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
.
4
,
A
u
g
u
s
t
201
9
,
p
p
.
2
4
1
6
~
2
4
2
4
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
9
i
4
.
p
p
2
4
1
6
-
2424
2416
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
Integ
ra
ted
m
o
dell
ing
appro
a
ch
for
enha
ncing
brain
M
RI
w
ith
flexible pr
e
-
pro
ce
ss
ing
capa
bility
H
a
rish
S
.
1
,
G.
F
.
Ali A
ha
mm
ed
2
1
V
T
U Bela
g
a
v
i,
In
d
ia
2
V
T
U P
G
-
Ce
n
ter,
M
y
su
ru
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
1
9
,
2
0
1
8
R
ev
i
s
ed
Dec
2
1
,
2
0
1
8
A
cc
ep
ted
Ma
r
4
,
2
0
1
9
T
h
e
a
ss
u
ra
n
c
e
o
f
a
n
in
f
o
rm
a
ti
o
n
q
u
a
li
ty
o
f
th
e
in
p
u
t
m
e
d
ica
l
ima
g
e
is
a
c
rit
ica
l
ste
p
to
o
ff
e
r
h
ig
h
l
y
p
re
c
is
e
a
n
d
re
li
a
b
le d
iag
n
o
sis o
f
c
li
n
ica
l
c
o
n
d
it
io
n
in
h
u
m
a
n
.
T
h
e
i
m
p
o
rtan
c
e
o
f
su
c
h
a
ss
u
ra
n
c
e
b
e
c
o
m
e
s
m
o
re
w
h
i
le
d
e
a
li
n
g
w
it
h
i
m
p
o
rtan
t
o
rg
a
n
li
k
e
b
ra
in
.
M
a
g
n
e
ti
c
Re
so
n
a
n
c
e
I
m
a
g
in
g
(M
RI)
is
o
n
e
o
f
th
e
m
o
st
tru
ste
d
m
e
d
iu
m
s
to
in
v
e
stig
a
te
b
ra
in
.
L
o
o
k
in
g
in
to
th
e
e
x
isti
n
g
tren
d
s
o
f
in
v
e
stig
a
ti
n
g
b
ra
in
M
RI
,
it
w
a
s
o
b
se
rv
e
d
th
a
t
re
se
a
rc
h
e
rs
a
re
m
o
re
p
ro
n
e
to
in
v
e
stig
a
te
a
d
v
a
n
c
e
d
p
ro
b
lem
s
e
.
g
.
se
g
m
e
n
tatio
n
,
lo
c
a
li
z
a
ti
o
n
,
c
las
si
f
ica
ti
o
n
,
e
tc
c
o
n
sid
e
rin
g
ima
g
e
d
a
tas
e
t.
T
h
e
re
is
les
s
w
o
rk
c
a
rried
o
u
t
to
w
a
rd
s
i
m
a
g
e
p
re
p
ro
c
e
ss
in
g
t
h
a
t
p
o
te
n
ti
a
l
a
ff
e
c
ts
th
e
l
a
ter
sta
g
e
o
f
d
iag
n
o
sin
g
.
T
h
e
re
f
o
re
,
th
is
p
a
p
e
r
in
tro
d
u
c
e
s
a
n
o
v
e
l
m
o
d
e
l
o
f
in
teg
ra
ted
im
a
g
e
e
n
h
a
n
c
e
m
e
n
t
a
lg
o
rit
h
m
th
a
t
is
c
a
p
a
b
le
o
f
so
lv
in
g
d
if
f
e
re
n
t
a
n
d
d
isc
re
te
p
ro
b
lem
s
o
f
p
e
rf
o
r
m
in
g
ima
g
e
p
re
-
p
ro
c
e
ss
in
g
f
o
r
o
ff
e
ri
n
g
h
ig
h
ly
im
p
ro
v
e
d
a
n
d
e
n
h
a
n
c
e
d
b
ra
in
M
RI.
T
h
e
c
o
m
p
a
ra
ti
v
e
o
u
tco
m
e
s
e
x
h
ib
it
th
e
a
d
v
a
n
tag
e
o
f
it
s si
m
p
li
stic im
p
le
m
e
tatio
n
stra
teg
y
.
K
ey
w
o
r
d
s
:
B
r
ain
E
n
h
a
n
ce
m
en
t
Ma
g
n
e
tic
R
e
s
o
n
a
n
ce
I
m
a
g
in
g
P
r
e
-
P
r
o
ce
s
s
in
g
R
eso
l
u
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
.
All
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Har
is
h
S
.
,
R
esear
ch
Sch
o
lar
,
VT
U
B
elag
av
i,
I
n
d
ia
E
m
ail:
h
ar
is
h
s
r
i
n
i
v
asaia
h
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
t
h
e
cu
r
r
e
n
t
s
ce
n
ar
io
o
f
r
ad
io
lo
g
ical
d
iag
n
o
s
i
s
,
v
ar
io
u
s
m
ed
ical
i
m
a
g
i
n
g
tech
n
iq
u
es
h
a
v
e
e
m
er
g
ed
as
ad
v
an
ta
g
eo
u
s
to
o
l
to
s
er
v
e
a
b
en
ef
icial
f
ea
t
u
r
e
to
m
ed
ic
al
p
r
ac
tio
n
er
s
an
d
ex
p
er
ts
in
o
r
d
er
to
d
etec
t
an
d
cu
r
e
ab
n
o
r
m
alit
ies
i
n
h
u
m
a
n
b
o
d
y
i
n
ea
is
er
m
an
n
er
an
d
with
lo
w
er
m
en
ta
l
r
is
k
[
1
]
.
I
m
ag
es
ca
p
t
u
r
ed
f
r
o
m
v
ar
io
u
s
d
e
v
ices
u
s
in
g
d
if
f
er
e
n
t
m
o
d
es
s
u
c
h
as
X
-
r
a
y
,
C
T
s
ca
n
,
MRI
a
n
d
E
C
G.
Am
o
n
g
t
h
ese
i
m
a
g
i
n
g
m
o
d
els
MRI
i
s
co
n
s
id
er
ed
to
b
e
v
er
y
p
o
ten
tial a
n
d
tr
u
s
t
f
u
ll
to
o
l to
v
is
u
alize
t
h
e
co
m
p
le
x
a
n
d
i
n
te
r
n
al
p
ar
ts
o
f
h
u
m
a
n
o
r
g
an
s
in
d
etailed
.
T
h
e
MRI
s
tan
d
s
f
o
r
Ma
g
n
et
ic
R
e
s
o
n
a
n
ce
I
m
a
g
in
g
th
at
co
n
s
tr
u
ct
i
m
ag
e
u
s
in
g
r
ad
io
w
a
v
es
an
d
m
a
g
n
etic
f
ield
a
n
d
it
is
la
r
g
l
y
ad
o
p
ted
in
er
a
o
f
n
e
u
r
o
lo
g
ical
s
y
s
te
m
f
o
r
an
al
y
s
i
s
o
f
b
r
ain
d
is
o
r
d
er
s
s
u
c
h
as
tu
m
o
r
s
,
ca
n
ce
r
,
lesi
o
n
s
,
et
c.
[
2
]
.
Ho
w
ev
er
,
th
er
e
ar
e
v
ar
io
u
s
ch
al
len
g
es
a
n
d
is
s
u
es
ass
o
ciate
d
w
it
h
th
e
v
is
u
aliza
t
io
n
o
f
b
r
ain
M
R
I
d
u
e
to
n
o
is
e
s
s
u
c
h
as
t
h
er
m
al
n
o
is
e,
s
a
m
p
le
n
o
is
e,
i
n
co
r
p
o
r
ated
n
o
is
e,
p
o
o
r
co
n
tr
ast,
lack
o
f
b
o
u
n
d
ar
ies
a
n
d
etc.
Su
c
h
p
h
e
n
o
m
e
n
o
n
d
e
g
r
ad
es
th
e
q
u
alit
y
o
f
i
m
a
g
e
an
d
m
a
k
e
s
d
if
f
ic
u
lt
to
an
al
y
ze
,
r
ec
o
g
n
ize
t
u
m
o
r
in
t
h
e
b
r
ain
.
T
h
u
s
,
m
ed
ical
i
m
ag
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
e
s
i
s
co
n
s
i
d
er
ed
as
a
s
o
lu
tio
n
to
m
iti
g
ate
th
e
p
r
o
b
le
m
o
f
n
o
i
s
e
o
cc
u
r
r
ed
in
i
m
a
g
e
in
o
r
d
er
to
p
r
o
v
id
e
s
u
itab
le
d
ia
g
n
o
s
is
o
f
t
u
m
o
r
i
n
b
r
ai
n
[
3
]
.
T
h
e
im
a
g
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
i
n
clu
d
es
s
e
v
er
al
p
r
o
ce
s
s
es
s
u
ch
as
e
n
h
a
n
ce
m
en
t,
d
en
o
is
i
n
g
,
s
e
g
n
m
e
n
tatio
n
,
lo
ca
liza
tio
n
,
co
r
r
ec
tio
n
an
d
e
tc.
T
h
e
d
en
o
is
in
g
an
d
s
e
g
m
e
n
tatio
n
i
m
a
g
i
n
g
p
r
o
ce
s
s
in
g
t
ec
h
n
iq
u
e
p
r
o
v
id
es
b
etter
an
al
y
s
is
o
f
b
r
ai
n
tu
m
o
r
f
r
o
m
a
n
en
h
a
n
ce
d
i
m
a
g
e.
Ho
w
e
v
er
,
th
er
e
is
co
n
f
lict
b
et
w
ee
n
th
e
i
m
a
g
e
en
h
a
n
ce
m
en
t
an
d
d
en
o
i
s
i
n
g
p
r
o
ce
s
s
b
ec
au
s
e
d
en
o
is
in
g
i
s
th
e
p
r
o
ce
s
s
o
f
m
iti
g
ati
n
g
n
o
is
e
f
r
o
m
t
h
e
i
m
ag
e
s
ig
n
al
an
d
en
h
a
n
ce
m
en
t
i
s
th
e
p
r
o
ce
s
s
o
f
im
p
r
o
v
i
n
g
an
d
en
h
ac
in
g
t
h
e
q
u
alit
y
o
f
i
m
a
g
e
b
y
m
a
n
ip
u
la
tin
g
t
h
e
d
ig
ital
i
m
a
g
e
w
it
h
s
o
m
e
co
m
p
u
tat
io
n
al
ap
p
licatio
n
s
[
4
]
.
Fu
r
t
h
er
m
o
r
e,
it
h
as
b
ee
n
n
o
ticed
th
at
t
h
er
e
ar
e
v
ar
io
u
s
s
i
g
n
if
ican
t
r
esear
ch
w
o
r
k
to
w
ar
d
s
ad
d
r
ess
in
g
s
e
g
m
e
n
tat
io
n
p
r
o
b
le
m
s
as
w
el
l
as
cla
s
s
i
f
icatio
n
p
r
o
b
lem
s
p
e
r
tai
n
in
g
to
b
r
ain
MRI
[
5
-
8
]
.
I
t
ca
n
b
e
s
ee
n
t
h
a
t
th
e
e
x
is
tin
g
r
esear
c
h
co
m
m
u
n
i
t
y
is
co
m
p
le
tel
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
I
n
teg
r
a
ted
mo
d
ellin
g
a
p
p
r
o
a
c
h
fo
r
en
h
a
n
cin
g
b
r
a
in
M
R
I
w
ith
flexib
le
p
r
e
-
p
r
o
ce
s
s
in
g
…
(
Ha
r
is
h
S
.
)
2417
ab
s
o
r
b
ed
in
ev
o
lv
i
n
g
u
p
n
e
w
tech
n
iq
u
e
s
o
f
ad
v
an
ce
ap
p
li
c
atio
n
s
o
f
m
ed
ical
i
m
ag
e
p
r
o
c
ess
i
n
g
th
at
u
s
u
a
ll
y
in
cl
u
d
es
s
e
g
m
en
tatio
n
,
cla
s
s
if
icatio
n
,
an
d
lo
ca
lizatio
n
.
Ho
w
e
v
er
,
ess
e
n
tial
tech
n
iq
u
es
e.
g
.
i
m
a
g
e
p
r
e
-
p
r
o
ce
s
s
in
g
i
s
q
u
ite
f
o
u
n
d
ig
n
o
r
ed
an
d
h
av
e
n
o
t
w
it
n
es
s
ed
a
n
o
tab
le
p
r
o
g
r
ess
.
T
h
is
is
also
an
o
th
er
p
r
i
m
e
r
ea
s
o
n
w
h
y
ev
e
n
th
e
ad
v
an
ce
p
r
o
ce
s
s
in
g
tec
h
n
q
iu
e
s
ar
e
n
o
t
f
o
u
n
d
1
0
0
%
s
u
cc
ess
f
u
l.
T
h
e
r
ea
s
o
n
is
t
h
at
i
m
ag
e
en
h
a
n
ce
m
en
t b
ein
g
t
h
e
p
r
i
m
ar
y
s
tep
i
s
f
o
u
n
d
h
i
g
h
l
y
ig
n
o
r
ed
.
P
r
ep
r
o
ce
s
s
in
g
o
f
i
m
a
g
e
s
is
th
e
v
er
y
cr
u
cial
s
tep
r
eq
u
ir
ed
to
o
b
tain
ac
c
u
r
ate
i
m
ag
e
v
is
u
ali
za
tio
n
f
o
r
p
r
o
p
er
d
iag
n
o
s
is
Me
d
ical
i
m
a
g
es.
T
h
e
m
ed
ical
i
m
a
g
e
co
n
s
is
ts
o
f
s
e
v
er
al
ar
ti
f
ac
ts
an
d
n
o
i
s
es
t
h
at
cr
ea
te
co
m
p
l
ex
it
y
i
n
r
ea
d
in
g
o
f
m
ed
ical
i
m
a
g
es.
T
h
er
e
ar
e
v
ar
io
u
s
p
r
ep
r
o
ce
s
s
in
g
tec
h
n
iq
u
es
s
u
ch
as
A
d
ap
ti
v
e
Me
d
ia
n
Fil
ter
,
Mo
r
p
h
o
lo
g
ical
Op
er
atio
n
s
,
Me
a
n
F
ilter
o
r
Av
er
ag
e
Fi
lter
,
His
to
g
r
a
m
E
q
u
aliza
tio
n
,
Sp
atial
Do
m
ai
n
E
n
h
a
n
ce
m
en
t
Me
th
o
d
,
etc
ar
e
u
s
ed
to
en
h
a
n
ce
th
e
m
ed
ical
i
m
a
g
e
f
o
r
b
etter
v
is
i
b
ilit
y
[
9
-
1
0
]
.
