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.
3
8
,
No
.
3
,
J
u
n
e
2
0
2
5
,
p
p
.
1
905
~
1
9
1
3
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
38
.i
3
.
pp
1
9
0
5
-
1
9
1
3
1905
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Bra
in
t
umo
r clas
s
ificatio
n f
o
r
opti
mizing
perf
o
rma
nce using
hy
brid RN
N
c
la
ss
ifier
B
o
y
a
Net
ha
pp
a
G
a
ri
K
a
l
a
v
a
t
hi
,
Um
a
dev
i R
a
m
a
mo
o
rt
hy
S
c
h
o
o
l
o
f
S
c
i
e
n
c
e
S
t
u
d
i
e
s (S
O
S
S
)
,
C
M
R
U
n
i
v
e
r
si
t
y
(
O
M
B
R
C
a
m
p
u
s)
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
May
16
,
2
0
2
4
R
ev
is
ed
Dec
9
,
2
0
2
4
Acc
ep
ted
Feb
27
,
2
0
2
5
Tu
m
o
r
is
t
h
e
u
n
c
o
n
tr
o
ll
e
d
g
r
o
wt
h
o
f
c
a
n
c
e
r
c
e
ll
s
in
a
n
y
p
a
rt
o
f
t
h
e
h
u
m
a
n
b
o
d
y
.
Bra
i
n
t
u
m
o
ris
t
h
e
lea
d
in
g
c
a
u
se
o
f
c
a
n
c
e
r
d
e
a
th
s
wo
rl
d
wi
d
e
a
m
o
n
g
a
d
u
lt
s
a
n
d
c
h
il
d
re
n
s.
Early
d
e
tec
t
io
n
o
f
b
ra
in
c
a
n
c
e
rs
is
e
ss
e
n
ti
a
l.
To
p
re
v
e
n
t
m
o
re
issu
e
s,
e
a
rly
d
e
fe
c
t
d
e
tec
ti
o
n
is
e
ss
e
n
ti
a
l.
He
a
lt
h
c
a
re
p
h
y
si
c
ian
s
m
a
y
d
isc
o
v
e
r
a
n
d
c
a
teg
o
rize
b
ra
i
n
t
u
m
o
rs
wit
h
th
e
u
se
o
f
c
o
m
p
u
tatio
n
a
l
in
telli
g
e
n
c
e
-
fo
c
u
se
d
to
o
ls.
A
n
e
ss
e
n
ti
a
l
tas
k
f
o
r
d
iag
n
o
sin
g
t
u
m
o
rs
a
n
d
c
h
o
o
si
n
g
th
e
ri
g
h
t
ty
p
e
o
f
th
e
ra
p
y
is
c
las
sify
i
n
g
b
ra
in
tu
m
o
rs
.
Br
a
in
t
u
m
o
r
id
e
n
ti
fica
ti
o
n
a
n
d
se
g
m
e
n
tati
o
n
u
sin
g
m
a
g
n
e
ti
c
re
so
n
a
n
c
e
ima
g
i
n
g
(
M
RI
)
sc
a
n
s
is
n
o
w
re
c
o
g
n
ize
d
a
s
o
n
e
o
f
th
e
m
o
st
sig
n
ifi
c
a
n
t
a
n
d
d
i
fficu
l
t
re
se
a
rc
h
a
re
a
s
in
th
e
wo
rld
o
f
m
e
d
ica
l
ima
g
e
p
ro
c
e
ss
in
g
.
Th
e
fiel
d
o
f
m
e
d
ica
l
ima
g
in
g
h
a
s
g
a
in
e
d
g
re
a
tl
y
fro
m
th
e
u
se
o
f
a
rti
ficia
l
in
telli
g
e
n
c
e
(
AI)
in
t
h
e
fo
rm
o
f
m
a
c
h
in
e
lea
rn
in
g
(M
L)
a
n
d
d
e
e
p
lea
rn
i
n
g
(DL).
DL
h
a
s
sh
o
wn
sig
n
ifi
c
a
n
t
p
re
se
n
tatio
n
,
e
sp
e
c
iall
y
i
n
th
e
a
re
a
s
o
f
b
ra
in
tu
m
o
r
c
la
ss
ifi
c
a
ti
o
n
a
n
d
se
g
m
e
n
tatio
n
.
I
n
t
h
is
wo
r
k
,
b
ra
in
t
u
m
o
r
c
las
sifica
ti
o
n
fo
r
o
p
ti
m
izin
g
p
e
rfo
rm
a
n
c
e
u
si
n
g
h
y
b
r
id
re
c
u
r
re
n
t
n
e
u
ra
l
n
e
two
r
k
(
RNN
)
c
las
sifier
is
p
re
se
n
ted
.
Diffe
re
n
t
t
y
p
e
s
o
f
b
ra
i
n
t
u
m
o
rs
a
re
c
las
sified
u
sin
g
a
m
ix
o
f
RN
N
a
n
d
i
n
c
e
p
ti
o
n
re
sid
u
a
l
n
e
u
ra
l
n
e
t
wo
rk
(
Re
sN
e
t
).
T
h
is
stra
teg
y
wil
l
p
r
o
d
u
c
e
imp
ro
v
e
d
F
1
-
sc
o
r
e
,
p
re
c
isio
n
,
a
c
c
u
ra
c
y
,
a
n
d
re
c
a
ll
sc
o
re
s
.
K
ey
w
o
r
d
s
:
Ar
tific
ial
in
tellig
en
ce
B
r
ain
t
umor
C
las
s
if
icatio
n
Dee
p
lear
n
in
g
R
ec
u
r
r
en
t n
eu
r
al
n
etwo
r
k
Seg
m
en
tatio
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
:
B
o
y
a
Neth
ap
p
a
Gar
i K
alav
ath
i
Sch
o
o
l o
f
Scien
ce
Stu
d
ies (
SOSS
)
,
C
MR Un
iv
er
s
ity
(
OM
B
R
C
am
p
u
s
)
B
en
g
alu
r
u
,
Kar
n
atak
a,
I
n
d
ia
E
m
ail:
b
n
k
alav
ath
i
1
2
3
@
g
m
ail
.
co
m
1.
I
NT
RO
D
UCT
I
O
N
An
ab
n
o
r
m
al
ce
ll
d
ev
elo
p
m
e
n
t
in
th
e
b
r
ain
r
esu
lts
in
th
e
cr
ea
tio
n
o
f
a
b
r
ain
t
u
m
o
r
,
s
o
m
etim
es
r
ef
er
r
ed
to
as
an
i
n
tr
ac
r
an
ial
n
eo
p
lasm.
Hea
d
ac
h
e,
v
o
m
itin
g
,
v
is
io
n
p
r
o
b
lem
s
,
a
n
d
m
en
t
al
ab
n
o
r
m
alities
ar
e
p
o
s
s
ib
le
s
y
m
p
to
m
s
.
A
tu
m
o
r
is
es
s
en
tially
th
e
b
o
d
y
’
s
ce
lls
g
r
o
win
g
ab
n
o
r
m
ally
an
d
u
n
co
n
tr
o
llab
ly
[
1
]
.
A
b
r
ain
t
u
m
o
r
is
an
ab
n
o
r
m
al
m
ass
o
f
tis
s
u
e
in
wh
ich
ce
lls
g
r
o
w
r
ap
i
d
ly
an
d
u
n
co
n
t
r
o
llab
l
y
in
s
id
e
th
e
b
r
ain
’
s
tis
s
u
es.
E
ar
ly
id
en
tific
atio
n
o
f
b
r
ain
tu
m
o
r
s
is
im
p
o
r
tan
t.
W
h
en
it
d
ev
elo
p
s
,
it
b
ec
o
m
es
ex
tr
em
ely
life
-
s
av
in
g
.
I
f
a
b
r
ain
tu
m
o
r
is
d
is
co
v
er
e
d
ea
r
ly
o
n
,
th
e
p
atien
t
’
s
ch
an
c
es
o
f
s
u
r
v
iv
al
will
in
cr
ea
s
e.
T
h
e
p
o
s
s
ib
ilit
y
o
f
a
p
er
s
o
n
s
u
r
v
i
v
in
g
a
b
r
ain
t
u
m
o
r
is
d
ef
in
itely
in
cr
ea
s
ed
b
y
ea
r
ly
d
etec
tio
n
an
d
im
m
ed
iate
tr
e
atm
en
t [
2
]
.
B
r
ain
t
u
m
o
r
s
m
ay
s
p
r
ea
d
t
h
r
o
u
g
h
o
u
t
th
e
b
r
ain
at
d
if
f
er
e
n
t
r
ates.
I
ts
g
r
o
wth
r
ate
is
d
e
p
en
d
en
t
u
p
o
n
th
e
b
r
ain
tu
m
o
r
’
s
lo
ca
tio
n
.
R
eg
ar
d
in
g
h
ar
m
to
th
e
h
u
m
an
n
er
v
o
u
s
s
y
s
tem
,
th
e
tu
m
o
r
’
s
lo
ca
tio
n
is
eq
u
ally
ess
en
tial
[
3
]
.
T
h
e
t
u
m
o
r
’
s
s
ize,
lo
ca
tio
n
,
a
n
d
t
y
p
e
all
af
f
ec
t
th
e
way
it
is
tr
ea
ted
at
t
h
e
s
am
e
tim
e.
T
h
e
p
atien
t
’
s
v
ar
io
u
s
s
y
m
p
to
m
s
ar
e
th
e
f
ir
s
t
s
tep
to
war
d
s
a
b
r
ain
tu
m
o
r
d
iag
n
o
s
is
.
A
p
h
y
s
ician
m
ak
es
a
n
ass
es
s
m
en
t
o
f
th
e
n
er
v
es,
s
tr
e
n
g
th
,
r
ef
le
x
es,
b
alan
ce
,
an
d
s
en
s
es.
Ad
d
itio
n
al
ex
am
in
atio
n
m
eth
o
d
s
ar
e
u
s
ed
to
d
iag
n
o
s
e
b
r
ain
tu
m
o
r
if
th
e
p
h
y
s
ician
b
eliev
es
th
er
e
is
a
tu
m
o
r
.
B
r
ain
tu
m
o
r
is
o
n
e
o
f
th
e
m
o
s
t
ty
p
ical
k
in
d
s
o
f
b
r
ain
d
is
ea
s
e.
I
t
is
o
cc
u
r
r
ed
d
u
e
to
th
e
d
ev
el
o
p
m
en
t
o
f
u
n
r
eg
u
lated
b
r
ain
ce
lls
.
Gen
er
ally
,
th
e
tu
m
o
r
class
if
ied
in
to
p
r
im
ar
y
an
d
s
ec
o
n
d
ar
y
b
r
ai
n
tu
m
o
r
s
.
T
h
e
f
ir
s
t
s
tar
ts
in
th
e
b
r
ain
an
d
s
tay
s
th
er
e
wh
ile
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2502
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
3
8
,
No
.
3
,
J
u
n
e
2
0
2
5
: 1
9
0
5
-
1
9
1
3
1906
latter
s
tar
ts
as
ca
n
ce
r
at
s
o
m
e
wh
er
e
in
th
e
b
o
d
y
an
d
s
p
r
ea
d
s
to
th
e
b
r
ai
n
[
4
]
.
T
h
er
e
ar
e
t
wo
ty
p
es
o
f
tu
m
o
r
s
:
b
en
ig
n
tu
m
o
r
s
,
wh
ich
a
r
e
m
a
d
e
u
p
o
f
m
alig
n
an
t
ce
lls
an
d
a
r
e
less
d
an
g
er
o
u
s
s
in
ce
th
ey
d
o
n
o
t
s
p
r
ea
d
to
o
th
e
r
ce
lls
.
On
th
e
o
th
e
r
h
a
n
d
,
m
a
lig
n
an
t
tu
m
o
r
s
ar
e
m
ass
es
o
f
ce
lls
th
at
ar
e
d
a
n
g
er
o
u
s
,
ca
n
ce
r
o
u
s
,
a
n
d
m
o
r
e
s
u
s
ce
p
tib
le
to
s
p
r
ea
d
to
o
th
er
tis
s
u
es
an
d
ce
lls
.
A
tu
m
o
r
is
ess
en
tially
a
co
llectio
n
o
f
ce
lls
th
at
cr
ea
te
a
tis
s
u
e
th
at
h
as
an
u
n
r
estricte
d
g
r
o
win
g
o
f
d
ev
elo
p
m
en
t
a
n
d
lack
s
th
e
co
n
tr
o
l
t
h
at
n
o
r
m
al
ce
l
ls
h
av
e
[
5
]
.
B
r
ain
t
u
m
o
r
s
ca
n
b
e
ca
teg
o
r
ized
in
t
o
n
u
m
e
r
o
u
s
ty
p
es,
in
clu
d
in
g
p
itu
itar
y
,
g
lio
m
a,
an
d
m
en
in
g
io
m
a.
On
e
ty
p
e
o
f
tu
m
o
r
t
h
at
af
f
ec
ts
th
e
b
r
ain
a
n
d
s
p
in
al
c
o
r
d
is
ca
lled
a
g
lio
m
a.
B
r
ain
an
d
o
t
h
er
p
ar
ts
o
f
th
e
n
er
v
o
u
s
s
y
s
tem
,
s
u
ch
as th
e
b
r
ain
s
tem
a
n
d
s
p
i
n
al
co
lu
m
n
,
ca
n
d
ev
elo
p
g
lio
m
as.
