T
E
L
K
O
M
N
I
K
A
T
elec
o
m
m
un
ica
t
io
n,
Co
m
pu
t
ing
,
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
19
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
1
,
p
p
.
6
3
~7
2
I
SS
N:
1
6
9
3
-
6
9
3
0
,
ac
cr
ed
ited
First Gr
ad
e
b
y
Kem
en
r
is
tek
d
i
k
ti,
Dec
r
ee
No
: 2
1
/E/KPT
/2
0
1
8
DOI
: 1
0
.
1
2
9
2
8
/TE
L
KOM
NI
K
A.
v
1
9
i1
.
1
5
1
4
2
63
J
o
ur
na
l
ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
Co
ro
na
l slice seg
menta
tion usin
g
a
watershed
met
ho
d f
o
r early
identif
i
ca
tion o
f
p
eo
ple wit
h
Alz
hei
mer's
Ret
no
Su
priy
a
nti
1
,
Anug
er
a
h K
ev
in M
a
rc
hel
2
,
Yo
g
i R
a
m
a
dh
a
ni
3
,
H
a
ris
B
udi
Wi
do
do
4
1
,
2,
3
El
e
c
tri
c
a
l
E
n
g
i
n
e
e
rin
g
De
p
a
rt
m
e
n
t
,
Je
n
d
e
ra
l
S
o
e
d
irma
n
Un
iv
e
r
sity
,
P
u
rwo
k
e
rto
,
In
d
o
n
e
sia
4
M
e
d
ica
l
F
a
c
u
lt
y
,
Je
n
d
e
ra
l
S
o
e
d
ir
m
a
n
Un
iv
e
rsity
,
P
u
rwo
k
e
rto
,
I
n
d
o
n
e
sia
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
2
,
2
0
2
0
R
ev
is
ed
Ma
y
4
,
2
0
2
0
Acc
ep
ted
Sep
5
,
2
0
2
0
On
e
p
h
y
sic
a
l
sig
n
o
f
a
p
e
rso
n
w
h
o
h
a
s
Alz
h
e
ime
r'
s
is
th
e
d
imin
u
ti
o
n
o
f
t
h
e
a
re
a
o
f
th
e
h
ip
p
o
c
a
m
p
u
s
a
n
d
v
e
n
tri
c
les
.
A
g
o
o
d
q
u
a
li
ty
m
a
g
n
e
ti
c
re
so
n
a
n
c
e
ima
g
in
g
(
M
RI
)
wil
l
p
r
o
v
i
d
e
a
h
ig
h
-
q
u
a
li
ty
ima
g
e
so
t
h
a
t
th
e
d
o
c
to
r
wil
l
q
u
ick
ly
a
n
a
ly
z
e
t
h
e
a
b
n
o
rm
a
li
ti
e
s
o
f
t
h
e
h
ip
p
o
c
a
m
p
u
s
a
n
d
v
e
n
tri
c
le
a
re
a
.
Ho
we
v
e
r,
fo
r
lo
w
-
q
u
a
li
t
y
M
RI,
t
h
is
is d
iffi
c
u
l
t
t
o
d
o
.
Th
is
c
o
n
d
it
i
o
n
wi
ll
b
e
a
sig
n
ifi
c
a
n
t
p
r
o
b
lem
f
o
r
so
m
e
r
e
g
io
n
s
in
d
e
v
e
l
o
p
i
n
g
c
o
u
n
tri
e
s
in
c
lu
d
i
n
g
In
d
o
n
e
sia
,
wh
e
re
m
a
n
y
h
o
sp
it
a
l
s
h
a
v
e
o
n
ly
lo
w
-
q
u
a
li
t
y
M
RI
,
a
n
d
m
a
n
y
h
o
sp
i
tals
d
o
n
o
t
h
a
v
e
th
e
m
a
t
a
ll
.
Th
e
p
rima
ry
p
u
r
p
o
se
o
f
th
is
re
s
e
a
rc
h
is
to
d
e
v
e
lo
p
sim
p
le
to
o
ls
to
a
n
a
ly
z
e
m
o
rp
h
o
lo
g
ica
l
c
h
a
ra
c
teristics
in
Alz
h
e
ime
r'
s
p
a
ti
e
n
t
s.
I
n
t
h
is
p
a
p
e
r,
we
fo
c
u
s
o
n
l
y
o
n
c
o
r
o
n
a
l
sl
ice
a
n
a
ly
sis.
We
will
u
se
wa
ters
h
e
d
m
e
th
o
d
se
g
m
e
n
tatio
n
,
b
e
c
a
u
se
o
f
t
h
is
m
e
th
o
d
a
b
le
t
o
se
g
m
e
n
t
t
h
e
b
o
u
n
d
a
ries
a
u
to
m
a
ti
c
a
ll
y
,
s
o
th
a
t
p
a
rts
o
f
t
h
e
h
ip
p
o
c
a
m
p
u
s
a
n
d
v
e
n
tri
c
les
c
a
n
b
e
id
e
n
ti
f
ied
i
n
a
n
M
RI
ima
g
e
.
An
a
ly
sis
o
f
m
o
r
p
h
o
lo
g
ica
l
c
h
a
ra
c
teristics
is
a
lso
c
las
sified
b
y
a
g
e
a
n
d
g
e
n
d
e
r.
Th
e
n
b
y
re
fe
rrin
g
to
t
h
e
v
a
lu
e
o
f
t
h
e
c
li
n
ica
l
d
e
m
e
n
ti
a
ra
ti
n
g
(CDR),
th
e
p
r
o
c
e
ss
o
f
id
e
n
ti
fy
i
n
g
b
e
twe
e
n
ima
g
e
s
with
Alz
h
e
ime
r'
s
d
ise
a
s
e
(AD
)
a
n
d
h
e
a
lt
h
y
m
o
d
e
ls
is
d
o
n
e
b
a
se
d
o
n
th
e
m
o
rp
h
o
lo
g
ica
l
a
n
a
ly
sis
t
h
a
t
h
a
s
b
e
e
n
d
o
n
e
.
Th
e
re
su
lt
s
s
h
o
w
t
h
is
m
e
th
o
d
h
a
s
a
b
e
tt
e
r
p
e
rfo
rm
a
n
c
e
c
o
m
p
a
re
d
t
o
th
e
p
re
v
io
u
sly
w
o
rk
.
K
ey
w
o
r
d
s
:
Alzh
eim
er
C
lin
ical
d
em
en
tia
r
atin
g
Hip
p
o
ca
m
p
u
s
Ven
tr
icle
W
ater
s
h
ed
s
eg
m
en
tatio
n
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r
th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
R
etn
o
Su
p
r
iy
an
ti
Dep
ar
tm
en
t o
f
E
lectr
ical
E
n
g
i
n
ee
r
in
g
J
en
d
er
al
So
ed
ir
m
an
Un
iv
er
s
ity
Kam
p
u
s
B
later
,
Ma
y
jen
d
Su
n
g
k
o
n
o
St.
KM
5
,
B
later
,
Pu
r
b
a
lin
g
g
a
5
3
1
2
5
,
J
awa
T
en
g
a
h
,
I
n
d
o
n
esia
E
m
ail:
r
etn
o
_
s
u
p
r
iy
an
ti@
u
n
s
o
ed
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
Alzh
eim
er
'
s
d
is
ea
s
e
(
AD)
is
a
co
n
d
itio
n
th
at
is
ch
a
r
ac
ter
ized
b
y
a
d
ec
r
e
ase
in
m
em
o
r
y
,
d
ec
r
ea
s
ed
th
e
ab
ilit
y
to
th
in
k
an
d
s
p
ea
k
,
an
d
ch
an
g
es
in
b
eh
av
i
o
r
in
p
atien
t
s
d
u
e
to
d
is
o
r
d
er
s
in
th
e
b
r
ain
t
h
at
ar
e
p
r
o
g
r
ess
iv
e
o
r
s
lo
wly
(
AD)
[
1
]
.
C
u
r
r
en
tly
,
th
is
d
is
ea
s
e
is
o
n
e
o
f
th
e
m
o
s
t
f
ea
r
ed
d
is
ea
s
es,
b
ec
au
s
e
th
is
d
is
ea
s
e
is
a
m
ajo
r
d
is
aster
th
at
o
cc
u
r
s
in
p
atien
t
s
an
d
th
eir
f
am
ilies
,
wh
er
e
th
e
ex
p
er
ien
ce
o
f
p
atien
ts
wh
o
ex
p
er
ien
ce
it
is
an
en
d
less
en
d
u
n
til
d
ea
th
ar
r
iv
es.
AD
d
iag
n
o
s
is
ca
n
b
e
m
ad
e
b
y
k
n
o
win
g
o
th
er
f
o
r
m
s
o
f
d
em
en
tia,
b
u
t
th
e
d
eter
m
in
atio
n
ca
n
o
n
ly
b
e
m
a
d
e
af
ter
p
o
s
t
-
m
o
r
tem
s
tu
d
ies
o
f
b
r
ain
tis
s
u
e.
T
h
is
p
o
s
t
-
m
o
r
te
m
s
tu
d
y
ca
n
b
e
d
o
n
e
u
s
in
g
m
ag
n
etic
r
eso
n
an
ce
i
m
ag
in
g
(
MRI
)
.
MRI
ex
am
i
n
atio
n
aim
s
to
d
eter
m
in
e
t
h
e
m
o
r
p
h
o
l
o
g
ical
ch
ar
ac
ter
is
tics
(
lo
ca
tio
n
,
s
ize,
s
h
ap
e,
ex
ten
s
i
o
n
,
an
d
o
th
er
s
o
f
p
ath
o
lo
g
ical
co
n
d
itio
n
s
)
.
T
h
ese
o
b
jectiv
es
ca
n
b
e
o
b
tain
e
d
b
y
ass
ess
in
g
o
n
e
o
r
a
co
m
b
i
n
atio
n
o
f
a
x
ial,
s
ag
ittal,
co
r
o
n
al
o
r
o
b
liq
u
e
cr
o
s
s
-
s
ec
tio
n
al
im
ag
es
d
ep
en
d
i
n
g
o
n
t
h
e
lo
ca
tio
n
o
f
th
e
o
r
g
a
n
an
d
p
o
s
s
ib
le
p
ath
o
lo
g
y
.
I
m
a
g
e
p
r
o
ce
s
s
in
g
is
a
p
r
o
c
ess
o
f
p
r
o
ce
s
s
in
g
an
im
ag
e
an
aly
s
is
th
at
ai
m
s
to
im
p
r
o
v
e
th
e
q
u
ality
o
f
th
e
im
a
g
e
s
o
ca
n
b
e
in
ter
p
r
eted
b
y
h
u
m
an
s
o
r
m
ac
h
in
es (
in
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
19
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
1
:
6
3
-
72
64
th
is
ca
s
e
co
m
p
u
ter
s
)
ea
s
ily
[
2
]
.
C
u
r
r
en
tly
,
m
an
y
im
ag
e
p
r
o
ce
s
s
in
g
ap
p
licatio
n
s
ar
e
also
wid
e
ly
ap
p
lied
in
m
a
n
y
way
s
,
o
n
e
o
f
wh
ich
is
th
e
f
ield
o
f
m
ed
ical
im
a
g
in
g
.
C
lin
ical
d
em
en
tia
r
atin
g
(
C
D
R
)
is
a
n
u
m
er
ical
s
ca
le
u
s
ed
to
m
ea
s
u
r
e
th
e
s
ev
er
ity
o
f
s
y
m
p
to
m
s
o
f
d
em
en
tia
b
ased
o
n
th
e
s
tag
e.
C
D
R
u
s
es
s
ix
co
g
n
itiv
e
an
d
f
u
n
ctio
n
al
d
o
m
ain
s
o
f
p
er
f
o
r
m
an
ce
to
id
en
tify
p
o
s
s
ib
le
co
g
n
it
iv
e
im
p
ai
r
m
en
t
s
,
n
am
ely
:
m
em
o
r
y
,
o
r
ien
tatio
n
,
ass
ess
m
en
t
an
d
p
r
o
b
lem
s
o
lv
in
g
,
c
o
m
m
u
n
ity
n
ee
d
s
,
h
o
m
e
&
h
o
b
b
ies
,
an
d
p
er
s
o
n
al
ca
r
e.
T
h
e
r
e
ar
e
5
lev
el
s
o
f
d
em
en
tia
b
ased
o
n
t
h
e
C
DR
v
alu
es,
n
am
ely
:
0
(
n
o
r
m
al
)
,
0
.
5
(
v
e
r
y
m
ild
d
e
m
en
tia)
,
1
(
m
ild
d
em
en
tia)
,
2
(
mo
d
er
ate
d
em
en
tia)
,
3
(
s
ev
er
e
d
em
en
tia)
[
3
]
.
At
p
r
esen
t,
th
e
s
ev
er
ity
o
f
Alzh
ei
m
er
'
s
r
ef
er
s
to
th
e
u
s
e
o
f
th
e
C
DR
s
ca
le,
s
o
th
at
a
p
er
s
o
n
ca
n
b
e
tr
ea
ted
ac
co
r
d
i
n
g
to
th
e
s
ev
er
ity
.
C
u
r
r
en
tly
,
m
u
ch
r
esear
ch
is
d
is
cu
s
s
in
g
MRI
im
ag
e
an
aly
s
is
ab
o
u
t
th
e
id
en
tific
atio
n
o
f
Al
zh
eim
er
'
s
.
Z
u
b
al
[
4
]
in
h
is
r
esear
ch
d
ev
e
lo
p
ed
d
u
p
licatio
n
o
f
1
2
3
^
I
-
P
-
C
I
T
s
tr
iatal
V3
"in
th
e
ca
s
e
s
tu
d
y
o
f
Par
k
in
s
o
n
'
s
d
is
ea
s
e
an
d
ap
p
lied
it
to
im
ag
e
p
r
o
ce
s
s
in
g
tech
n
o
lo
g
y
.
Yu
[
5
]
p
r
o
p
o
s
ed
a
m
eth
o
d
o
f
im
a
g
e
q
u
ality
a
n
aly
s
is
ap
p
r
o
ac
h
th
at
is
m
o
d
eled
as
a
f
ea
tu
r
e
e
x
tr
ac
tio
n
e
x
p
r
ess
ed
i
n
a
p
a
r
ticu
lar
s
co
r
e
v
alu
e.
