I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
9
,
No
.
2
,
A
p
r
il
201
9
,
p
p
.
1410
~
1
4
1
7
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
9
i
2
.
pp
1
4
1
0
-
1417
1410
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
A
no
v
el f
ra
m
ew
o
rk f
o
r e
ff
i
cient
id
entif
ica
tion o
f
bra
in cancer
regi
o
n f
ro
m
brain
M
RI
P
a
rv
a
t
i A
ng
a
di
1
,
M
.
Na
g
end
ra
2
,
H
a
nu
m
a
ntha
p
pa
M
.
3
1
Ra
y
a
las
e
e
m
a
Un
iv
e
rsit
y
,
Ku
rn
o
o
l,
In
d
ia
2
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
&
T
e
c
h
n
o
l
o
g
y
,
S
K Un
iv
e
rsit
y
,
In
d
ia
3
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
,
Ba
n
g
a
lo
re
Un
iv
e
rsity
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
2
2
,
2
0
1
7
R
ev
i
s
ed
J
u
l 1
7
,
2
0
1
8
A
cc
ep
ted
Sep
2
,
2
0
1
8
Dia
g
n
o
sis
o
f
b
ra
in
c
a
n
c
e
r
u
sin
g
e
x
isti
n
g
i
m
a
g
in
g
te
c
h
n
iq
u
e
s,
e
.
g
.
,
M
a
g
n
e
ti
c
Re
so
n
a
n
c
e
Im
a
g
in
g
(M
RI)
is
sh
r
o
u
d
e
d
w
it
h
v
a
rio
u
s
d
e
g
re
e
s
o
f
c
h
a
ll
e
n
g
e
s.
A
t
p
re
se
n
t,
th
e
re
a
re
v
e
r
y
f
e
w
sig
n
if
ica
n
t
re
se
a
r
c
h
m
o
d
e
ls
f
o
c
u
sin
g
o
n
in
tro
d
u
c
i
n
g
so
m
e
n
o
v
e
l
a
n
d
u
n
iq
u
e
so
l
u
ti
o
n
s
to
w
a
rd
s
su
c
h
p
r
o
b
lem
s
o
f
d
e
tec
ti
o
n
.
M
o
re
o
v
e
r,
e
x
isti
n
g
tec
h
n
i
q
u
e
s
a
re
f
o
u
n
d
t
o
h
a
v
e
les
se
r
a
c
c
u
ra
c
y
a
s
c
o
m
p
a
re
d
to
o
th
e
r
d
e
tec
ti
o
n
sc
h
e
m
e
s.
T
h
e
re
f
o
re
,
th
e
p
ro
p
o
se
d
p
a
p
e
r
p
re
se
n
ts
a
f
ra
m
e
w
o
rk
th
a
t
in
tr
o
d
u
c
e
s
a
se
ries
o
f
si
m
p
le
a
n
d
c
o
m
p
u
tat
i
o
n
a
ll
y
c
o
st
-
e
ffe
c
ti
v
e
tec
h
n
iq
u
e
s
th
a
t
h
a
v
e
a
s
siste
d
in
lev
e
ra
g
in
g
th
e
a
c
c
u
ra
c
y
lev
e
l
to
a
v
e
r
y
h
ig
h
e
r
d
e
g
re
e
.
T
h
e
p
ro
p
o
s
e
d
f
ra
m
e
w
o
rk
ta
k
e
s
th
e
in
p
u
t
i
m
a
g
e
a
n
d
su
b
jec
ts
it
to
n
o
n
-
c
o
n
v
e
n
ti
o
n
a
l
se
g
m
e
n
tatio
n
m
e
c
h
a
n
is
m
f
o
ll
o
w
e
d
b
y
o
p
ti
m
izin
g
th
e
p
e
rf
o
rm
a
n
c
e
u
s
in
g
d
irec
ted
a
c
y
c
li
c
g
ra
p
h
,
Ba
y
e
sia
n
Ne
tw
o
rk
,
a
n
d
n
e
u
ra
l
n
e
tw
o
rk
.
T
h
e
stu
d
y
o
u
tco
m
e
o
f
th
e
p
ro
p
o
se
d
sy
ste
m
sh
o
w
s
th
e
sig
n
if
ica
n
tl
y
h
ig
h
e
r
d
e
g
re
e
o
f
a
c
c
u
ra
c
y
in
d
e
tec
ti
o
n
p
e
rf
o
rm
a
n
c
e
a
s
c
o
m
p
a
re
d
to
f
re
q
u
e
n
tl
y
e
x
isti
n
g
a
p
p
r
o
a
c
h
e
s
.
K
ey
w
o
r
d
s
:
A
cc
u
r
ac
y
B
r
ain
c
an
ce
r
Ma
g
n
e
tic
r
eso
n
a
n
ce
i
m
ag
i
n
g
Op
ti
m
izatio
n
T
u
m
o
r
d
etec
tio
n
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
P
ar
v
ati
An
g
ad
i
,
R
a
y
ala
s
ee
m
a
Un
i
v
er
s
i
t
y
,
Ku
r
n
o
o
l,
I
n
d
ia
.
E
m
ail:
p
ar
v
ati_
a
n
g
ad
i
@
y
ah
o
o
.
co
m
1.
I
NT
RO
D
UCT
I
O
N
B
r
ain
ca
n
ce
r
is
co
n
s
id
er
ed
as
o
n
e
o
f
th
e
m
o
s
t
let
h
al
f
o
r
m
o
f
th
e
ca
n
ce
r
in
h
u
m
a
n
b
ein
g
as
w
h
er
e
th
e
co
m
p
lica
tio
n
s
o
f
d
iag
n
o
s
is
a
n
d
tr
ea
t
m
e
n
t
is
e
x
p
o
n
en
tiall
y
h
ig
h
[
1
]
.
No
r
m
all
y
,
b
r
ain
c
an
ce
r
is
a
s
ta
g
e
o
f
ca
n
ce
r
w
h
er
e
a
b
r
ai
n
r
eg
io
n
h
as
p
r
esen
ce
o
f
eit
h
er
lesi
o
n
s
o
r
tu
m
o
r
[
2
]
.
L
e
s
io
n
s
ar
e
r
eq
u
ir
ed
to
b
e
r
ep
air
e
d
in
o
r
d
er
to
s
to
p
b
ein
g
ca
u
s
in
g
f
u
r
t
h
er
in
ter
n
a
l
h
e
m
o
r
r
h
ag
e.
Si
m
ilar
l
y
,
b
r
ain
tu
m
o
r
c
o
u
ld
b
e
b
en
ig
n
o
r
m
ali
g
n
a
n
t
[
3
]
.
Ho
w
e
v
er
,
in
b
o
th
th
e
ca
s
e
s
,
an
e
x
p
en
s
iv
e
s
u
r
g
er
y
w
it
h
co
m
p
lica
ted
s
u
r
g
ical
eq
u
ip
m
e
n
t,
p
r
o
ce
d
u
r
es,
an
d
h
ig
h
l
y
s
k
ille
d
s
u
r
g
eo
n
i
s
r
eq
u
ir
ed
.
A
ll
t
h
is
j
u
s
t
b
eg
in
s
w
it
h
t
h
e
d
iag
n
o
s
is
s
ta
g
e
w
h
er
e
n
o
r
m
all
y
Ma
g
n
e
tic
R
e
s
o
n
a
n
c
e
I
m
ag
in
g
(
MRI)
i
s
h
ig
h
l
y
p
r
ef
er
r
ed
in
i
n
itial
s
ta
g
e
o
f
an
al
y
s
i
s
[
4
]
.
Ho
w
e
v
er
,
ap
ar
t
f
r
o
m
MRI,
th
er
e
ar
e
o
th
er
i
m
a
g
in
g
tec
h
n
iq
u
es
to
o
v
iz.
C
o
m
p
u
ted
T
o
m
o
g
r
ap
h
y
(
C
T
)
s
ca
n
,
Po
s
itro
n
E
m
is
s
io
n
T
o
m
o
g
r
ap
h
y
(
P
E
T
)
s
ca
n
[
5
]
.
Alth
o
u
g
h
,
w
it
h
t
h
e
i
n
clu
s
io
n
o
f
tec
h
n
o
lo
g
y
,
r
ad
io
l
o
g
ical
s
t
u
d
ies
h
a
v
e
s
ig
n
i
f
ica
n
tl
y
i
m
p
r
o
v
ed
.
Ho
w
e
v
er
,
th
e
y
h
av
e
a
li
m
itat
io
n
to
o
[
6
]
.
A
t
p
r
esen
t,
all
t
h
e
i
m
a
g
i
n
g
tec
h
n
iq
u
es
co
u
ld
j
u
s
t
as
s
is
t
s
i
n
ca
p
t
u
r
in
g
t
h
e
r
eg
io
n
s
u
s
p
ec
ted
f
r
o
m
ca
n
ce
r
f
r
o
m
v
er
y
in
ter
n
al
-
d
ep
th
(
3
D
Do
p
p
ler
s
ca
n
w
i
th
m
u
lti
-
s
lice
s
)
,
h
o
w
ev
er
,
t
h
er
e
is
n
o
s
u
c
h
m
ac
h
i
n
es
o
r
tec
h
n
o
lo
g
y
w
h
o
o
f
f
er
s
co
n
clu
s
i
v
e
in
f
er
en
ce
o
f
th
e
r
esu
lta
n
t
i
m
a
g
es.
I
t
o
n
l
y
d
ep
en
d
s
o
n
t
h
e
e
x
p
er
ien
ce
o
f
p
h
y
s
icia
n
t
h
at
t
h
e
i
n
f
er
en
ce
i
s
m
ad
e
co
n
s
id
er
i
n
g
a
s
lig
h
t
p
r
o
b
ab
ilit
y
t
h
at
h
u
m
a
n
er
r
o
r
.
Fr
o
m
r
esear
c
h
v
ie
w
p
o
i
n
t,
th
er
e
h
as
b
ee
n
a
s
er
ies
o
f
r
esear
ch
w
o
r
k
b
ein
g
ca
r
r
ied
o
u
t
to
w
ar
d
ca
n
ce
r
d
ete
ctio
n
p
r
o
b
le
m
;
h
o
w
ev
er
m
aj
o
r
it
y
o
f
t
h
e
e
x
is
t
in
g
r
esear
c
h
w
o
r
k
h
a
s
ac
t
u
all
y
n
o
t
f
o
cu
s
ed
o
n
b
r
ain
M
R
I
i
m
ag
e
s
.
T
h
er
e
ar
e
v
er
y
les
s
n
u
m
b
er
o
f
s
i
g
n
i
f
ica
n
t
r
esear
ch
w
o
r
k
to
w
ar
d
s
id
e
n
ti
f
icatio
n
o
f
b
r
ain
t
u
m
o
r
in
r
ec
en
t
ti
m
es
.
T
h
e
m
o
s
t
r
ec
e
n
t
s
u
r
v
e
y
is
c
ar
r
ied
o
u
t
3
y
ea
r
b
ac
k
b
y
As
h
w
at
h
y
[
7
]
to
p
r
o
v
e
th
at
n
o
t
m
u
c
h
p
r
o
g
r
ess
h
a
s
h
ap
p
en
ed
in
th
is
ar
ea
o
f
ca
n
ce
r
d
etec
tio
n
.
T
h
e
co
m
p
licatio
n
in
b
r
ain
ca
n
ce
r
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
A
n
o
ve
l fra
mewo
r
k
fo
r
efficien
t id
en
tifi
ca
tio
n
o
f b
r
a
i
n
ca
n
ce
r
r
eg
io
n
fr
o
m
b
r
a
in
MRI
(
P
a
r
va
ti A
n
g
a
d
i
)
1411
v
er
y
d
if
f
er
en
t
t
h
an
o
th
er
f
o
r
m
s
o
f
ca
n
ce
r
e.
g
.
i)
it
is
h
ig
h
l
y
g
r
a
y
s
ca
le
i
m
a
g
e
w
h
er
e
t
h
e
tu
m
o
r
r
eg
io
n
s
ar
e
v
er
y
less
id
e
n
ti
f
ied
ac
cu
r
atel
y
f
r
o
m
r
a
w
i
m
a
g
es,
ii)
p
er
f
o
r
m
i
n
g
p
r
ep
r
o
ce
s
s
in
g
o
n
M
R
I
i
m
ag
e
co
u
ld
lead
to
lo
s
s
o
f
s
o
m
e
s
i
g
n
i
f
ican
t
in
f
o
r
m
at
io
n
u
n
t
il
an
d
u
n
le
s
s
it
is
n
o
t
ass
u
r
ed
th
at
it
h
a
s
s
o
m
e
n
o
is
e
o
r
e
r
r
o
r
s
,
iii)
n
o
r
m
all
y
b
r
ain
i
m
a
g
e
s
ar
e
h
i
g
h
l
y
s
y
m
m
etr
ical
i
n
n
at
u
r
e
th
a
t
ca
u
s
es
a
g
r
ea
ter
d
eg
r
ee
o
f
ch
a
llen
g
es
w
h
e
n
i
t
co
m
e
s
to
f
ea
t
u
r
e
ex
tr
ac
t
io
n
p
r
o
ce
s
s
,
iv
)
u
s
a
g
e
o
f
tr
ai
n
i
n
g
o
r
m
ac
h
i
n
e
lear
n
i
n
g
al
g
o
r
ith
m
co
u
ld
r
es
u
lt
in
g
e
n
er
atio
n
o
f
h
ig
h
er
q
u
an
tit
y
o
f
f
alse
p
o
s
iti
v
e
u
n
til
a
n
d
u
n
less
a
p
r
o
p
er
s
t
o
p
p
in
g
f
u
n
ctio
n
i
s
d
esi
g
n
ed
o
r
d
ev
elo
p
a
s
tr
ate
g
y
th
at
ca
n
r
ec
o
g
n
ize
th
e
elite
o
u
tco
m
e
s
.