T
h
e
s
y
m
p
to
m
s
o
f
g
lio
m
as
v
a
r
y
d
ep
e
n
d
in
g
o
n
th
is
ty
p
e.
H
ea
d
ac
h
es,
s
eizu
r
es,
ir
r
itab
ilit
y
,
v
o
m
itin
g
,
v
is
io
n
p
r
o
b
lem
s
an
d
n
u
m
b
n
es
s
o
r
wea
k
n
ess
in
th
e
ex
tr
em
ities
ar
e
a
f
ew
o
f
th
em
.
A
tu
m
o
r
th
at
d
ev
elo
p
s
in
th
e
m
en
in
g
es,
th
e
tis
s
u
e
lay
er
s
p
r
o
tectin
g
y
o
u
r
b
r
ain
a
n
d
s
p
in
al
co
r
d
,
is
k
n
o
wn
as
a
m
en
in
g
io
m
a.
Alth
o
u
g
h
th
ey
ar
e
o
f
ten
b
en
i
g
n
(
n
o
t
ca
n
ce
r
o
u
s
)
,
th
ey
ca
n
o
cc
asio
n
ally
b
e
m
alig
n
an
t
(
ca
n
ce
r
o
u
s
)
.
M
en
in
g
io
m
as
ca
n
b
e
m
an
ag
ed
.
On
e
o
f
th
e
m
o
s
t
d
ev
astatin
g
f
o
r
m
s
o
f
ca
n
ce
r
is
Ma
lig
n
an
t
b
r
ain
tu
m
o
r
w
h
ich
ca
n
b
e
m
ar
k
ed
as
d
is
m
al
s
u
r
v
iv
al
r
ates
an
d
r
e
m
ain
ed
u
n
ch
a
n
g
ed
o
v
e
r
t
h
e
d
ec
ad
es
[
6
]
.
Un
u
s
u
al
g
r
o
wth
s
in
th
e
p
itu
itar
y
g
la
n
d
ar
e
ca
lled
p
itu
itar
y
tu
m
o
r
s
.
Hea
d
ac
h
es
o
r
a
b
n
o
r
m
alities
i
n
v
is
io
n
ar
e
s
ig
n
s
.
Ho
r
m
o
n
es
m
ay
also
b
e
im
p
ac
te
d
in
s
o
m
e
s
itu
atio
n
s
,
d
is
r
u
p
tin
g
m
en
s
tr
u
al
cy
cles a
n
d
lead
i
n
g
t
o
s
ex
u
al
d
y
s
f
u
n
ctio
n
.
Su
r
g
er
y
an
d
m
ed
icatio
n
ar
e
u
s
ed
as
tr
ea
tm
en
ts
to
r
ed
u
c
e
t
h
e
tu
m
o
r
o
r
s
to
p
th
e
o
v
er
p
r
o
d
u
ctio
n
o
f
h
o
r
m
o
n
es.
R
ad
io
a
ctiv
ity
m
ay
also
b
e
u
tili
ze
d
in
ce
r
tain
s
itu
atio
n
s
[
7
]
.
T
h
e
p
atien
t’
s
v
ar
io
u
s
s
y
m
p
to
m
s
ar
e
th
e
f
ir
s
t
s
tep
to
war
d
s
a
b
r
ain
tu
m
o
r
d
iag
n
o
s
is
.
Nex
t,
a
p
h
y
s
ician
m
ak
es
an
ass
ess
m
en
t
o
f
th
e
n
er
v
es,
s
tr
en
g
th
,
r
ef
lex
es,
b
ala
n
ce
,
an
d
s
en
s
es.
Ad
d
itio
n
al
e
x
am
in
atio
n
m
et
h
o
d
s
ar
e
u
s
ed
to
d
iag
n
o
s
e
b
r
ain
tu
m
o
r
s
if
th
e
p
h
y
s
ician
b
eliev
es
th
er
e
is
a
tu
m
o
r
.
T
h
e
d
iag
n
o
s
is
o
f
b
r
ain
tu
m
o
r
is
p
r
o
v
e
d
to
b
e
c
h
allen
g
in
g
d
u
e
to
th
e
r
esem
b
lan
ce
b
etwe
en
ca
n
ce
r
o
u
s
a
n
d
h
ea
lth
y
ce
lls
an
d
th
e
s
im
ilar
ities
b
etwe
en
d
if
f
er
en
t
k
in
d
s
o
f
b
r
ain
tu
m
o
r
s
[
8
]
.
Un
tr
ea
ted
o
f
b
r
ai
n
tu
m
o
r
s
ca
n
r
esu
lt
in
d
ea
th
.
Hea
lth
ca
r
e
p
r
o
v
id
e
r
s
h
av
e
d
if
f
icu
lties
in
d
etec
tin
g
an
d
tr
ea
ti
n
g
p
e
o
p
l
e
th
at
h
av
e
b
r
ai
n
tu
m
o
r
d
u
e
t
o
th
eir
co
m
p
lex
ity
.
T
o
s
tar
t
tr
ea
tm
e
n
t
as
ea
r
ly
as
p
o
s
s
ib
le,
it
is
ess
en
tial
to
id
en
tify
th
e
ty
p
e
o
f
t
u
m
o
r
t
h
at
a
p
atien
t
h
as
[
9
]
.
I
m
ag
e
p
r
o
ce
s
s
in
g
-
b
ased
b
r
a
in
tu
m
o
r
d
etec
tio
n
h
as
b
e
en
a
m
ajo
r
f
ield
o
f
s
tu
d
y
in
r
ec
en
t
y
ea
r
s
.
E
v
en
th
o
u
g
h
,
n
u
m
e
r
o
u
s
r
esear
ch
es
wo
r
k
d
escr
ib
e
d
,
s
till
a
r
eliab
le
tech
n
iq
u
e
f
o
r
d
etec
ti
n
g
b
r
ain
tu
m
o
r
s
is
ch
allen
g
in
g
.
Patien
ts
ar
e
n
o
w
t
r
ea
ted
wit
h
s
u
r
g
er
y
,
r
a
d
iatio
n
,
c
h
em
o
t
h
er
ap
y
,
o
r
a
co
m
b
in
atio
n
o
f
tr
ea
tm
en
ts
.
B
ec
au
s
e
b
r
ain
tu
m
o
r
b
io
p
s
ies
n
ee
d
s
u
r
g
er
y
,
th
e
y
ar
e
m
o
r
e
d
if
f
icu
lt
th
a
n
b
io
p
s
ies
o
f
o
th
e
r
b
o
d
y
a
r
ea
s
[
1
0
]
.
I
t
is
th
er
ef
o
r
e
ess
en
tial
to
h
av
e
a
d
if
f
er
en
t
tech
n
i
q
u
e
f
o
r
o
b
tain
in
g
a
p
r
ec
is
e
d
iag
n
o
s
is
with
o
u
t
s
u
r
g
er
y
.
T
h
e
m
o
s
t
ef
f
ec
tiv
e
an
d
wid
e
ly
u
s
ed
m
eth
o
d
f
o
r
id
en
tif
y
in
g
b
r
ain
ca
n
ce
r
s
is
m
ag
n
etic
r
eso
n
an
ce
im
ag
in
g
(
MRI)
.
Diag
n
o
s
tic
im
ag
in
g
tech
n
iq
u
es
in
clu
d
in
g
co
m
p
u
te
d
to
m
o
g
r
ap
h
y
(
CT
)
s
ca
n
s
an
d
MRIs
ca
n
id
en
tify
b
r
ain
t
u
m
o
r
[
1
1
]
.
Utilizin
g
im
ag
e
p
r
o
ce
s
s
in
g
,
o
n
e
m
ay
g
ath
er
an
d
s
ep
ar
ate
i
m
p
o
r
tan
t
in
f
o
r
m
atio
n
f
r
o
m
a
r
an
g
e
o
f
d
atasets
.
I
n
th
e
f
ield
o
f
im
ag
e
d
iag
n
o
s
tic
r
esear
ch
,
m
an
y
m
a
ch
in
e
lear
n
in
g
(
ML
)
tech
n
i
q
u
es
ar
e
u
s
ed
f
o
r
MRI
im
ag
e
s
eg
m
en
tatio
n
[
1
2
]
.
Uti
lizin
g
MRI
to
s
eg
m
e
n
t
b
r
ai
n
t
umor
s
is
im
p
o
r
tan
t
an
d
s
ig
n
i
f
ican
t
f
o
r
m
ed
ical
f
ield
s
in
ce
it
s
u
p
p
o
r
ts
in
d
iag
n
o
s
is
an
d
p
r
o
g
n
o
s
is
,
g
en
er
al
g
r
o
wth
f
o
r
ec
asts
,
tu
m
o
r
d
en
s
ity
m
ea
s
u
r
em
en
ts
,
an
d
p
atien
t
tr
ea
tm
en
t
p
lan
s
.
T
h
r
ee
d
if
f
er
en
t
d
ir
ec
tio
n
s
ar
e
u
s
ed
t
o
ca
p
tu
r
e
th
e
MR
im
ag
es.
T
h
ese
p
er
s
p
ec
tiv
es
ar
e
k
n
o
wn
as c
o
r
o
n
a,
ax
ial,
an
d
s
ag
ittal [
1
3
]
.
I
n
th
e
d
o
m
ain
s
o
f
co
m
p
u
ter
v
is
io
n
an
d
m
ed
ical
im
ag
e
an
aly
s
is
,
im
ag
e
s
eg
m
en
tatio
n
is
a
cr
u
cia
l
p
h
en
o
m
en
o
n
.
T
h
e
g
o
al
o
f
b
r
a
in
t
u
m
o
r
s
eg
m
e
n
tatio
n
is
to
s
ep
ar
ate
ab
n
o
r
m
al
b
r
ain
tis
s
u
es
f
r
o
m
n
o
r
m
al
b
r
ain
tis
s
u
es,
s
u
ch
as
wh
ite
m
atter
(
W
M)
,
g
r
ay
m
atter
(
GM
)
,
an
d
ce
r
eb
r
o
-
s
p
i
n
al
f
lu
id
(
C
SF
)
,
in
clu
d
in
g
ac
tiv
e
ce
lls
,
n
ec
r
o
tic
co
r
e,
an
d
e
d
em
a
[
1
4
]
.
T
h
e
e
x
is
ten
ce
o
f
n
o
n
-
h
o
m
o
g
en
e
o
u
s
in
ten
s
ity
d
is
tr
ib
u
t
io
n
s
u
r
r
o
u
n
d
in
g
th
e
tu
m
o
r
,
n
o
is
y
b
ac
k
g
r
o
u
n
d
,
c
o
m
p
licated
s
tr
u
ct
u
r
e
with
f
u
zz
y
b
o
u
n
d
ar
ies,
a
n
d
lo
w
co
n
tr
ast
r
elativ
e
to
o
th
er
b
r
ain
tis
s
u
es
m
ak
e
t
u
m
o
r
s
eg
m
en
tatio
n
ex
tr
em
el
y
ch
allen
g
in
g
.
Au
to
m
atic
t
u
m
o
r
s
eg
m
en
tatio
n
alg
o
r
ith
m
s
ar
e
f
aster
,
m
o
r
e
a
cc
u
r
a
te,
a
n
d
aid
i
n
tu
m
o
r
an
aly
s
is
an
d
d
ia
g
n
o
s
is
co
m
p
ar
e
d
to
m
an
u
al
tu
m
o
r
s
eg
m
en
tatio
n
[
1
5
]
.
R
ad
io
lo
g
is
ts
d
etec
t a
n
d
d
iag
n
o
s
e
ca
n
ce
r
s
u
s
in
g
th
e
tr
ad
itio
n
al
ap
p
r
o
ac
h
f
o
r
t
u
m
o
r
d
etec
tio
n
,
wh
ich
is
ex
tr
em
ely
lab
o
r
io
u
s
an
d
tim
e
-
co
n
s
u
m
in
g
.
C
o
m
p
u
ter
-
aid
e
d
m
ed
ical
d
ia
g
n
o
s
is
(
C
AM
D
)
,
wh
ich
m
a
y
h
elp
p
h
y
s
ician
s
an
aly
ze
m
ed
ical
i
m
ag
es
in
a
m
atter
o
f
s
ec
o
n
d
s
,
h
as
ad
v
an
ce
d
s
ig
n
i
f
ican
tly
a
s
a
r
esu
lt
o
f
r
ec
en
t
ad
v
an
ce
m
e
n
ts
in
a
r
tific
ial
in
t
ellig
en
ce
(
AI
)
an
d
ML
.
Me
d
i
ca
l
im
ag
in
g
p
atter
n
s
h
av
e
b
e
en
r
ec
o
g
n
ized
an
d
ca
teg
o
r
ized
d
u
e
to
r
ec
e
n
t
d
ev
elo
p
m
en
ts
in
ML
.
On
e
o
f
th
e
ar
ea
s
o
f
s
u
cc
ess
in
th
is
f
ield
is
th
at
in
f
o
r
m
atio
n
ca
n
n
o
w
b
e
r
etr
iev
e
d
an
d
e
x
t
r
ac
ted
f
r
o
m
d
ata
in
s
tead
o
f
h
av
in
g
t
o
b
e
lear
n
e
d
f
r
o
m
s
p
e
cialist
s
o
r
s
cien
tific
tex
ts
[
1
6
]
.