T
h
er
e
ar
e
s
ev
er
al
alg
o
r
ith
m
s
p
r
o
p
o
s
ed
in
r
ev
ie
w
o
f
liter
at
u
r
e
f
o
r
ac
h
iev
in
g
b
etter
r
ea
d
ab
ili
t
y
o
f
b
r
ain
MRI
i
m
a
g
es.
T
h
is
p
ap
er
p
r
esen
ts
a
d
is
cu
s
s
i
o
n
o
f
a
n
o
v
el
an
d
s
i
m
p
le
s
o
l
u
tio
n
th
at
tar
g
ets
to
ad
d
r
ess
th
e
r
esear
ch
g
ap
ass
o
ciate
d
w
it
h
i
m
a
g
e
p
r
ep
r
o
ce
s
s
in
g
o
f
b
r
ain
MRI.
T
h
e
o
r
g
an
iza
tio
n
o
f
t
h
e
p
r
o
p
o
s
ed
m
a
n
u
s
cr
ip
t
is
as
f
o
llo
w
in
g
:
-
Sectio
n
1
.
1
d
i
s
cu
s
s
es
ab
o
u
t
t
h
e
ex
i
s
tin
g
liter
at
u
r
es
w
h
er
e
d
if
f
er
en
t
tech
n
iq
u
es
ar
e
d
is
cu
s
s
ed
f
o
r
d
etec
tio
n
s
c
h
e
m
es
u
s
ed
i
n
p
o
w
er
tr
an
s
m
i
s
s
io
n
l
in
e
s
f
o
llo
wed
b
y
d
is
c
u
s
s
io
n
o
f
r
esear
ch
p
r
o
b
lem
s
in
Sect
io
n
1
.
2
an
d
p
r
o
p
o
s
ed
s
o
lu
tio
n
i
n
1
.
3
.
Sectio
n
2
d
is
c
u
s
s
es
ab
o
u
t
a
lg
o
r
i
th
m
i
m
p
le
m
e
n
tatio
n
f
o
llo
w
ed
b
y
d
is
c
u
s
s
io
n
o
f
r
esu
lt a
n
al
y
s
i
s
in
Sectio
n
3
.
Fin
all
y
,
th
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
tu
d
y
d
is
c
u
s
s
ed
ab
o
u
t
v
ar
io
u
s
r
esear
ch
a
tte
m
p
t
s
to
war
d
r
esear
ch
-
b
ased
tech
n
iq
u
e
s
o
n
b
r
ain
MRI
I
m
ag
e
s
.
T
h
e
w
o
r
k
ca
r
r
ie
d
o
u
t
b
y
Min
a
n
d
K
y
u
[
1
1
]
h
av
e
u
s
ed
f
u
s
io
n
tech
n
iq
u
e
f
o
r
B
r
ain
s
MRI
i
m
a
g
e
en
h
a
n
ce
m
en
t
an
d
cl
u
s
ter
in
g
tech
n
iq
u
e
f
o
r
tu
m
o
r
s
e
g
m
en
tatio
n
.
A
le
x
et
al.
[
1
2
]
h
a
v
e
ap
p
lied
m
ac
h
i
n
e
lear
n
in
g
ap
p
r
o
ac
h
w
i
th
clas
s
i
cica
l
au
to
e
n
co
d
er
in
o
r
d
er
to
p
er
f
o
r
m
t
u
m
er
s
eg
m
e
n
tatio
n
task
o
f
b
r
ain
MRI.
Or
tiz
et
al.
[
1
3
]
h
av
e
co
n
s
tr
u
c
ted
a
f
ea
tu
r
ed
f
r
a
m
e
w
o
r
k
t
h
at
b
ased
o
n
u
n
s
u
p
er
v
i
s
ed
tech
n
i
q
u
es
t
h
at
co
n
tai
n
s
b
o
th
v
ec
to
r
q
u
an
t
izatio
n
an
d
f
u
zz
y
s
y
s
te
m
f
o
r
b
r
ain
MRI
s
eg
m
e
n
tatio
n
.
A
b
b
asi
a
n
d
T
aj
er
i
P
o
u
r
[
1
4
]
h
av
e
co
n
s
id
er
ed
jo
in
t
ap
p
r
o
ac
h
o
f
class
i
f
icatio
n
an
d
clu
s
ter
in
g
t
o
d
etec
t
th
e
b
r
ain
tu
m
o
r
f
r
o
m
MRI
i
m
a
g
es.
Gu
p
ta
an
d
P
o
r
w
al
[
1
5
]
h
av
e
u
s
ed
I
m
ag
e
en
h
a
n
ce
m
e
n
t
A
lo
g
o
r
it
h
m
i
n
o
r
d
er
to
en
h
a
n
ce
t
h
e
v
is
i
b
ilit
y
o
f
B
r
ain
a
n
d
B
r
ea
r
t
ca
n
ce
r
m
ed
ical
I
m
ag
e
s
.
I
n
th
e
w
o
r
k
o
f
Me
n
ze
et
a
l.
[
1
6
]
h
av
e
r
e
p
o
r
ted
ab
o
u
t
th
e
p
er
f
o
r
m
an
ce
o
f
B
r
ain
T
u
m
o
r
M
R
I
Se
g
m
e
n
tatio
n
m
u
lti
m
o
d
el
th
a
t
co
n
d
u
cted
in
MI
C
C
A
I
2
0
1
2
an
d
in
co
n
f
er
en
ce
s
2
0
1
3
.
B
h
ask
ar
r
ao
et
al.
[
1
7
]
h
av
e
m
ad
e
th
eir
ef
f
o
r
t
b
ased
o
n
B
er
k
ele
y
w
a
v
elet
tr
an
s
f
o
r
m
atio
n
with
SV
M
class
if
ie
r
in
o
r
d
er
to
r
ed
u
ce
th
e
co
m
p
le
x
it
y
o
cc
u
r
s
in
m
ed
ical
i
m
a
g
e
s
eg
m
e
n
tat
io
n
o
p
er
atio
n
.
Dh
ag
e
et
al.
[
1
8
]
h
av
e
ca
r
r
ied
w
ater
s
h
ed
i
m
ag
e
s
e
g
m
en
tatio
n
ap
p
r
o
ac
h
o
f
b
r
ain
MRI
an
a
l
y
s
is
f
o
r
d
i
f
f
er
en
tiat
i
n
g
n
o
r
m
al
a
n
d
ab
n
o
r
l
m
al
b
ar
in
tis
s
u
e.
T
h
e
s
t
u
d
y
o
f
Fais
al
et
al.
[
1
9
]
h
a
v
e
u
tili
ze
d
m
at
h
e
m
a
tical
m
o
d
elin
g
f
o
r
r
ed
u
cin
g
n
o
is
e
w
i
th
i
m
p
r
o
v
ed
s
eg
m
e
n
tatio
n
tech
n
i
q
u
e
f
o
r
d
etec
tin
g
tu
m
o
r
f
r
o
m
2
D
b
ar
in
MRI
i
m
a
g
es.
I
n
[
2
0
]
J
u
i
et
al.
h
av
e
p
r
esen
ted
a
n
e
w
ap
p
r
o
ac
h
b
ased
o
n
f
ea
tu
r
e
e
x
tr
ac
tio
n
f
o
r
ac
h
iev
in
g
b
ette
r
ac
cu
r
ac
y
i
n
m
ed
ical
i
m
a
g
e
s
eg
m
e
n
tat
io
n
.
Ka
u
r
a
n
d
R
a
n
i
[
2
1
]
h
av
e
i
n
tr
o
d
u
ce
d
a
h
i
s
to
g
r
a
m
tech
n
iq
u
e
as
ef
f
ec
tiv
e
ap
p
r
o
ac
h
f
o
r
en
h
a
n
c
in
g
co
n
tr
ast
a
n
d
b
r
ig
h
tn
e
s
s
o
f
m
ed
ical
i
m
ag
e
s
.
Me
g
er
s
a
an
d
A
le
m
u
[
2
2
]
h
av
e
d
esig
n
ed
an
au
to
m
ated
f
r
a
m
e
w
o
r
k
b
ased
o
n
n
e
u
r
al
n
et
wo
r
k
co
m
p
o
s
ed
o
f
p
r
ep
r
o
ce
s
s
i
n
g
,
i
m
a
g
e
f
u
s
io
n
,
class
i
f
icatio
n
task
f
o
r
au
to
m
atic
i
m
ag
e
s
e
g
m
e
n
tatio
n
a
n
d
tu
m
o
r
d
etec
tio
n
f
o
r
m
b
r
ain
MRI.
I
n
[
2
3
]
th
e
P
ar
v
ee
n
an
d
Si
n
g
h
h
a
v
e
u
s
e
d
co
m
b
i
n
ed
tech
n
iq
u
e
th
a
t
c
o
m
p
o
s
ed
o
f
SVM
a
n
d
d
ata
c
lu
s
ter
i
n
g
tec
h
n
iq
u
e
in
o
r
d
er
to
en
h
a
n
ce
t
h
e
MRI
i
m
ag
e
s
f
o
r
p
r
ed
ictin
g
b
r
ain
tu
m
o
r
.
P
er
eir
a
et
al.
[
2
4
]
h
av
e
d
is
cu
s
s
ed
ab
o
u
t
M
R
I
as
a
n
e
f
f
ec
ti
v
e
w
a
y
to
an
al
y
ze
t
h
e
b
r
ai
n
t
u
m
er
a
n
d
t
h
e
au
t
h
o
r
h
av
e
p
r
esen
ted
a
m
o
d
el
b
ased
o
n
t
h
e
C
o
n
v
o
lu
tio
n
al
n
e
u
r
al
n
et
w
o
r
k
in
o
r
d
er
to
ac
h
ie
v
e
a
r
eliab
le
s
eg
m
e
n
tatio
n
o
f
MRI.
I
n
w
o
r
k
o
f
[
2
5
]
R
ao
et
al.
h
av
e
co
n
s
id
er
ed
a
class
o
f
s
ta
tis
tical
m
o
d
eli
n
g
tech
n
iq
u
e
to
class
i
f
y
a
n
d
d
etec
t
t
h
e
r
e
g
io
n
o
f
b
r
ain
t
u
m
o
r
in
th
e
MRI.
I
n
t
h
e
s
a
m
e
w
a
y
Sen
t
h
il
k
u
m
ar
an
an
d
T
h
i
m
m
iar
aj
a
[
2
6
]
h
a
v
e
u
s
ed
His
to
g
r
a
m
eq
u
ali
za
tio
n
a
n
d
Sh
ar
m
a
an
d
Me
g
h
r
aj
an
i
[
2
7
]
h
av
e
u
s
ed
m
at
h
e
m
atica
l
m
o
r
p
h
o
lo
g
ical
m
o
d
el
to
e
n
h
a
n
ce
th
e
m
ed
ical
i
m
ag
e
v
is
ib
il
it
y
f
o
r
e
f
f
icie
n
tl
y
a
n
al
y
zin
g
b
ar
in
tu
m
o
r
f
r
o
m
M
R
I
.
T
h
e
w
o
r
k
o
f
Su
lai
m
a
n
et
al.
[
2
8
]
p
r
esen
ted
a
n
e
w
m
o
d
el
b
ased
o
n
th
e
cl
u
s
ter
i
n
g
alg
o
r
it
h
m
,
w
h
ic
h
o
b
j
ec
tiv
e
is
to
r
em
o
v
e
th
e
s
al
t
an
d
p
ep
p
er
n
io
s
e
f
r
o
m
th
e
b
r
ain
MRI.
Xiao
et
al.
[
2
9
]
h
av
e
i
n
tr
o
d
u
ce
d
a
n
o
v
el
m
et
h
o
d
o
f
later
al
v
e
n
tr
ic
u
la
r
co
m
p
r
ess
io
n
a
n
d
d
ef
o
r
m
atio
n
f
o
r
tu
m
o
r
s
e
g
m
en
tatio
n
a
n
d
d
etec
tio
n
.
Z
elj
k
o
v
ic
et
al.
[
3
0
]
h
a
v
e
d
ev
elo
p
ed
an
i
n
telli
g
e
n
t
f
r
a
m
e
w
o
r
k
co
m
p
o
s
ed
o
f
m
u
lti
p
le
task
s
s
u
c
h
as
e
n
h
an
ce
m
e
n
t
,
s
eg
m
e
n
tatio
n
,
clas
s
i
f
icatio
n
an
d
t
u
m
o
r
a
n
al
y
s
i
s
f
r
o
m
t
h
e
B
r
ain
M
R
I
.
T
h
e
p
r
o
p
o
s
ed
f
r
am
e
w
o
r
k
ac
h
iev
e
s
g
o
o
d
ac
cu
r
ac
y
r
ate
i
n
a
u
to
m
atic
s
eg
m
e
n
tatio
n
p
r
o
ce
s
s
co
m
p
ar
ed
to
m
a
n
n
u
l
s
eg
m
e
n
tat
io
n
p
r
o
ce
s
s
.
T
h
e
w
o
r
k
is
d
o
n
e
b
y
Ha
m
ia
n
e
a
n
d
Sa
ee
d
[
3
1
]
s
h
o
w
s
th
e
SVM
ca
teg
o
r
izatio
n
o
f
MRI
B
r
ain
i
m
a
g
es
f
o
r
co
m
p
u
ter
h
elp
ed
s
tu
d
ies.
J
u
n
g
et
al.
[
3
2
]
h
av
e
p
r
esen
ted
a
m
et
h
o
d
o
f
alter
in
g
th
e
cl
u
s
te
r
o
p
tim
al
b
ef
o
r
e
clu
s
ter
p
r
o
ce
s
s
i
n
g
i
n
th
e
o
b
tain
ab
le
K
-
m
ea
n
s
p
r
ac
tice
in
to
a
f
le
x
ib
le
clu
s
ter
o
p
ti
m
al
t
h
r
o
u
g
h
p
r
i
n
cip
al
m
o
d
u
le
s
t
u
d
y
,
a
n
d
en
h
an
ci
n
g
t
h
e
p
o
s
s
ib
ilit
y
o
f
d
ata
clu
s
ter
i
n
g
.
L
a
f
ta
et
al.
[
3
3
]
h
av
e
d
e
m
o
n
s
t
r
ated
a
m
eth
o
d
f
o
r
d
iag
n
o
s
i
n
g
a
s
et
o
f
d
i
s
ea
s
es
co
n
tai
n
i
n
g
t
w
o
k
in
d
s
o
f
ca
n
ce
r
(
lu
n
g
a
s
w
ell
as
b
r
ea
s
t
ca
n
ce
r
)
,
t
w
o
d
ataset
s
f
o
r
h
ea
r
t
atta
ck
a
n
d
d
iab
et
es.
