
o
v
in
g
ima
g
e
.
T
h
e
p
re
su
m
p
ti
o
n
is
th
a
t
w
h
e
n
e
v
e
r
M
I
re
a
c
h
e
s
it
s
h
ig
h
e
st
v
a
lu
e
,
t
h
is
c
o
rre
sp
o
n
d
s
to
th
e
b
e
st
m
a
tch
.
T
h
is
p
a
p
e
r
sh
o
w
s
th
a
t
th
is
p
re
su
m
p
ti
o
n
is
n
o
t
a
lw
a
y
s
v
a
li
d
a
n
d
th
is
lea
d
s
to
re
g
istratio
n
e
rro
r.
T
o
o
v
e
rc
o
m
e
th
is
p
ro
b
lem
,
w
e
p
ro
p
o
se
to
u
se
p
o
in
t
sim
il
a
r
it
y
m
e
a
su
re
s
(P
S
M
)
w
h
ich
in
c
o
n
tras
t
to
M
I
a
ll
o
ws
c
o
n
sta
n
t
in
ten
sity
d
e
p
e
n
d
e
n
c
e
e
stim
a
tes
c
a
ll
e
d
p
o
i
n
t
sim
il
a
rit
y
f
u
n
c
ti
o
n
s
(P
S
F
).
W
e
c
o
m
p
a
re
M
I
a
n
d
P
S
M
sim
il
a
rit
y
m
e
a
su
re
s
in
term
s
o
f
re
g
istratio
n
m
is
a
li
g
n
m
e
n
t
e
rro
rs.
T
h
e
re
su
lt
o
f
th
e
c
o
m
p
a
riso
n
c
o
n
f
irm
s
th
a
t
th
e
b
e
st
a
li
g
n
m
e
n
t
is
n
o
t
a
t
t
h
e
h
ig
h
e
st
v
a
lu
e
o
f
M
I
b
u
t
n
e
a
r
to
it
a
n
d
it
sh
o
w
s
th
a
t
P
S
M
p
e
rf
o
rm
s
b
e
tt
e
r
th
a
n
M
I
if
P
S
F
m
a
tch
e
s
th
e
c
o
rre
c
t
in
ten
sity
d
e
p
e
n
d
e
n
c
e
b
e
tw
e
e
n
i
m
a
g
e
s.
T
h
is
o
p
e
n
s
a
n
e
w
d
irec
ti
o
n
o
f
re
s
e
a
r
c
h
to
w
a
rd
s
th
e
im
p
ro
v
e
m
e
n
t
o
f
ima
g
e
re
g
istr
a
ti
o
n
.
K
ey
w
o
r
d
s
:
L
o
ca
lit
y
Mu
t
u
al
in
f
o
r
m
a
tio
n
P
o
in
t si
m
i
lar
it
y
m
ea
s
u
r
es
R
eg
i
s
tr
atio
n
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
W
ass
i
m
E
l H
aj
j
C
h
eh
ad
e
Ma
th
e
m
atics
a
n
d
C
o
m
p
u
ter
S
cien
ce
Dep
ar
t
m
e
n
t
B
eir
u
t A
r
ab
Un
iv
er
s
it
y
R
iad
E
l So
lh
,
1
1
0
7
2
8
0
9
,
P
.
O.
B
o
x
1
1
-
5
0
2
0
B
eir
u
t,
L
eb
an
o
n
E
m
ail:
w
a
s
s
i
m
.
c
h
eh
ad
e
@
b
au
.
ed
u
.
lb
1.
I
NT
RO
D
UCT
I
O
N
I
m
ag
e
r
e
g
is
tr
atio
n
is
a
n
i
m
p
o
r
tan
t
f
ield
i
n
i
m
ag
e
p
r
o
ce
s
s
in
g
.
I
t
co
n
s
i
s
ts
i
n
ali
g
n
in
g
t
w
o
i
m
ag
e
s
ac
co
r
d
in
g
to
an
id
en
ti
f
ied
tr
an
s
f
o
r
m
atio
n
.
I
n
m
ed
ical
i
m
ag
in
g
,
t
h
e
r
e
g
is
tr
atio
n
o
f
i
m
ag
es
f
r
o
m
d
i
f
f
er
en
t
m
o
d
ali
ties
is
o
f
ten
clas
s
i
f
ied
as
m
u
lt
i
m
o
d
al.
T
h
ese
i
m
ag
es
ca
n
b
e
en
h
an
ce
d
[
1
,
2
]
an
d
th
en
u
s
ed
f
o
r
r
eg
is
tr
atio
n
.
W
h
en
ch
a
n
g
e
s
o
r
m
o
t
i
o
n
s
i
n
im
ag
e
s
a
r
e
l
im
it
e
d
t
o
g
l
o
b
a
l
r
o
t
a
ti
o
n
s
an
d
t
r
an
s
l
a
t
io
n
s
th
e
r
eg
is
t
r
at
i
o
n
i
s
c
al
l
e
d
r
ig
i
d
an
d
w
h
en
m
o
ti
o
n
s
in
c
lu
d
e
c
o
m
p
l
ex
l
o
c
al
v
a
r
i
ati
o
n
s
th
e
r
eg
is
t
r
a
ti
o
n
c
a
l
le
d
n
o
n
-
r
ig
id
.
I
n
ten
s
it
y
-
b
ased
r
e
g
is
tr
at
io
n
i
s
u
s
ed
to
f
i
n
d
th
e
o
p
ti
m
al
g
eo
m
etr
ic
tr
a
n
s
f
o
r
m
atio
n
w
h
ic
h
m
ax
i
m
izes
th
e
co
r
r
esp
o
n
d
en
ce
s
b
et
w
ee
n
i
m
a
g
es.
T
h
is
co
r
r
esp
o
n
d
en
ce
ca
n
b
e
m
ea
s
u
r
ed
u
s
in
g
in
te
n
s
i
t
y
-
b
ased
s
i
m
i
lar
it
y
m
ea
s
u
r
es.
I
n
t
h
e
liter
atu
r
e,
a
v
ar
iet
y
o
f
in
ten
s
it
y
-
b
a
s
ed
s
i
m
il
ar
it
y
m
ea
s
u
r
e
s
ex
i
s
t
[
3
,
4
]
.
T
h
e
y
ca
n
b
e
class
i
f
ie
d
in
to
m
o
n
o
-
m
o
d
al
a
n
d
m
u
lti
-
m
o
d
al
m
ea
s
u
r
es
d
ep
en
d
in
g
o
n
i
m
ag
e
in
ten
s
it
y
r
elatio
n
s
a
n
d
ch
ar
ac
ter
is
tic
s
.
T
h
is
p
ap
er
f
o
cu
s
es
o
n
i
n
te
n
s
it
y
-
b
ased
r
eg
is
tr
atio
n
u
s
i
n
g
m
u
lti
-
m
o
d
alit
y
s
i
m
ilar
it
y
m
ea
s
u
r
e
s
w
h
ic
h
ar
e
o
f
te
n
co
n
s
id
er
ed
as
s
o
lv
ed
p
r
o
b
le
m
s
u
s
i
n
g
M
u
t
u
al
I
n
f
o
r
m
atio
n
b
u
t
ar
e
s
til
l
s
u
b
j
ec
t
to
d
if
f
ic
u
lt
i
es
r
eq
u
ir
i
n
g
ac
ti
v
e
f
u
r
t
h
er
r
esear
ch
.
R
eg
i
s
tr
atio
n
o
f
m
ed
ical
i
m
a
g
es
ten
d
s
to
f
in
d
th
e
o
p
ti
m
al
g
eo
m
e
tr
ic
tr
an
s
f
o
r
m
at
io
n
b
y
o
p
ti
m
izi
n
g
a
cr
iter
io
n
f
u
n
ctio
n
o
v
er
m
u
lti
p
le
o
p
ti
m
izatio
n
s
tep
s
.
I
n
ea
ch
s
tep
,
th
e
tr
a
n
s
f
o
r
m
atio
n
i
s
alter
ed
a
n
d
th
e
cr
iter
io
n
f
u
n
ctio
n
is
r
ec
o
m
p
u
ted
.
T
h
e
p
r
o
ce
s
s
is
s
to
p
p
ed
w
h
e
n
t
h
e
cr
iter
io
n
f
u
n
ctio
n
r
ea
ch
es
i
ts
o
p
ti
m
u
m
v
alu
e.
T
h
e
cr
iter
io
n
f
u
n
c
tio
n
co
m
p
r
is
e
s
s
i
m
ilar
it
y
m
ea
s
u
r
e
s
u
s
ed
to
ev
a
lu
ate
th
e
q
u
alit
y
o
f
t
h
e
i
m
ag
e
m
atc
h
.
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.
11
,
No
.
3
,
J
u
n
e
2
0
2
1
:
2
6
1
3
-
2620
2614
M
u
t
u
a
l
i
n
f
o
r
m
a
t
i
o
n
(
MI
)
is
t
h
e
m
o
s
t
w
id
el
y
u
s
ed
m
u
lti
-
m
o
d
al
s
i
m
ilar
i
t
y
m
ea
s
u
r
e
[
5
-
7
]
.
I
t
is
a
s
tati
s
tical
m
ea
s
u
r
e
t
h
at
e
v
al
u
ates
j
o
in
t
in
te
n
s
it
y
d
is
tr
ib
u
tio
n
.
Alt
h
o
u
g
h
it
w
a
s
p
r
o
p
o
s
ed
2
5
y
e
ar
s
ag
o
,
it
is
s
t
ill
co
n
s
id
er
ed
o
p
ti
m
al
a
n
d
s
e
lect
ed
f
o
r
th
e
v
a
s
t
m
aj
o
r
it
y
o
f
m
u
lti
-
m
o
d
alit
y
i
m
a
g
e
r
eg
i
s
tr
atio
n
alg
o
r
it
h
m
s
[
8
-
1
0
]
.
T
h
e
w
ea
k
n
es
s
o
f
m
u
tu
al
i
n
f
o
r
m
atio
n
a
s
a
s
i
m
ilar
it
y
m
ea
s
u
r
e
is
its
h
ig
h
co
m
p
u
tatio
n
a
l c
o
s
t.
T
o
r
e
d
u
ce
th
e
r
eg
i
s
tr
atio
n
c
o
m
p
u
tatio
n
co
s
t
p
ar
allel
p
r
o
ce
s
s
i
n
g
tec
h
n
iq
u
es
ca
n
b
e
u
s
ed
.
T
h
ese
tech
n
iq
u
es
tr
y
to
p
ar
allelize
th
e
i
m
p
le
m
en
ta
tio
n
o
f
e
x
i
s
ti
n
g
i
m
ag
e
r
e
g
is
tr
atio
n
al
g
o
r
ith
m
s
w
it
h
o
u
t
o
p
ti
m
izi
n
g
th
eir
co
r
e
i
m
p
le
m
en
tatio
n
[
1
1
-
1
4
]
.
R
ec
en
t
s
t
u
d
ies
h
a
v
e
also
d
e
m
o
n
s
tr
ated
t
h
at
d
ee
p
lear
n
i
n
g
m
et
h
o
d
s
,
n
o
tab
l
y
co
n
v
o
l
u
tio
n
al
n
e
u
r
al
n
et
w
o
r
k
s
(
C
o
n
v
Nets),
ca
n
b
e
u
s
ed
f
o
r
ad
d
r
ess
i
n
g
c
h
alle
n
g
in
g
i
m
a
g
e
r
eg
i
s
tr
atio
n
p
r
o
b
lem
s
[
1
5
,
1
6
]
.
T
h
ese
s
t
u
d
ies
ca
n
b
e
class
i
f
ied
in
to
t
w
o
m
ai
n
r
esear
c
h
ar
ea
s
:
tr
an
s
f
o
r
m
at
io
n
esti
m
at
io
n
an
d
s
i
m
ilar
it
y
e
s
ti
m
atio
n
.
