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.
7
,
No
.
5
,
Octo
b
e
r
2
0
1
7
,
p
p
.
2
5
5
5
~
2
5
6
4
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v7
i
1
.
p
p
2
5
5
5
-
2564
2555
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
l
in
e/in
d
ex
.
p
h
p
/I
JE
C
E
SVM
Clas
sifica
ti
o
n of MRI
Bra
in
I
m
a
g
es for
Co
m
p
uter
-
Ass
isted Diag
no
si
s
M
a
din
a
H
a
m
ia
ne
1
,
F
a
t
e
m
a
Sa
ee
d
2
De
p
a
rt
m
e
n
t
o
f
T
e
le
c
o
m
m
u
n
ica
ti
o
n
En
g
i
n
e
e
rin
g
,
A
h
li
a
Un
iv
e
rsity
,
M
a
n
a
m
a
,
Ba
h
ra
in
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
22
,
2
0
1
6
R
ev
i
s
ed
J
an
11
,
2
0
1
7
A
cc
ep
ted
J
u
l
2
6
,
2
0
1
7
M
a
g
n
e
ti
c
Re
so
n
a
n
c
e
Im
a
g
in
g
is
a
p
o
w
e
rf
u
l
tec
h
n
iq
u
e
t
h
a
t
h
e
lp
s
in
th
e
d
iag
n
o
sis
o
f
v
a
rio
u
s
m
e
d
ica
l
c
o
n
d
it
io
n
s.
M
RI
Im
a
g
e
p
re
-
p
ro
c
e
ss
in
g
f
o
ll
o
we
d
b
y
d
e
tec
ti
o
n
o
f
b
ra
in
a
b
n
o
rm
a
li
ti
e
s,
su
c
h
a
s
b
ra
i
n
t
u
m
o
rs,
a
re
c
o
n
sid
e
re
d
in
th
is
w
o
rk
.
T
h
e
se
i
m
a
g
e
s
a
re
o
f
te
n
c
o
rr
u
p
ted
b
y
n
o
ise
f
ro
m
v
a
rio
u
s
so
u
rc
e
s.
T
h
e
Disc
re
te
Wav
e
let
T
ra
n
s
f
o
r
m
s
(DWT
)
w
it
h
d
e
tails
th
re
sh
o
ld
i
n
g
is
u
se
d
f
o
r
e
ff
icie
n
t
n
o
ise
re
m
o
v
a
l
f
o
ll
o
w
e
d
b
y
e
d
g
e
d
e
tec
ti
o
n
a
n
d
th
re
sh
o
ld
se
g
m
e
n
tatio
n
o
f
th
e
d
e
n
o
ise
d
i
m
a
g
e
s.
S
e
g
m
e
n
ted
i
m
a
g
e
f
e
a
tu
r
e
s
a
re
th
e
n
e
x
trac
ted
u
sin
g
m
o
rp
h
o
l
o
g
ica
l
o
p
e
ra
ti
o
n
s.
T
h
e
se
f
e
a
tu
re
s
a
re
f
in
a
ll
y
u
se
d
to
train
a
n
im
p
ro
v
e
d
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
c
las
sif
ier
th
a
t
u
se
s
a
Ga
u
ss
sia
n
ra
d
ial
b
a
sis
f
u
n
c
ti
o
n
k
e
rn
e
l.
T
h
e
p
e
rf
o
rm
a
n
c
e
o
f
th
e
c
las
si
f
ier
is
e
v
a
l
u
a
ted
a
n
d
t
h
e
re
su
lt
s o
f
th
e
c
las
sif
ica
ti
o
n
sh
o
w
th
a
t
th
e
p
r
o
p
o
se
d
sc
h
e
m
e
a
c
c
u
ra
tel
y
d
isti
n
g
u
is
h
e
s
n
o
rm
a
l
b
ra
in
i
m
a
g
e
s
f
ro
m
th
e
a
b
n
o
rm
a
l
o
n
e
s
a
n
d
b
e
n
ig
n
les
io
n
s
f
ro
m
m
a
li
g
n
a
n
t
tu
m
o
u
rs.