I
an
n
etti
[
6
]
u
s
ed
o
f
a
p
r
o
to
co
l
th
at
co
u
l
d
b
e
u
s
ed
to
q
u
an
tify
m
ito
c
h
o
n
d
r
ia
clea
r
ly
o
n
h
u
m
a
n
s
k
in
.
Dai
[
7
]
d
ev
elo
p
ed
a
4
D
ex
tr
ac
tio
n
to
o
l
f
o
r
b
r
ai
n
an
aly
s
is
s
p
ec
if
ically
f
o
r
ad
u
lts
to
b
e
ab
le
to
an
a
ly
ze
MRI
im
ag
es.
He
u
s
es
a
d
ef
o
r
m
ab
le
ex
tr
ac
ti
o
n
alg
o
r
ith
m
.
Kala
v
at
h
i [
8
]
in
h
is
p
ap
er
,
h
e
r
e
v
iewe
d
th
e
m
eth
o
d
s
av
ailab
le
f
o
r
o
v
e
r
all
s
k
u
ll a
n
aly
s
is
.
L
an
d
au
[
9
]
I
n
h
is
r
esear
ch
,
h
e
s
tan
d
ar
d
ize
d
th
e
m
eth
o
d
o
l
o
g
y
in
th
e
u
s
e
o
f
am
y
lo
id
PET
f
o
r
Alz
h
eim
e
r
'
s
c
lin
ical
tr
ial
s
.
He
co
m
p
ar
ed
th
e
r
ete
n
tio
n
o
f
th
e
co
m
p
o
u
n
d
B
(
PiB
)
p
itt
s
b
u
r
g
h
s
u
p
er
-
r
ad
i
o
tr
ac
er
an
d
two
o
f
th
e
two
am
y
lo
id
r
ad
io
tr
ac
er
s
s
o
u
p
1
8
^
F
(
f
lo
r
b
etap
ir
an
d
f
lu
tem
etam
o
l)
u
s
in
g
two
ty
p
es
o
f
p
o
p
u
latio
n
m
o
d
els.
E
s
k
ild
s
en
[
1
0
]
h
e
p
r
o
p
o
s
ed
a
m
eth
o
d
f
o
r
p
r
ed
ictin
g
th
e
s
ev
er
ity
o
f
Alzh
eim
er
'
s
a
t
a
s
till
lo
w
lev
el
b
y
m
ea
s
u
r
in
g
co
r
t
ical
th
ick
n
ess
in
MRI
im
ag
es.
Z
h
an
g
[
1
1
]
h
e
p
r
o
p
o
s
ed
th
e
Alzh
e
im
er
'
s
d
etec
tio
n
m
eth
o
d
u
s
in
g
d
is
p
lace
m
en
t
f
ield
(
DF)
wh
ich
ca
n
class
if
y
th
e
b
r
ain
with
an
AD
an
d
h
ea
lth
y
b
r
ain
.
R
o
b
itaille
[
1
2
]
p
r
esen
ted
a
n
ew
tech
n
iq
u
e
ca
lled
STa
n
d
ar
d
izatio
n
o
f
I
n
ten
s
ity
(
ST
I
)
wh
ich
was
u
s
ed
n
o
t
o
n
ly
to
a
d
ju
s
t
th
e
h
is
to
g
r
a
m
o
f
t
h
e
in
p
u
t
im
ag
e
in
to
th
e
s
tan
d
ar
d
b
u
t
also
to
co
m
b
in
e
in
f
o
r
m
atio
n
o
n
s
p
ati
al
n
etwo
r
k
in
ten
s
ity
.
L
iu
[
1
3
]
I
n
h
is
r
esear
ch
,
h
e
p
r
o
p
o
s
ed
a
m
eth
o
d
o
f
b
r
ai
n
i
m
ag
e
s
eg
m
e
n
tatio
n
al
g
o
r
ith
m
th
at
c
o
m
b
in
es
d
ef
o
r
m
a
b
le
f
o
r
m
s
an
d
in
f
o
r
m
ativ
e
f
ea
tu
r
es.
I
ts
p
r
im
ar
y
f
u
n
ctio
n
is
to
b
e
ab
le
to
s
eg
m
en
t
with
m
o
r
e
co
n
s
id
er
ab
le
an
ato
m
ical
v
ar
iatio
n
s
.
Das
[
1
4
]
p
r
o
p
o
s
ed
a
m
eth
o
d
f
o
r
test
in
g
th
e
s
u
itab
ilit
y
o
f
h
ig
h
f
ield
in
t
en
s
ity
–
m
ag
n
etic
r
eso
n
a
n
ce
im
ag
in
g
(
HF
-
MRI
)
in
p
r
ed
ictin
g
l
o
n
g
itu
d
in
al
ch
an
g
e
s
b
y
co
m
p
a
r
in
g
m
ea
s
u
r
ed
atr
o
p
h
y
lev
els
th
r
o
u
g
h
o
u
t
t
h
e
h
ip
p
o
ca
m
p
u
s
ar
ea
u
s
in
g
u
n
b
iased
d
ef
o
r
m
atio
n
-
b
ased
m
o
r
p
h
o
m
etr
y
(
DB
M)
.
Ver
cly
tte
[
1
5
]
h
e
im
p
lem
en
te
d
co
r
tical
-
b
ased
s
u
r
f
ac
e
p
r
o
jectio
n
s
ap
p
lied
to
p
atien
ts
with
th
e
ea
r
ly
-
lev
el
AD
to
i
m
p
r
o
v
e
th
e
q
u
ality
an
d
v
is
u
aliza
tio
n
o
f
im
ag
e
d
ata.
Osad
eb
ey
[
1
6
]
p
r
o
p
o
s
ed
a
m
e
th
o
d
f
o
r
e
x
tr
ac
tin
g
im
a
g
e
f
ea
t
u
r
es
u
s
in
g
g
r
ay
s
ca
le
an
d
co
n
tr
ast
f
ea
tu
r
es.
I
m
ag
e
q
u
ality
is
esti
m
ated
b
y
m
ea
s
u
r
in
g
s
tr
u
ctu
r
al
s
im
ilar
ities
b
etwe
en
th
e
r
ig
h
t
b
in
ar
y
im
ag
e
p
air
s
.
Gr
ay
[
1
7
]
c
o
n
d
u
cted
an
an
a
ly
s
is
o
f
th
e
in
co
r
p
o
r
atio
n
o
f
cr
o
s
s
-
s
ec
tio
n
al
an
d
lo
n
g
itu
d
in
al
m
u
lti
-
r
eg
io
n
f
lu
o
r
o
d
eo
x
y
g
lu
c
o
s
e
-
p
o
s
itro
n
e
m
is
s
io
n
t
o
m
o
g
r
a
p
h
y
(
FDG
-
PET
)
in
f
o
r
m
atio
n
f
o
r
class
if
icatio
n
.
Or
tiz
[
1
8
]
p
r
o
p
o
s
ed
a
m
eth
o
d
f
o
r
s
elec
tin
g
r
eg
io
n
s
o
f
in
te
r
est
(
R
OI
)
in
b
r
ain
MRI
im
ag
es
to
m
a
k
e
a
d
ia
g
n
o
s
is
u
s
in
g
v
ec
to
r
q
u
an
tizatio
n
tech
n
iq
u
es
an
d
s
t
atis
tical
lear
n
in
g
in
p
atien
ts
w
ith
an
AD.
Kh
ajeh
n
ejad
[
1
9
]
p
r
o
p
o
s
ed
a
m
eth
o
d
f
o
r
d
ia
g
n
o
s
in
g
AD
at
an
ea
r
l
y
s
tag
e
b
y
u
s
in
g
lab
el
p
r
o
p
a
g
atio
n
o
f
a
m
a
n
if
o
ld
b
ased
o
n
s
em
i
-
s
u
p
er
v
is
ed
lear
n
in
g
.
Hu
an
g
[
2
0
]
p
r
o
p
o
s
ed
lo
n
g
itu
d
in
al
m
ea
s
u
r
e
m
en
ts
o
f
MRI
b
r
ain
im
ag
es
an
d
h
ier
ar
c
h
ical
class
if
icatio
n
m
eth
o
d
s
in
th
e
class
if
icatio
n
o
f
th
e
AD
to
d
eter
m
in
e
th
e
s
ev
e
r
ity
o
f
Alzh
eim
er
'
s
.
Acc
o
r
d
in
g
to
t
h
e
d
ef
in
itio
n
o
f
Alzh
eim
er
'
s
,
th
e
m
eth
o
d
o
f
d
iag
n
o
s
is
an
d
s
tu
d
ies
d
escr
ib
ed
ab
o
v
e,
it
will
b
ec
o
m
e
a
p
r
o
b
lem
th
at
is
q
u
ite
im
p
o
r
tan
t
if
th
e
d
iag
n
o
s
is
will
b
e
m
ad
e
in
a
d
ev
elo
p
i
n
g
c
o
u
n
tr
y
s
u
c
h
as
I
n
d
o
n
esia.
As
alr
ea
d
y
k
n
o
wn
,
th
at
th
e
eq
u
ip
m
en
t
u
s
ed
to
d
et
ec
t
Alzh
eim
er
's
d
is
ea
s
e
is
o
n
e
o
f
th
em
is
M
R
I
th
a
t
ca
n
v
is
u
alize
th
e
an
ato
m
y
o
f
t
h
e
h
u
m
a
n
b
o
d
y
,
esp
ec
ially
in
p
ar
ts
o
f
th
e
h
u
m
an
b
r
ain
.
Fu
r
t
h
er
m
o
r
e
,
th
e
d
o
ct
o
r
will
an
aly
ze
th
e
r
esu
lts
o
f
t
h
e
MRI
im
ag
e
to
d
eter
m
in
e
th
e
s
ev
er
ity
o
f
d
em
e
n
tia
d
i
s
ea
s
e
b
ased
o
n
t
h
e
in
f
o
r
m
atio
n
co
n
tain
ed
i
n
th
e
d
atab
ase.
So
it
ca
n
b
e
s
aid
th
at
th
e
r
esu
lts
o
f
th
e
d
iag
n
o
s
is
d
ep
en
d
v
e
r
y
m
u
c
h
o
n
th
e
r
esu
lts
o
f
th
e
d
o
ct
o
r
'
s
an
aly
s
is
.
T
h
e
d
o
cto
r
'
s
an
aly
s
is
also
d
ep
en
d
s
o
n
th
e
q
u
ality
o
f
t
h
e
e
x
is
tin
g
MRI
im
ag
e.
T
h
e
b
etter
th
e
MRI
m
ac
h
in
e,
th
e
b
etter
th
e
q
u
ality
o
f
th
e
i
m
ag
e
p
r
o
d
u
ce
d
.
H
o
wev
er
,
u
n
f
o
r
tu
n
ately
in
s
o
m
e
im
ag
es
th
at
h
a
v
e
d
ec
r
ea
s
ed
i
n
q
u
ality
,
f
o
r
ex
am
p
le,
co
n
ta
in
n
o
is
e,
th
e
c
o
lo
r
is
to
o
co
n
tr
asti
n
g
,
less
s
h
ar
p
,
b
lu
r
r
ed
,
an
d
s
o
o
n
.
T
h
e
im
ag
e
with
p
o
o
r
q
u
ality
b
ec
o
m
es
m
o
r
e
d
if
f
ic
u
lt
to
in
ter
p
r
et
b
ec
au
s
e
th
e
in
f
o
r
m
atio
n
de
liv
er
ed
is
r
e
d
u
ce
d
.
I
t
h
a
p
p
en
s
a
lo
t
in
im
ag
es
p
r
o
d
u
ce
d
b
y
MRI,
esp
ec
ially
lo
w
-
r
eso
lu
tio
n
MRI.
On
th
e
o
th
er
h
an
d
,
alm
o
s
t
all
h
o
s
p
itals
in
I
n
d
o
n
esia,
in
clu
d
in
g
in
t
h
e
p
r
o
v
in
ce
o
f
C
en
tr
al
J
av
a,
o
n
ly
h
av
e
lo
w
-
r
eso
lu
tio
n
MRIs,
an
d
th
e
n
u
m
b
er
s
ar
e
m
i
n
im
al,
o
n
l
y
in
s
o
m
e
h
o
s
p
itals
[
2
1
]
.
Mu
n
ee
r
[
2
2
]
M
u
n
ee
r
d
ev
e
lo
p
ed
a
n
I
o
T
-
b
ased
h
ea
lth
m
o
n
ito
r
in
g
s
y
s
tem
th
at
was
s
u
f
f
icien
t
to
o
v
er
co
m
e
t
h
e
lim
itatio
n
s
o
f
h
ea
lth
f
ac
ilit
ies.W
h
en
r
ef
er
r
in
g
to
th
e
p
r
o
b
lem
s
f
ac
ed
b
y
m
o
s
t
h
o
s
p
itals
in
I
n
d
o
n
esia,
esp
ec
ially
th
e
a
v
ailab
ili
ty
o
f
lo
w
-
q
u
ality
MRI
m
ac
h
in
es,
a
m
an
u
al
an
aly
s
is
will
b
e
h
az
ar
d
o
u
s
an
d
m
ay
lead
to
m
is
d
iag
n
o
s
is
.
B
e
s
id
es
r
ef
er
r
in
g
to
th
e
li
m
itatio
n
s
o
f
h
u
m
an
r
eso
u
r
ce
s
,
esp
ec
ially
n
eu
r
o
s
cien
tis
ts
[
2
1
]
,
a
s
im
p
le
an
d
ac
cu
r
ate
d
ev
ice
is
n
ee
d
ed
to
au
to
m
atica
lly
an
aly
ze
th
e
MRI
im
ag
e
r
esu
lts
,
esp
ec
iall
y
in
th
e
h
ip
p
o
ca
m
p
u
s
an
d
v
en
tr
icu
lar
r
eg
io
n
s
as
th
e
p
r
i
m
ar
y
s
u
p
p
o
r
t
in
th
e
d
iag
n
o
s
is
o
f
Alzh
eim
er
ty
p
e
d
em
en
tia.