A
l
t
h
o
u
g
h
d
ee
p
lear
n
i
n
g
co
n
s
tit
u
t
es
a
f
a
m
o
u
s
a
n
d
p
r
o
m
i
s
in
g
te
ch
n
iq
u
e
f
o
r
i
m
ag
e
r
eg
is
tr
atio
n
,
it
s
till
f
ac
es
s
o
m
e
ch
alle
n
g
es
in
c
lu
d
i
n
g
t
h
e
l
a
c
k
o
f
a
r
o
b
u
s
t
s
i
m
i
l
a
r
i
t
y
m
e
a
s
u
r
e
f
o
r
m
u
l
t
i
m
o
d
a
l
a
p
p
l
i
c
a
t
i
o
n
s
,
t
h
e
l
a
c
k
o
f
l
a
r
g
e
d
a
t
a
s
e
t
s
,
t
h
e
d
i
f
f
i
c
u
l
t
y
i
n
o
b
t
a
i
n
i
n
g
s
e
g
m
e
n
t
a
t
i
o
n
a
n
d
g
r
o
u
n
d
t
r
u
t
h
r
e
g
i
s
t
r
a
t
i
o
n
s
[
1
7
]
.
T
h
er
e
ex
is
t
also
o
th
er
w
ea
k
n
es
s
es
o
f
m
u
t
u
al
in
f
o
r
m
a
tio
n
w
h
ic
h
is
n
o
t
s
o
ev
id
e
n
t
an
d
m
a
y
b
e
co
m
m
o
n
to
m
a
n
y
m
u
lti
m
o
d
alit
y
s
i
m
ilar
it
y
m
ea
s
u
r
es.
I
t
r
esid
es
in
t
h
e
p
r
esu
m
p
tio
n
t
h
at
a
h
ig
h
er
v
al
u
e
o
f
s
i
m
ilar
it
y
co
r
r
esp
o
n
d
s
to
lo
w
er
alig
n
m
e
n
t
er
r
o
r
.
T
h
is
p
r
esu
m
p
tio
n
i
s
n
o
t
co
r
r
ec
t
an
d
r
ef
l
ec
ts
in
r
ed
u
ci
n
g
th
e
q
u
alit
y
o
f
th
e
i
m
ag
e
m
atc
h
[
1
8
]
.
I
n
r
ea
lit
y
,
w
h
en
a
g
eo
m
etr
ic
tr
a
n
s
f
o
r
m
atio
n
T
is
s
ea
r
ch
ed
b
ased
o
n
o
p
tim
izin
g
a
s
i
m
ilar
it
y
m
ea
s
u
r
e,
th
e
alig
n
m
e
n
t
er
r
o
r
b
etw
e
en
th
e
r
eg
i
s
ter
ed
i
m
a
g
e
an
d
t
h
e
r
ef
er
en
ce
i
m
a
g
e
m
a
y
n
o
t
b
e
t
h
e
lo
w
est
at
t
h
e
o
p
tim
ized
s
i
m
ilar
it
y
v
a
lu
e
b
u
t
n
ea
r
to
it.
Mo
r
eo
v
er
,
th
is
a
li
g
n
m
e
n
t
er
r
o
r
co
u
ld
d
if
f
er
b
ased
o
n
t
h
e
s
i
m
i
lar
it
y
m
ea
s
u
r
e
u
s
ed
.
As
an
a
lter
n
ati
v
e,
d
ee
p
m
etr
ics
w
er
e
p
r
o
p
o
s
ed
[
1
9
-
21
]
,
h
o
w
e
v
er
th
e
p
r
o
b
le
m
o
f
p
r
ec
is
io
n
r
e
m
ain
s
t
h
e
s
a
m
e.
T
h
er
ef
o
r
e,
th
e
r
e
is
an
i
m
p
o
r
tan
t
n
ee
d
f
o
r
s
ea
r
ch
in
g
alter
n
ati
v
e
m
u
lti
-
m
o
d
alit
y
s
i
m
i
lar
it
y
m
ea
s
u
r
es t
h
at
co
u
n
ter
th
is
w
ea
k
n
e
s
s
.
T
o
tack
le
th
ese
p
r
o
b
le
m
s
,
a
n
alter
n
a
tiv
e
ap
p
r
o
ac
h
ca
lled
p
o
in
t
s
i
m
ilar
it
y
m
ea
s
u
r
es
(
P
SM)
w
as
p
r
o
p
o
s
ed
in
2
0
0
3
[
2
2
]
b
u
t
h
as
n
ev
er
r
ea
ch
ed
w
id
e
atten
ti
o
n
o
f
th
e
i
m
a
g
e
r
eg
i
s
tr
atio
n
co
m
m
u
n
it
y
.
I
t
u
s
es
co
n
s
ta
n
t
i
m
a
g
e
i
n
te
n
s
i
t
y
d
ep
en
d
en
ce
e
s
ti
m
ate
s
ca
lled
p
o
i
n
t
s
i
m
ilar
it
y
f
u
n
c
tio
n
(
P
SF
)
d
u
r
in
g
t
h
e
r
e
g
is
tr
atio
n
o
p
tim
izatio
n
s
tep
s
w
h
ich
co
n
t
r
ib
u
tes
in
r
ed
u
c
in
g
s
i
m
ilar
it
y
co
m
p
u
tatio
n
ti
m
e.
Mo
r
eo
v
er
,
P
SM
ca
n
en
h
a
n
ce
g
r
ea
tl
y
t
h
e
q
u
al
it
y
o
f
th
e
i
m
a
g
e
m
atc
h
i
f
P
SF
is
co
m
p
u
ted
at
th
e
co
r
r
ec
t
i
m
a
g
e
al
ig
n
m
en
t.
I
n
t
h
i
s
p
ap
er
,
w
e
w
il
l
s
h
o
w
th
e
p
o
ten
tial
o
f
u
s
i
n
g
P
SM
f
o
r
en
h
a
n
ci
n
g
th
e
q
u
alit
y
o
f
i
m
a
g
e
m
atc
h
w
h
ile
le
av
in
g
it
s
p
o
ten
tial
i
n
r
ed
u
cin
g
co
m
p
u
tatio
n
ti
m
e
f
o
r
an
o
th
er
p
ap
er
.
W
e
w
i
l
l
i
l
l
u
s
t
r
a
t
e
t
h
e
a
d
v
a
n
t
a
g
e
s
o
f
t
h
i
s
m
e
t
h
o
d
f
o
r
c
o
n
v
e
n
t
i
o
n
a
l
i
m
a
g
e
r
e
g
i
s
t
r
a
t
i
o
n
a
p
p
r
o
a
c
h
e
s
a
n
d
s
t
i
m
u
l
a
t
e
i
t
s
u
s
e
i
n
m
o
d
e
r
n
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
b
ased
s
o
l
u
t
io
n
s
.
I
n
th
is
p
ap
er
,
w
e
w
i
ll
f
ir
s
t
d
e
m
o
n
s
tr
ate
th
at
th
e
b
est
i
m
a
g
e
m
atc
h
is
n
o
t
al
w
a
y
s
o
b
tain
ed
at
th
e
h
ig
h
e
s
t
v
al
u
e
o
f
MI
o
r
P
SM.
W
e
w
ill
co
m
p
ar
e
alig
n
m
en
t
er
r
o
r
s
o
f
im
a
g
es
f
r
o
m
d
if
f
er
e
n
t
m
o
d
ali
ties
u
s
i
n
g
MI
s
i
m
ilar
it
y
m
ea
s
u
r
e
an
d
P
SM
d
er
iv
ed
f
r
o
m
MI
.
W
e
w
ill
p
r
o
v
e
th
e
n
t
h
at
P
SM
w
it
h
an
o
p
ti
m
al
c
h
o
ice
o
f
P
SF
ca
n
r
ed
u
ce
th
e
alig
n
m
en
t
er
r
o
r
ev
en
m
o
r
e
th
an
u
s
i
n
g
M
u
tu
al
in
f
o
r
m
a
tio
n
.
T
h
e
r
em
ai
n
d
er
o
f
th
is
p
ap
er
is
o
r
g
an
ized
as
:
s
ec
tio
n
2
p
r
ese
n
ts
p
o
in
t
s
i
m
ilar
it
y
m
ea
s
u
r
e
s
an
d
h
o
w
it
ca
n
b
e
ap
p
lied
to
co
m
p
u
te
i
m
ag
e
s
i
m
ilar
it
y
.
Sectio
n
3
s
h
o
w
s
a
co
m
p
ar
ati
v
e
s
tu
d
y
b
et
w
ee
n
M
I
an
d
P
SM
in
r
eg
i
s
ter
in
g
m
ed
i
ca
l
i
m
a
g
es.
Sectio
n
4
an
d
5
p
r
esen
t d
is
cu
s
s
io
n
s
a
n
d
co
n
clu
s
io
n
s
.
2.
P
O
I
NT
S
I
M
I
L
ARI
T
Y
M
E
ASURE
S
Me
asu
r
i
n
g
s
i
m
ilar
it
y
u
s
in
g
p
o
in
t
s
i
m
ilar
it
y
m
ea
s
u
r
es
co
n
s
is
t
s
o
f
t
w
o
s
tep
s
.
T
h
e
f
ir
s
t
s
tep
c
o
m
p
u
tes
a
p
o
in
t
s
i
m
ilar
it
y
f
u
n
ctio
n
(
P
SF
)
(
)
w
h
ic
h
is
an
e
s
ti
m
ate
o
f
t
h
e
in
te
n
s
it
y
d
ep
en
d
e
n
ce
b
et
w
ee
n
t
w
o
i
m
a
g
es
A
an
d
B
.
T
h
e
s
ec
o
n
d
s
tep
u
s
es
th
e
p
o
in
t
s
i
m
ilar
it
y
f
u
n
ctio
n
(
)
to
p
r
o
v
id
e
ac
tu
al
m
ea
s
u
r
e
m
e
n
t
o
f
s
i
m
ilar
it
y
b
et
w
ee
n
i
m
a
g
e
s
A
an
d
B
.
2
.
1
.
Co
m
pu
t
ing
P
SF
P
SF
ca
n
b
e
d
er
iv
ed
f
r
o
m
al
m
o
s
t
an
y
in
te
n
s
it
y
-
b
ased
s
i
m
ilar
it
y
m
ea
s
u
r
e.
Mu
t
u
al
i
n
f
o
r
m
atio
n
(
MI
)
is
o
n
e
o
f
t
h
ese
i
n
te
n
s
it
y
-
b
ased
s
i
m
ilar
it
y
m
ea
s
u
r
es.
I
n
t
h
i
s
p
ap
er
,
w
e
w
ill
d
er
i
v
e
P
SF
f
r
o
m
Mu
t
u
al
I
n
f
o
r
m
atio
n
s
i
m
ilar
it
y
m
ea
s
u
r
e.
MI
ca
n
b
e
co
m
p
u
ted
as
(
1
)
.
=
∑
(
)
(
(
)
(
)
(
)
)
(
1
)
w
h
er
e
i=[
i
A
,i
B
]
i
s
a
n
i
n
ten
s
it
y
p
air
co
r
r
esp
o
n
d
in
g
to
i
m
ag
e
i
n
ten
s
itie
s
i
n
i
m
a
g
es
A
an
d
B
at
p
o
s
itio
n
o
f
v
o
x
el
v
,
p
(
i
A
)
an
d
p
(
i
B
)
ar
e
m
ar
g
i
n
al
in
t
en
s
it
y
p
r
o
b
ab
ilit
ies
an
d
p
(
i)
=
p
(
i
A
,
i
B
)
is
th
e
j
o
in
t
in
ten
s
i
t
y
p
r
o
b
ab
ilit
y
,
esti
m
ated
f
r
o
m
t
h
e
i
m
ag
e
s
.
T
o
illu
s
tr
ate
h
o
w
P
S
F
ca
n
b
e
c
o
m
p
u
ted
,
i
m
ag
in
e
t
w
o
s
i
m
p
le
i
m
a
g
es
A
a
n
d
B
o
f
s
ize
(
6
*
6
w
h
er
e
ea
ch
ce
ll
r
ep
r
esen
t
s
o
n
e
p
ix
el)
r
ep
r
esen
ti
n
g
th
e
s
a
m
e
o
b
j
ec
t
as
s
h
o
w
n
i
n
Fig
u
r
e
1
.
I
m
a
g
es
A
an
d
B
co
n
s
is
ts
o
f
o
n
l
y
t
w
o
i
n
ten
s
i
t
y
co
lo
r
v
alu
e
s
.
I
n
I
m
a
g
e
A
,
i
n
te
n
s
it
y
o
f
lig
h
t
p
ix
e
ls
is
r
ep
r
esen
ted
b
y
i
1
A
w
h
er
ea
s
d
ar
k
p
ix
el
s
ar
e
r
ep
r
e
s
en
ted
b
y
i
2A
.