S
u
c
h
co
m
p
lica
tio
n
s
ar
e
f
o
u
n
d
v
er
y
les
s
to
b
e
as
s
u
m
ed
i
n
e
x
is
t
in
g
s
y
s
te
m
t
h
at
ca
u
s
e
s
in
cr
ea
s
in
g
n
u
m
b
er
o
f
r
esear
c
h
ef
f
o
r
t
in
th
i
s
d
ir
ec
tio
n
[
8
]
,
[9
]
.
I
t
is
also
s
ee
n
t
h
at
s
eg
m
e
n
tatio
n
is
p
ar
t
a
n
d
p
ar
ce
l
o
f
al
m
o
s
t
e
v
er
y
d
etec
tio
n
tec
h
n
iq
u
es
in
ex
i
s
ti
n
g
s
y
s
te
m
;
h
o
w
ev
er
,
th
e
tech
n
iq
u
e
s
ar
e
to
o
s
tr
aig
h
tf
o
r
w
ar
d
.
E
x
is
ti
n
g
s
e
g
m
en
tati
o
n
f
o
cu
s
es
o
n
j
u
s
t
f
o
r
eg
r
o
u
n
d
d
etails
w
h
er
ea
s
in
o
r
d
er
to
p
e
r
f
o
r
m
cl
u
s
ter
i
n
g
a
n
d
class
i
f
icatio
n
f
o
r
b
ig
g
er
d
ata
s
et,
th
e
b
ac
k
g
r
o
u
n
d
in
f
o
r
m
atio
n
i
s
eq
u
all
y
ess
e
n
tial.
T
h
er
e
is
a
lo
t
o
f
s
c
o
p
e
o
f
im
p
r
o
v
e
m
e
n
t
i
n
ad
d
r
e
s
s
i
n
g
t
h
e
p
r
o
b
le
m
o
f
d
etec
ti
n
g
b
r
ain
tu
m
o
r
w
h
ich
w
e
f
i
n
d
v
er
y
le
s
s
i
n
n
u
m
b
er
i
n
ex
is
ti
n
g
s
y
s
te
m
a
n
d
th
er
eb
y
it
p
o
s
es a
s
ig
n
i
f
ican
t r
esear
c
h
g
a
p
.
T
h
er
ef
o
r
e,
th
is
m
a
n
u
s
cr
ip
t
o
f
f
er
s
a
v
er
y
s
i
m
p
le
o
p
ti
m
izati
o
n
tech
n
iq
u
e
o
f
b
r
ain
t
u
m
o
r
d
etec
tio
n
w
h
er
e
th
er
e
i
s
s
p
lit
e
m
p
h
a
s
is
o
n
co
m
p
u
tatio
n
a
l
ef
f
icie
n
c
y
as
w
ell
a
s
s
y
s
te
m
p
er
f
o
r
m
an
ce
co
n
ce
r
n
i
n
g
ac
cu
r
ac
y
.
T
h
e
p
o
ten
tial
f
ea
t
u
r
es
o
f
Ne
u
r
al
Net
w
o
r
k
,
a
B
ay
es
ian
n
et
w
o
r
k
,
w
ater
s
h
ed
tr
an
s
f
o
r
m
-
b
ased
tech
n
iq
u
es
w
er
e
h
ar
n
e
s
s
ed
to
o
p
ti
m
ize
t
h
e
ac
c
u
r
ac
y
p
er
f
o
r
m
an
ce
.
Usa
g
e
o
f
s
u
c
h
tec
h
n
i
q
u
es
r
es
u
lt
s
i
n
n
o
n
-
iter
ativ
e
a
n
d
p
r
o
g
r
ess
iv
e
e
n
h
an
ce
m
e
n
t
o
f
th
e
e
x
tr
ac
tio
n
o
f
in
f
o
r
m
atio
n
t
h
at
r
ed
ef
i
n
es
t
h
e
v
alu
e
o
f
f
ea
t
u
r
e
s
b
ei
n
g
ex
tr
ac
ted
t
h
at
f
in
all
y
r
esu
lt
s
i
n
o
p
ti
m
al
p
er
f
o
r
m
an
ce
in
th
e
id
en
t
if
ica
tio
n
o
f
b
r
ain
t
u
m
o
r
r
e
g
io
n
ex
tr
ac
tio
n
f
r
o
m
t
h
e
M
R
I
i
m
a
g
es
o
f
th
e
b
r
ai
n
.
Sectio
n
1
.
1
d
is
cu
s
s
es
t
h
e
e
x
is
t
in
g
liter
at
u
r
e
f
o
llo
w
ed
b
y
t
h
e
d
is
cu
s
s
io
n
o
f
r
esear
ch
p
r
o
b
lem
s
i
n
Sectio
n
1
.
2
a
n
d
p
r
o
p
o
s
ed
s
o
lu
tio
n
in
1
.
3
.
Sectio
n
2
d
is
cu
s
s
es
al
g
o
r
ith
m
i
m
p
le
m
en
ta
tio
n
f
o
llo
w
ed
b
y
t
h
e
d
is
cu
s
s
io
n
o
f
r
esu
lt
a
n
al
y
s
i
s
in
Sectio
n
3
.
Fin
all
y
,
t
h
e
co
n
clu
s
i
v
e
r
e
m
ar
k
s
ar
e
p
r
o
v
id
ed
in
Sectio
n
4
.
T
h
is
s
ec
tio
n
d
is
c
u
s
s
e
s
ab
o
u
t
t
h
e
e
x
is
ti
n
g
r
esear
c
h
ap
p
r
o
ac
h
b
ei
n
g
ca
r
r
ied
o
u
t
to
w
ar
d
s
id
e
n
ti
f
icatio
n
o
f
b
r
ain
ca
n
ce
r
.
T
h
e
s
t
u
d
y
ca
r
r
ied
o
u
t
b
y
An
it
h
a
a
n
d
Mu
r
u
g
a
v
alli
[
1
0
]
h
av
e
p
r
ese
n
ted
a
clas
s
if
icatio
n
tech
n
iq
u
e
f
o
r
in
v
es
tig
a
tin
g
b
r
ain
t
u
m
o
u
r
ce
ll
s
u
s
i
n
g
K
-
Nea
r
est
Nei
g
h
b
o
r
alg
o
r
it
h
m
.
Usa
g
e
o
f
s
o
p
h
is
ticated
i
m
a
g
e
ca
p
t
u
r
i
n
g
d
ev
ice
s
w
a
s
i
n
tr
o
d
u
ce
d
in
th
e
s
t
u
d
y
o
f
B
ag
h
ae
i
et
a
l
.
[
1
1
]
f
o
r
id
en
t
if
ica
ti
o
n
o
f
le
s
io
n
s
f
r
o
m
th
e
p
h
an
to
m
b
r
ain
i
m
a
g
es
t
h
at
h
as
ex
h
ib
ited
th
e
ca
p
ab
ilit
y
t
o
id
en
tify
le
s
s
th
a
n
7
m
m
s
ize
o
f
lesi
o
n
s
.
Si
m
ilar
d
ir
ec
tio
n
o
f
t
h
e
s
tu
d
y
to
w
ar
d
s
d
etec
tio
n
p
r
o
c
ess
w
a
s
also
ca
r
r
ied
o
u
t
b
y
B
ed
d
ad
an
d
Hac
h
e
m
i
[
1
2
]
w
h
o
h
av
e
u
s
ed
f
u
zz
y
cl
u
s
ter
i
n
g
m
et
h
o
d
f
o
r
class
if
ica
tio
n
alo
n
g
w
it
h
th
e
lev
el
s
et
a
l
g
o
r
it
h
m
.
Se
g
m
en
tatio
n
h
as
b
ee
n
m
ar
k
ed
as
r
o
le
p
lay
er
i
n
m
aj
o
r
it
y
o
f
th
e
e
x
is
t
in
g
s
t
u
d
ies.
W
o
r
k
d
o
n
e
b
y
De
m
ir
h
a
n
et
a
l
.
[
1
3
]
h
as
p
r
esen
ted
a
s
i
m
p
le
s
e
g
m
en
tat
io
n
p
r
o
ce
s
s
u
s
i
n
g
s
e
lf
-
o
r
g
a
n
izi
n
g
m
ap
an
d
v
ec
to
r
q
u
a
n
tizat
io
n
.
T
h
e
tec
h
n
iq
u
e
h
a
s
al
s
o
u
s
ed
w
a
v
elet
s
f
o
r
ex
tr
ac
tin
g
f
ea
t
u
r
es.
Si
m
ilar
p
r
o
b
lem
to
w
ar
d
s
s
eg
m
e
n
tat
io
n
w
a
s
also
ad
d
r
ess
ed
b
y
Ha
m
a
m
ci
et
al
.
[
1
4
]
o
n
co
n
tr
asted
i
m
ag
e
u
s
i
n
g
ce
llu
lar
au
to
m
a
ta.
Har
ith
a
[
1
5
]
h
av
e
s
tu
d
ied
v
ar
io
u
s
d
etec
tio
n
m
et
h
o
d
s
w
h
er
e
k
-
m
ea
n
s
alg
o
r
it
h
m
i
s
f
o
u
n
d
to
o
f
f
er
b
etter
co
m
p
u
tatio
n
al
p
er
f
o
r
m
a
n
ce
.
P
r
o
b
le
m
s
p
er
tain
i
n
g
to
s
eg
m
e
n
tatio
n
a
n
d
d
etec
tio
n
w
a
s
also
ad
d
r
ess
ed
b
y
I
s
la
m
et
a
l
.
[
1
6
]
u
s
in
g
Gab
o
r
f
i
lt
er
s
an
d
en
h
a
n
cin
g
A
d
aB
o
o
s
t
alg
o
r
it
h
m
.
Kav
i
th
a
et
a
l
.
[
1
7
]
h
av
e
u
s
ed
f
ee
d
-
f
o
r
w
ar
d
al
g
o
r
ith
m
a
n
d
r
ad
ial
b
asis
f
u
n
ctio
n
to
en
h
a
n
ce
th
e
d
etec
tio
n
p
r
o
ce
s
s
.
Nag
to
d
e
et
al
.
[
1
8
]
h
av
e
u
s
e
d
d
is
cr
ete
w
a
v
elet
tr
an
s
f
o
r
m
,
Gab
o
r
tr
an
s
f
o
r
m
s
,
an
d
n
e
u
r
al
n
et
w
o
r
k
f
o
r
clas
s
if
icatio
n
o
f
ca
n
ce
r
.
Usag
e
o
f
m
o
r
p
h
o
lo
g
ical
o
p
er
ato
r
s
an
d
s
eg
m
en
tat
io
n
f
o
r
d
etec
tin
g
ca
n
ce
r
w
as
s
ee
n
i
n
t
h
e
w
o
r
k
o
f
Nan
d
i
[
1
9
]
.
A
d
o
p
tio
n
o
f
ti
m
e
-
r
eso
lv
ed
f
l
u
o
r
esce
n
ce
i
s
u
s
ed
b
y
Nie
et
a
l
.
[
2
0
]
f
o
r
id
en
ti
f
icat
io
n
o
f
t
u
m
o
u
r
m
ar
g
in
i
n
b
r
ain
.
P
er
ez
et
a
l
.
[
2
1
]
h
a
v
e
s
tu
d
ied
v
a
r
io
u
s
tec
h
n
iq
u
e
s
o
f
id
en
ti
f
y
i
n
g
ca
n
ce
r
s
ta
g
es
o
f
b
r
ain
f
r
o
m
MRI
i
m
a
g
es.
R
e
s
ae
ieh
et
a
l
.
[
2
2
]
h
av
e
in
v
e
s
tig
ated
m
icr
o
w
a
v
e
i
m
a
g
in
g
f
o
r
id
en
tific
atio
n
o
f
b
r
ain
tu
m
o
r
f
o
llo
w
ed
b
y
p
r
o
ce
s
s
o
f
p
er
f
o
r
m
a
n
ce
v
er
i
f
ic
atio
n
.
Sal
w
e
et
a
l
.