T
h
is
r
esear
ch
h
as
a
g
o
al
to
d
ev
elo
p
an
au
to
m
atic,
lo
w
-
co
s
t
an
d
s
tr
aig
h
tf
o
r
war
d
t
o
o
l
f
o
r
an
al
y
zin
g
h
i
p
p
o
ca
m
p
u
s
an
d
v
en
tr
icu
lar
ch
ar
ac
ter
is
tics
in
d
e
m
en
tia
p
atien
ts
b
y
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
C
o
r
o
n
a
l sli
ce
s
eg
men
ta
tio
n
u
s
in
g
a
w
a
ters
h
ed
meth
o
d
fo
r
ea
r
ly
id
en
tifi
ca
tio
n
o
f
… (
R
etn
o
S
u
p
r
iya
n
ti
)
65
o
p
tim
izin
g
ex
is
tin
g
MRI
im
ag
es.
W
ib
o
wo
[
2
3
]
u
s
ed
th
e
g
r
ay
lev
el
co
-
o
cc
u
r
r
en
ce
m
atr
i
x
in
an
aly
zin
g
3
D
im
ag
es
in
m
u
s
cles.
W
id
o
d
o
[
2
4
]
a
p
p
lies
th
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
m
eth
o
d
in
r
ec
o
g
n
i
zin
g
lu
n
g
d
is
ea
s
e.
Me
m
o
n
[
2
5
]
ap
p
lied
th
e
Me
d
i
an
f
ilter
to
r
em
o
v
e
n
o
is
e
in
th
e
m
icr
o
s
co
p
ic
im
ag
e.
Su
p
r
iy
an
t
i
[
2
6
]
im
p
lem
en
ted
th
e
h
is
to
g
r
am
e
q
u
aliza
tio
n
m
eth
o
d
to
n
o
r
m
alize
in
p
u
t
im
a
g
es.
Ho
wev
er
,
in
th
is
p
ap
e
r
,
we
em
p
h
asize
th
e
d
is
cu
s
s
io
n
o
n
co
r
o
n
al
s
lice
a
n
aly
s
is
o
n
ly
in
ex
p
l
o
r
in
g
th
e
m
o
r
p
h
o
lo
g
ical
in
f
o
r
m
atio
n
in
it.
I
n
o
u
r
p
r
ev
io
u
s
r
esear
ch
[
2
7
]
,
we
ca
r
r
ie
d
o
u
t
th
e
p
r
o
ce
s
s
o
f
s
eg
m
e
n
tin
g
th
e
co
r
o
n
al
s
lice
u
s
in
g
th
e
ac
ti
v
e
co
n
t
o
u
r
m
eth
o
d
.
Ho
wev
er
,
th
e
r
esu
lts
o
b
tain
ed
s
ee
m
to
n
ee
d
to
b
e
im
p
r
o
v
e
d
ag
ain
.
So
in
th
is
ex
p
er
im
e
n
t,
we
tr
ied
to
u
s
e
th
e
wate
r
s
h
ed
m
eth
o
d
.
W
e
tr
ied
u
s
in
g
th
e
wate
r
s
h
e
d
s
eg
m
en
t
atio
n
m
eth
o
d
b
ec
au
s
e
th
is
m
eth
o
d
is
o
n
e
o
f
th
e
s
eg
m
en
tatio
n
m
et
h
o
d
s
th
at
ar
e
wid
ely
u
s
ed
in
m
ed
ical
im
a
g
es.
T
h
is
m
eth
o
d
is
k
n
o
w
n
as
s
im
p
le,
ef
f
icien
t
f
o
r
co
m
p
lex
im
a
g
e
s
eg
m
en
tatio
n
,
an
d
ca
n
p
r
o
d
u
ce
a
c
o
m
p
lete
d
iv
is
io
n
o
f
t
h
e
im
ag
e
i
n
to
s
ev
er
al
r
eg
io
n
s
ev
en
th
o
u
g
h
th
e
im
ag
e
q
u
ality
is
n
o
t g
o
o
d
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
2
.
1
.
Da
t
a
a
cquis
it
io
n
T
h
e
d
ata
u
s
ed
in
th
is
ex
p
er
im
en
t
is
f
r
o
m
th
e
OASI
S
d
atab
ase
wh
ich
is
p
u
b
licly
p
r
o
v
id
e
d
in
th
e
in
ter
est
o
f
s
tu
d
y
an
d
an
aly
s
is
.
T
h
e
b
a
s
elin
e
d
ata
co
n
s
is
ted
o
f
cr
o
s
s
-
s
ec
tio
n
al
d
atasets
f
r
o
m
ag
ed
1
8
to
9
6
y
ea
r
s
an
d
d
iag
n
o
s
ed
clin
ically
with
Al
zh
eim
er
'
s
with
a
v
er
y
m
ild
to
m
o
d
er
ate
ca
teg
o
r
y
[
3
,
28
-
3
1
]
.
T
h
e
o
v
er
all
ex
p
er
im
en
ts
co
n
d
u
cted
in
t
h
is
p
ap
er
ar
e
s
h
o
w
n
in
Fig
u
r
e
1
.
B
ased
o
n
Fig
u
r
e
1
,
th
e
s
eg
m
en
tatio
n
p
r
o
ce
s
s
is
ca
r
r
ied
o
u
t
b
y
th
e
wate
r
s
h
e
d
m
eth
o
d
.
Firstl
y
,
th
e
r
ea
d
i
n
g
o
f
th
e
d
i
g
ital
im
ag
e
o
f
th
e
MRI
o
f
th
e
co
r
o
n
al
s
lice
b
r
ain
will
b
e
p
r
o
ce
s
s
ed
.
Fu
r
th
e
r
m
o
r
e,
t
h
e
im
ag
e
th
at
h
as
b
ee
n
r
ea
d
b
y
th
e
s
y
s
t
em
will
b
e
ch
a
n
g
ed
in
g
r
a
y
f
o
r
m
,
an
d
th
e
b
r
ig
h
tn
ess
is
ad
ju
s
ted
u
s
in
g
co
n
tr
ast
s
tr
etch
in
g
.
T
h
e
n
t
h
e
im
ag
e
c
r
o
p
p
in
g
p
r
o
ce
s
s
to
t
ak
e
s
p
ec
if
ic
r
eg
i
o
n
.
T
h
en
th
e
cr
o
p
p
ed
im
ag
e
is
co
n
v
er
ted
in
to
a
b
in
a
r
y
im
ag
e.
T
h
is
b
in
ar
y
im
ag
e
will
b
e
an
in
p
u
t
im
ag
e
in
th
e
wat
er
s
h
ed
s
eg
m
en
tatio
n
p
r
o
ce
s
s
.
Af
ter
th
e
wate
r
s
h
ed
s
eg
m
e
n
tatio
n
o
b
ject
is
o
b
tain
ed
,
th
e
ex
ten
s
iv
e
ca
lcu
latio
n
p
r
o
ce
s
s
o
f
t
h
e
h
i
p
p
o
ca
m
p
u
s
an
d
v
en
t
r
icles
is
ca
r
r
ied
o
u
t
in
p
i
x
el
u
n
its
to
d
eter
m
in
e
th
e
s
ev
e
r
ity
o
f
Alzh
eim
er
'
s
b
ased
o
n
th
e
C
DR
v
alu
e
o
b
tain
ed
f
r
o
m
th
e
OASI
S f
ac
t sh
ee
t.
Fig
u
r
e
1
.
B
lo
ck
d
iag
r
am
o
f
o
v
er
all
ex
p
er
im
en
t
2
.
2
.
I
ma
g
e
pre
-
pro
ce
s
s
ing
T
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
s
tag
e
is
d
o
n
e
to
g
et
a
b
etter
im
ag
e
th
an
th
e
in
itial
im
ag
e.
T
h
is
p
r
o
ce
s
s
i
s
d
o
n
e
b
ec
au
s
e
to
d
o
wate
r
s
h
ed
s
eg
m
en
tatio
n
,
an
im
ag
e
with
a
b
etter
lev
el
o
f
q
u
ality
m
u
s
t
b
e
o
b
tain
ed
c
o
n
ce
r
n
i
n
g
lig
h
tin
g
.
T
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
s
tag
e
in
clu
d
es
co
n
tr
a
s
t
s
tr
etch
i
n
g
.
I
t
is
d
o
n
e
to
c
o
n
tr
ast
th
e
i
m
ag
e
m
o
r
e
te
n
u
o
u
s
th
an
b
ef
o
r
e
,
s
o
th
at
im
ag
e
lig
h
tin
g
is
b
etter
.
C
o
n
tr
ast
s
tr
etch
in
g
is
o
n
e
m
eth
o
d
o
f
im
p
r
o
v
in
g
im
ag
e
q
u
ality
.
I
n
o
u
r
p
r
ev
io
u
s
r
eser
ch
[
3
2
,
3
3
]
we
d
id
it.
I
m
ag
e
p
r
o
ce
s
s
in
g
h
a
s
a
h
ig
h
e
r
co
n
tr
ast
v
al
u
e
s
o
th
a
t
it
ca
n
p
r
o
d
u
ce
n
ew
in
f
o
r
m
atio
n
.
I
t
is
d
o
n
e
b
y
ad
d
in
g
o
r
r
e
d
u
cin
g
co
n
tr
ast
s
o
th
at
th
e
im
ag
e
is
s
h
ar
p
er
th
a
n
b
ef
o
r
e
[
2
]
.
I
t
is
ex
p
ec
ted
t
h
at
co
n
tr
ast
s
tr
etch
in
g
ca
n
p
r
o
d
u
ce
im
ag
es
th
at
h
a
v
e
p
r
o
p
er
lig
h
tin
g
d
is
tr
ib
u
tio
n
s
o
th
at
th
e
r
esu
ltin
g
im
ag
e
is
v
is
ib
le.
2
.
3
.
Wa
t
er
s
hed seg
m
ent
a
t
io
n
T
h
e
s
eg
m
en
tatio
n
m
et
h
o
d
u
s
ed
is
th
e
wate
r
s
h
ed
m
eth
o
d
f
o
r
s
eg
m
en
tin
g
t
h
e
h
ip
p
o
ca
m
p
u
s
an
d
v
en
tr
icu
lar
a
r
ea
s
.
T
h
er
e
ar
e
s
ev
er
al
ty
p
es
o
f
wate
r
s
h
ed
s
eg
m
en
tatio
n
,
n
am
ely
wate
r
s
h
ed
s
eg
m
en
tatio
n
u
s
in
g
d
is
tan
ce
tr
an
s
f
o
r
m
atio
n
,
u
s
in
g
g
r
ad
ien
ts
,
an
d
u
s
in
g
m
ar
k
e
r
-
co
n
tr
o
lled
[
2
]
.
I
n
th
is
r
esear
ch
,
we
u
s
e
wate
r
s
h
ed
s
eg
m
en
tatio
n
u
s
in
g
m
ar
k
e
r
-
co
n
tr
o
lled
.
T
h
is
ty
p
e
o
f
s
eg
m
e
n
t
atio
n
is
u
s
ed
to
co
n
tr
o
l
o
v
er
-
s
eg
m
en
tatio
n
b
ased
o
n
th
e
m
ar
k
er
co
n
ce
p
t.
W
h
at
we
d
o
is
cr
ea
te
an
in
ter
n
al
m
a
r
k
er
th
at
is
in
s
id
e
ea
ch
d
esire
d
o
b
ject
an
d
also
an
ex
ter
n
al
m
a
r
k
er
th
at
c
o
n
tain
s
t
h
e
b
ac
k
g
r
o
u
n
d
.
T
h
ese
two
m
a
r
k
er
s
ar
e
th
en
u
s
ed
to
m
o
d
if
y
t
h
e
g
r
a
d
ien
t
im
a
g
e.
T
o
ap
p
l
y
wate
r
s
h
ed
m
ar
k
e
r
-
c
o
n
tr
o
lled
s
eg
m
en
tatio
n
b
eg
in
s
b
y
tr
a
n
s
f
o
r
m
i
n
g
wate
r
s
h
ed
f
r
o
m
g
r
a
d
ien
t
im
a
g
es
with
o
u
t
o
th
e
r
p
r
o
ce
s
s
es.
T
h
e
n
we
ca
lcu
late
th
e
lo
ca
tio
n
o
f
all
r
e
g
io
n
al
m
in
im
a
in
th
e
i
m
ag
e.
T
h
e
r
eg
io
n
al
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
19
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
1
:
6
3
-
72
66
f
u
n
ctio
n
o
f
m
in
im
a
in
g
r
a
d
ien
t im
ag
es is
u
s
ed
to
s
ee
wh
y
w
ater
s
h
ed
f
u
n
ctio
n
s
p
r
o
d
u
ce
m
a
n
y
s
m
all
ca
tch
m
en
t
b
asin
s
.
T
h
e
r
eg
io
n
al
m
in
im
a
c
an
also
b
e
ex
ce
s
s
iv
e.
T
h
en
we
ca
lcu
late
th
e
n
u
m
b
er
o
f
"lo
w
s
p
o
ts
"
in
th
e
im
ag
e.
Nex
t
is
an
e
x
ter
n
al
m
ar
k
e
r
s
ea
r
ch
.
T
h
e
a
p
p
r
o
ac
h
is
to
m
ar
k
t
h
e
b
ac
k
g
r
o
u
n
d
with
p
ix
el
s
ea
r
ch
wh
ich
is
m
id
way
b
etwe
en
in
ter
n
al
m
ar
k
er
s
.
T
o
d
o
th
is
is
to
ca
lcu
late
wate
r
s
h
ed
tr
an
s
f
o
r
m
atio
n
s
f
r
o
m
th
e
t
r
an
s
f
o
r
m
atio
n
o
f
t
h
e
m
ar
k
er
'
s
in
ter
n
al
im
ag
e
d
is
tan
ce
.
Af
ter
in
ter
n
al
an
d
ex
te
r
n
al
m
ar
k
er
s
h
av
e
b
ee
n
o
b
tain
e
d
,
t
h
en
b
o
th
a
r
e
u
s
ed
to
m
o
d
if
y
th
e
g
r
ad
ie
n
t
im
ag
e
u
s
in
g
a
p
r
o
ce
d
u
r
e
ca
lled
m
in
im
a
im
p
o
s
itio
n
.