Si
m
i
lar
l
y
,
i
n
ten
s
it
y
o
f
lig
h
t
p
i
x
els
i
n
i
m
ag
e
B
is
r
ep
r
esen
ted
i
1B
an
d
i
2B
f
o
r
d
ar
k
p
ix
e
ls
.
T
h
e
j
o
in
t
h
i
s
to
g
r
a
m
o
f
t
h
ese
t
w
o
i
m
ag
es
is
d
ep
icted
in
T
ab
le
1
(
a
)
.
A
s
w
e
ca
n
s
ee
,
t
h
i
s
j
o
in
t
h
is
to
g
r
a
m
co
n
s
i
s
ts
o
n
l
y
o
f
t
w
o
n
o
n
-
ze
r
o
v
alu
e
s
at
i
n
te
n
s
it
y
p
air
s
[
i
1A
,
i
1B
]
an
d
[
i
2A
,
i
2B
]
b
ec
au
s
e
i
n
ten
s
it
y
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:
2
0
8
8
-
8708
C
o
mp
a
r
is
o
n
o
f m
u
tu
a
l in
fo
r
m
a
tio
n
a
n
d
its
p
o
in
t simil
a
r
ity
imp
leme
n
ta
tio
n
…
(
W
a
s
s
im
E
l
Ha
jj C
h
eh
a
d
e
)
2615
r
eg
io
n
s
i
n
i
m
ag
e
s
A
an
d
B
p
er
f
ec
tl
y
o
v
er
lap
.
On
th
e
o
th
e
r
h
an
d
,
w
h
e
n
i
m
a
g
es
d
o
n
o
t
o
v
er
lap
ex
ac
tl
y
a
s
s
h
o
w
n
i
n
Fi
g
u
r
e
2
,
ad
d
it
io
n
al
in
te
n
s
it
y
p
air
s
ap
p
ea
r
(
[
i
1A
,
i
2B
]
an
d
/o
r
[
i
2A
,
i
1B
]
)
.
T
h
e
v
al
u
e
s
at
in
te
n
s
it
y
p
air
s
d
ep
en
d
o
n
th
e
s
ize
o
f
o
v
er
lap
p
in
g
r
eg
io
n
s
.
T
h
e
j
o
in
t
h
is
to
g
r
a
m
co
r
r
esp
o
n
d
in
g
to
th
ese
t
w
o
i
m
a
g
e
s
is
s
h
o
w
n
in
T
ab
le
2
(
a
)
.
T
h
e
jo
in
t
d
is
tr
ib
u
tio
n
ca
n
n
o
w
b
e
es
ti
m
a
ted
b
y
d
iv
id
i
n
g
t
h
e
v
a
lu
e
s
in
th
e
j
o
in
t
h
i
s
to
g
r
a
m
b
y
t
h
e
n
u
m
b
er
o
f
v
o
x
els
w
h
ic
h
e
q
u
als
in
o
u
r
ca
s
e
to
6
*
6
=
3
6
v
o
x
els.
T
ab
les
1
(
b
)
an
d
2
(
b
)
s
h
o
w
r
esp
ec
ti
v
el
y
t
h
e
j
o
in
t
d
is
tr
ib
u
tio
n
s
co
r
r
esp
o
n
d
in
g
to
th
e
p
er
f
ec
tl
y
an
d
n
o
t
p
er
f
ec
tl
y
ali
g
n
ed
i
m
ag
e
s
.
Hav
in
g
n
o
w
t
h
e
j
o
in
t
d
is
tr
ib
u
tio
n
,
MI
co
u
ld
b
e
co
m
p
u
ted
u
s
i
n
g
(
1
)
.
MI
h
as
a
h
ig
h
co
m
p
u
tatio
n
al
co
s
t
s
i
n
c
e
it
r
eq
u
ir
es
to
b
e
co
m
p
u
ted
in
ea
ch
o
p
ti
m
izati
o
n
.
T
h
e
alg
o
r
ith
m
co
n
ti
n
u
es
lo
o
p
in
g
u
n
til
t
h
e
o
p
ti
m
u
m
v
a
lu
e
o
f
th
e
cr
iter
io
n
f
u
n
ctio
n
is
f
o
u
n
d
.
C
o
m
p
u
ti
n
g
MI
in
ea
ch
o
p
t
i
m
izatio
n
s
tep
in
d
u
ce
s
co
m
p
u
t
in
g
t
h
e
j
o
in
t
h
is
to
g
r
a
m
,
t
h
e
j
o
in
t
d
is
tr
ib
u
tio
n
t
h
e
n
ca
lli
n
g
t
h
e
lo
g
f
u
n
ctio
n
.
C
o
n
s
eq
u
en
t
l
y
,
t
h
is
co
n
tr
ib
u
tes to
i
n
cr
ea
s
e
MI
co
m
p
u
tat
io
n
al
co
s
t.
(
A
)
(
B
)
Fig
u
r
e
1
.
I
m
a
g
es
A
a
n
d
B
p
er
f
ec
tl
y
ali
g
n
ed
(
A
)
(
B
)
Fig
u
r
e
2
.
I
m
a
g
es
A
a
n
d
B
m
is
alig
n
ed
T
ab
le
1
.
P
er
f
ec
tl
y
alig
n
ed
i
m
a
g
es
(
a)
j
o
in
t h
is
to
g
r
a
m
,
a
n
d
(
b
)
jo
in
t d
is
tr
ib
u
tio
n
i
1A
i
2A
i
2B
0
6
i
1B
30
0
(
a)
i
1A
i
2A
i
2B
0
0
.
1
6
6
i
1B
0
.
8
3
3
0
(
b
)
T
ab
le
2
.
Misalig
n
ed
i
m
ag
e
s
(
a)
j
o
in
t h
is
to
g
r
a
m
,
a
n
d
(
b
)
jo
in
t
d
is
tr
ib
u
tio
n
i
1A
i
2A
i
2B
2
4
i
1B
28
2
(
a)
i
1A
i
2A
i
2B
0
.
0
5
0
.
1
1
i
1B
0
.
7
7
0
.
0
5
(
b
)
T
o
r
ed
u
ce
th
is
co
s
t,
P
SM
r
elies
in
s
tead
o
n
u
s
i
n
g
P
SF
c
o
m
p
u
ted
o
n
ce
at
th
e
b
e
g
in
n
i
n
g
o
f
th
e
r
eg
is
tr
atio
n
p
r
o
ce
s
s
.
P
SF
r
ep
r
esen
t
s
an
e
s
ti
m
ate
o
f
th
e
in
te
n
s
it
y
d
ep
en
d
en
ce
b
et
w
ee
n
r
e
f
er
en
ce
an
d
m
o
v
i
n
g
i
m
a
g
es
m
ea
s
u
r
ed
f
o
r
ea
ch
in
te
n
s
it
y
p
air
i =
[
i
A
,
i
B
]
u
s
i
n
g
(
2
)
.
(
)
=
(
(
)
(
)
(
)
)
(
2
)
w
h
e
n
th
e
s
e
s
i
m
i
lar
ities
ar
e
g
r
o
u
p
ed
in
o
n
e
tab
le,
th
e
y
f
o
r
m
w
h
at
w
e
ca
ll
p
o
i
n
t
s
i
m
ilar
it
y
f
u
n
ctio
n
(
P
SF
)
.
T
ab
le
3
s
h
o
w
s
r
esp
ec
tiv
el
y
P
SF
f
o
r
th
e
i
m
a
g
es
p
er
f
ec
tl
y
an
d
n
o
t
p
er
f
ec
tl
y
ali
g
n
ed
.
T
o
s
h
o
w
h
o
w
P
SF
is
co
m
p
u
ted
p
r
ac
ticall
y
,
let
u
s
co
n
s
id
er
th
e
ca
s
e
w
h
er
e
i
m
a
g
es
ar
e
p
er
f
ec
tl
y
ali
g
n
ed
.
He
r
e,
a
p
r
o
b
lem
ar
i
s
es
w
h
e
n
ap
p
ly
in
g
(
2
)
to
co
m
p
u
t
e
P
SF
f
o
r
in
ten
s
it
y
p
air
s
(
i
1A
,
i
2B
)
an
d
(
i
2A
,
i
1B
)
th
at
h
av
e
0
v
alu
e
s
in
t
h
e
j
o
in
t
h
is
to
g
r
a
m
T
ab
le
1
(
a
)
.
T
o
av
o
i
d
h
av
in
g
s
u
ch
co
m
p
u
tatio
n
er
r
o
r
s
(
i.e
.
lo
g
(
0
)
)
an
ε
co
u
ld
b
e
ad
d
ed
to
ea
ch
ce
ll
to
h
av
e
an
u
p
d
ated
j
o
in
t h
is
to
g
r
a
m
.
Her
e
w
e
ad
d
ed
+1
f
o
r
e
ac
h
v
al
u
e
i
n
t
h
e
j
o
in
t h
is
to
g
r
a
m
T
ab
le
4
(
a
)
.
Usi
n
g
n
o
w
th
e
n
e
w
j
o
in
t
h
i
s
t
o
g
r
a
m
an
d
(
2
)
,
s
i
m
i
lar
it
y
f
o
r
in
te
n
s
it
y
p
air
[
i
1A
,
i
1B
]
ca
n
b
e
co
m
p
u
ted
,
f
o
r
ex
a
m
p
le,
as
(
3
)
.
=
(
(
1
,
1
)
(
1
)
(
1
)
)
=
l
og
(
0
.
775
30
36
×
30
36
)
=
0
.
109
(
3
)
T
h
e
co
m
p
u
ta
tio
n
o
f
o
t
h
er
in
te
n
s
it
y
p
air
s
f
o
llo
w
s
th
e
s
a
m
e
p
r
in
cip
le.
T
h
e
g
lo
b
al
s
i
m
i
lar
it
y
m
ea
s
u
r
e
MI
b
ased
o
n
P
SF
T
a
b
le
3
ca
n
b
e
co
m
p
u
ted
f
o
r
th
e
p
er
f
ec
t
l
y
an
d
n
o
t
p
er
f
ec
tl
y
ali
g
n
ed
i
m
a
g
es
u
s
i
n
g
(
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.
11
,
No
.
3
,
J
u
n
e
2
0
2
1
:
2
6
1
3
-
2620
2616
=
1
∑
×
(
i
)
(
4
)
w
h
er
e
N
is
t
h
e
to
tal
n
u
m
b
er
o
f
v
o
x
els i
n
t
h
e
i
m
ag
e
a
n
d
i
r
ep
r
esen
t
s
in
te
n
s
it
y
p
air
s
.
Usi
n
g
(
4
)
,
th
e
s
i
m
ilar
it
y
b
et
wee
n
p
er
f
ec
tl
y
ali
g
n
ed
i
m
ag
e
s
is
th
en
:
MI
1
=[
(
3
1
×0
.
1
0
9
)
+
(
7
×
1
.
84)
+
(
1
×
-
1
.
7
1
4
)
+(
1
×
-
1
.
7
1
4
)
]
/4
0
=
0
.
3
2
an
d
f
o
r
n
o
t
ali
g
n
ed
i
m
a
g
es
MI
2
=[
(
2
8
×0
.
1
1
3
)
+(
4
×1
.
3
8
6
)
+(
2
×
-
1
.
0
2
)
+
(
2
×
-
1
.
0
2
)
]
/3
6
=
0
.
1
2
8
5
6
.
W
e
n
o
tice
th
at
MI
1
is
g
r
ea
ter
th
an
MI
2
,
w
h
ic
h
is
e
x
p
ec
ted
.
2
.
2
.
Reg
is
t
ra
t
io
n ba
s
ed
o
n P
SM
T
h
e
ad
v
an
tag
e
o
f
u
s
in
g
p
o
in
t
s
i
m
ilar
it
y
m
ea
s
u
r
es
i
n
i
m
a
g
e
r
eg
is
tr
atio
n
is
t
h
at
P
SF
ca
n
b
e
co
m
p
u
ted
o
n
ce
an
d
u
s
ed
f
o
r
all
f
u
r
th
er
s
i
m
ilar
it
y
m
ea
s
u
r
e
m
e
n
t
s
.
Fo
r
in
s
ta
n
ce
,
let
'
s
s
u
p
p
o
s
e
in
itiall
y
th
at
i
m
ag
e
s
A
an
d
B
ar
e
n
o
t
p
er
f
ec
tl
y
ali
g
n
ed
a
s
s
h
o
w
n
i
n
Fig
u
r
e
2
.