[
2
3
]
h
av
e
in
tr
o
d
u
ce
d
a
n
ad
ap
tiv
e
p
r
o
ce
s
s
o
f
w
a
v
elet
i
m
p
le
m
en
t
atio
n
w
h
er
e
f
i
n
e
w
in
d
o
w
i
n
g
o
p
er
atio
n
as
w
ell
a
s
th
r
es
h
o
ld
s
w
as
u
s
ed
f
o
r
d
etec
tin
g
tu
m
o
r
ce
lls
o
f
b
r
ain
.
A
d
o
p
tio
n
o
f
en
tr
o
p
y
f
ac
to
r
to
w
a
r
d
s
i
m
ilar
d
etec
tio
n
p
r
o
b
lem
w
as
s
ee
n
in
t
h
e
wo
r
k
ca
r
r
ied
o
u
t
b
y
So
m
w
a
n
s
h
i
et
a
l
.
[
2
4
]
f
o
r
en
h
a
n
ci
n
g
th
e
s
e
g
m
e
n
tat
io
n
p
er
f
o
r
m
a
n
ce
.
Dic
tio
n
ar
y
lear
n
in
g
w
as
u
s
ed
ad
o
p
ted
f
o
r
in
c
o
r
p
o
r
atin
g
ad
ap
tiv
en
e
s
s
in
th
e
d
etec
tio
n
p
r
o
ce
s
s
f
o
llo
w
ed
b
y
u
s
a
g
e
o
f
s
p
ar
s
e
r
ec
o
n
s
tr
u
ctio
n
p
r
o
ce
s
s
as
s
ee
n
in
t
h
e
w
o
r
k
c
ar
r
ied
o
u
t
b
y
S
u
et
a
l
.
[
2
5
]
.
Su
b
as
h
i
n
i
a
n
d
Sa
h
o
o
[
2
6
]
u
s
ed
b
ac
k
p
r
o
p
ag
atio
n
a
s
w
e
ll
as
p
u
l
s
ed
_
co
u
p
led
n
e
u
r
al
n
et
w
o
r
k
f
o
r
d
etec
tio
n
b
r
ain
tu
m
o
r
ce
lls
.
T
h
ar
a
an
d
J
as
m
i
n
e
[
2
7
]
u
s
ed
f
u
zz
y
K
-
m
ea
n
s
clu
s
ter
i
n
g
as
w
ell
as
C
-
m
ea
n
s
clu
s
ter
in
g
i
n
o
r
d
er
t
o
p
er
f
o
r
m
s
e
g
m
e
n
tatio
n
th
at
i
s
f
u
r
th
er
f
o
llo
w
ed
b
y
n
eu
r
al
n
et
w
o
r
k
f
o
r
i
m
ag
e
cla
s
s
if
ica
tio
n
.
Usa
g
e
o
f
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
s
f
o
r
ad
d
r
ess
in
g
s
i
m
ilar
p
r
o
b
le
m
w
as
also
s
ee
n
i
n
t
h
e
w
o
r
k
o
f
Vis
h
n
u
m
u
r
th
y
et
a
l
.
[
2
8
]
.
Z
h
an
g
et
a
l
.
[
2
9
]
h
av
e
u
s
ed
m
icr
o
w
a
v
e
i
m
ag
in
g
an
d
esp
ec
i
all
y
Vi
v
ald
i
an
te
n
n
a
f
o
r
d
etec
tin
g
b
r
ain
tu
m
o
r
.
He
n
ce
,
e
x
i
s
tin
g
s
y
s
te
m
o
f
f
er
s
v
ar
io
u
s
ap
p
r
o
ac
h
es
w
it
h
b
en
e
f
it
s
a
s
w
ell
as
li
m
itatio
n
.
T
h
e
n
e
x
t
s
ec
tio
n
o
u
tlin
e
s
t
h
e
r
esear
ch
p
r
o
b
le
m
s
id
en
tifie
d
.
T
h
e
s
ig
n
i
f
ica
n
t r
esear
c
h
p
r
o
b
l
e
m
s
ar
e
as
f
o
llo
w
s
:
a.
E
x
is
ti
n
g
ap
p
r
o
ac
h
es
m
a
in
l
y
s
u
b
j
ec
ts
th
e
i
n
p
u
t
i
m
ag
e
to
ei
th
er
s
e
g
m
e
n
tatio
n
,
cl
u
s
ter
i
n
g
,
class
if
icatio
n
,
tr
ain
i
n
g
al
g
o
r
ith
m
s
w
it
h
o
u
t
m
u
ch
e
m
p
h
a
s
izi
n
g
o
n
p
r
o
ce
s
s
in
g
m
o
r
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
2
,
A
p
r
il
201
9
:
1
4
1
0
-
1417
1412
b.
E
x
is
ti
n
g
s
e
g
m
en
ta
tio
n
al
g
o
r
ith
m
s
o
n
l
y
f
o
cu
s
o
n
th
e
f
o
r
eg
r
o
u
n
d
w
h
er
ea
s
b
ac
k
g
r
o
u
n
d
in
f
o
r
m
at
io
n
is
ig
n
o
r
ed
r
esu
l
tin
g
i
n
ca
s
es o
f
f
alse p
o
s
itiv
e
s
.
c.
L
e
v
el
o
f
e
n
h
a
n
ce
m
en
t
to
w
ar
d
s
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
is
v
er
y
m
u
c
h
li
m
i
ted
o
n
l
y
to
er
o
s
io
n
a
n
d
d
ilatio
n
w
h
er
ea
s
m
o
r
e
p
o
ten
tia
l o
f
th
e
m
o
r
p
h
o
lo
g
ical
o
p
er
ato
r
co
u
ld
b
e
h
ar
n
ess
ed
.
d.
L
es
s
er
f
o
cu
s
o
n
co
m
p
le
x
f
ea
t
u
r
es
ex
tr
ac
tio
n
is
a
n
o
th
er
ca
u
s
e
o
f
f
al
s
e
p
o
s
itiv
e
esp
ec
ial
l
y
w
h
en
s
u
b
j
ec
ted
to
m
ac
h
i
n
e
lear
n
i
n
g
alg
o
r
it
h
m
s
.
T
h
er
ef
o
r
e,
th
e
p
r
o
b
le
m
s
ta
te
m
e
n
t
o
f
t
h
e
p
r
o
p
o
s
ed
s
t
u
d
y
ca
n
b
e
s
tated
as
“
I
t
is
h
ig
h
ly
co
mp
u
ta
tio
n
a
lly
ch
a
llen
g
in
g
t
a
s
k
to
fo
r
mu
la
te
a
fr
a
mewo
r
k
th
a
t
u
s
es
co
s
t
-
effec
tive
tech
n
iq
u
es
to
ex
tr
a
ctio
n
s
u
b
s
ta
n
tia
l
in
fo
r
ma
tio
n
fr
o
m
th
e
ima
g
e
th
a
t
co
u
l
d
a
s
s
is
t
in
s
u
p
erio
r
id
en
tifi
ca
tio
n
o
f
b
r
a
in
ca
n
ce
r
.
"
T
h
e
n
ex
t
s
ec
tio
n
d
is
c
u
s
s
es t
h
e
p
r
o
p
o
s
ed
s
o
lu
tio
n
.
T
h
e
p
r
o
p
o
s
ed
s
tu
d
y
is
an
e
x
ten
s
io
n
o
f
o
u
r
p
r
io
r
c
o
n
tr
ib
u
tio
n
[
3
0
]
w
h
er
e
w
e
p
r
esen
tl
y
f
o
cu
s
o
n
u
s
i
n
g
s
er
ies
o
f
s
m
aller
a
n
d
co
m
p
u
tatio
n
all
y
co
s
t
-
ef
f
ec
ti
v
e
tech
n
iq
u
es
to
le
v
er
ag
e
t
h
e
ac
cu
r
ac
y
o
f
b
r
ai
n
ca
n
ce
r
d
etec
tio
n
.
T
h
e
m
et
h
o
d
o
lo
g
y
i
n
v
o
l
v
ed
in
d
esig
n
in
g
t
h
e
f
ir
s
t c
ase
s
t
u
d
y
i
s
as b
r
ief
l
y
d
is
cu
s
s
ed
:
a.
T
h
e
r
atio
n
ale
b
eh
i
n
d
Se
lectio
n
o
f
B
r
ain
MRI
I
m
ag
e
:
T
h
e
f
i
r
s
t
p
ar
t
o
f
o
u
r
s
tu
d
y
c
h
o
o
s
es
t
o
w
o
r
k
o
n
b
r
ai
n
MRI
i
m
a
g
es
o
w
i
n
g
to
th
e
co
m
p
licatio
n
o
f
th
e
t
y
p
e
o
f
o
n
c
o
lo
g
ical
ca
n
ce
r
.
B
r
ain
ca
n
ce
r
is
s
till
t
h
e
m
o
s
t
ch
alle
n
g
i
n
g
ca
n
ce
r
o
u
s
co
n
d
iti
o
n
w
it
h
i
n
cr
ea
s
ed
m
o
r
talit
y
r
a
te,
an
d
h
e
n
ce
ac
c
u
r
ac
y
i
n
d
ia
g
n
o
s
is
i
s
h
ig
h
l
y
r
eq
u
ir
ed
.
W
e
b
eliev
e
th
at
o
w
i
n
g
to
t
h
e
co
m
p
lica
ted
f
o
r
m
o
f
th
e
b
r
ain
M
R
I
i
m
a
g
e
s
;
th
er
e
ar
e
p
o
s
s
ib
ilit
ies
o
f
p
er
f
o
r
m
i
n
g
i
n
ac
cu
r
ate
f
ea
tu
r
e
e
x
tr
ac
tio
n
th
at
m
a
y
ca
l
l
f
o
r
f
alse
alar
m
.
T
h
er
ef
o
r
e,
o
w
i
n
g
to
t
h
e
cr
iticalit
y
o
f
th
e
d
is
ea
s
e
co
n
d
it
io
n
,
w
e
c
h
o
o
s
e
to
co
n
s
id
er
b
r
ain
MRI
i
m
a
g
e
as o
u
r
f
ir
s
t c
ase
s
tu
d
y
.
b.
Data
s
et
u
s
ed
: M
R
-
T
I
P
d
atab
ase.
c.
P
r
o
ce
s
s
I
n
v
o
lv
ed
i
n
Desi
g
n
Me
th
o
d
o
lo
g
y
:
T
h
e
p
r
o
p
o
s
ed
s
y
s
t
e
m
ta
k
e
s
t
h
e
i
n
p
u
t
o
f
B
r
ain
M
R
I
i
m
ag
e
a
n
d
ap
p
lies
g
r
ad
ien
t
m
a
g
n
i
tu
d
e
f
o
r
b
etter
d
ef
in
itio
n
o
f
p
o
s
s
ib
le
ed
g
es
Fi
g
u
r
e
1
.
T
h
is
is
f
o
llo
wed
b
y
ap
p
l
y
i
n
g
w
ater
s
h
ed
-
b
ased
tr
an
s
f
o
r
m
ati
o
n
s
ch
e
m
e
f
o
r
ass
i
s
ti
n
g
i
n
b
etter
s
eg
m
e
n
tatio
n
s
ch
e
m
e.
T
h
e
p
r
o
ce
s
s
ed
im
a
g
e
is
f
u
r
th
er
m
ar
k
ed
f
o
r
b
o
th
f
o
r
eg
r
o
u
n
d
s
as
w
e
ll
as
a
b
ac
k
g
r
o
u
n
d
.
Fi
n
all
y
,
a
w
ater
s
h
ed
alg
o
r
ith
m
i
s
ap
p
lied
to
p
er
f
o
r
m
p
r
o
p
e
r
s
eg
m
e
n
tat
i
o
n
o
f
th
e
f
o
r
eg
r
o
u
n
d
o
b
j
ec
t.
A
B
a
y
e
s
ia
n
Net
w
o
r
k
(
B
N)
is
co
n
s
tr
u
cted
alo
n
g
w
it
h
Dir
ec
ted
A
c
y
clic
Gr
ap
h
(
DA
G)
f
o
llo
w
ed
b
y
h
i
s
to
g
r
a
m
ca
lc
u
latio
n
a
n
d
r
eg
io
n
m
er
g
in
g
.
T
h
is
e
n
tire
p
r
o
ce
s
s
s
i
g
n
i
f
ica
n
tl
y
a
s
s
i
s
ts
i
n
ex
tr
ac
ti
n
g
e
n
o
u
g
h
in
f
o
r
m
a
tio
n
ab
o
u
t
t
h
e
n
o
r
m
al
a
n
d
ab
n
o
r
m
al
co
n
d
itio
n
o
f
an
o
b
j
ec
t.
T
h
is
s
ta
g
e
r
es
u
lt
s
in
t
h
e
f
o
r
m
atio
n
o
f
f
ea
tu
r
e
s
th
at
ar
e
f
i
n
all
y
s
u
b
j
ec
ted
to
th
e
s
u
p
er
v
is
ed
tr
ain
i
n
g
ca
r
r
ied
o
u
t b
y
A
r
ti
f
ici
al
Neu
r
al
Net
w
o
r
k
(
A
NN)
.