T
h
e
a
c
c
u
ra
c
y
o
f
th
e
c
la
ss
i
f
ica
ti
o
n
is
sh
o
w
n
to
b
e
1
0
0
%
w
h
ich
is
su
p
e
rio
r
t
o
t
h
e
re
su
lt
s rep
o
rted
i
n
t
h
e
li
tera
tu
r
e
.
K
ey
w
o
r
d
:
Dis
cr
ete
w
av
ele
t tr
an
s
f
o
r
m
su
p
p
o
r
t v
ec
to
r
m
ac
h
in
e
C
las
s
i
f
ier
Featu
r
e
ex
tr
ac
tio
n
MRI
b
r
ain
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
I
m
ag
e
s
e
g
m
e
n
tatio
n
Co
p
y
rig
h
t
©
2
0
1
7
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Ma
d
in
a
Ha
m
ian
e
Dep
ar
te
m
en
t o
f
T
elec
o
m
m
u
n
icatio
n
E
n
g
i
n
ee
r
in
g
,
Ah
lia
U
n
i
v
er
s
it
y
,
Ma
n
a
m
a,
Ki
n
g
d
o
m
o
f
B
ah
r
ain
E
m
ail:
m
h
h
a
m
ia
n
e
@
ah
l
ia.
ed
u
.
b
h
1.
I
NT
RO
D
UCT
I
O
N
I
n
th
e
f
ield
o
f
m
ed
ici
n
e,
m
ed
ical
I
m
a
g
e
p
r
o
ce
s
s
i
n
g
an
d
a
n
al
y
s
i
s
h
as
e
x
ce
s
s
i
v
e
s
ig
n
i
f
ica
n
ce
.
I
t
h
as
ar
is
en
a
s
o
n
e
o
f
t
h
e
g
r
ea
tes
t
s
ig
n
i
f
ica
n
t
to
o
ls
to
d
etec
t
as
w
ell
as
id
en
ti
f
y
m
an
y
d
i
s
o
r
d
er
s
.
I
t
en
ab
les
b
o
th
d
o
cto
r
s
an
d
r
ad
io
l
o
g
is
ts
to
r
ea
ch
a
s
p
ec
if
ic
d
ia
g
n
o
s
is
,
b
y
v
is
u
alizi
n
g
a
n
d
an
al
y
zi
n
g
t
h
e
i
m
a
g
e.
C
o
m
p
u
ter
-
Ai
d
ed
Diag
n
o
s
i
s
(
C
A
D)
is
a
m
et
h
o
d
th
at
is
g
ai
n
in
g
i
m
p
o
r
tan
ce
in
t
h
e
d
a
y
-
to
-
d
a
y
li
f
e.
I
t
ca
n
h
elp
r
ad
io
lo
g
is
ts
p
r
ec
is
el
y
r
ea
d
i
m
a
g
e
s
an
d
d
etec
t
p
r
o
b
ab
le
f
i
n
d
in
g
s
to
a
v
o
id
i
m
p
r
o
p
er
u
n
d
er
s
ta
n
d
in
g
o
f
lesi
o
n
s
.
Ho
w
ev
er
,
it
i
s
e
s
s
e
n
ti
al
to
p
o
in
t
o
u
t
th
at
C
AD
s
y
s
te
m
s
ca
n
o
n
l
y
p
r
o
v
id
e
a
s
ec
o
n
d
o
p
in
io
n
a
n
d
ca
n
b
y
n
o
m
ea
n
s
r
ep
lace
r
ad
io
lo
g
is
ts
o
r
p
h
y
s
icia
n
s
.
T
h
er
e
ar
e
m
a
n
y
i
m
a
g
i
n
g
te
ch
n
iq
u
es
f
o
r
th
e
h
u
m
an
s
o
f
t
tis
s
u
e
an
ato
m
y
,
s
u
c
h
as
C
o
m
p
u
ted
T
o
m
o
g
r
ap
h
y
(
C
T
)
,
m
a
m
m
o
g
r
a
m
f
u
n
ct
io
n
,
Ma
g
n
e
tic
R
eso
n
an
ce
I
m
ag
i
n
g
(
MRI)
a
n
d
s
o
o
n
.