T
o
s
tar
t
t
h
e
r
eg
i
s
tr
atio
n
p
r
o
ce
s
s
u
s
i
n
g
p
o
in
t
s
i
m
ilar
it
y
m
ea
s
u
r
es,
w
e
n
ee
d
f
ir
s
t
to
co
m
p
u
te
t
h
e
j
o
in
t
h
is
to
g
r
a
m
T
ab
le
2
(
a)
th
en
P
SF
T
a
b
le
3
(
b
)
.
T
h
e
in
i
tial
s
i
m
ilar
it
y
b
et
w
ee
n
i
m
a
g
es
u
s
in
g
P
SM
is
th
e
s
a
m
e
as
it
w
as
co
m
p
u
ted
p
r
ev
io
u
s
l
y
a
n
d
eq
u
a
ls
to
0
.
1
2
8
5
6
.
Su
p
p
o
s
e
n
o
w
th
at
th
e
r
eg
i
s
tr
atio
n
p
r
o
ce
s
s
h
as
led
to
a
tr
a
n
s
f
o
r
m
atio
n
T
th
at
tr
an
s
f
o
r
m
ed
i
m
ag
e
B
i
n
Fig
u
r
e
2
to
i
m
a
g
e
B
i
n
Fig
u
r
e
1
.
T
o
co
m
p
u
te
t
h
e
s
i
m
ilar
it
y
u
s
i
n
g
p
o
in
t
s
i
m
ilar
it
y
m
ea
s
u
r
e,
w
e
j
u
s
t
n
ee
d
to
co
m
p
u
te
t
h
e
n
e
w
j
o
in
t
h
is
to
g
r
a
m
b
et
w
ee
n
t
h
e
i
m
a
g
e
A
i
n
Fig
u
r
e
2
an
d
i
m
a
g
e
B
in
Fig
u
r
e
1
an
d
u
s
e
t
h
e
alr
ea
d
y
c
o
m
p
u
ted
P
SF
T
ab
le
4
(
b
)
.
T
h
e
jo
in
t
h
is
to
g
r
a
m
w
a
s
ca
lc
u
lated
an
d
p
r
esen
ted
in
T
ab
le
1
(
a
)
.
No
w
,
u
s
i
n
g
(
4
)
,
th
e
g
lo
b
al
s
i
m
ilar
it
y
b
et
w
ee
n
i
m
a
g
e
A
an
d
i
m
a
g
e
T
(
B
)
ca
n
th
e
n
b
e
co
m
p
u
ted
a
s
:
MI
=
[
N(
i
1A
,
i
1B
)
×
f
MI
(i
1A
,
i
1B
)+
N(
i
1A
,
i
2B
)
×f
MI
(i
1A
,
i
2B
)
+
N(
i
2A
,
i
1B
)
×
f
MI
(i
2A
,
i
1B
)
+
N(
i
2A
,
i
2B
)
×
f
MI
(i
2A
,
i
2B
)
]
/3
6
=
(
3
0
×0
.
1
1
3
+
0
×
-
1
.
02
+0
×
-
1
.
0
2
+
6
×1
.
3
8
6
)
/3
6
=
0
.
3
2
5
1
.
W
e
ca
n
s
ee
clea
r
l
y
t
h
at
t
h
e
n
e
w
v
al
u
e
o
f
p
o
in
t
s
i
m
ilar
it
y
m
ea
s
u
r
e
is
h
i
g
h
er
th
a
n
t
h
e
i
n
itial
v
a
lu
e
m
ea
s
u
r
ed
b
ef
o
r
e
s
tar
tin
g
r
e
g
i
s
tr
atio
n
.
T
h
is
r
ef
lect
s
a
r
ea
l
s
itu
atio
n
s
i
n
ce
th
e
o
b
tain
ed
tr
an
s
f
o
r
m
ed
i
m
a
g
e
is
p
er
f
ec
tl
y
ali
g
n
ed
w
it
h
t
h
e
r
ef
er
en
ce
i
m
a
g
e
w
h
ic
h
m
ea
n
s
a
h
ig
h
er
s
i
m
ilar
it
y
v
a
lu
e
i
s
ex
p
ec
ted
.
On
th
e
o
th
er
h
an
d
,
i
f
t
h
e
tr
a
n
s
f
o
r
m
atio
n
led
to
a
m
o
r
e
i
m
ag
e
m
is
ali
g
n
m
e
n
t
as
s
h
o
w
n
i
n
Fi
g
u
r
e
3
.
T
h
is
w
il
l
b
e
r
ef
lecte
d
b
y
th
e
v
alu
e
o
f
t
h
e
g
lo
b
al
s
i
m
ilar
it
y
MI
.
I
n
Fi
g
u
r
e
3
,
th
er
e
i
s
t
w
o
-
th
ir
d
s
m
is
ali
g
n
m
e
n
t
w
ith
t
h
e
r
ef
er
e
n
ce
i
m
ag
e
A
a
n
d
th
e
j
o
in
t
h
is
to
g
r
a
m
co
r
r
esp
o
n
d
in
g
to
t
h
is
s
it
u
atio
n
is
s
h
o
w
n
i
n
T
ab
le
5
.
T
h
e
g
l
o
b
al
s
i
m
ilar
it
y
MI
b
et
w
ee
n
i
m
a
g
e
A
an
d
i
m
a
g
e
T
(
B
)
ca
n
th
e
n
b
e
co
m
p
u
ted
a
s
:
MI
=
[
N(
i
1A
,
i
1B
)
×
f
MI
(i
1A
,
i
1B
)+
N(
i
1A
,
i
2B
)
×
f
MI
(i
1A
,
i
2B
)+
N(
i
2A
,
i
1B
)
×
f
MI
(i
2A
,
i
1B
)+
N(
i
2A
,
i
2B
)
×
f
MI
(i
2A
,
i
2B
)
]
/3
6
=
(
2
6
×
0
.
1
1
3
+4
×
-
1
.
0
2
+
4
×
-
1
.
0
2
+
2
×
1
.
3
8
6
)
/3
6
=
-
0
.
0
6
8
.
T
h
e
o
b
tain
ed
MI
v
alu
e
i
s
lo
wer
th
an
t
h
e
in
itial
s
i
m
i
lar
it
y
v
alu
e
(
0
.
1
2
8
5
6
)
co
m
p
u
ted
at
t
h
e
b
eg
i
n
n
i
n
g
o
f
t
h
e
r
eg
is
tr
atio
n
p
r
o
ce
s
s
an
d
th
i
s
c
o
n
f
ir
m
s
t
h
e
m
is
ali
g
n
m
en
t.
Fig
u
r
e
3
.
I
m
a
g
e
m
is
al
ig
n
ed
d
u
e
to
b
ad
r
eg
is
tr
atio
n
T
ab
le
3
.
C
o
m
p
u
t
in
g
P
SF
(
a)
f
o
r
co
r
r
ec
tly
,
(
b
)
f
o
r
n
o
t
co
r
r
ec
tl
y
ali
g
n
ed
i
m
ag
e
s
i
1A
i
2A
i
2B
-
1
.
7
1
4
1
.
8
4
i
1B
0
.
1
0
9
-
1
.
7
1
4
(
a)
i
1A
i
2A
i
2B
-
1
.
0
2
1
.
3
8
6
i
1B
0
.
1
1
3
-
1
.
0
2
(
b
)
T
a
b
le 4
.
Co
m
p
u
ti
n
g
P
S
F
(
a
)
J
o
in
t
h
isto
g
ra
m
a
n
d
(
b
)
j
o
i
n
t
d
istri
b
u
ti
o
n
f
o
r
p
e
rf
e
c
tl
y
a
li
g
n
e
d
im
a
g
e
s u
p
d
a
ted
t
o
a
v
o
i
d
c
o
m
p
u
tatio
n
e
rr
o
rs
i
1A
i
2A
i
2B
1
7
i
1B
31
1
(
a)
i
1A
i
2A
i
2B
0
.
0
2
5
0
.
1
7
5
i
1B
0
.
7
7
5
0
.
0
2
5
(
b
)
T
ab
le
5
.
J
o
in
t h
is
to
g
r
a
m
f
o
r
a
o
n
e
-
t
h
ir
d
alig
n
ed
i
m
a
g
e
s
i
1A
i
2A
i
2B
4
2
i
1B
26
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:
2
0
8
8
-
8708
C
o
mp
a
r
is
o
n
o
f m
u
tu
a
l in
fo
r
m
a
tio
n
a
n
d
its
p
o
in
t simil
a
r
ity
imp
leme
n
ta
tio
n
…
(
W
a
s
s
im
E
l
Ha
jj C
h
eh
a
d
e
)
2617
3.
T
E
ST
I
N
G
O
N
M
E
DICAL
I
M
AG
E
S
T
o
ev
alu
ate
p
o
in
t
s
i
m
ilar
it
y
m
ea
s
u
r
es,
a
co
m
p
ar
ati
v
e
s
tu
d
y
w
a
s
p
er
f
o
r
m
ed
b
et
w
ee
n
th
e
w
id
el
y
u
s
ed
s
i
m
ilar
it
y
m
ea
s
u
r
e
m
u
tu
a
l
in
f
o
r
m
at
io
n
(
MI
)
an
d
p
o
in
t
s
i
m
i
lar
it
y
m
ea
s
u
r
e
(
P
SM)
.
T
h
e
C
T
an
d
MRI
tr
ain
in
g
d
ataset
in
Van
d
er
b
ilt
d
atab
ase
f
r
o
m
th
e
r
etr
o
s
p
ec
ti
v
e
i
m
a
g
e
r
eg
is
tr
atio
n
ev
a
lu
at
io
n
(
R
I
R
E
)
P
r
o
j
ec
t
w
er
e
u
s
ed
[
2
3
]
.
T
h
is
tr
ain
i
n
g
d
atase
t
h
as
f
iv
e
i
m
ag
e
s
s
u
c
h
a
s
C
T
(
5
1
2
×
5
1
2
×
2
9
)
,
MR
-
T
1
(
2
5
6
×2
5
6
×2
5
)
,
MR
-
T
2
(
2
5
6
×
2
5
6
×
2
5
)
,
MR
-
P
D
(
2
5
6
×
2
5
6
×2
5
)
an
d
P
E
T
(
1
2
8
×1
2
8
×
1
5
)
.
T
h
e
ad
v
an
tag
e
o
f
u
s
i
n
g
R
I
R
E
tr
ain
i
n
g
d
atase
t
in
th
e
s
e
ex
p
er
i
m
en
ts
i
s
th
a
t
th
e
co
r
r
ec
t
tr
an
s
f
o
r
m
at
io
n
T
th
at
allo
w
s
p
er
f
ec
t
i
m
a
g
e
ali
g
n
m
e
n
t
is
k
n
o
w
n
.
T
h
er
ef
o
r
e,
w
h
e
n
ali
g
n
i
n
g
a
m
o
v
i
n
g
i
m
a
g
e
B
to
a
r
ef
er
e
n
ce
i
m
a
g
e
A
b
y
ap
p
ly
in
g
th
e
g
i
v
en
tr
an
s
f
o
r
m
a
tio
n
an
d
t
h
en
m
ea
s
u
r
i
n
g
t
h
e
s
i
m
ilar
it
y
b
et
w
e
en
T
(
B
)
an
d
A
,
w
e
s
h
o
u
ld
ex
p
ec
t
to
h
av
e
t
h
e
h
ig
h
est
v
a
lu
e
o
f
s
i
m
ilar
it
y
b
ased
o
n
MI
o
r
P
SM.
Mo
r
eo
v
er
,
if
we
alter
a
tr
an
s
latio
n
p
ar
am
eter
(
d
)
o
f
t
h
e
r
i
g
id
tr
a
n
s
f
o
r
m
atio
n
T
b
y
a
s
m
all
v
al
u
e
+/
-
d
i
n
p
o
s
iti
v
e
o
r
n
e
g
ati
v
e
d
ir
ec
tio
n
s
,
a
n
d
w
e
r
ec
o
m
p
u
te
s
i
m
ilar
it
y
w
e
s
h
o
u
ld
ex
p
ec
t
to
h
av
e
lo
w
er
s
i
m
il
ar
it
y
v
al
u
es
t
h
a
n
th
o
s
e
o
b
tai
n
ed
u
s
in
g
T
.