Fin
all
y
,
th
e
d
etec
tio
n
p
r
o
ce
s
s
is
ca
r
r
ied
o
u
t
to
d
etec
t
th
e
lo
c
atio
n
o
f
ca
n
ce
r
,
an
d
th
e
s
t
u
d
y
o
u
tco
m
e
is
ass
es
s
ed
u
s
i
n
g
co
n
v
en
t
io
n
al
a
cc
u
r
ac
y
p
ar
a
m
eter
s
,
e.
g
.
,
T
r
u
e/f
alse
-
p
o
s
itiv
e
/n
e
g
ati
v
e,
Se
n
s
itiv
it
y
,
R
ec
all
r
ate
,
Sp
ec
if
icit
y
,
P
r
ec
is
io
n
,
F1
-
Sco
r
e.
T
h
e
n
ex
t
s
ec
t
io
n
d
is
c
u
s
s
es
th
e
alg
o
r
it
h
m
i
m
p
le
m
en
tatio
n
f
o
r
d
ev
e
lo
p
in
g
t
h
e
p
r
o
p
o
s
ed
d
etec
tio
n
m
ec
h
a
n
is
m
.
I
n
p
u
t
B
r
a
i
n
M
R
I
I
m
a
g
e
G
r
a
d
i
e
n
t
m
a
g
n
i
t
u
d
e
W
a
t
e
r
s
h
e
d
T
r
a
n
s
f
o
r
m
M
a
r
k
F
o
r
e
g
r
o
u
n
d
R
e
m
o
v
e
d
a
r
k
S
p
o
t
s
R
e
g
i
o
n
a
l
M
a
x
i
m
a
S
u
p
e
r
i
m
p
o
s
e
M
a
r
k
B
a
c
k
g
r
o
u
n
d
W
a
t
e
r
s
h
e
d
(
S
e
g
m
e
n
t
a
t
i
o
n
)
C
o
n
s
t
r
u
c
t
D
A
G
C
o
n
s
t
r
u
c
t
B
N
H
i
s
t
o
g
r
a
m
C
a
l
c
u
l
a
t
i
o
n
R
e
g
i
o
n
M
e
r
g
i
n
g
E
x
t
r
a
c
t
F
e
a
t
u
r
e
s
A
N
N
T
r
a
i
n
i
n
g
A
N
N
D
e
t
e
c
t
i
o
n
Fig
u
r
e
1
.
Me
th
o
d
o
lo
g
y
ad
o
p
ted
f
o
r
1
s
t c
ase
s
tu
d
y
2.
AL
G
O
RI
T
H
M
I
M
P
L
E
M
E
NT
A
T
I
O
N
T
h
is
s
ec
tio
n
d
is
c
u
s
s
es
t
h
e
al
g
o
r
ith
m
t
h
at
p
er
f
o
r
m
s
id
en
t
if
ic
atio
n
o
f
t
h
e
ca
n
ce
r
o
u
s
r
eg
io
n
f
o
r
a
g
iv
e
n
MRI
i
m
ag
e
o
f
a
b
r
ain
.
T
h
e
al
g
o
r
ith
m
tak
e
s
t
h
e
i
n
p
u
t i
m
a
g
e
I
th
at
a
f
ter
p
r
o
ce
s
s
i
n
g
y
ie
ld
s
to
th
e
f
i
n
al
i
m
a
g
e
I
det
w
it
h
s
u
s
p
ec
ted
ca
n
ce
r
o
u
s
r
eg
i
o
n
s
.
T
h
e
s
ig
n
i
f
ican
t step
s
o
f
t
h
e
alg
o
r
ith
m
ar
e
as f
o
llo
w
s
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
A
n
o
ve
l fra
mewo
r
k
fo
r
efficien
t id
en
tifi
ca
tio
n
o
f b
r
a
i
n
ca
n
ce
r
r
eg
io
n
fr
o
m
b
r
a
in
MRI
(
P
a
r
va
ti A
n
g
a
d
i
)
1413
Alg
o
rit
h
m
f
o
r
ca
ncer
det
ec
t
io
n f
ro
m
bra
in M
RI i
m
a
g
e
I
np
ut
: I
(
in
p
u
t b
r
ain
MRI)
O
utput
: I
d
et
(
I
m
a
g
e
d
etec
ted
w
it
h
ca
n
ce
r
)
Sta
rt
1
.
Ob
tain
2
2
y
x
m
I
I
g
,
w
h
er
e
(
I
x
, I
y
)
=ϕ
(
Δ
I
)
2
.
I
ws
μ
(
g
m
)
3
.
I
mf
mr
1
(
s
tr
u
ct
(
f
1
(I
o)
,
f
2
(I
e
)))
4
.
I
ds
mr
2
(
s
tr
u
ct
(I
o
))
5
.
I
rm
f
3
(
α
(
β(γ
(
θ(
s
tr
u
ct(
I
mf
))))))
6
.
I
mb
f
4
(
β,
γ
)
7
.
I
si
μ
(
m
i
n
i
m
a(
g
m
(I
mb
)))
8
.
C
o
n
s
tr
u
ct
I
D
A
G
, I
BN
9
.
F
o
r
i=1
:m
ax
(
I
si
)
10.
h
1
=H
[
I
(
R
)
]
11.
E
nd
1
2
.
F
o
r
j
=
1
:s
ize(
I
DA
G
)
13.
c=
B
C
/∑
(
ψ
1
+ ψ
2
)
1
4
.
I
rm
f
5
(I
BN
,
c)
1
5
.
E
nd
1
6
.
I
feat
s
tats
(
I
(
R
)
)
1
7
.
A
p
p
ly
ANN
tr
ain
i
n
g
(
I
feat
)
1
8
.
I
det
Use G
T
f
o
r
ca
n
ce
r
d
e
tectio
n
E
nd
T
h
e
s
tep
s
o
f
th
e
ab
o
v
e
m
en
t
io
n
ed
alg
o
r
it
h
m
is
as
d
i
s
cu
s
s
ed
b
elo
w
:
I
n
itial
l
y
,
th
e
in
p
u
t
i
m
a
g
e
I
u
n
d
er
g
o
e
s
a
p
r
o
ce
s
s
in
g
to
o
b
tain
g
r
ad
ie
n
t
m
ag
n
it
u
d
e
g
m
(
L
i
n
e
-
1
)
.
Fo
r
th
i
s
p
u
r
p
o
s
e,
i
m
a
g
e
f
ilter
ϕ
i
s
ap
p
lied
to
th
e
i
m
a
g
e
I
w
h
er
e
a
So
b
el
o
p
er
ato
r
Δ
is
ap
p
lied
t
o
ex
tr
ac
t
I
x
an
d
I
y
.
T
h
e
n
ex
t
p
ar
t
o
f
th
e
alg
o
r
it
h
m
is
to
ap
p
ly
th
e
w
ater
s
h
ed
tr
an
s
f
o
r
m
μ
o
n
t
h
e
ac
co
m
p
l
is
h
ed
g
r
ad
ie
n
t
m
a
g
n
i
tu
d
e
g
m
o
f
i
n
p
u
t
i
m
ag
e
(
L
i
n
e
-
2
)
in
o
r
d
er
to
o
b
tain
th
e
tr
an
s
f
o
r
m
ed
i
m
a
g
e
I
ws
.
T
h
e
n
e
x
t
s
tep
o
f
t
h
e
a
lg
o
r
ith
m
i
s
to
m
ar
k
t
h
e
f
o
r
e
g
r
o
u
n
d
o
f
a
n
i
m
a
g
e
(
L
in
e
-
3
)
.
Fo
r
t
h
is
p
u
r
p
o
s
e
a
f
u
n
ct
io
n
f
1
is
u
s
ed
f
o
r
o
p
en
i
n
g
th
e
i
m
a
g
e
m
o
r
p
h
o
lo
g
ical
l
y
a
n
d
a
f
u
n
ctio
n
f
2
is
u
s
ed
f
o
r
er
o
d
in
g
t
h
e
i
m
a
g
e
with
r
esp
ec
t
to
th
e
d
is
k
m
o
r
p
h
o
lo
g
ical
s
tr
u
ctu
r
e
s
t
r
u
ct
.
Fin
a
ll
y
,
a
m
et
h
o
d
mr
1
is
u
s
ed
f
o
r
r
ec
o
n
s
tr
u
cti
n
g
th
e
m
o
r
p
h
o
lo
g
ical
f
ac
to
r
s
o
f
a
n
i
m
ag
e
I
w
it
h
r
e
s
p
ec
t
to
I
e
i
n
o
r
d
er
to
o
b
tain
f
in
al
l
y
m
ar
k
ed
i
m
ag
e
I
mf
.
T
h
is
p
r
o
ce
s
s
is
also
f
o
llo
w
ed
b
y
r
e
m
o
v
al
o
f
th
e
d
ar
k
s
p
o
ts
b
y
ap
p
l
y
in
g
m
o
r
p
h
o
lo
g
ical
clo
s
in
g
o
p
er
ato
r
mr
2
o
n
I
o
w
it
h
r
esp
ec
t
to
th
e
s
tr
u
c
tu
r
e
s
tr
u
ct
(
L
i
n
e
-
4
)
.
T
h
e
n
ex
t
p
ar
t
o
f
th
e
alg
o
r
ith
m
p
er
f
o
r
m
s
d
ilatio
n
o
p
er
atio
n
θ
o
n
f
o
r
e
g
r
o
u
n
d
m
ar
k
ed
i
m
a
g
e
I
mf
w
it
h
r
esp
ec
t
to
th
e
s
tr
u
ct
u
r
e
s
t
r
u
ct
(
L
in
e
-
5
)
.
T
h
is
o
p
er
atio
n
is
f
u
r
t
h
er
s
u
cc
ee
d
ed
b
y
r
ec
o
n
s
tr
u
c
tio
n
p
r
o
ce
s
s
γ
ca
r
r
ied
o
u
t
m
o
r
p
h
o
lo
g
i
ca
ll
y
t
h
at
is
f
u
r
t
h
er
en
ca
p
s
u
lated
b
y
f
u
n
ctio
n
f
o
r
co
m
p
u
tatio
n
o
f
co
m
p
le
m
e
n
t
i
m
ag
e
β
.
Fin
al
l
y
,
w
e
ap
p
l
y
m
o
r
p
h
o
lo
g
ical
f
u
n
ctio
n
o
f
r
eg
io
n
m
ax
i
m
a
f
u
n
ctio
n
α
an
d
th
is
i
s
f
u
r
th
er
e
n
ca
p
s
u
lat
ed
b
y
th
e
f
u
n
ctio
n
f
3
u
s
ed
f
o
r
s
u
p
er
i
m
p
o
s
in
g
t
h
e
f
o
r
e
g
r
o
u
n
d
in
o
r
d
er
to
o
b
tain
s
u
p
er
i
m
p
o
s
ed
i
m
a
g
e
o
f
r
e
g
io
n
al
m
ax
i
m
a
I
rm
.
No
w
t
h
e
alg
o
r
it
h
m
ap
p
lies
a
p
r
in
cip
le
o
f
b
ac
k
g
r
o
u
n
d
m
ar
k
in
g
a
n
d
f
o
r
t
h
is
i
t
o
b
tain
s
t
h
e
b
in
ar
y
i
m
ag
e
f
r
o
m
th
e
p
r
io
r
ac
co
m
p
li
s
h
ed
s
tep
s
u
s
i
n
g
th
e
f
u
n
ctio
n
β a
n
d
γ
(
L
i
n
e
-
6
)
.
T
h
e
o
b
tain
ed
i
m
a
g
e
is
th
a
n
e
x
p
lo
r
ed
f
o
r
its
d
is
ta
n
ce
b
et
w
e
en
t
w
o
tr
a
n
s
f
o
r
m
ed
p
o
in
t
s
i
n
th
e
i
m
a
g
e
th
at
is
f
i
n
all
y
f
o
llo
w
ed
b
y
th
e
o
p
er
atio
n
o
f
th
e
w
ater
s
h
ed
tr
an
s
f
o
r
m
atio
n
o
p
er
ato
r
f
4
(
L
in
e
-
6
)
in
o
r
d
er
to
o
b
tain
th
e
i
m
a
g
e
w
h
er
e
t
h
e
m
ar
k
ed
b
ac
k
g
r
o
u
n
d
is
o
b
tain
ed
I
mb
.
Af
ter
o
b
tain
in
g
b
o
th
f
o
r
eg
r
o
u
n
d
an
d
b
ac
k
g
r
o
u
n
d
i
m
a
g
e,
th
e
n
ex
t
s
tep
w
ill
b
e
to
ap
p
ly
t
h
e
p
r
o
ce
s
s
in
g
f
o
r
in
iti
atin
g
th
e
s
eg
m
e
n
tatio
n
p
r
o
ce
s
s
.