T
h
e
id
en
tific
atio
n
an
d
ca
te
g
o
r
izatio
n
o
f
m
ed
ical
im
a
g
in
g
p
atter
n
s
is
th
e
r
esu
lt
o
f
r
ec
e
n
t
d
ev
elo
p
m
e
n
ts
in
ML
,
p
ar
ticu
l
ar
ly
d
ee
p
lear
n
in
g
(
DL
)
.
On
e
o
f
th
e
s
u
cc
ess
es in
th
is
f
ield
is
th
at
k
n
o
wled
g
e
ca
n
n
o
w
b
e
r
etr
iev
e
d
an
d
e
x
tr
ac
t
ed
f
r
o
m
d
ata
in
s
tead
o
f
b
ein
g
tau
g
h
t
b
y
s
p
ec
ialis
ts
o
r
s
c
ien
tific
tex
ts
[
1
7
]
.
A
n
u
m
b
e
r
o
f
m
e
d
ical
ap
p
lic
atio
n
s
ar
e
f
i
n
d
in
g
DL
to
b
e
a
u
s
ef
u
l
tech
n
iq
u
e
f
o
r
im
p
r
o
v
in
g
p
er
f
o
r
m
an
ce
,
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
B
r
a
in
t
u
mo
r
cla
s
s
ifica
tio
n
fo
r
o
p
timiz
in
g
p
erfo
r
ma
n
ce
u
s
in
g
h
yb
r
id
…
(
B
o
y
a
N
eth
a
p
p
a
Ga
r
i Ka
la
va
th
i
)
1907
s
u
ch
as
th
e
tis
s
u
e
s
eg
m
en
tatio
n
,
illn
ess
p
r
ed
ictio
n
a
n
d
d
iag
n
o
s
is
,
ce
llu
lar
an
d
m
o
lecu
lar
s
tr
u
ctu
r
e
id
en
tific
atio
n
,
an
d
im
ag
e
class
if
icatio
n
[
1
8
]
.
ML
-
b
ased
s
eg
m
en
tatio
n
an
d
c
lass
if
icatio
n
o
f
b
r
ain
t
umor
s
was
d
em
o
n
s
tr
ated
.
I
n
o
r
d
er
to
r
ed
u
ce
th
e
s
m
all
p
o
s
s
ib
ilit
y
o
f
m
is
s
ca
te
g
o
r
izatio
n
er
r
o
r
,
t
h
is
r
esear
ch
f
o
cu
s
es
o
n
ac
cu
r
ately
class
if
y
in
g
tu
m
o
r
s
f
r
o
m
MRI
im
ag
es
u
tili
zin
g
s
ev
er
al
s
eg
m
en
tatio
n
m
eth
o
d
s
.
W
h
en
co
m
p
ar
ed
to
a
s
in
g
le
s
eg
m
en
t
atio
n
alg
o
r
ith
m
,
th
e
r
esu
lts
p
r
o
d
u
ce
d
b
y
m
an
y
s
eg
m
en
tatio
n
alg
o
r
ith
m
s
ar
e
m
o
r
e
ex
ac
t
an
d
ac
cu
r
ate.
I
n
o
r
d
er
to
d
o
th
is
,
th
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM
)
c
lass
if
ier
is
co
m
b
in
e
d
with
t
h
e
wate
r
s
h
ed
,
K
-
m
e
an
s
,
an
d
th
r
esh
o
ld
s
eg
m
en
tatio
n
alg
o
r
ith
m
s
,
an
d
th
e
en
d
r
esu
lt is
a
9
0
%
ab
o
v
e
class
if
icatio
n
r
esu
lt [
1
9
]
.
T
o
d
etec
t
th
e
b
r
ain
t
umor
s
d
ee
p
n
eu
r
al
n
etwo
r
k
(
DNN
)
al
g
o
r
ith
m
is
em
p
lo
y
ed
.
A
DNN
s
tr
u
ctu
r
e
th
at
m
ak
es
u
s
e
o
f
s
tack
e
d
a
u
to
-
en
co
d
er
s
is
s
h
o
wn
.
B
io
p
s
ies
ar
e
n
o
t
o
f
ten
d
o
n
e
b
ef
o
r
e
co
n
cl
u
s
iv
e
b
r
ai
n
s
u
r
g
er
y
; in
s
tead
,
th
e
y
ar
e
u
s
ed
to
ca
teg
o
r
ize
b
r
ain
t
u
m
o
r
s
.
W
ith
o
u
t r
eq
u
ir
in
g
in
v
asiv
e
p
r
o
c
ed
u
r
es,
r
ad
i
o
lo
g
is
ts
will
h
av
e
ad
d
itio
n
al
h
elp
in
tu
m
o
r
d
iag
n
o
s
is
d
u
e
to
th
e
d
ev
e
lo
p
m
en
t
o
f
ML
.
T
h
ey
u
s
e
its
s
p
ee
d
an
d
b
en
e
f
its
f
o
r
t
h
e
h
u
m
an
b
ei
n
g
to
e
n
h
an
c
e
m
ed
ical
i
m
ag
in
g
f
ac
ilit
ies.
Me
d
ica
l
p
r
o
f
ess
io
n
als
m
ay
f
in
d
n
ew
o
p
p
o
r
tu
n
ities
with
ML
’
s
in
cr
ea
s
ed
tr
ain
in
g
s
p
ee
d
s
an
d
ac
c
u
r
ac
y
.
B
y
av
o
i
d
in
g
th
e
co
m
p
u
tatio
n
al
s
tr
ain
o
f
m
an
u
ally
g
o
in
g
th
r
o
u
g
h
m
ed
ical
im
a
g
es,
it
s
im
p
lifie
d
th
e
p
r
o
ce
s
s
o
f
u
n
d
er
s
tan
d
in
g
th
e
h
u
m
an
b
r
ain
a
n
d
s
av
e
a
s
ig
n
if
ican
t
am
o
u
n
t
o
f
tim
e
[
2
0
]
.
T
h
e
u
s
e
o
f
ML
to
d
etec
t
b
r
a
in
t
um
o
r
s
was
p
r
esen
ted
.
T
h
i
s
m
eth
o
d
o
f
f
er
s
a
m
o
d
el
th
at
u
s
es
ML
tech
n
iq
u
es
to
ac
cu
r
ately
id
e
n
tify
b
r
ain
t
u
m
o
r
s
u
s
in
g
m
ag
n
e
tic
r
eso
n
an
ce
im
ag
in
g
.
Seg
m
e
n
tatio
n
an
d
f
ea
tu
r
e
ex
tr
ac
tio
n
h
a
v
e
b
ee
n
p
er
f
o
r
m
ed
u
s
in
g
a
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN)
.
T
h
e
u
tili
ze
d
d
at
aset
was
o
b
tain
ed
f
r
o
m
a
web
s
ite
o
n
th
e
in
ter
n
et
[
2
1
]
.
A
tr
an
s
f
er
lear
n
i
n
g
m
et
h
o
d
f
o
r
class
if
y
in
g
b
r
ain
ca
n
ce
r
s
u
s
in
g
AI
was
d
is
cu
s
s
ed
.
T
h
is
ar
ticle
p
r
o
p
o
s
es
th
e
u
s
e
o
f
DL
alg
o
r
ith
m
s
f
o
r
AI
-
b
ased
ca
teg
o
r
iza
tio
n
o
f
b
r
ain
t
umor
ty
p
es
u
s
in
g
d
atasets
th
at
ar
e
r
ea
d
ily
av
ailab
le.
T
h
ese
d
at
ab
ases
ca
teg
o
r
ize
b
r
ain
tu
m
o
r
s
as
eith
er
b
en
ig
n
o
r
m
al
ig
n
an
t.
Fo
r
test
in
g
p
u
r
p
o
s
es,
th
e
d
atasets
co
n
s
i
s
t
o
f
6
9
6
im
ag
es o
n
T
1
-
weig
h
te
d
im
ag
es.
T
h
e
p
r
ed
icted
co
n
f
i
g
u
r
atio
n
ac
h
ie
v
es a
n
im
p
r
ess
iv
e
r
esu
lt with
th
e
f
in
e
s
t a
cc
u
r
ac
y
[
2
2
].
ML
-
b
ased
p
ix
el
-
le
v
el
f
ea
tu
r
e
s
p
ac
e
m
o
d
elin
g
was
d
esig
n
ed
f
o
r
b
r
ain
t
umor
id
en
tific
atio
n
.
I
n
o
r
d
er
to
im
p
r
o
v
e
t
h
e
ab
ilit
y
o
f
a
ML
ap
p
r
o
ac
h
to
id
en
tif
y
b
r
ai
n
t
umor
a
r
ea
s
at
th
e
p
ix
el
lev
el
in
an
MRI
b
r
ai
n
im
ag
e,
a
f
ea
tu
r
e
lear
n
in
g
tech
n
iq
u
e
is
p
r
o
v
id
ed
.
T
h
e
b
r
ain
t
u
m
o
r
s
eg
m
e
n
tatio
n
(
B
r
aT
S
2
0
1
5
)
d
atasets
wer
e
m
o
d
if
ied
in
o
r
d
er
to
cr
ea
te
an
d
v
er
if
y
t
h
e
s
u
g
g
ested
co
m
p
u
t
atio
n
al
f
r
am
ewo
r
k
.
Usi
n
g
a
r
a
n
g
e
o
f
q
u
an
titativ
e
an
d
q
u
alitativ
e
m
ea
s
u
r
e
m
en
ts
,
th
e
a
u
th
o
r
s
ass
ess
ed
th
e
r
an
d
o
m
f
o
r
est
(
R
F),
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
,
an
d
SVM
m
o
d
els.
B
ased
o
n
th
e
p
r
ec
is
io
n
-
r
ec
all
cu
r
v
e,
th
e
y
f
o
u
n
d
th
at
th
e
R
F
m
o
d
el
lear
n
ed
9
2
%
o
f
th
e
p
er
f
ec
t
m
o
d
el
’
s
tu
m
o
r
d
etec
tio
n
ab
ilit
ies,
wh
er
ea
s
A
NN
an
d
SVM
lear
n
ed
9
0
%
an
d
8
8
%
o
f
th
e
p
er
f
ec
t
m
o
d
el
’
s
tu
m
o
r
d
etec
tio
n
s
k
ills
[
2
3
]
.
A
co
m
p
u
tatio
n
al
m
et
h
o
d
b
ased
o
n
in
ter
n
et
o
f
m
ed
ical
th
in
g
s
(
I
o
MT
)
was
p
r
esen
ted
f
o
r
b
r
ain
t
u
m
o
r
d
etec
tio
n
.
B
r
ain
t
u
m
o
r
s
ar
e
cl
ass
if
ied
in
to
g
r
a
d
es
I
th
r
o
u
g
h
I
V
u
s
in
g
t
h
e
Par
tial
T
r
e
e
ass
o
ciatio
n
r
u
le
lear
n
er
,
wh
ich
h
as
an
ex
ten
s
iv
e
f
ea
tu
r
e
s
et.
1
0
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
is
u
s
ed
to
v
alid
ate
th
e
s
u
g
g
ested
m
o
d
el,
an
d
it
is
co
n
tr
asted
with
th
e
cu
r
r
en
t
a
p
p
r
o
ac
h
es
r
an
d
o
m
tr
ee
,
RF
,
class
if
icatio
n
an
d
r
eg
r
ess
io
n
tr
ee
s
(
C
A
R
T
)
,
an
d
Naiv
e
B
ay
es
(
NB
)
.
T
h
e
r
es
u
lts
s
h
o
w
th
at
t
h
e
a
b
o
v
e
m
eth
o
d
s
ar
e
s
u
r
p
ass
ed
b
y
in
c
o
m
p
lete
tr
ee
s
with
im
p
r
o
v
e
d
f
ea
tu
r
e
s
ets.
T
h
e
m
ea
s
u
r
es
o
f
p
er
f
o
r
m
an
ce
t
h
at
ar
e
u
s
ed
f
o
r
ev
alu
atio
n
i
n
clu
d
e
F
-
m
ea
s
u
r
e
,
p
r
ec
is
io
n
,
an
d
r
ec
all
[
2
4
]
.
B
r
ain
t
umo
r
d
etec
tio
n
an
d
s
eg
m
en
tatio
n
o
f
MRI
im
ag
es
u
s
in
g
n
eu
r
al
n
etwo
r
k
s
was
d
escr
ib
ed
.
I
n
an
ef
f
o
r
t
to
im
p
r
o
v
e
y
i
eld
an
d
p
r
ec
is
io
n
,
th
is
wo
r
k
h
as
im
p
lem
en
ted
an
au
to
m
ated
b
r
ain
t
u
m
o
r
d
etec
tio
n
ap
p
r
o
ac
h
;
h
o
wev
e
r
,
th
e
d
iag
n
o
s
tic
tim
e
i
s
d
ec
r
ea
s
ed
.
T
h
e
o
b
jectiv
e
is
to
d
iv
id
e
th
e
tis
s
u
es
in
to
two
g
r
o
u
p
s
:
n
o
r
m
al
an
d
ab
n
o
r
m
al.
I
t
is
p
o
s
s
ib
le
to
ef
f
icien
tly
u
s
e
th
is
tech
n
iq
u
e
to
id
en
tify
th
e
tu
m
o
r
’
s
g
eo
m
etr
ical
d
im
e
n
s
io
n
s
.