I
n
th
is
ex
p
er
i
m
e
n
t,
w
e
ar
e
g
o
i
n
g
to
t
est
t
h
is
h
y
p
o
th
e
s
is
to
ch
ec
k
i
t
s
co
r
r
ec
tn
es
s
a
n
d
if
p
r
o
v
ed
it
s
h
o
w
s
o
p
ti
m
ali
t
y
o
f
th
e
s
i
m
ilar
it
y
m
ea
s
u
r
es.
I
n
t
h
e
f
ir
s
t
e
x
p
er
i
m
e
n
t,
w
e
u
s
ed
MI
as
a
s
i
m
ilar
it
y
m
ea
s
u
r
e
to
d
eter
m
i
n
e
t
h
e
tr
an
s
latio
n
d
is
tan
ce
d
f
r
o
m
T
w
h
er
e
MI
r
ea
ch
es
its
h
ig
h
e
s
t
v
al
u
e.
W
e
h
av
e
co
m
p
u
ted
th
i
s
tr
an
s
la
tio
n
o
n
1
2
i
m
ag
e
m
o
d
alit
y
p
air
s
ea
ch
i
n
all
t
h
r
ee
s
p
atial
-
d
ir
ec
ti
o
n
s
.
Fo
r
ea
c
h
i
m
a
g
e
p
air
,
w
e
s
tar
ted
b
y
alter
i
n
g
th
e
co
r
r
ec
t tr
an
s
f
o
r
m
atio
n
T
b
y
tr
an
s
lati
n
g
th
e
i
m
ag
e
i
n
o
n
e
d
ir
ec
tio
n
o
f
th
e
th
r
ee
-
d
i
m
e
n
s
i
o
n
al
s
p
ac
e
b
y
a
s
m
a
ll
s
tep
v
alu
e
0
.
0
1
m
m
a
n
d
w
it
h
i
n
a
p
r
ed
ef
in
ed
r
a
n
g
e
(
i.e
.
-
5
to
5
m
m
)
.
T
h
en
f
o
r
ea
ch
tr
an
s
lat
io
n
d
,
t
h
e
s
i
m
ilar
it
y
is
c
o
m
p
u
ted
u
s
i
n
g
MI
.
T
h
e
tr
an
s
latio
n
t
h
at
g
iv
e
s
t
h
e
h
i
g
h
est
s
i
m
ilar
it
y
v
al
u
e
is
th
en
r
ec
o
r
d
ed
.
Fig
u
r
e
4
s
h
o
w
s
a
g
r
ap
h
o
f
th
e
MI
-
b
ased
s
i
m
ilar
it
y
v
alu
e
s
co
m
p
u
ted
u
s
i
n
g
tr
an
s
latio
n
s
r
a
n
g
i
n
g
ar
o
u
n
d
th
e
co
r
r
ec
t
i
m
a
g
e
alig
n
m
en
t
f
o
r
o
n
e
i
m
a
g
e
p
air
(
T
1
-
C
T
)
.
I
n
th
is
F
ig
u
r
e,
w
e
ca
n
s
ee
h
o
w
t
h
e
v
al
u
e
o
f
MI
in
cr
ea
s
e
s
f
r
o
m
a
m
i
n
i
m
u
m
v
a
lu
e
at
T
-
5
m
m
to
r
ea
ch
a
m
ax
i
m
u
m
v
al
u
e
th
e
n
it
d
ec
r
ea
s
es
a
g
ai
n
.
An
i
m
p
o
r
tan
t
t
h
in
g
to
n
o
tice
o
n
t
h
e
g
r
ap
h
i
s
th
at
t
h
e
m
ax
i
m
u
m
s
i
m
i
lar
it
y
v
al
u
e
is
n
o
t
o
b
tain
ed
at
th
e
co
r
r
ec
t
i
m
ag
e
ali
g
n
m
e
n
t
(
T
)
b
u
t
n
ea
r
to
it
(
at
T
+0
.
4
1
m
m
)
.
W
e
p
er
f
o
r
m
ed
th
e
n
th
e
s
a
m
e
ex
p
er
i
m
e
n
t
o
n
all
i
m
ag
e
p
air
s
.
T
a
b
le
6
,
co
lu
m
n
MI
,
s
h
o
w
s
th
e
tr
an
s
latio
n
s
(
d
)
th
at
g
av
e
t
h
e
h
ig
h
es
t
s
i
m
ilar
i
t
y
v
a
lu
e
s
f
o
r
all
i
m
ag
e
p
air
s
.
A
ll
t
h
e
s
e
tr
an
s
latio
n
s
r
an
g
e
ar
o
u
n
d
th
e
co
r
r
ec
t
i
m
a
g
e
alig
n
m
en
t
ex
ce
p
t
in
o
n
e
ca
s
e
(
T
2
-
C
T
r
ec
tif
ied
)
.
T
h
is
m
ea
n
s
th
at
t
h
e
p
r
esu
m
p
tio
n
s
tati
n
g
t
h
at
al
w
a
y
s
th
e
b
est
m
a
tch
i
s
w
h
er
e
MI
h
as
its
h
i
g
h
e
s
t
v
al
u
e
i
s
n
o
t
ac
cu
r
ate
an
d
lead
s
to
s
o
m
e
r
eg
is
tr
atio
n
er
r
o
r
.
T
h
er
ef
o
r
e,
th
er
e
is
a
n
ee
d
to
f
i
n
d
r
ea
s
o
n
s
f
o
r
th
is
er
r
o
r
an
d
m
eth
o
d
s
to
r
ed
u
ce
it.
Fig
u
r
e
4
.
MI
s
i
m
ilar
it
y
v
a
lu
e
s
co
m
p
u
ted
w
it
h
in
t
h
e
r
an
g
e
T
+/
-
d
.
T
h
e
h
ig
h
est
s
i
m
ilar
it
y
v
al
u
e
n
o
t lo
ca
ted
at
th
e
co
r
r
ec
t a
lig
n
m
e
n
t T
I
n
th
e
s
ec
o
n
d
ex
p
er
i
m
en
t,
w
e
u
s
ed
P
SM
b
ased
o
n
MI
as
a
s
i
m
ilar
it
y
m
ea
s
u
r
e.
As
w
e
m
en
tio
n
ed
i
n
s
ec
tio
n
2
,
P
SM
s
tar
ts
f
ir
s
t
b
y
co
m
p
u
ti
n
g
P
SF
at
th
e
b
eg
i
n
n
i
n
g
o
f
t
h
e
r
eg
is
tr
atio
n
p
r
o
ce
s
s
an
d
th
en
u
s
ed
in
all
th
e
u
p
co
m
i
n
g
tr
an
s
latio
n
s
.
I
n
th
i
s
ex
p
er
i
m
e
n
t,
w
e
test
e
d
P
SM
w
it
h
P
SF
s
co
m
p
u
te
d
at
n
in
e
d
if
f
er
en
t
tr
an
s
latio
n
s
(
i.e
.
0
,
+/
-
1
,
+/
-
2
m
m
,
+/
-
5
m
m
a
n
d
+/
-
1
0
m
m
)
.
Fo
r
ea
ch
P
SF
,
w
e
co
m
p
u
ted
t
h
e
s
i
m
ilar
i
t
y
v
al
u
es
w
it
h
r
esp
ec
t
to
tr
a
n
s
lat
io
n
s
a
n
d
f
o
u
n
d
t
h
e
tr
a
n
s
latio
n
w
h
er
e
s
i
m
ilar
it
y
h
a
s
its
h
i
g
h
est
v
al
u
e
as
w
e
d
id
i
n
t
h
e
f
ir
s
t
e
x
p
er
i
m
en
t.
W
e
h
a
v
e
t
ested
P
SM
o
n
t
h
e
s
a
m
e
1
2
i
m
a
g
e
m
o
d
alit
y
p
air
s
ea
ch
i
n
all
th
r
ee
s
p
atial
-
d
ir
ec
tio
n
s
.
T
h
e
id
ea
is
t
o
co
m
p
ar
e
th
e
tr
an
s
latio
n
s
o
b
tain
ed
u
s
i
n
g
P
SM
w
i
th
t
h
o
s
e
o
b
tain
e
d
u
s
in
g
MI
.
T
ab
le
6
s
h
o
w
s
also
t
h
e
tr
an
s
latio
n
wh
er
e
th
e
s
i
m
ilar
it
y
r
ea
ch
e
s
it
s
m
a
x
i
m
u
m
u
s
i
n
g
P
SM
co
m
p
u
ted
b
ased
o
n
n
in
e
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.
11
,
No
.
3
,
J
u
n
e
2
0
2
1
:
2
6
1
3
-
2620
2618
d
if
f
er
e
n
t
P
SF
s
.
T
h
e
b
o
ld
v
al
u
es
in
t
h
e
tab
le
r
ep
r
ese
n
t
P
S
M
p
er
f
o
r
m
i
n
g
b
etter
t
h
an
MI
an
d
t
h
e
u
n
d
er
lin
ed
v
alu
e
s
r
ep
r
esen
t t
h
e
s
m
alle
s
t t
r
an
s
latio
n
s
.
I
t
is
clea
r
f
ir
s
t
t
h
at
th
e
h
ig
h
e
s
t
v
alu
e
o
f
s
i
m
ilar
i
t
y
u
s
i
n
g
P
SM
is
n
o
t
al
w
a
y
s
o
b
tain
ed
at
th
e
co
r
r
ec
t
m
atc
h
(
i.e
.
,
d
=
0
)
.
An
o
th
er
i
n
t
er
esti
n
g
o
b
s
er
v
at
io
n
i
s
t
h
at
P
SM
b
ased
o
n
MI
,
w
h
e
n
P
SF
i
s
o
b
tain
ed
f
r
o
m
t
h
e
co
r
r
ec
t
im
a
g
e
alig
n
m
e
n
t,
is
al
w
a
y
s
at
lea
s
t
th
e
s
a
m
e
o
r
b
etter
th
an
MI
.
Mo
r
eo
v
er
,
th
e
b
est
r
esu
lt
s
(
u
n
d
er
li
n
ed
v
alu
e
s
)
ar
e
o
b
tain
ed
w
h
en
P
S
F is
co
m
p
u
ted
s
o
m
e
w
h
er
e
in
t
h
e
v
ici
n
it
y
o
f
t
h
e
co
r
r
ec
t i
m
a
g
e
alig
n
m
e
n
t.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
r
esu
lts
o
f
t
h
e
ex
p
er
i
m
e
n
t
s
p
r
o
v
e
clea
r
l
y
t
h
at
t
h
e
m
i
n
i
m
u
m
ali
g
n
m
e
n
t
er
r
o
r
is
n
o
t
al
wa
y
s
w
h
er
e
th
e
s
i
m
ilar
it
y
v
al
u
e
i
s
m
a
x
i
m
al.
T
h
e
r
esu
lts
s
h
o
w
al
s
o
t
h
at
P
SM
p
er
f
o
r
m
s
b
etter
t
h
a
n
s
t
an
d
ar
d
MI
in
s
o
m
e
ca
s
es
w
h
e
n
e
v
er
th
e
P
SF
is
co
m
p
u
ted
at
th
e
co
r
r
ec
t
im
ag
e
alig
n
m
en
t.
Mo
r
eo
v
er
,
w
e
ca
n
an
al
y
ze
th
e
p
er
f
o
r
m
a
n
ce
o
f
s
i
m
ilar
it
y
m
e
asu
r
e
w
it
h
r
esp
ec
t
to
m
is
al
ig
n
m
en
t
at
w
h
ich
P
SF
is
co
m
p
u
t
ed
,
an
d
w
e
ca
n
s
ee
th
at
t
h
e
b
est
r
esu
l
t
is
al
w
a
y
s
w
h
e
n
P
SF
is
co
m
p
u
ted
n
ea
r
to
th
e
p
er
f
ec
t
alig
n
m
en
t
(
s
ee
u
n
d
er
lin
ed
v
al
u
es
i
n
T
ab
le
6
)
.
Fo
r
in
s
tan
ce
,
th
e
r
e
g
is
tr
atio
n
ca
s
e
T
1
-
C
T
in
d
ir
ec
ti
o
n
x
h
as
t
h
e
m
in
i
m
u
m
ali
g
n
m
en
t
er
r
o
r
o
b
tain
ed
u
s
i
n
g
a
P
SF
co
m
p
u
ted
at
-
1
m
m
.