Fo
r
th
i
s
p
u
r
p
o
s
e,
in
itial
l
y
th
e
i
m
a
g
e
w
ith
g
r
ad
i
en
t
m
a
g
n
it
u
d
e
g
m
a
n
d
th
e
co
n
ca
ten
a
tio
n
o
f
b
ac
k
g
r
o
u
n
d
i
m
ag
e
I
mb
a
n
d
i
m
a
g
e
w
it
h
r
e
g
io
n
al
m
a
x
i
m
a
I
rm
an
d
ed
g
es
an
d
t
h
i
s
p
r
o
ce
s
s
in
g
o
f
f
e
r
s
s
ec
o
n
d
s
ta
g
e
g
r
ad
ien
t
m
a
g
n
itu
d
e
f
o
llo
w
ed
b
y
m
i
n
i
m
a
-
b
ased
o
p
er
atio
n
(
L
i
n
e
-
7
)
.
T
h
i
s
o
p
er
atio
n
is
f
u
r
t
h
e
r
s
u
b
j
ec
ted
to
w
ater
s
h
ed
al
g
o
r
ith
m
μ
f
o
r
b
etter
s
eg
m
e
n
tatio
n
p
er
f
o
r
m
an
ce
in
o
r
d
er
to
o
b
tain
th
e
s
e
g
m
en
ted
i
m
a
g
e
I
si
.
Fo
r
b
etter
co
m
p
u
ta
tio
n
al
p
er
f
o
r
m
a
n
ce
,
w
e
ap
p
l
y
d
ir
ec
t
ac
y
clic
g
r
ap
h
I
DA
G
a
n
d
B
ay
e
s
ian
n
et
w
o
r
k
I
BN
in
o
r
d
er
to
f
u
r
th
er
o
p
ti
m
ize
t
h
e
d
etec
tio
n
p
er
f
o
r
m
a
n
ce
(
L
in
e
-
8
)
.
T
h
e
m
ec
h
an
i
s
m
ap
p
lied
f
o
r
co
n
s
tr
u
cti
n
g
D
A
G
a
n
d
B
ay
e
s
ia
n
Net
w
o
r
k
is
as
f
o
llo
w
s
:
T
h
e
f
i
r
s
t
s
tep
in
co
n
s
tr
u
ct
io
n
ac
y
clic
g
r
ap
h
is
t
o
g
i
v
e
lab
els
to
all
th
e
r
eg
io
n
s
an
d
in
o
r
d
er
to
d
o
th
is
a
lo
o
p
is
cr
ea
ted
f
o
r
all
th
e
p
o
s
s
ib
le
v
al
u
e
o
f
lab
els
(
ex
tr
ac
ted
f
r
o
m
w
ater
s
h
ed
tr
an
s
f
o
r
m
)
w
h
er
e
all
th
e
r
eg
io
n
s
ar
e
ex
tr
ac
ted
alo
n
g
w
it
h
m
o
r
p
h
o
lo
g
ical
d
ilatio
n
o
p
er
atio
n
f
r
o
m
w
h
er
e
th
e
u
n
iq
u
e
lab
els
ar
e
ex
tr
ac
ted
lo
g
ical
l
y
.
T
h
e
n
ex
t
s
tep
is
to
ap
p
ly
a
p
r
o
b
ab
ilis
tic
g
r
a
p
h
ical
m
o
d
el,
i.e
.
,
B
a
y
e
s
ia
n
n
et
w
o
r
k
o
n
o
b
tai
n
ed
d
ir
ec
ted
ac
y
clic
g
r
ap
h
co
n
ce
r
n
i
n
g
s
izes o
f
t
h
e
n
o
d
es.
T
h
e
n
ex
t
s
tep
o
f
th
e
al
g
o
r
it
h
m
i
s
to
p
er
f
o
r
m
r
e
g
io
n
m
er
g
in
g
o
p
er
atio
n
.
I
n
o
r
d
er
to
d
o
s
o
,
a
lo
o
p
is
cr
ea
ted
f
o
r
all
t
h
e
m
a
x
i
m
u
m
v
al
u
es
o
f
s
eg
m
e
n
ted
i
m
a
g
e
I
si
(
L
i
n
e
-
9
)
,
w
h
er
e
r
eg
io
n
s
R
ar
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
2
,
A
p
r
il
201
9
:
1
4
1
0
-
1417
1414
ch
ec
k
ed
f
o
r
th
e
ir
eq
u
iv
ale
n
c
y
w
it
h
t
h
e
m
a
x
i
m
u
m
v
al
u
es.
A
h
is
to
g
r
a
m
o
p
er
ato
r
H
is
th
en
a
p
p
lied
to
th
e
im
a
g
e
w
it
h
o
n
l
y
r
eg
io
n
i
n
f
o
r
m
atio
n
t
o
f
i
n
all
y
e
x
tr
ac
t
t
h
e
h
is
to
g
r
a
m
h
1
(
L
i
n
e
-
1
0
)
.
T
h
is
o
p
er
atio
n
i
s
f
u
r
t
h
er
f
o
llo
w
ed
u
p
b
y
co
m
p
u
ta
tio
n
o
f
m
er
g
ed
r
eg
io
n
s
.
Fo
r
th
i
s
p
u
r
p
o
s
e
a
lo
o
p
is
cr
ea
ted
f
o
r
all
th
e
m
a
x
i
m
u
m
v
al
u
es
o
b
tain
ed
b
y
f
i
n
d
i
n
g
th
e
s
ize
o
f
d
ir
ec
t
a
c
y
clic
g
r
ap
h
,
w
h
er
e
all
t
h
e
co
n
n
ec
ted
co
m
p
o
n
e
n
ts
f
o
r
ea
ch
s
eg
m
e
n
ts
ar
e
f
o
u
n
d
.
A
h
i
s
to
g
r
ap
h
o
f
t
h
e
c
u
r
r
en
t
n
o
d
e
is
o
b
tain
ed
f
o
llo
w
e
d
b
y
t
h
e
co
m
p
u
ta
tio
n
o
f
th
e
B
h
attac
h
a
r
y
a
C
o
e
f
f
icie
n
t B
C
(
L
in
e
-
1
3
)
.
Fin
all
y
,
all
t
h
e
co
n
n
ec
ted
co
m
p
o
n
en
ts
c
is
co
m
p
u
ted
u
s
in
g
a
s
i
m
p
le
m
a
th
e
m
at
ical
ex
p
r
ess
io
n
th
a
t
u
s
e
s
B
a
y
esia
n
n
et
w
o
r
k
o
n
ce
ag
ain
as
s
h
o
w
n
i
n
L
i
n
e
-
1
4
.
T
h
is
p
r
o
ce
s
s
r
esu
lt
s
i
n
I
rm
t
h
at
is
a
f
i
n
al
r
eg
io
n
m
er
g
i
n
g
i
m
a
g
e.
T
h
e
f
u
n
ctio
n
f
5
r
ep
r
esen
t
s
r
eg
io
n
m
er
g
in
g
o
p
er
atio
n
an
d
t
h
e
v
ar
iab
les
ψ
1
an
d
ψ
2
r
ep
r
esen
t
s
ce
ll
w
ith
1
x
1
d
i
m
e
n
s
io
n
a
n
d
1
x
d
i
m
en
s
io
n
o
f
al
l
th
e
c
o
n
n
ec
ted
co
m
p
o
n
e
n
ts
r
e
s
p
ec
tiv
el
y
.
T
h
i
s
s
tep
i
s
f
o
llo
w
ed
b
y
ex
tr
ac
tio
n
o
f
s
ta
tis
tical
f
ea
t
u
r
es
s
ta
ts
o
n
t
h
e
r
eg
io
n
s
o
f
a
n
i
m
a
g
e
i
n
o
r
d
er
to
o
b
tain
an
i
m
ag
e
m
atr
i
x
I
feat
(
L
i
n
e
-
1
6
)
.
Fin
all
y
,
n
eu
r
al
n
et
w
o
r
k
i
s
ap
p
lied
o
n
th
ese
f
ea
t
u
r
es
(
L
in
e
-
1
7
)
w
h
e
r
e
th
e
g
r
o
u
n
d
tr
u
t
h
GT
im
ag
e
s
w
er
e
u
s
ed
f
o
r
ass
ess
i
n
g
t
h
e
r
eg
io
n
s
t
h
at
ar
e
p
o
s
s
ib
l
y
i
n
f
ec
ted
b
y
ca
n
ce
r
in
r
esu
lta
n
t
i
m
a
g
e
I
det
(
L
in
e
-
1
8
)
.
T
h
er
ef
o
r
e,
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
i
m
p
le
m
e
n
ts
v
ar
io
u
s
s
m
aller
s
tep
s
in
o
r
d
er
to
f
in
a
ll
y
p
er
f
o
r
m
d
etec
tio
n
o
f
ca
n
ce
r
o
u
s
p
o
r
tio
n
s
f
o
r
a
g
i
v
e
n
MRI
i
m
a
g
e
o
f
a
b
r
ain
.
T
h
e
n
ex
t
s
ec
tio
n
d
is
c
u
s
s
es a
b
o
u
t t
h
e
r
es
u
lts
b
ein
g
o
b
tain
ed
3.
RE
SU
L
T
S AN
A
L
YS
I
S
T
h
is
s
ec
tio
n
d
is
c
u
s
s
e
s
t
h
e
r
es
u
lt
b
ei
n
g
o
b
tain
ed
a
f
ter
i
m
p
le
m
en
tin
g
th
e
co
n
ce
p
t
w
r
itte
n
i
n
t
h
e
p
r
io
r
s
ec
tio
n
.
T
h
e
co
m
p
lete
a
n
al
y
s
is
is
ca
r
r
ied
o
u
t
o
n
i
m
ag
e
s
o
b
tain
ed
f
r
o
m
MR
-
T
I
P
d
ata
b
a
s
e
[
3
1
]
w
h
er
e
t
h
e
d
i
m
en
s
io
n
o
f
t
h
e
i
m
a
g
e
s
ar
e
a
p
p
r
o
x
im
a
tel
y
6
1
8
x
6
3
0
w
it
h
t
h
e
o
cc
u
p
atio
n
o
f
3
6
.
2
KB
o
f
m
e
m
o
r
y
.
T
h
e
v
is
u
al
o
u
tco
m
es
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
ar
e
s
h
o
w
n
in
Fi
g
u
r
e
2
w
h
er
e
it
ca
n
b
e
s
ee
n
t
h
at
in
p
u
t
i
m
ag
e
s
af
ter
s
u
b
j
ec
tin
g
to
g
r
ad
ien
t
m
a
g
n
it
u
d
e
lo
s
es
its
co
n
tr
ast
a
n
d
h
ig
h
li
g
h
t
s
f
o
r
ed
g
e
-
b
ased
i
n
f
o
r
m
atio
n
F
ig
u
r
e
2
(
b
)
.
A
p
p
l
y
in
g
w
ater
s
h
ed
alg
o
r
it
h
m
f
u
r
t
h
er
ass
i
s
ts
i
n
an
e
f
f
ec
ti
v
e
s
e
g
m
e
n
tat
io
n
p
r
o
ce
s
s
Fi
g
u
r
e
2
(
c)
an
d
h
en
ce
it
h
ig
h
li
g
h
ts
all
t
h
e
p
o
s
s
ib
le
co
lo
r
s
f
o
r
th
e
tr
an
s
f
o
r
m
ed
i
m
a
g
e.
I
n
th
e
p
r
o
ce
s
s
o
f
s
e
g
m
en
t,
it
w
as
f
o
u
n
d
th
a
t
f
o
r
eg
r
o
u
n
d
m
ar
k
i
n
g
Fi
g
u
r
e
2
(
d
)
o
f
f
er
s
in
ter
n
al
ch
a
n
g
e
s
an
d
n
o
t
m
u
c
h
o
n
s
u
p
er
f
icia
l
ch
an
g
e
s
f
o
llo
w
e
d
b
y
r
eg
io
n
m
er
g
i
n
g
Fi
g
u
r
e
2
(
e)
.
A
clo
s
er
lo
o
k
in
to
th
e
r
eg
io
n
m
er
g
i
n
g
o
p
er
atio
n
in
Fi
g
u
r
e
2
(
e)
s
h
o
w
s
t
h
at
th
e
s
u
s
p
ec
ted
p
o
r
tio
n
o
f
ca
n
ce
r
co
u
ld
b
e
lo
ca
ted
w
ith
in
t
h
e
r
e
g
io
n
.
T
h
er
ef
o
r
e,
it
ca
n
b
e
s
ai
d
th
at
tr
u
e
o
u
tco
m
e
s
tar
ts
co
m
in
g
o
n
l
y
a
f
ter
r
eg
io
n
m
er
g
i
n
g
o
p
er
atio
n
.