T
h
e
aim
ed
at
n
e
u
r
al
n
etwo
r
k
a
p
p
r
o
ac
h
co
n
s
is
ts
o
f
s
ev
er
al
p
h
ases
,
in
cl
u
d
in
g
d
etec
tio
n
,
s
eg
m
en
tatio
n
,
clas
s
if
icatio
n
,
d
im
en
s
io
n
ality
r
e
d
u
ctio
n
,
an
d
f
ea
tu
r
e
e
x
tr
ac
tio
n
.
T
h
e
s
u
g
g
ested
ap
p
r
o
ac
h
f
o
r
t
h
e
id
e
n
tific
atio
n
a
n
d
s
eg
m
e
n
tatio
n
o
f
b
r
a
in
t
u
m
o
r
s
in
t
h
is
s
tu
d
y
is
m
o
r
e
p
r
ec
is
e
an
d
ef
f
icien
t [
2
5
]
.
T
h
e
ac
tiv
e
co
n
to
u
r
m
o
d
el
an
d
s
elf
-
o
r
g
a
n
izin
g
-
m
ap
was
u
s
ed
to
s
eg
m
en
t
b
r
ain
t
u
m
o
r
s
f
r
o
m
MRIs
ef
f
icien
tly
.
I
n
o
r
d
er
t
o
ef
f
ec
ti
v
ely
s
ep
ar
ate
b
r
ain
t
u
m
o
r
s
f
r
o
m
MR
im
ag
es,
th
is
wo
r
k
p
r
o
v
id
es
a
co
m
b
in
atio
n
m
eth
o
d
u
s
in
g
th
e
s
elf
-
o
r
g
an
izin
g
m
ap
(
SOM)
an
d
ac
tiv
e
co
n
to
u
r
m
o
d
el
(
AC
M)
.
E
n
er
g
y
-
b
as
ed
im
ag
e
s
eg
m
en
tatio
n
tech
n
i
q
u
es
k
n
o
wn
as
AC
Ms
ap
p
r
o
ac
h
th
e
tas
k
o
f
s
eg
m
e
n
tatio
n
as
an
o
p
tim
izatio
n
is
s
u
e.
T
h
is
is
d
o
n
e
iter
ativ
ely
d
u
r
in
g
th
e
o
p
tim
izatio
n
p
r
o
ce
s
s
to
h
elp
c
h
o
o
s
e
wh
eth
er
to
r
e
d
u
ce
o
r
in
cr
ea
s
e
th
e
cu
r
r
en
t
co
n
to
u
r
.
I
t
p
er
f
o
r
m
s
th
is
b
y
co
r
r
ec
tly
in
teg
r
ati
n
g
th
e
g
l
o
b
al
d
ata
g
en
er
ated
b
y
th
e
tr
ai
n
ed
SOM
n
eu
r
o
n
s
weig
h
ts
o
r
p
r
o
to
ty
p
es [
2
6
]
.
Ov
er
th
e
y
ea
r
s
,
m
an
y
a
p
p
r
o
ac
h
es
h
av
e
b
ee
n
p
r
esen
te
d
to
d
etec
t
an
d
class
if
y
th
e
b
r
ain
t
um
or
.
Ho
wev
er
,
th
e
r
e
is
a
n
ee
d
o
f
a
tech
n
iq
u
e
th
at
m
ig
h
t
id
e
n
tify
a
b
r
ain
t
u
m
o
r
with
ex
ce
llen
t
a
cc
u
r
ac
y
.
T
h
e
m
ai
n
p
r
o
b
lem
with
cu
r
r
en
t
m
o
d
el
s
is
th
eir
ac
cu
r
ac
y
,
wh
ich
is
im
p
o
r
tan
t
f
o
r
in
tellig
en
t
h
ea
lth
ca
r
e
s
y
s
tem
s
.
T
o
ad
d
r
ess
th
is
p
r
o
b
lem
,
a
v
e
r
y
ac
cu
r
ate
m
o
d
el
will b
e
d
esig
n
ed
i.e
.
,
b
r
ain
t
u
m
o
r
class
if
icatio
n
f
o
r
o
p
t
im
izin
g
p
er
f
o
r
m
an
ce
u
s
in
g
h
y
b
r
id
R
NN
class
if
ier
is
p
r
esen
ted
.
T
h
e
r
em
ain
in
g
wo
r
k
is
ar
r
a
n
g
ed
as
f
o
llo
ws:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2502
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
3
8
,
No
.
3
,
J
u
n
e
2
0
2
5
: 1
9
0
5
-
1
9
1
3
1908
t
h
e
s
ec
tio
n
2
p
r
esen
ted
th
e
b
r
ain
t
u
m
o
r
class
if
icatio
n
f
o
r
o
p
tim
izin
g
p
er
f
o
r
m
an
ce
u
s
in
g
h
y
b
r
id
R
NN
class
if
ier
.
T
h
e
v
alid
atio
n
o
f
t
h
e
r
esu
lts
o
f
th
e
an
aly
s
is
o
f
th
e
s
u
g
g
ested
f
r
am
ewo
r
k
is
d
o
n
e
in
s
ec
tio
n
3
.
L
astl
y
,
s
ec
tio
n
4
p
r
o
v
id
es th
e
co
n
clu
s
io
n
.
2.
M
E
T
H
O
D
I
n
th
is
s
ec
tio
n
,
b
r
ain
t
u
m
o
r
class
if
icatio
n
f
o
r
o
p
tim
izin
g
p
e
r
f
o
r
m
an
ce
u
s
in
g
h
y
b
r
id
R
NN
class
if
ier
i
s
d
escr
ib
ed
.
T
h
e
p
r
esen
ted
f
r
am
ewo
r
k
’
s
b
lo
c
k
d
iag
r
am
is
d
is
p
lay
ed
in
F
ig
u
r
e
1
.
Fo
r
th
e
p
u
r
p
o
s
e
o
f
b
r
ain
t
u
m
o
r
id
en
tific
atio
n
an
d
class
if
icatio
n
,
th
is
m
eth
o
d
u
s
es
a
h
y
b
r
id
R
NN
th
at
co
m
b
in
es
I
n
ce
p
tio
n
R
esNetv
2
with
R
NN.
T
h
e
d
ataset
u
s
ed
in
th
i
s
p
ap
er
is
th
e
b
r
ain
tu
m
o
r
M
R
I
.
On
e
o
f
th
e
m
ain
an
d
m
o
s
t
im
p
o
r
tan
t
task
s
o
f
ev
er
y
ML
p
r
o
ject
is
d
ata
co
llectio
n
.
C
o
n
s
id
er
in
g
th
at
th
e
d
ata
s
er
v
es
as
th
e
alg
o
r
ith
m
s
in
p
u
t.
T
h
u
s
,
th
e
q
u
ality
an
d
ac
cu
r
ac
y
o
f
th
e
d
ata
th
at
is
g
ath
er
ed
d
eter
m
in
es
th
e
ef
f
icien
cy
an
d
ac
cu
r
ac
y
o
f
th
e
al
g
o
r
ith
m
.
T
h
u
s
,
th
e
r
esu
lt
will
b
e
th
e
s
am
e
a
s
th
e
d
ata.
Fo
r
ev
er
y
p
atien
t,
a
v
a
r
i
ab
le
n
u
m
b
er
o
f
im
ag
es
is
r
eq
u
ir
ed
.
B
r
ain
t
u
m
o
r
s
,
tr
au
m
atic
b
r
ain
in
ju
r
y
,
an
o
m
alies
in
d
ev
elo
p
m
en
t,
m
u
l
tip
le
s
cler
o
s
is
,
s
tr
o
k
e,
d
em
e
n
tia,
in
f
ec
tio
n
,
an
d
h
ea
d
ac
h
e
r
ea
s
o
n
s
ca
n
all
b
e
id
en
tifie
d
u
s
in
g
MRI.
T
h
e
p
r
o
ce
s
s
o
f
tr
an
s
f
o
r
m
in
g
u
n
p
r
o
ce
s
s
ed
d
ataset
s
in
to
a
r
ea
d
ab
le,
u
n
d
er
s
tan
d
a
b
le
f
o
r
m
at
th
at
m
ay
b
e
u
s
ed
f
o
r
ad
d
itio
n
al
an
aly
s
is
is
k
n
o
wn
as d
ata
p
r
e
-
p
r
o
ce
s
s
in
g
.
Fo
r
en
s
u
r
in
g
t
h
e
ac
cu
r
ac
y
,
c
o
n
s
is
ten
cy
an
d
co
m
p
leten
ess
o
f
i
n
p
u
t
d
atasets
is
a
cr
u
cial
s
tag
e
in
e
v
er
y
d
ata
a
n
aly
s
is
ef
f
o
r
t.
T
o
im
p
r
o
v
e
th
e
m
o
d
el
’
s
ac
cu
r
ac
y
at
th
is
p
o
in
t,
n
o
is
e
f
r
o
m
th
e
MRI
im
ag
es
will
b
e
r
em
o
v
ed
.
A
lo
t
o
f
n
o
is
e
is
p
r
esen
t in
MRI
im
ag
e
s
,
wh
ich
in
cr
ea
s
es r
ed
u
n
d
an
cy
an
d
r
e
d
u
ce
s
m
o
d
el
ac
cu
r
ac
y
.
n
o
is
e
o
n
its
b
o
r
d
er
s
o
f
an
MR
I
in
cr
ea
s
es
th
e
p
o
s
s
ib
ilit
y
th
at
a
tu
m
o
r
wo
n
’
t
b
e
id
e
n
tifie
d
.
So
h
as
an
im
p
ac
t
o
n
th
e
m
o
d
el
’
s
ac
cu
r
a
cy
.
T
h
ey
p
er
f
o
r
m
ed
p
r
e
-
p
r
o
c
ess
in
g
b
y
b
ein
g
r
ed
u
ce
d
,
s
ca
led
,
an
d
g
r
ay
s
ca
led
.
I
m
ag
es
p
re
-
p
r
o
ce
s
s
in
g
is
d
o
n
e
to
im
p
r
o
v
e
th
e
im
a
g
e
’
s
q
u
ality
,
lo
o
k
s
,
an
d
f
ea
t
u
r
es.
On
e
o
f
th
e
m
o
s
t
f
u
n
d
am
e
n
tal
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
f
o
r
ev
er
y
s
eg
m
en
tatio
n
m
eth
o
d
is
n
o
is
e
r
ed
u
ctio
n
.
T
h
e
g
iv
en
d
ataset
h
as
n
o
is
e
p
r
e
-
f
ilter
ed
o
u
t
o
f
it
alr
ea
d
y
.
T
h
u
s
,
t
h
ey
f
ir
s
t
p
r
e
p
r
o
c
ess
ev
er
y
im
a
g
e
u
s
in
g
o
u
r
o
wn
n
o
is
e
r
ed
u
ctio
n
tech
n
iq
u
e.
T
h
e
im
ag
e
en
h
a
n
ce
m
en
t
ap
p
r
o
a
ch
is
u
s
ed
s
in
ce
th
e
d
ataset
co
n
tain
s
a
f
ew
d
ar
k
im
ag
es.
MRI
d
ata
is
s
u
b
jecte
d
to
a
th
r
esh
o
ld
i
n
g
-
b
ased
tech
n
iq
u
e
to
elim
in
ate
b
ias
f
ield
ar
tifa
cts.
T
h
e
p
r
ep
r
o
ce
s
s
in
g
s
tag
e
also
m
ak
es
ad
v
an
tag
e
o
f
th
e
h
is
to
g
r
am
ex
p
lain
ed
.
E
ac
h
im
a
g
e
in
th
e
d
ataset
is
th
e
f
i
r
s
t
h
is
to
g
r
am
th
at
th
e
in
d
iv
id
u
al
im
a
g
e
f
r
o
m
th
e
d
a
taset
s
p
ec
if
ies.
E
ac
h
r
eg
io
n
o
f
in
ter
est
(
R
o
I
)
in
t
h
e
im
ag
e
h
as
its
o
wn
s
et
o
f
ch
ar
ac
ter
is
tics
th
at
ar
e
ex
tr
ac
t
ed
.
I
n
th
is
r
esear
ch
,
th
e
tu
m
o
r
is
s
eg
m
en
ted
u
s
in
g
s
tati
s
tical
an
d
n
eig
h
b
o
r
h
o
o
d
f
ea
tu
r
e
ex
tr
ac
tio
n
ap
p
r
o
ac
h
es.
T
h
ese
r
etr
iev
e
d
ch
ar
ac
te
r
is
tics
h
av
e
a
n
u
m
b
e
r
o
f
u
s
es
in
th
e
f
ield
o
f
im
ag
e
p
r
o
ce
s
s
in
g
,
s
u
ch
as e
v
al
u
atin
g
th
e
im
ag
e
’
s
q
u
ality
.
Fig
u
r
e
1
.
B
lo
ck
d
iag
r
am
o
f
b
r
ain
t
u
m
o
r
class
if
icatio
n
f
o
r
o
p
tim
izin
g
p
er
f
o
r
m
an
ce
u
s
in
g
h
y
b
r
id
R
NN
class
if
ier
T
h
e
MRI
s
ca
n
s
ar
e
u
s
ed
to
e
x
tr
ac
t
two
g
r
o
u
p
s
o
f
f
ea
tu
r
es:
f
ir
s
t
o
r
d
er
a
n
d
h
ig
h
er
o
r
d
e
r
.