Si
m
ilar
l
y
,
t
h
e
r
eg
i
s
tr
atio
n
ca
s
e
T
2
-
C
T
in
d
ir
ec
tio
n
1
h
as
t
h
e
m
i
n
i
m
u
m
alig
n
m
e
n
t
er
r
o
r
o
b
tain
ed
u
s
in
g
a
P
S
F
co
m
p
u
ted
at
p
er
f
ec
t
alig
n
m
e
n
t
0
m
m
.
T
h
is
s
u
g
g
ests
th
at
w
e
s
h
o
u
ld
al
w
a
y
s
co
m
p
u
te
P
SF
clo
s
e
t
o
th
e
co
r
r
ec
t
i
m
a
g
e
ali
g
n
m
e
n
t.
B
u
t
u
n
f
o
r
t
u
n
a
tel
y
,
to
r
e
g
i
s
ter
th
e
i
m
a
g
es,
th
e
co
r
r
ec
t
im
a
g
e
alig
n
m
en
t
i
s
n
o
t
k
n
o
w
n
.
Ho
w
e
v
er
,
if
w
e
co
m
p
u
te
P
SF
at
h
ig
h
l
y
m
is
a
lig
n
ed
i
m
ag
e
s
(
s
ee
+/
-
10
m
m
i
n
T
ab
le
6
)
,
w
e
s
till
g
et
t
h
e
m
ax
i
m
u
m
clo
s
e
to
t
h
e
co
r
r
ec
t
i
m
a
g
e
ali
g
n
m
en
t.
T
h
er
ef
o
r
e,
if
w
e
r
e
g
is
ter
ed
th
e
i
m
ag
e
u
s
i
n
g
P
SF
at
m
is
al
i
g
n
ed
i
m
ag
e
s
to
g
et
an
ap
p
r
o
x
i
m
atel
y
r
eg
i
s
ter
ed
i
m
ag
e,
t
h
e
n
w
e
r
ec
o
m
p
u
te
P
SF
b
ased
o
n
t
h
e
n
e
w
l
y
r
eg
i
s
ter
e
d
i
m
a
g
e
a
n
d
r
estar
t
t
h
e
r
e
g
is
tr
atio
n
,
w
e
ca
n
e
x
p
ec
t
r
eg
i
s
tr
atio
n
i
m
p
r
o
v
e
m
e
n
t
co
m
p
ar
ed
to
u
s
i
n
g
s
ta
n
d
ar
d
MI
.
Mo
r
eo
v
er
,
m
ac
h
i
n
e
-
lear
n
in
g
tec
h
n
iq
u
e
s
co
u
ld
b
e
u
s
ed
to
p
r
ed
ict
th
e
b
est
P
SF
f
o
r
h
ig
h
q
u
a
lit
y
i
m
a
g
e
m
atc
h
s
i
m
i
lar
l
y
to
th
e
w
a
y
t
h
e
y
h
a
v
e
b
ee
n
u
s
ed
f
o
r
d
etec
tin
g
a
n
o
m
alie
s
a
n
d
d
is
ea
s
es
f
r
o
m
m
ed
ical
i
m
a
g
es
[
2
4
-
26]
.
T
ab
le
6
.
Dis
p
lace
m
e
n
t o
f
t
h
e
m
ax
i
m
a
f
r
o
m
t
h
e
co
r
r
ec
t i
m
a
g
e
alig
n
m
e
n
t
f
o
r
P
SM
R
e
f
-
mo
v
i
mag
e
D
i
r
e
c
t
i
o
n
MI
P
S
M
[
P
S
F
-
D]
-
10
-
5
-
2
-
1
0
1
2
5
10
T1
-
CT
X
0
.
4
1
0
.
5
6
0
.
5
2
0
.
4
3
0
.
3
5
0
.
3
6
0
.
4
9
0
.
5
1
0
.
5
5
0
.
5
8
T1
-
CT
Y
-
0
.
5
2
-
0
.
9
2
-
0
.
9
5
-
0
.
9
6
-
0
.
7
3
-
0
.
3
4
-
0
.
0
2
-
0
.
0
4
-
0
.
2
7
-
0
.
4
9
T1
-
CT
Z
-
0
.
1
2
-
1
.
5
7
-
1
.
3
2
-
0
.
6
8
-
0
.
4
3
-
0
.
1
2
0
.
2
0
0
.
5
4
1
.
6
6
1
.
3
3
T2
-
CT
x
0
.
5
5
0
.
6
1
0
.
5
8
0
.
5
5
0
.
4
9
0
.
4
9
0
.
6
2
0
.
6
4
0
.
6
3
0
.
6
6
T2
-
CT
Y
0
.
1
1
-
0
.
3
2
-
0
.
3
0
-
0
.
2
3
-
0
.
2
4
0
.
0
6
0
.
3
9
0
.
4
3
0
.
4
1
0
.
0
4
T2
-
CT
Z
0
.
7
0
-
1
.
6
8
-
0
.
2
3
0
.
1
6
0
.
3
6
0
.
5
2
0
.
7
0
0
.
8
6
1
.
1
4
1
.
1
4
PD
-
CT
X
0
.
3
5
0
.
4
3
0
.
3
8
0
.
3
2
0
.
2
6
0
.
3
0
0
.
4
2
0
.
4
2
0
.
4
4
0
.
4
7
PD
-
CT
Y
-
0
.
2
6
-
0
.
5
3
-
0
.
6
8
-
0
.
6
8
-
0
.
5
3
-
0
.
1
9
0
.
0
8
0
.
1
3
0
.
4
2
0
.
3
4
PD
-
CT
Z
0
.
8
7
-
1
.
1
4
-
0
.
7
6
-
0
.
2
0
0
.
2
0
0
.
5
6
0
.
8
5
1
.
1
1
1
.
6
9
1
.
8
8
T1
-
r
e
c
t
i
f
i
e
d
-
CT
X
-
0
.
1
6
-
0
.
0
3
-
0
.
1
1
-
0
.
1
8
-
0
.
2
3
-
0
.
1
4
-
0
.
0
6
-
0
.
1
0
-
0
.
0
6
0
.
0
0
T1
-
r
e
c
t
i
f
i
e
d
-
CT
Y
-
0
.
6
3
-
0
.
8
3
-
0
.
8
2
-
0
.
7
9
-
0
.
7
0
-
0
.
5
0
-
0
.
4
2
-
0
.
4
7
-
0
.
4
7
-
0
.
5
3
T1
-
r
e
c
t
i
f
i
e
d
-
CT
Z
0
.
9
6
-
0
.
7
2
-
0
.
5
3
-
0
.
1
2
0
.
2
1
0
.
5
7
0
.
9
3
1
.
2
5
1
.
8
4
1
.
9
9
T2
-
r
e
c
t
i
f
i
e
d
-
CT
X
0
.
0
0
0
.
0
5
0
.
0
3
-
0
.
0
6
-
0
.
1
0
0
.
0
0
0
.
0
9
0
.
0
7
0
.
0
7
0
.
1
2
T2
-
r
e
c
t
i
f
i
e
d
-
CT
Y
-
0
.
1
8
-
0
.
8
8
-
0
.
6
7
-
0
.
4
2
-
0
.
3
5
-
0
.
1
4
-
0
.
0
3
-
0
.
1
0
-
0
.
2
1
-
0
.
4
4
T2
-
r
e
c
t
i
f
i
e
d
-
CT
Z
1
.
1
5
-
1
.
6
8
-
0
.
5
3
0
.
1
6
0
.
5
5
0
.
8
8
1
.
1
1
1
.
2
7
1
.
5
2
1
.
5
3
P
D
-
r
e
c
t
i
f
i
e
d
-
CT
X
0
.
0
7
0
.
1
8
0
.
1
4
0
.
0
6
0
.
0
1
0
.
0
7
0
.
1
5
0
.
1
3
0
.
1
6
0
.
1
9
P
D
-
r
e
c
t
i
f
i
e
d
-
CT
Y
-
0
.
2
0
0
.
1
8
-
0
.
4
4
-
0
.
3
7
-
0
.
3
5
-
0
.
1
6
0
.
0
1
-
0
.
0
1
-
0
.
0
5
-
0
.
2
6
P
D
-
r
e
c
t
i
f
i
e
d
-
CT
Z
0
.
3
3
-
0
.
5
7
-
0
.
5
8
-
0
.
2
6
-
0
.
1
1
0
.
1
8
0
.
5
0
0
.
8
1
1
.
6
3
1
.
9
0
T1
-
P
ET
X
0
.
7
0
0
.
5
0
-
4.
8
3
-
1
.
89
-
0
.
9
1
0
.
0
3
0
.
9
6
1
.
9
1
4
.
7
7
0
.
7
0
T1
-
P
ET
Y
1
.
9
5
0
.
3
8
-
4
.
8
7
-
1
.
8
9
-
0
.
9
1
0
.
0
7
1
.
0
0
1
.
9
9
4
.
8
8
1
.
8
2
T1
-
P
ET
Z
-
3
.
17
-
9
.
1
8
-
4
.
0
5
-
2
.
3
1
-
1
.
4
8
-
0
.
3
3
0
.
7
1
1
.
5
6
4
.
4
3
9
.
0
6
T2
-
P
ET
X
0
.
9
5
0
.
9
2
0
.
8
4
-
1
.
8
2
-
0
.
8
7
0
.
0
8
0
.
9
8
1
.
9
3
4
.
7
6
0
.
8
5
T2
-
P
ET
Y
0
.
8
7
0
.
8
6
-
4
.
8
6
-
1
.
8
8
-
0
.
9
1
0
.
0
6
1
.
0
0
1
.
9
7
4
.
8
6
1
.
1
4
T2
-
P
ET
Z
-
2
.
1
3
-
2
.
7
0
-
4
.
0
5
-
1
.
9
9
-
1
.
3
9
-
0
.
7
2
0
.
2
8
1
.
6
8
3
.
9
2
-
1
.
4
8
PD
-
P
ET
X
0
.
6
1
0
.
0
9
-
4
.
82
-
1
.
8
8
-
0
.
9
1
0
.
0
2
0
.
9
6
1
.
9
0
4
.
7
7
0
.
1
6
PD
-
P
ET
Y
1
.
5
9
1
.
4
9
-
4
.
8
5
-
1
.
8
7
-
0
.
9
0
0
.
0
4
1
.
0
1
2
.
0
1
4
.
8
9
2
.
3
5
PD
-
P
ET
Z
-
1
.
7
5
-
1
.
9
8
-
3
.
5
6
-
1
.
8
6
-
1
.
3
3
-
0
.
7
2
0
.
0
6
0
.
6
9
4
.
9
8
-
0
.
9
8
T1
-
r
e
c
t
i
f
i
e
d
-
P
ET
X
-
0
.
1
2
-
0
.
1
3
-
4
.
8
4
-
1
.
8
9
-
0
.
9
4
-
0
.
0
2
0
.
9
4
1
.
8
7
4
.
7
9
0
.
0
9
T1
-
r
e
c
t
i
f
i
e
d
-
P
ET
Y
0
.
4
9
0
.
7
4
-
4
.
8
5
-
1
.
9
1
-
0
.
92
0
.
0
7
1
.
0
0
1
.
9
8
4
.
8
8
2
.
2
7
T1
-
r
e
c
t
i
f
i
e
d
-
P
ET
Z
-
2
.
3
1
-
9
.
5
2
-
3
.
7
6
-
2
.
0
9
-
1
.
4
4
-
0
.
6
9
0
.
1
4
1
.
5
8
4
.
6
9
7
.
9
6
T2
-
r
e
c
t
i
f
i
e
d
-
P
ET
X
0
.
1
9
0
.
0
3
0
.
1
2
-
1
.
8
5
-
0
.
9
0
0
.
0
1
0
.
9
3
1
.
8
7
0
.
2
8
0
.
2
7
T2
-
r
e
c
t
i
f
i
e
d
-
P
ET
Y
0
.
6
9
1
.
2
3
-
4
.
8
4
-
1
.
8
8
-
0
.
9
1
0
.
0
6
1
.
0
1
1
.
9
6
4
.
8
2
1
.
7
2
T2
-
r
e
c
t
i
f
i
e
d
-
P
ET
Z
-
2
.
3
1
-
8
.
4
2
-
4
.
3
3
-
2
.
0
6
-
1
.
1
9
-
0
.