F
u
r
th
er
i
m
p
l
y
in
g
t
h
e
d
ir
ec
t
ac
y
clic
g
r
ap
h
an
d
B
a
y
esia
n
n
et
w
o
r
k
,
th
e
id
e
n
ti
f
icatio
n
p
e
r
f
o
r
m
an
ce
o
f
t
h
e
ca
n
ce
r
o
u
s
r
eg
io
n
s
h
as
tr
e
m
en
d
o
u
s
l
y
i
n
cr
ea
s
ed
as
w
ell
as
it
o
f
f
er
s
b
etter
in
f
er
en
ce
o
f
t
h
e
o
u
tco
m
e
o
f
t
h
e
p
r
o
ce
s
s
ed
i
m
ag
e.
At
t
h
e
s
a
m
e
ti
m
e,
all
th
e
m
i
s
s
i
n
g
p
ix
el
ele
m
e
n
ts
ar
e
s
u
cc
es
s
f
u
ll
y
h
an
d
led
as
all
th
e
en
co
d
in
g
is
ca
r
r
ied
o
u
t
u
s
in
g
B
ay
e
s
ia
n
n
et
wo
r
k
.
E
v
en
f
r
o
m
t
h
e
ac
cu
r
ac
y
v
ie
w
p
o
in
t,
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
o
f
f
er
s
h
ig
h
l
y
en
h
a
n
ce
d
ac
cu
r
ac
y
lev
el
a
s
it
ca
n
m
iti
g
ate
t
h
e
p
r
o
b
lem
o
f
o
v
er
f
itt
in
g
to
m
a
x
i
m
ize
th
e
o
u
tco
m
e
o
f
id
e
n
ti
f
i
ca
tio
n
.
Fi
n
all
y
,
ap
p
l
y
in
g
n
e
u
r
al
n
et
w
o
r
k
tr
ai
n
i
n
g
h
as
f
u
r
th
er
o
p
ti
m
ized
th
e
o
u
tc
o
m
e
th
e
ac
cu
r
ac
y
lev
e
l
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
w
i
th
th
e
s
h
o
r
test
iter
atio
n
o
f
t
h
e
lear
n
in
g
p
r
o
c
ess
.
T
h
e
co
m
p
let
e
o
p
tim
iza
tio
n
w
a
s
ca
r
r
ied
o
u
t u
s
i
n
g
d
a
m
p
ed
leas
t sq
u
ar
e
al
g
o
r
ith
m
.
Fo
r
b
etter
s
tu
d
y
ef
f
ec
t
iv
e
n
es
s
,
w
e
co
m
p
ar
e
th
e
o
u
tco
m
e
o
f
t
h
e
p
r
o
p
o
s
ed
s
tu
d
y
w
it
h
th
at
o
f
Su
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
(
SVM)
a
n
d
K
-
Nea
r
est
Ne
ig
h
b
o
r
(
KNN)
alg
o
r
ith
m
t
h
at
is
f
r
eq
u
e
n
tl
y
u
s
e
d
in
ex
is
tin
g
s
y
s
te
m
f
o
r
class
i
f
icatio
n
p
u
r
p
o
s
e.
T
h
e
n
u
m
er
ical
o
u
tco
m
e
is
s
h
o
w
n
i
n
T
ab
le
1
.
T
ab
le
1
.
C
o
m
p
ar
ativ
e
An
al
y
s
i
s
o
f
E
x
i
s
ti
n
g
S
y
s
te
m
P
a
r
a
me
t
e
r
s
S
V
M
K
N
N
P
r
o
p
o
se
d
S
y
st
e
m
S
e
n
si
t
i
v
i
t
y
/
R
e
c
a
l
l
r
a
t
e
0
.
4
5
7
2
1
0
.
3
2
8
7
2
0
.
6
5
3
0
2
4
S
p
e
c
i
f
i
c
i
t
y
0
.
9
7
6
9
5
0
.
9
3
7
8
6
0
.
9
9
9
9
4
8
P
r
e
c
i
si
o
n
0
.
9
8
6
7
5
0
.
9
7
6
5
8
0
.
9
9
9
9
2
0
A
c
c
u
r
a
c
y
9
5
%
9
3
%
9
9
%
T
h
e
o
u
tco
m
e
s
h
o
w
s
t
h
at
p
r
o
p
o
s
ed
s
y
s
te
m
u
s
i
n
g
n
e
u
r
al
n
et
w
o
r
k
o
f
f
er
s
b
etter
ac
cu
r
ac
y
a
s
co
m
p
ar
ed
to
SVM
an
d
KNN.
T
h
e
p
r
im
e
r
ea
s
o
n
b
eh
in
d
th
i
s
is
SVM
an
d
KNN
o
f
f
er
s
h
i
g
h
er
co
m
p
u
tatio
n
al
p
r
o
b
le
m
w
h
e
n
it
co
m
e
s
to
p
er
f
o
r
m
i
n
g
class
i
f
icatio
n
o
f
i
n
cr
ea
s
ed
s
ize
o
f
d
ata.
Mo
r
eo
v
er
,
b
o
th
th
e
alg
o
r
ith
m
p
er
f
o
r
m
s
o
p
tim
izatio
n
til
l
a
th
r
es
h
o
ld
v
alu
e
w
h
er
ea
s
in
n
eu
r
al
n
et
w
o
r
k
t
h
e
o
p
ti
m
izat
io
n
is
m
o
r
e
ap
p
licab
le
o
n
m
i
n
i
m
izatio
n
o
f
er
r
o
r
s
.
T
h
is
w
il
l
m
ea
n
t
h
at
er
r
o
r
m
in
i
m
izi
n
g
o
p
er
atio
n
i
s
b
etter
f
o
r
n
e
u
r
al
n
et
w
o
r
k
i
n
e
v
er
y
asp
ec
t.
T
h
er
ef
o
r
e,
p
r
o
p
o
s
ed
s
y
s
te
m
w
i
ll
n
eu
r
al
n
et
w
o
r
k
o
f
f
er
s
e
n
h
a
n
ce
d
ac
cu
r
ac
y
as
co
m
p
ar
ed
to
e
x
is
ti
n
g
s
y
s
te
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
A
n
o
ve
l fra
mewo
r
k
fo
r
efficien
t id
en
tifi
ca
tio
n
o
f b
r
a
i
n
ca
n
ce
r
r
eg
io
n
fr
o
m
b
r
a
in
MRI
(
P
a
r
va
ti A
n
g
a
d
i
)
1415
(
a)
(
b
)
(
c)
(
d
)
(
e)
(
e)
Fig
u
r
e
2
.
(
a)
I
n
p
u
t i
m
ag
e
,
(
b
)
Gr
ad
ien
t
m
a
g
n
it
u
d
e
,
(c
)
W
ater
s
h
ed
t
r
an
s
f
o
r
m
,
(
d
)
Ma
r
k
f
o
r
e
g
r
o
u
n
d
,
(
e
)
.
R
eg
io
n
m
er
g
i
n
g
,
(
f
)
Dete
c
tio
n
o
f
t
u
m
o
r
4.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
h
as
p
r
es
en
te
d
a
s
i
m
p
le
an
d
c
o
s
t
-
ef
f
ec
tiv
e
t
ec
h
n
i
q
u
e
f
o
r
en
h
an
c
in
g
th
e
ac
cu
r
a
c
y
lev
el
o
f
b
r
ain
c
an
ce
r
d
e
tec
ti
o
n
u
s
in
g
a
s
er
i
es
o
f
o
p
e
r
a
ti
o
n
s
.
T
h
e
r
ea
s
o
n
b
eh
in
d
its
co
s
t
ef
f
ec
t
iv
en
ess
is
b
e
ca
u
s
e
n
o
n
e
o
f
th
e
alg
o
r
i
th
m
s
u
s
ed
in
p
r
o
p
o
s
ed
s
y
s
tem
co
n
s
u
m
es
m
ax
i
m
u
m
m
e
m
o
r
y
o
r
is
d
e
p
en
d
en
t
o
n
h
ig
h
er
n
u
m
b
er
o
f
tr
a
in
e
d
d
a
tase
t.
M
o
s
t
s
ig
n
if
ic
an
tly
,
th
e
r
es
p
o
n
s
e
tim
e
o
f
p
r
o
p
o
s
e
d
s
y
s
tem
is
v
er
y
less
as
co
m
p
a
r
e
d
t
o
th
e
ex
is
tin
g
s
y
s
te
m
.
T
h
e
p
r
o
p
o
s
e
d
s
y
s
te
m
also
in
tr
o
d
u
ce
s
a
u
n
i
q
u
e
m
ec
h
an
is
m
to
p
e
r
f
o
r
m
s
eg
m
en
tatio
n
w
h
er
e
th
e
im
p
o
r
t
an
ce
is
b
e
in
g
s
h
ar
e
d
e
q
u
ally
to
f
o
r
m
ar
k
in
g
b
o
th
f
o
r
e
g
r
o
u
n
d
an
d
b
a
ck
g
r
o
u
n
d
.
Us
ag
e
o
f
d
ir
ec
t
e
d
ac
y
clic
g
r
a
p
h
as
w
ell
as
B
ay
esian
Ne
t
w
o
r
k
h
as
ass
is
te
d
t
o
im
p
r
o
v
e
t
h
e
ex
t
r
ac
ti
o
n
o
f
u
n
iq
u
e
in
f
o
r
m
ati
o
n
th
at
w
as
u
s
ed
f
o
r
c
o
n
s
t
r
u
ctin
g
f
ea
tu
r
es
.
Fin
al
ly
,
s
u
ch
f
ea
tu
r
es
w
h
en
f
ed
to
n
eu
r
al
n
etw
o
r
k
,
w
e
f
in
d
m
u
ch
-
en
h
an
ce
d
ac
cu
r
a
cy
p
e
r
f
o
r
m
an
ce
.
T
h
e
co
m
p
le
te
a
n
aly
s
is
is
f
o
u
n
d
t
o
o
f
f
er
h
ig
h
er
ac
cu
r
a
cy
lev
el
in
c
o
n
tr
ast
t
o
ex
is
tin
g
m
eth
o
d
s
.
Ou
r
f
u
tu
r
e
w
o
r
k
w
il
l
b
e
to
co
n
tin
u
e
th
e
p
r
esen
ce
r
ese
ar
ch
a
n
d
in
clu
d
e
m
o
r
e
c
o
m
p
lic
ati
o
n
s
in
d
iag
n
o
s
is
u
s
in
g
n
o
v
el
o
p
t
im
izati
o
n
s
ch
em
es
.
RE
F
E
RE
NCES
[1
]
A
d
e
k
u
n
le
M
.
A
d
e
si
n
a
,
T
a
r
ik
T
i
h
a
n
,
C
h
r
is
ti
n
e
E
.
F
u
ll
e
r
,
T
i
n
a
Y
o
u
n
g
P
o
u
ss
a
i
n
t
,
"
A
tl
a
s
o
f
P
e
d
ia
tr
ic
B
ra
i
n
T
u
m
o
rs
,
"
S
p
r
i
n
g
e
r
,
2
0
1
6
.
[2
]
Jü
rg
H
o
d
le
r,
Ra
h
e
l
A
.
K
u
b
ik
-
H
u
c
h
,
G
u
s
tav
K
.
v
o
n
S
c
h
u
lt
h
e
s
s,
"
Dise
a
se
s
o
f
t
h
e
B
ra
i
n
,
He
a
d
a
n
d
Ne
c
k
,
S
p
i
n
e
2016
-
2
0
1
9
:
D
iag
n
o
st
ic
Im
a
g
i
n
g
,
"
S
p
r
i
n
g
e
r
,
2
0
1
6
.
[3
]
A
les
sa
n
d
r
o
Cr
im
i,
B
jo
e
r
n
M
e
n
z
e
,
Os
k
a
r
M
a
ier
,
M
a
u
ric
i
o
Re
y
e
s,
"
Bra
in
les
i
o
n
:
G
li
o
m
a
,
M
u
lt
i
p
le
S
c
l
e
ro
si
s
,
S
tr
o
k
e
a
n
d
T
ra
u
m
a
ti
c
B
ra
i
n
I
n
j
u
r
ies
,
"
S
p
ri
n
g
e
r
,
2
0
1
7
.
[4
]
Ch
ri
st
o
p
h
e
r
M
.
C
o
l
li
n
s
,
"
El
e
c
t
r
o
m
a
g
n
e
ti
c
s
i
n
M
a
g
n
e
ti
c
Re
s
o
n
a
n
c
e
Im
a
g
i
n
g
:
P
h
y
s
ica
l
P
ri
n
c
i
p
les
,
Re
la
te
d
A
p
p
li
c
a
t
i
o
n
s,
a
n
d
O
n
g
o
i
n
g
De
v
e
l
o
p
m
e
n
ts,
"
M
o
r
g
a
n
&
Cl
a
y
p
o
o
l
P
u
b
l
is
h
e
r
s
,
2
0
1
6
[5
]
S
.
Ca
o
r
si
,
A
.
M
a
s
sa
,
M
.
P
a
s
t
o
r
i
n
o
a
n
d
A
.