T
h
e
im
p
o
s
itio
n
m
in
im
a
tech
n
i
q
u
e
m
o
d
if
ies th
e
g
r
a
y
s
ca
le
im
ag
e
s
o
th
at
r
eg
io
n
al
m
in
i
m
a
o
cc
u
r
s
o
n
ly
in
th
e
m
ar
k
e
d
lo
ca
tio
n
.
2
.
4
.
M
o
rpho
lo
g
ica
l
cha
r
a
ct
e
ristic
ca
lcula
t
io
n
T
h
e
ca
lcu
latio
n
o
f
t
h
e
ar
ea
o
f
v
en
tr
icles
an
d
h
ip
p
o
ca
m
p
u
s
is
d
o
n
e
b
y
ca
lcu
latin
g
t
h
e
to
tal
n
u
m
b
er
o
f
p
ix
els
th
at
h
av
e
a
v
alu
e
o
f
1
.
T
h
e
ca
lcu
lated
im
a
g
e
is
b
in
a
r
y
s
o
th
a
t
wh
e
n
ca
lcu
latin
g
a
r
ea
it
is
en
o
u
g
h
to
ca
lcu
late
th
e
n
u
m
b
er
o
f
v
alu
e
s
th
at
ex
is
t
in
th
e
im
ag
e
m
atr
i
ce
s
.
T
h
e
d
if
f
er
e
n
ce
b
etwe
en
th
e
ca
lcu
latio
n
o
f
th
e
v
en
tr
icu
lar
ar
ea
an
d
th
e
h
ip
p
o
ca
m
p
u
s
a
r
ea
is
o
n
ly
th
e
n
u
m
b
er
o
f
im
ag
es
ca
lcu
lated
.
I
f
in
th
e
v
en
tr
icu
la
r
d
etec
tio
n
s
y
s
tem
th
er
e
is
o
n
ly
o
n
e
im
ag
e
ca
lcu
lated
,
th
en
in
th
e
h
ip
p
o
ca
m
p
u
s
d
etec
tio
n
s
y
s
tem
th
er
e
ar
e
two
im
ag
es.
I
t
is
b
ec
au
s
e
o
f
th
e
h
ip
p
o
ca
m
p
u
s
d
etec
tio
n
s
y
s
tem
o
f
b
r
ain
MRI
im
ag
es.
I
t
is
s
ep
ar
ated
b
etwe
en
th
e
lef
t
v
iewe
r
an
d
th
e
r
i
g
h
t
v
iew
er
.
T
h
e
a
r
e
a
v
al
u
es
o
f
th
e
lef
t
an
d
r
i
g
h
t
h
i
p
p
o
ca
m
p
u
s
ar
e
s
ea
r
ch
ed
a
n
d
a
d
d
ed
to
g
eth
er
r
esp
ec
tiv
ely
.
T
h
e
t
o
tal
s
u
m
m
atio
n
r
esu
lt is
th
e
v
alu
e
o
f
th
e
b
r
ain
'
s
h
ip
p
o
ca
m
p
al
M
R
I
im
ag
e.
2
.
5
.
I
ma
g
e
cla
s
s
if
ica
t
io
n
I
n
o
u
r
ex
p
er
im
e
n
ts
,
th
e
id
en
t
if
icatio
n
s
tag
e
in
ad
d
itio
n
to
c
alcu
latin
g
th
e
ar
ea
o
f
t
h
e
s
eg
m
en
ted
h
ip
p
o
ca
m
p
u
s
o
b
ject
also
id
e
n
tifie
d
th
e
C
DR
v
alu
e
o
f
th
e
b
r
a
in
MRI
im
ag
e
u
s
ed
.
Fro
m
th
is
C
DR
v
alu
e,
it
ca
n
b
e
s
ee
n
th
e
s
ev
er
ity
o
f
a
p
er
s
o
n
'
s
Alzh
eim
er
'
s
.
At
th
e
im
ag
e
class
if
icatio
n
s
tag
e,
we
u
s
e
b
ac
k
p
r
o
p
ag
atio
n
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
(
AN
N)
.
T
h
e
tr
ain
in
g
d
ata
u
s
ed
is
th
e
r
esu
lt
o
f
th
e
ca
lcu
latio
n
o
f
th
e
h
ip
p
o
ca
m
p
u
s
an
d
v
en
tr
icu
lar
ar
ea
t
h
at
h
as
b
ee
n
ca
r
r
ied
o
u
t
o
n
all
tr
ial
im
ag
es.
T
h
en
we
d
eter
m
in
e
th
e
tr
ain
in
g
tar
g
et
wh
ich
is
th
e
v
alu
e
o
f
th
e
C
DR
th
at
is
th
e
tar
g
et
o
f
id
e
n
tific
atio
n
.
T
h
e
ar
ch
itectu
r
al
f
o
r
m
o
f
th
e
b
ac
k
p
r
o
p
ag
atio
n
ANN
u
s
ed
in
th
is
s
tu
d
y
is
1
-
2
-
1
wh
ich
c
o
n
s
is
ts
o
f
1
in
p
u
t,
two
h
id
d
en
lay
er
s
,
an
d
o
n
e
o
u
tp
u
t.
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
As
ex
p
lain
ed
in
th
e
s
u
b
s
ec
tio
n
ab
o
v
e,
th
at
in
th
is
p
r
e
-
p
r
o
ce
s
s
in
g
p
h
ase,
we
u
s
e
co
n
tr
ast
s
t
r
etch
in
g
to
g
et
a
b
etter
in
p
u
t
im
ag
e
to
b
e
p
r
o
ce
s
s
ed
.
A
g
r
ay
-
s
ca
le
im
ag
e
is
a
m
atr
ix
ar
r
an
g
em
en
t
th
at
h
as
in
ten
s
ity
v
alu
es
f
r
o
m
0
to
2
5
5
.
T
h
ese
v
alu
es
r
ep
r
esen
t
in
ten
s
ity
v
al
u
es
in
s
p
e
cif
ic
r
o
ws
an
d
co
lu
m
n
s
in
th
e
im
ag
e.
So
th
at
i
f
ch
an
g
es
in
v
alu
e
ar
e
m
ad
e,
th
e
in
ten
s
ity
o
f
th
e
im
ag
e
also
ch
an
g
es.
T
h
e
co
n
t
r
ast
s
tr
etch
in
g
alg
o
r
ith
m
u
s
ed
in
th
e
r
esear
ch
is
s
h
o
wn
in
(
1
)
.
=
{
1
1
,
0
≤
<
1
1
+
(
−
1
)
∗
(
2
−
1
)
(
2
−
1
)
2
+
(
−
2
)
∗
(
255
−
2
)
(
255
−
2
)
(
1
)
T
h
e
p
o
in
ts
(
r
1
,
s
1
)
an
d
p
o
in
ts
(
r
2
,
s
2
)
d
eter
m
i
n
e
th
e
f
o
r
m
o
f
tr
an
s
f
o
r
m
atio
n
a
n
d
ca
n
b
e
s
et
to
d
eter
m
in
e
th
e
lev
el
o
f
s
p
r
ea
d
o
f
t
h
e
g
r
a
y
lev
el
o
f
th
e
r
esu
ltin
g
im
a
g
e.
I
f
r
1
=
s
1
an
d
r
2
=
s
2
,
th
e
n
th
e
t
r
an
s
f
o
r
m
atio
n
will
b
e
in
th
e
f
o
r
m
o
f
a
s
tr
aig
h
t
lin
e
wh
ich
m
ea
n
s
th
er
e
is
n
o
ch
a
n
g
e
in
th
e
g
r
ay
le
v
el
o
f
th
e
im
ag
e
p
r
o
d
u
ce
d
.
I
t
is
g
en
er
ally
ass
u
m
ed
th
at
r
1
≤
r
2
an
d
s
1
≤
s
2
s
o
t
h
at
th
e
f
u
n
ctio
n
will
p
r
o
d
u
ce
a
s
in
g
le
v
alu
e
an
d
th
e
v
alu
e
will
alwa
y
s
r
is
e.
I
n
co
n
tr
ast,
s
tr
etc
h
in
g
alg
o
r
i
th
m
th
at
we
u
s
e,
th
e
v
alu
es
o
f
r
1
,
r
2
,
s
1
,
an
d
s
2
h
av
e
b
ee
n
d
eter
m
in
e
d
s
o
th
at
we
d
o
n
o
t
n
ee
d
to
s
et
th
em
m
an
u
ally
.
Ho
we
v
er
,
b
etwe
en
th
e
v
en
tr
ic
u
lar
d
et
ec
tio
n
s
y
s
tem
an
d
h
ip
p
o
ca
m
p
u
s
d
etec
tio
n
,
th
e
v
a
lu
es
o
f
r
1
,
r
2
,
s
1
,
an
d
s
2
ar
e
d
if
f
er
en
t.
T
h
is
is
b
ec
a
u
s
e,
in
th
eir
n
ee
d
f
o
r
wate
r
s
h
e
d
s
eg
m
en
tatio
n
p
r
o
ce
s
s
es,
b
o
th
h
av
e
d
if
f
er
en
ce
s
in
th
e
lev
el
o
f
im
ag
e
in
ten
s
ity
.
T
h
e
v
alu
es
o
f
r
1
,
r
2
,
s
1
,
an
d
s
2
in
th
e
v
en
tr
icu
la
r
d
etec
tio
n
s
y
s
tem
ar
e
0
.
2
4
,
0
.
2
5
,
0
.
3
3
an
d
0
.
3
5
.
W
h
ile
f
o
r
Hip
p
o
ca
m
p
u
s
d
e
tectio
n
s
y
s
tem
s
a
r
e
0
.
3
5
,
0
.
3
7
,
0
.
3
9
,
an
d
0
.
4
1
.
T
h
e
v
alu
es
o
f
r
1
,
r
2
,
s
1
,
a
n
d
s
2
th
at
h
av
e
b
ee
n
d
eter
m
in
e
d
will
f
o
r
m
a
tr
an
s
f
o
r
m
atio
n
lin
e
as sh
o
wn
in
Fig
u
r
e
2
.
T
h
e
v
alu
es o
f
r
1
,
r
2
,
s
1
,
an
d
s
2
s
elec
ted
ar
e
o
b
tai
n
ed
f
r
o
m
t
h
e
r
etestin
g
p
r
o
ce
s
s
.
Af
ter
th
e
ex
p
er
im
en
t
u
s
in
g
s
ev
en
m
o
r
e
s
ets
o
f
v
alu
es
r
1
,
r
2
,
s
1
,
a
n
d
s
2
f
o
r
v
e
n
tr
icu
lar
d
etec
tio
n
s
y
s
tem
s
an
d
1
3
m
o
r
e
s
ets
o
f
v
alu
es
r
1
,
r
2
,
s
1
,
an
d
s
2
f
o
r
th
e
h
ip
p
o
ca
m
p
u
s
d
etec
tio
n
s
y
s
tem
o
b
tain
ed
a
s
et
o
f
v
alu
es
th
at
h
ad
th
e
h
ig
h
est
p
er
ce
n
tag
e
o
f
s
u
cc
ess
an
d
p
er
f
o
r
m
an
ce
h
i
g
h
f
o
r
b
o
t
h
s
y
s
tem
s
.
T
h
e
e
n
tir
e
im
ag
e
test
ed
,
in
r
ea
lity
,
d
o
e
s
n
o
t
h
av
e
a
1
0
0
%
s
u
cc
ess
p
er
ce
n
tag
e
wh
en
s
eg
m
en
ted
d
u
e
to
in
ac
cu
r
ate
co
n
t
r
ast
s
tr
etch
in
g
.
Alth
o
u
g
h
th
e
p
r
ed
eter
m
in
ed
v
alu
es
o
f
r
1
,
r
2
,
s
1
,
an
d
s
2
h
av
e
th
e
h
i
g
h
est
s
u
cc
ess
r
ates
am
o
n
g
o
th
er
s
,
th
ey
ar
e
s
t
ill
n
o
t
1
0
0
%
s
u
c
ce
s
s
f
u
l.
Fig
u
r
e
3
is
an
ex
am
p
le
o
f
th
e
r
esu
lts
o
f
co
n
tr
ast
s
tr
etch
in
g
u
s
in
g
th
e
ex
ac
t
v
alu
es
o
f
r
1
,
r
2
,
s
1
,
an
d
s
2
an
d
wate
r
s
h
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
C
o
r
o
n
a
l sli
ce
s
eg
men
ta
tio
n
u
s
in
g
a
w
a
ters
h
ed
meth
o
d
fo
r
ea
r
ly
id
en
tifi
ca
tio
n
o
f
… (
R
etn
o
S
u
p
r
iya
n
ti
)
67
s
eg
m
en
tatio
n
r
esu
lts
in
v
e
n
tr
i
cu
lar
d
etec
tio
n
.
W
h
ile
Fig
u
r
e
4
is
an
ex
am
p
le
o
f
t
h
e
r
esu
lts
o
f
u
s
in
g
th
e
v
alu
es
r
1
,
r
2
,
s
1
,
an
d
s
2
in
th
e
d
etec
ti
o
n
o
f
th
e
h
ip
p
o
ca
m
p
u
s
.
(
a
)
(
b
)
Fig
u
r
e
2
.
Gr
a
p
h
o
f
co
n
tr
ast s
tr
etch
in
g
tr
an
s
f
o
r
m
atio
n
f
u
n
ctio
n
o
f
;
(
a)
v
en
tr
ic
u
lar
d
etec
tio
n
s
y
s
tem
,
(
b
)
h
ip
p
o
ca
m
p
u
s
d
etec
tio
n
s
y
s
tem
Fig
u
r
e
3
.
Ven
tr
ic
u
lar
d
etec
tio
n
;
(
a)
o
r
ig
in
al
im
ag
e,
(
b
)
co
n
tr
ast s
tr
etch
in
g
r
esu
lts
,
(
c)
s
eg
m
en
tatio
n
r
esu
lts
Fig
u
r
e
4
.
