I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
25
,
No
.
1
,
J
an
u
ar
y
2
0
2
2
,
p
p
.
2
7
3
~
2
8
0
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
25
.i
1
.
pp
273
-
2
8
0
273
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
The
Io
T
a
nd
regi
s
tration
o
f
M
RI
br
a
in dia
g
no
sis
bas
ed on
g
enetic
a
lg
o
rithm
and co
nv
o
lution
al
neura
l ne
twork
Ahm
ed
Sh
iha
b A
hm
ed
1
,
H
us
s
ein A
li Sa
la
h
2
1
D
e
p
a
r
t
me
n
t
o
f
B
a
si
c
S
c
i
e
n
c
e
s,
C
o
l
l
e
g
e
o
f
N
u
r
si
n
g
,
U
n
i
v
e
r
si
t
y
o
f
B
a
g
h
d
a
d
,
B
a
g
h
d
a
d
,
I
r
a
q
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
y
st
e
ms,
T
e
c
h
n
i
c
a
l
I
n
st
i
t
u
t
e
-
S
u
w
a
i
r
a
,
M
i
d
d
l
e
Te
c
h
n
i
c
a
l
U
n
i
v
e
r
si
t
y
,
B
a
g
h
d
a
d
,
I
r
a
q
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l
16
,
2
0
2
1
R
ev
is
ed
Oct
24
,
2
0
2
1
Acc
ep
ted
No
v
26
,
2
0
2
1
Th
e
tec
h
n
o
l
o
g
y
o
f
th
e
m
u
lt
imo
d
a
l
b
ra
i
n
ima
g
e
re
g
istrati
o
n
is t
h
e
k
e
y
m
e
th
o
d
fo
r
a
c
c
u
ra
te
a
n
d
ra
p
id
d
ia
g
n
o
sis
a
n
d
trea
tme
n
t
o
f
b
ra
in
d
ise
a
se
s.
F
o
r
a
c
h
iev
in
g
h
i
g
h
-
re
so
lu
ti
o
n
ima
g
e
re
g
istratio
n
,
a
fa
st
s
u
b
p
i
x
e
l
r
e
g
istratio
n
a
lg
o
rit
h
m
is
u
se
d
b
a
se
d
o
n
si
n
g
le
-
ste
p
d
isc
re
te
wa
v
e
let
tran
sfo
rm
(DWT
)
c
o
m
b
in
e
d
with
p
h
a
se
c
o
n
v
o
l
u
ti
o
n
n
e
u
ra
l
n
e
two
r
k
(CNN
)
to
c
las
sify
th
e
re
g
istratio
n
o
f
b
ra
i
n
tu
m
o
rs.
I
n
t
h
is
wo
rk
a
p
p
ly
t
h
e
g
e
n
e
ti
c
a
lg
o
r
it
h
m
a
n
d
CNN
c
las
ifc
a
ti
o
n
in
re
g
istrati
o
n
o
f
m
a
g
n
e
ti
c
re
so
n
a
n
c
e
ima
g
i
n
g
(
M
RI
)
ima
g
e
.
Th
is
a
p
p
r
o
a
c
h
f
o
ll
o
ws
e
ig
h
t
ste
p
s,
re
a
d
i
n
g
t
h
e
so
u
rc
e
o
f
M
RI
b
ra
i
n
ima
g
e
a
n
d
lo
a
d
i
n
g
t
h
e
re
fe
re
n
c
e
ima
g
e
,
e
n
h
e
n
c
m
e
n
t
a
ll
M
RI
ima
g
e
s
b
y
b
il
a
tera
l
fil
ter
,
tra
n
sfo
rm
in
g
DW
T
ima
g
e
b
y
a
p
p
l
y
i
n
g
t
h
e
D
WT
2
,
e
v
a
lu
a
ti
n
g
(fit
n
e
ss
fu
n
c
ti
o
n
)
e
a
c
h
M
RI
ima
g
e
b
y
u
si
n
g
e
n
tr
o
p
y
,
a
p
p
ly
i
n
g
t
h
e
g
e
n
e
ti
c
a
lg
o
rit
h
m
,
b
y
se
lec
ti
n
g
t
h
e
two
i
m
a
g
e
s
b
a
se
d
o
n
ro
ll
o
u
t
wh
e
e
l
a
n
d
c
ro
ss
o
v
e
r
o
f
th
e
two
ima
g
e
s,
th
e
CNN
c
las
sify
th
e
re
su
lt
o
f
su
b
trac
ti
o
n
to
n
o
rm
a
l
o
r
a
b
n
o
rm
a
l,
“
in
t
h
e
e
ig
h
th
o
n
e
,
”
t
h
e
Ard
u
i
n
o
a
n
d
g
l
o
b
a
l
sy
ste
m
f
o
r
m
o
b
il
e
(G
S
M
)
8
0
8
0
a
re
a
p
p
li
e
d
t
o
se
n
d
t
h
e
m
e
ss
a
g
e
to
p
a
ti
e
n
t.
T
h
e
p
ro
p
o
se
d
m
o
d
e
l
is
tes
ted
o
n
M
RI
M
e
d
ica
l
Cit
y
Ho
sp
it
a
l
in
Ba
g
h
d
a
d
d
a
tab
a
se
c
o
n
sist
5
5
0
n
o
rm
a
l
a
n
d
3
5
0
a
b
n
o
rm
a
l
a
n
d
sp
li
t
t
o
8
0
%
trai
n
in
g
a
n
d
2
0
tes
ti
n
g
,
th
e
p
ro
p
o
se
d
m
o
d
e
l
re
su
lt
a
c
h
iev
e
s th
e
9
8
.
8
%
a
c
c
u
r
a
c
y
.
K
ey
w
o
r
d
s
:
Ar
d
u
in
o
g
lo
b
al
s
y
s
tem
f
o
r
m
o
b
ile
C
o
n
v
o
lu
tio
n
n
eu
r
al
n
etwo
r
k
Dis
cr
ete
wav
elet
tr
an
s
f
o
r
m
Gen
etic
alg
o
r
ith
m
I
n
ter
n
et
o
f
th
in
g
s
R
eg
is
tr
atio
n
o
f
m
ag
n
etic
r
eso
n
an
ce
im
ag
i
n
g
b
r
ain
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
:
Hu
s
s
ein
Ali Sala
h
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Sy
s
t
em
s
,
T
ec
h
n
ical
I
n
s
titu
te
-
Su
wa
ir
a,
Mid
d
le
T
ec
h
n
ical
Un
iv
er
s
ity
Mu
ask
er
Al
R
ash
id
Stre
et,
B
a
g
h
d
ad
,
I
r
aq
E
m
ail:
h
u
s
s
ein
_
tech
@
m
tu
.
ed
u
.
iq
1.
I
NT
RO
D
UCT
I
O
N
C
u
r
r
e
n
t
ly
,
m
e
d
ic
al
i
m
a
g
i
n
g
s
y
s
tem
s
h
a
v
e
a
c
r
u
cia
l r
o
l
e
in
t
h
e
cl
i
n
ic
al
w
o
r
k
f
l
o
w
,
d
u
e
t
o
t
h
e
ir
a
b
i
lit
y
t
o
r
e
f
le
ct
an
at
o
m
ic
al
a
n
d
p
h
y
s
io
l
o
g
ic
al
f
e
at
u
r
es
w
h
ic
h
ar
e
n
o
t o
th
e
r
w
is
e
av
ail
ab
le
f
o
r
i
n
s
p
ec
t
i
o
n
[1
]
,
[
2
]
.
Me
d
ic
al
im
a
g
e
te
ch
n
o
l
o
g
y
u
s
es
a
v
a
r
i
ety
o
f
d
i
f
f
er
e
n
t
c
o
n
c
ep
ts
t
o
q
u
a
n
ti
f
y
t
h
e
s
p
a
tia
l
d
is
t
r
i
b
u
ti
o
n
s
o
f
t
h
e
p
h
y
s
ic
al
ch
ar
ac
t
er
is
ti
cs
o
f
h
u
m
a
n
s
a
n
d
h
el
p
t
o
b
et
te
r
u
n
d
e
r
s
t
an
d
i
n
g
t
o
c
o
m
p
le
x
o
r
u
n
u
s
u
a
l
d
is
ea
s
es.
Data
p
r
o
ce
s
s
i
n
g
is
ess
e
n
ti
al
f
o
r
co
m
p
u
te
r
ass
is
t
an
ce
m
e
d
ic
al
d
ia
g
n
o
s
e
[
3
]
,
[
4
]
.
T
h
e
m
et
h
o
d
t
o
in
te
g
r
ate
c
o
m
p
le
m
e
n
ta
r
y
in
f
o
r
m
at
io
n
f
r
o
m
m
o
r
e
t
h
a
n
o
n
e
i
m
a
g
e
o
f
a
c
er
tai
n
o
r
g
a
n
i
n
t
o
o
n
e
c
o
m
p
o
s
it
e
im
a
g
e
ca
n
p
r
o
v
id
e
u
s
e
f
u
l
in
f
o
r
m
at
io
n
.
T
h
e
n
u
m
b
e
r
o
f
a
v
ai
la
b
l
e
m
o
d
al
ities
a
n
d
t
h
e
d
at
a
v
o
l
u
m
e
o
f
d
a
ta
i
n
m
e
d
ic
al
i
m
a
g
es
m
a
k
es
i
t
v
er
y
d
i
f
f
ic
u
lt
t
o
ex
p
l
ici
tl
y
u
s
e
t
h
e
m
a
t
d
i
f
f
e
r
e
n
t
le
v
e
ls
o
f
c
o
m
p
le
m
e
n
t
a
r
y
d
at
a
[
5
]
,
[
6
]
.
Mo
r
eo
v
e
r
,
e
ac
h
m
et
h
o
d
o
f
f
er
s
a
p
a
r
ti
al
am
o
u
n
t o
f
k
n
o
wle
d
g
e,
a
n
d
o
f
t
e
n
tw
o
o
r
m
o
r
e
m
o
d
es
f
r
o
m
t
h
e
s
a
m
e
p
at
ie
n
t a
r
e
e
m
p
lo
y
ed
t
o
g
et
well
-
u
n
d
er
s
t
o
o
d
s
e
n
s
e
d
m
ate
r
i
al.
T
h
e
f
i
r
s
t
o
n
e
c
an
p
r
o
v
i
d
e
d
ec
e
n
t
s
t
r
u
ct
u
r
a
l d
e
tai
ls
(
i
.
e
.
b
r
i
llia
n
t
c
o
n
t
r
as
t to
t
h
e
b
o
n
es)
is
co
m
p
u
te
d
t
o
m
o
g
r
a
p
h
y
(
CT
)
s
c
an
n
e
r
,
w
h
il
e
t
h
e
m
ag
n
e
tic
r
eso
n
an
ce
im
ag
in
g
(
MRI)
p
r
o
v
i
d
es
g
o
o
d
d
at
a
o
n
we
ak
tis
s
u
e
(
s
o
f
t
tis
s
u
e
)
.
T
w
o
m
o
d
alit
ies
ar
e
f
r
e
q
u
e
n
tl
y
u
s
e
d
i
n
b
r
ai
n
v
is
u
a
liz
a
tio
n
(
s
u
c
h
as
w
h
i
te
m
at
te
r
an
d
g
r
e
y
m
att
er
[
7
]
-
[
9
]
.
T
h
e
w
o
r
d
‘‘
r
e
g
is
t
r
a
ti
o
n
’’
i
ll
u
s
tr
a
tes
t
h
at
is
,
f
i
n
d
in
g
a
m
atc
h
b
et
we
en
tw
o
im
ag
e
r
e
g
is
t
r
a
ti
o
n
is
u
s
e
d
t
o
d
et
er
m
i
n
e
g
e
o
m
et
r
ic
tr
an
s
iti
o
n
s
to
p
r
o
v
i
d
e
a
n
o
r
m
al
o
r
r
e
f
e
r
en
ce
i
m
a
g
e
i
n
t
h
e
c
r
e
at
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
25
,
No
.
1
,
J
an
u
ar
y
20
22
:
273
-
2
8
0
274
im
a
g
e
[
10
]
,
[
11
]
.
T
h
e
te
ch
n
i
q
u
e
o
f
r
e
g
is
t
r
a
ti
o
n
o
f
i
m
a
g
es
c
an
b
e
d
iv
id
e
d
i
n
t
o
t
h
r
ee
ty
p
es,
th
e
o
p
t
im
iza
ti
o
n
o
f
s
im
il
ar
it
y
m
ea
s
u
r
es
,
g
e
o
m
et
r
i
c
tr
an
s
f
o
r
m
a
ti
o
n
,
a
n
d
i
n
te
r
p
o
lat
io
n
.
T
h
e
m
ea
s
u
r
e
o
f
s
i
m
il
ar
it
y
r
e
p
r
es
en
ts
t
h
e
k
e
y
s
tep
in
t
h
e
r
e
co
r
d
i
n
g
o
f
i
m
a
g
es
[
1
2
]
-
[
14]
.
T
h
e
r
e
g
is
t
r
a
ti
o
n
p
r
o
c
e
d
u
r
e
is
o
f
i
m
m
e
n
s
e
i
m
p
o
r
ta
n
ce
.
MRI
is
cu
r
r
e
n
tl
y
t
h
e
m
o
s
t
i
m
p
o
r
t
a
n
t
way
o
f
o
b
tai
n
i
n
g
s
o
f
t
tis
s
u
e
i
m
a
g
i
n
g
es
p
e
cia
ll
y
i
n
o
n
co
lo
g
y
,
s
in
ce
th
e
i
m
a
g
e
co
n
t
r
as
ts
a
n
d
r
es
o
l
u
t
io
n
o
f
l
esio
n
s
a
n
d
h
e
alt
h
y
t
is
s
u
e
ar
e
s
ig
n
i
f
i
ca
n
t
ly
i
m
p
r
o
v
e
d
[
15
]
,
[
16
]
.