R
o
sa
n
i,
"
M
icr
o
w
a
v
e
M
e
d
i
c
a
l
Im
a
g
in
g
:
P
o
te
n
ti
a
l
it
ies
a
n
d
Lim
it
a
t
io
n
s
o
f
a
S
t
o
c
h
a
st
ic
O
p
t
im
iza
t
i
o
n
T
e
c
h
n
i
q
u
e
,
"
i
n
I
EE
E
T
r
a
n
s
a
c
t
i
o
n
s
o
n
M
i
c
r
o
w
a
v
e
T
h
e
o
ry
a
n
d
T
e
c
h
n
i
q
u
e
s
,
v
o
l
.
5
2
,
n
o
.
8
,
p
p
.
1
9
0
9
-
1
9
1
6
,
A
u
g
.
2
0
0
4
.
[6
]
Riv
k
a
R.
C
o
le
n
,
I
m
a
g
in
g
o
f
B
ra
i
n
T
u
m
o
rs
,
"
A
n
Iss
u
e
o
f
M
a
g
n
e
ti
c
Re
s
o
n
a
n
c
e
Im
a
g
in
g
Cl
i
n
ic
s
o
f
N
o
rt
h
A
m
e
rica
,
"
E
-
B
o
o
k
,
E
lse
v
ier
He
a
lt
h
S
c
i
e
n
c
e
s
,
2
0
1
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
2
,
A
p
r
il
201
9
:
1
4
1
0
-
1417
1416
[7
]
S
.
U
.
A
sw
a
th
y
,
G
.
G
.
De
v
a
D
h
a
s
a
n
d
S
.
S
.
K
u
m
a
r,
"
A
S
u
rv
e
y
o
n
D
e
tec
t
io
n
o
f
Br
a
i
n
T
u
m
o
r
f
r
o
m
M
RI
Bra
i
n
Im
a
g
e
s
,
"
2
0
1
4
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
n
tr
o
l
,
I
n
s
tr
u
m
e
n
t
a
t
i
o
n
,
C
o
mm
u
n
ic
a
t
i
o
n
a
n
d
Co
mp
u
t
a
t
i
o
n
a
l
T
e
c
h
n
o
l
o
g
ies
(
ICC
IC
CT
)
,
Ka
n
y
a
k
u
m
a
ri
,
p
p
.
8
7
1
-
8
7
7
,
2
0
1
4
.
[8
]
Ro
y
a
Ba
b
a
ie
A
g
h
d
a
m
,
A
ti
e
h
S
a
d
a
t
Ba
y
a
t
G
h
ias
i,
P
a
ra
st
o
o
F
a
tem
i,
Na
z
a
n
i
n
S
a
d
a
t
Ha
s
h
e
m
i
,
"
C
h
a
l
le
n
g
e
s
i
n
B
ra
i
n
M
a
g
n
e
t
i
c
R
e
s
o
n
a
n
c
e
Im
a
g
e
S
e
g
m
e
n
tat
i
o
n
,
"
Ame
r
ic
a
n
S
c
ie
n
t
if
ic
Res
e
a
rc
h
J
o
u
r
n
a
l
f
o
r
E
n
g
i
n
e
e
r
in
g
,
tec
h
n
o
l
o
g
y
,
a
n
d
S
c
ie
n
c
e
s,
v
o
l
.
2
7
(
1
)
,
2
0
1
7
.
[9
]
Iv
a
n
a
De
s
p
o
t
o
v
ić
,
Ba
r
t
G
o
o
s
se
n
s,
a
n
d
W
il
f
r
ie
d
P
h
i
li
p
s
,
"
M
R
I
S
e
g
m
e
n
tat
i
o
n
o
f
t
h
e
H
u
m
a
n
Bra
i
n
:
C
h
a
ll
e
n
g
e
s,
M
e
t
h
o
d
s
,
a
n
d
A
p
p
l
ica
t
i
o
n
s
,
"
Co
m
p
u
t
a
ti
o
n
a
l
a
n
d
M
a
t
h
e
m
a
t
ic
a
l
M
e
t
h
o
d
s
i
n
M
e
d
ic
i
n
e
,
2
0
1
5
.
[1
0
]
V.
A
n
i
t
h
a
a
n
d
S
.
M
u
r
u
g
a
v
a
ll
i
,
"
Bra
in
T
u
m
o
u
r
Cl
a
ss
if
ica
t
i
o
n
u
si
n
g
T
w
o
-
T
ie
r
Cla
ss
if
ie
r
w
it
h
A
d
a
p
ti
v
e
S
e
g
m
e
n
t
a
t
i
o
n
T
e
c
h
n
i
q
u
e
,
"
i
n
I
ET
Co
mp
u
ter
Vi
s
i
o
n
,
v
o
l.
1
0
(
1
)
,
p
p
.
9
-
17,
2
0
1
6
.
[1
1
]
H.
Ba
g
h
a
e
i
e
t
a
l
.
,
"
C
o
m
p
a
ris
o
n
o
f
Bra
i
n
P
h
a
n
t
o
m
L
e
si
o
n
Im
a
g
in
g
Ca
p
a
b
i
li
ty
o
f
t
h
e
B
ra
i
n
a
n
d
W
h
o
l
e
-
B
o
d
y
M
o
d
e
s
o
f
t
h
e
T
ra
n
sf
o
rm
a
b
le
H
OT
P
ET
C
a
m
e
ra
,
"
i
n
I
E
EE
T
r
a
n
s
a
c
t
io
n
s
o
n
Nu
c
le
a
r
S
c
ie
n
c
e
,
v
o
l.
5
8
(
3
)
,
p
p
.
7
3
0
-
7
3
5
,
J
u
n
2
0
1
1
.
[1
2
]
B.
Be
d
d
a
d
a
n
d
K
.
Ha
c
h
e
m
i
,
"
Bra
in
T
u
m
o
r
D
e
tec
t
i
o
n
b
y
u
s
i
n
g
a
M
o
d
if
i
e
d
F
C
M
a
n
d
L
e
v
e
l
S
e
t
a
l
g
o
r
it
h
m
s
,
"
2016
4
t
h
I
n
ter
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Co
n
tr
o
l
E
n
g
i
n
e
e
r
i
n
g
&
In
f
o
r
m
a
t
io
n
T
e
c
h
n
o
l
o
g
y
(
C
EI
T
)
,
Ha
m
m
a
m
e
t,
p
p
.
1
-
5
,
2
0
1
6
.
[1
3
]
A
.
De
m
irh
a
n
,
M
.
T
ö
r
ü
a
n
d
İ.
G
ü
ler
,
"
S
e
g
m
e
n
ta
ti
o
n
o
f
T
u
m
o
r
a
n
d
E
d
e
m
a
A
lo
n
g
W
it
h
H
e
a
l
t
h
y
T
issu
e
s
o
f
B
ra
i
n
Us
i
n
g
W
a
v
e
let
s
a
n
d
Ne
u
r
a
l
Ne
t
w
o
rk
s,"
i
n
I
EE
E
J
o
u
r
n
a
l
o
f
B
i
o
me
d
ic
a
l
a
n
d
He
a
l
t
h
I
n
f
o
rm
a
t
ics
,
v
o
l
.
1
9
(
4
)
,
p
p
.
1451
-
1
4
5
8
,
J
u
l
2
0
1
5
.
[1
4
]
A
.
Ha
m
a
m
c
i,
N
.
K
u
c
u
k
,
K
.
Ka
r
a
m
a
n
,
K
.
E
n
g
in
a
n
d
G
.
U
n
a
l,
"
T
u
m
o
r
-
C
u
t
:
S
e
g
m
e
n
ta
ti
o
n
o
f
Bra
in
T
u
m
o
r
s
o
n
Co
n
tra
st
E
n
h
a
n
c
e
d
M
R
Im
a
g
e
s
f
o
r
Ra
d
i
o
s
u
rg
e
ry
A
p
p
li
c
a
t
i
o
n
s,"
i
n
I
EE
E
T
r
a
n
s
a
c
t
i
o
n
s
o
n
M
e
d
ic
a
l
Ima
g
i
n
g
,
v
o
l.
31
(
3
),
p
p
.
7
9
0
-
8
0
4
,
M
a
r
2012.
[1
5
]
D.
Ha
r
i
th
a
,
"
C
o
m
p
a
r
a
t
iv
e
S
t
u
d
y
o
n
Bra
i
n
T
u
m
o
r
De
tec
t
io
n
T
e
c
h
n
i
q
u
e
s
,
"
2
0
1
6
I
n
ter
n
a
t
i
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
S
i
g
n
a
l
Pr
o
c
e
ss
i
n
g
,
C
o
m
m
u
n
ic
a
ti
o
n
,
P
o
we
r
a
n
d
Em
b
e
d
d
e
d
S
y
ste
m
(
S
CO
PE
S
)
,
P
a
ra
lak
h
e
m
u
n
d
i
,
O
d
i
s
h
a
,
I
n
d
ia,
p
p
.
1
3
8
7
-
1392
,
2016
.
[1
6
]
A
.
Isla
m
,
S
.
M
.
S
.
R
e
z
a
a
n
d
K
.
M
.
If
tek
h
a
r
u
d
d
in
,
"
M
u
lt
if
ra
c
tal
T
e
x
t
u
re
Est
im
a
ti
o
n
f
o
r
De
tec
t
io
n
a
n
d
S
e
g
m
e
n
t
a
t
i
o
n
o
f
B
ra
in
T
u
m
o
rs
,
"
i
n
I
EE
E
T
r
a
n
s
a
c
ti
o
n
s
o
n
B
i
o
me
d
ic
a
l
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l.
6
0
(
11
)
,
p
p
.
3
2
0
4
-
3
2
1
5
,
N
o
v
2
0
1
3
.
[1
7
]
A
.
R.
Ka
v
it
h
a
,
C.
C
h
e
ll
a
m
u
t
h
u
a
n
d
K.
R
u
p
a
,
"
A
n
Ef
f
icie
n
t
A
p
p
r
o
a
c
h
f
o
r
B
ra
i
n
T
u
m
o
u
r
De
tec
t
io
n
Ba
s
e
d
o
n
M
o
d
if
ie
d
Re
g
i
o
n
G
ro
w
i
n
g
a
n
d
N
e
u
r
a
l
Ne
tw
o
rk
i
n
M
RI
Im
a
g
e
s
,
"
2
0
1
2
I
n
te
r
n
a
t
i
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
C
o
m
p
u
ti
n
g
,
El
e
c
tr
o
n
ics
a
n
d
El
e
c
tr
ic
a
l
T
e
c
h
n
o
lo
g
ies
(
IC
CE
E
T
)
,
Ku
m
a
ra
c
o
il
,
p
p
.
1
0
8
7
-
1
0
9
5
,
2
0
1
2
.
[1
8
]
S
.
A
.
Na
g
t
o
d
e
,
B
.
B.
P
o
t
d
u
k
h
e
a
n
d
P
.
M
o
r
e
y
,
"
T
w
o
Dim
e
n
s
i
o
n
a
l
Disc
re
t
e
W
a
v
e
le
t
t
ra
n
sf
o
rm
a
n
d
P
r
o
b
a
b
il
is
ti
c
Ne
u
ra
l
Ne
tw
o
rk
u
se
d
f
o
r
Br
a
i
n
T
u
m
o
r
De
tec
t
i
o
n
a
n
d
C
las
s
if
ica
ti
o
n
,
"
2
0
1
6
Fi
ft
h
I
n
ter
n
a
t
i
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Ec
o
-
fri
e
n
d
ly
C
o
m
p
u
ti
n
g
a
n
d
Co
mm
u
n
i
c
a
ti
o
n
S
y
s
tem
s
(
IC
ECC
S
)
,
Bh
o
p
a
l
,
p
p
.
2
0
-
26
,
2016
.
[1
9
]
A
.
Na
n
d
i
,
"
De
tec
t
io
n
o
f
Hu
m
a
n
Bra
in
T
u
m
o
u
r
u
s
i
n
g
M
R
I
Im
a
g
e
S
e
g
m
e
n
ta
ti
o
n
a
n
d
M
o
r
p
h
o
l
o
g
ica
l
Op
e
ra
to
rs
,
"
2
0
1
5
I
E
EE
I
n
ter
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
te
r
G
r
a
p
h
ics
,
V
isi
o
n
a
n
d
I
n
f
o
rm
a
ti
o
n
S
e
c
u
r
it
y
(
CGV
I
S
)
,
Bh
u
b
a
n
e
sw
a
r
,
p
p
.
5
5
-
60
,
2015
.
[2
0
]
Z.
N
ie
e
t
a
l
.
,
"
I
n
teg
ra
te
d
T
im
e
-
Re
s
o
lv
e
d
F
l
u
o
re
sc
e
n
c
e
a
n
d
D
if
f
u
se
Re
f
lec
ta
n
c
e
S
p
e
c
t
r
o
sc
o
p
y
In
str
u
m
e
n
t
f
o
r
In
tra
o
p
e
ra
ti
v
e
De
t
e
c
t
i
o
n
o
f
Bra
i
n
T
u
m
o
r
M
a
rg
i
n
,
"
i
n
I
EE
E
J
o
u
r
n
a
l
o
f
S
e
lec
te
d
T
o
p
ic
s
i
n
Q
u
a
n
t
u
m
E
lec
t
r
o
n
ics
,
v
o
l
.