Hip
p
o
ca
m
p
u
s
d
etec
t
io
n
; (
a)
o
r
ig
in
al
im
ag
e,
(
b
)
co
n
tr
ast s
tr
etch
in
g
r
esu
lts
,
(
c)
s
e
g
m
en
tatio
n
r
esu
lts
R
ef
er
r
in
g
to
Fig
u
r
e
3
an
d
Fig
u
r
e
4
it
ca
n
b
e
s
ee
n
th
at
th
e
i
m
ag
e
af
ter
th
e
co
n
tr
ast
s
tr
etch
in
g
p
r
o
ce
s
s
h
as
an
ev
e
n
d
is
tr
ib
u
tio
n
o
f
lig
h
t
co
m
p
a
r
ed
to
th
e
o
r
ig
in
al
i
m
ag
e.
Seg
m
e
n
tatio
n
u
s
ed
f
o
r
v
en
tr
icu
lar
d
etec
tio
n
is
a
wate
r
s
h
ed
s
eg
m
en
tatio
n
m
eth
o
d
u
s
in
g
a
m
a
r
k
er
-
c
o
n
tr
o
lled
tech
n
iq
u
e.
T
o
u
s
e
th
is
tec
h
n
iq
u
e,
we
lo
o
k
f
o
r
g
r
ad
ien
t
v
al
u
es
f
r
o
m
e
d
g
e
d
etec
tio
n
.
T
h
e
e
d
g
e
d
etec
tio
n
m
eth
o
d
u
s
ed
is
So
b
el
ed
g
e
d
etec
tio
n
.
T
h
en
an
in
ter
n
al
m
ar
k
er
s
ea
r
ch
was
ca
r
r
ied
o
u
t
to
b
e
ab
le
t
o
p
r
o
ce
s
s
wate
r
s
h
ed
s
eg
m
en
tatio
n
o
n
d
is
tan
ce
t
r
an
s
f
o
r
m
atio
n
f
r
o
m
th
e
in
ter
n
al
m
ar
k
er
s
ea
r
c
h
r
esu
lts
im
ag
e.
T
h
e
r
esu
lts
o
f
th
e
s
eg
m
en
tatio
n
ar
e
u
s
ed
as
ex
te
r
n
al
m
ar
k
er
s
.
T
h
is
tech
n
iq
u
e
r
esu
lts
in
r
e
g
io
n
al
m
in
im
a
o
cc
u
r
r
i
n
g
o
n
ly
in
m
ar
k
ed
lo
ca
tio
n
s
.
T
h
e
r
esu
lt
s
o
f
th
e
wate
r
s
h
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
19
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
1
:
6
3
-
72
68
s
eg
m
en
tatio
n
p
r
o
ce
s
s
ar
e
d
is
p
lay
ed
in
a
x
es.
T
h
e
wate
r
s
h
e
d
s
eg
m
en
tatio
n
p
r
o
ce
s
s
will
p
r
o
d
u
ce
an
o
r
ig
in
al
im
ag
e
with
s
ev
er
al
wate
r
s
h
ed
lin
es
en
cir
clin
g
s
ev
er
al
o
b
jec
ts
.
T
h
is
wate
r
s
h
ed
lin
e
s
h
o
ws
th
e
o
b
ject
th
at
was
s
u
cc
ess
f
u
lly
id
en
tifie
d
.
I
n
t
h
e
v
en
tr
icu
lar
d
etec
tio
n
s
y
s
tem
,
th
e
p
ar
am
eter
s
o
f
s
u
c
ce
s
s
o
f
th
e
im
ag
e
s
eg
m
en
tatio
n
s
tag
e
ar
e
wh
en
t
h
e
wate
r
s
h
ed
lin
e
is
s
u
cc
ess
f
u
lly
cir
clin
g
th
e
v
e
n
tr
icu
lar
o
b
j
ec
t.
Af
ter
s
ee
in
g
a
wate
r
s
h
ed
lin
e
en
cir
clin
g
a
v
e
n
tr
icu
lar
o
b
ject,
cr
o
p
p
in
g
is
d
o
n
e
s
o
t
h
at
o
th
e
r
o
b
jects
th
at
ar
e
also
d
etec
ted
b
y
th
e
wate
r
s
h
ed
lin
e
ar
e
n
o
t
ta
k
en
f
o
r
th
e
n
ex
t
p
r
o
ce
s
s
.
T
h
e
n
ex
t
p
r
o
ce
s
s
is
ch
an
g
in
g
th
e
s
eg
m
en
ted
im
ag
e
to
a
b
in
ar
y
im
ag
e.
Fig
u
r
e
5
illu
s
tr
ates
th
e
s
tag
es
o
f
im
ag
e
s
eg
m
en
tatio
n
in
v
e
n
tr
icu
lar
d
ete
ctio
n
.
R
ef
er
r
in
g
to
Fig
u
r
e
5
it
ca
n
b
e
s
ee
n
th
at
t
h
e
r
esu
lts
o
f
wate
r
s
h
ed
s
eg
m
en
tatio
n
in
th
e
f
o
r
m
o
f
o
r
ig
in
al
i
m
ag
es
with
th
e
ad
d
itio
n
o
f
a
wate
r
s
h
ed
lin
e
o
n
s
o
m
e
o
b
jects
h
av
e
m
an
ag
ed
to
g
et
th
e
d
esire
d
o
b
ject,
n
am
ely
v
en
tr
icles.
T
h
e
v
en
tr
icu
lar
o
b
ject
is
s
u
r
r
o
u
n
d
e
d
b
y
a
wate
r
s
h
ed
lin
e
w
h
ich
b
ec
o
m
es
a
r
ef
er
e
n
ce
th
at
th
e
o
b
ject
is
s
u
cc
ess
f
u
lly
s
eg
m
en
ted
.
I
n
th
e
d
et
ec
tio
n
s
y
s
tem
o
f
th
e
h
ip
p
o
ca
m
p
u
s
,
th
e
p
r
o
ce
s
s
ed
i
m
ag
e
h
as
2
,
s
o
th
er
e
ar
e
two
o
r
ien
tatio
n
s
,
n
am
ely
in
th
e
lef
t
v
iewe
r
a
n
d
r
i
g
h
t
v
iewe
r
.
T
h
e
h
ip
p
o
ca
m
p
u
s
d
etec
tio
n
s
y
s
tem
is
n
o
t
u
s
ed
s
i
n
g
le
ed
g
e
d
etec
tio
n
.
T
o
ch
an
g
e
th
e
tech
n
iq
u
e,
we
u
s
e
m
o
r
p
h
o
lo
g
ical
o
p
er
at
io
n
s
.
T
h
en
f
ilter
in
g
th
e
o
r
ig
in
al
i
m
ag
e
u
s
in
g
to
p
-
h
at
tr
an
s
f
o
r
m
s
an
d
b
o
tto
m
-
h
at
tr
a
n
s
f
o
r
m
s
.
T
h
e
n
we
in
cr
ea
s
e
th
e
g
ap
b
etwe
en
th
e
ex
is
tin
g
o
b
jects
b
y
ad
d
in
g
th
e
o
r
ig
in
al
im
ag
e
with
th
e
to
p
-
h
at
tr
an
s
f
o
r
m
s
im
ag
e,
th
en
th
e
r
esu
lts
o
f
th
e
s
u
m
ar
e
r
ed
u
ce
d
b
y
th
e
b
o
tto
m
-
h
at
tr
an
s
f
o
r
m
s
r
esu
lt
im
ag
e
.
T
h
is
in
cr
ea
s
e
in
g
a
p
also
aim
s
to
m
ax
im
ize
co
n
tr
ast.
T
h
en
c
o
m
p
l
em
en
tin
g
th
e
im
ag
e
r
esu
lts
o
f
th
is
in
cr
ea
s
e
in
a
g
a
p
.
Af
ter
th
is
m
o
d
if
icatio
n
,
th
e
s
eg
m
en
tatio
n
p
r
o
ce
s
s
h
as
s
im
ilar
ities
in
d
etec
tin
g
v
en
tr
icles,
n
am
ely
in
t
er
n
al
m
ar
k
er
s
ea
r
ch
es.
As
in
th
e
ca
s
e
o
f
v
en
tr
icu
la
r
d
etec
tio
n
,
th
e
d
etec
tio
n
o
f
th
e
h
ip
p
o
ca
m
p
u
s
will
also
p
r
o
d
u
ce
an
o
r
ig
in
al
im
ag
e
with
s
ev
er
al
wate
r
s
h
ed
lin
es
en
ci
r
clin
g
s
ev
er
al
o
b
jects.
Ho
wev
er
,
u
n
lik
e
th
e
wate
r
s
h
e
d
lin
e
o
n
a
v
en
tr
icu
lar
d
etec
tio
n
s
y
s
t
em
th
at
is
wh
ite,
th
e
wate
r
s
h
ed
lin
e
o
n
th
is
s
y
s
tem
is
b
lack
.
I
t
is
b
ec
au
s
e
th
e
n
ee
d
f
o
r
s
eg
m
en
tatio
n
b
etwe
en
v
en
tr
ic
u
lar
an
d
h
ip
p
o
ca
m
p
al
o
b
jects
is
d
if
f
er
en
t.
Fig
u
r
e
6
s
h
o
ws th
e
r
esu
lts
o
f
wate
r
s
h
ed
s
eg
m
en
tatio
n
in
th
e
d
etec
tio
n
o
f
th
e
h
ip
p
o
ca
m
p
u
s
.
Fig
u
r
e
5
.
R
esu
lts
o
f
v
en
tr
ic
u
la
r
d
etec
tio
n
s
eg
m
e
n
tatio
n
s
tag
e
s
;
(
a)
s
eg
m
en
tatio
n
r
esu
lts
,
(
b
)
r
esu
lts
o
f
c
r
o
p
p
in
g
,
a
n
d
(
c
)
f
o
r
m
c
o
n
v
e
r
s
io
n
to
b
i
n
ar
y
im
ag
es
Fig
u
r
e
6
.
T
h
e
r
esu
lts
o
f
th
e
h
i
p
p
o
ca
m
p
u
s
d
etec
tio
n
s
eg
m
e
n
t
atio
n
s
tag
e
;
(
a)
th
e
in
itial p
h
ase
o
f
s
eg
m
en
tatio
n
,
(
b
)
th
e
s
tag
e
o
f
cr
o
p
p
in
g
,
an
d
(
c)
th
e
co
n
v
er
s
io
n
p
h
ase
to
b
in
ar
y
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
C
o
r
o
n
a
l sli
ce
s
eg
men
ta
tio
n
u
s
in
g
a
w
a
ters
h
ed
meth
o
d
fo
r
ea
r
ly
id
en
tifi
ca
tio
n
o
f
… (
R
etn
o
S
u
p
r
iya
n
ti
)
69
R
ef
er
r
in
g
to
Fig
u
r
e
6
it
ca
n
b
e
s
ee
n
th
at
wh
en
th
e
im
a
g
e
s
eg
m
en
tatio
n
s
tag
e
is
ex
ec
u
ted
th
e
h
ip
p
o
ca
m
p
u
s
o
b
ject
is
s
u
cc
ess
f
u
lly
id
en
tifie
d
o
n
th
e
b
la
ck
c
o
lo
r
ed
wate
r
s
h
ed
lin
e.
T
h
er
e
ar
e
also
o
th
er
o
b
jects
th
at
ar
e
also
id
en
tifie
d
.
T
h
er
ef
o
r
e,
t
h
er
e
a
r
e
o
th
er
wate
r
s
h
ed
lin
es.
T
o
ca
lcu
late
th
e
a
r
ea
o
f
th
e
h
ip
p
o
ca
m
p
u
s
,
th
en
we
d
i
d
cr
o
p
s
o
t
h
at
o
th
e
r
o
b
jects d
o
n
o
t
p
ar
ticip
ate
in
t
h
e
ar
ea
.
At
th
e
id
en
tific
a
tio
n
s
tag
e,
th
e
im
a
g
e
u
s
ed
is
th
e
r
esu
lt
o
f
co
n
v
e
r
s
io
n
to
b
i
n
ar
y
im
ag
e
s
eg
m
e
n
tatio
n
r
esu
l
ts
.
T
h
e
b
in
ar
y
im
a
g
e
th
en
c
o
u
n
ts
th
e
ar
ea
in
p
ix
el
s
ize.
Af
ter
o
b
tain
in
g
th
e
im
a
g
e
ar
ea
,
it
ca
n
b
e
id
e
n
tifie
d
wh
eth
er
th
e
im
ag
e
is
an
im
a
g
e
o
f
a
p
e
r
s
o
n
with
Alzh
eim
er
'
s
o
r
n
o
t
b
ased
o
n
t
h
e
C
DR
lev
el.
Fig
u
r
e
7
an
d
Fig
u
r
e
8
s
h
o
ws
a
g
r
ap
h
o
f
t
h
e
ca
lcu
latio
n
o
f
th
e
av
er
ag
e
v
e
n
tr
icu
lar
a
n
d
h
i
p
p
o
ca
m
p
u
s
ar
ea
b
ased
o
n
g
en
d
e
r
,
ag
e
an
d
C
DR
s
ca
le.
R
ef
er
r
in
g
to
Fig
u
r
e
8
in
f
o
r
m
atio
n
is
o
b
tain
ed
r
e
g
ar
d
in
g
th
e
av
er
ag
e
h
i
p
p
o
ca
m
p
al
ar
ea
b
y
g
en
d
er
,
C
DR
,
an
d
ag
e
class
.
I
n
th
e
a
v
er
ag
e
h
ip
p
o
ca
m
p
al
ar
ea
b
y
g
e
n
d
er
,
t
h
e
av
er
a
g
e
h
i
p
p
o
ca
m
p
a
l
ar
ea
o
f
wo
m
en
is
s
m
aller
th
an
th
at
o
f
m
e
n
.
T
h
e
av
er
ag
e
h
ip
p
o
ca
m
p
al
ar
ea
b
as
ed
o
n
C
DR
s
h
o
ws
th
at
th
e
h
ig
h
er
th
e
C
DR
v
alu
e,
th
e
s
m
aller
th
e
h
ip
p
o
ca
m
p
u
s
ar
ea
.
I
t
is
b
y
th
e
th
eo
r
y
th
at
th
e
h
ig
h
er
th
e
C
DR
v
alu
e,
th
e
s
m
aller
th
e
h
ip
p
o
ca
m
p
u
s
.
T
h
er
ef
o
r
e,
t
h
e
r
ed
u
ctio
n
o
f
th
e
h
ip
p
o
ca
m
p
u
s
i
s
o
n
e
s
ig
n
o
f
Alzh
eim
er
'
s
d
is
ea
s
e.