T
h
e
MRI
is
co
n
s
i
d
e
r
e
d
to
b
e
m
o
r
e
a
cc
u
r
at
e
t
o
ass
ess
t
h
e
le
v
el
o
f
c
an
ce
r
in
f
ilt
r
ati
o
n
t
h
a
n
co
m
p
u
te
d
t
o
m
o
g
r
ap
h
y
[
17
]
-
[
19
]
.
T
h
e
r
e
g
is
tr
ati
o
n
o
f
b
i
o
m
e
d
ic
a
l
i
m
a
g
es
h
as
m
a
n
y
a
p
p
r
o
a
ch
e
s
,
g
o
l
d
s
t
a
n
d
ar
d
u
s
es
r
e
g
i
o
n
-
of
-
i
n
t
er
est
m
ar
k
er
s
,
an
d
o
t
h
e
r
m
et
h
o
d
s
i
n
c
lu
d
e
c
o
r
r
ela
ti
o
n
o
f
g
e
o
m
et
r
i
ca
l
c
h
a
r
a
cte
r
is
t
ics
[
20
]
,
[
21
]
.
I
n
te
n
s
i
ty
-
b
as
ed
m
et
h
o
d
s
a
r
e
m
o
r
e
wo
r
k
e
d
i
n
r
e
ce
n
t
y
e
ar
s
t
o
q
u
an
ti
f
y
c
o
r
r
e
lat
io
n
s
b
e
twe
e
n
a
n
i
m
a
g
e
wit
h
t
h
e
i
n
te
n
s
i
ty
v
al
u
es
(
co
lo
r
o
r
g
r
ay
lev
el
)
.
T
h
e
c
o
n
s
is
t
e
n
c
y
o
f
r
e
co
r
d
i
n
g
m
e
d
ic
al
im
ag
es
d
e
p
e
n
d
s
o
n
t
h
e
o
p
t
io
n
s
m
ad
e
u
s
i
n
g
t
h
e
m
et
h
o
d
o
f
p
r
o
ce
s
s
i
n
g
,
i
n
te
r
p
o
la
ti
o
n
,
s
im
i
l
ar
i
ty
c
alc
u
l
ati
o
n
,
a
n
d
o
p
ti
m
iz
a
tio
n
.
A
s
p
ec
if
i
c
u
s
e
o
f
t
h
e
g
en
e
tic
al
g
o
r
i
th
m
is
t
h
e
p
r
im
ar
y
o
r
i
g
i
n
a
l
c
h
a
r
ac
t
er
is
ti
c
o
f
t
h
e
m
et
h
o
d
(
f
r
o
m
e
n
c
o
d
in
g
t
o
g
en
eti
c
s
p
a
ce
s
cr
ee
n
i
n
g
)
[
22
]
,
[
23
].
Ge
n
e
tic
a
lg
o
r
it
h
m
(
GA
)
r
eli
es
u
p
o
n
‘
‘
s
u
r
v
i
v
al
o
f
th
e
f
i
ttes
t
’’
p
r
i
n
c
ip
le
an
d
a
g
lo
b
al
s
el
ec
t
io
n
o
f
t
h
e
b
est
f
o
r
t
h
e
n
ew
g
e
n
e
r
a
ti
o
n
b
y
c
r
o
s
s
o
v
er
a
n
d
m
u
tat
io
n
o
p
e
r
a
to
r
s
s
el
ec
t
t
h
e
wo
r
l
d
'
s
b
est
n
ew
g
en
e
r
at
io
n
.
T
h
e
o
p
ti
m
iz
ati
o
n
s
ch
em
e
is
i
n
it
ial
ize
d
b
y
u
p
d
a
tin
g
th
e
g
en
er
ati
o
n
s
wit
h
a
r
an
d
o
m
p
o
p
u
la
ti
o
n
o
f
s
o
l
u
ti
o
n
s
a
n
d
s
e
ar
c
h
es
f
o
r
o
p
ti
m
a
[
24
]
,
[
25
]
.
N
eu
r
a
l
n
et
wo
r
k
s
a
r
e
p
la
y
i
n
g
a
s
i
g
n
if
ica
n
t
p
ar
t
i
n
m
e
d
i
ca
l
d
ia
g
n
o
s
is
a
n
d
c
las
s
i
f
i
ca
t
io
n
o
f
b
r
ai
n
a
n
d
t
u
m
o
r
s
d
is
e
ases
.
T
h
e
n
eu
r
al
n
et
wo
r
k
m
et
h
o
d
s
we
r
e
im
p
l
em
e
n
te
d
t
o
r
e
la
y
t
h
e
n
e
u
r
al
ar
ch
ite
ct
u
r
e
o
f
th
e
i
m
a
g
e
s
e
g
m
e
n
t
ati
o
n
n
e
tw
o
r
k
,
als
o
a
h
y
b
r
i
d
i
m
a
g
e
s
eg
m
e
n
ta
ti
o
n
n
e
u
r
al
n
et
wo
r
k
wit
h
f
u
zz
y
[
26
]
,
[
27
]
.
T
h
e
m
ain
m
o
tiv
atio
n
s
o
f
th
is
wo
r
k
is
in
cr
em
en
tal
g
r
o
wth
i
n
th
e
in
ter
n
et
o
f
th
in
g
s
(
I
o
T
)
tech
n
o
lo
g
y
to
b
e
an
y
w
h
er
e,
a
n
y
tim
e
r
esu
lts
in
in
cr
ea
s
in
g
d
em
an
d
f
o
r
au
to
m
atio
n
in
e
-
h
ea
lth
.
T
h
e
n
ee
d
f
o
r
au
to
m
atic
d
iag
n
o
s
is
ap
p
licatio
n
s
with
less
tim
e
co
m
p
lex
ity
an
d
ac
cu
r
ac
y
is
h
ig
h
ly
p
r
ef
er
r
e
d
.
B
ig
d
at
a
an
d
d
ata
s
cien
ce
ar
e
a
n
ew
h
o
t
t
o
p
ic
a
d
d
r
ess
ed
b
y
s
o
f
t
co
m
p
u
tin
g
tech
n
iq
u
es
f
o
r
t
h
eir
a
p
p
licab
ilit
y
t
o
d
ea
l
with
v
ag
u
e
n
ess
an
d
u
n
ce
r
tain
d
ata
b
esid
es
lear
n
in
g
ca
p
ab
ilit
y
.
T
h
e
o
b
j
ec
ti
v
es o
f
t
h
is
w
o
r
k
t
o
d
e
v
el
o
p
a
t
r
a
n
s
m
is
s
io
n
m
o
d
el
f
o
r
th
e
I
o
T
e
n
v
ir
o
n
m
e
n
t
b
ase
d
o
n
t
h
e
c
ell
u
l
ar
n
etw
o
r
k
t
h
at
e
n
a
b
les
c
li
n
ic
al
d
ia
g
n
o
s
tic
a
u
t
o
m
at
io
n
.
T
h
e
m
a
in
co
n
t
r
i
b
u
ti
o
n
s
is
d
e
v
el
o
p
in
g
a
MRI
al
g
o
r
i
th
m
b
as
ed
o
n
wav
el
et
a
n
d
f
u
s
io
n
tec
h
n
o
l
o
g
y
i
n
s
i
d
e
GA
wi
th
co
n
v
o
lu
ti
o
n
n
e
u
r
al
n
etw
o
r
k
(
C
NN)
f
o
r
d
et
ec
t
io
n
h
ig
h
a
cc
u
r
a
cy
o
f
t
h
e
p
r
o
p
o
s
ed
w
o
r
k
.
T
h
e
m
ai
n
p
r
o
b
l
em
o
f
wo
r
k
is
i
n
t
r
o
d
u
c
e
a
u
t
o
m
a
ti
c
s
y
s
te
m
f
o
r
d
e
tec
ti
o
n
a
n
d
d
ai
g
n
o
s
is
MR
I
b
r
ai
n
wit
h
h
i
g
h
a
cc
u
r
a
cy
.
I
n
th
is
s
t
u
d
y
,
a
h
y
b
r
i
d
s
y
s
te
m
was
p
r
o
p
o
s
e
d
,
wh
i
ch
co
n
s
is
ts
o
f
tw
o
s
ta
g
es,
t
h
e
f
i
r
s
t
s
ta
g
e
i
s
im
ag
e
r
e
g
is
t
r
at
io
n
t
h
at
i
n
cl
u
d
es
t
h
e
g
e
n
e
tic
al
g
o
r
it
h
m
,
an
d
th
e
s
ec
o
n
d
s
ta
g
e
is
im
ag
e
d
e
tec
ti
o
n
t
h
at
i
n
c
lu
d
es C
NN
a
n
d
c
o
n
n
ec
te
d
i
n
b
y
u
s
i
n
g
g
l
o
b
al
s
y
s
te
m
f
o
r
m
o
b
il
e
(
GSM
8
0
8
0
)
f
o
r
s
e
n
d
m
ass
ag
e
t
o
p
ati
en
t
an
I
o
T
e
n
v
i
r
o
n
m
e
n
t
.
T
h
is
w
o
r
k
ai
m
s
t
o
d
e
v
el
o
p
a
s
o
f
t
co
m
p
u
ti
n
g
m
o
d
e
l
f
o
r
i
m
ag
e
r
e
g
is
t
r
ati
o
n
as
a
f
i
r
s
t
s
ta
g
e
i
n
t
h
e
au
to
m
a
tic
d
ia
g
n
o
s
i
s
s
y
s
t
em
.
T
h
e
n
,
i
t
p
r
o
p
o
s
es
a
n
d
in
co
r
p
o
r
ates
a
d
ete
cti
o
n
s
t
a
g
e
t
o
a
u
t
o
m
ate
t
h
e
d
ia
g
n
o
s
is
p
r
o
c
ess
,
w
h
ic
h
wi
ll
p
r
o
v
e
t
h
e
ac
c
u
r
a
cy
o
f
t
h
e
p
r
o
p
o
s
e
d
r
e
g
is
tr
ati
o
n
s
ta
g
e
i
n
th
e
cli
n
i
ca
l
w
o
r
k
f
l
o
w
b
as
ed
o
n
t
h
e
I
o
T
e
n
v
ir
o
n
m
en
t.
2.
RE
L
AT
E
D
WO
RK
S
An
ar
ak
i
et
al
.
[
28
]
,
p
r
o
p
o
s
ed
a
C
NN
-
b
ased
m
eth
o
d
a
n
d
g
en
etic
alg
o
r
ith
m
f
o
r
class
if
y
i
n
g
v
ar
i
o
u
s
g
r
ad
in
g
o
f
g
lio
m
a
b
y
MRI.
I
n
th
e
p
r
o
p
o
s
ed
m
eth
o
d
,
C
NN'
s
ar
ch
itectu
r
e
is
d
e
v
elo
p
ed
b
y
t
h
e
u
s
e
o
f
a
g
en
etic
alg
o
r
ith
m
,
as
o
p
p
o
s
ed
to
c
u
r
r
en
t
tech
n
iq
u
es
o
f
s
elec
tio
n
t
h
e
(
DNN)
ar
c
h
itectu
r
e,
wh
ich
r
elies
u
p
o
n
o
n
tr
ial
an
d
er
r
o
r
o
r
t
h
r
o
u
g
h
th
e
a
d
o
p
tio
n
co
m
m
o
n
s
tr
u
ctu
r
es
th
at
a
r
e
d
ef
in
ed
i
n
ad
v
a
n
ce
.
Fu
r
th
er
m
o
r
e,
to
m
in
i
m
ize
p
r
ed
ictio
n
e
r
r
o
r
v
ar
ian
ce
,
b
a
g
g
i
n
g
as
an
e
n
s
em
b
le
alg
o
r
ith
m
was
u
s
ed
o
n
t
h
e
o
p
tim
u
m
m
o
d
el
th
at
g
en
etic
alg
o
r
ith
m
d
ev
el
o
p
ed
.
T
o
in
d
ic
ate
th
e
r
esu
lts
b
r
ief
ly
,
in
o
n
e
ca
s
e
s
tu
d
y
,
a
9
0
.
9
%
ac
cu
r
ac
y
i
s
g
o
tten
to
class
if
y
th
r
ee
g
r
ad
es
o
f
g
lio
m
a
in
d
if
f
er
en
t
ca
s
e
s
tu
d
y
,
Pit
u
itar
y
,
Me
n
in
g
io
m
a
,
an
d
Glio
m
a
tu
m
o
r
ty
p
es
ar
e
ca
teg
o
r
ized
with
th
e
to
tal
ac
c
u
r
ac
y
at
9
4
.
2
%
.
Sh
ah
a
m
at
an
d
Ab
ad
eh
[
29
]
,
i
n
tr
o
d
u
ce
d
3
D
-
C
NN
f
o
r
class
if
y
in
g
b
r
ain
m
ag
n
etic
r
eso
n
an
ce
im
ag
in
g
in
to
two
p
r
e
-
d
eter
m
in
e
d
class
if
icatio
n
s
.