2
2
(
3
)
,
p
p
.
4
9
-
5
7
,
M
a
y
-
J
u
n
2
0
1
6
.
[2
1
]
U.
P
e
re
z
,
E
.
A
ra
n
a
,
a
n
d
D.
M
o
ra
tal
,
"
B
ra
i
n
M
e
tas
tas
e
s
De
tec
t
i
o
n
A
lg
o
r
it
h
m
s
i
n
M
a
g
n
e
ti
c
Re
s
o
n
a
n
c
e
Im
a
g
in
g
,"
IE
EE
L
a
t
i
n
Ame
r
ic
a
T
r
a
n
s
a
c
t
i
o
n
s
,
v
o
l.
1
4
(
3
)
,
p
p
.
1
1
0
9
-
1
1
1
4
,
2
0
1
6
.
[2
2
]
S
.
A
h
d
i
Re
z
a
e
ie
h
,
A
.
Zam
a
n
i
a
n
d
A
.
M
.
A
b
b
o
s
h
,
"
3
-
D
W
i
d
e
b
a
n
d
A
n
te
n
n
a
f
o
r
He
a
d
-
Im
a
g
in
g
S
y
ste
m
w
it
h
P
e
rf
o
rm
a
n
c
e
Ve
r
if
ica
ti
o
n
i
n
B
ra
i
n
T
u
m
o
r
De
tec
ti
o
n
,
"
i
n
IE
E
E
A
n
te
n
n
a
s
a
n
d
W
i
re
le
ss
Pr
o
p
a
g
a
ti
o
n
L
e
tt
e
rs
,
v
o
l
.
1
4
,
n
o
.
3
,
p
p
.
9
1
0
-
9
1
4
,
2
0
1
5
.
[2
3
]
S
.
S
a
lw
e
,
R.
Ra
u
t
a
n
d
P
.
H
a
ja
r
e
,
"
B
ra
i
n
T
u
m
o
r
P
i
x
e
l
s
De
tec
ti
o
n
u
s
i
n
g
A
d
a
p
ti
v
e
W
a
v
e
let
Ba
se
d
H
is
t
o
g
ra
m
T
h
re
s
h
o
l
d
i
n
g
a
n
d
F
i
n
e
W
i
n
d
o
w
i
n
g
,
"
2
0
1
6
I
n
ter
n
a
t
i
o
n
a
l
C
o
n
fe
re
n
c
e
o
n
I
n
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
(
I
n
C
IT
e
)
-
T
h
e
Ne
x
t
Ge
n
e
ra
t
i
o
n
IT
S
u
mm
it
o
n
t
h
e
T
h
e
m
e
-
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s:
C
o
n
n
e
c
t
y
o
u
r W
o
r
l
d
s
,
N
o
i
d
a
,
p
p
.
2
5
6
-
260
,
2016
.
[2
4
]
D.
S
o
m
w
a
n
s
h
i
,
A
.
Ku
m
a
r
,
P
.
S
h
a
rm
a
a
n
d
D
.
J
o
s
h
i
,
"
A
n
Ef
f
icie
n
t
B
ra
i
n
T
u
m
o
r
De
tec
t
i
o
n
f
r
o
m
M
RI
Im
a
g
e
s
u
si
n
g
E
n
t
ro
p
y
M
e
a
su
re
s
,
"
2
0
1
6
I
n
t
e
r
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
Rec
e
n
t
A
d
v
a
n
c
e
s
a
n
d
I
n
n
o
v
a
t
i
o
n
s i
n
E
n
g
i
n
e
e
ri
n
g
(
IC
RA
IE
)
,
Ja
i
p
u
r
,
p
p
.
1
-
5
,
2016
.
[2
5
]
H.
S
u
,
F
.
Xi
n
g
a
n
d
L
.
Ya
n
g
,
"
Ro
b
u
s
t
Ce
ll
De
tec
t
i
o
n
o
f
H
is
t
o
p
a
t
h
o
l
o
g
ica
l
B
ra
i
n
T
u
m
o
r
Im
a
g
e
s
Us
in
g
S
p
a
rs
e
Re
c
o
n
st
r
u
c
t
i
o
n
a
n
d
A
d
a
p
ti
v
e
Di
c
ti
o
n
a
ry
S
e
lec
ti
o
n
,
"
i
n
IE
E
E
T
r
a
n
s
a
c
ti
o
n
s
o
n
M
e
d
ic
a
l
Im
a
g
i
n
g
,
v
o
l
.
3
5
(
6
)
,
p
p
.
1
5
7
5
-
1
5
8
6
,
J
u
n
2
0
1
6
.
[2
6
]
M
.
M
.
S
u
b
a
s
h
i
n
i
a
n
d
S
.
K
.
S
a
h
o
o
,
"
Br
a
i
n
T
u
m
o
u
r
De
te
c
t
i
o
n
u
s
in
g
P
u
l
se
C
o
u
p
le
d
Ne
u
ra
l
Ne
tw
o
rk
(
P
CNN
)
a
n
d
Ba
c
k
P
r
o
p
a
g
a
t
i
o
n
Ne
tw
o
rk
,
"
I
E
T
C
h
e
n
n
a
i
3
rd
I
n
te
r
n
a
t
i
o
n
a
l
o
n
S
u
s
t
a
i
n
a
b
l
e
E
n
e
r
g
y
a
n
d
In
te
ll
i
g
e
n
t
S
y
ste
ms
(
S
EI
S
CON
2
0
1
2
)
,
T
ir
u
c
h
e
n
g
o
d
e
,
p
p
.
1
-
6
,
2
0
1
2
.
[2
7
]
K.
S
.
T
h
a
ra
a
n
d
K
.
Ja
sm
in
e
,
"
Bra
i
n
T
u
m
o
u
r
D
e
tec
t
io
n
i
n
M
R
I
Im
a
g
e
s
u
si
n
g
P
NN
a
n
d
G
RNN
,
"
2
0
1
6
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
W
ire
les
s
Co
m
mu
n
ic
a
t
i
o
n
s
,
S
i
g
n
a
l
Pr
o
c
e
ss
i
n
g
a
n
d
Ne
tw
o
r
k
i
n
g
(
W
iS
PN
E
T
)
,
C
h
e
n
n
a
i
,
p
p
.
1
5
0
4
-
1510
,
2016
.
[2
8
]
T
.
D.
Vis
h
n
u
m
u
r
t
h
y
,
H.
S
.
M
o
h
a
n
a
a
n
d
V.
A
.
M
e
s
h
r
a
m
,
"
A
u
t
o
m
a
ti
c
S
e
g
m
e
n
ta
ti
o
n
o
f
Bra
i
n
M
RI
Im
a
g
e
s
a
n
d
T
u
m
o
r
De
t
e
c
t
i
o
n
u
s
i
n
g
M
o
r
p
h
o
l
o
g
i
c
a
l
T
e
c
h
n
i
q
u
e
s
,
"
2
0
1
6
I
n
te
rn
a
t
i
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
El
e
c
tr
ic
a
l
,
El
e
c
tr
o
n
ics
,
Co
mm
u
n
ic
a
ti
o
n
,
C
o
m
p
u
ter
a
n
d
O
p
t
im
iz
a
ti
o
n
T
e
c
h
n
i
q
u
e
s
(
IC
EE
CC
OT)
,
M
y
s
u
r
u
,
I
n
d
ia
,
p
p
.
6
-
11
,
2016
.
[2
9
]
H.
Z
h
a
n
g
,
B.
F
ly
n
n
,
A
.
T
.
Er
d
o
g
a
n
a
n
d
T
.
A
rsla
n
,
"
M
ic
r
o
w
a
v
e
Im
a
g
i
n
g
f
o
r
Bra
i
n
T
u
m
o
u
r
De
te
c
ti
o
n
u
s
i
n
g
a
n
UW
B
V
iv
a
l
d
i
A
n
te
n
n
a
a
rra
y
,
"
2
0
1
2
L
o
u
g
h
b
o
r
o
u
g
h
An
te
n
n
a
s
&
Pro
p
a
g
a
t
i
o
n
C
o
n
f
e
re
n
c
e
(
L
AP
C)
,
L
o
u
g
h
b
o
r
o
u
g
h
,
p
p
.
1
-
4
,
2
0
1
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
A
n
o
ve
l fra
mewo
r
k
fo
r
efficien
t id
en
tifi
ca
tio
n
o
f b
r
a
i
n
ca
n
ce
r
r
eg
io
n
fr
o
m
b
r
a
in
MRI
(
P
a
r
va
ti A
n
g
a
d
i
)
1417
[3
0
]
P
.
N
.
A
n
g
a
d
i
a
n
d
P
.
K
.
S
rim
a
n
i,
"
DO
DO
R
:
D
u
a
l
O
p
ti
m
iza
ti
o
n
f
o
r
De
tec
ti
o
n
o
f
On
c
o
l
o
g
ic
a
l
Re
g
i
o
n
i
n
Ra
d
i
o
l
o
g
ica
l
Im
a
g
e
,
"
2
0
1
5
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
E
me
r
g
i
n
g
Res
e
a
rc
h
in
El
e
c
tr
o
n
ics
,
C
o
m
p
u
t
e
r
S
c
ie
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
(
IC
ER
EC
T
)
,
M
a
n
d
y
a
,
p
p
.
1
9
8
-
203
,
2015
.
[3
1
]
“
Bra
i
n
M
R
I”
,
h
tt
p
:/
/w
w
w
.
m
r
-
ti
p
.
c
o
m
/se
rv
1
.
p
h
p
?
ty
p
e
=
d
b
1
&
d
b
s=
Br
a
i
n
%
2
0
M
R
I
,
Re
t
ri
e
v
e
d
o
n
1
5
th
J
u
l
y
,
2
0
1
7
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Pa
r
v
a
ti
A
n
g
a
d
i
,
is
a
re
se
a
rc
h
sc
h
o
lar
o
f
Ra
y
a
las
e
e
m
a
Un
iv
e
rsit
y
h
a
v
in
g
2
0
y
e
a
rs
o
f
In
d
u
stry
a
n
d
T
e
a
c
h
in
g
Ex
p
e
rien
c
e
.
S
h
e
h
a
s
p
u
b
li
s
h
e
d
o
v
e
r
2
0
p
a
p
e
rs
h
e
r
a
re
a
o
f
in
tere
st
f
o
c
u
se
s
m
a
in
l
y
o
n
A
u
to
m
a
ti
o
n
.
Dr
.
M
Na
g
e
n
d
r
a
,
is
p
ro
f
e
ss
o
r
a
n
d
HO
D
a
t
D
e
p
a
rt
m
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
S
.
K.
Un
iv
e
rsity
.
He
h
a
s
a
ri
c
h
a
c
a
d
e
m
ic
e
x
p
e
rien
c
e
o
f
o
v
e
r
2
8
y
e
a
r
s.
His
a
re
a
s
o
f
in
tere
st
a
r
e
Co
m
p
u
ter
Ne
t
w
o
rk
s
a
n
d
S
o
f
tw
a
re
En
g
in
e
e
rin
g
.
He
is
a
n
a
u
th
o
r
o
f
o
v
e
r
2
0
p
u
b
li
c
a
ti
o
n
s
a
n
d
h
e
m
e
n
to
re
d
6
P
h
.
D
st
u
d
e
n
ts
.
He
h
a
s
b
e
e
n
tea
c
h
in
g
v
a
riet
y
o
f
p
a
p
e
rs
in
Co
m
p
u
ter
S
c
ien
c
e
f
o
r
M
CA
a
n
d
M
.
S
c
(CS
)
c
o
u
rse
s
a
t
De
p
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
S
.
K.
Un
iv
e
rsit
y
,
A
n
a
n
tp
u
ra
m
u
Dr
.
H
a
n
u
m
a
n
th
a
p
p
a
M
,
is
p
r
o
f
e
ss
o
r
a
t
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
Ba
n
g
a
lo
re
Un
iv
e
rsity
.
Ha
v
in
g
1
8
y
e
a
rs
o
f
t
e
a
c
h
in
g
,
a
d
m
in
istratio
n
a
n
d
i
n
d
u
stry
e
x
p
e
rien
c
e
.
His
re
se
a
rc
h
f
o
c
u
se
s
o
n
In
f
o
rm
a
ti
o
n
re
tri
e
v
a
l,
Da
ta
m
in
i
n
g
,
Ne
tw
o
rk
se
c
u
rit
y
a
n
d
Na
tu
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
.
He
is
a
u
th
o
r
o
f
5
b
o
o
k
s
a
n
d
o
v
e
r
9
5
p
u
b
li
c
a
ti
o
n
s.
He
h
a
s
a
d
ju
d
ica
ted
n
e
a
rl
y
5
0
P
h
.
D
a
n
d
M
.
P
h
il
t
h
e
sis.
He
h
a
s m
a
n
y
d
isti
n
c
ti
o
n
s co
n
f
e
rre
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.