On
th
e
av
er
a
g
e
h
ip
p
o
ca
m
p
u
s
ar
ea
b
ased
o
n
ag
e
class
,
it c
an
b
e
s
ee
n
th
at
th
e
o
ld
er
a
p
er
s
o
n
is
,
th
e
s
m
aller
th
e
h
ip
p
o
ca
m
p
u
s
is
.
T
h
is
is
f
o
llo
win
g
th
e
ex
is
tin
g
th
eo
r
y
t
h
at
th
e
lo
wer
th
e
h
u
m
an
ag
e,
t
h
e
h
ig
h
er
th
e
li
k
elih
o
o
d
o
f
d
em
en
tia.
Fu
r
th
er
m
o
r
e
,
af
ter
th
e
ar
ea
o
f
th
e
h
ip
p
o
ca
m
p
u
s
o
f
th
e
b
r
ain
,
MRI
im
ag
e
was
ca
lc
u
lated
,
th
e
s
tag
e
o
f
id
en
tific
atio
n
o
f
th
e
C
DR
v
alu
e
was
ca
r
r
ied
o
u
t.
C
DR
v
alu
e
is
u
s
ed
i
n
d
eter
m
in
in
g
th
e
lev
el
o
f
d
e
m
en
tia.
Dete
r
m
in
atio
n
o
f
C
DR
v
alu
e
is
d
o
n
e
u
s
in
g
a
r
tific
ial
n
eu
r
al
n
etwo
r
k
s
.
Fig
u
r
e
7
.
Gr
a
p
h
o
f
th
e
a
v
er
ag
e
v
en
tr
icu
lar
a
r
ea
b
y
g
en
d
er
,
a
g
e
an
d
s
ca
le
o
f
C
DR
Fig
u
r
e
8
.
Gr
a
p
h
o
f
th
e
a
v
er
ag
e
h
ip
p
o
ca
m
p
u
s
ar
ea
b
y
g
en
d
er
,
ag
e
an
d
s
ca
le
o
f
C
DR
T
h
e
ar
ch
itectu
r
al
f
o
r
m
o
f
th
e
b
ac
k
p
r
o
p
ag
atio
n
ANN
u
s
ed
i
n
th
is
s
tu
d
y
is
1
-
2
-
1
wh
ich
co
n
s
is
ts
o
f
1
in
p
u
t,
two
h
id
d
en
la
y
er
s
,
an
d
o
n
e
o
u
tp
u
t.
I
n
th
is
ex
p
e
r
im
en
t
,
we
u
s
e
th
e
b
in
ar
y
s
ig
m
o
id
ac
tiv
atio
n
f
u
n
ctio
n
in
th
e
h
id
d
en
lay
er
an
d
th
e
lin
ea
r
ac
tiv
atio
n
f
u
n
ctio
n
at
th
e
o
u
tp
u
t
lay
er
.
W
h
ile
th
e
tr
ain
in
g
f
u
n
ctio
n
u
s
es
th
e
g
r
ad
ien
t
d
escen
t
m
eth
o
d
.
T
h
e
weig
h
t
v
alu
e
u
s
ed
is
r
an
d
o
m
.
T
ab
le
1
s
h
o
ws
th
e
r
esu
lts
o
f
id
en
tify
in
g
C
DR
v
alu
es f
o
r
b
r
ain
MRI
im
ag
es t
h
at
wer
e
u
s
ed
as test d
ata
in
th
is
ex
p
er
im
en
t.
T
ab
le
1
it c
a
n
b
e
s
ee
n
th
at
th
e
p
r
o
ce
s
s
o
f
id
en
tif
y
in
g
C
DR
h
as satis
f
ac
to
r
y
p
er
f
o
r
m
a
n
ce
.
Fr
o
m
4
0
test
d
ata,
th
e
s
y
s
tem
ca
n
r
ec
o
g
n
iz
e
C
DR
v
alu
es
ac
cu
r
ately
f
o
r
3
9
im
ag
es.
Fo
llo
win
g
ar
e
th
e
p
er
f
o
r
m
a
n
ce
ca
lcu
latio
n
:
39
40
×
100%
=
97
,
5%
As
we
s
ta
ted
in
th
e
s
u
b
s
ec
tio
n
ab
o
v
e
,
th
at
o
u
r
p
r
ev
i
o
u
s
r
e
s
ea
r
ch
tr
ied
to
u
s
e
th
e
ac
tiv
e
co
n
to
u
r
m
eth
o
d
t
o
s
eg
m
en
t
th
e
h
ip
p
o
ca
m
p
u
s
an
d
v
en
tr
ic
u
lar
a
r
ea
s
to
ca
lcu
late
th
e
a
r
ea
.
C
o
m
p
ar
is
o
n
o
f
id
e
n
tific
atio
n
r
esu
lts
is
s
h
o
wn
in
T
ab
le
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
19
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
1
:
6
3
-
72
70
T
ab
le
1
.
R
esu
lts
o
f
id
en
tific
ati
o
n
o
f
C
DR
v
alu
es
NO
ID
M
A
LE
/
F
E
M
A
LE
A
g
e
C
D
R
I
d
e
n
t
i
f
i
c
a
t
i
o
n
R
e
s
u
l
t
1
O
A
S
1
_
0
0
0
1
_
M
R
1
F
74
0
0
2
O
A
S
1
_
0
0
0
2
_
M
R
1
F
55
0
0
3
O
A
S
1
_
0
0
1
1
_
M
R
1
F
52
0
0
4
O
A
S
1
_
0
0
1
9
_
M
R
1
F
89
0
0
5
O
A
S
1
_
0
0
2
0
_
M
R
1
F
48
0
0
6
O
A
S
1
_
0
0
2
6
_
M
R
1
F
58
0
0
7
O
A
S
1
_
0
0
3
0
_
M
R
1
F
65
0
0
8
O
A
S
1
_
0
0
3
3
_
M
R
1
F
80
0
0
9
O
A
S
1
_
0
0
4
4
_
M
R
1
F
47
0
0
10
O
A
S
1
_
0
0
5
8
_
M
R
1
F
46
0
0
11
O
A
S
1
_
0
0
1
0
_
M
R
1
M
74
0
0
12
O
A
S
1
_
0
0
1
8
_
M
R
1
M
39
0
0
13
O
A
S
1
_
0
0
3
4
_
M
R
1
M
51
0
0
14
O
A
S
1
_
0
0
6
5
_
M
R
1
M
90
0
0
15
O
A
S
1
_
0
0
6
9
_
M
R
1
M
33
0
0
16
O
A
S
1
_
0
0
7
4
_
M
R
1
M
43
0
0
17
O
A
S
1
_
0
1
1
0
_
M
R
1
M
84
0
0
18
O
A
S
1
_
0
1
1
4
_
M
R
1
M
62
0
0
19
O
A
S
1
_
0
1
3
0
_
M
R
1
M
68
0
0
20
O
A
S
1
_
0
1
3
5
_
M
R
1
M
64
0
0
21
O
A
S
1
_
0
0
3
5
_
M
R
1
F
84
1
1
22
O
A
S
1
_
0
0
5
2
_
M
R
1
F
78
1
1
23
O
A
S
1
_
0
0
5
3
_
M
R
1
F
83
1
1
24
O
A
S
1
_
0
0
5
6
_
M
R
1
F
72
1
1
25
O
A
S
1
_
0
0
6
7
_
M
R
1
F
71
1
1
26
O
A
S
1
_
0
1
8
4
_
M
R
1
F
65
1
1
27
O
A
S
1
_
0
2
6
9
_
M
R
1
F
72
1
1
28
O
A
S
1
_
0
3
1
6
_
M
R
1
F
72
1
1
29
O
A
S
1
_
0
3
8
2
_
M
R
1
F
67
1
1
30
O
A
S
1
_
0
0
3
1
_
M
R
1
M
88
1
1
31
O
A
S
1
_
0
1
3
4
_
M
R
1
M
80
1
1
32
O
A
S
1
_
0
2
2
3
_
M
R
1
M
84
1
1
33
O
A
S
1
_
0
2
6
8
_
M
R
1
M
78
1
1
34
O
A
S
1
_
0
3
9
9
_
M
R
1
M
78
1
1
35
O
A
S
1
_
0
4
0
5
_
M
R
1
M
77
1
1
36
O
A
S
1
_
0
4
2
4
_
M
R
1
M
75
1
1
37
O
A
S
1
_
0
4
3
0
_
M
R
1
M
71
1
1
38
O
A
S
1
_
0
4
5
2
_
M
R
1
M
75
1
1
39
O
A
S
1
_
0
3
0
8
_
M
R
1
F
78
2
2
40
O
A
S
1
_
0
3
5
1
_
M
R
1
M
86
2
1
T
ab
le
2
.
Per
f
o
r
m
an
ce
co
m
p
a
r
is
o
n
b
etwe
en
s
eg
m
en
tatio
n
o
f
ac
tiv
e
co
n
to
u
r
m
eth
o
d
an
d
wa
ter
s
h
ed
m
eth
o
d
No
M
e
t
h
o
d
P
e
r
f
o
r
ma
n
c
e
1
A
c
t
i
v
e
C
o
n
t
o
u
r
9
3
.
7
5
%
2
W
a
t
e
r
s
h
e
d
9
7
.
5
%
4.
CO
NCLU
SI
O
N
C
o
n
tr
ast
v
alu
es
ar
e
in
f
lu
en
ci
n
g
Seg
m
en
tatio
n
u
s
in
g
th
e
wate
r
s
h
ed
m
eth
o
d
.
W
ater
s
h
e
d
lin
e
th
at
ap
p
ea
r
s
af
ter
th
e
wate
r
s
h
ed
s
eg
m
en
tatio
n
p
r
o
ce
s
s
is
r
u
n
in
d
icate
s
an
o
b
ject
th
at
h
as
b
ee
n
s
u
cc
ess
f
u
lly
s
eg
m
en
ted
b
y
s
ep
ar
atin
g
th
e
s
eg
m
en
tatio
n
ar
ea
u
s
in
g
lin
es.
T
h
e
av
er
ag
e
h
i
p
p
o
ca
m
p
u
s
ar
e
a
o
f
th
e
MRI
im
ag
e
o
f
th
e
b
r
ain
o
f
d
em
e
n
tia
p
atien
ts
is
s
m
aller
th
an
th
at
o
f
th
e
MRI
im
ag
e
o
f
a
h
ea
lth
y
p
er
s
o
n
'
s
b
r
ain
.
T
h
e
a
v
er
ag
e
h
ip
p
o
ca
m
p
u
s
ar
ea
o
f
th
e
MRI
im
ag
e
o
f
th
e
h
u
m
an
b
r
ain
o
v
er
5
0
y
ea
r
s
is
s
m
aller
th
an
th
o
s
e
u
n
d
er
5
0
y
ea
r
s
.
T
h
e
r
esu
lts
o
f
wate
r
s
h
ed
s
eg
m
en
tatio
n
o
f
v
en
tr
icles
an
d
h
ip
p
o
ca
m
p
u
s
d
o
n
o
t
h
a
v
e
1
0
0
%
ac
cu
r
ac
y
o
r
p
er
f
o
r
m
an
ce
r
eg
ar
d
in
g
d
etec
ti
n
g
th
e
ac
tu
al
s
h
a
p
e,
b
u
t
al
r
ea
d
y
h
a
v
e
a
r
ea
s
o
n
ab
l
y
g
o
o
d
ac
cu
r
ac
y
o
r
p
er
f
o
r
m
an
ce
co
m
p
ar
ed
to
th
e
ac
tiv
e
co
n
to
u
r
m
eth
o
d
we
h
av
e
d
o
n
e
b
ef
o
r
e
.
Fo
r
f
u
r
th
e
r
r
esear
c
h
,
it
is
ex
p
ec
ted
to
b
e
a
b
le
to
f
in
d
th
e
v
o
lu
m
e
o
f
th
e
h
ip
p
o
c
am
p
u
s
an
d
v
en
tr
icu
lar
b
y
wat
er
s
h
ed
s
eg
m
en
tatio
n
m
eth
o
d
s
o
th
at
it
ca
n
b
e
u
s
ed
as a
n
o
th
er
r
e
f
er
en
ce
to
d
eter
m
in
e
th
e
lev
el
o
f
d
em
e
n
tia.
ACK
NO
WL
E
DG
E
M
E
NT
S
W
e
T
h
an
k
th
e
Op
e
n
Acc
ess
Se
r
ies
o
f
I
m
ag
in
g
Stu
d
ies
(
OASI
S)
d
atasets
an
d
i
n
th
e
ass
o
ciate
d
Pu
b
Me
d
C
en
tr
al
s
u
b
m
is
s
io
n
:
P5
0
AG0
5
6
8
1
,
P0
1
AG0
3
9
9
1
,
R
0
1
A
G0
2
1
9
1
0
,
P5
0
MH
0
7
1
6
1
6
,
U2
4
R
R
0
2
1
3
8
2
,
R
0
1
MH
5
6
5
8
4
.
T
h
ese
wo
r
k
s
a
r
e
s
u
p
p
o
r
ted
b
y
t
h
e
Dir
ec
to
r
ate
o
f
R
esear
ch
an
d
C
o
m
m
u
n
ity
S
er
v
ice,
Min
is
tr
y
o
f
R
esear
ch
an
d
T
ec
h
n
o
lo
g
y
I
n
d
o
n
esia th
r
o
u
g
h
“Fu
n
d
am
en
tal
R
esaer
ch
”
Sch
em
e
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
C
o
r
o
n
a
l sli
ce
s
eg
men
ta
tio
n
u
s
in
g
a
w
a
ters
h
ed
meth
o
d
fo
r
ea
r
ly
id
en
tifi
ca
tio
n
o
f
… (
R
etn
o
S
u
p
r
iya
n
ti
)
71
RE
F
E
R
E
NC
E
S
[1
]
G
.
M
c
Kh
a
n
n
,
D.
Dra
c
h
m
a
n
,
M
.
F
o
lstein
,
R.
Ka
tzm
a
n
,
D.
P
rice
,
a
n
d
E.
M
.