Mo
r
eo
v
er
,
a
m
eth
o
d
o
f
g
en
etic
alg
o
r
ith
m
b
ased
b
r
ain
m
ask
in
g
was
s
u
g
g
ested
as
a
v
is
u
aliza
tio
n
tech
n
iq
u
e
p
r
o
v
id
in
g
a
cle
ar
u
n
d
e
r
s
tan
d
in
g
t
o
th
r
ee
-
d
im
en
s
io
n
co
n
v
o
lu
tio
n
a
l
n
eu
r
al
n
etwo
r
k
f
u
n
ctio
n
.
T
h
i
s
m
eth
o
d
is
co
m
p
o
s
ed
two
s
tep
s
.
I
n
th
e
f
ir
s
t
o
n
e,
a
s
et
o
f
b
r
ai
n
MRI
s
ca
n
s
will b
e
u
tili
ze
d
f
o
r
tr
ain
in
g
t
h
e
th
r
e
e
-
d
im
en
s
io
n
co
n
v
o
lu
tio
n
al
n
e
u
r
al
n
etwo
r
k
.
I
n
th
e
s
ec
o
n
d
o
n
e,
a
g
en
etic
alg
o
r
it
h
m
is
im
p
lem
en
ted
to
d
etec
t
b
r
ain
r
eg
io
n
s
in
MRI
s
ca
n
n
in
g
.
T
h
e
r
eg
io
n
s
ar
e
b
r
ain
ar
ea
s
m
o
s
tly
u
s
ed
b
y
3
D
-
C
NN
f
o
r
ex
tr
ac
tin
g
s
ig
n
if
ic
an
t
an
d
d
is
cr
im
in
ativ
e
tr
aits
f
r
o
m
th
ese
ar
e
as.
T
o
ap
p
ly
GA
to
m
ag
n
etic
r
eso
n
an
ce
im
ag
in
g
s
ca
n
s
o
f
b
r
ain
,
a
n
ew
ap
p
r
o
ac
h
o
f
ch
r
o
m
o
s
o
m
al
en
co
d
in
g
is
s
u
g
g
ested
.
Fu
r
th
e
r
m
o
r
e
,
a
n
e
v
alu
atio
n
is
c
o
n
d
u
cted
to
th
i
s
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
b
y
t
h
e
u
s
e
Alzh
eim
er
'
s
d
is
ea
s
e
Neu
r
o
im
ag
in
g
i
n
itiativ
e
(
ADNI
)
(
in
cl
u
d
in
g
o
n
e
h
u
n
d
r
ed
f
o
r
t
y
in
d
iv
i
d
u
als
to
d
is
e
ase
class
if
icat
io
n
o
f
Alzh
eim
er
)
an
d
a
u
tis
m
b
r
ai
n
im
ag
in
g
d
ata
ex
c
h
an
g
e
(
A
B
I
DE
)
(
in
clu
d
in
g
o
n
e
th
o
u
s
an
d
in
d
i
v
id
u
als
f
o
r
Au
tis
m
class
if
icatio
n
)
b
r
ain
MRI
d
atasets
.
E
x
p
er
im
en
tal
r
esu
lts
s
h
o
wed
a
f
iv
e
-
f
o
ld
clas
s
if
icatio
n
ac
cu
r
ac
y
o
f
0
.
7
0
f
o
r
th
e
d
ataset
o
f
Au
tis
m
b
r
ain
im
ag
in
g
d
ata
ex
c
h
an
g
e
an
d
0
.
8
5
f
o
r
th
e
d
ataset
o
f
Alzh
eim
er
'
s
d
is
ea
s
e
Neu
r
o
im
ag
in
g
in
itiativ
e
.
T
h
o
s
e
r
eg
io
n
s
ar
e
i
n
ter
p
r
eted
as
b
r
ain
s
eg
m
en
ts
,
w
h
ich
3
D
-
C
NN
ty
p
ically
u
s
es
to
ex
tr
ac
t
f
ea
tu
r
es
to
class
if
y
b
r
ain
d
is
ea
s
es.
E
x
p
er
im
en
tal
r
esu
lts
s
h
o
wed
th
at
alo
n
g
with
in
ter
p
r
etab
ilit
y
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
Th
e
I
o
T
a
n
d
r
eg
is
tr
a
tio
n
o
f m
a
g
n
etic
r
eso
n
a
n
ce
ima
g
in
g
b
r
a
in
d
ia
g
n
o
s
is
b
a
s
ed
on
…
(
A
h
med
S
h
ih
a
b
A
h
me
d
)
275
m
o
d
el,
th
is
m
eth
o
d
in
cr
ea
s
es
th
e
class
if
icatio
n
m
o
d
el'
s
f
in
a
l
p
er
f
o
r
m
a
n
ce
in
n
u
m
b
e
r
o
f
c
ases
co
n
ce
r
n
in
g
th
e
p
ar
am
eter
s
o
f
t
h
e
m
o
d
el
Sajjad
et
a
l
.
[
30
]
i
n
tr
o
d
u
ce
d
m
u
lti
-
g
r
ad
e
b
r
ain
t
u
m
o
r
cla
s
s
if
icatio
n
s
y
s
tem
b
ased
C
N
N.
Firstl
y
:
s
eg
m
en
tin
g
tu
m
o
r
r
e
g
io
n
s
f
r
o
m
im
ag
es o
f
m
a
g
n
etic
r
eso
n
a
n
ce
im
ag
in
g
b
y
th
e
u
s
e
o
f
d
ee
p
lear
n
in
g
tech
n
iq
u
e.
Seco
n
d
ly
:
au
g
m
e
n
tin
g
d
ata
w
id
ely
ca
n
b
e
u
s
ed
to
tr
ain
th
e
s
y
s
tem
p
r
o
p
o
s
ed
in
o
r
d
er
to
av
o
id
an
y
p
r
o
b
lem
r
elate
d
to
lack
in
g
d
ata
wh
en
h
an
d
lin
g
with
MRI
to
class
if
y
m
u
lti
-
g
r
ad
e
d
b
r
ain
t
u
m
o
r
s
.
T
h
ir
d
ly
:
a
p
r
e
-
tr
ai
n
ed
C
NN
m
o
d
el
is
f
in
e
-
t
u
n
ed
u
s
i
n
g
a
u
g
m
en
te
d
d
ata
f
o
r
b
r
ain
tu
m
o
r
g
r
ad
e
class
if
icatio
n
.
T
h
ir
d
ly
,
C
NN
m
o
d
el
tr
ain
ed
in
ad
v
an
ce
is
f
in
e
-
tu
n
e
d
u
s
in
g
b
y
th
e
u
s
e
o
f
au
g
m
en
t
ed
d
ata
to
class
if
y
th
e
d
e
g
r
ee
o
f
b
r
ai
n
tu
m
o
r
.
C
h
an
g
et
a
l
.
[
3
1
]
i
n
f
o
r
m
atio
n
r
elate
d
to
MRI
an
d
m
o
lec
u
lar
d
ata,
f
o
r
2
5
9
p
atien
ts
,
f
r
o
m
ca
n
ce
r
im
ag
in
g
ar
ch
iv
es
wer
e
o
b
tain
ed
,
th
o
s
e
in
d
iv
id
u
als
wer
e
h
av
in
g
g
lio
m
a,
eith
er
h
ig
h
o
r
lo
w
-
g
r
ad
e.
C
NN
was
tr
ain
ed
f
o
r
class
if
y
in
g
1
p
/1
9
q
co
d
eletio
n
,
is
o
citr
ate
d
e
h
y
d
r
o
g
e
n
ase
1
(
I
DH1
)
m
u
tatio
n
s
tatu
s
,
an
d
O
6
-
m
eth
y
lg
u
a
n
in
e
-
DNA
m
eth
y
ltra
n
s
f
er
ase
(
MG
MT
)
p
r
o
m
o
te
r
h
y
p
er
m
eth
y
latio
n
s
tatu
s
.
Prin
cip
al
co
m
p
o
n
e
n
t
an
aly
s
is
o
f
t
h
e
f
i
n
al
co
n
v
o
l
u
tio
n
al
n
e
u
r
al
n
etwo
r
k
lay
er
was
u
s
ed
to
ex
tr
ac
t
th
e
k
ey
im
ag
in
g
f
ea
tu
r
es
t
o
class
if
y
ca
s
es
ac
cu
r
ately
.
R
esu
lts
:
th
e
p
r
o
ce
s
s
o
f
class
if
icati
o
n
is
h
ig
h
ly
ac
cu
r
ate:
I
DH1
m
u
tatio
n
s
tatu
s
,
9
4
%.
T
h
e
au
th
o
r
s
R
ah
m
an
et
a
l
.
[
3
2
]
i
m
p
lem
e
n
ted
I
o
T
t
o
f
ac
ilit
ate
f
ar
m
in
g
,
p
ar
ticu
la
r
ly
f
o
r
th
o
s
e
wh
o
wan
t
a
s
m
ar
t
ap
p
r
o
ac
h
t
o
ag
r
icu
ltu
r
e.
T
h
is
s
tu
d
y
f
o
c
u
s
es
o
n
r
e
al
-
tim
e
s
u
r
v
eillan
ce
with
th
e
lo
w
co
s
t
-
ef
f
ec
tiv
e
s
ec
u
r
ity
s
o
lu
tio
n
.
Ma
k
e
th
e
m
o
s
t
o
f
co
m
p
u
ter
r
eso
u
r
ce
s
s
u
c
h
en
cr
y
p
tio
n
an
d
d
ec
r
y
p
tio
n
tim
e,
b
atter
y
u
s
ag
e,
an
d
s
o
o
n
,
d
iv
id
e
th
e
d
ata
u
tili
ze
d
in
th
e
I
o
T
en
v
ir
o
n
m
en
t
in
to
th
r
ee
ca
teg
o
r
ies
o
f
s
en
s
itiv
ity
:
lo
w,
m
ed
iu
m
,
an
d
h
ig
h
s
en
s
itiv
e
d
ata
[
3
3
]
.
I
n
th
is
p
ap
er
,
a
f
r
am
ewo
r
k
is
p
r
o
v
id
ed
f
o
r
e
n
cr
y
p
tin
g
d
ata
b
a
s
ed
o
n
th
e
lev
el
o
f
s
en
s
itiv
ity
u
tili
zin
g
m
ac
h
in
e
lear
n
in
g
K
-
n
ea
r
est
n
eig
h
b
o
r
s
(
K
-
NN)
.
T
an
h
et
a
l
.
[
3
4
]
en
h
an
ce
d
s
ec
u
r
ity
p
r
o
to
co
ls
p
r
esen
ted
a
v
ia
b
le
s
o
lu
tio
n
f
o
r
co
m
p
r
eh
e
n
s
iv
e
p
r
o
tectio
n
o
f
I
o
T
s
y
s
tem
s
f
r
o
m
n
etwo
r
k
s
ec
u
r
ity
ass
au
lts
.
Alg
o
r
ith
m
ic
en
h
a
n
ce
m
en
t
f
av
o
r
ab
l
y
co
n
tr
ib
u
tes
t
o
th
is
cr
u
cial
wo
r
k
b
y
c
o
m
b
in
i
n
g
s
ec
u
r
ity
s
o
lu
tio
n
s
o
n
th
e
lev
els
o
f
t
h
e
I
o
T
with
co
d
e
o
p
tim
izatio
n
.
Als
o
,
en
h
an
ce
an
d
co
m
b
i
n
e
th
e
DT
L
S
Pro
to
co
l
with
th
e
o
v
er
h
ea
r
in
g
m
ec
h
an
is
m
,
an
d
t
h
en
c
o
n
d
u
ct
test
s
to
d
em
o
n
s
tr
ate
ef
f
ec
tiv
en
ess
,
f
ea
s
ib
ilit
y
,
c
o
s
t
-
ef
f
icien
cy
,
an
d
ap
p
licab
ilit
y
o
n
p
o
p
u
la
r
I
o
T
n
etwo
r
k
m
o
d
els.
Pre
s
en
ts
NB
-
I
o
T
test
in
g
ap
p
r
o
ac
h
t
h
at
is
tailo
r
ed
to
th
e
lo
ca
l
r
ad
io
n
etwo
r
k
p
lan
n
in
g
r
e
q
u
ir
em
en
ts
[
3
5
]
.
Ad
d
u
cin
g
th
e
m
ajo
r
f
in
d
in
g
s
ab
o
u
t
th
e
v
iab
ilit
y
o
f
em
p
lo
y
in
g
a
n
in
-
b
an
d
s
ce
n
a
r
io
f
o
r
d
ep
l
o
y
in
g
NB
-
I
o
T
o
v
er
a
4
G
n
etwo
r
k
in
a
s
u
b
u
r
b
a
n
s
ettin
g
b
ased
o
n
th
e
ac
q
u
ir
e
d
d
ata.
R
ajb
o
n
g
s
h
i
et
a
l
.
[
3
6
]
,
E
r
win
et
a
l
.
[
3
7
]
s
u
g
g
ested
d
if
f
er
e
n
t
ty
p
es
o
f
leaf
d
is
ea
s
es,
s
u
ch
as
an
th
r
ac
n
o
s
e,
g
all
m
ac
h
i,
p
o
w
d
er
y
m
ild
ew,
an
d
r
ed
r
u
s
t,
ar
e
em
p
lo
y
ed
in
th
e
d
ataset,
wh
ich
in
clu
d
es
1
5
0
0
p
h
o
to
s
o
f
d
am
a
g
ed
an
d
h
ea
lth
y
m
a
n
g
o
leav
es.
A
n
ew
ca
teg
o
r
y
h
as
b
ee
n
a
d
d
ed
t
o
th
e
d
ataset.