T
h
e
n
ex
t
s
e
ctio
n
b
r
ief
s
o
f
th
e
p
r
o
b
lem
s
e
x
tr
ac
ted
f
r
o
m
t
h
e
a
b
o
v
e
ap
p
r
o
ac
h
es in
an
al
y
zin
g
b
r
ain
MRI.
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
.
4
,
A
u
g
u
s
t
201
9
:
2
4
1
6
-
2424
2418
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
:
1.
Ma
j
o
r
ity
o
f
t
h
e
e
x
is
t
in
g
s
t
u
d
i
es
to
w
ar
d
s
a
n
al
y
zi
n
g
b
r
ai
n
M
R
I
ar
e
r
elate
d
to
p
r
o
b
lem
s
o
f
s
eg
m
e
n
tatio
n
an
d
class
i
f
icat
io
n
w
h
ile
v
er
y
l
ess
w
o
r
k
to
w
ar
d
s
ad
d
r
ess
in
g
e
n
h
a
n
ce
m
en
t iss
u
e.
2.
Usag
e
o
f
i
m
ag
e
en
h
a
n
ce
m
e
n
t
tech
n
iq
u
es
ar
e
eith
er
v
er
y
s
i
m
p
le
o
r
v
er
y
m
u
c
h
co
m
p
licat
ed
th
at
d
o
esn
’
t
o
f
f
er
m
u
c
h
p
r
ac
tical
in
s
i
g
h
t o
f
th
e
r
ea
l
-
u
s
a
g
e
i
n
th
e
d
ia
g
n
o
s
i
s
p
r
o
ce
s
s
.
3.
Usag
e
o
f
ex
i
s
ti
n
g
s
y
s
te
m
to
war
d
s
i
m
ag
e
a
n
al
y
s
i
s
is
h
i
g
h
l
y
iter
ativ
e
a
n
d
th
er
e
ar
e
v
er
y
l
ess
s
i
m
p
li
f
ied
tech
n
iq
u
es a
v
ailab
le
f
o
r
b
r
ain
MRI
i
m
a
g
es.
4.
T
h
er
e
is
also
les
s
av
a
ilab
ilit
y
o
f
j
o
in
t
m
ec
h
a
n
is
m
to
d
ea
l
w
i
th
m
u
ltip
le
n
u
m
b
er
o
f
p
r
o
b
lem
s
a
s
s
o
ciate
d
w
it
h
i
m
a
g
e
p
r
ep
r
o
ce
s
s
.
T
h
er
ef
o
r
e,
th
e
p
r
o
b
lem
s
tat
e
m
en
t
o
f
th
e
p
r
o
p
o
s
ed
s
tu
d
y
ca
n
b
e
s
tated
as
“
Dev
elo
p
in
g
a
co
m
p
u
tatio
n
al
m
o
d
el
th
at
c
an
j
o
in
tl
y
ad
d
r
ess
m
u
ltip
le
p
r
o
b
lem
s
as
s
o
ciate
d
w
i
th
i
m
ag
e
e
n
h
an
ce
m
e
n
t
ex
clu
s
i
v
el
y
r
elate
d
to
b
r
ai
n
M
R
I
is
ch
a
llen
g
i
n
g
”.
T
h
e
n
e
x
t
s
ec
tio
n
o
u
tli
n
es
th
e
p
r
o
p
o
s
ed
s
o
lu
tio
n
to
ad
d
r
ess
th
is
p
r
o
b
le
m
.
T
h
e
p
r
im
e
ai
m
o
f
t
h
e
p
r
o
p
o
s
ed
s
tu
d
y
i
s
to
o
f
f
er
s
o
lu
tio
n
s
to
w
ar
d
s
s
o
m
e
o
f
t
h
e
f
r
eq
u
e
n
tl
y
o
cc
u
r
r
in
g
p
r
o
b
lem
s
t
h
at
ac
t
a
s
i
m
p
ed
i
m
en
t
i
n
an
al
y
zi
n
g
m
ed
ical
i
m
a
g
es
esp
ec
ial
l
y
b
r
a
in
MRI.
Fro
m
t
h
e
p
r
io
r
s
ec
tio
n
,
it h
as b
ee
n
s
ee
n
t
h
at
t
h
er
e
ar
e
p
r
o
b
lem
s
as
s
o
ciate
d
w
it
h
h
o
m
o
g
en
it
y
o
f
p
i
x
el
in
f
o
r
m
a
tio
n
,
n
o
is
e
i
n
clu
s
io
n
,
a
n
d
co
m
p
le
x
i
m
p
le
m
en
tatio
n
p
r
o
ce
s
s
t
h
at
ad
v
er
s
el
y
af
f
ec
t
s
t
h
e
ad
v
an
ce
f
o
r
m
s
o
f
a
n
al
y
s
i
s
o
v
er
th
e
b
r
ai
n
M
R
I
i
m
a
g
e.
T
h
er
ef
o
r
e,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
o
f
f
er
s
t
h
r
ee
d
if
f
er
en
t
s
et
o
f
s
o
lu
t
io
n
i
n
o
r
d
er
to
ad
d
r
ess
th
i
s
p
r
o
b
le
m
th
at
i
s
d
ir
ec
tl
y
r
e
lated
to
i
m
a
g
e
e
n
h
an
ce
m
e
n
t.
F
ig
u
r
e
1
h
ig
h
li
g
h
ts
th
e
s
c
h
e
m
atic
d
ia
g
r
a
m
o
f
p
r
o
p
o
s
ed
s
o
lu
tio
n
.
A
l
g
o
r
i
t
h
m
f
o
r
m
i
n
i
m
i
z
i
n
g
h
o
m
o
g
e
n
i
t
y
p
r
o
b
l
e
m
s
A
l
g
o
r
i
t
h
m
f
o
r
C
o
n
t
r
o
l
l
i
n
g
N
o
i
s
e
-
r
e
l
a
t
e
d
E
n
h
a
n
c
e
m
e
n
t
A
l
g
o
r
i
t
h
m
f
o
r
P
r
o
g
r
e
s
s
i
v
e
E
n
h
a
n
c
e
m
e
n
t
H
o
m
o
g
e
n
e
i
t
y
N
o
i
s
e
S
i
m
p
l
e
I
m
p
l
e
m
e
n
t
a
t
i
o
n
P
r
o
p
o
s
e
d
S
y
s
t
e
m
P
r
o
b
l
e
m
s
A
d
d
r
e
s
s
e
d
I
n
p
u
t
B
r
a
i
n
M
R
I
O
u
t
p
u
t
E
n
h
a
n
c
e
d
I
m
a
g
e
Fig
u
r
e
1
.
Sch
e
m
atic
d
iag
r
a
m
o
f
p
r
o
p
o
s
ed
s
o
lu
tio
n
A
cc
o
r
d
in
g
to
th
e
p
r
o
p
o
s
ed
s
ch
e
m
e,
t
h
e
p
r
i
m
e
id
eo
lo
g
y
o
f
t
h
e
p
r
o
p
o
s
ed
im
p
le
m
e
n
tatio
n
s
ce
n
ar
io
is
th
at
d
if
f
er
en
t
b
r
ain
MRI
i
m
a
g
es
h
av
e
d
if
f
er
e
n
t
in
c
lu
s
io
n
o
f
r
eq
u
ir
e
m
e
n
ts
o
f
p
r
ep
r
o
ce
s
s
in
g
w
h
er
ea
s
o
n
l
y
s
in
g
le
al
g
o
r
ith
m
is
ex
ec
u
ted
to
p
er
f
o
r
m
i
m
a
g
e
en
h
a
n
ce
m
e
n
t.
T
h
is
p
r
o
b
lem
is
s
o
l
v
ed
b
y
i
n
tr
o
d
u
ci
n
g
th
r
e
e
d
if
f
er
e
n
t
s
ch
e
m
e
s
o
f
i
m
p
le
m
e
n
tatio
n
t
h
at
e
m
p
h
asize
s
o
n
ad
d
r
ess
in
g
t
h
e
h
o
m
o
g
e
n
it
y
p
r
o
b
le
m
s
,
n
o
i
s
e
-
r
elae
d
is
s
u
es,
a
s
w
e
ll
a
s
s
i
m
p
le
i
m
p
l
e
m
en
tatio
n
is
s
u
e
s
.
As
b
r
ain
M
R
I
i
m
ag
e
s
ar
e
u
s
u
al
l
y
d
ar
k
e
r
an
d
t
h
e
p
r
o
p
o
r
tio
n
s
o
f
th
e
d
ar
k
p
ix
els
ar
e
co
m
p
ar
ativ
el
y
m
o
r
e
th
a
n
MRI
o
f
o
th
er
o
r
g
an
s
o
f
h
u
m
a
n
b
o
d
y
,
it
is
ess
en
tial
t
h
at
th
er
e
th
e
i
m
ag
e
co
u
ld
b
e
s
u
b
j
ec
ted
to
alg
o
r
ith
m
s
t
h
at
is
ca
p
ab
le
o
f
p
er
f
o
r
m
i
n
g
p
r
e
-
p
r
o
ce
s
s
i
n
g
w
i
th
h
ig
h
er
d
eg
r
ee
o
f
f
le
x
ib
ilit
y
.
B
y
ad
o
p
tin
g
t
h
e
a
n
al
y
tical
r
esear
ch
m
et
h
o
d
o
lo
g
y
,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
d
es
ig
n
ed
to
o
f
f
er
th
r
ee
in
d
iv
id
u
al
a
n
d
d
is
cr
ete
s
et
o
f
i
m
ag
e
e
n
h
a
n
ce
m
en
t
o
p
er
atio
n
in
o
r
d
er
to
as
s
is
t
i
n
d
ia
g
n
o
s
in
g
b
r
ain
M
R
I
i
m
ag
e
m
o
r
e
clo
s
el
y
.
T
h
e
ad
v
an
ta
g
es
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
ar
e
as f
o
llo
w
s
:
i)
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
o
f
f
er
s
s
o
l
u
tio
n
to
m
u
ltip
le
p
r
o
b
le
m
s
a
s
s
o
ciate
d
w
i
th
i
m
ag
e
e
n
h
an
ce
m
e
n
t
t
h
at
ar
e
f
r
eq
u
en
tl
y
e
n
co
u
n
ter
ed
in
ex
is
t
in
g
r
esear
ch
-
b
ased
i
m
p
le
m
en
tatio
n
,
ii)
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
as
s
es
s
ed
u
s
i
n
g
n
o
v
el
p
er
f
o
r
m
a
n
ce
p
ar
am
eter
t
h
at
en
s
u
r
e
p
r
o
p
er
ass
es
s
m
en
t
o
f
co
n
tr
ast,
b
r
ig
h
tn
e
s
s
,
s
h
ar
p
n
es
s
,
lo
ca
lit
y
,
ex
ec
u
tio
n
p
er
f
o
r
m
a
n
ce
all
to
g
et
h
er
.
iii)
A
ll
th
e
th
r
ee
s
e
ts
o
f
alg
o
r
it
h
m
s
ar
e
m
ea
n
t to
ad
d
r
ess
d
if
f
er
e
n
t p
r
o
b
lem
s
; h
o
w
e
v
er
,
th
e
y
ca
n
also
b
e
in
ter
-
ch
an
g
ea
b
l
y
u
s
ed
i
f
m
u
lt
ip
le
s
u
ch
p
r
o
b
lem
s
ar
e
p
r
esen
t in
t
h
e
g
iv
e
n
i
n
p
u
t i
m
a
g
e,
iv
)
I
t
s
av
es
ti
m
e
a
n
d
o
f
f
er
s
m
o
r
e
p
r
o
d
u
ctiv
it
y
to
p
h
y
s
icia
n
,
w
h
o
ca
n
p
er
f
o
r
m
clo
s
er
s
t
u
d
y
o
f
g
iv
e
n
i
n
p
u
t
o
f
b
r
ain
MRI
i
m
a
g
e
w
it
h
w
id
er
r
an
g
es
o
f
s
elec
tio
n
o
f
i
m
ag
e
en
h
a
n
ce
m
en
t
o
p
er
atio
n
.
Ap
ar
t
f
r
o
m
t
h
e
ab
o
v
e
-
m
en
t
io
n
ed
ad
v
a
n
tag
e
s
,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
a
ls
o
o
f
f
er
s
o
p
ti
m
izatio
n
to
s
i
m
p
le
f
ilt
er
in
g
p
r
o
ce
s
s
w
h
ic
h
w
ill
in
f
er
a
f
ac
t
th
at
it
is
f
ea
s
ib
le
to
p
er
f
o
r
m
n
o
n
-
r
ec
u
r
s
i
v
e
o
p
er
atio
n
i
n
o
r
d
er
to
o
b
tain
h
i
g
h
l
y
en
h
a
n
ce
d
i
m
a
g
e.
T
h
e
n
e
x
t sec
tio
n
ill
u
s
tr
ate
s
ab
o
u
t th
e
al
g
o
r
ith
m
s
b
ein
g
i
m
p
le
m
en
ted
.
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
I
n
teg
r
a
ted
mo
d
ellin
g
a
p
p
r
o
a
c
h
fo
r
en
h
a
n
cin
g
b
r
a
in
M
R
I
w
ith
flexib
le
p
r
e
-
p
r
o
ce
s
s
in
g
…
(
Ha
r
is
h
S
.
)
2419
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
p
r
esen
t
s
d
is
c
u
s
s
i
o
n
o
f
all
th
e
co
r
e
alg
o
r
ith
m
s
th
at
w
o
r
k
s
i
n
a
n
i
n
te
g
r
ated
m
an
n
er
to
o
f
f
er
a
co
m
p
r
e
h
en
s
i
v
e
en
h
a
n
c
e
m
en
t
o
f
t
h
e
b
r
ain
MRI
i
m
a
g
e.
T
h
e
id
eo
lo
g
y
o
f
t
h
is
alg
o
r
it
h
m
co
n
s
tr
u
ctio
n
is
th
at
d
if
f
er
en
t
b
r
ain
MRI
i
m
ag
es
w
il
l
h
a
v
e
d
if
f
er
e
n
t
f
o
r
m
s
o
f
p
r
o
b
lem
s
w
h
ic
h
ar
e
r
eq
u
ir
ed
to
b
e
ad
d
r
ess
ed
in
p
r
ep
r
o
ce
s
s
in
g
s
ta
g
es
it
s
elf
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
d
is
cu
s
s
e
s
ab
o
u
t
th
r
ee
d
if
f
er
en
t
p
o
s
s
ib
il
ities
o
f
s
o
lu
tio
n
s
to
elev
iate
t
h
e
i
m
ag
e
e
n
h
a
n
ce
m
e
n
t p
r
o
ce
s
s
u
s
in
g
s
i
m
p
le
p
r
o
ce
s
s
o
f
i
m
p
le
m
e
n
tatio
n
.