T
h
e
m
an
y
s
tatis
t
ical
ch
ar
ac
ter
is
tics
P
ix
el
in
ten
s
ities
ar
e
ca
lcu
lated
u
s
in
g
ex
tr
ac
tio
n
tech
n
iq
u
es,
s
u
ch
as
s
tan
d
ar
d
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
B
r
a
in
t
u
mo
r
cla
s
s
ifica
tio
n
fo
r
o
p
timiz
in
g
p
erfo
r
ma
n
ce
u
s
in
g
h
yb
r
id
…
(
B
o
y
a
N
eth
a
p
p
a
Ga
r
i Ka
la
va
th
i
)
1909
d
ev
iatio
n
,
h
is
to
g
r
a
m
,
k
u
r
to
s
is
,
s
k
ewn
ess
,
etc.
I
n
th
e
h
ig
h
er
-
o
r
d
er
ex
a
m
p
le,
th
e
co
n
n
ec
tiv
i
ty
r
elatio
n
b
etwe
en
p
ix
els
is
d
eter
m
in
ed
.
I
n
s
ig
h
t
s
eg
m
en
tatio
n
an
d
r
eg
is
tr
atio
n
to
o
lk
it
(
ITK
-
Sn
a
p
)
p
r
o
v
i
d
es
m
an
u
al
d
elin
ea
tio
n
,
im
ag
e
n
av
ig
atio
n
,
a
n
d
s
em
i
-
au
to
m
atic
s
eg
m
en
tatio
n
u
tili
zin
g
ac
tiv
e
co
n
to
u
r
a
p
p
r
o
ac
h
e
s
in
p
r
ep
r
o
ce
s
s
in
g
.
I
t
will
s
u
p
p
ly
th
e
two
-
d
ir
ec
ti
o
n
al
im
ag
e
is
n
ee
d
ed
f
o
r
ad
d
itio
n
al
im
ag
e
p
r
o
ce
s
s
in
g
m
et
h
o
d
s
r
elate
d
to
th
e
s
eg
m
en
tatio
n
p
h
ase.
T
h
e
b
r
ai
n
im
ag
e
R
o
I
is
d
ev
e
lo
p
ed
u
s
in
g
im
ag
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es.
Seg
m
en
ted
b
r
ain
t
umor
im
ag
es
ar
e
th
e
n
u
tili
ze
d
to
ex
tr
ac
t
f
o
r
m
f
ea
t
u
r
es
s
u
ch
a
s
th
e
tu
m
o
r
r
e
g
io
n
’
s
s
o
lid
ity
,
ce
n
ter
o
f
g
r
a
v
ity
,
co
n
v
ex
ity
,
an
d
r
atio
o
f
cir
c
u
l
ar
ity
to
r
ec
tan
g
u
lar
ity
.
On
ly
t
h
e
b
r
ain
t
u
m
o
r
r
em
ain
s
in
th
ese
ex
tr
ac
ted
b
r
ain
t
u
m
o
r
s
af
ter
all
o
th
er
th
in
g
s
h
av
e
b
ee
n
elim
in
ated
.
B
y
ap
p
ly
in
g
m
o
r
p
h
o
lo
g
ical
p
r
o
ce
s
s
es
s
u
ch
as
er
o
s
io
n
,
o
p
en
,
clo
s
e,
a
n
d
f
ilter
in
g
,
th
is
tu
m
o
r
ar
ea
’
s
R
o
I
is
r
etr
iev
ed
.
T
h
e
p
r
o
ce
d
u
r
e
to
ex
tr
ac
t
m
ea
n
in
g
f
u
l
i
n
f
o
r
m
atio
n
f
r
o
m
an
im
ag
e
is
ca
lled
f
ea
t
u
r
e
ex
tr
ac
tio
n
.
Utilizin
g
p
ix
e
l
-
b
ased
f
ea
tu
r
e
ex
tr
ac
tio
n
,
d
a
ta
is
ex
tr
ac
ted
an
d
ca
teg
o
r
ized
as
eith
er
tu
m
o
r
o
r
n
o
n
-
tu
m
o
r
.
T
h
e
q
u
an
tity
o
f
r
ed
u
n
d
a
n
t
d
ata
in
th
e
d
ata
co
llectio
n
is
d
ec
r
ea
s
ed
with
th
e
s
u
p
p
o
r
t
o
f
f
ea
tu
r
e
e
x
tr
ac
tio
n
.
Ultim
ately
,
th
e
p
r
o
ce
s
s
o
f
d
ata
r
ed
u
ctio
n
s
p
ee
d
s
u
p
th
e
lear
n
in
g
,
g
en
er
aliza
tio
n
p
h
ases
an
d
aid
s
in
th
e
co
n
s
tr
u
ctio
n
o
f
th
e
m
o
d
el
with
less
co
m
p
u
tatio
n
al
ef
f
o
r
t.
I
m
p
r
o
v
in
g
o
n
th
e
I
n
ce
p
tio
n
f
a
m
ily
o
f
ar
ch
itectu
r
es,
I
n
ce
p
tio
n
-
R
esNet
-
v
2
i
s
a
CN
N
ar
ch
itectu
r
e
th
at
ad
d
s
r
esid
u
al
co
n
n
ec
tio
n
s
(
w
h
ich
tak
e
th
e
p
lace
o
f
th
e
I
n
ce
p
tio
n
ar
ch
itectu
r
e
’
s
f
ilter
co
n
ca
ten
atio
n
s
tag
e)
.
T
h
e
s
u
g
g
ested
ap
p
r
o
ac
h
a
p
p
li
es
s
eg
m
en
tatio
n
t
h
r
o
u
g
h
th
e
u
s
e
o
f
k
-
m
ea
n
s
clu
s
ter
in
g
.
T
h
e
d
is
tan
ce
b
etwe
en
a
p
o
in
t
an
d
th
e
ce
n
tr
o
i
d
is
ex
p
r
ess
ed
in
E
u
clid
ea
n
ter
m
s
.
T
h
e
clo
s
est
n
ew
ce
n
tr
o
id
an
d
th
e
id
en
tical
d
ata
s
e
t
p
o
in
ts
ar
e
b
in
d
in
g
.
Af
ter
th
at,
a
lo
o
p
is
cr
ea
ted
.
T
h
e
p
lace
s
with
co
m
p
ar
ab
le
p
i
x
el
v
alu
es
ar
e
d
iv
id
ed
in
t
o
two
o
r
m
o
r
e
clu
s
ter
s
as
a
co
n
s
eq
u
en
ce
o
f
t
h
is
lo
o
p
.
Usi
n
g
I
n
c
e
p
tio
n
R
esNetV2
with
R
NN,
b
r
ain
MRI
im
ag
es
ar
e
class
if
ied
as n
o
n
-
tu
m
o
r
o
r
tu
m
o
r
.
A
C
NN
d
esig
n
ca
lled
I
n
ce
p
tio
n
-
R
esNet
-
v
2
ex
p
an
d
s
u
p
o
n
t
h
e
I
n
ce
p
tio
n
f
a
m
ily
o
f
ar
ch
it
ec
tu
r
es
b
y
ad
d
in
g
r
esid
u
al
co
n
n
ec
tio
n
s
,
wh
ich
tak
e
th
e
p
lace
o
f
th
e
I
n
ce
p
tio
n
ar
c
h
itectu
r
e
’
s
f
ilter
co
n
ca
ten
atio
n
s
tag
e.
T
h
e
I
n
ce
p
tio
n
R
estNetv
2
is
t
r
ain
ed
o
n
th
e
I
m
ag
eNe
t
d
ata
b
ase
wh
ich
co
n
tain
s
o
v
er
a
m
illi
o
n
im
ag
es.
T
h
e
n
etwo
r
k
ca
n
ca
teg
o
r
ize
th
e
im
ag
es
in
to
1
,
0
0
0
v
ar
io
u
s
o
b
ject
ty
p
es
an
d
h
as
1
6
4
lay
er
s
.
C
o
n
s
eq
u
en
tly
,
a
wid
e
r
an
g
e
o
f
im
ag
e
r
ich
f
ea
t
u
r
e
r
e
p
r
esen
tatio
n
s
h
av
e
b
ee
n
tr
ai
n
e
d
b
y
t
h
e
n
etwo
r
k
.
A
co
m
p
lex
ar
ch
itectu
r
e
is
u
s
ed
b
y
th
e
I
n
ce
p
tio
n
-
R
esn
et
-
v
2
t
o
ex
tr
ac
t
im
p
o
r
ta
n
t
in
f
o
r
m
ati
o
n
f
r
o
m
th
e
im
a
g
es.
A
lis
t
o
f
esti
m
ated
class
p
r
o
b
a
b
ilit
ies
is
th
e
n
etwo
r
k
’
s
o
u
tp
u
t,
an
d
th
e
in
p
u
t
im
ag
e
’
s
s
ize
is
2
9
9
b
y
2
9
9
p
ix
els.
Star
tin
g
p
r
io
r
to
th
e
weig
h
t m
atr
ix
(
co
n
v
o
lu
tio
n
o
p
er
atio
n
)
m
u
ltip
licatio
n
,
r
esid
u
al
n
etwo
r
k
v
er
s
io
n
2
(
R
esNet
V2
)
p
er
f
o
r
m
s
b
atch
n
o
r
m
aliza
tio
n
a
n
d
r
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
U
)
ac
tiv
atio
n
to
t
h
e
in
p
u
t.
T
h
e
way
a
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
(
R
NN)
f
u
n
ctio
n
s
is
b
y
g
r
ad
u
ally
p
r
o
ce
s
s
in
g
s
eq
u
e
n
tial
d
ata.
I
t
k
ee
p
s
a
h
id
d
en
s
tate
th
at
o
p
er
ates
as
a
ty
p
e
o
f
m
em
o
r
y
,
at
ea
ch
tim
e
s
tep
,
th
e
h
id
d
en
s
tate
f
r
o
m
th
e
p
r
ev
io
u
s
tim
e
s
tep
an
d
th
e
in
p
u
t
d
ata
ar
e
u
p
d
ated
.
R
NN
s
u
ti
lize
p
atter
n
s
to
id
en
tify
th
e
s
e
q
u
en
tial
f
ea
tu
r
es
o
f
d
ata
an
d
p
r
ed
ict
th
e
m
o
s
t
lik
ely
p
atter
n
o
f
d
ev
elo
p
m
en
ts
.
On
e
ty
p
e
o
f
n
eu
r
al
n
etwo
r
k
th
at
is
u
s
ef
u
l
f
o
r
r
ep
r
esen
tin
g
s
eq
u
en
ce
d
ata
is
th
e
R
NN.
Similar
to
th
e
b
e
h
av
io
r
o
f
h
u
m
an
b
r
ai
n
s
,
R
NNs
ar
e
d
er
iv
e
d
f
r
o
m
f
ee
d
-
f
o
r
war
d
n
etwo
r
k
s
.
All
len
g
th
s
o
f
in
p
u
ts
m
ay
b
e
p
r
o
ce
s
s
ed
u
s
in
g
R
NN.
An
y
tim
e
s
er
ies
p
r
ed
icto
r
ca
n
b
en
ef
it
g
r
ea
tly
f
r
o
m
an
R
NN
m
o
d
el
’
s
ab
ilit
y
to
r
etain
all
o
f
th
e
d
ata
t
h
r
o
u
g
h
o
u
t
tim
e.
T
h
e
m
o
d
el
s
iz
e
r
em
ain
s
c
o
n
s
tan
t,
wh
atev
er
th
e
am
o
u
n
t
o
f
th
e
i
n
p
u
t.
W
h
en
d
ea
lin
g
with
s
eq
u
en
tial
d
ata,
R
NN
s
ca
n
p
r
ed
ict
r
esu
lts
th
o
s
e
o
th
er
alg
o
r
ith
m
s
can
’
t.
I
n
ce
p
tio
n
R
esn
etV2
with
R
NN
ca
n
class
if
y
th
e
b
r
ain
t
u
m
o
r
b
etter
th
an
p
r
e
v
io
u
s
m
o
d
e
ls
an
d
it
is
alm
o
s
t
th
e
b
est
m
o
d
el
f
o
r
im
a
g
e
class
if
icatio
n
.
T
h
is
ap
p
r
o
ac
h
h
as
v
er
y
ef
f
ec
tiv
ely
d
etec
ted
an
d
class
if
ied
th
e
b
r
ain
t
umor
.
I
f
th
e
tu
m
o
r
is
d
etec
ted
an
d
class
if
ied
co
r
r
ec
tly
th
en
p
r
o
p
e
r
d
iag
n
o
s
is
is
p
r
o
v
id
ed
as
a
r
esu
lt
p
atien
t
’
s
liv
es will b
e
s
av
ed
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
th
is
s
ec
tio
n
,
b
r
ain
t
u
m
o
r
class
if
icatio
n
f
o
r
o
p
tim
izin
g
p
e
r
f
o
r
m
an
ce
u
s
in
g
h
y
b
r
id
R
NN
class
if
ier
i
s
im
p
lem
en
ted
.
T
h
e
b
r
ai
n
tu
m
o
r
MRI
d
ataset,
wh
ich
in
clu
d
es 7
,
0
2
3
MRI
im
ag
es
o
f
th
e
h
u
m
an
b
r
ain
,
is
u
s
ed
in
th
is
m
eth
o
d
.