Als
o
lo
o
k
ed
at
th
e
o
v
er
all
p
er
f
o
r
m
an
ce
m
at
r
ices
an
d
d
is
co
v
er
ed
th
at
th
e
Den
s
eNe
t2
0
1
b
ea
ts
o
t
h
er
m
o
d
els
b
y
ac
h
iev
in
g
t
h
e
h
ig
h
est
a
cc
u
r
ac
y
o
f
9
8
.
0
0
%.
Fad
il
et
a
l
.
[
3
8
]
T
h
e
m
e
d
ical
im
ag
es
ar
e
en
h
a
n
ce
d
u
s
in
g
t
h
e
f
u
zz
y
C
-
m
ea
n
s
clu
s
ter
in
g
(
FC
M)
ap
p
r
o
ac
h
.
T
h
er
e
ar
e
two
s
tag
es
to
t
h
e
e
n
h
an
cin
g
p
r
o
ce
d
u
r
e.
On
t
h
e
p
ict
u
r
e
p
i
x
els,
th
e
s
u
g
g
ested
tech
n
iq
u
e
p
er
f
o
r
m
s
a
clu
s
ter
t
est.
T
h
e
d
i
f
f
er
en
ce
in
g
r
a
y
lev
el
b
etwe
en
t
h
e
v
a
r
io
u
s
item
s
i
s
th
en
in
c
r
ea
s
ed
t
o
ac
h
iev
e
th
e
m
e
d
ical
p
ictu
r
e
e
n
h
an
cin
g
g
o
al.
Var
io
u
s
p
h
o
t
o
s
wer
e
u
s
ed
to
test
th
e
ex
p
e
r
im
e
n
tal
o
u
tco
m
es.
3.
T
H
E
P
RO
P
O
SE
D
M
O
D
E
L
CO
M
P
O
NE
N
T
S O
F
M
RI B
RAIN D
I
AG
NO
SI
S
I
n
th
is
p
r
o
p
o
s
ed
wo
r
k
,
th
e
g
en
etic
alg
o
r
ith
m
a
n
d
C
NN
ar
e
u
s
ed
to
d
eter
m
in
e
th
e
b
r
ain
tu
m
o
r
class
if
icatio
n
b
ased
o
n
th
e
p
r
in
cip
le
o
f
r
eg
is
tr
atio
n
an
d
th
is
is
ac
h
iev
ed
b
y
lo
ad
in
g
th
e
(
s
o
u
r
ce
an
d
r
ef
e
r
en
ce
)
im
ag
e.
Af
ter
th
at,
im
ag
e
is
p
r
o
ce
s
s
ed
in
r
e
g
ar
d
with
s
m
o
o
th
in
g
,
r
ed
u
cin
g
n
o
is
e,
b
y
u
s
in
g
Gau
s
s
ian
f
ilter
.
Gen
etic
alg
o
r
ith
m
is
also
ap
p
lied
to
ac
h
iev
e
th
e
p
r
in
cip
le
o
f
r
e
g
is
tr
atio
n
,
th
en
,
C
NN
is
u
s
ed
to
class
if
y
th
e
b
r
ain
tu
m
o
r
.
E
v
e
n
tu
ally
,
s
en
d
in
g
a
m
ass
ag
e
to
a
p
atien
t
ex
p
lain
in
g
th
e
t
u
m
o
r
g
r
a
d
e
d
ep
en
d
in
g
o
n
GSM
A
r
d
u
in
o
t
o
ac
h
iev
e
t
h
e
p
r
i
n
cip
le
o
f
I
o
T
,
as sh
o
wn
in
Fig
u
r
e
1
an
d
Fig
u
r
e
2
.
Fig
u
r
e
1
.
Descr
ib
e
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
o
f
wo
r
k
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
25
,
No
.
1
,
J
an
u
ar
y
20
22
:
273
-
2
8
0
276
Fig
u
r
e
2
.
T
h
e
wo
r
k
f
lo
w
o
f
M
R
I
b
r
ain
d
iag
n
o
s
is
4.
M
RI
B
RA
I
N
DIAG
NO
SI
S S
YST
E
M
I
M
P
L
E
M
E
NT
AT
I
O
N
T
h
is
wo
r
k
p
r
o
p
o
s
ed
t
h
e
au
to
m
atic
m
o
d
el
to
d
etec
t
th
e
b
r
a
in
tu
m
o
r
a
n
d
s
en
d
a
m
ess
ag
e
to
p
atien
t,
th
at
ca
n
ac
h
ie
v
ed
b
y
u
s
in
g
MA
T
L
AB
2
0
2
0
a
an
d
Ar
d
u
in
o
with
GSM8
0
8
0
.
I
t
u
s
es
d
atab
ase
f
r
o
m
Me
d
ical
C
ity
Ho
s
p
ital
in
B
ag
h
d
ad
,
f
o
r
8
0
p
atien
ts
,
(
8
0
0
)
im
ag
es
ar
e
d
iag
n
o
s
ed
t
o
two
class
es
n
o
r
m
al
5
5
p
e
r
s
o
n
s
an
d
3
5
p
atien
ts
.
T
h
e
s
o
u
r
ce
im
ag
e
an
d
r
ef
er
en
ce
im
ag
e
a
r
e
lo
ad
ed
as
s
h
o
wn
in
Fig
u
r
e
3
,
th
e
g
en
etic
alg
o
r
ith
m
is
ap
p
lied
to
ac
h
iev
e
th
e
r
eg
is
tr
a
tio
n
,
th
en
th
e
o
u
tp
u
t
o
f
g
e
n
etic
alg
o
r
ith
m
is
s
u
b
tr
ac
te
d
f
r
o
m
s
o
u
r
ce
MRI
im
ag
e
th
en
,
th
e
d
atab
ase
is
d
iv
id
ed
to
8
0
tr
ain
in
g
an
d
2
0
test
in
g
b
ased
o
n
cr
o
s
s
-
v
alid
atio
n
.
I
n
a
d
d
itio
n
to
,
th
e
C
NN
is
ap
p
li
ed
to
class
if
y
th
e
im
ag
e
an
d
s
en
d
it to
p
atien
t b
y
GSM
as sh
o
wn
,
in
F
ig
u
r
e
s
3
-
5
.
Fig
u
r
e
3
.
T
h
e
Gu
i o
f
M
atlab
s
h
o
w
th
e
r
esu
lt o
f
p
r
o
p
o
s
ed
w
o
r
k
Fig
u
r
e
4
.
T
h
e
Ar
d
u
in
o
a
n
d
GS
M
ar
e
co
n
n
ec
ted
to
Ma
tlab
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
Th
e
I
o
T
a
n
d
r
eg
is
tr
a
tio
n
o
f m
a
g
n
etic
r
eso
n
a
n
ce
ima
g
in
g
b
r
a
in
d
ia
g
n
o
s
is
b
a
s
ed
on
…
(
A
h
med
S
h
ih
a
b
A
h
me
d
)
277
Fig
u
r
e
5
.
T
h
e
m
ess
ag
e
s
en
t to
p
atien
t
T
h
e
C
N
N
t
r
a
i
n
i
n
g
m
o
d
e
l
i
s
i
n
t
r
o
d
u
c
e
d
,
t
h
e
v
o
l
u
m
e
o
f
e
n
t
e
r
e
d
M
R
I
i
s
1
0
0
*
1
0
0
*
3
1
,
a
n
d
t
r
a
i
n
i
n
g
s
e
t
u
p
o
f
C
N
N
w
o
r
k
s
,
a
s
s
h
o
w
n
h
e
r
e
,
m
o
m
e
n
t
u
m
i
s
0
.
9
a
n
d
l
e
a
r
n
i
n
g
r
a
t
e
i
s
0
.
0
0
1
a
n
d
t
h
e
a
r
c
h
i
t
e
c
t
u
r
e
o
f
n
e
t
w
o
r
k
i
s
c
o
m
p
o
s
e
d
4
p
o
o
l
i
n
g
l
a
y
e
r
s
a
n
d
4
c
o
n
v
o
l
u
t
i
o
n
l
a
y
e
r
s
a
n
d
,
t
w
o
f
u
l
l
y
c
o
n
n
e
c
t
e
d
l
a
y
e
r
s
f
o
l
l
o
w
t
h
o
s
e
l
a
y
e
r
s
.
A
R
e
l
u
l
a
y
e
r
c
o
m
e
s
a
f
t
e
r
a
c
o
n
v
o
l
u
t
i
o
n
l
a
y
e
r
,
a
n
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
f
o
r
i
m
p
r
o
v
i
n
g
t
h
e
C
N
N
s
p
e
r
f
o
r
m
a
n
c
e
.
I
n
t
h
e
n
e
t
w
o
r
k
t
r
a
i
n
i
n
g
,
r
e
g
u
l
a
r
i
z
a
t
i
o
n
w
i
t
h
t
h
e
w
e
i
g
h
t
d
e
c
a
y
f
i
v
e
×
t
e
n
−
f
o
u
r
w
a
s
u
s
e
d
.
I
n
i
t
i
a
l
l
y
,
t
h
e
l
e
a
r
n
i
n
g
r
a
t
e
w
a
s
s
e
t
t
o
0
.
0
0
1
,
t
h
e
t
r
a
i
n
i
n
g
w
a
s
s
t
o
p
p
e
d
a
f
t
e
r
1
0
0
0
e
p
o
c
h
,
a
n
d
t
h
e
d
r
o
p
o
u
t
r
a
t
i
o
w
a
s
s
e
t
t
o
z
e
r
o
.
0
,
a
s
s
h
o
w
n
i
n
T
a
b
l
e
1
.
T
ab
le
1
.
An
aly
s
is
r
esu
lt o
f
C
N
N
m
o
d
el
La
y
e
r
N
a
me
A
c
t
i
v
a
t
i
o
n
s
Le
a
r
n
a
b
l
e
1
I
mag
e
i
n
p
u
t
1
0
0
*
1
0
0
*
1
-
2
C
o
n
v
o
l
u
t
i
o
n
1
9
6
*
9
6
*
1
W
e
i
g
h
t
5
*
5
*
1
*
2
0
,
B
i
a
s
1
*
1
*
2
0
3
R
e
l
u
1
9
6
*
9
6
*
1
-
4
P
o
o
l
m
a
x
1
4
8
*
4
8
*
2
0
-
5
C
o
n
v
o
l
u
t
i
o
n
2
4
4
*
4
4
*
2
0
W
e
i
g
h
t
5
*
5
*
2
0
*
2
0
B
i
a
s
1
*
1
*
2
0
6
R
e
l
u
2
4
4
*
4
4
*
2
0
-
7
P
o
o
l
m
a
x
2
2
2
*
2
2
*
2
0
-
8
F
u
l
l
y
C
o
n
n
e
c
t
e
d
La
y
e
r
1
*
1
*
1
0
2
4
-
9
F
u
l
l
y
C
o
n
n
e
c
t
e
d
La
y
e
r
1
*
1
*
2
5
6
-
10
F
u
l
l
y
C
o
n
n
e
c
t
e
d
La
y
e
r
1
*
1
*
2
-
11
S
o
f
t
M
a
x
L
a
y
e
r
1
*
1
*
2
-
12
C
l
a
s
si
f
i
c
a
t
i
o
n
La
y
e
r
-
-
Af
ter
b
u
ild
in
g
th
e
n
etwo
r
k
ar
ch
itectu
r
e
as
s
h
o
wn
in
T
ab
le
2
,
th
e
h
y
b
r
i
d
Ma
m
d
a
n
i
f
u
zz
y
an
d
C
NN
tr
ain
m
o
d
el
s
tar
ts
in
ep
o
c
h
(
1
)
,
th
e
p
ar
a
m
eter
o
f
E
lap
s
ed
tim
e
is
2
s
ec
o
n
d
,
p
a
r
am
eter
o
f
ac
cu
r
ac
y
is
2
8
.
1
3
%
an
d
th
e
p
ar
a
m
eter
o
f
m
i
n
i b
atc
h
lo
s
s
is
1
.
4
1
4
9
.
At
th
e
ep
o
ch
14
th
e
p
ar
a
m
eter
o
f
ac
c
u
r
ac
y
r
ea
ch
ed
to
9
2
.
1
9
%,
p
ar
am
eter
o
f
m
i
n
i
b
atch
lo
s
s
0
.
2
0
2
4
an
d
th
e
elap
s
ed
tim
e
i
s
0
5
:4
1
m
in
u
te.
At
th
e
ep
o
c
h
28
th
e
p
ar
am
eter
o
f
ac
cu
r
ac
y
r
ea
ch
ed
to
9
9
.
2
2
%,
p
ar
am
eter
o
f
m
in
i
b
atc
h
lo
s
s
0
.
0
5
7
6
a
n
d
t
h
e
elap
s
ed
tim
e
i
s
1
1
:0
8
m
in
u
te
.
At
th
e
ep
o
c
h
4
1
th
e
p
ar
a
m
eter
o
f
ac
cu
r
ac
y
r
ea
ch
ed
to
1
0
0
%,
p
ar
am
eter
o
f
m
in
i
b
atch
lo
s
s
0
.
0
0
2
1
an
d
th
e
elap
s
ed
tim
e
is
1
6
.
3
2
m
in
u
te.
Af
ter
tr
ain
in
g
th
e
m
o
d
els
f
o
r
r
ec
o
g
n
itio
n
o
f
a
b
r
ain
t
u
m
o
r
,
th
e
class
if
icatio
n
r
esu
lts
ar
e
as
s
h
o
wn
in
T
ab
le
3
,
a
d
etailed
class
if
icati
o
n
o
f
th
e
test
s
am
p
les
is
li
s
te
d
.