T
h
e
f
o
cu
s
o
f
th
i
s
w
o
r
k
i
s
o
n
MRI
i
m
a
g
es.
M
R
I
is
a
m
ed
ical
i
m
a
g
i
n
g
tec
h
n
iq
u
e
th
at
ta
k
es
i
m
a
g
es
o
f
t
h
e
in
s
id
e
o
f
th
e
h
u
m
a
n
b
o
d
y
.
I
t
is
a
p
ain
-
f
r
ee
,
n
o
n
-
ag
g
r
es
s
i
v
e,
n
o
n
-
r
ad
io
ac
tiv
e
tech
n
iq
u
e
f
o
r
v
is
u
aliz
in
g
d
e
tailed
in
f
o
r
m
atio
n
r
eg
ar
d
in
g
t
h
e
t
u
m
o
r
s
a
n
d
a
b
n
o
r
m
alitie
s
w
it
h
o
u
t a
n
y
h
u
m
a
n
i
n
v
o
l
v
e
m
en
t.
I
n
d
ig
ital
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
,
i
m
ag
e
d
e
-
n
o
is
i
n
g
is
a
n
i
m
p
o
r
t
an
t
p
r
o
ce
d
u
r
e
to
o
b
tain
q
u
alit
y
i
m
ag
e
s
,
an
d
en
h
a
n
ce
an
d
r
ec
o
v
er
d
etailed
in
f
o
r
m
a
tio
n
t
h
at
m
i
g
h
t
b
e
h
id
d
en
in
t
h
e
d
ata.
I
t
r
em
o
v
es
th
e
n
o
i
s
e
th
at
i
s
ac
q
u
i
r
ed
b
y
t
h
e
i
m
a
g
e
d
u
r
in
g
its
ac
q
u
i
s
itio
n
o
r
tr
an
s
m
is
s
io
n
.
T
h
is
n
o
is
e
is
a
n
o
b
s
tacle
f
o
r
ef
f
icien
t
i
m
a
g
e
p
r
o
ce
s
s
in
g
s
i
n
ce
it
g
i
v
es
a
p
o
o
r
i
m
ag
e
q
u
al
it
y
.
Me
d
ical
i
m
ag
e
s
ar
e
a
ls
o
co
r
r
u
p
ted
by
n
o
is
e
th
at
lo
w
er
s
th
e
v
is
ib
il
it
y
o
f
lo
w
co
n
tr
a
s
t
o
b
j
ec
ts
a
n
d
cr
ea
te
s
u
n
d
esira
b
le
v
is
u
al
q
u
alit
y
.
T
h
e
d
e
-
n
o
is
i
n
g
p
r
o
ce
s
s
f
ac
ilit
ate
s
t
h
e
i
m
a
g
e
class
if
icatio
n
ac
c
u
r
ac
y
an
d
en
h
a
n
ce
s
th
e
m
ed
ical
d
iag
n
o
s
is
.
T
h
e
o
b
j
ec
tiv
e
o
f
t
h
i
s
w
o
r
k
is
to
p
r
o
v
id
e
a
n
a
u
to
m
atic
d
iag
n
o
s
t
ic
to
o
l
t
h
at
w
i
ll
h
el
p
m
ed
ical
p
r
ac
titi
o
n
er
s
in
d
ia
g
n
o
s
in
g
b
r
a
in
les
io
n
s
b
y
d
is
ti
n
g
u
i
s
h
in
g
t
h
e
m
f
r
o
m
n
o
r
m
al
b
r
ain
t
is
s
u
e.
T
h
e
f
ir
s
t
s
tep
i
s
to
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
5
,
Octo
b
er
2
0
1
7
:
2
5
5
5
–
2
5
6
4
2556
en
h
a
n
ce
t
h
e
MRI
I
m
a
g
es
b
y
d
ev
elo
p
in
g
th
eir
ap
p
ea
r
an
ce
an
d
r
em
o
v
in
g
t
h
e
u
n
u
s
u
a
l
p
atter
n
s
ca
u
s
ed
b
y
n
o
i
s
e
f
r
o
m
th
e
i
n
ter
f
er
e
n
ce
o
f
d
if
f
e
r
en
t
s
o
u
r
ce
s
.