B
r
ain
s
ca
n
s
o
f
th
e
co
llected
p
atien
ts
ar
e
p
r
e
-
p
r
o
ce
s
s
ed
to
in
cr
ea
s
e
ac
cu
r
ac
y
a
n
d
r
ed
u
ce
n
o
is
e
.
T
o
d
etec
t
an
d
ca
teg
o
r
ize
th
e
b
r
ain
t
umor
,
C
NN
is
u
s
ed
with
th
e
s
eg
m
en
ted
d
ata.
W
h
en
a
b
r
ain
t
umor
is
d
is
co
v
er
ed
,
it
is
ca
te
g
o
r
ized
in
to
s
ev
er
al
ca
teg
o
r
ie
s
,
in
clu
d
in
g
p
itu
itar
y
,
g
lio
m
a
,
an
d
m
en
in
g
io
m
a.
T
h
e
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
a
r
e
u
s
ed
to
ass
ess
its
p
er
f
o
r
m
an
ce
.
−
Pre
cisi
o
n
:
t
h
e
lev
el
to
wh
ich
th
e
m
o
d
el
p
r
o
d
u
ce
d
ac
cu
r
ate
p
r
ed
ictio
n
s
.
T
h
e
r
atio
o
f
r
ea
l
p
o
s
itiv
es
to
all
p
o
s
itiv
e
p
r
ed
icts
is
k
n
o
wn
as p
r
ec
i
s
io
n
.
−
R
ec
all:
i
t
ca
n
also
know
as
s
e
n
s
itiv
ity
o
r
tr
u
e
p
o
s
itiv
e
r
ate
(
T
PR
)
.
I
t
is
ex
p
r
ess
ed
as
th
e
r
atio
o
f
th
e
to
tal
n
u
m
b
er
o
f
p
o
s
itiv
e
ca
s
es to
th
e
n
u
m
b
e
r
o
f
ac
cu
r
ately
r
ec
o
g
n
ized
p
o
s
itiv
e
in
s
tan
ce
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2502
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
3
8
,
No
.
3
,
J
u
n
e
2
0
2
5
: 1
9
0
5
-
1
9
1
3
1910
−
F1
-
s
co
r
e:
t
h
e
ac
cu
r
ac
y
o
f
a
m
o
d
el
is
d
eter
m
in
e
d
b
y
t
h
e
F1
-
s
co
r
e,
an
ass
ess
m
en
t
m
etr
ic.
I
t
in
teg
r
ates
a
m
o
d
el
’
s
ac
cu
r
ac
y
an
d
r
ec
all
r
atin
g
s
.
T
h
e
n
u
m
b
e
r
o
f
tim
es
a
m
o
d
el
c
o
r
r
ec
tly
p
r
ed
icted
th
r
o
u
g
h
o
u
t
t
h
e
wh
o
le
d
ataset
is
ca
lcu
lated
b
y
th
e
ac
cu
r
ac
y
m
ea
s
u
r
e.
T
h
e
p
er
f
o
r
m
an
ce
o
f
p
r
esen
te
d
ap
p
r
o
ac
h
is
co
m
p
ar
ed
with
d
if
f
er
en
t
class
if
ier
s
lik
e
R
F
an
d
lin
ea
r
r
eg
r
ess
io
n
(
L
R
)
.
T
h
e
T
ab
le
1
s
h
o
ws
th
e
p
er
f
o
r
m
an
ce
an
al
y
s
is
.
C
o
m
p
ar
ed
t
o
R
F,
L
R
cl
ass
if
ier
s
,
p
r
esen
ted
h
y
b
r
id
R
NN
class
if
ier
h
as
b
e
tter
p
r
ec
is
io
n
.
T
h
e
Fig
u
r
e
2
s
h
o
ws
th
e
p
er
f
o
r
m
an
ce
m
etr
ic
s
co
m
p
ar
is
o
n
.
T
h
e
Fig
u
r
e
2
(
a)
s
h
o
ws
th
e
p
r
ec
is
io
n
p
er
f
o
r
m
a
n
ce
an
d
Fig
u
r
e
2
(
b
)
s
h
o
ws
th
e
r
ec
all
co
m
p
ar
is
o
n
.
I
n
F
ig
u
r
e
2
(
a
)
,
th
e
x
-
ax
is
in
d
icate
s
d
if
f
er
en
t
b
r
ain
t
umor
class
if
icatio
n
alg
o
r
ith
m
s
wh
er
ea
s
y
-
a
x
is
in
d
icate
s
p
r
ec
is
io
n
p
er
f
o
r
m
an
ce
.
C
o
m
p
ar
e
d
to
R
F
an
d
L
R
,
p
r
esen
ted
h
y
b
r
id
R
NN
alg
o
r
ith
m
h
as
b
etter
p
r
ec
is
io
n
f
o
r
b
r
ain
t
u
m
o
r
class
if
icatio
n
.
T
h
e
h
y
b
r
id
R
N
N
h
as o
b
tain
ed
b
etter
r
ec
all
th
an
L
R
an
d
R
F a
lg
o
r
ith
m
s
.
T
h
e
Fig
u
r
e
3
s
h
o
ws th
e
ac
cu
r
ac
y
co
m
p
ar
is
o
n
.
I
n
Fig
u
r
e
3
,
x
-
a
x
is
in
d
i
ca
tes
th
e
d
if
f
er
e
n
t
tu
m
o
r
class
if
icatio
n
alg
o
r
ith
m
s
an
d
y
-
a
x
is
in
d
icate
s
th
e
a
cc
u
r
ac
y
v
alu
es.
C
o
m
p
ar
e
d
t
o
L
R
an
d
R
F,
p
r
esen
ted
h
y
b
r
id
R
NN
h
as
o
b
tain
ed
b
etter
ac
cu
r
ac
y
f
o
r
b
r
ain
t
umor
class
if
icatio
n
.
T
h
e
F
ig
u
r
e
4
s
h
o
ws
F1
-
s
co
r
e
co
m
p
ar
is
o
n
.
Pre
s
en
ted
h
y
b
r
id
R
NN
cla
s
s
if
ier
h
as
ac
h
iev
ed
b
etter
F
1
-
s
co
r
e
th
an
L
R
an
d
R
F
a
lg
o
r
ith
m
s
.
Hen
ce
th
is
ap
p
r
o
ac
h
h
as
ac
h
iev
ed
b
ette
r
p
er
f
o
r
m
an
ce
f
o
r
class
if
icatio
n
o
f
b
r
ain
t
u
m
o
r
.
T
ab
le
1
.
Per
f
o
r
m
an
ce
c
o
m
p
a
r
is
o
n
P
e
r
f
o
r
ma
n
c
e
m
e
t
r
i
c
s
Li
n
e
a
r
r
e
g
r
e
s
si
o
n
R
a
n
d
o
m
f
o
r
e
s
t
P
r
e
sen
t
e
d
h
y
b
r
i
d
R
N
N
c
l
a
ss
i
f
i
e
r
P
r
e
c
i
s
i
o
n
(
%)
9
1
.
5
9
2
.
3
9
5
.
6
R
e
c
a
l
l
(
%)
9
0
.
2
3
9
3
.
2
9
6
.
4
A
c
c
u
r
a
c
y
(
%)
9
0
.
1
2
9
2
.
5
6
9
7
.
2
F1
-
sc
o
r
e
(
%)
8
9
.
9
8
9
1
.
4
9
7
.
1
(a
)
(
b
)
Fig
u
r
e
2
.
Per
f
o
r
m
an
c
e
co
m
p
ar
is
o
n
in
ter
m
s
o
f
(
a)
p
r
ec
is
io
n
a
n
d
(
b
)
r
ec
all
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
B
r
a
in
t
u
mo
r
cla
s
s
ifica
tio
n
fo
r
o
p
timiz
in
g
p
erfo
r
ma
n
ce
u
s
in
g
h
yb
r
id
…
(
B
o
y
a
N
eth
a
p
p
a
Ga
r
i Ka
la
va
th
i
)
1911
Fig
u
r
e
3
.
Acc
u
r
ac
y
c
o
m
p
ar
is
o
n
Fig
u
r
e
4
.
F1
-
s
co
r
e
co
m
p
ar
is
o
n
4.
CO
NCLU
SI
O
N
I
n
th
is
wo
r
k
,
b
r
ai
n
t
u
m
o
r
class
if
icatio
n
f
o
r
o
p
tim
izin
g
p
er
f
o
r
m
an
ce
u
s
in
g
h
y
b
r
id
R
NN
class
if
ier
i
s
p
r
esen
ted
.
De
v
elo
p
in
g
a
h
ig
h
ly
ac
cu
r
ate
m
o
d
el
to
id
en
tif
y
a
n
d
ca
teg
o
r
ize
b
r
ain
t
u
m
o
r
s
f
r
o
m
MRI
im
a
g
es
is
th
e
m
ain
aim
.
T
h
is
m
o
d
el
w
o
r
k
s
b
ased
o
n
th
e
h
y
b
r
id
DL
alg
o
r
ith
m
R
NN.
T
h
e
tu
m
o
r
r
e
g
io
n
h
as
b
ee
n
id
en
tifie
d
b
y
a
p
p
ly
in
g
s
eg
m
e
n
tatio
n
tech
n
iq
u
es
to
th
e
s
eg
m
e
n
t.
Usi
n
g
im
a
g
e
p
r
o
ce
s
s
in
g
te
ch
n
iq
u
es,
t
h
e
b
r
ain
im
ag
e
’
s
R
o
I
is
cr
ea
ted
.
Seg
m
en
ted
im
ag
es
o
f
b
r
ain
t
u
m
o
r
s
ar
e
th
en
u
tili
ze
d
to
ex
tr
ac
t
th
e
f
o
r
m
f
ea
tu
r
es.
T
h
e
s
eg
m
en
tatio
n
r
esu
lts
ar
e
a
p
p
li
ed
to
I
n
ce
p
tio
n
R
esNetv
2
with
R
NN
alg
o
r
ith
m
t
o
d
etec
t
a
n
d
class
if
y
th
e
b
r
ai
n
t
umor
.
Firstl
y
,
it
d
etec
ts
wea
t
h
er
a
p
er
s
o
n
h
as
b
r
ain
t
umor
o
r
n
o
t.
I
f
b
r
ain
t
u
m
o
r
d
is
ea
s
e
is
d
etec
ted
th
en
class
if
icatio
n
is
p
er
f
o
r
m
ed
in
to
d
if
f
er
en
t
ty
p
es
s
u
ch
as
0
,
1
,
2
,
3
.
Fin
ally
,
th
e
ap
p
r
o
ac
h
es
p
er
f
o
r
m
an
ce
s
h
av
e
b
ee
n
ca
lcu
lated
.
T
h
e
F1
-
s
co
r
e
,
p
r
e
cisi
o
n
,
ac
cu
r
ac
y
,
a
n
d
r
ec
a
ll
o
f
th
e
s
u
g
g
ested
tech
n
iq
u
e
ar
e
u
s
ed
to
ass
e
s
s
its
p
er
f
o
r
m
an
ce
.
C
o
m
p
ar
e
d
to
p
r
ev
io
u
s
ap
p
r
o
ac
h
es
th
is
ap
p
r
o
ac
h
h
as
ac
h
iev
ed
b
etter
an
d
h
ig
h
p
er
f
o
r
m
an
ce
.
Hen
ce
th
is
ap
p
r
o
ac
h
h
as
d
etec
ted
an
d
class
if
ied
th
e
b
r
ain
tu
m
o
r
v
er
y
ac
cu
r
atel
y
an
d
as
a
r
esu
lt
p
atien
t
’
s
liv
es
will
b
e
s
av
ed
.
T
h
er
ef
o
r
e
,
it
will
b
e
u
s
ed
in
r
ea
l
tim
e
f
o
r
b
r
ain
tu
m
o
r
d
etec
tio
n
an
d
class
if
icatio
n
.
I
n
f
u
t
u
r
e,
h
y
b
r
id
Neu
r
al
n
etwo
r
k
with
U
-
n
ets
will
b
e
d
esig
n
ed
to
f
u
r
th
er
im
p
r
o
v
e
th
e
ac
cu
r
a
cy
o
f
b
r
ain
t
u
m
o
r
class
if
icatio
n
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
B
o
y
a
Neth
ap
p
a
Gar
i
Kala
v
ath
i
✓
✓
✓
✓
✓
✓
✓
✓
Um
ad
ev
i Ram
am
o
o
r
t
h
y
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2502
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
3
8
,
No
.
3
,
J
u
n
e
2
0
2
5
: 1
9
0
5
-
1
9
1
3
1912
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
-
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
i
n
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
o
p
en
ly
av
ailab
le
in
[
J
.
Sh
ed
b
a
lk
ar
et.
al.
,
]
at
h
ttp
://
1
0
.
1
1
5
9
1
/ijeecs.v
3
3
.
i3
.
p
p
1
4
0
5
-
1
4
1
5
.
o
r
g
/[
1
0
.
1
1
5
9
1
/ijeecs.v
3
3
.
i3
.
p
p
1
4
0
5
-
1
4
1
5
]
,
[
1
]
.
-
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
a
r
e
o
p
en
ly
a
v
ailab
le
in
[
S.
Ko
th
ar
i
et.
al.
,
]
at
h
ttp
://
1
0
.