3
6
0
.
4
8
1
.
2
5
3
.
6
1
-
1
.
8
6
P
ED
-
r
e
c
t
i
f
i
e
d
-
P
ET
X
0
.
7
9
0
.
3
2
-
4
.
8
4
-
1
.
9
0
-
0
.
9
5
0
.
0
2
0
.
9
7
1
.
8
9
4
.
8
2
0
.
5
7
P
ED
-
r
e
c
t
i
f
i
e
d
-
P
ET
Y
1
.
8
5
1
.
2
9
-
4
.
86
-
1
.
9
0
-
0
.
9
1
0
.
0
5
1
.
0
3
1
.
9
8
4
.
8
8
1
.
9
0
P
ED
-
r
e
c
t
i
f
i
e
d
-
P
ET
Z
-
1
.
1
2
-
8
.
5
8
-
3
.
9
2
-
1
.
6
3
-
0
.
9
6
-
0
.
3
2
0
.
3
1
1
.
0
3
4
.
0
6
-
0
.
1
3
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:
2
0
8
8
-
8708
C
o
mp
a
r
is
o
n
o
f m
u
tu
a
l in
fo
r
m
a
tio
n
a
n
d
its
p
o
in
t simil
a
r
ity
imp
leme
n
ta
tio
n
…
(
W
a
s
s
im
E
l
Ha
jj C
h
eh
a
d
e
)
2619
5.
CO
NCLU
SI
O
N
I
n
t
h
is
p
ap
er
,
w
e
d
e
m
o
n
s
tr
at
ed
th
at
t
h
e
tr
ad
itio
n
al
r
e
g
is
tr
atio
n
p
r
o
ce
s
s
a
s
s
u
m
in
g
th
at
w
h
e
n
ev
er
a
s
i
m
ilar
it
y
m
ea
s
u
r
e
r
ea
ch
e
s
it
s
h
ig
h
e
s
t
v
a
lu
e,
t
h
is
co
r
r
esp
o
n
d
s
to
th
e
b
est
m
atc
h
is
n
o
t
al
wa
y
s
v
alid
.
T
h
is
w
as
d
o
n
e
b
y
a
n
al
y
zin
g
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
w
o
s
i
m
i
la
r
it
y
m
ea
s
u
r
es,
t
h
e
p
o
p
u
lar
an
d
w
id
el
y
u
s
ed
Mu
t
u
al
I
n
f
o
r
m
a
tio
n
an
d
o
u
r
p
r
o
p
o
s
ed
p
o
in
t
s
i
m
ilar
it
y
m
ea
s
u
r
e.
No
n
e
o
f
MI
an
d
P
SM
h
as
th
eir
h
ig
h
e
s
t
v
a
lu
e
s
at
th
e
b
est
m
atch
.
Ho
w
e
v
er
,
P
SM
h
as
s
h
o
w
n
b
etter
p
er
f
o
r
m
an
ce
w
h
e
n
P
SF
m
atc
h
es
t
h
e
co
r
r
ec
t
in
ten
s
it
y
d
ep
en
d
e
n
ce
b
et
w
ee
n
i
m
a
g
es.
So
,
th
e
f
ir
s
t
co
n
tr
ib
u
tio
n
o
f
th
i
s
p
ap
er
is
to
s
h
o
w
th
at
t
h
er
e
is
s
till
a
p
o
ten
tial
f
o
r
f
u
r
t
h
er
r
esear
c
h
i
n
t
h
i
s
f
ield
a
s
MI
i
s
n
o
t
al
w
a
y
s
th
e
b
est
c
h
o
ice
f
o
r
s
i
m
ilar
it
y
m
ea
s
u
r
e
in
i
m
a
g
e
r
eg
is
tr
atio
n
.
T
h
e
s
ec
o
n
d
co
n
tr
ib
u
tio
n
i
s
to
p
r
ese
n
t
t
h
e
p
o
ten
t
ial
o
f
p
o
in
t
s
i
m
ilar
it
y
m
ea
s
u
r
es
i
n
i
m
ag
e
r
e
g
is
tr
atio
n
a
n
d
h
o
w
r
eg
is
tr
atio
n
er
r
o
r
s
co
u
ld
b
e
r
e
d
u
ce
d
u
s
i
n
g
co
r
r
ec
t P
SF
s
.
C
o
r
r
ec
t
P
SF
is
t
h
e
k
e
y
f
o
r
h
ig
h
-
q
u
al
it
y
i
m
ag
e
r
eg
is
tr
atio
n
.
So
,
f
u
t
u
r
e
w
o
r
k
w
ill
co
n
c
en
tr
ate
o
n
p
r
o
p
o
s
in
g
tech
n
iq
u
es
to
co
m
p
u
te
t
h
e
b
est
P
SF
.
M
ac
h
i
n
e
lea
r
n
in
g
tec
h
n
iq
u
es
w
ill
b
e
u
s
ed
to
lear
n
f
r
o
m
p
r
io
r
r
eg
is
tr
atio
n
r
esu
l
ts
to
p
r
ed
ict
th
e
b
est P
SF
f
o
r
h
i
g
h
-
q
u
alit
y
i
m
ag
e
m
atc
h
.
RE
F
E
R
E
NC
E
S
[1
]
T
.
S
.
M
u
rth
y
a
n
d
G
.
S
a
d
a
sh
iv
a
p
p
a
,
"
F
ra
m
e
w
o
rk
f
o
r
c
o
m
p
re
h
e
n
siv
e
e
n
h
a
n
c
e
m
e
n
t
o
f
b
ra
in
tu
m
o
r
im
a
g
e
s
w
it
h
sin
g
le
-
w
in
d
o
w
o
p
e
ra
ti
o
n
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
E
lec
trica
l
&
Co
mp
u
ter
En
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
1
0
,
n
o
.
1
,
p
p
.
8
0
1
-
8
0
8
,
2
0
2
0
.
[2
]
S
.
Ha
rish
a
n
d
G
.
F
.
A
li
A
h
a
m
m
e
d
,
"
In
teg
ra
ted
m
o
d
e
ll
in
g
a
p
p
ro
a
c
h
f
o
r
e
n
h
a
n
c
in
g
b
ra
in
M
RI
w
it
h
f
le
x
ib
le
p
re
-
pr
o
c
e
ss
in
g
c
a
p
a
b
il
it
y
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
E
lec
trica
l
a
n
d
Co
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
9
,
n
o
.
4
,
p
p
.
2
4
1
6
-
2
4
2
4
,
2
0
1
9
.
[3
]
D.
L.
G
.
Hill
a
n
d
D.
H
a
w
k
e
s,
"
A
c
ro
ss
-
m
o
d
a
li
t
y
r
e
g
istratio
n
u
sin
g
in
ten
sity
-
b
a
s
e
d
c
o
st
f
u
n
c
ti
o
n
s,"
in
:
I.
Ba
n
k
m
a
n
(Ed
.
),
H
a
n
d
b
o
o
k
o
f
M
e
d
ica
l
Ima
g
e
Pro
c
e
ss
in
g
,
Ac
a
d
e
mic
Pre
ss
,
Ne
w
Yo
rk
,
p
p
.
5
3
7
-
5
5
3
,
1
9
9
9
.
[4
]
Ho
ld
e
n
M
.
,
e
t
a
l.
,
"
V
o
x
e
l
si
m
il
a
r
it
y
m
e
a
su
re
s
f
o
r
3
-
D
s
e
ri
a
l
M
R
b
ra
in
im
a
g
e
r
e
g
istratio
n
,"
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
M
e
d
ica
l
Ima
g
in
g
,
v
o
l.
1
9
,
n
o
.
2
,
p
p
.
9
4
-
1
0
2
,
2
0
0
0
.
[5
]
P
.
V
io
la
a
n
d
W
.
W
e
ll
s,
"
A
li
g
n
m
e
n
t
b
y
m
a
x
i
m
i
z
a
ti
o
n
o
f
m
u
tu
a
l
in
f
o
rm
a
ti
o
n
,
"
Pro
c
e
e
d
in
g
s
o
f
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
m
p
u
ter
Vi
si
o
n
,
Ca
m
b
rid
g
e
,
M
A
,
USA
,
1
9
9
5
,
p
p
.
1
6
-
23.
[6
]
A
.
Co
ll
ig
n
o
n
,
e
t
a
l.
,
"
A
u
to
m
a
t
e
d
m
u
lt
im
o
d
a
li
t
y
i
m
a
g
e
r
e
g
istrati
o
n
b
a
se
d
o
n
in
f
o
rm
a
ti
o
n
t
h
e
o
ry
,
"
In
fo
rm
a
ti
o
n
Pro
c
e
ss
in
g
i
n
M
e
d
ica
l
Im
a
g
i
n
g
,
Klu
we
r A
c
a
d
e
mic
,
p
p
.
2
6
3
-
2
7
4
,
1
9
9
5
.
[7
]
J.
P
.
P
lu
im
,
J.
A
.
M
a
in
tz,
M
.
A
.
V
ierg
e
v
e
r,
"
M
u
tu
a
l
-
in
f
o
rm
a
ti
o
n
-
b
a
se
d
re
g
istratio
n
o
f
m
e
d
ica
l
i
m
a
g
e
s:
a
su
rv
e
y
,
"
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
M
e
d
ica
l
I
ma
g
in
g
,
v
o
l.
2
2
,
n
o
.
8
,
p
p
.
9
8
6
-
1
0
0
4
,
2
0
0
3
.
[8
]
S
.
K.
Ka
sh
y
a
p
,
e
t
a
l.
,
"
Zern
ik
e
M
o
m
e
n
t
a
n
d
M
u
tu
a
l
In
f
o
rm
a
ti
o
n
Ba
se
d
M
e
th
o
d
s
f
o
r
M
u
lt
im
o
d
a
l
I
m
a
g
e
Re
g
istratio
n
,
"
Pro
c
e
e
d
in
g
s
o
f
3
r
d
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
mp
u
ter
Vi
si
o
n
a
n
d
Im
a
g
e
Pr
o
c
e
ss
in
g
,
S
i
n
g
a
p
o
re
,
v
o
l.
1
0
2
4
,
2
0
2
0
,
p
p
.
1
0
1
-
1
1
3
.
[9
]
G
d
e
V
o
s,
e
t
a
l.
,
"
M
u
tu
a
l
in
f
o
rm
a
ti
o
n
f
o
r
u
n
su
p
e
rv
ise
d
d
e
e
p
lea
rn
in
g
im
a
g
e
re
g
istratio
n
,
"
M
e
d
ica
l
Ima
g
i
n
g
2
0
2
0
:
Ima
g
e
Pro
c
e
ss
in
g
.
I
n
ter
n
a
t
io
n
a
l
S
o
c
iety
fo
r O
p
ti
c
s a
n
d
Ph
o
to
n
ics
,
v
o
l.
1
1
3
1
3
,
2
0
2
0
.
[1
0
]
V
.
A
g
g
a
r
wa
l
a
n
d
A
.
G
u
p
ta,
"
In
teg
ra
ti
n
g
m
o
rp
h
o
lo
g
ica
l
e
d
g
e
d
e
tec
ti
o
n
a
n
d
m
u
tu
a
l
in
f
o
rm
a
ti
o
n
f
o
r
n
o
n
rig
i
d
re
g
istratio
n
o
f
m
e
d
ica
l
i
m
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.
1
5
,
n
o
.
3
,
p
p
.
2
9
2
-
3
0
0
,
2
0
1
9
.
[1
1
]
J.
A
.
S
h
a
c
k
le
f
o
rd
,
e
t
a
l.
,
"
On
d
e
v
e
lo
p
in
g
B
-
sp
li
n
e
re
g
istratio
n
a
l
g
o
rit
h
m
s
f
o
r
m
u
lt
i
-
c
o
re
p
ro
c
e
s
so
rs
,"
Ph
y
sic
s
in
M
e
d
icin
e
&
Bi
o
lo
g
y
,
v
o
l
.
5
5
,
n
o
.
2
1
,
p
.
6
3
2
9
,
2
0
1
0
.
[1
2
]
X
.
D
u
,
e
t
a
l.
,
"
A
p
a
ra
ll
e
l
n
o
n
rig
id
re
g
istratio
n
a
lg
o
rit
h
m
b
a
se
d
o
n
b
sp
li
n
e
f
o
r
m
e
d
ica
l
i
m
a
g
e
s,"
Co
mp
u
ta
ti
o
n
a
l
a
n
d
ma
th
e
ma
ti
c
a
l
me
th
o
d
s i
n
me
d
ici
n
e
,
v
o
l.