S
tad
la
n
,
“
Cli
n
ica
l
d
ia
g
n
o
sis
o
f
Alz
h
e
ime
r’s
d
ise
a
se
:
Re
p
o
rt
o
f
th
e
NIN
CDS
-
AD
RDA
Wo
rk
G
ro
u
p
u
n
d
e
r
t
h
e
a
u
sp
ice
s
o
f
De
p
a
rtme
n
t
o
f
He
a
l
th
a
n
d
Hu
m
a
n
S
e
rv
ice
s T
a
sk
F
o
rc
e
o
n
Alz
h
e
ime
r’s Dise
a
se
,
”
Ne
u
ro
lo
g
y
,
v
o
l.
3
4
,
p
p
.
9
3
9
–
9
4
4
,
1
9
8
4
.
[2
]
Ra
fa
e
l
C.
G
o
n
z
a
lez
a
n
d
Rich
a
rd
E.
Wo
o
d
s,
"
Di
g
it
a
l
Im
a
g
e
P
ro
c
e
ss
in
g
,
"
3
rd
e
d
it
io
n
.
Ne
w
Je
rse
y
:
Pre
n
ti
c
e
Ha
ll
,
2
0
0
8
.
[3
]
J.
M
o
rris,
“
T
h
e
Cli
n
ica
l
De
m
e
n
ti
a
Ra
ti
n
g
(CDR):
c
u
rre
n
t
v
e
r
sio
n
a
n
d
sc
o
ri
n
g
r
u
les
.
,
”
Ne
u
r
o
lo
g
y
,
v
o
l.
4
3
,
p
p
.
2
4
1
2
b
-
2
4
1
4
b
,
1
9
9
3
.
[4
]
I.
G
.
Zu
b
a
l,
M
.
Early
,
O.
Y
u
a
n
,
D.
Je
n
n
in
g
s,
K.
M
a
re
k
,
a
n
d
J.
P
.
S
e
ib
y
l
,
“
Op
ti
m
ize
d
,
Au
t
o
m
a
ted
S
tri
a
tal
Up
tak
e
An
a
ly
sis
Ap
p
li
e
d
t
o
S
P
ECT
Bra
i
n
S
c
a
n
s
o
f
P
a
rk
i
n
so
n
’s
Dise
a
se
P
a
t
ien
ts,”
J
.
Nu
c
l.
M
e
d
.
,
v
o
l.
4
8
,
n
o
.
6
,
p
p
.
8
5
7
-
8
6
4
,
2
0
0
7
.
[5
]
S
.
Yu
,
S
.
W
u
,
L
.
Wan
g
,
F
.
Jia
n
g
,
Y.
Xie
,
a
n
d
L
.
Li
,
“
A
sh
a
ll
o
w
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
two
r
k
fo
r
b
l
in
d
ima
g
e
sh
a
rp
n
e
ss
a
ss
e
ss
m
e
n
t,
”
PL
o
S
O
n
e
, v
o
l.
1
2
,
n
o
.
5
,
p
p
.
1
-
1
7
,
2
0
1
7
.
[6
]
E.
F
.
Ia
n
n
e
tt
i
,
J.
A.
M
.
S
m
e
it
in
k
,
J
.
Be
y
ra
th
,
P
.
H.
G
.
M
.
Wi
l
lem
s,
a
n
d
W
.
J.
H.
Ko
o
p
m
a
n
,
“
M
u
lt
i
p
lex
e
d
h
i
g
h
-
c
o
n
ten
t
a
n
a
ly
sis
o
f
m
it
o
c
h
o
n
d
rial
m
o
rp
h
o
fu
n
c
ti
o
n
u
sin
g
li
v
e
-
c
e
ll
m
icro
sc
o
p
y
,
”
N
a
t.
Pro
t
o
c
.
,
v
o
l.
1
1
,
n
o
.
9
,
p
p
.
1
6
9
3
-
1
7
1
0
,
2
0
1
6
.
[7
]
Y.
Da
i,
Y.
Wan
g
,
L.
Wa
n
g
,
G
.
Wu
,
F
.
S
h
i,
a
n
d
D.
S
h
e
n
,
“
a
BEAT:
A
To
o
l
b
o
x
f
o
r
C
o
n
siste
n
t
An
a
ly
si
s
o
f
L
o
n
g
it
u
d
i
n
a
l
Ad
u
lt
Bra
i
n
M
RI
,
”
PL
o
S
O
n
e
,
v
o
l.
8
,
n
o
.
4
,
2
0
1
3
.
[8
]
P
.
Ka
lav
a
th
i
a
n
d
V.
B.
S
.
P
ra
sa
th
,
“
M
e
th
o
d
s
o
n
S
k
u
ll
S
tr
ip
p
in
g
o
f
M
RI
He
a
d
S
c
a
n
Im
a
g
e
s
—
a
R
e
v
iew
,
”
J
.
Dig
it
.
Ima
g
i
n
g
,
v
o
l.
2
9
,
n
o
.
3
,
p
p
.
3
6
5
-
3
7
9
,
2
0
1
6
.
[9
]
S
.
M
.
Lan
d
a
u
,
e
t
a
l
.
,
“
Am
y
lo
i
d
P
ET
ima
g
in
g
i
n
Alz
h
e
ime
r’s
d
ise
a
se
:
A
c
o
m
p
a
riso
n
o
f
th
re
e
ra
d
io
tr
a
c
e
rs,”
Eu
r.
J
.
Nu
c
l.
M
e
d
.
M
o
l.
Ima
g
in
g
,
v
o
l
.
4
1
,
n
o
.
7
,
p
p
.
1
3
9
8
-
1
4
0
7
,
2
0
1
4
.
[1
0
]
S
.
F
.
Esk
il
d
se
n
,
P
.
Co
u
p
é
,
D.
G
a
r
c
ía
-
Lo
re
n
z
o
,
V.
F
o
n
o
v
,
J.
C.
P
ru
e
ss
n
e
r,
a
n
d
D.
L.
Co
ll
in
s,
“
P
re
d
ictio
n
o
f
Alz
h
e
ime
r’s
d
ise
a
se
in
su
b
jec
ts
with
m
il
d
c
o
g
n
i
ti
v
e
imp
a
irme
n
t
fro
m
th
e
AD
NI
c
o
h
o
rt
u
sin
g
p
a
t
tern
s
o
f
c
o
rti
c
a
l
th
in
n
in
g
,
”
Ne
u
r
o
ima
g
e
,
v
o
l.
6
5
,
p
p
.
5
1
1
-
5
2
1
,
2
0
1
3
.
[1
1
]
Y.
Zh
a
n
g
a
n
d
S
.
Wan
g
,
“
De
tec
ti
o
n
o
f
Alz
h
e
ime
r’s
d
ise
a
se
b
y
d
i
sp
lac
e
m
e
n
t
field
a
n
d
m
a
c
h
in
e
le
a
rn
in
g
,
”
Pee
rJ
,
v
o
l.
3
,
2
0
1
5
.
[1
2
]
N.
Ro
b
it
a
il
le,
A.
M
o
u
ih
a
,
B.
Cré
p
e
a
u
lt
,
F
.
Va
ld
i
v
ia,
a
n
d
S
.
Du
c
h
e
s
n
e
,
“
Ti
ss
u
e
-
b
a
se
d
M
RI
in
ten
si
ty
s
tan
d
a
rd
iza
ti
o
n
:
Ap
p
li
c
a
ti
o
n
t
o
m
u
l
ti
c
e
n
tri
c
d
a
tas
e
ts,”
In
t.
J
.
Bi
o
me
d
.
Ima
g
in
g
,
v
o
l.
2
0
1
2
,
2
0
1
2
.
[1
3
]
C.
Y.
Li
u
,
J.
E.
Ig
les
ias
,
a
n
d
Z.
T
u
,
“
De
fo
rm
a
b
le
tem
p
late
s
g
u
i
d
e
d
d
isc
rimin
a
ti
v
e
m
o
d
e
ls
fo
r
r
o
b
u
st
3
D
b
ra
i
n
M
RI
se
g
m
e
n
tatio
n
,
”
Ne
u
r
o
in
fo
rm
a
t
ics
,
v
o
l
.
1
1
,
n
o
.
4
,
p
p
.
4
4
7
-
4
6
8
,
2
0
1
3
.
[1
4]
S
.
R.
Da
s
,
e
t
a
l.
,
“
M
e
a
su
rin
g
l
o
n
g
it
u
d
in
a
l
c
h
a
n
g
e
in
t
h
e
h
ip
p
o
c
a
m
p
a
l
fo
rm
a
ti
o
n
fro
m
in
v
iv
o
h
i
g
h
-
re
so
lu
t
io
n
T2
-
we
ig
h
ted
M
RI,
”
Ne
u
ro
im
a
g
e
,
v
o
l
.
6
0
,
n
o
.
2
,
p
p
.
1
2
6
6
-
1
2
7
9
,
2
0
1
2
.
[1
5
]
S
.
Ve
rc
ly
tt
e
,
R.
Lo
p
e
s,
C.
De
lma
ire,
J.
C.
F
e
rre
,
F
.
P
a
sq
u
ier,
a
n
d
X.
Lec
lerc
,
“
Op
ti
m
iza
ti
o
n
o
f
b
ra
i
n
p
e
rfu
sio
n
ima
g
e
q
u
a
li
t
y
b
y
c
o
rti
c
a
l
su
rfa
c
e
-
b
a
se
d
p
ro
jec
ti
o
n
o
f
a
rteria
l
sp
in
lab
e
li
n
g
m
a
p
s
in
e
a
rly
-
o
n
se
t
Alz
h
e
ime
r’s
d
ise
a
s
e
p
a
ti
e
n
ts,”
E
u
r.
R
a
d
i
o
l.
,
v
o
l.
2
5
,
n
o
.
8
,
p
p
.
2
4
7
9
-
2
4
8
4
,
2
0
1
5
.
[1
6
]
M
.
E.
Os
a
d
e
b
e
y
,
M
.
P
e
d
e
rse
n
,
D
.
L
.
Arn
o
ld
,
a
n
d
K.
E.
Wen
d
e
l
-
M
it
o
ra
j,
“
S
tan
d
a
rd
ize
d
q
u
a
li
ty
m
e
tri
c
sy
ste
m
fo
r
stru
c
tu
ra
l
b
ra
in
m
a
g
n
e
t
ic
re
so
n
a
n
c
e
ima
g
e
s
in
m
u
lt
i
-
c
e
n
ter
n
e
u
ro
i
m
a
g
in
g
st
u
d
y
,
”
B
M
C
M
e
d
.
Ima
g
i
n
g
,
v
o
l.
1
8
,
n
o
.
1
,
p
p
.
1
-
2
0
,
2
0
1
8
.
[1
7
]
K.
R.
G
ra
y
,
R.
Wo
lz,
R.
A.
He
c
k
e
m
a
n
n
,
P
.
Alja
b
a
r,
A
.
Ha
m
m
e
rs,
a
n
d
D.
Ru
e
c
k
e
rt,
“
M
u
lt
i
-
re
g
io
n
a
n
a
l
y
sis
o
f
lo
n
g
it
u
d
i
n
a
l
F
DG
-
P
ET
fo
r
th
e
c
las
sifica
ti
o
n
o
f
Alz
h
e
ime
r’s
d
ise
a
se
,
”
Ne
u
ro
ima
g
e
,
v
o
l.
6
0
,
n
o
.
1
,
p
p
.
2
2
1
-
2
2
9
,
2
0
1
2
.
[1
8
]
A.
Ortiz,
J.
M
.
G
ó
rriz,
J.
Ra
m
írez
,
F
.
J.
M
a
rti
n
e
z
-
M
u
rc
ia,
a
n
d
,
Alz
h
e
ime
r’
s
Dise
a
s
e
Ne
u
ro
ima
g
in
g
In
it
iativ
e
,
“
Au
to
m
a
ti
c
{ROI}
S
e
lec
ti
o
n
i
n
S
t
ru
c
tu
ra
l
Bra
in
{M
RI}
Us
in
g
{S
O
M
}
{
3
D}
P
r
o
jec
ti
o
n
.
,
”
{PL
o
S
}
O
n
e
,
v
o
l
.
9
,
n
o
.
4
,
2
0
1
4
.
[1
9
]
M
.
Kh
a
jeh
n
e
jad
,
F
.
H.
S
a
a
tl
o
u
,
a
n
d
H
.
M
o
h
a
m
m
a
d
z
a
d
e
,
“
Alz
h
e
ime
r’s d
ise
a
se
e
a
rly
d
iag
n
o
sis
u
sin
g
m
a
n
i
fo
ld
-
b
a
se
d
se
m
i
-
su
p
e
rv
ise
d
lea
rn
i
n
g
,
”
Br
a
in
S
c
i.
,
v
o
l
.
7
,
n
o
.
8
,
p
p
.
1
-
2
0
,
2
0
1
7
.
[2
0
]
M
.
Hu
a
n
g
,
W.
Ya
n
g
,
Q.
F
e
n
g
,
a
n
d
E.
All,
“
L
o
n
g
it
u
d
i
n
a
l
m
e
a
su
re
m
e
n
t
a
n
d
h
iera
rc
h
ica
l
c
las
sifica
ti
o
n
fra
m
e
wo
rk
fo
r
th
e
p
re
d
ictio
n
o
f
Alz
h
e
ime
r’s d
is
e
a
se
,
”
S
c
i.
Rep
.
,
v
o
l
.
7
,
n
o
.
N
o
v
e
m
b
e
r
2
0
1
6
,
p
p
.
1
-
1
4
,
2
0
1
7
.
[2
1
]
Y.
M
a
h
e
n
d
ra
d
h
a
ta
,
e
t
a
l
.
,
"
Th
e
Re
p
u
b
li
c
o
f
I
n
d
o
n
e
sia
He
a
lt
h
S
y
ste
m
Re
v
iew
,
"
W
o
rld
He
a
lt
h
Or
g
a
n
i
za
ti
o
n
,
Reg
i
o
n
a
l
Offi
c
e
fo
r S
o
u
t
h
-
E
a
st A
sia
,
v
o
l.
7
,
n
o
.
1
,
2
0
1
7
.
[2
2
]
A.
M
u
n
e
e
r,
S
.
M
.
F
a
ti
,
a
n
d
S
.