T
h
e
tr
u
e
an
d
r
ef
er
e
n
ce
co
l
u
m
n
s
r
ep
r
e
s
en
t
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
25
,
No
.
1
,
J
an
u
ar
y
20
22
:
273
-
2
8
0
278
tr
u
e
s
itu
atio
n
,
wh
ile
th
e
r
o
w
v
alu
es
ar
e
th
e
p
r
e
d
icted
tr
u
e,
th
e
m
o
d
el
o
r
th
e
m
o
d
el
h
as
to
p
r
ed
ict
f
alse
as
s
h
o
wn
in
T
ab
le
3
.
I
n
T
ab
le
4
p
r
esen
t th
e
co
m
p
a
r
e
th
e
p
r
o
p
o
s
ed
wo
r
k
with
o
th
er
r
esear
ch
er
.
T
ab
le
2
.
S
h
o
w
t
h
e
tr
ain
o
n
C
NN
Ep
o
c
h
I
t
e
r
a
t
i
o
n
Ti
me
El
a
p
se
d
(
h
h
:
mm
:
ss
)
M
i
n
i
-
b
a
t
c
h
A
c
c
u
r
a
c
y
M
i
n
i
-
b
a
t
c
h
l
o
ss
B
a
se
Le
a
r
n
i
n
g
R
a
t
e
1
1
0
0
:
0
0
:
0
2
2
8
.
1
3
%
1
.
4
1
4
9
0
.
0
0
1
0
5
50
0
0
:
0
1
:
5
2
4
6
.
0
6
%
0
.
9
0
8
8
0
.
0
0
1
0
10
1
0
0
0
0
:
0
3
:
4
3
8
4
.
3
8
%
0
.
4
8
0
4
0
.
0
0
1
0
14
1
5
0
0
0
:
0
5
:
4
1
9
2
.
1
9
%
0
.
2
0
2
4
0
.
0
0
1
0
19
2
0
0
0
0
:
0
7
:
3
2
9
8
.
4
4
%
0
.
1
1
0
2
0
.
0
0
1
0
23
2
5
0
0
0
:
0
9
:
2
0
8
6
.
7
2
%
0
.
3
9
2
8
0
.
0
0
1
0
28
3
0
0
0
0
:
1
1
:
0
8
9
9
.
2
2
%
0
.
0
5
7
6
0
.
0
0
1
0
32
3
5
0
0
0
:
1
2
:
5
6
1
0
0
.
0
0
%
0
.
0
9
3
6
0
.
0
0
1
0
37
4
0
0
0
0
:
1
4
:
4
4
1
0
0
.
0
0
%
0
.
0
3
6
1
0
.
0
0
1
0
41
4
5
0
0
0
:
1
6
:
3
2
1
0
0
.
0
0
%
0
.
0
0
2
1
0
.
0
0
1
0
46
5
0
0
0
0
:
1
8
:
2
0
1
0
0
.
0
0
%
0
.
0
0
0
3
0
.
0
0
1
0
50
5
5
0
0
0
:
2
0
:
0
3
1
0
0
.
0
0
%
0
.
0
0
0
5
0
.
0
0
1
0
55
6
0
0
0
0
:
2
1
:
4
6
1
0
0
.
0
0
%
0
.
0
0
0
3
0
.
0
0
1
0
60
6
5
0
0
0
:
2
3
:
4
1
1
0
0
.
0
0
%
0
.
0
0
0
3
0
.
0
0
1
0
64
7
0
0
0
0
:
2
5
:
3
9
1
0
0
.
0
0
%
0
.
0
0
0
2
0
.
0
0
1
0
69
7
5
0
0
0
:
2
7
:
3
1
1
0
0
.
0
0
%
0
.
0
0
0
2
0
.
0
0
1
0
73
8
0
0
0
0
:
2
9
:
2
4
1
0
0
.
0
0
%
0
.
0
0
0
3
0
.
0
0
1
0
78
8
5
0
0
0
:
3
1
:
1
8
1
0
0
.
0
0
%
0
.
0
0
0
2
0
.
0
0
1
0
82
9
0
0
0
0
:
3
3
:
1
2
1
0
0
.
0
0
%
0
.
0
0
0
2
0
.
0
0
1
0
N
o
t
e
d
:
Tr
a
i
n
i
n
g
o
n
s
i
n
g
l
e
C
P
U
I
n
i
t
i
a
l
i
z
a
t
i
o
n
i
m
a
g
e
n
o
r
m
a
l
i
z
a
t
i
o
n
T
ab
le
3
.
T
est
p
h
ase
s
tatis
tic
m
ea
s
u
r
es
f
o
r
th
e
C
NN
S
t
a
t
i
st
i
c
D
e
scri
p
t
i
o
n
C
N
N
A
c
c
u
r
a
c
y
R
a
t
e
o
f
c
o
r
r
e
c
t
l
y
p
r
e
d
i
c
t
e
d
A
C
C
=
TP+
TN
/
(
TP+
TN
+
F
P
+
F
N
)
9
8
.
8
8
%
Tr
u
e
p
o
si
t
i
v
e
N
u
mb
e
r
o
f
c
o
r
r
e
c
t
l
y
p
r
e
d
i
c
t
e
d
.
55
Tr
u
e
N
e
g
a
t
i
v
e
N
u
mb
e
r
o
f
ma
l
i
c
i
o
u
s
o
b
j
e
c
t
w
h
i
c
h
a
r
e
c
o
r
r
e
c
t
l
y
c
l
a
ssi
f
i
e
d
34
F
a
l
se
p
o
si
t
i
v
e
N
u
mb
e
r
o
f
i
n
c
o
r
r
e
c
t
l
y
p
r
e
d
i
c
t
e
d
0
F
a
l
se
N
e
g
a
t
i
v
e
N
u
mb
e
r
o
f
ma
l
i
c
i
o
u
s
o
b
j
e
c
t
w
h
i
c
h
a
r
e
i
n
c
o
r
r
e
c
t
l
y
p
r
e
d
i
c
t
e
d
4
M
i
s
c
l
a
ssi
f
i
c
a
t
i
o
n
R
a
t
e
t
h
e
p
e
r
c
e
n
t
a
g
e
o
f
i
n
c
o
r
r
e
c
t
l
y
p
r
e
d
i
c
t
e
d
M
i
s
c
l
a
ssi
f
i
c
a
t
i
o
n
R
a
t
e
=
(
F
P
+
F
N
)
/
t
o
t
a
l
1
.
1
2
S
p
e
c
i
f
i
c
i
t
y
c
a
l
c
u
l
a
t
e
d
a
s t
h
e
n
u
m
b
e
r
o
f
c
o
r
r
e
c
t
n
e
g
a
t
i
v
e
p
r
e
d
i
c
t
i
o
n
s
S
p
e
c
i
f
i
c
i
t
y
=
TN
/
(
T
N
+
F
P
)
0
.
9
8
1
4
P
r
e
c
i
s
i
o
n
c
a
l
c
u
l
a
t
e
d
a
s t
h
e
n
u
m
b
e
r
o
f
c
o
r
r
e
c
t
p
o
si
t
i
v
e
P
r
e
c
i
s
i
o
n
=
TP
/
(
TP+F
P
)
1
T
ab
le
4
.
C
o
m
p
a
r
e
th
e
p
r
o
p
o
s
ed
wo
r
k
with
o
th
er
wo
r
k
A
u
t
h
o
r
A
c
c
u
r
a
c
y
M
e
t
h
o
d
s
A
n
a
r
a
k
i
e
t
a
l
.
[
2
8
]
9
4
.
2
%
GA
-
C
N
N
Za
c
h
a
r
a
k
i
e
t
a
l
.
[
3
9
]
8
5
%
S
v
m+
K
n
n
C
h
e
n
g
e
t
a
l
.
[
4
0
]
9
1
.
2
8
%
S
v
m+
K
n
n
P
a
u
l
e
t
a
l
.
[
4
1
]
9
1
.
4
3
%
C
N
N
A
f
sh
a
r
e
t
a
l
.
[
4
2
]
9
0
.
8
9
%
C
N
N
Er
t
o
s
u
n
a
n
d
R
u
b
i
n
[
4
3
]
9
6
%
C
N
N
S
u
l
t
a
n
e
t
a
l
.
[
4
4
]
9
6
.
1
3
C
N
N
C
h
a
n
d
r
a
a
n
d
B
a
j
p
a
i
[
4
5
]
-
f
r
a
c
t
i
o
n
a
l
f
i
l
t
e
r
(
mas
k
d
e
s
i
g
n
)
f
o
r
b
e
n
i
g
n
b
r
a
i
n
t
u
m
o
r
d
e
t
e
c
t
i
o
n
S
w
a
t
i
e
t
a
l
.
[
4
6
]
9
4
.
8
2
%
p
r
e
-
t
r
a
i
n
e
d
d
e
e
p
C
N
N
m
o
d
e
l
a
n
d
p
r
o
p
o
s
e
a
b
l
o
c
k
-
w
i
se
f
i
n
e
-
t
u
n
i
n
g
st
r
a
t
e
g
y
b
a
s
e
d
o
n
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
P
r
o
p
o
se
d
w
o
r
k
9
8
.
8
%
G
e
n
e
t
i
c
A
l
g
o
r
i
t
h
m
a
n
d
C
o
n
v
o
l
u
t
i
o
n
N
e
u
r
a
l
N
e
t
w
o
r
k
5.
CO
NCLU
SI
O
N
T
h
is
wo
r
k
p
r
o
p
o
s
es
b
u
ild
in
g
au
to
m
atic
I
o
T
to
d
etec
t
an
d
cl
ass
if
y
b
r
ain
MRI
b
ased
o
n
d
e
ep
lear
n
in
g
an
d
a
r
d
u
in
o
GSM.
Mo
r
eo
v
er
,
th
e
p
r
in
ci
p
le
o
f
r
eg
is
tr
atio
n
is
ap
p
lied
to
MRI
u
s
in
g
g
e
n
etic
alg
o
r
ith
m
,
as
f
o
llo
win
g
,
r
ea
d
in
g
t
h
e
s
o
u
r
ce
im
ag
e
an
d
l
o
ad
in
g
th
e
r
ef
e
r
e
n
ce
m
ag
e,
r
ed
u
cin
g
th
e
n
o
is
e
o
f
MRI
im
ag
e
b
y
b
ilater
al
f
ilter
,
th
e
g
e
n
etic
al
g
o
r
ith
m
is
ap
p
lied
to
o
b
tain
t
h
e
b
est
f
u
s
io
n
im
ag
e
f
r
o
m
s
o
u
r
ce
an
d
r
ef
e
r
en
ce
im
ag
e,
co
m
p
u
tin
g
th
e
s
im
ilar
ly
b
y
s
u
b
tr
ac
tin
g
th
e
r
esu
lt o
f
r
eg
is
tr
atio
n
im
ag
e
to
g
et
th
e
b
est f
ea
t
u
r
e
o
f
im
ag
e,
C
NN
is
ap
p
lied
to
class
if
y
b
r
ain
tu
m
o
r
,
a
n
d
s
en
d
in
g
m
ess
ag
e
to
p
atien
t
b
y
GSM.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
Th
e
I
o
T
a
n
d
r
eg
is
tr
a
tio
n
o
f m
a
g
n
etic
r
eso
n
a
n
ce
ima
g
in
g
b
r
a
in
d
ia
g
n
o
s
is
b
a
s
ed
on
…
(
A
h
med
S
h
ih
a
b
A
h
me
d
)
279
test
ed
o
n
MRI
Me
d
ical
C
ity
Ho
s
p
ital
in
B
ag
h
d
ad
,
d
atab
ase
co
n
s
is
ts
o
f
5
5
0
n
o
r
m
al
an
d
3
5
0
ab
n
o
r
m
al
im
ag
es
an
d
s
p
lit to
8
0
% tr
ain
in
g
an
d
2
0
test
in
g
,
th
e
p
r
o
p
o
s
ed
m
o
d
e
l r
esu
lt a
ch
iev
es th
e
9
8
.
8
% a
c
cu
r
ac
y
.
I
n
th
e
f
u
tu
r
e
wo
r
k
we
ca
n
ap
p
l
y
th
e
I
o
T
t
ec
h
n
iq
u
e
an
d
r
e
g
is
tr
atio
n
o
f
s
k
in
ca
n
ce
r
b
ased
o
n
K
-
m
ea
n
s
clu
s
ter
an
d
s
el
f
o
r
g
an
izin
g
m
ap
s
b
y
u
s
in
g
a
d
a
ta
s
et
o
f
m
ed
ical
im
ag
es.
RE
F
E
R
E
NC
E
S
[
1
]
H
.
Z
a
i
d
i
a
n
d
I
.
E
l
N
a
q
a
,
“
P
E
T
-
g
u
i
d
e
d
d
e
l
i
n
e
a
t
i
o
n
o
f
r
a
d
i
a
t
i
o
n
t
h
e
r
a
p
y
t
r
e
a
t
m
e
n
t
v
o
l
u
m
e
s
:
a
s
u
r
v
e
y
o
f
i
m
a
g
e
s
e
g
m
e
n
t
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
,
”
E
u
r
o
p
e
a
n
j
o
u
r
n
a
l
o
f
n
u
c
l
e
a
r
m
e
d
i
c
i
n
e
a
n
d
m
o
l
e
c
u
l
a
r
i
m
a
g
i
n
g
,
v
o
l
.
3
7
,
n
o
.
1
1
,
p
p
.
2
1
6
5
-
2
1
8
7
,
2
0
1
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
2
5
9
-
0
1
0
-
1
4
2
3
-
3
.
[
2
]
N
.