2
.
1
.
So
lutio
n t
o
wa
rds
ho
m
o
g
eneit
y
pro
ble
m
s
o
f
bra
in
M
RI
As
s
ee
n
i
n
e
x
is
ti
n
g
s
y
s
te
m
,
t
h
er
e
ar
e
v
ar
io
u
s
f
o
r
m
s
o
f
ap
p
r
o
ac
h
es
f
o
r
s
tr
etch
i
n
g
t
h
e
c
u
m
u
l
ativ
e
g
r
a
y
lev
els
o
f
t
h
e
m
ed
ical
i
m
a
g
es
o
f
th
e
b
r
ai
n
.
Ho
w
ev
er
,
n
o
t
all
tech
n
iq
u
e
s
h
a
v
e
b
ee
n
u
s
ed
f
o
r
MRI
f
o
r
m
,
w
h
ic
h
o
f
f
er
s
b
etter
r
eso
lu
t
io
n
co
m
p
a
r
ed
to
o
th
er
f
o
r
m
s
o
f
r
ad
io
lo
g
ical
i
m
a
g
es
o
f
b
r
ain
.
T
h
er
ef
o
r
e,
th
e
p
r
i
m
e
ai
m
o
f
th
is
s
o
l
u
tio
n
is
to
o
f
f
er
a
n
o
n
-
li
n
ea
r
i
m
a
g
e
en
h
an
ce
m
e
n
t
p
r
o
ce
s
s
to
m
a
k
e
s
i
m
p
le
p
r
o
ce
s
s
o
f
r
ec
tify
in
g
th
e
ar
tif
ac
ts
ir
r
esp
ec
t o
f
a
n
y
f
o
r
m
o
f
i
m
a
g
es.
T
h
e
alg
o
r
it
h
m
d
es
i
g
n
ed
f
o
r
th
is
p
u
r
p
o
s
e
is
a
s
s
h
o
w
n
b
elo
w
:
Alg
o
rit
h
m
f
o
r
m
in
i
m
izi
ng
ho
m
o
g
enit
y
pro
ble
m
s
I
np
ut
: I
(
I
n
p
u
t b
r
ai
n
MRI)
,
a
(
ex
p
o
n
en
t)
O
utput
: β
1
(
co
n
tr
ast),
β
2
(
s
h
ar
p
n
ess
)
Sta
rt
1
.
in
it I
,
a
2
.
I
1
I
a
3
.
I
1
f
1
(
2
5
5
*
I
1
.
/3
0
0
)
4
.
[
α
1
α
2
]
f
2
(
f
1
(I
1
))
5
.
α
3
f
3
(
f
1
(I
1
))
6
.
β
1
f
4
(
f
1
(I
1
))
7
.
β
2
f
5
(
f
1
(I
1
))
8
.
a
o
p
tim
ize(
b
ix
)
9
.
r
ep
ea
t step
-
5
,
6
,
7
f
o
r
n
e
w
a
v
alu
e
E
nd
T
h
e
h
o
m
o
g
e
n
it
y
p
r
o
b
le
m
s
i
n
b
r
ain
MRI
i
s
u
s
u
a
ll
y
ca
u
s
ed
i
f
t
h
e
co
n
tr
a
s
ts
a
s
w
ell
a
s
s
h
ar
p
n
ess
ar
e
n
o
t
u
n
i
f
o
r
m
l
y
m
ain
tain
ed
.
T
h
e
s
tep
-
w
i
s
e
d
escr
ip
tio
n
o
f
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
is
a
s
f
o
llo
w
s
:
T
h
e
alg
o
r
it
h
m
tak
es
t
h
e
in
p
u
t
i
m
ag
e
(
I
)
an
d
ex
p
o
n
en
t
ial
f
ac
to
r
(
a)
as
th
e
i
n
p
u
t
t
h
at
af
ter
p
r
o
ce
s
s
in
g
o
f
f
e
r
s
t
w
o
s
i
g
n
i
f
ican
t
s
o
u
tco
m
e
o
f
β
1
(
I
n
p
u
t
b
r
ain
MRI)
an
d
β
2
(
s
h
ar
p
n
e
s
s
)
(
L
i
n
e
-
1
)
.
T
h
e
ex
p
o
n
en
tial
v
ar
iab
le
a
is
u
s
ed
f
o
r
en
co
d
in
g
an
d
d
ec
o
d
in
g
o
p
er
atio
n
in
o
r
d
er
to
p
er
f
o
r
m
n
o
n
-
li
n
ea
r
it
y
o
p
er
atio
n
s
(
L
in
e
-
2
)
to
o
b
tain
a
p
r
o
ce
s
s
ed
i
m
a
g
e
I
1
.
A
s
e
t
o
f
s
i
m
p
le
d
is
cr
ete
f
u
n
ct
io
n
f
1
(
x
)
is
d
esi
g
n
ed
f
o
r
m
a
k
i
n
g
it
a
s
u
n
s
i
g
n
ed
in
te
g
er
o
f
8
b
its
(
L
in
e
-
3
)
.
T
h
is
o
p
er
atio
n
is
f
o
llo
w
ed
b
y
ap
p
ly
in
g
a
s
p
ec
i
f
ic
f
u
n
ctio
n
f
2
(
x
)
in
L
in
e
-
4
i
n
o
r
d
er
to
o
b
tain
a
co
n
tr
ast
-
s
p
ec
if
ic
in
f
o
r
m
atio
n
f
r
o
m
I
1
.
T
h
e
alg
o
r
ith
m
al
s
o
co
m
p
u
te
s
co
n
tr
a
s
t p
er
p
ix
els
α
3
w
it
h
a
n
aid
o
f
f
u
n
c
tio
n
f
3
(
x
)
in
L
i
n
e
-
5
w
it
h
an
i
n
p
u
t
o
f
g
r
a
y
s
ca
le
i
m
ag
e.
I
t
is
o
b
tain
ed
b
y
ca
lcu
latin
g
av
er
ag
e
o
f
m
atr
i
x
ele
m
en
ts
f
o
r
d
if
f
er
en
tial
i
m
a
g
e
th
a
t
is
e
x
tr
ac
ted
b
y
ap
p
ly
in
g
co
n
v
o
lu
tio
n
o
p
er
atio
n
o
n
g
r
a
y
s
ca
le
i
m
a
g
e
u
s
i
n
g
k
er
n
el
m
atr
ix
(
L
i
n
e
-
5
)
.
Fin
all
y
,
t
w
o
f
u
n
ctio
n
s
β
1
(
x
)
an
d
β
2
(
x
)
ar
e
ap
p
lied
to
o
b
tain
th
e
co
n
tr
as
t
an
d
s
h
ar
p
n
es
s
in
t
h
e
p
r
o
ce
s
s
ed
i
m
a
g
e
I
1
(
L
i
n
e
-
6
an
d
L
in
e
-
7
)
.
T
h
e
c
o
n
tr
ast
i
s
ca
lc
u
lated
as
f
o
llo
ws
-
it
co
m
p
u
te
s
t
h
e
m
ea
n
o
f
th
e
in
p
u
t
i
m
a
g
e
th
a
n
s
u
b
tr
ac
t
t
h
e
m
ea
n
f
r
o
m
m
ai
n
m
atr
i
x
o
f
i
n
p
u
t
i
m
a
g
e.
T
h
e
o
b
tain
e
d
d
if
f
er
e
n
ce
is
t
h
a
n
s
q
u
ar
ed
f
o
llo
w
ed
b
y
ap
p
ly
i
n
g
s
q
u
ar
er
o
o
t
o
f
s
u
m
m
atio
n
o
f
all
th
e
s
q
u
ar
ed
d
if
f
er
en
ce
o
b
tain
ed
in
p
r
io
r
s
tep
.
T
h
e
co
n
tr
ast
is
o
b
tain
ed
b
y
d
i
v
id
i
n
g
t
h
e
s
q
u
ar
e
-
r
o
o
t
o
f
s
u
m
to
p
r
o
d
u
ct
o
f
s
i
ze
s
o
f
o
r
ig
i
n
al
i
m
a
g
es.
T
h
e
s
h
ar
p
n
ess
i
s
o
b
tain
ed
by
ap
p
l
y
i
n
g
ap
p
r
o
x
i
m
ated
g
r
a
d
ien
t
to
th
e
d
o
u
b
le
p
r
ec
is
io
n
im
ag
e.
T
h
e
s
q
u
ar
e
r
o
o
t
o
f
th
e
s
u
m
m
at
io
n
s
o
f
d
u
al
co
ef
f
icie
n
t
s
is
o
b
tain
ed
f
o
llo
w
ed
b
y
d
iv
id
in
g
th
e
s
u
m
o
f
all
th
e
o
b
tain
ed
s
q
u
ar
e
r
o
o
t
v
alu
e
to
n
u
m
b
er
o
f
m
atr
i
x
ele
m
en
t
s
.
T
h
is
o
p
er
atio
n
f
i
n
all
y
g
i
v
es
b
etter
s
h
ar
p
n
es
s
to
i
m
a
g
e.
T
h
e
n
e
x
t
p
r
o
ce
s
s
i
s
to
p
er
f
o
r
m
o
p
tim
izatio
n
o
f
b
o
th
co
n
tr
ast
s
as
w
ell
a
s
s
h
ar
p
n
e
s
s
f
ac
to
r
.
F
o
r
th
is
p
u
r
p
o
s
e,
th
e
e
x
p
o
n
en
ti
al
v
al
u
e
a
i
s
f
u
r
t
h
er
o
p
tim
ized
u
s
i
n
g
a
n
e
w
v
ar
iab
le
b
ix
w
h
er
e
b
ix
r
ep
r
esen
ts
a
c
o
n
d
itio
n
w
h
er
e
s
u
m
m
atio
n
o
f
s
h
ar
p
n
es
s
v
alu
e
i
s
eq
u
al
to
m
ax
i
m
u
m
v
a
lu
e
o
f
s
h
ar
p
n
ess
.
2
.
2
.
So
lutio
n t
o
wa
rds
no
is
e
-
re
la
t
ed
enha
nce
m
ent
pro
ble
m
Den
o
is
i
n
g
p
r
in
cip
les
u
s
u
all
y
i
n
v
o
l
v
es
to
o
m
an
y
s
er
ies
o
f
o
p
er
atio
n
r
ig
h
t
f
r
o
m
id
en
ti
f
icatio
n
o
f
n
o
is
e
t
y
p
es
to
p
r
ev
en
tin
g
it.
Hen
ce
,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
co
n
tr
ib
u
tes
to
o
f
f
er
a
s
i
m
p
le
d
en
o
i
s
in
g
p
r
in
c
ip
le
t
h
at
ca
n
p
er
f
o
r
m
r
e
m
o
v
al
o
f
n
o
i
s
e
wh
ile
b
alan
c
in
g
t
h
e
i
m
a
g
e
e
n
h
an
ce
m
e
n
t
p
r
o
ce
s
s
s
i
m
u
lata
n
e
o
u
s
l
y
.
P
r
ese
n
ce
o
f
s
ig
n
i
f
ica
n
t
n
o
is
e
s
e.
g
.
m
u
l
tip
licativ
e
n
o
is
e
is
q
u
ite
in
e
v
it
ab
le
in
b
r
ain
MRI
i
m
a
g
es
t
h
at
also
af
f
ec
t
t
h
e
b
r
ig
h
t
n
es
s
asp
ec
t
o
f
it.
T
h
e
p
r
esen
t
al
g
o
r
ith
m
is
ca
p
ab
l
e
o
f
id
en
tify
i
n
g
t
h
e
f
r
eq
u
en
c
y
d
o
m
ai
n
o
f
t
h
e
illu
m
i
n
an
ce
a
s
w
ell
as
r
e
f
lecta
n
ce
f
ac
to
r
f
o
r
ad
d
r
ess
in
g
t
h
e
e
n
h
a
n
ce
m
en
t
an
d
n
o
is
e
p
r
o
b
lem
.
T
h
e
s
tep
s
o
f
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
ar
e
as
f
o
ll
o
w
s
:
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
.
4
,
A
u
g
u
s
t
201
9
:
2
4
1
6
-
2424
2420
Alg
o
rit
h
m
f
o
r
Co
ntr
o
llin
g
N
o
is
e
-
re
la
t
ed
E
nh
a
nce
m
e
nt
I
np
ut
: I
(
in
p
u
t i
m
ag
e)
,
r
(
r
o
w
s
)
,
c
(
co
lu
m
n
s
)
,
an
d
n
(
f
ilter
)
O
utput
: I
1
(
en
h
a
n
ce
d
i
m
a
g
ed
)
Sta
rt
1
.
in
it r
,
c,
n
2
.
F
o
r
i=1
:
r
3
.
F
o
r
j
=1
:c
4
.
5
.
0
2
2
,
))
)
2
(
)
2
(((
c
j
r
i
A
j
i
5
)
))
10
((
1
(
1
2
.
,
n
j
i
j
i
A
H
6
.
E
nd
7
.
E
nd
8
.
I
1
g
(
I
,
n
,
aL
,
aH)
E
nd
T
h
e
alg
o
r
ith
m
tak
e
s
th
e
i
n
p
u
t
i
m
a
g
e
I
as
w
ell
as
r
(
r
o
w
s
)
,
c
(
co
lu
m
n
s
)
,
an
d
n
(
f
ilter
)
.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
i
s
u
s
ed
f
o
r
en
h
an
ci
n
g
th
e
g
r
a
y
s
ca
le
i
m
a
g
e
o
f
b
r
ain
M
R
I
w
it
h
r
esp
ec
t
to
it
s
ap
p
ea
r
an
ce
.
I
t
d
o
es
s
o
b
y
co
m
p
r
ess
io
n
t
h
e
i
llu
m
i
n
ati
o
n
an
d
i
m
p
r
o
v
es
t
h
e
r
ef
lectio
n
asp
ec
t
o
f
t
h
e
i
m
a
g
e.