F
u
d
d
a
h
,
“
S
m
a
rt
h
e
a
lt
h
m
o
n
it
o
ri
n
g
sy
ste
m
u
sin
g
I
o
T
b
a
se
d
sm
a
rt
f
it
n
e
ss
m
irro
r
,
”
T
EL
KOM
NIKA
T
e
lec
o
mm
u
n
ic
a
ti
o
n
C
o
mp
u
ti
n
g
El
e
c
tro
n
ics
a
n
d
Co
n
tro
l
,
v
o
l
.
1
8
,
n
o
.
1
,
p
p
.
3
1
7
-
3
3
1
,
2
0
2
0
.
[2
3
]
H.
Wi
b
o
wo
,
E.
M
.
Y
u
n
iarn
o
,
A
.
Wi
d
a
y
a
ti
,
a
n
d
M
.
H.
P
u
rn
o
m
o
,
“
F
ro
n
talis
m
u
sc
le
stre
n
g
t
h
c
a
lcu
lat
io
n
b
a
se
d
o
n
3
D
ima
g
e
u
sin
g
G
ra
y
Lev
e
l
Co
-
o
c
c
u
rre
n
c
e
M
a
tri
x
(G
LCM
)
a
n
d
c
o
n
fi
d
e
n
c
e
in
ter
v
a
l,
”
T
EL
KOM
NIK
A
T
e
lec
o
mm
u
n
ica
ti
o
n
Co
mp
u
ti
n
g
E
lec
tro
n
ics
a
n
d
C
o
n
tr
o
l
,
v
o
l
.
1
6
,
n
o
.
1
,
p
p
.
3
6
8
-
3
7
5
,
2
0
1
8
.
[2
4
]
S
.
Wi
d
o
d
o
,
R.
N.
R
o
h
m
a
h
,
B
.
Ha
n
d
a
g
a
,
a
n
d
L.
D.
D.
Arin
i,
“
Lu
n
g
d
ise
a
se
s
d
e
tec
ti
o
n
c
a
u
se
d
b
y
sm
o
k
in
g
u
si
n
g
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
,
”
T
EL
K
OM
NIKA
T
e
lec
o
mm
u
n
ica
ti
o
n
C
o
mp
u
ti
n
g
El
e
c
tro
n
ics
a
n
d
Co
n
tro
l
,
v
o
l.
1
7
,
n
o
.
3
,
p
p
.
1
2
5
6
-
1
2
6
6
,
2
0
1
9
.
[2
5
]
M
.
H.
M
e
m
o
n
,
T
.
J.
S
.
Kh
a
n
z
a
d
a
,
S
.
M
e
m
o
n
,
a
n
d
S
.
R.
Ha
ss
a
n
,
“
Blo
o
d
ima
g
e
a
n
a
ly
sis
to
d
e
tec
t
m
a
lari
a
u
sin
g
fi
lt
e
rin
g
ima
g
e
e
d
g
e
s
a
n
d
c
las
sifica
ti
o
n
,
”
T
EL
KOM
NIKA
T
e
lec
o
mm
u
n
ica
ti
o
n
Co
mp
u
ti
n
g
El
e
c
tro
n
ics
a
n
d
C
o
n
tro
l
,
v
o
l.
1
7
,
n
o
.
1
,
p
p
.
1
9
4
-
2
0
1
,
2
0
1
9
.
[2
6
]
R.
S
u
p
riy
a
n
ti
,
S
.
A.
P
riy
o
n
o
,
E.
M
u
rd
y
a
n
t
o
ro
,
a
n
d
H.
B.
Wi
d
o
d
o
,
“
Histo
g
ra
m
Eq
u
a
li
z
a
ti
o
n
f
o
r
Im
p
r
o
v
i
n
g
Q
u
a
li
ty
o
f
Lo
w
-
Re
so
lu
t
io
n
Ultras
o
n
o
g
ra
p
h
y
Im
a
g
e
s,”
T
EL
KOM
NIKA
T
e
lec
o
m
mu
n
ica
t
io
n
Co
m
p
u
ti
n
g
El
e
c
tro
n
ic
s
a
n
d
Co
n
tro
l
,
v
o
l.
1
5
,
n
o
.
3
,
p
p
.
1
3
9
7
-
1
4
0
8
,
2
0
1
7
.
[2
7
]
R.
S
u
p
riy
a
n
ti
,
A.
R.
S
u
b
h
i,
Y
.
Ra
m
a
d
h
a
n
i,
a
n
d
H.
B
.
Wi
d
o
d
o
,
“
Ca
lcu
latin
g
Ve
n
tri
c
le’s
Are
a
b
a
se
d
o
n
Cli
n
ica
l
De
m
e
n
ti
a
Ra
ti
n
g
(CDR)
Va
l
u
e
s
o
n
C
o
ro
n
a
l
M
RI
ima
g
e
,
”
2
0
th
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
C
o
mp
u
ter
-
Ba
se
d
Pa
ti
e
n
t
Rec
o
rd
s a
n
d
Err
o
r P
re
v
e
n
ti
o
n
(I
CCPR
EP
)
,
2
0
1
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
19
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
1
:
6
3
-
72
72
[2
8
]
R.
Bu
c
k
n
e
r
,
e
t
a
l.
,
“
A
u
n
ifi
e
d
a
p
p
ro
a
c
h
f
o
r
m
o
r
p
h
o
m
e
tri
c
a
n
d
fu
n
c
t
io
n
a
l
d
a
ta
a
n
a
l
y
sis
i
n
y
o
u
n
g
,
o
l
d
,
a
n
d
d
e
m
e
n
ted
a
d
u
lt
s
u
sin
g
a
u
to
m
a
ted
a
tl
a
s
-
b
a
se
d
h
e
a
d
siz
e
n
o
rm
a
li
z
a
ti
o
n
:
re
li
a
b
i
li
ty
a
n
d
v
a
li
d
a
ti
o
n
a
g
a
in
st
m
a
n
u
a
l
m
e
a
su
re
m
e
n
t
o
f
to
tal
in
trac
ra
n
ial
v
o
lu
m
e
.
,
”
Ne
u
ro
ima
g
e
,
v
o
l.
2
3
,
p
p
.
7
2
4
-
7
3
8
,
2
0
0
4
.
[2
9
]
E.
Ru
b
i
n
,
e
t
a
l
.
,
“
A
p
ro
s
p
e
c
ti
v
e
stu
d
y
o
f
c
o
g
n
it
i
v
e
fu
n
c
ti
o
n
a
n
d
o
n
se
t
o
f
d
e
m
e
n
ti
a
in
c
o
g
n
it
iv
e
l
y
h
e
a
lt
h
y
e
ld
e
rs.,
”
Arc
h
Ne
u
ro
l
,
v
o
l.
5
5
,
p
p
.
3
9
5
-
4
0
1
,
1
9
9
8
.
[3
0
]
Y.
Zh
a
n
g
,
M
.
Bra
d
y
,
a
n
d
S
.
S
m
it
h
,
“
S
e
g
m
e
n
tati
o
n
o
f
b
ra
in
M
R
ima
g
e
s
th
r
o
u
g
h
a
h
i
d
d
e
n
M
a
r
k
o
v
ra
n
d
o
m
field
m
o
d
e
l
a
n
d
t
h
e
e
x
p
e
c
tatio
n
m
a
x
imiz
a
ti
o
n
a
lg
o
rit
h
m
,
”
IEE
E
T
ra
n
s.
M
e
d
.
I
ma
g
in
g
,
v
o
l.
2
0
,
n
o
.
1
,
p
p
.
4
5
-
5
7
,
2
0
0
1
.
[3
1
]
A.
F
o
ten
o
s,
A.
S
n
y
d
e
r,
L.
G
irt
o
n
,
J.
M
o
rris,
a
n
d
R.
B
u
c
k
n
e
r,
“
No
rm
a
ti
v
e
e
stim
a
tes
o
f
c
ro
ss
-
se
c
ti
o
n
a
l
a
n
d
lo
n
g
it
u
d
in
a
l
b
ra
in
v
o
l
u
m
e
d
e
c
li
n
e
i
n
a
g
i
n
g
a
n
d
AD
,
”
Ne
u
ro
lo
g
y
,
v
o
l.
6
4
,
p
p
.
1
0
3
2
-
1
0
3
9
,
2
0
0
5
.
[3
2
]
R
.
S
u
p
r
i
y
a
n
t
i
,
e
t
a
l
.
,
“
A
c
t
i
v
e
C
o
n
t
o
u
r
M
e
t
h
o
d
f
o
r
I
d
e
n
t
i
f
y
i
n
g
A
r
e
a
o
f
S
a
g
i
t
t
a
l
a
n
d
A
x
i
a
l
S
l
i
c
e
s
t
o
I
d
e
n
ti
f
y
t
h
e
S
e
v
e
r
i
t
y
o
f
A
l
z
h
e
i
m
e
r’
s
d
i
s
e
a
s
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
R
e
c
e
n
t
A
d
v
a
n
c
e
s
i
n
E
n
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
(
I
C
R
A
E
T
)
,
2
0
1
9
.
[3
3
]
R.
S
u
p
riy
a
n
ti
,
A.
R.
S
u
b
h
i,
Y.
R
a
m
a
d
h
a
n
i,
a
n
d
H.
B.
Wi
d
o
d
o
,
“
Co
ro
n
a
l
slice
s
se
g
m
e
n
tatio
n
o
f
m
ri
ima
g
e
s
u
sin
g
a
c
ti
v
e
c
o
n
to
u
r
m
e
th
o
d
o
n
i
n
it
ial
i
d
e
n
ti
fica
ti
o
n
o
f
a
lzh
e
ime
r
se
v
e
rit
y
lev
e
l
b
a
se
d
o
n
c
li
n
ica
l
d
e
m
e
n
ti
a
ra
ti
n
g
(CDR),
”
J
.
En
g
.
S
c
i.
T
e
c
h
n
o
l.
,
v
o
l.
1
4
,
n
o
.
3
,
p
p
.
1
6
7
2
-
1
6
8
6
,
2
0
1
9
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Re
tn
o
S
u
p
r
iy
a
n
ti
is
a
n
a
c
a
d
e
m
ic
sta
ff
a
t
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
De
p
a
rtme
n
t,
Je
n
d
e
ra
l
S
o
e
d
irma
n
Un
iv
e
rsity
,
In
d
o
n
e
sia
.
S
h
e
re
c
e
iv
e
d
h
e
r
P
h
D i
n
M
a
rc
h
2
0
1
0
fro
m
Na
ra
In
stit
u
te o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
Ja
p
a
n
.
Also
,
sh
e
re
c
e
iv
e
d
h
e
r
M
.
S
d
e
g
r
e
e
a
n
d
Ba
c
h
e
lo
r
d
e
g
re
e
in
2
0
0
1
a
n
d
1
9
9
8
,
re
sp
e
c
ti
v
e
ly
,
fro
m
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
D
e
p
a
rtme
n
t,
G
a
d
jah
M
a
d
a
Un
iv
e
r
sity
In
d
o
n
e
sia
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
l
u
d
e
ima
g
e
p
ro
c
e
ss
in
g
,
c
o
m
p
u
ter
v
isi
o
n
,
p
a
tt
e
rn
re
c
o
g
n
it
i
o
n
,
b
io
m
e
d
ica
l
a
p
p
li
c
a
ti
o
n
,
e
-
h
e
a
lt
h
,
tele
-
h
e
a
lt
h
a
n
d
tele
m
e
d
icin
e
Anu
g
e
r
a
h
K
e
v
i
n
Ma
r
c
h
e
l
re
c
e
iv
e
d
h
is
Ba
c
h
e
l
o
r
d
e
g
re
e
fr
o
m
El
e
c
tri
c
a
l
En
g
in
e
e
ri
n
g
De
p
ra
tme
n
t,
Je
n
d
e
ra
l
S
o
e
d
irma
n
Un
iv
e
rsity
I
n
d
o
n
e
sia
.
His
re
se
a
rc
h
in
tere
st
Im
a
g
e
P
ro
c
e
ss
in
g
field
Yo
g
i
Ra
m
a
d
h
a
n
i
is
a
n
a
c
a
d
e
m
ic
sta
ff
a
t
El
e
c
tri
c
a
l
E
n
g
in
e
e
rin
g
De
p
a
rtme
n
t,
Je
n
d
e
ra
l
S
o
e
d
irma
n
Un
i
v
e
rsity
,
In
d
o
n
e
sia
.
He
re
c
e
iv
e
d
h
is
M
S
G
a
d
jah
M
a
d
a
Un
iv
e
rsirt
In
d
o
n
e
sia
,
a
n
d
h
is
Ba
c
h
e
lo
r
d
e
g
re
e
fr
o
m
Je
n
d
e
ra
l
S
o
e
d
irma
n
Un
i
v
e
rsity
I
n
d
o
n
e
sia
.
His
re
se
a
rc
h
in
tere
st
in
c
lu
d
in
g
Co
m
p
u
ter Ne
two
r
k
,
De
c
isio
n
S
u
p
p
o
r
t
S
y
e
tem
,
Tele
m
e
d
icin
e
a
n
d
M
e
d
ica
l
ima
g
in
g
H
a
r
is
Bu
d
i
Wid
o
d
o
is
a
n
a
c
a
d
e
m
ic
sta
ff
a
t
P
u
b
li
c
He
a
lt
h
De
p
a
rt
m
e
n
t,
Je
n
d
e
ra
l
S
o
e
d
irma
n
Un
iv
e
rsity
,
In
d
o
n
e
sia
.
He
re
c
e
iv
e
d
h
is
P
h
.
D
fro
m
Airlan
g
g
a
Un
i
v
e
rsity
In
d
o
n
e
sia
.
Also
He
re
c
e
iv
e
d
h
is
M
.
S
d
e
g
re
e
a
n
d
b
a
c
h
e
lo
r
d
e
g
re
e
fr
o
m
G
a
d
jah
M
a
d
a
Un
iv
e
rsity
In
d
o
n
e
sia
.
His
re
se
a
rc
h
in
tere
st i
n
c
lu
d
in
g
p
u
b
l
ic
h
e
a
lt
h
,
e
-
h
e
a
lt
h
a
n
d
tele
m
e
d
icin
e
Evaluation Warning : The document was created with Spire.PDF for Python.