P
r
a
sat
h
,
V
.
P
a
n
d
i
,
S
.
M
a
n
i
c
k
a
v
a
sa
g
a
m
,
a
n
d
P
.
R
a
m
a
d
o
ss,
“
A
c
o
m
p
a
r
a
t
i
v
e
a
n
d
c
o
m
p
r
e
h
e
n
s
i
v
e
st
u
d
y
o
f
p
r
e
d
i
c
t
i
o
n
o
f
P
a
r
k
i
n
s
o
n
'
s
d
i
s
e
a
se
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
3
,
n
o
.
3
,
p
p
.
1
7
4
8
-
1
7
6
0
,
S
e
p
t
e
mb
e
r
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
2
3
.
i
3
.
p
p
1
7
4
8
-
1
7
6
0
.
[
3
]
S.
M
i
t
r
a
a
n
d
B.
U.
S
h
a
n
k
a
r
,
“
M
e
d
i
c
a
l
i
m
a
g
e
a
n
a
l
y
s
i
s
f
o
r
c
a
n
c
e
r
ma
n
a
g
e
m
e
n
t
in
n
a
t
u
r
a
l
c
o
mp
u
t
i
n
g
f
r
a
me
w
o
r
k
,
”
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
306
,
p
p
.
1
1
1
-
1
3
1
,
S
e
p
t
.
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
s.
2
0
1
5
.
0
2
.
0
1
5
.
[
4
]
A.
A.
A
b
b
o
o
d
,
Q.
M.
S
h
a
l
l
a
l
,
a
n
d
M.
A.
F
a
d
h
e
l
,
“
A
u
t
o
m
a
t
e
d
b
r
a
i
n
t
u
mo
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
v
a
r
i
o
u
s
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s
:
A
c
o
m
p
a
r
a
t
i
v
e
s
t
u
d
y
,
”
I
n
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
of
El
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
2
,
n
o
.
1,
p
p
.
252
-
2
5
9
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
2
2
.
i
1
.
p
p
2
5
2
-
2
5
9
.
[
5
]
R.
S
i
n
g
h
a
n
d
A.
K
h
a
r
e
,
“
F
u
s
i
o
n
of
mu
l
t
i
m
o
d
a
l
me
d
i
c
a
l
i
ma
g
e
s
u
s
i
n
g
D
a
u
b
e
c
h
i
e
s
c
o
m
p
l
e
x
w
a
v
e
l
e
t
t
r
a
n
sf
o
r
m
–
A
m
u
l
t
i
r
e
s
o
l
u
t
i
o
n
a
p
p
r
o
a
c
h
,
”
I
n
f
o
rm
a
t
i
o
n
f
u
si
o
n
,
v
o
l
.
1
9
,
p
p
.
49
-
60
,
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
f
f
u
s.
2
0
1
2
.
0
9
.
0
0
5
.
[
6
]
N.
H.
I.
M.
Z
a
i
h
a
n
i
,
R.
R
o
sl
a
n
,
Z.
I
b
r
a
h
i
m,
a
n
d
K.
A.
F.
A.
S
a
ma
h
,
“
A
u
t
o
ma
t
e
d
se
g
m
e
n
t
a
t
i
o
n
a
n
d
d
e
t
e
c
t
i
o
n
of
T1
-
w
e
i
g
h
t
e
d
mag
n
e
t
i
c
r
e
s
o
n
a
n
c
e
i
m
a
g
i
n
g
b
r
a
i
n
i
mag
e
s
of
g
l
i
o
m
a
b
r
a
i
n
t
u
mo
r
,
”
Bu
l
l
e
t
i
n
of
E
l
e
c
t
ri
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
9,
n
o
.
3,
p
p
.
1
0
3
2
-
1
0
3
7
,
J
u
n
e
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
e
e
i
.
v
9
i
3
.
2
0
7
9
.
[
7
]
V.
L
a
u
r
e
n
t
,
G.
T
r
a
u
s
c
h
,
O.
B
r
u
o
t
,
P.
O
l
i
v
i
e
r
,
J.
F
e
l
b
l
i
n
g
e
r
,
a
n
d
D.
R
é
g
e
n
t
,
“
C
o
m
p
a
r
a
t
i
v
e
s
t
u
d
y
of
t
w
o
w
h
o
l
e
-
b
o
d
y
i
m
a
g
i
n
g
t
e
c
h
n
i
q
u
e
s
in
t
h
e
c
a
s
e
of
m
e
l
a
n
o
m
a
m
e
t
a
s
t
a
s
e
s
:
a
d
v
a
n
t
a
g
e
s
of
m
u
l
t
i
-
c
o
n
t
r
a
s
t
M
R
I
e
x
a
m
i
n
a
t
i
o
n
i
n
c
l
u
d
i
n
g
a
d
i
f
f
u
s
i
o
n
-
w
e
i
g
h
t
e
d
s
e
q
u
e
n
c
e
in
c
o
m
p
a
r
i
s
o
n
w
i
t
h
P
E
T
-
C
T
,
”
E
u
r
o
p
e
a
n
j
o
u
r
n
a
l
of
r
a
d
i
o
l
o
g
y
,
v
o
l
.
7
5
,
n
o
.
3,
pp.
376
-
3
8
3
,
2
0
1
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
j
r
a
d
.
2
0
0
9
.
0
4
.
0
5
9
.
[
8
]
J.
L.
E
l
ma
n
,
“
On
t
h
e
m
e
a
n
i
n
g
of
w
o
r
d
s
a
n
d
d
i
n
o
sa
u
r
b
o
n
e
s
:
Le
x
i
c
a
l
k
n
o
w
l
e
d
g
e
w
i
t
h
o
u
t
a
l
e
x
i
c
o
n
,
”
C
o
g
n
i
t
i
v
e
sci
e
n
c
e
,
v
o
l
.
3
3
,
n
o
.
4,
p
p
.
5
4
7
-
5
8
2
,
2
0
0
9
,
d
o
i
:
1
0
.
1
1
1
1
/
j
.
1
5
5
1
-
6
7
0
9
.
2
0
0
9
.
0
1
0
2
3
.
x
.
[
9
]
N.
H.
R.
A
z
a
mi
n
,
M.
N.
Ta
i
b
,
A.
H.
Jah
i
d
i
n
,
D.
S.
A
w
a
n
g
,
a
n
d
M.
S.
A.
M.
A
l
i
,
“
IQ
l
e
v
e
l
p
r
e
d
i
c
t
i
o
n
a
n
d
c
r
o
s
s
-
r
e
l
a
t
i
o
n
a
l
a
n
a
l
y
si
s
w
i
t
h
p
e
r
c
e
p
t
u
a
l
a
b
i
l
i
t
y
u
si
n
g
EEG
-
b
a
sed
S
V
M
c
l
a
ssi
f
i
c
a
t
i
o
n
mo
d
e
l
,
”
I
AE
S
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
of
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
8,
n
o
.
4,
p
p
.
4
3
6
-
4
4
2
,
D
e
c
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
8
.
i
4
.
p
p
4
3
6
-
4
4
2
.
[
1
0
]
K.
K.
B
r
o
c
k
,
S.
M
u
t
i
c
,
T.
R.
M
c
N
u
t
t
,
H.
Li
,
a
n
d
M.
L.
K
e
ssl
e
r
,
“
U
s
e
of
i
m
a
g
e
r
e
g
i
st
r
a
t
i
o
n
a
n
d
f
u
si
o
n
a
l
g
o
r
i
t
h
ms
a
n
d
t
e
c
h
n
i
q
u
e
s
in
r
a
d
i
o
t
h
e
r
a
p
y
:
r
e
p
o
r
t
of
t
h
e
A
A
P
M
R
a
d
i
a
t
i
o
n
T
h
e
r
a
p
y
C
o
mm
i
t
t
e
e
Ta
s
k
G
r
o
u
p
n
o
.
1
3
2
,
”
Me
d
i
c
a
l
p
h
y
s
i
c
s
,
v
o
l
.
4
4
,
n
o
.
7,
p
p
.
e
4
3
-
e
7
6
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
0
2
/
mp
.
1
2
2
5
6
.
[
1
1
]
S.
I
b
r
a
h
i
m,
N.
E.
A.
K
h
a
l
i
d
,
a
n
d
M.
M
a
n
a
f
,
“
C
A
P
S
O
C
A
:
H
y
b
r
i
d
t
e
c
h
n
i
q
u
e
f
o
r
n
o
s
o
l
o
g
i
c
se
g
m
e
n
t
a
t
i
o
n
of
p
r
i
m
a
r
y
b
r
a
i
n
t
u
m
o
r
s,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
of
E
l
e
c
t
r
i
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
6
,
n
o
.
1,
p
p
.
2
6
7
-
2
7
4
,
O
c
t
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
1
6
.
i
1
.
p
p
2
6
7
-
2
7
4
.
[
1
2
]
D.
M
a
t
t
e
s
,
D.
R.
H
a
y
n
o
r
,
H.
V
e
ss
e
l
l
e
,
T.
K.
Le
w
e
l
l
e
n
,
a
n
d
W.
E
u
b
a
n
k
,
"
P
ET
-
CT
i
m
a
g
e
r
e
g
i
st
r
a
t
i
o
n
in
t
h
e
c
h
e
st
u
s
i
n
g
f
r
e
e
-
f
o
r
m
d
e
f
o
r
mat
i
o
n
s
,
"
in
I
EE
E
T
r
a
n
s
a
c
t
i
o
n
s
on
M
e
d
i
c
a
l
I
m
a
g
i
n
g
,
v
o
l
.
2
2
,
n
o
.
1,
p
p
.
1
2
0
-
1
2
8
,
Ja
n
.
2
0
0
3
,
d
o
i
:
1
0
.
1
1
0
9
/
T
M
I
.
2
0
0
3
.
8
0
9
0
7
2
.
[
1
3
]
J.
P.
W.
P
l
u
i
m,
J.
B.
A.
M
a
i
n
t
z
,
a
n
d
M.
A.
V
i
e
r
g
e
v
e
r
,
"
M
u
t
u
a
l
-
i
n
f
o
r
ma
t
i
o
n
-
b
a
s
e
d
r
e
g
i
st
r
a
t
i
o
n
of
me
d
i
c
a
l
i
m
a
g
e
s
:
a
s
u
r
v
e
y
,
"
in
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
on
M
e
d
i
c
a
l
I
m
a
g
i
n
g
,
v
o
l
.
2
2
,
n
o
.
8,
p
p
.
986
-
1
0
0
4
,
A
u
g
.
2
0
0
3
,
d
o
i
:
1
0
.
1
1
0
9
/
T
M
I
.
2
0
0
3
.
8
1
5
8
6
7
.
[
1
4
]
S.
A
b
d
e
l
a
z
i
z
a
n
d
S.
L
u
,
“
K
-
me
a
n
s
a
l
g
o
r
i
t
h
m
w
i
t
h
l
e
v
e
l
s
e
t
f
o
r
b
r
a
i
n
t
u
mo
r
se
g
me
n
t
a
t
i
o
n
,
”
I
n
d
o
n
e
s
i
a
n
J
o
u
rn
a
l
of
El
e
c
t
ri
c
a
l
En
g
i
n
e
e
ri
n
g
and
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
5
,
n
o
.
2,
p
p
.
9
9
1
-
1
0
0
0
,
A
u
g
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
1
5
.
i
2
.
p
p
9
9
1
-
1
0
0
0
.
[
1
5
]
B.
H
u
a
n
g
,
F.
Y
a
n
g
,
M.
Y
i
n
,
X.
M
o
,
a
n
d
C.
Z
h
o
n
g
,
“
A
r
e
v
i
e
w
of
mu
l
t
i
m
o
d
a
l
me
d
i
c
a
l
i
m
a
g
e
f
u
si
o
n
t
e
c
h
n
i
q
u
e
s,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
a
n
d
m
a
t
h
e
m
a
t
i
c
a
l
m
e
t
h
o
d
s
in
m
e
d
i
c
i
n
e
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
0
/
8
2
7
9
3
4
2
.
[
1
6
]
S.
H
a
r
i
sh
a
n
d
G.
F.
A.
A
h
a
mm
e
d
,
“
I
n
t
e
g
r
a
t
e
d
m
o
d
e
l
l
i
n
g
a
p
p
r
o
a
c
h
f
o
r
e
n
h
a
n
c
i
n
g
b
r
a
i
n
M
R
I
w
i
t
h
f
l
e
x
i
b
l
e
p
r
e
-
p
r
o
c
e
ss
i
n
g
c
a
p
a
b
i
l
i
t
y
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
of
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
(
I
J
EC
E)
,
v
o
l
.
9,
n
o
.
4,
p
p
.
2
4
1
6
-
2
4
2
4
,
A
u
g
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
9
i
4
.
p
p
2
4
1
6
-
2
4
2
4
.
[
1
7
]
A.
C.
T
e
st
a
et
al
.,
“
I
mag
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
t
h
e
e
v
a
l
u
a
t
i
o
n
of
c
e
r
v
i
c
a
l
c
a
n
c
e
r
,
”
Be
s
t
p
r
a
c
t
i
c
e
&
res
e
a
rc
h
C
l
i
n
i
c
a
l
o
b
st
e
t
ri
c
s
&
g
y
n
a
e
c
o
l
o
g
y
,
v
o
l
.
2
8
,
n
o
.
5,
p
p
.
741
-
7
6
8
,
J
u
l
y
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
p
o
b
g
y
n
.
2
0
1
4
.
0
4
.
0
0
9
.
[
1
8
]
N.
K.
K
i
m
,
M.
J.
K
i
m,
S.