T
h
e
al
g
o
r
ith
m
co
n
s
id
er
s
co
m
p
u
tatio
n
f
o
r
all
t
h
e
r
o
w
s
(
L
i
n
e
-
2
)
a
n
d
all
th
e
co
l
u
m
n
s
(
L
in
e
-
3
)
to
co
m
p
u
te
th
e
e
m
p
ir
ic
al
ex
p
r
ess
io
n
o
f
t
h
e
f
ilter
(
L
in
e
-
4
an
d
L
in
e
-
5
)
.
T
h
e
alg
o
r
ith
m
also
co
n
s
id
er
s
th
r
ee
u
s
er
-
d
e
f
i
n
ed
in
p
u
t
s
i.e
.
n
,
aL
,
an
d
aH
in
o
r
d
er
to
f
u
r
t
h
er
ex
ec
u
tes
a
f
u
n
ctio
n
g
(
L
in
e
-
8
)
.
T
h
e
f
u
n
ctio
n
g
(
x
)
is
r
esp
o
n
s
ib
le
f
o
r
o
p
tim
iz
in
g
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
n
o
is
e
-
r
e
m
o
v
al
o
p
er
atio
n
i
n
o
r
d
er
to
o
f
f
er
a
n
o
u
tp
u
t
o
f
en
h
an
ce
d
i
m
a
g
e
I
1
(
L
i
n
e
-
8
)
.
T
h
e
en
h
a
n
ce
m
e
n
t
p
r
o
ce
s
s
is
as
f
o
llo
w
s
:
-
t
h
e
i
n
p
u
t
g
r
a
y
s
ca
led
i
m
a
g
e
i
s
ch
an
g
ed
to
d
o
u
b
le
p
r
ec
is
io
n
i
m
ag
e
f
o
llo
w
ed
b
y
ex
tr
ac
tio
n
o
f
s
ize
o
f
th
i
s
i
m
a
g
e
to
g
e
n
er
ate
r
a
n
d
c
v
al
u
es
th
at
is
u
s
ed
i
n
L
i
n
e
-
2
a
n
d
L
i
n
e
-
3
.
T
h
e
e
m
p
ir
ical
ex
p
r
ess
io
n
i
n
L
i
n
e
-
5
is
ex
ec
u
t
ed
to
r
em
o
v
e
t
h
e
ar
tif
ac
t
s
w
i
t
h
r
esp
ec
t
to
th
e
in
p
u
t
ar
g
u
m
e
n
ts
o
f
r
,
c,
an
d
n
in
o
r
d
er
t
o
g
en
er
ate
f
il
ter
ed
i
m
ag
e
H.
H
(
aH
-
a
L
)
*
H)
+a
L
(
1
)
T
h
e
n
ex
t
p
r
o
ce
s
s
is
to
o
b
tai
n
th
e
lo
g
ar
it
h
m
ic
v
er
s
io
n
o
f
an
i
m
a
g
e
f
o
llo
w
ed
b
y
p
er
f
o
r
m
i
n
g
Fa
s
t
Fo
u
r
ier
T
r
an
s
f
o
r
m
o
p
er
atio
n
o
n
it.
A
f
ter
ap
p
ly
i
n
g
i
n
v
er
s
e
o
p
er
atio
n
,
th
e
n
o
r
m
alize
d
i
m
a
g
e
is
o
b
tain
ed
th
at
is
b
asicall
y
tr
ea
ted
as
t
h
e
f
i
n
all
y
en
h
a
n
ce
d
i
m
a
g
e
o
f
t
h
i
s
o
p
er
atio
n
.
2
.
3
.
So
lutio
n t
o
wa
rds
s
i
m
pl
i
s
t
ic
in i
m
p
le
m
ent
a
t
io
n str
a
t
eg
y
I
t
w
as
alr
ea
d
y
n
o
ticed
th
at
ex
is
ti
n
g
ap
p
r
o
ac
h
es
h
av
e
u
s
ed
h
i
g
h
l
y
iter
ati
v
e
o
p
er
atio
n
w
h
il
e
p
er
f
o
r
m
in
g
i
m
a
g
e
clas
s
i
f
icati
o
n
,
w
h
ic
h
i
s
n
o
r
m
all
y
t
h
e
la
s
t
s
ta
g
e.
T
h
e
in
v
o
l
v
e
m
e
n
t
s
o
f
iter
ati
v
e
s
tep
s
ar
e
q
u
ite
r
eq
u
ir
ed
as
it
i
s
n
ec
e
s
s
ar
y
to
d
o
u
b
le
ch
ec
k
t
h
e
f
i
n
al
o
u
tco
m
e
b
y
e
x
tr
ac
ti
n
g
t
h
e
b
est
o
u
tco
m
e.
Ho
w
e
v
er
,
th
is
p
r
o
ce
s
s
o
f
iter
atio
n
ca
n
b
e
m
i
n
i
m
ized
i
f
n
ec
es
s
ar
y
,
ca
r
e
is
ta
k
e
n
i
n
t
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
s
tep
it
s
elf
.
T
h
er
ef
o
r
e,
th
e
p
r
i
m
e
a
g
en
d
a
o
f
th
is
al
g
o
r
ith
m
is
to
o
f
f
e
r
a
h
ig
h
l
y
p
r
o
g
r
ess
iv
e
a
s
well
as
n
o
n
-
iter
ati
v
e
ap
p
r
o
ac
h
f
o
r
p
er
f
o
r
m
in
g
i
m
a
g
e
en
h
a
n
ce
m
en
t.
T
h
e
s
tep
s
o
f
t
h
e
alg
o
r
it
h
m
ar
e
as
f
o
llo
w
s
:
Alg
o
rit
h
m
f
o
r
P
ro
g
re
s
s
iv
e
E
nh
a
nce
m
ent
I
np
ut
: I
(
in
p
u
t i
m
a
g
e)
O
utput
: I
1
(
en
h
a
n
ce
d
i
m
a
g
e)
Sta
rt
1
.
in
it r
2
.
[
co
ef
]
ϕ
+
(
I
,
f
(
s
elec
t)
)
3
.
L
L
δ (
co
ef
,
r
)
4
.
I
1
ϕ
-
(
co
ef
,
f
(
s
elec
t)
)
E
nd
T
h
e
alg
o
r
ith
m
tak
e
s
t
h
e
in
p
u
t
o
f
g
r
a
y
s
ca
led
b
r
ain
MRI
i
m
a
g
e
th
at
a
f
ter
p
r
o
ce
s
s
i
n
g
g
i
v
es
t
h
e
o
u
tco
m
e
o
f
I
1
(
en
h
a
n
ce
d
i
m
a
g
e)
.
T
h
e
a
lg
o
r
ith
m
also
ta
k
es
t
h
e
r
v
alu
e
as
t
h
e
i
n
p
u
t
(
L
i
n
e
-
1
)
w
it
h
a
s
e
lectio
n
o
f
u
s
er
-
d
ef
i
n
ed
f
il
ter
in
g
tec
h
n
q
iu
es.
A
tr
a
n
s
f
o
r
m
ed
-
b
a
s
ed
tech
n
iq
u
e
is
a
p
p
lied
f
o
r
th
e
p
r
o
p
o
s
ed
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
I
n
teg
r
a
ted
mo
d
ellin
g
a
p
p
r
o
a
c
h
fo
r
en
h
a
n
cin
g
b
r
a
in
M
R
I
w
ith
flexib
le
p
r
e
-
p
r
o
ce
s
s
in
g
…
(
Ha
r
is
h
S
.
)
2421
A
f
u
n
ctio
n
t
w
o
-
d
i
m
e
n
s
io
n
al
f
u
n
ctio
n
d
is
cr
ete
w
av
e
tr
an
s
f
o
r
m
s
ϕ
+
is
i
m
p
le
m
e
n
ted
co
n
s
id
er
in
g
t
h
e
in
p
u
t
ar
g
u
m
e
n
t
o
f
i
n
p
u
t
i
m
ag
e
a
n
d
a
f
u
n
ctio
n
to
s
elec
t
th
e
tr
an
s
f
o
r
m
atio
n
tec
h
n
iq
u
e
(
L
in
e
-
2
)
.
T
h
e
o
u
tco
m
e
f
o
r
th
i
s
p
r
o
ce
s
s
is
g
en
er
atio
n
o
f
4
d
if
f
er
en
t
co
e
f
f
icie
n
ts
e.
g
.
L
L
(
L
o
w
-
L
o
w
)
,
L
H
(
L
o
w
-
h
i
g
h
)
,
HL
(
Hig
h
L
o
w
)
,
HH
(
Hig
h
Hi
g
h
)
.
He
n
ce
,
co
e
f
=
(
L
L
,
L
H,
H
L
,
HH)
.
T
h
e
n
ex
t
p
ar
t
o
f
t
h
e
alg
o
r
it
h
m
is
to
o
f
f
er
f
u
r
t
h
er
en
h
a
n
ce
m
en
t
b
y
tar
g
eti
n
g
L
L
co
ef
f
icie
n
t
f
o
llo
w
ed
b
y
ap
p
ly
in
g
i
n
v
er
s
e
f
u
n
ct
io
n
o
n
it.
T
h
e
f
u
n
c
tio
n
δ(
x
)
i
s
m
ea
n
t
f
o
r
th
i
s
p
u
r
p
o
s
e
(
L
i
n
e
-
3
)
.
Fin
all
y
,
f
o
r
all
th
e
v
al
u
e
s
o
f
r
,
th
e
alg
o
r
it
h
m
ap
p
lies
ϕ
(
x
)
as
th
e
o
p
ti
m
ized
p
ar
am
eter
to
e
n
h
an
ce
it
f
u
r
t
h
er
.
I
n
o
r
d
er
to
p
er
f
o
r
m
o
p
ti
m
izatio
n
,
f
o
llo
w
in
g
s
tep
s
ar
e
c
o
n
d
u
cted
:
p
er
f
o
r
m
n
o
r
m
aliza
t
io
n
o
f
i
m
ag
e
f
o
llo
w
ed
b
y
g
r
a
y
s
ca
le
th
r
es
h
o
ld
in
g
to
o
b
tain
h
i
g
h
l
y
en
h
a
n
ce
d
i
m
a
g
e
I
1
(
L
in
e
-
4
)
.
T
h
er
ef
o
r
e,
th
e
alg
o
r
it
h
m
is
h
ig
h
l
y
p
r
o
g
r
es
s
iv
e
an
d
t
h
e
e
n
h
a
n
ce
m
en
t
o
f
f
er
ed
is
h
i
g
h
l
y
s
u
p
er
io
r
w
i
th
o
u
t
in
cl
u
s
io
n
o
f
an
y
co
m
p
u
tatio
n
a
ll
y
b
u
r
d
en
i
n
g
tas
k
.
T
h
e
n
ex
t
s
ec
tio
n
d
is
cu
s
s
e
s
th
e
o
u
tco
m
e
s
o
b
tain
ed
.
3.
RE
SU
L
T
S
ANA
L
YS
I
S
T
h
e
an
al
y
s
is
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
i
s
ca
r
r
ied
o
u
t
co
n
s
id
er
in
g
all
t
h
e
th
r
ee
a
lg
o
r
ith
m
s
i.e
.
A
l
g
o
r
ith
m
-
1
(
Alg
o
r
it
h
m
f
o
r
m
i
n
i
m
izi
n
g
h
o
m
o
g
en
i
t
y
p
r
o
b
le
m
s
)
,
A
l
g
o
r
ith
m
-
2
(
A
l
g
o
r
it
h
m
f
o
r
C
o
n
tr
o
llin
g
No
is
e
-
r
elate
d
E
n
h
a
n
ce
m
e
n
t)
,
an
d
A
l
g
o
r
ith
m
-
3
(
A
l
g
o
r
ith
m
f
o
r
P
r
o
g
r
ess
iv
e
E
n
h
a
n
ce
m
en
t)
.
T
h
e
co
m
p
lete
ass
es
s
m
en
t
w
a
s
ca
r
r
ied
o
u
t b
o
th
v
i
s
u
all
y
a
n
d
g
r
ap
h
ica
ll
y
u
s
i
n
g
s
tan
d
ar
d
b
r
ain
MRI
i
m
ag
e
d
ataset
[
3
4
]
3
.
1
.
Vis
ua
l o
utc
o
m
e
s
T
h
e
v
is
u
al
o
u
tco
m
e
s
T
ab
le
1
h
ig
h
li
g
h
ts
th
a
t
ea
ch
al
g
o
r
ith
m
o
f
f
er
s
d
if
f
er
e
n
t
f
o
r
m
s
o
f
v
i
s
u
alit
y
to
th
e
en
h
a
n
ce
d
i
m
a
g
e.
Fo
r
s
i
m
i
lar
s
et
o
f
g
iv
e
n
i
n
p
u
ts
,
t
h
e
o
u
t
p
u
ts
s
i
g
n
if
ican
t
d
i
f
f
er
s
th
at
s
ee
m
s
to
b
e
h
ig
h
l
y
s
p
ec
if
ic
to
s
p
ec
i
f
ic
alg
o
r
it
h
m
s
.
Ho
w
ev
er
,
ea
ch
v
i
s
u
al
o
u
tco
m
e
is
g
o
o
d
en
o
u
g
h
f
o
r
p
er
f
o
r
m
i
n
g
d
ia
g
n
o
s
tic
an
d
h
en
ce
o
f
f
er
b
etter
f
le
x
ib
ilit
y
in
i
n
v
e
s
t
g
atin
g
th
e
i
n
p
u
t
o
f
b
r
ain
M
R
I
.
A
ll
t
h
e
s
ig
n
i
f
ic
an
t
p
ar
a
m
eter
s
e.
g
.
co
n
tr
ast,
b
r
ig
h
tn
e
s
s
,
an
d
s
h
ar
p
n
es
s
h
as b
ee
n
s
i
g
n
if
ica
n
tl
y
i
m
p
r
o
v
ed
f
o
r
ea
ch
o
u
tco
m
es o
f
e
ac
h
alg
o
r
it
h
m
.
T
ab
le
1
.
Vis
u
al
o
u
tco
m
e
s
o
f
p
r
o
p
o
s
ed
s
y
s
te
m
A
l
g
o
r
i
t
h
m
-
1
A
l
g
o
r
i
t
h
m
-
2
A
l
g
o
r
i
t
h
m
-
3
I
n
p
u
t
I
mag
e
En
h
a
n
c
e
d
I
mag
e
I
n
p
u
t
I
mag
e
En
h
a
n
c
e
d
I
mag
e
I
n
p
u
t
I
mag
e
En
h
a
n
c
e
d
I
mag
e
3
.
2
.