1
1
5
9
1
/ijeecs.v
2
6
.
i3
.
p
p
1
6
5
1
-
1
6
6
1
.
o
r
g
/[
1
0
.
1
1
5
9
1
/ijeecs.v
2
6
.
i3
.
p
p
1
6
5
1
-
1
6
6
1
]
,
[
5
]
.
-
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
o
p
en
l
y
av
ailab
le
in
[
T
.
C
h
ith
am
b
a
r
am
et.
al.
,
]
at
h
ttp
://
1
0
.
2
3
9
5
6
/ijar
css
e/v
7
i3
/0
1
6
4
.
o
r
g
/[
1
0
.
2
3
9
5
6
/ijar
css
e/v
7
i3
/0
1
6
4
]
,
[
2
5
]
.
-
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
will
b
e
a
v
ailab
le
in
[
I
E
E
E
]
[
DOI
:
1
0
.
1
1
0
9
/AC
C
E
SS
.
2
0
2
4
.
3
3
5
9
4
1
8
]
f
o
llo
win
g
a
[
6
m
o
n
th
]
em
b
ar
g
o
f
r
o
m
th
e
d
ate
o
f
p
u
b
licatio
n
to
allo
w
f
o
r
th
e
c
o
m
m
er
cializa
ti
o
n
o
f
r
esear
ch
f
i
n
d
in
g
s
.
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
a
r
e
av
a
ilab
le
o
n
r
eq
u
est
f
r
o
m
th
e
Kag
g
le
Platfo
r
m
[
Ma
s
o
u
d
Nick
p
ar
v
ar
]
.
T
h
e
d
at
a,
wh
ich
co
n
tain
in
f
o
r
m
atio
n
t
h
at
co
u
ld
c
o
m
p
r
o
m
is
e
th
e
p
r
iv
ac
y
o
f
r
esear
c
h
p
ar
ticip
an
ts
,
ar
e
n
o
t
p
u
b
licly
a
v
ailab
le
d
u
e
to
ce
r
tain
r
estrictio
n
s
.
RE
F
E
R
E
NC
E
S
[
1
]
J.
S
h
e
d
b
a
l
k
a
r
a
n
d
K
.
P
r
a
b
h
u
s
h
e
t
t
y
,
“
D
e
e
p
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
m
o
d
e
l
f
o
r
b
r
a
i
n
t
u
m
o
r
se
g
me
n
t
a
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
U
N
e
t
a
n
d
c
h
o
p
p
e
d
V
G
G
N
e
t
,
”
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
E
l
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
(
I
J
E
EC
S
)
,
v
o
l
.
3
3
,
n
o
.
3
,
p
p
.
1
4
0
5
–
1
4
1
5
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
3
3
.
i
3
.
p
p
1
4
0
5
-
1
4
1
5
.
[
2
]
A
.
Ja
b
b
a
r
,
S
.
N
a
s
e
e
m
,
T
.
M
a
h
m
o
o
d
,
T.
S
a
b
a
,
F
.
S
.
A
l
a
mr
i
,
a
n
d
A
.
R
e
h
ma
n
,
“
B
r
a
i
n
t
u
mo
r
d
e
t
e
c
t
i
o
n
a
n
d
m
u
l
t
i
-
g
r
a
d
e
s
e
g
m
e
n
t
a
t
i
o
n
t
h
r
o
u
g
h
h
y
b
r
i
d
c
a
ps
-
V
G
G
N
e
t
m
o
d
e
l
,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
7
2
5
1
8
–
7
2
5
3
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
8
9
2
2
4
.
[
3
]
K
.
V
.
A
r
c
h
a
n
a
a
n
d
G
.
K
o
mar
a
sam
y
,
“
A
n
o
v
e
l
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
b
r
a
i
n
t
u
mo
r
d
e
t
e
c
t
i
o
n
u
si
n
g
t
h
e
b
a
g
g
i
n
g
e
n
s
e
m
b
l
e
w
i
t
h
K
-
n
e
a
r
e
s
t
n
e
i
g
h
b
o
r
,
”
J
o
u
r
n
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
,
v
o
l
.
3
2
,
n
o
.
1
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
5
1
5
/
j
i
sy
s
-
2
0
2
2
-
0
2
0
6
.
[
4
]
A
.
A
.
A
si
r
i
,
T.
A
.
S
o
o
mr
o
,
A
.
A
.
S
h
a
h
,
G
.
P
o
g
r
e
b
n
a
,
M
.
I
r
f
a
n
,
a
n
d
S
.
A
l
q
a
h
t
a
n
i
,
“
O
p
t
i
m
i
z
e
d
b
r
a
i
n
t
u
mo
r
d
e
t
e
c
t
i
o
n
:
a
d
u
a
l
-
mo
d
u
l
e
a
p
p
r
o
a
c
h
f
o
r
M
R
I
i
mag
e
e
n
h
a
n
c
e
men
t
a
n
d
Tu
m
o
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
in
I
EEE
A
c
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
4
2
8
6
8
-
4
2
8
8
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
3
7
9
1
3
6
[
5
]
S
.
K
o
t
h
a
r
i
,
S
.
C
h
i
w
h
a
n
e
,
S
.
Ja
i
n
,
a
n
d
M
.
B
a
g
h
e
l
,
“
C
a
n
c
e
r
o
u
s
b
r
a
i
n
t
u
m
o
r
d
e
t
e
c
t
i
o
n
u
si
n
g
h
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
f
r
a
mew
o
r
k
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
El
e
c
t
ri
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
(
I
J
EEC
S
)
,
v
o
l
.
2
7
,
n
o
.
1
,
p
p
.
1
6
5
1
–
1
6
6
1
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
2
6
.
i
3
.
p
p
1
6
5
1
-
1
6
6
1
.
[
6
]
A
.
Y
o
u
n
i
s
e
t
a
l
.,
“
A
b
n
o
r
mal
b
r
a
i
n
t
u
m
o
r
s
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
R
e
sN
e
t
5
0
a
n
d
i
t
s
c
o
m
p
r
e
h
e
n
si
v
e
e
v
a
l
u
a
t
i
o
n
,
”
in
I
E
EE
A
c
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
7
8
8
4
3
-
7
8
8
5
3
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
4
0
3
9
0
2
[
7
]
S
.
A
si
f
,
W
.
Y
i
,
Q
.
U
.
A
i
n
,
J
.
H
o
u
,
T
.
Y
i
,
a
n
d
J
.
S
i
,
“
I
mp
r
o
v
i
n
g
e
f
f
e
c
t
i
v
e
n
e
ss
o
f
d
i
f
f
e
r
e
n
t
d
e
e
p
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
-
b
a
se
d
mo
d
e
l
s
f
o
r
d
e
t
e
c
t
i
n
g
b
r
a
i
n
t
u
mo
r
s
f
r
o
m
M
R
i
m
a
g
e
s,”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
3
4
7
1
6
–
3
4
7
3
0
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
5
3
3
0
6
.
[
8
]
S
.
S
.
H
u
ss
a
i
n
,
N
.
A
.
W
a
n
i
,
J
.
K
a
u
r
,
N
.
A
h
ma
d
,
a
n
d
S
.
A
h
ma
d
,
“
N
e
x
t
-
g
e
n
e
r
a
t
i
o
n
a
u
t
o
ma
t
i
o
n
i
n
n
e
u
r
o
-
o
n
c
o
l
o
g
y
:
a
d
v
a
n
c
e
d
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
o
r
M
R
I
-
b
a
sed
b
r
a
i
n
t
u
m
o
r
seg
m
e
n
t
a
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
in
I
EE
E
A
c
c
e
ss
,
v
o
l
.
1
3
,
p
p
.
4
1
1
4
1
-
4
1
1
5
8
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
5
.
3
5
4
7
7
9
6
.
[
9
]
S
.
H
o
ssa
i
n
,
A
.
C
h
a
k
r
a
b
a
r
t
y
,
T.
R
.
G
a
d
e
k
a
l
l
u
,
M
.
A
l
a
z
a
b
,
a
n
d
M
.
J.
P
i
r
a
n
,
“
V
i
s
i
o
n
t
r
a
n
sf
o
r
mers
,
e
n
sem
b
l
e
m
o
d
e
l
,
a
n
d
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
l
e
v
e
r
a
g
i
n
g
e
x
p
l
a
i
n
a
b
l
e
A
I
f
o
r
b
r
a
i
n
t
u
m
o
r
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
in
I
E
EE
J
o
u
r
n
a
l
o
f
Bi
o
m
e
d
i
c
a
l
a
n
d
H
e
a
l
t
h
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
2
8
,
n
o
.
3
,
p
p
.
1
2
6
1
-
1
2
7
2
,
M
a
r
c
h
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
JB
H
I
.
2
0
2
3
.
3
2
6
6
6
1
4
.
[
1
0
]
P
.
I
.
R
.
Je
n
i
f
e
r
,
S
.
S
.
S
a
i
k
u
mar
,
B
.
S
.
R
h
a
m
,
K
.
S
o
o
r
y
a
,
a
n
d
P
.
V
.
K
u
mar,
“
B
r
a
i
n
t
u
mo
r
d
e
t
e
c
t
i
o
n
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
Re
s
e
a
r
c
h
i
n
S
c
i
e
n
c
e
,
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
T
e
c
h
n
o
l
o
g
y
(
I
J
ARS
C
T
)
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
2
3
4
–
2
3
9
,
2
0
2
2
,
d
o
i
:
1
0
.
4
8
1
7
5
/
5
6
8
.
[
1
1
]
S
.
G
a
i
k
w
a
d
,
S
.
P
a
t
e
l
,
a
n
d
A
.
S
h
e
t
t
y
,
“
B
r
a
i
n
t
u
mo
r
d
e
t
e
c
t
i
o
n
:
a
n
a
p
p
l
i
c
a
t
i
o
n
b
a
se
d
o
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
2
0
2
1
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
f
o
r E
m
e
rg
i
n
g
T
e
c
h
n
o
l
o
g
y
(
I
N
C
ET)
,
M
a
y
2
0
2
1
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
N
C
ET5
1
4
6
4
.
2
0
2
1
.
9
4
5
6
3
4
7
.
[
1
2
]
H
.
A
.
S
h
a
h
,
F
.
S
a
e
e
d
,
S
.
Y
u
n
,
J.
-
H
.
P
a
r
k
,
A
.
P
a
u
l
,
a
n
d
J.
-
M
.
K
a
n
g
,
“
A
r
o
b
u
s
t
a
p
p
r
o
a
c
h
f
o
r
b
r
a
i
n
t
u
mo
r
d
e
t
e
c
t
i
o
n
i
n
mag
n
e
t
i
c
r
e
so
n
a
n
c
e
i
ma
g
e
s
u
si
n
g
f
i
n
e
t
u
n
e
d
Ef
f
i
c
i
e
n
t
N
e
t
,
”
I
EE
E
A
c
c
e
s
s
,
v
o
l
.
1
0
,
p
p
.
6
5
4
2
6
–
6
5
4
3
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
8
4
1
1
3
.
[
1
3
]
M
.
S
.
M
a
j
i
b
,
M
.
M
.
R
a
h
ma
n
,
T.
M
.
S
.
S
a
z
z
a
d
,
N
.
I
.
K
h
a
n
,
a
n
d
S
.
K
.
D
e
y
,
“
V
G
G
-
S
C
N
e
t
:
a
V
G
G
N
e
t
-
b
a
s
e
d
d
e
e
p
l
e
a
r
n
i
n
g
f
r
a
mew
o
r
k
f
o
r
b
r
a
i
n
t
u
mo
r
d
e
t
e
c
t
i
o
n
o
n
M
R
I
i
mag
e
s,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
9
,
p
p
.
1
1
6
9
4
2
–
1
1
6
9
5
2
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
1
0
5
8
7
4
.
[
1
4
]
H
.
Z
.
El
d
i
n
e
t
a
l
.
,
“
B
r
a
i
n
t
u
mo
r
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
si
n
e
-
c
o
s
i
n
e
f
i
t
n
e
ss
g
r
e
y
w
o
l
f
o
p
t
i
mi
z
a
ti
o
n
,
”
Bi
o
e
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
0
,
n
o
.
1
,
p
.
1
8
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
b
i
o
e
n
g
i
n
e
e
r
i
n
g
1
0
0
1
0
0
1
8
.
[
1
5
]
H
.
Li
u
,
Z
.
N
i
,
D
.
N
i
e
,
D
.
S
h
e
n
,
J.
W
a
n
g
,
a
n
d
Z.
Ta
n
g
,
“
M
u
l
t
i
m
o
d
a
l
b
r
a
i
n
t
u
mo
r
se
g
me
n
t
a
t
i
o
n
b
o
o
st
e
d
b
y
mo
n
o
m
o
d
a
l
n
o
r
ma
l
b
r
a
i
n
i
ma
g
e
s,”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
m
a
g
e
Pr
o
c
e
ss
i
n
g
,
v
o
l
.
3
3
,
p
p
.
1
1
9
9
–
1
2
1
0
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
P
.
2
0
2
4
.
3
3
5
9
8
1
5
.
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
B
r
a
in
t
u
mo
r
cla
s
s
ifica
tio
n
fo
r
o
p
timiz
in
g
p
erfo
r
ma
n
ce
u
s
in
g
h
yb
r
id
…
(
B
o
y
a
N
eth
a
p
p
a
Ga
r
i Ka
la
va
th
i
)
1913
[
1
6
]
A
.