H.
Y
u
n
,
S.
K
.
S
o
h
n
,
a
n
d
J.
S.
M
i
n
,
“
C
o
mp
a
r
a
t
i
v
e
st
u
d
y
of
t
r
a
n
sr
e
c
t
a
l
u
l
t
r
a
s
o
n
o
g
r
a
p
h
y
,
p
e
l
v
i
c
c
o
m
p
u
t
e
r
i
z
e
d
t
o
mo
g
r
a
p
h
y
,
a
n
d
ma
g
n
e
t
i
c
r
e
s
o
n
a
n
c
e
i
m
a
g
i
n
g
in
p
r
e
o
p
e
r
a
t
i
v
e
s
t
a
g
i
n
g
of
r
e
c
t
a
l
c
a
n
c
e
r
,
”
D
i
se
a
s
e
s
of
t
h
e
c
o
l
o
n
&
rec
t
u
m
,
v
o
l
.
4
2
,
n
o
.
6,
p
p
.
7
7
0
-
7
7
5
,
1
9
9
9
,
d
o
i
:
1
0
.
1
0
0
7
/
B
F
0
2
2
3
6
9
3
3
.
[
1
9
]
H.
A.
La
f
t
a
,
Z.
F.
H
a
sa
n
,
a
n
d
N.
K.
A
y
o
o
b
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
of
me
d
i
c
a
l
d
a
t
a
s
e
t
s
u
si
n
g
b
a
c
k
p
r
o
p
a
g
a
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
p
o
w
e
r
e
d
by
g
e
n
e
t
i
c
-
b
a
s
e
d
f
e
a
t
u
r
e
se
l
e
c
t
o
r
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
of
El
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
(
I
J
EC
E)
,
v
o
l
.
9,
n
o
.
2,
p
p
.
1
3
7
9
-
1
3
8
4
,
A
p
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
9
i
2
.
p
p
.
1
3
7
9
-
1
3
8
4
.
[
2
0
]
E.
B.
v
a
n
de
K
r
a
a
t
s
,
G.
P.
P
e
n
n
e
y
,
D.
T
o
m
a
z
e
v
i
c
,
T.
v
a
n
W
a
l
s
u
m
,
a
n
d
W.
J.
N
i
e
s
s
e
n
,
"
S
t
a
n
d
a
r
d
i
z
e
d
e
v
a
l
u
a
t
i
o
n
m
e
t
h
o
d
o
l
o
g
y
f
o
r
2
-
D
-
3
-
D
r
e
g
i
s
t
r
a
t
i
o
n
,
"
in
I
E
E
E
T
r
a
n
s
a
c
t
i
o
n
s
on
M
e
d
i
c
a
l
I
m
a
g
i
n
g
,
v
o
l
.
2
4
,
n
o
.
9,
p
p
.
1
1
7
7
-
1
1
8
9
,
2
0
0
5
,
d
o
i
:
1
0
.
1
1
0
9
/
T
M
I
.
2
0
0
5
.
8
5
3
2
4
0
.
[
2
1
]
A.
M
a
r
a
t
h
e
,
P.
Ja
i
n
,
a
n
d
V.
V
y
a
s,
‘
‘
I
t
e
r
a
t
i
v
e
i
mp
r
o
v
e
d
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
f
o
r
p
e
t
r
o
g
r
a
p
h
i
c
i
ma
g
e
c
l
a
ssi
f
i
c
a
t
i
o
n
a
c
c
u
r
a
c
y
e
n
h
a
n
c
e
me
n
t
,
’
’
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
of
El
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
EC
E)
,
v
o
l
.
9,
n
o
.
1,
p
p
.
2
8
9
-
2
9
6
,
F
e
b
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
9
i
1
.
p
p
2
8
9
-
2
9
6
.
[
2
2
]
W.
M.
W
e
l
l
s
I
I
I
,
P.
V
i
o
l
a
,
H.
A
t
su
m
i
,
S.
N
a
k
a
j
i
m
a
,
a
n
d
R.
K
i
k
i
n
i
s
e
,
“
M
u
l
t
i
-
mo
d
a
l
v
o
l
u
m
e
r
e
g
i
st
r
a
t
i
o
n
by
ma
x
i
m
i
z
a
t
i
o
n
of
mu
t
u
a
l
i
n
f
o
r
mat
i
o
n
,
”
Me
d
i
c
a
l
i
m
a
g
e
a
n
a
l
y
si
s
,
v
o
l
.
1,
n
o
.
1,
p
p
.
35
-
5
1
,
1
9
9
6
,
d
o
i
:
1
0
.
1
0
1
6
/
S
1
3
6
1
-
8
4
1
5
(
0
1
)
8
0
0
0
4
-
9
.
[
2
3
]
A.
M.
Al
-
S
ma
d
i
,
M.
K.
A
l
s
ma
d
i
,
A.
B
a
a
r
e
h
,
I.
A
l
mara
s
h
d
e
h
,
H.
A
b
o
u
e
l
m
a
g
d
,
a
n
d
O.
S.
S.
A
h
me
d
,
‘
‘
Em
e
r
g
e
n
t
si
t
u
a
t
i
o
n
s
f
o
r
smar
t
c
i
t
i
e
s
:
A
su
r
v
e
y
,
’
’
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
of
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
ri
n
g
(
I
J
E
C
E)
,
v
o
l
.
9,
n
o
.
6,
p
p
.
4
7
7
7
-
4
7
8
7
,
D
e
c
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
9
i
6
.
p
p
4
7
7
7
-
4
7
8
7
.
[
2
4
]
S.
B
i
n
i
t
h
a
,
a
n
d
S.
S.
S
a
t
h
y
a
,
“
A
su
r
v
e
y
of
b
i
o
i
n
s
p
i
r
e
d
o
p
t
i
mi
z
a
t
i
o
n
a
l
g
o
r
i
t
h
ms
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
j
o
u
r
n
a
l
of
s
o
f
t
c
o
m
p
u
t
i
n
g
a
n
d
e
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2,
n
o
.
2,
p
p
.
1
3
7
-
1
5
1
,
2
0
1
2
.
[
2
5
]
M.
K.
A
l
s
ma
d
i
,
M.
Ta
y
f
o
u
r
,
R.
A.
A
l
k
h
a
saw
n
e
h
,
U.
B
a
d
a
w
i
,
I.
A
l
m
a
r
a
s
h
d
e
h
,
a
n
d
F.
H
a
d
d
a
d
,
‘
‘
R
o
b
u
s
t
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
met
h
o
d
s
f
o
r
g
e
n
e
r
a
l
f
i
s
h
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
’
’
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
of
El
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
.
9,
n
o
.
6,
p
p
.
5
1
9
2
-
5
2
0
4
,
D
e
c
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
9
i
6
.
p
p
5
1
9
2
-
5
2
0
4
.
[
2
6
]
M.
W
o
ź
n
i
a
k
a
n
d
D.
P
o
ł
a
p
,
“
A
d
a
p
t
i
v
e
n
e
u
r
o
-
h
e
u
r
i
s
t
i
c
h
y
b
r
i
d
mo
d
e
l
f
o
r
f
r
u
i
t
p
e
e
l
d
e
f
e
c
t
s
d
e
t
e
c
t
i
o
n
,
”
N
e
u
ra
l
N
e
t
w
o
r
k
s
,
v
o
l
.
9
8
,
p
p
.
16
-
3
3
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
n
e
t
.
2
0
1
7
.
1
0
.
0
0
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
25
,
No
.
1
,
J
an
u
ar
y
20
22
:
273
-
2
8
0
280
[
2
7
]
M.
Ta
k
r
u
r
i
,
M.
K.
A.
M
a
h
mo
u
d
,
a
n
d
A.
A
.
-
Ju
m
a
i
l
y
,
“
PSO
-
S
V
M
h
y
b
r
i
d
s
y
st
e
m
f
o
r
m
e
l
a
n
o
ma
d
e
t
e
c
t
i
o
n
f
r
o
m
h
i
s
t
o
-
p
a
t
h
o
l
o
g
i
c
a
l
i
ma
g
e
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
of
E
l
e
c
t
ri
c
a
l
and
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
ri
n
g
(
I
J
EC
E)
,
v
o
l
.
9,
n
o
.
4,
p
p
.
2
9
4
1
-
2
9
4
9
,
A
u
g
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
9
i
4
.
p
p
2
9
4
1
-
2
9
4
9
.
[
2
8
]
A.
K.
A
n
a
r
a
k
i
,
M.
A
y
a
t
i
,
a
n
d
F.
K
a
z
e
m
i
,
“
M
a
g
n
e
t
i
c
r
e
s
o
n
a
n
c
e
i
m
a
g
i
n
g
b
a
s
e
d
b
r
a
i
n
t
u
m
o
r
g
r
a
d
e
s
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
n
d
g
r
a
d
i
n
g
v
i
a
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
a
n
d
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
s
,
”
B
i
o
c
y
b
e
r
n
e
t
i
c
s
B
i
o
m
e
d
.
E
n
g
.,
v
o
l
.
39,
no.
1,
pp.
63
-
74,
2019,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
b
e
.
2
0
1
8
.
1
0
.
0
0
4
.
[
2
9
]
H.
S
h
a
h
a
ma
t
a
n
d
M.
S.
A
b
a
d
e
h
,
“
B
r
a
i
n
M
R
I
a
n
a
l
y
s
i
s
u
s
i
n
g
a
d
e
e
p
l
e
a
r
n
i
n
g
b
a
s
e
d
e
v
o
l
u
t
i
o
n
a
r
y
a
p
p
r
o
a
c
h
,
”
N
e
u
ra
l
N
e
t
w
o
r
k
s
,
v
o
l
.
1
2
6
,
p
p
.
2
1
8
-
2
3
4
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
n
e
t
.
2
0
2
0
.
0
3
.
0
1
7
.
[
3
0
]
M.
S
a
j
j
a
d
,
S.
K
h
a
n
,
K.
M
u
h
a
mm
a
d
,
W.
W
u
,
A.
U
l
l
a
h
,
a
n
d
S.
W.
B
a
i
k
,
“
M
u
l
t
i
-
g
r
a
d
e
b
r
a
i
n
t
u
mo
r
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
d
e
e
p
C
N
N
w
i
t
h
e
x
t
e
n
s
i
v
e
d
a
t
a
a
u
g
me
n
t
a
t
i
o
n
,
”
J
o
u
rn
a
l
of
c
o
m
p
u
t
a
t
i
o
n
a
l
sci
e
n
c
e
,
v
o
l
.
3
0
,
p
p
.
1
7
4
-
1
8
2
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
o
c
s.
2
0
1
8
.
1
2
.
0
0
3
.
[
3
1
]
P.
C
h
a
n
g
et
al
.,
“
D
e
e
p
-
l
e
a
r
n
i
n
g
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
a
c
c
u
r
a
t
e
l
y
c
l
a
ssi
f
y
g
e
n
e
t
i
c
m
u
t
a
t
i
o
n
s
in
g
l
i
o
mas
,
”
Am
e
ri
c
a
n
J
o
u
rn
a
l
of
N
e
u
r
o
r
a
d
i
o
l
o
g
y
,
v
o
l
.
3
9
,
n
o
.
7,
p
p
.
1
2
0
1
-
1
2
0
7
,
2
0
1
8
,
d
o
i
:
1
0
.
3
1
7
4
/
a
j
n
r
.
A
5
6
6
7
.
[
3
2
]
W.
R
a
h
ma
n
,
E.
H
o
ssai
n
,
R.
I
sl
a
m,
H
.
-
Ar
-
R
a
sh
i
d
,
N
.
-
A
-
A
l
a
m,
a
n
d
M.
H
a
san
,
“
R
e
a
l
-
t
i
m
e
a
n
d
l
o
w
-
c
o
s
t
I
o
T
b
a
sed
f
a
r
mi
n
g
u
si
n
g
r
a
sp
b
e
r
r
y
P
i
,
”
I
n
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
of
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
7
,
n
o
.
1,
p
p
.
197
-
2
0
4
,
Ja
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
1
7
.
i
1
.
p
p
1
9
7
-
204
.
[
3
3
]
Q.
M.
S
h
a
l
l
a
l
,
Z.
A.
H
u
ss
i
e
n
,
a
n
d
A.
A.
A
b
b
o
o
d
,
“
M
e
t
h
o
d
to
i
mp
l
e
m
e
n
t
K
-
NN
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
o
c
l
a
ssi
f
y
d
a
t
a
p
r
i
v
a
c
y
in
I
o
T
e
n
v
i
r
o
n
m
e
n
t
,
”
I
n
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
of
E
l
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
and
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
0
,
n
o
.
2,
p
p
.
985
-
9
9
0
,
N
o
v
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
2
0
.
i
2
.
p
p
9
8
5
-
990
.
[
3
4
]
N.
V.
T
a
n
h
,
N.
Q.
Tr
i
,
a
n
d
M.
M.
Tr
u
n
g
,
“
Th
e
s
o
l
u
t
i
o
n
to
i
m
p
r
o
v
e
i
n
f
o
r
m
a
t
i
o
n
s
e
c
u
r
i
t
y
f
o
r
I
o
T
n
e
t
w
o
r
k
s
by
c
o
m
b
i
n
i
n
g
l
i
g
h
t
w
e
i
g
h
t
e
n
c
r
y
p
t
i
o
n
p
r
o
t
o
c
o
l
s,”
I
n
d
o
n
e
s
i
a
n
J
o
u
rn
a
l
of
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
3
,
n
o
.
3,
p
p
.