G
ra
ph
ica
l o
utc
o
m
es
T
h
e
ass
ess
m
e
n
t
o
f
n
u
m
er
ical
o
u
tco
m
es
w
as
ca
r
r
ied
o
u
t
co
n
s
id
er
in
g
n
o
n
-
co
n
v
e
n
tio
n
al
e
n
h
an
ce
m
e
n
t
p
r
o
ce
s
s
e.
g
.
Glo
b
al
co
n
tr
ast
f
a
cto
r
,
co
n
tr
ast
p
er
p
ix
el,
co
n
tr
ast,
an
d
s
h
ar
p
n
e
s
s
.
T
h
is
p
ar
am
eter
is
co
n
s
id
er
ed
as
a
d
ir
ec
t
r
ep
r
esen
tatio
n
o
f
p
er
ce
p
tio
n
o
f
an
i
m
a
g
e
b
y
t
h
e
h
u
m
a
n
w
it
h
r
esp
ec
t
to
co
n
tr
ast.
Usi
n
g
d
i
f
f
er
e
n
t
lev
els
o
f
r
e
s
o
lu
tio
n
,
t
h
is
p
ar
a
m
eter
i
s
u
s
ed
f
o
r
ca
lcu
lat
in
g
o
v
er
all
v
al
u
e
o
f
t
h
e
co
n
tr
ast.
T
h
e
n
u
m
er
ical
o
u
tco
m
e
s
h
o
w
s
t
h
at
al
g
o
r
it
h
m
-
3
o
f
f
er
s
b
etter
Glo
b
al
C
o
n
tr
ast
f
ac
to
r
in
co
m
p
ar
is
o
n
to
o
t
h
e
r
t
w
o
a
lg
o
r
it
h
m
s
a
s
s
h
o
w
n
in
Fi
g
u
r
e
2
.
A
clo
s
er
lo
o
k
w
il
l
s
h
o
w
th
a
t
alg
o
r
ith
m
-
1
an
d
al
g
o
r
ith
m
-
2
o
f
f
er
s
n
ea
r
l
y
s
i
m
ilar
p
er
f
o
r
m
a
n
ce
.
T
h
e
ac
tu
al
i
n
f
er
en
ce
to
th
is
g
r
ap
h
ical
o
u
tco
m
e
w
ill
m
ea
n
th
at
t
h
e
r
es
u
lta
n
t
i
m
a
g
e
o
b
tain
ed
b
y
alg
o
r
ith
m
-
3
is
h
a
v
i
n
g
p
er
ce
p
tib
le
co
n
tr
ast
t
h
at
ca
n
b
e
p
r
ac
ti
ca
ll
y
s
en
s
ed
b
y
a
n
y
h
u
m
a
n
,
w
h
ic
h
is
g
o
o
d
f
r
o
m
ap
p
licatio
n
v
ie
w
p
o
in
t.
T
h
e
n
ex
t
p
er
f
o
r
m
a
n
ce
p
ar
a
m
e
ter
co
n
s
id
er
ed
f
o
r
as
s
es
s
m
e
n
t
is
co
n
tr
a
s
t
p
er
p
ix
el
th
a
t
is
ca
l
cu
lated
b
y
m
ea
n
d
if
f
er
e
n
ce
o
f
a
n
y
p
o
in
t
o
f
a
g
iv
e
n
p
i
x
el
w
i
th
it
s
n
ei
g
h
b
o
r
in
g
p
i
x
el
r
e
f
er
F
ig
u
r
e
3
.
I
n
t
h
i
s
ca
s
e,
th
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
.
4
,
A
u
g
u
s
t
201
9
:
2
4
1
6
-
2424
2422
o
u
tco
m
e
s
h
o
w
s
t
h
at
co
n
tr
as
t
v
alu
e
o
f
f
er
ed
b
y
Alg
o
r
it
h
m
-
1
i
s
m
o
r
e
as
co
m
p
ar
ed
to
alg
o
r
ith
m
-
2
an
d
alg
o
r
ith
m
-
3
.
Ho
w
e
v
er
,
t
h
e
i
n
cr
ea
s
ed
v
al
u
e
o
f
co
n
tr
as
t
w
il
l
o
n
l
y
m
ea
n
h
u
m
a
n
i
m
p
er
ce
p
tib
le
i
m
ag
e
b
y
ex
h
ib
it
in
g
t
h
e
i
m
a
g
e
to
b
e
n
e
ar
to
w
h
it
h
is
h
.
I
t
w
il
l
also
m
ea
n
t
h
at
lo
w
er
ed
v
al
u
e
o
f
co
n
tr
ast
p
er
p
ix
e
l
w
il
l
m
ea
n
a
d
ar
k
er
p
ix
el,
w
h
ic
h
is
also
h
u
m
a
n
i
m
p
er
ce
p
tib
le.
Hen
ce
,
alg
o
r
ith
m
-
1
is
g
o
o
d
f
o
r
d
ar
k
er
i
m
ag
e
w
h
il
e
alg
o
r
ith
m
-
2
is
g
o
o
d
f
o
r
i
m
ag
e
w
ith
ab
n
o
r
m
all
y
i
n
cr
ea
s
ed
c
o
n
tr
ast
r
an
g
es.
Ho
w
ev
er
,
al
g
o
r
ith
m
-
3
i
s
f
o
u
n
d
to
o
f
f
er
a
g
o
o
d
b
alan
ce
b
et
w
ee
n
th
e
h
ig
h
er
an
d
lo
w
er
in
ten
s
it
y
an
d
t
h
er
eb
y
it
o
f
f
er
s
c
u
m
u
l
ativ
el
y
g
o
o
d
g
lo
b
al
co
n
tr
ast f
ac
to
r
as seen
i
n
Fi
g
u
r
e
2.
Fig
u
r
e
4
h
ig
h
li
g
h
ts
th
e
co
m
p
a
r
ativ
e
a
n
al
y
s
i
s
o
f
th
e
all
th
e
t
h
r
ee
al
g
o
r
ith
m
s
w
it
h
r
esp
ec
t
t
o
co
n
tr
ast
w
it
h
an
ag
e
n
d
a
to
s
ee
b
etter
ca
p
ab
ilit
y
to
attai
n
i
n
cr
ea
s
e
d
co
n
tr
ast
v
al
u
e.
T
h
e
o
u
tco
m
e
s
h
o
w
s
t
h
at
o
n
l
y
alg
o
r
ith
m
-
1
an
d
al
g
o
r
ith
m
-
3
o
f
f
er
s
s
u
ch
ca
p
ab
ilit
y
to
o
f
f
er
s
co
n
tr
ast
w
i
th
i
n
b
etter
to
ler
a
b
leli
m
it
s
o
f
h
u
m
an
p
er
ce
p
tio
n
.
Ho
w
e
v
er
,
th
er
e
is
a
d
is
cr
ee
t
m
ea
n
n
g
f
o
r
b
o
th
o
f
th
e
m
as
al
g
o
r
ith
m
-
1
is
all
ab
o
u
t
n
o
n
-
lin
ea
r
m
ec
h
a
n
i
s
m
to
co
n
tr
o
l
co
n
tr
ast
w
h
i
le
alg
o
r
it
h
m
-
3
i
n
clu
d
e
s
v
ar
io
u
s
tr
an
s
f
o
r
m
ed
-
b
ased
s
tep
s
f
o
llo
w
ed
b
y
en
h
a
n
ci
n
g
t
h
e
p
i
x
els
i
n
L
L
r
e
g
io
n
alo
n
g
w
i
th
o
p
ti
m
izatio
n
.
Hen
ce
,
te
n
d
en
c
y
to
o
b
tain
b
etter
i
m
a
g
e
is
al
w
a
y
s
g
o
o
d
f
o
r
alg
o
r
ith
m
-
3
as
co
m
p
ar
ed
to
alg
o
r
ith
m
-
1
.
On
t
h
e
o
th
er
h
a
n
d
,
alg
o
r
ith
m
-
2
d
o
esn
’
t
o
f
f
er
m
u
c
h
f
le
x
ib
ilit
y
in
t
h
e
ca
lc
u
latio
n
o
f
H
th
at
r
es
u
lts
i
n
les
s
ca
p
ab
ilit
y
to
p
er
f
o
r
m
in
cr
ea
s
e
i
n
co
n
tr
ast.
Fig
u
r
e
5
s
h
o
w
s
th
e
co
m
p
ar
ativ
e
a
n
al
y
s
i
s
o
f
all
t
h
e
i
m
ag
es
w
ith
r
esp
ec
t
to
s
h
ar
p
n
ess
a
s
p
ec
t.
A
lt
h
o
u
g
h
,
s
h
ar
p
n
es
s
is
n
ec
es
s
ar
y
f
o
r
b
ette
r
i
m
ag
e
e
n
h
a
n
c
e
m
en
t
b
u
t
h
i
g
h
er
d
eg
r
ee
o
f
s
h
ar
p
n
es
s
r
esu
lts
i
n
p
ix
elate
d
i
m
ag
e
in
th
e
o
u
tco
m
e.
T
h
is
f
ac
t
ca
n
b
e
v
is
ib
le
i
n
g
r
ap
h
ical
tr
e
n
d
w
h
er
e
a
lg
o
r
ith
m
-
1
is
f
o
u
n
d
to
s
h
o
w
th
e
h
i
g
h
est
s
h
ar
p
n
es
s
w
h
ile
alg
o
r
it
h
m
-
3
is
f
o
u
n
d
to
s
h
o
w
s
l
ig
h
tl
y
le
s
s
s
h
ar
p
.
A
l
g
o
r
ith
m
-
3
ca
n
n
o
t
b
e
co
n
s
id
er
ed
to
o
f
f
er
m
u
ch
h
i
g
h
er
s
h
ar
p
n
es
s
.
Fig
u
r
e
2
.
C
o
m
p
ar
ativ
e
a
n
al
y
s
i
s
o
f
g
lo
b
al
co
n
tr
ast
f
ac
to
r
Fig
u
r
e
3
.
C
o
m
p
ar
ativ
e
a
n
al
y
s
i
s
o
f
co
n
tr
ast p
er
p
ix
el
Fig
u
r
e
4
.
C
o
m
p
ar
ativ
e
a
n
al
y
s
i
s
o
f
co
n
tr
ast
Fig
u
r
e
5
.
C
o
m
p
ar
ativ
e
a
n
al
y
s
i
s
o
f
s
h
ar
p
n
es
s
4.
CO
NCLU
SI
O
N
T
h
e
co
n
t
r
i
b
u
ti
o
n
s
o
f
th
e
p
r
o
p
o
s
e
d
s
y
s
tem
s
ar
e:
i
)
i
t
o
f
f
er
s
t
h
r
ee
s
et
o
f
f
lex
i
b
le
im
ag
e
en
h
an
ce
m
en
t
alg
o
r
ith
m
w
ith
o
p
t
im
ized
p
e
r
f
o
r
m
an
ce
,
ii
)
i
t
is
ca
p
a
b
l
e
o
f
b
alan
c
in
g
m
u
ltip
le
as
p
ec
ts
w
h
ile
p
er
f
o
r
m
in
g
im
ag
e
en
h
an
ce
m
en
t,
iii
)
it
is
co
m
p
u
tati
o
n
al
ly
f
aster
f
o
r
b
r
a
in
MRI
im
ag
es.
I
t
w
as
f
o
u
n
d
th
at
f
o
r
1
0
MRI
b
r
a
in
im
ag
es,
alg
o
r
ih
m
-
1
t
o
o
k
a
p
p
r
o
x
im
ately
0
.
7
6
6
5
s
ec
,
a
lg
o
r
ith
m
2
to
o
k
ap
p
r
o
x
im
ately
0
.
9
2
8
3
s
e
c,
w
h
ile
alg
o
r
ith
m
-
3
co
n
s
u
m
ed
a
p
p
r
o
x
im
ately
0
.
4
2
7
1
s
ec
.
E
a
ch
alg
o
r
ith
m
h
as
its
o
w
n
ca
p
a
b
i
lity
to
p
e
r
f
o
r
m
im
ag
e
en
h
an
ce
m
en
t
w
h
ich
co
m
p
let
el
y
d
ep
en
d
s
u
p
o
n
th
e
in
p
u
t
im
ag
e
o
f
b
r
ain
MR
I
.
Ou
r
f
u
tu
r
e
w
o
r
k
w
ill
b
e
in
th
e
d
i
r
e
cti
o
n
o
f
f
u
r
th
er
c
o
n
tin
u
tin
g
in
v
esti
g
a
ti
o
n
o
n
i
t t
o
a
p
p
ly
o
n
d
is
ea
s
e
id
en
tif
ic
ati
o
n
p
r
o
b
lem
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
I
n
teg
r
a
ted
mo
d
ellin
g
a
p
p
r
o
a
c
h
fo
r
en
h
a
n
cin
g
b
r
a
in
M
R
I
w
ith
flexib
le
p
r
e
-
p
r
o
ce
s
s
in
g
…
(
Ha
r
is
h
S
.
)
2423
RE
F
E
R
E
NC
E
S
[1
]
P
.
V
a
su
k
i,
J.
Ka
n
im
o
z
h
i
a
n
d
M
.
B.
De
v
i,
"
A
su
rv
e
y
o
n
im
a
g
e
p
re
p
ro
c
e
ss
in
g
tec
h
n
i
q
u
e
s
f
o
r
d
iv
e
rse
f
ield
s
o
f
m
e
d
ica
l
ima
g
e
r
y
,
"
2
0
1
7
IEE
E
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
El
e
c
trica
l,
In
stru
me
n
t
a
ti
o
n
a
n
d
C
o
mm
u
n
ic
a
ti
o
n
En
g
i
n
e
e
rin
g
(
ICEICE
)
,
Ka
ru
r
,
p
p
.
1
-
6
,
2
0
1
7
.
[2
]
S
.
L
.
Ju
i
e
t
a
l
.
,
"
Bra
in
M
RI
T
u
m
o
r
S
e
g
m
e
n
tatio
n
w
it
h
3
D
I
n
tra
c
ra
n
ial
S
tru
c
tu
re
De
f
o
rm
a
ti
o
n
F
e
a
tu
re
s,"
in
IEE
E
In
telli
g
e
n
t
S
y
ste
ms
,
v
o
l.
3
1
,
n
o
.
2
,
p
p
.
6
6
-
7
6
,
M
a
r.
-
A
p
r.
2
0
1
6
.
[3
]
De
sp
o
to
v
ić,
Iv
a
n
a
,
Ba
rt
G
o
o
ss
e
n
s,
a
n
d
W
il
f
ried
P
h
il
i
p
s.