2
0
1
6
,
2
0
1
6
.
[1
3
]
D.
Ru
ij
ters
,
B.
M
.
ter
Ha
a
r
Ro
m
e
n
y
,
P
.
S
u
e
ten
s,
"
G
P
U
-
a
c
c
e
lera
te
d
e
las
ti
c
3
D
i
m
a
g
e
re
g
istratio
n
f
o
r
in
tra
-
su
rg
ica
l
a
p
p
li
c
a
ti
o
n
s,"
Co
mp
u
ter
me
th
o
d
s
a
n
d
p
r
o
g
ra
ms
i
n
b
io
me
d
icin
e
,
v
o
l
.
1
0
3
,
n
o
.
2
,
p
p
.
1
0
4
-
1
1
2
,
2
0
1
1
.
[1
4
]
D.
S
h
a
m
o
n
in
,
"
F
a
st
p
a
ra
ll
e
l
ima
g
e
re
g
istratio
n
o
n
C
P
U
a
n
d
G
P
U
f
o
r
d
iag
n
o
st
ic
c
las
sif
i
c
a
ti
o
n
o
f
A
lzh
e
i
m
e
r
'
s
d
ise
a
se
,
"
Fro
n
ti
e
rs
in
Ne
ru
o
in
f
o
r
ma
ti
c
s
,
v
o
l.
7
,
p
p
.
1
-
1
5
,
2
0
1
4
.
[1
5
]
G
.
L
it
jen
s,
e
t
a
l.
,
"
A
su
rv
e
y
o
n
d
e
e
p
lea
r
n
in
g
in
m
e
d
ica
l
i
m
a
g
e
a
n
a
l
y
sis,"
M
e
d
ica
l
ima
g
e
a
n
a
lys
is
,
v
o
l.
4
2
,
p
p
.
6
0
-
8
8
,
2
0
1
7
.
[1
6
]
X
.
Ca
o
,
e
t
a
l.
,
"I
m
a
g
e
re
g
istratio
n
u
si
n
g
d
e
e
p
lea
rn
i
n
g
,
"
Ha
n
d
b
o
o
k
o
f
M
e
d
ica
l
Ima
g
e
C
o
mp
u
ti
n
g
a
n
d
Co
m
p
u
te
r
Assiste
d
In
ter
v
e
n
ti
o
n
,
p
p
.
3
1
9
-
3
4
2
,
2
0
2
0
.
[1
7
]
G
.
Ha
s
k
in
s,
U.
Kru
g
e
r,
P
.
Ya
n
,
"
De
e
p
lea
rn
in
g
in
m
e
d
ica
l
i
m
a
g
e
r
e
g
istratio
n
:
a
su
rv
e
y
,
"
M
a
c
h
in
e
Vi
sio
n
a
n
d
Ap
p
li
c
a
ti
o
n
s
,
v
o
l
.
3
1
,
n
o
.
1
,
p
p
.
8
,
2
0
2
0
.
[1
8
]
G
.
Ha
s
k
in
s,
e
t
a
l.
,
"
L
e
a
rn
in
g
d
e
e
p
sim
il
a
rit
y
m
e
tri
c
f
o
r
3
D
M
R
-
T
RUS
im
a
g
e
re
g
istratio
n
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
mp
u
ter
Assis
ted
Ra
d
io
lo
g
y
a
n
d
S
u
r
g
e
ry
,
v
o
l.
1
4
,
n
o
.
3
,
p
p
.
4
1
7
-
4
2
5
,
2
0
1
9
.
[1
9
]
M
.
M
.
Bro
n
ste
in
,
e
t
a
l
.
,
"
Da
ta
fu
s
io
n
th
r
o
u
g
h
c
ro
ss
-
m
o
d
a
li
ty
m
e
tri
c
lea
rn
in
g
u
si
n
g
sim
il
a
rit
y
-
se
n
siti
v
e
h
a
s
h
in
g
,
"
2
0
1
0
IEE
E
C
o
mp
u
ter
S
o
c
iety
Co
n
fer
e
n
c
e
o
n
Co
mp
u
ter
Vi
sio
n
a
n
d
Pa
tt
e
rn
Rec
o
g
n
it
io
n
,
S
a
n
F
ra
n
c
isc
o
,
CA
,
2
0
1
0
,
p
p
.
3
5
9
4
-
3
6
0
1
.
[2
0
]
X
.
C
h
e
n
g
,
e
t
a
l
.
,
"
De
e
p
sim
il
a
rit
y
le
a
rn
in
g
f
o
r
m
u
lt
i
m
o
d
a
l
m
e
d
ica
l
im
a
g
e
s,
"
Co
mp
u
ter
M
e
th
o
d
s
i
n
Bi
o
me
c
h
a
n
ics
a
n
d
Bi
o
me
d
ica
l
En
g
in
e
e
rin
g
:
Ima
g
in
g
&
Vi
su
a
li
za
ti
o
n
,
v
o
l.
6
,
n
o
.
3
,
p
p
.
2
4
8
-
2
5
2
,
2
0
1
8
.
[2
1
]
L
.
Da
e
w
o
n
,
e
t
a
l.
,
"
L
e
a
rn
in
g
sim
i
larity
m
e
a
su
re
f
o
r
m
u
lt
i
-
m
o
d
a
l
3
D
im
a
g
e
re
g
istr
a
ti
o
n
,
"
2
0
0
9
IEE
E
Co
n
fer
e
n
c
e
o
n
Co
mp
u
ter
V
isio
n
a
n
d
Pa
t
ter
n
Rec
o
g
n
it
io
n
,
M
iam
i,
F
L
,
2
0
0
9
,
p
p
.
1
8
6
-
1
9
3
.
[2
2
]
P
.
Ro
g
e
lj
,
S
.
Ko
v
a
c
ic,
J.
C.
Ge
e
,
"
P
o
i
n
t
sim
il
a
rit
y
m
e
a
su
re
s
fo
r
n
o
n
-
r
ig
id
re
g
istratio
n
o
f
m
u
l
ti
-
m
o
d
a
l
d
a
ta,"
Co
mp
u
ter
V
isio
n
a
n
d
Ima
g
e
U
n
d
e
rs
ta
n
d
i
n
g
,
v
o
l.
9
2
,
n
o
.
1
,
p
p
.
1
1
2
-
1
4
0
,
2
0
0
3
.
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.
11
,
No
.
3
,
J
u
n
e
2
0
2
1
:
2
6
1
3
-
2620
2620
[2
3
]
J.
M
.
F
it
z
p
a
tri
c
k
,
J.
B.
W
e
st,
C.
R.
M
a
u
re
r,
"
P
re
d
icti
n
g
e
rro
r
in
rig
id
-
b
o
d
y
p
o
in
t
-
b
a
se
d
re
g
istratio
n
,
"
IE
E
E
T
ra
n
sa
c
ti
o
n
s
o
n
M
e
d
ica
l
Im
a
g
i
n
g
,
v
o
l.
1
7
,
n
o
.
5
,
p
p
.
6
9
4
-
7
0
2
,
1
9
9
8
.
[2
4
]
Hijaz
i,
M
o
h
d
Ha
n
a
f
i
A
h
m
a
d
,
e
t
a
l.
,
"
En
se
m
b
le
d
e
e
p
lea
rn
in
g
f
o
r
tu
b
e
rc
u
l
o
sis
d
e
tec
ti
o
n
u
sin
g
c
h
e
st
X
-
ra
y
a
n
d
c
a
n
n
y
e
d
g
e
d
e
tec
ted
i
m
a
g
e
s,
"
IA
ES
I
n
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
f
Arti
f
icia
l
I
n
telli
g
e
n
c
e
(
IJ
-
AI)
,
v
o
l.
8
,
n
o
.
4
,
p
p
.
4
2
9
-
4
3
5
,
2
0
1
9
.
[2
5
]
N.
Ra
ju
,
H.
B.
A
n
it
a
,
P
.
A
u
g
u
stin
e
,
"
Id
e
n
ti
f
ica
ti
o
n
o
f
i
n
ters
ti
ti
a
l
l
u
n
g
d
ise
a
se
s
u
sin
g
d
e
e
p
lea
rn
in
g
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
&
Co
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
, v
o
l.
10
,
n
o
.
6
,
p
p
.
6
2
8
3
-
6
2
9
1
,
2
0
2
0
.
[2
6
]
B.
A
ls
a
a
id
a
,
a
n
d
M
.
A
l
-
G
a
w
a
g
z
e
h
,
"
G
li
o
b
las
to
m
a
s
b
ra
in
tu
m
o
u
r
se
g
m
e
n
tatio
n
b
a
s
e
d
o
n
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
"
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
(
I
J
E
C
E
)
,
v
o
l
.
1
0
,
n
o
.
5
,
p
p
.
4738
-
4744
,
2
0
2
0
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Wa
ss
i
m
El
-
H
a
jj
-
Cheha
d
e
re
c
e
iv
e
d
h
is
P
h
D
d
e
g
re
e
in
t
h
e
f
ield
o
f
so
f
t
w
a
re
e
n
g
in
e
e
rin
g
f
ro
m
P
a
ris
XI
Un
iv
e
rsity
in
2
0
1
1
w
h
e
re
h
e
w
o
rk
e
d
a
t
th
e
Lab
o
ra
to
ry
o
f
M
o
d
e
l
Driv
e
n
En
g
in
e
e
rin
g
f
o
r
Em
b
e
d
d
e
d
S
y
ste
m
s
a
t
CE
A
L
IS
T
.
Af
ter
o
b
tain
in
g
h
is
P
h
D,
h
e
w
o
rk
e
d
f
o
r
a
sta
rt
-
u
p
c
o
m
p
a
n
y
b
a
se
d
i
n
Brit
ta
n
y
,
F
ra
n
c
e
.
Cu
rre
n
tl
y
,
h
e
is
a
n
a
ss
istan
t
p
r
o
f
e
ss
o
r
a
t
th
e
F
a
c
u
lt
y
o
f
S
c
ien
c
e
a
t
Be
iru
t
A
ra
b
Un
iv
e
rsit
y
sin
c
e
2
0
1
4
.
H
is
re
se
a
rc
h
in
tere
sts
a
re
in
ima
g
e
p
ro
c
e
ss
in
g
,
m
o
d
e
l
d
riv
e
n
e
n
g
in
e
e
rin
g
,
re
a
l
-
ti
m
e
e
m
b
e
d
d
e
d
s
y
ste
m
s a
n
d
m
o
b
il
e
a
p
p
l
ica
ti
o
n
d
e
v
e
lo
p
m
e
n
t.
Pete
r
Ro
g
e
lj
re
c
e
iv
e
d
h
is
P
h
D
i
n
2
0
0
3
f
ro
m
th
e
Un
iv
e
rsit
y
o
f
L
ju
b
lj
a
n
a
,
S
l
o
v
e
n
ia,
in
th
e
f
ield
o
f
e
lec
tri
c
a
l
e
n
g
in
e
e
rin
g
.
His
m
a
in
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
im
a
g
e
p
r
o
c
e
ss
in
g
w
it
h
sp
e
c
ial
e
m
p
h
a
sis
o
n
m
e
d
ica
l
ima
g
e
p
ro
c
e
ss
in
g
a
n
d
a
rti
f
icia
l
in
telli
g
e
n
c
e
.
He
sp
e
n
t
se
v
e
r
a
l
y
e
a
rs
in
th
e
in
d
u
stry
a
s
a
so
f
t
w
a
re
d
e
v
e
lo
p
e
r
a
n
d
p
ro
jec
t
m
a
n
a
g
e
r.
Cu
rre
n
tl
y
,
h
e
is an
a
ss
ista
n
t
p
r
o
f
e
ss
o
r
a
t
th
e
Un
iv
e
rsity
o
f
P
rim
o
rsk
a
,
S
lo
v
e
n
ia,
lec
tu
rin
g
t
o
p
ics
in
c
o
m
p
u
ter
v
isio
n
,
im
a
g
e
p
ro
c
e
ss
in
g
,
so
f
twa
re
e
n
g
in
e
e
rin
g
,
a
n
d
c
o
m
p
u
ter n
e
tw
o
rk
s.
Evaluation Warning : The document was created with Spire.PDF for Python.