1
7
2
7
-
1
7
3
5
,
S
e
p
t
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
2
3
.
i
3
.
p
p
1
7
2
7
-
1
7
3
5
.
[
3
5
]
K.
T
u
r
z
h
a
n
o
v
a
,
S.
K
o
n
sh
i
n
,
V.
T
i
k
h
v
i
n
s
k
i
y
,
a
n
d
A.
S
o
l
o
c
h
s
h
e
n
k
o
,
“
P
e
r
f
o
r
man
c
e
e
v
a
l
u
a
t
i
o
n
of
NB
-
I
o
T
in
-
b
a
n
d
d
e
p
l
o
y
me
n
t
mo
d
e
in
s
u
b
u
r
b
a
n
a
r
e
a
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
of
El
e
c
t
ri
c
a
l
En
g
i
n
e
e
r
i
n
g
and
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
3
,
n
o
.
3,
p
p
.
8
5
5
-
8
6
2
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
2
3
.
i
2
.
p
p
8
5
5
-
862
.
[
3
6
]
A.
R
a
j
b
o
n
g
sh
i
,
T.
K
h
a
n
,
M
d
.
M.
R
a
h
man
,
A.
P
r
a
m
a
n
i
k
,
S.
Md
T.
S
i
d
d
i
q
u
e
e
,
a
n
d
N.
R.
C
h
a
k
r
a
b
o
r
t
y
,
“
R
e
c
o
g
n
i
t
i
o
n
of
ma
n
g
o
l
e
a
f
d
i
s
e
a
se
u
s
i
n
g
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
m
o
d
e
l
s
:
a
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
of
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
3
,
n
o
.
3,
p
p
.
1
6
8
1
-
1
6
8
8
,
S
e
p
t
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
2
3
.
i
3
.
p
p
1
6
8
1
-
1
6
8
8
.
[
3
7
]
E.
Er
w
i
n
,
S.
S
a
p
a
r
u
d
i
n
,
a
n
d
W.
S
a
p
u
t
r
i
,
“
H
y
b
r
i
d
m
u
l
t
i
l
e
v
e
l
t
h
r
e
s
h
o
l
d
i
n
g
a
n
d
i
m
p
r
o
v
e
d
h
a
r
m
o
n
y
se
a
r
c
h
a
l
g
o
r
i
t
h
m
f
o
r
seg
m
e
n
t
a
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
of
E
l
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
ri
n
g
(
I
J
E
C
E)
,
v
o
l
.
8,
n
o
.
6,
p
p
.
4
5
9
3
-
4
6
0
2
,
D
e
c
.
2
0
1
8
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
8
i
6
.
p
p
4
5
9
3
-
4
6
0
2
.
[
3
8
]
Y.
A.
F
a
d
i
l
,
B.
Al
-
B
a
n
d
e
r
,
a
n
d
H.
Y.
R
a
d
h
i
,
“
E
n
h
a
n
c
e
me
n
t
of
m
e
d
i
c
a
l
i
m
a
g
e
s
u
si
n
g
f
u
z
z
y
l
o
g
i
c
,
”
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
of
E
l
e
c
t
r
i
c
a
l
En
g
i
n
e
e
ri
n
g
and
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
3
,
n
o
.
3,
p
p
.
1
4
7
8
-
1
4
8
4
,
S
e
p
t
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
2
3
.
i
3
.
p
p
1
4
7
8
-
1
4
8
4
.
[
3
9
]
E.
I.
Za
c
h
a
r
a
k
i
et
al
.,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
of
b
r
a
i
n
t
u
m
o
r
t
y
p
e
a
n
d
g
r
a
d
e
u
s
i
n
g
M
R
I
t
e
x
t
u
r
e
a
n
d
s
h
a
p
e
in
a
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
sc
h
e
me,
”
Ma
g
n
.
R
e
s
o
n
.
M
e
d
.,
v
o
l
.
6
2
,
no.
6,
p
p
.
1
6
0
9
-
1
6
1
8
,
O
c
t
.
2
0
0
9
,
d
o
i
:
1
0
.
1
0
0
2
/
mr
m.2
2
1
4
7
.
[
4
0
]
J.
C
h
e
n
g
et
al
.,
“
E
n
h
a
n
c
e
d
p
e
r
f
o
r
ma
n
c
e
of
b
r
a
i
n
t
u
mo
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
v
i
a
t
u
m
o
r
r
e
g
i
o
n
a
u
g
me
n
t
a
t
i
o
n
a
n
d
p
a
r
t
i
t
i
o
n
,
”
P
l
o
S
O
N
E
,
v
o
l
.
1
0
,
n
o
.
1
0
,
p.
e
0
1
4
0
3
8
1
,
O
c
t
.
2
0
1
5
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
1
4
0
3
8
1
.
[
4
1
]
J.
S.
P
a
u
l
,
A.
J.
P
l
a
s
sard
,
B.
A.
La
n
d
man
,
a
n
d
D.
F
a
b
b
r
i
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
b
r
a
i
n
t
u
mo
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
Pr
o
c
.
S
PI
E,
Me
d
.
I
m
a
g
.
,
B
i
o
me
d
.
A
p
p
l
.
M
o
l
.
,
S
t
r
u
c
t
.
,
F
u
n
c
t
.
I
mag
.
,
v
o
l
.
1
0
1
3
7
,
p.
1
0
1
3
7
1
0
,
M
a
r
.
2
0
1
7
,
d
o
i
:
1
0
.
1
1
1
7
/
1
2
.
2
2
5
4
1
9
5
.
[
4
2
]
P.
A
f
sh
a
r
,
K.
N.
P
l
a
t
a
n
i
o
t
i
s
,
a
n
d
A.
M
o
h
a
mm
a
d
i
,
"
C
a
p
s
u
l
e
N
e
t
w
o
r
k
s
f
o
r
B
r
a
i
n
T
u
m
o
r
C
l
a
ss
i
f
i
c
a
t
i
o
n
B
a
s
e
d
on
M
R
I
I
mag
e
s
a
n
d
C
o
a
r
se
Tu
m
o
r
B
o
u
n
d
a
r
i
e
s,"
I
C
A
S
S
P
2
0
1
9
-
2
0
1
9
I
EE
E
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
on
A
c
o
u
s
t
i
c
s,
S
p
e
e
c
h
a
n
d
S
i
g
n
a
l
Pro
c
e
ss
i
n
g
(
I
C
AS
S
P)
,
2
0
1
9
,
p
p
.
1
3
6
8
-
1
3
7
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
S
S
P
.
2
0
1
9
.
8
6
8
3
7
5
9
.
[
4
3
]
M.
G.
E
r
t
o
s
u
n
a
n
d
D.
L.
R
u
b
i
n
,
“
A
u
t
o
m
a
t
e
d
g
r
a
d
i
n
g
of
g
l
i
o
m
a
s
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
in
d
i
g
i
t
a
l
p
a
t
h
o
l
o
g
y
i
m
a
g
e
s
:
A
m
o
d
u
l
a
r
a
p
p
r
o
a
c
h
w
i
t
h
e
n
s
e
m
b
l
e
of
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
,
”
in
P
r
o
c
.
A
M
I
A
A
n
n
u
.
S
y
m
p
.
P
r
o
c
.
,
v
o
l
.
2
0
1
5
,
p
p
.
1
8
9
9
-
1
9
0
8
,
N
o
v
.
2
0
1
5
.
[
4
4
]
H.
H.
S
u
l
t
a
n
,
N.
M.
S
a
l
e
m,
a
n
d
W.
A
.
-
A
t
a
b
a
n
y
,
"
M
u
l
t
i
-
C
l
a
ss
i
f
i
c
a
t
i
o
n
of
B
r
a
i
n
T
u
m
o
r
I
mag
e
s
U
si
n
g
D
e
e
p
N
e
u
r
a
l
N
e
t
w
o
r
k
,
"
in
I
EEE
A
c
c
e
ss
,
v
o
l
.
7,
p
p
.
6
9
2
1
5
-
6
9
2
2
5
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
1
9
1
2
2
.
[
4
5
]
S.
K.
C
h
a
n
d
r
a
a
n
d
M.
K.
B
a
j
p
a
i
,
"
Ef
f
e
c
t
i
v
e
A
l
g
o
r
i
t
h
m
F
o
r
B
e
n
i
g
n
B
r
a
i
n
Tu
m
o
r
D
e
t
e
c
t
i
o
n
U
s
i
n
g
F
r
a
c
t
i
o
n
a
l
C
a
l
c
u
l
u
s
,"
T
EN
C
O
N
2
0
1
8
-
2
0
1
8
I
EEE
Re
g
i
o
n
10
C
o
n
f
e
r
e
n
c
e
,
2
0
1
8
,
p
p
.
2
4
0
8
-
2
4
1
3
,
d
o
i
:
1
0
.
1
1
0
9
/
TEN
C
O
N
.
2
0
1
8
.
8
6
5
0
1
6
3
.
[
4
6
]
Z.
N.
K.
S
w
a
t
i
et
al
,
“
B
r
a
i
n
t
u
mo
r
c
l
a
ssi
f
i
c
a
t
i
o
n
f
o
r
MR
i
ma
g
e
s
u
si
n
g
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
a
n
d
f
i
n
e
-
t
u
n
i
n
g
,
”
C
o
m
p
u
t
e
r
i
ze
d
M
e
d
i
c
a
l
I
m
a
g
i
n
g
a
n
d
G
r
a
p
h
i
c
s
,
v
o
l
.
7
5
,
p
p
.
34
-
46,
J
u
l
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
m
e
d
i
m
a
g
.
2
0
1
9
.
0
5
.
0
0
1
.
B
I
O
G
RAP
H
I
E
S
OF
AUTH
O
RS
Ahm
e
d
S
h
ih
a
b
Ahm
e
d
is
a
c
o
m
p
u
ter
sc
ien
ti
st
sp
e
c
ialize
d
in
t
h
e
fiel
d
of
ima
g
e
p
ro
c
e
ss
in
g
a
n
d
d
e
c
isio
n
su
p
p
o
rt
sy
ste
m
s.
He
re
c
e
iv
e
d
th
e
fo
u
r
-
y
e
a
r
B.
S
c
.
d
e
g
re
e
in
C
o
m
p
u
ter
S
c
ien
c
e
in
2
0
0
0
fr
o
m
Al
-
Ra
fid
a
i
n
Un
i
v
e
rsity
C
o
ll
e
g
e
,
Ira
q
.
In
2
0
1
5
,
he
c
o
n
c
lu
d
e
d
a
M
a
ste
r
in
Co
m
p
u
ter
S
c
ien
c
e
(M
CS
)
fro
m
M
id
d
le
Eas
t
U
n
iv
e
rsit
y
,
J
o
rd
a
n
.
He
h
a
s
b
e
e
n
w
o
rk
i
n
g
as
a
p
ro
g
ra
m
m
e
r
at
Un
iv
e
rsity
of
Ba
g
h
d
a
d
fro
m
2
0
0
4
u
n
ti
l
2
0
1
4
a
n
d
th
e
n
wo
rk
e
d
as
an
a
ss
istan
t
lec
tu
re
r
at
U
n
iv
e
rsit
y
of
Ba
g
h
d
a
d
fr
o
m
2
0
1
5
u
n
ti
l
n
o
w.
His
m
a
in
re
se
a
rc
h
i
n
tere
sts
i
n
c
lu
d
e
:
a
rti
ficia
l
n
e
u
ra
l
n
e
two
r
k
,
ima
g
e
p
ro
c
e
ss
in
g
,
d
e
c
isio
n
s
u
p
p
o
rt
sy
st
e
m
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
h
m
e
d
sh
ih
a
b
i
n
fo
@c
o
n
u
rsi
n
g
.
u
o
b
a
g
h
d
a
d
.
e
d
u
.
iq
.
H
u
ss
e
in
Ali
S
a
la
h
re
c
e
iv
e
d
th
e
fo
u
r
-
y
e
a
r
B.
S
c
.
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
in
2
0
0
0
fro
m
Al
-
Ra
fid
a
in
U
n
iv
e
rsit
y
C
o
l
leg
e
,
Ira
q
.
In
2
0
0
4
,
he
c
o
n
c
l
u
d
e
d
a
M
a
ste
r
in
C
o
m
p
u
ter
S
c
ien
c
e
(M
CS
)
fro
m
Ba
g
h
d
a
d
Un
i
v
e
rsity
,
c
o
ll
e
g
e
of
sc
ien
c
e
.
He
re
c
e
iv
e
d
th
e
P
h
.
D.
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
IT
in
2
0
1
6
fro
m
P
o
li
teh
n
ica
’
Un
iv
e
rsit
y
of
Bu
c
h
a
re
st,
Bu
c
h
a
re
st,
Ro
m
a
n
ia.
His
m
a
in
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
d
a
ta
m
i
n
in
g
,
d
e
c
isio
n
su
p
p
o
rt
sy
ste
m
,
w
e
b
d
e
sig
n
a
n
d
i
n
telli
g
e
n
t
DS
S
.
He
h
a
s
wo
rk
e
d
as
a
h
e
a
d
of
t
h
e
c
o
m
p
u
ter
sy
ste
m
s
d
e
p
a
rtme
n
t
,
M
id
d
le
Tec
h
n
ica
l
Un
i
v
e
rsity
,
Tec
h
n
ica
l
In
stit
u
te
-
S
u
wa
ira,
Was
it
/Iraq
fro
m
2
0
1
6
u
n
ti
l
n
o
w.
H
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
u
ss
e
in
_
tec
h
@m
tu
.
e
d
u
.
i
q
.
Evaluation Warning : The document was created with Spire.PDF for Python.