F
a
r
z
a
mn
i
a
,
S
.
H
.
H
a
z
a
v
e
h
,
S
.
S
.
S
i
a
d
a
t
,
a
n
d
E.
G
.
M
o
u
n
g
,
“
M
R
I
b
r
a
i
n
t
u
m
o
r
d
e
t
e
c
t
i
o
n
me
t
h
o
d
s
u
si
n
g
c
o
n
t
o
u
r
l
e
t
t
r
a
n
sf
o
r
m
b
a
se
d
o
n
t
i
me
a
d
a
p
t
i
v
e
s
e
l
f
-
o
r
g
a
n
i
z
i
n
g
ma
p
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
1
1
3
4
8
0
–
1
1
3
4
9
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
3
2
2
4
5
0
.
[
1
7
]
S
.
A
h
ma
d
a
n
d
P
.
K
.
C
h
o
u
d
h
u
r
y
,
“
O
n
t
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
d
e
e
p
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
n
e
t
w
o
r
k
s
f
o
r
b
r
a
i
n
t
u
mo
r
d
e
t
e
c
t
i
o
n
u
si
n
g
M
R
i
ma
g
e
s,
”
I
E
EE
A
c
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
5
9
0
9
9
–
5
9
1
1
4
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
7
9
3
7
6
.
[
1
8
]
M
.
F
.
A
l
mu
f
a
r
e
h
,
M
.
I
mr
a
n
,
A
.
K
h
a
n
,
M
.
H
u
ma
y
u
n
,
a
n
d
M
.
A
si
m,
“
A
u
t
o
mat
e
d
b
r
a
i
n
t
u
mo
r
s
e
g
m
e
n
t
a
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
i
n
M
R
I
u
si
n
g
Y
O
LO
-
b
a
se
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
1
6
1
8
9
–
1
6
2
0
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
3
5
9
4
1
8
.
[
1
9
]
H
.
H
a
b
i
b
,
A
.
M
e
h
m
o
o
d
,
T.
N
a
z
i
r
,
M
.
N
a
w
a
z
,
M
.
M
a
s
o
o
d
,
a
n
d
R
.
M
a
h
u
m,
“
B
r
a
i
n
t
u
m
o
r
s
e
g
m
e
n
t
a
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
2
0
2
1
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
A
p
p
l
i
e
d
a
n
d
En
g
i
n
e
e
ri
n
g
M
a
t
h
e
m
a
t
i
c
s
(
I
C
AE
M)
,
A
u
g
.
2
0
2
1
,
p
p
.
1
3
–
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
E
M
5
3
5
5
2
.
2
0
2
1
.
9
5
4
7
0
8
4
.
[
2
0
]
M
.
B
.
S
a
h
a
a
i
,
G
.
R
.
Jo
t
h
i
l
a
k
sh
m
i
,
a
n
d
S
.
S
i
n
g
h
,
“
B
r
a
i
n
t
u
mo
r
d
e
t
e
c
t
i
o
n
u
s
i
n
g
D
N
N
a
l
g
o
r
i
t
h
m,”
T
u
rk
i
s
h
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r a
n
d
Ma
t
h
e
m
a
t
i
c
s E
d
u
c
a
t
i
o
n
,
v
o
l
.
1
2
,
n
o
.
1
1
,
p
p
.
3
3
3
8
–
334
5
,
2
0
2
1
,
d
o
i
:
1
0
.
1
7
7
6
2
/
t
u
r
c
o
m
a
t
.
v
1
2
i
1
1
.
6
3
7
9
.
[
2
1
]
M
.
S
h
a
r
ma,
P
.
S
h
a
r
ma
,
R
.
M
i
t
t
a
l
,
a
n
d
K
.
G
u
p
t
a
,
“
B
r
a
i
n
t
u
m
o
u
r
d
e
t
e
c
t
i
o
n
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
J
o
u
r
n
a
l
o
f
El
e
c
t
ro
n
i
c
s
a
n
d
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
3
,
n
o
.
4
,
p
p
.
2
9
8
–
3
0
8
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
3
6
5
4
8
/
j
e
i
.
2
0
2
1
.
4
.
0
0
5
.
[
2
2
]
R
.
M
e
h
r
o
t
r
a
,
M
.
A
.
A
n
sari
,
R
.
A
g
r
a
w
a
l
,
a
n
d
R
.
S
.
A
n
a
n
d
,
“
A
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
A
I
-
b
a
se
d
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
b
r
a
i
n
t
u
m
o
r
s,
”
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
,
p
.
1
0
0
0
0
3
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
ml
w
a
.
2
0
2
0
.
1
0
0
0
0
3
.
[
2
3
]
R
.
J
o
sh
i
a
n
d
S
.
S
u
t
h
a
h
a
r
a
n
,
“
P
i
x
e
l
-
l
e
v
e
l
f
e
a
t
u
r
e
s
p
a
c
e
m
o
d
e
l
i
n
g
a
n
d
b
r
a
i
n
t
u
m
o
r
d
e
t
e
c
t
i
o
n
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
1
9
t
h
I
EE
E
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
M
a
c
h
i
n
e
L
e
a
rn
i
n
g
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s,
I
C
MLA
2
0
2
0
,
D
e
c
.
2
0
2
0
,
p
p
.
8
2
1
–
8
2
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
M
LA
5
1
2
9
4
.
2
0
2
0
.
0
0
1
3
4
.
[
2
4
]
S
.
R
.
K
h
a
n
,
M
.
S
i
k
a
n
d
a
r
,
A
.
A
l
m
o
g
r
e
n
,
I
.
U
d
D
i
n
,
A
.
G
u
e
r
r
i
e
r
i
,
a
n
d
G
.
F
o
r
t
i
n
o
,
“
I
o
M
T
-
b
a
s
e
d
c
o
m
p
u
t
a
t
i
o
n
a
l
a
p
p
r
o
a
c
h
f
o
r
d
e
t
e
c
t
i
n
g
b
r
a
i
n
t
u
m
o
r
,
”
F
u
t
u
r
e
G
e
n
e
r
a
t
i
o
n
C
o
m
p
u
t
e
r
S
y
s
t
e
m
s
,
v
o
l
.
1
0
9
,
p
p
.
3
6
0
–
3
6
7
,
A
u
g
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
u
t
u
r
e
.
2
0
2
0
.
0
3
.
0
5
4
.
[
2
5
]
T.
C
h
i
t
h
a
m
b
a
r
a
m
a
n
d
K
.
P
e
r
u
m
a
l
,
“
B
r
a
i
n
t
u
mo
r
d
e
t
e
c
t
i
o
n
a
n
d
se
g
me
n
t
a
t
i
o
n
i
n
M
R
I
i
ma
g
e
s
u
si
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
Re
se
a
rc
h
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
S
o
f
t
w
a
r
e
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
7
,
n
o
.
3
,
p
p
.
1
5
5
–
1
6
4
,
M
a
r
.
2
0
1
7
,
d
o
i
:
1
0
.
2
3
9
5
6
/
i
j
a
r
c
sse
/
v
7
i
3
/
0
1
6
4
.
[
2
6
]
G
.
S
a
n
d
h
y
a
,
G
.
B
.
K
a
n
d
e
,
a
n
d
T
.
S
a
t
y
a
S
a
v
i
t
h
r
i
,
“
A
n
e
f
f
i
c
i
e
n
t
M
R
I
b
r
a
i
n
t
u
mo
r
s
e
g
m
e
n
t
a
t
i
o
n
b
y
t
h
e
f
u
si
o
n
o
f
a
c
t
i
v
e
c
o
n
t
o
u
r
mo
d
e
l
a
n
d
se
l
f
-
o
r
g
a
n
i
z
i
n
g
-
m
a
p
,
”
J
o
u
r
n
a
l
o
f
B
i
o
m
i
m
e
t
i
c
s
,
Bi
o
m
a
t
e
r
i
a
l
s
a
n
d
Bi
o
m
e
d
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
4
0
,
p
p
.
7
9
–
9
1
,
F
e
b
.
2
0
1
9
,
d
o
i
:
1
0
.
4
0
2
8
/
w
w
w
.
s
c
i
e
n
t
i
f
i
c
.
n
e
t
/
J
B
B
B
E.
4
0
.
7
9
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Mrs
.
Bo
y
a
Ne
th
a
p
p
a
G
a
r
i
K
a
la
v
a
th
i
is
c
u
rre
n
t
ly
w
o
r
k
in
g
a
s
a
ss
istan
t
p
ro
fe
ss
o
r
i
n
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
Dra
v
id
ia
n
U
n
iv
e
rsit
y
,
Ku
p
p
a
m
,
A
n
d
h
ra
P
ra
d
e
sh
,
I
n
d
ia
a
n
d
sh
e
is
p
u
rs
u
in
g
P
h
.
D
.
in
S
OSS
,
CM
R
Un
iv
e
rsity
(O
M
BR
Ca
m
p
u
s),
Be
n
g
a
lu
r
u
,
Ka
r
n
a
tak
a
,
I
n
d
ia.
He
r
a
re
a
o
f
re
se
a
rc
h
is
m
a
c
h
in
e
lea
rn
in
g
.
S
h
e
o
r
g
a
n
ize
d
a
UG
C
sp
o
n
s
o
re
d
tw
o
-
d
a
y
Na
ti
o
n
a
l
le
v
e
l
c
o
n
fe
re
n
c
e
o
rg
a
n
ize
d
o
n
b
ig
d
a
ta
Tec
h
n
o
lo
g
ies
a
n
d
Ap
p
li
c
a
ti
o
n
in
Dra
v
i
d
ian
Un
i
v
e
rsity
o
n
M
a
rc
h
2
0
1
7
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
n
k
a
la
v
a
th
i
1
2
3
@g
m
a
il
.
c
o
m
.
Dr
.
Um
a
d
e
v
i
Ra
m
a
m
o
o
r
th
y
a
M
.
S
.
i
n
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
a
n
d
M
a
n
a
g
e
m
e
n
t
fro
m
Bh
a
ra
th
iar
Un
iv
e
rsity
,
h
a
s
c
o
m
p
lete
d
h
e
r
M
.
P
h
i
l
.
in
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
P
h
.
D
.
in
Co
m
p
u
ter
S
c
ien
c
e
a
t
P
e
riy
a
r
Un
i
v
e
rsity
,
S
a
lem
a
n
d
p
re
se
n
tl
y
w
o
rk
i
n
g
a
s
a
ss
o
c
iate
p
ro
fe
ss
o
r
i
n
CM
R
U
n
iv
e
rsit
y
,
Ba
n
g
a
lo
re
,
Ka
rn
a
t
a
k
a
.
Wi
t
h
1
8
y
e
a
rs o
f
tea
c
h
in
g
e
x
p
e
rie
n
c
e
a
n
d
7
y
e
a
rs
o
f
re
se
a
rc
h
e
x
p
e
rien
c
e
,
sh
e
h
a
s
b
e
e
n
p
re
se
n
ti
n
g
a
n
d
p
u
b
li
s
h
e
d
p
a
p
e
rs
in
se
v
e
ra
l
In
tern
a
ti
o
n
a
l
a
n
d
Na
ti
o
n
a
l
Co
n
fe
r
e
n
c
e
s
a
n
d
j
o
u
r
n
a
ls
i
n
d
e
x
e
d
b
y
S
CI
Ex
p
a
n
d
e
d
,
S
c
o
p
u
s,
UG
C
Ca
re
a
n
d
UG
C
a
p
p
ro
v
e
d
l
ist.
S
h
e
i
s
a
m
e
m
b
e
r
o
f
IAENG
.
S
h
e
h
a
s
p
u
b
li
sh
e
d
p
a
ten
ts
a
n
d
g
o
t
d
e
sig
n
p
a
ten
t
b
y
In
tellec
tu
a
l
P
r
o
p
e
rty
,
G
o
v
e
rn
m
e
n
t
o
f
In
d
ia.
Cu
rre
n
tl
y
sh
e
is
g
u
i
d
in
g
6
re
se
a
rc
h
s
c
h
o
lars
a
n
d
re
c
o
g
n
ize
d
with
v
a
rio
u
s
a
wa
rd
s
su
c
h
a
s
b
e
st
y
o
u
n
g
sc
ien
ti
st
a
wa
rd
,
b
e
st
a
c
a
d
e
m
icia
n
a
wa
rd
,
a
n
d
b
e
st
p
a
p
e
r
a
wa
rd
.
S
h
e
is
e
d
it
o
rial
b
o
a
r
d
m
e
m
b
e
r
a
n
d
re
v
iew
m
e
m
b
e
r
in
v
a
ri
o
u
s
re
p
u
te
d
n
a
ti
o
n
a
l
a
n
d
i
n
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls.
S
h
e
h
a
s
i
n
v
it
e
d
a
s
re
so
u
rc
e
p
e
rso
n
fo
r
g
u
e
st t
a
lk
,
se
m
in
a
r
a
n
d
c
u
lt
u
ra
l
.
S
h
e
h
a
s o
r
g
a
n
ize
d
v
a
rio
u
s e
v
e
n
ts a
t
Na
ti
o
n
a
l
a
n
d
I
n
tern
a
t
i
o
n
a
l
Lev
e
l.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
u
m
a
d
e
v
i.
r@c
m
r.
e
d
u
.
i
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.