"
M
RI
se
g
m
e
n
tatio
n
o
f
th
e
h
u
m
a
n
b
r
a
in
:
c
h
a
ll
e
n
g
e
s,
m
e
th
o
d
s,
a
n
d
a
p
p
li
c
a
ti
o
n
s,
"
Co
m
p
u
t
a
ti
o
n
a
l
a
n
d
ma
t
h
e
ma
ti
c
a
l
me
th
o
d
s
in
me
d
icin
e
2
0
1
5
(
2
0
1
5
).
[4
]
Ko
b
a
sh
i,
S
y
o
ji
,
L
á
s
z
ló
G
.
N
y
ú
l,
a
n
d
Ja
y
a
ra
m
K.
Ud
u
p
a
.
"
S
o
f
t
Co
m
p
u
t
in
g
in
M
e
d
ica
l
Im
a
g
e
P
ro
c
e
ss
in
g
,
"
Co
mp
u
t
a
ti
o
n
a
l
a
n
d
m
a
t
h
e
ma
ti
c
a
l
me
th
o
d
s
in
me
d
icin
e
2
0
1
6
,
2
0
1
6
.
[5
]
O.
G
h
rib
i,
L
.
S
e
ll
a
m
i,
M
.
Be
n
S
l
im
a
,
A
.
Be
n
Ha
m
id
a
,
C.
M
h
iri
a
n
d
K.
B.
M
a
h
f
o
u
d
h
,
"
A
n
A
d
v
a
n
c
e
d
M
RI
M
u
lt
i
-
M
o
d
a
li
t
ies
S
e
g
m
e
n
tatio
n
M
e
th
o
d
o
lo
g
y
De
d
ica
ted
to
M
u
lt
ip
le
S
c
l
e
ro
sis
L
e
sio
n
s
Ex
p
l
o
ra
ti
o
n
a
n
d
Diff
e
r
e
n
ti
a
ti
o
n
,
"
in
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
N
a
n
o
Bi
o
sc
ien
c
e
,
v
o
l.
1
6
,
n
o
.
8
,
p
p
.
6
5
6
-
6
6
5
,
De
c
.
2
0
1
7
.
[6
]
Hira
lal,
Re
sh
m
a
,
a
n
d
He
m
a
P
.
M
e
n
o
n
.
"
A
S
u
rv
e
y
o
f
Bra
in
M
RI
Im
a
g
e
S
e
g
m
e
n
tatio
n
M
e
th
o
d
s
a
n
d
th
e
Iss
u
e
s
In
v
o
lv
e
d
,
"
T
h
e
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
siu
m
o
n
In
telli
g
e
n
t
S
y
ste
ms
T
e
c
h
n
o
l
o
g
ie
s
a
n
d
Ap
p
li
c
a
ti
o
n
,
S
p
rin
g
e
r,
Ch
a
m
,
2
0
1
6
.
[7
]
L
.
Do
ra
,
S
.
A
g
ra
w
a
l,
R.
P
a
n
d
a
a
n
d
A
.
A
b
ra
h
a
m
,
"
S
tate
-
of
-
th
e
-
A
rt
M
e
th
o
d
s
f
o
r
Bra
in
T
issu
e
S
e
g
m
e
n
tatio
n
:
A
Re
v
ie
w
,
"
in
IEE
E
Rev
iews
in
B
io
me
d
ica
l
En
g
in
e
e
rin
g
,
v
o
l
.
1
0
,
p
p
.
2
3
5
-
2
4
9
,
2
0
1
7
.
[8
]
G
o
n
z
á
lez
-
V
il
là,
S
a
n
d
ra
,
e
t
a
l.
"
A
re
v
ie
w
o
n
b
ra
i
n
stru
c
t
u
re
s
se
g
m
e
n
tatio
n
in
m
a
g
n
e
ti
c
re
so
n
a
n
c
e
im
a
g
in
g
,
"
Arti
fi
c
ia
l
in
telli
g
e
n
c
e
in
me
d
icin
e
7
3
,
45
-
69
,
2
0
1
6
.
[9
]
S
.
P
o
o
rn
a
c
h
a
n
d
ra
a
n
d
C.
Na
v
e
e
n
a
,
"
P
re
-
p
ro
c
e
ss
in
g
o
f
M
R
Im
a
g
e
s
f
o
r
Eff
ici
e
n
t
Qu
a
n
ti
tativ
e
Im
a
g
e
A
n
a
l
y
si
s
Us
in
g
De
e
p
L
e
a
rn
in
g
Tec
h
n
iq
u
e
s,"
2
0
1
7
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Rec
e
n
t
Ad
v
a
n
c
e
s
in
El
e
c
tro
n
ics
a
n
d
Co
mm
u
n
ica
ti
o
n
T
e
c
h
n
o
l
o
g
y
(
ICR
AE
CT
)
,
Ba
n
g
a
lo
re
,
p
p
.
1
9
1
-
1
9
5
,
2
0
1
7
.
[1
0
]
Ro
y
,
S
u
d
ip
ta,
e
t
a
l.
"
A
n
i
m
p
ro
v
e
d
b
ra
in
M
R
im
a
g
e
b
in
a
riza
ti
o
n
m
e
th
o
d
a
s
a
p
re
p
ro
c
e
ss
in
g
fo
r
a
b
n
o
rm
a
li
t
y
d
e
tec
ti
o
n
a
n
d
f
e
a
tu
re
s e
x
trac
ti
o
n
,
"
Fro
n
ti
e
rs
o
f
C
o
mp
u
ter
S
c
ien
c
e
1
1
.
4
S
p
rin
g
e
r
,
7
1
7
-
7
2
7
,
2
0
1
7
.
[1
1
]
A
.
M
i
n
a
n
d
Z.
M
.
Ky
u
,
"
M
RI
I
m
a
g
e
s
En
h
a
n
c
e
m
e
n
t
a
n
d
T
u
m
o
r
S
e
g
m
e
n
t
a
t
i
o
n
f
o
r
B
ra
i
n
,
"
2
0
1
7
1
8
t
h
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
P
a
r
a
ll
e
l
a
n
d
Di
str
ib
u
te
d
C
o
m
p
u
ti
n
g
,
A
p
p
l
ic
a
t
i
o
n
s
a
n
d
T
e
c
h
n
o
l
o
g
ies
(
PD
CA
T
)
,
T
a
i
p
e
i,
p
p
.
2
7
0
-
275
,
2017
.
[1
2
]
V.
A
lex
,
K
.
V
a
i
d
h
y
a
,
S
.
T
h
i
r
u
n
a
v
u
k
k
a
ra
s
u
,
C
.
Ke
sa
v
a
d
a
s
&
G
.
Kris
h
n
a
m
u
r
t
h
i,
“
S
e
m
is
u
p
e
rv
i
se
d
lea
r
n
i
n
g
u
si
n
g
d
e
n
o
i
si
n
g
a
u
t
o
e
n
c
o
d
e
rs f
o
r
b
ra
i
n
l
e
si
o
n
d
e
tec
ti
o
n
a
n
d
se
g
m
e
n
ta
ti
o
n
,”
J
o
u
r
n
a
l
o
f
M
e
d
i
c
a
l
Im
a
g
i
n
g
,
Vo
l.
4
(
4
)
,
0
4
1
3
1
1
,
2017
.
[1
3
]
A
.
Ort
iz
,
A
.
A
.
P
a
l
a
c
i
o
,
J
.
M
.
G
ó
r
riz
,
J
.
R
a
m
írez
,
a
n
d
D
.
S
-
G
o
n
z
á
le
z
,
“
R
e
se
a
rc
h
A
rt
icle
S
e
g
m
e
n
ta
ti
o
n
o
f
Br
a
i
n
M
R
I
Us
i
n
g
S
O
M
-
F
CM
-
Ba
s
e
d
M
e
t
h
o
d
a
n
d
3
D
S
ta
ti
s
t
ica
l
De
s
c
r
i
p
t
o
r
s
,
”
Hi
n
d
a
w
i
P
u
b
l
is
h
i
n
g
C
o
r
p
o
r
a
ti
o
n
Co
mp
u
t
a
t
i
o
n
a
l
and
M
a
t
h
e
m
a
ti
c
a
l
M
e
t
h
o
d
s
i
n
M
e
d
i
c
i
n
e
,
p
p
.
1
2
,
2
0
1
3
.
[1
4
]
S
.
A
b
b
a
si
a
n
d
F
.
T
a
jer
i
P
o
u
r,
"
A
h
y
b
r
i
d
a
p
p
ro
a
c
h
f
o
r
d
e
t
e
c
t
i
o
n
o
f
b
r
a
i
n
t
u
m
o
r
i
n
M
R
I
im
a
g
e
s
,"
2
0
1
4
2
1
t
h
I
ra
n
i
a
n
Co
n
f
e
re
n
c
e
o
n
B
i
o
m
e
d
ic
a
l
E
n
g
i
n
e
e
ri
n
g
(
ICB
M
E)
,
T
e
h
r
a
n
,
2
0
1
4
,
p
p
.
2
6
9
-
2
7
4
.
[1
5
]
S
.
G
u
p
ta a
n
d
R
.
P
o
rw
a
l
,
“
Re
se
a
rc
h
A
r
ti
c
le
A
p
p
r
o
p
r
ia
te
C
o
n
tr
a
st
E
n
h
a
n
c
e
m
e
n
t
M
e
a
su
re
s
f
o
r
B
ra
in
a
n
d
Bre
a
st
Ca
n
c
e
r
Im
a
g
e
s
,
”
Hi
n
d
a
w
i
P
u
b
li
s
h
i
n
g
C
o
r
p
o
r
a
ti
o
n
I
n
ter
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Bi
o
me
d
ic
a
l
Im
a
g
i
n
g
,
p
p
.
8
,
2
0
1
6
[1
6
]
B.
H.
M
e
n
z
e
e
t
a
l
.
,
"
T
h
e
M
u
lt
im
o
d
a
l
B
ra
i
n
T
u
m
o
r
Im
a
g
e
S
e
g
m
e
n
t
a
t
i
o
n
B
e
n
c
h
m
a
rk
(B
R
A
T
S
),
"
in
IE
EE
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
4
,
n
o
.
1
0
,
p
p
.
1
9
9
3
-
2
0
2
4
,
O
c
t.
2
0
1
5
.
[1
7
]
N.
B
.
Ba
h
a
d
u
re
,
A
.
K
.
Ra
y
a
n
d
H.
P
.
T
h
e
t
h
i
,
“
Re
s
e
a
rc
h
A
rt
icl
e
Im
a
g
e
A
n
a
ly
sis
f
o
r
M
R
I
Ba
s
e
d
B
ra
i
n
T
u
m
o
r
De
tec
ti
o
n
a
n
d
F
e
a
t
u
re
Ex
t
ra
c
t
i
o
n
Us
i
n
g
Bi
o
l
o
g
ica
ll
y
In
sp
i
re
d
BW
T
a
n
d
S
VM
,
”
H
i
n
d
a
wi
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Bi
o
me
d
ic
a
l
Im
a
g
i
n
g
,
p
p
.
1
2
,
2
0
1
7
.
[1
8
]
P
.
D
h
a
g
e
,
M
.
R.
P
h
e
g
a
d
e
a
n
d
S
.
K
.
S
h
a
h
,
"
W
a
ter
s
h
e
d
s
e
g
me
n
t
a
ti
o
n
b
r
a
i
n
t
u
mo
r
d
e
t
e
c
t
i
o
n
,"
2
0
1
5
I
n
te
rn
a
t
i
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
P
e
rv
a
s
iv
e
C
o
m
p
u
t
i
n
g
(I
C
P
C)
,
P
u
n
e
,
p
p
.
1
-
5
,
2
0
1
5
.
[1
9
]
A
.
F
a
isa
l,
S
.
P
a
rv
e
e
n
,
S
.
Ba
d
s
h
a
a
n
d
H.
S
a
rw
a
r
,
"
A
n
Im
p
ro
v
e
d
I
m
a
g
e
De
n
o
isi
n
g
a
n
d
S
e
g
m
e
n
tat
i
o
n
A
p
p
r
o
a
c
h
f
o
r
De
tec
ti
n
g
T
u
m
o
r
f
r
o
m
2
-
D
M
R
I
Bra
i
n
Im
a
g
e
s,"
2
0
1
2
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
A
d
v
a
n
c
e
d
C
o
mp
u
ter
S
c
ie
n
c
e
A
p
p
l
ic
a
t
i
o
n
s
a
n
d
T
e
c
h
n
o
l
o
g
ies
(
A
CS
A
T
)
,
K
u
a
la
L
u
m
p
u
r
,
p
p
.
4
5
2
-
457
,
2
0
1
2
.
[2
0
]
S
.
L
.
J
u
i
e
t
a
l
.
,
"
Bra
i
n
M
R
I
T
u
m
o
r
S
e
g
m
e
n
ta
ti
o
n
w
it
h
3
D
I
n
tra
c
ra
n
ia
l
S
t
r
u
c
tu
re
De
f
o
rm
a
t
i
o
n
F
e
a
t
u
re
s
,
"
i
n
IE
E
E
In
te
ll
i
g
e
n
t
S
y
s
tem
s
,
v
o
l
.
3
1
,
n
o
.
2
,
p
p
.
6
6
-
7
6
,
M
a
r
.
-
A
p
r.
2
0
1
6
.
[2
1
]
H.
Ka
u
r
a
n
d
J.
R
a
n
i
,
"
M
RI
b
r
a
i
n
im
a
g
e
e
n
h
a
n
c
e
me
n
t
u
s
i
n
g
His
t
o
g
ra
m
E
q
u
a
l
iz
a
t
i
o
n
tec
h
n
iq
u
e
s,
"
2
0
1
6
I
n
t
e
r
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
W
ir
e
le
ss
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
S
ig
n
a
l
P
r
o
c
e
s
si
n
g
a
n
d
Ne
tw
o
rk
i
n
g
(W
iS
P
N
ET
)
,
C
h
e
n
n
a
i,
p
p
.
7
7
0
-
773
,
2016
.
[2
2
]
Y.
M
e
g
e
rsa
a
n
d
G
.
A
lem
u
,
"
B
ra
i
n
tu
m
o
r
d
e
tec
t
io
n
a
n
d
se
g
m
e
n
ta
ti
o
n
u
si
n
g
h
y
b
r
i
d
i
n
tel
l
ig
e
n
t
a
lg
o
ri
t
h
m
s,"
A
FR
ICO
N
2015
,
A
d
d
is
A
b
a
b
a
,
p
p
.
1
-
8
,
2
0
1
5
.
[2
3
]
P
a
rv
e
e
n
a
n
d
A
.
S
in
g
h
,
"
D
e
tec
ti
o
n
o
f
b
r
a
i
n
tu
m
o
r
i
n
M
RI
im
a
g
e
s
,
u
s
i
n
g
c
o
m
b
i
n
a
t
i
o
n
o
f
fu
zz
y
c
-
me
a
n
s
a
n
d
S
VM
,
"
2
0
1
5
2
n
d
I
n
ter
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
ig
n
a
l
P
ro
c
e
ss
i
n
g
a
n
d
I
n
teg
ra
te
d
Ne
tw
o
rk
s
(S
P
I
N)
,
N
o
i
d
a
,
p
p
.
9
8
-
102
,
2015
.
[2
4
]
S
.
P
e
re
ira
,
A
.
P
i
n
t
o
,
V.
A
lv
e
s
a
n
d
C.
A
.
S
i
lv
a
,
"
Bra
i
n
T
u
m
o
r
S
e
g
m
e
n
tat
i
o
n
Us
i
n
g
Co
n
v
o
l
u
t
i
o
n
a
l
Ne
u
ra
l
Ne
tw
o
rk
s i
n
M
R
I
Im
a
g
e
s,"
i
n
IE
E
E
T
r
a
n
s
a
c
t
io
n
s
o
n
M
e
d
ic
a
l
Im
a
g
i
n
g
,
v
o
l.
3
5
,
n
o
.
5
,
p
p
.
1
2
4
0
-
1
2
5
1
,
M
a
y
2
0
1
6
.
[2
5
]
C.
H
.
Ra
o
,
P
.
V.
Na
g
a
n
ja
n
e
y
u
l
u
a
n
d
K
.
S
.
P
ra
sa
d
,
"
B
ra
i
n
T
u
m
o
r
De
tec
ti
o
n
a
n
d
S
e
g
m
e
n
ta
ti
o
n
U
si
n
g
C
o
n
d
it
i
o
n
a
l
Ra
n
d
o
m
F
ie
l
d
,
"
2
0
1
7
IE
E
E
7
t
h
In
ter
n
a
ti
o
n
a
l
A
d
v
a
n
c
e
C
o
m
p
u
ti
n
g
C
o
n
f
e
re
n
c
e
(
IA
CC)
,
Hy
d
e
r
a
b
a
d
,
p
p
.
8
0
7
-
8
1
0
,
2017
.
[2
6
]
N.
S
e
n
t
h
il
k
u
m
a
ra
n
a
n
d
J
.
T
h
i
m
m
iara
ja
,
"
H
ist
o
g
ra
m
E
q
u
a
l
iza
t
io
n
f
o
r
Im
a
g
e
E
n
h
a
n
c
e
m
e
n
t
U
si
n
g
M
RI
Bra
i
n
Im
a
g
e
s,"
2
0
1
4
W
o
r
l
d
C
o
n
g
re
s
s
o
n
C
o
m
p
u
ti
n
g
a
n
d
C
o
mm
u
n
ic
a
ti
o
n
T
e
c
h
n
o
l
o
g
ie
s
,
T
r
ic
h
i
ra
p
p
a
l
l
i,
p
p
.
8
0
-
83
,
2
0
1
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t
201
9
:
2
4
1
6
-
2424
2424
[2
7
]
Y.
S
h
a
rm
a
a
n
d
Y
.
K.
M
e
g
h
r
a
ja
n
i
,
"
B
ra
i
n
t
u
m
o
r
e
x
t
ra
c
ti
o
n
f
r
o
m
M
RI
im
a
g
e
u
s
i
n
g
m
a
th
e
m
a
ti
c
a
l
m
o
rp
h
o
l
o
g
ica
l
re
c
o
n
st
r
u
c
t
i
o
n
,
"
2
0
1
4
2
n
d
I
n
ter
n
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Eme
r
g
i
n
g
T
e
c
h
n
o
lo
g
y
T
re
n
d
s in
E
lec
tr
o
n
ic
s,
Co
mm
u
n
ic
a
ti
o
n
a
n
d
Ne
tw
o
rk
i
n
g
,
S
u
ra
t,
p
p
.
1
-
4
,
2
0
1
4
.
[2
8
]
S
.
N
.
S
u
la
im
a
n
,
S
.
M
.
C
.
Is
h
a
k
,
I
.
S
.
Is
a
a
n
d
N.
Ha
m
z
a
h
,
"
De
-
n
o
isi
n
g
o
f
n
o
isy
M
R
I
b
r
a
i
n
im
a
g
e
u
si
n
g
t
h
e
sw
it
c
h
i
n
g
-
b
a
se
d
c
l
u
ste
ri
n
g
a
lg
o
r
i
th
m
,
"
2
0
1
4
IE
E
E
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
C
o
n
tr
o
l
S
y
s
tem
,
C
o
m
p
u
t
i
n
g
a
n
d
E
n
g
i
n
e
e
ri
n
g
(
ICC
S
C
E
2
0
1
4
)
,
Ba
t
u
F
e
rr
i
n
g
h
i
,
p
p
.
1
-
6
,
2
0
1
4
.
[2
9
]
K.
Xia
o
,
A
.
E
.
Ha
ss
a
n
i
e
n
,
Y.
S
u
n
a
n
d
E
.
K
.
K
.
Ng
,
"
B
ra
i
n
M
R
im
a
g
e
t
u
m
o
r
s
e
g
m
e
n
ta
ti
o
n
w
it
h
v
e
n
tr
ic
u
la
r
d
e
f
o
rm
a
ti
o
n
,
"
2
0
1
1
I
EE
E
7
t
h
I
n
t
e
rn
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
I
n
te
ll
i
g
e
n
t
C
o
m
p
u
te
r
Co
mm
u
n
i
c
a
t
i
o
n
a
n
d
Pr
o
c
e
ss
i
n
g
,
Cl
u
j
-
Na
p
o
c
a
,
2
0
1
1
,
p
p
.
2
1
3
-
2
1
7
.
[3
0
]
V.
Z
e
l
jk
o
v
ic
e
t
a
l
.
,
"
A
u
to
m
a
t
ic
b
r
a
i
n
t
u
m
o
r
d
e
tec
ti
o
n
a
n
d
se
g
m
e
n
ta
ti
o
n
i
n
M
R
im
a
g
e
s,"
2
0
1
4
P
a
n
A
me
ric
a
n
He
a
lt
h
Ca
re
Exc
h
a
n
g
e
s
(
PA
HC
E)
,
Bra
si
l
ia,
p
p
.
1
-
1
,
2
0
1
4
.
[3
1
]
Ha
m
ian
e
,
M
a
d
in
a
,
a
n
d
F
a
tem
a
S
a
e
e
d
.
"
S
V
M
Clas
sif
ica
ti
o
n
o
f
M
RI
Bra
in
Im
a
g
e
s
f
o
r
Co
m
p
u
ter
-
A
ss
isted
Dia
g
n
o
sis."
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
i
n
e
e
rin
g
(
IJ
ECE
)
7
,
n
o
.
5
,
2
5
5
5
-
2
5
6
4
,
2
0
1
7
.
[3
2
]
Ju
n
g
,
S
e
-
Ho
o
n
,
Jo
n
g
-
Ch
a
n
Kim
,
a
n
d
Ch
u
n
-
Bo
S
im
.
"
P
re
d
ictio
n
d
a
ta
p
ro
c
e
ss
in
g
sc
h
e
m
e
u
sin
g
a
n
a
rti
f
ici
a
l
n
e
u
ra
l
n
e
tw
o
rk
a
n
d
d
a
ta
c
lu
ste
ri
n
g
f
o
r
Big
Da
ta."
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
ter
E
n
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
6
,
n
o
.
1
,
3
3
0
-
3
3
6
,
2
0
1
6
.
[3
3
]
Hu
ss
e
in
A
tt
y
a
L
a
f
ta,
Zain
a
b
F
a
lah
Ha
sa
n
,
No
o
r
Ka
d
h
im
Ay
o
o
b
,
“
T
h
e
c
las
si
f
ica
ti
o
n
o
f
m
e
d
ica
l
d
a
ta
se
ts
u
sin
g
b
a
c
k
p
ro
p
a
g
a
ti
o
n
n
e
u
ra
l
n
e
tw
o
rk
p
o
w
e
re
d
b
y
g
e
n
e
ti
c
-
b
a
se
d
f
e
a
tu
re
s
e
lec
to
r
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
ter
E
n
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
9
,
n
o
.
2
,
2
0
1
7
.
[3
4
]
G
o
rg
o
lew
sk
i
,
K.
J.
,
W
h
e
e
le
r,
K
.
,
e
t
a
l
.
,
“
T
h
e
im
p
a
c
t
o
f
sh
a
re
d
d
a
t
a
in
n
e
u
ro
im
a
g
i
n
g
:
t
h
e
c
a
se
o
f
Op
e
n
f
M
RI
.
o
rg
.
”
2
0
1
5
.
A
v
a
il
a
b
le
a
t:
h
t
t
p
:
/
/d
x
.
d
o
i
.
o
rg
/
1
0
.
7
4
9
0
/f
1
0
0
0
re
se
a
rc
h
.
1
1
1
0
0
4
0
.
1
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
H
a
r
is
h
S
.
,
I
h
a
v
e
c
o
m
p
lete
d
B.
E.
in
T
e
lec
o
m
m
u
n
ica
ti
o
n
En
g
in
e
e
r
in
g
f
ro
m
Ba
n
g
a
lo
re
Un
iv
e
rsit
y
,
a
n
d
M
.
T
e
c
h
in
In
f
o
rm
a
ti
o
n
&
Co
m
m
u
n
ica
ti
o
n
S
y
ste
m
s
f
ro
m
V
isv
e
sv
a
r
a
y
a
Tec
h
n
o
lo
g
ica
l
Un
iv
e
rsit
y
.
P
u
rs
u
in
g
P
h
.
D
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
f
ro
m
V
isv
e
s
v
a
ra
y
a
Tec
h
n
o
lo
g
ica
l
Un
iv
e
rsity
.
I
a
m
h
a
v
in
g
1
3
y
e
a
rs
o
f
t
e
a
c
h
in
g
e
x
p
e
rien
c
e
.
M
y
a
re
a
o
f
r
e
se
a
rc
h
is
Bio
-
m
e
d
ica
l
I
m
a
g
e
P
r
o
c
e
ss
in
g
.
G.
F.
Ali
A
h
a
m
m
e
d
w
o
rk
in
g
a
s
a
n
A
ss
o
c
iat
e
P
ro
f
e
ss
o
r
&
HO
D
in
th
e
De
p
a
rt
m
e
n
t
o
f
Di
g
it
a
l
El
e
c
tro
n
ics
&
Co
m
m
u
n
ica
ti
o
n
sy
ste
m
s
a
t
V
T
U
P
G
c
e
n
tre,
M
y
s
u
ru
.
He
is
h
a
v
in
g
1
5
y
e
a
rs
o
f
T
e
a
c
h
in
g
a
n
d
Re
se
a
rc
h
Ex
p
e
rien
c
e
.
He
p
u
rsu
e
d
P
h
.
D.,
Co
m
p
u
ter
S
c
ien
c
e
&
T
e
c
h
n
o
lo
g
y
,
f
ro
m
S
ri
Krish
n
a
De
v
a
ra
y
a
Un
iv
e
rsit
y
,
An
a
n
tap
u
r,
A
n
d
ra
P
ra
d
e
sh
.
M
a
ste
r
o
f
T
e
c
h
n
o
l
o
g
y
,
Ne
t
w
o
rk
in
g
&
I
n
tern
e
t
E
n
g
in
e
e
rin
g
,
f
ro
m
V
isv
e
s
v
a
ra
y
a
T
e
c
h
n
o
lo
g
ica
l
Un
iv
e
rsit
y
,
Be
lag
a
v
i,
Ba
c
h
e
lo
r
o
f
En
g
in
e
e
rin
g
i
n
El
e
c
tro
n
ics
&
C
o
m
m
u
n
ica
ti
o
n
En
g
in
e
e
ri
n
g
,
f
ro
m
Ba
n
g
a
lo
re
Un
iv
e
rsity
,
Ba
n
g
a
lo
re
.
He
w
o
rk
e
d
a
s
BOE
m
e
m
b
e
r
f
o
r
V
isv
e
sv
a
ra
y
a
T
e
c
h
n
o
l
o
g
ica
l
Un
iv
e
rsit
y
,
Be
lag
a
v
i
.
He
is
a
lso
BOE
m
e
m
b
e
r
f
o
r
S
JCE
M
y
so
re
&
NI
E
M
y
so
re
,
A
u
to
n
o
m
o
u
s
Co
ll
e
g
e
s.
He
is
BOS
m
e
m
b
e
r
f
o
r
NIE
A
u
to
n
o
m
o
u
s
c
o
ll
e
g
e
.
He
is
L
o
c
a
l
In
sp
e
c
ti
o
n
C
o
m
m
it
tee
(L
IC)
m
e
m
b
e
r
f
o
r
V
T
U,
Be
lag
a
v
i.
He
h
a
s
p
u
b
li
sh
e
d
se
v
e
ra
l
Re
se
a
rc
h
p
a
p
e
rs
in
In
ter
n
a
ti
o
n
a
l,
Na
ti
o
n
a
l
J
o
u
r
n
a
ls/co
n
f
e
re
n
c
e
s.
He
is
a
M
e
m
b
e
r
o
f
CS
I,
I
A
EN
G
,
IBM
Ac
a
d
e
m
ic
In
it
iativ
e
,
a
n
d
L
M
IS
T
E.
Dr.
G
.
F
.
A
li
A
h
a
m
m
e
d
a
re
a
o
f
in
tere
st
a
n
d
re
se
a
rc
h
in
c
lu
d
e
Ne
tw
o
rk
in
g
,
P
e
rf
o
r
m
a
n
c
e
e
n
h
a
n
c
e
m
e
n
t
a
lg
o
rit
h
m
s,
Clo
u
d
Co
m
p
u
ti
n
g
,
c
ry
p
to
g
ra
p
h
y
a
n
d
Co
m
m
u
n
ica
ti
o
n
.
He
h
a
s
th
e
Re
c
ip
ien
t
o
f
S
e
e
d
m
o
n
e
y
Yo
u
n
g
S
c
ien
ti
st
Re
se
a
rc
h
Aw
a
rd
(S
M
YSR)
f
ro
m
V
isio
n
G
ro
u
p
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
(V
G
S
T
),
Ba
n
g
a
lo
re
.
He
is also
f
e
tch
e
d
v
a
rio
u
s
G
ra
n
ts f
ro
m
V
G
S
T
&
A
IC
T
E
.
Evaluation Warning : The document was created with Spire.PDF for Python.