T
h
is
w
ill
r
esu
l
t
in
an
alter
n
at
iv
e
i
m
ag
e
w
i
th
en
h
a
n
ce
d
an
d
m
o
r
e
n
o
ticea
b
l
y
s
tr
u
ctu
r
e
s
.
T
h
e
s
ec
o
n
d
p
ar
t
o
f
th
is
w
o
r
k
i
s
to
ex
t
r
ac
t
i
m
p
o
r
tan
t
i
m
a
g
e
f
ea
t
u
r
es
f
r
o
m
th
e
d
e
-
n
o
is
e
d
i
m
a
g
es
a
n
d
u
s
e
t
h
e
s
e
i
m
a
g
e
ch
ar
ac
ter
is
tic
s
in
t
h
e
cla
s
s
i
f
icatio
n
o
f
t
h
e
MRI
i
m
a
g
es.
T
h
is
w
i
ll
as
s
is
t
t
h
e
m
ed
ical
s
p
ec
iali
s
t in
t
h
e
i
n
ter
p
r
etatio
n
o
f
MRI
B
r
ain
i
m
a
g
es.
2.
M
E
T
H
O
DO
L
O
G
Y
AND
R
E
SU
L
T
S
2
.
1
.
I
m
a
g
e
Da
t
a
ba
s
e:
MRI
b
r
ain
i
m
a
g
es
u
s
ed
i
n
t
h
is
w
o
r
k
w
er
e
s
elec
ted
f
r
o
m
Har
v
ar
d
Me
d
ical
Sch
o
o
l
Data
b
ase
[
1
]
w
h
ic
h
is
a
w
eb
-
b
ased
d
atab
ase
th
at
co
n
tai
n
s
a
lar
g
e
v
ar
iet
y
o
f
MRI
b
r
ain
s
lice
i
m
a
g
es.
T
h
e
d
atasets
u
s
ed
i
n
th
is
w
o
r
k
co
n
s
i
s
ts
o
f
T
2
-
w
ei
g
h
ted
MRI
b
r
ain
i
m
ag
e
s
in
a
x
i
al
p
lan
e.
T
2
m
o
d
el
w
as
c
h
o
s
e
n
in
t
h
i
s
w
o
r
k
s
i
n
ce
T
2
im
a
g
es a
r
e
o
f
h
i
g
h
er
-
co
n
tr
ast an
d
clea
r
er
v
is
io
n
co
m
p
ar
e
d
to
o
th
er
m
o
d
alities
.
T
h
e
n
u
m
b
er
o
f
MRI
b
r
ain
i
m
a
g
es i
n
t
h
e
i
n
p
u
t d
atase
t is
Fo
r
ty
.
T
w
en
t
y
ar
e
o
f
w
h
ic
h
ar
e
n
o
r
m
al
b
r
ai
n
i
m
a
g
es
a
n
d
t
w
e
n
t
y
o
f
ab
n
o
r
m
al
b
r
ain
i
m
ag
e
s
.
T
h
e
ab
n
o
r
m
a
l
b
r
ain
M
R
i
m
ag
e
s
o
f
t
h
e
d
at
aset
co
n
s
is
t
o
f
t
h
e
f
o
llo
w
in
g
d
i
s
ea
s
es:
A
c
u
te
s
tr
o
k
e,
A
lz
h
ei
m
er
's
d
is
ea
s
e,
C
er
e
b
r
al
T
o
x
o
p
las
m
o
s
is
,
C
h
r
o
n
ic
s
u
b
d
u
r
al
h
e
m
ato
m
a,
H
y
p
er
ten
s
iv
e
e
n
ce
p
h
alo
p
ath
y
,
L
y
m
e
en
ce
p
h
a
lo
p
ath
y
,
Me
tas
tatic
b
r
o
n
ch
o
g
en
ic
ca
r
cin
o
m
a,
Mu
ltip
le
s
cler
o
s
is
,
Sar
co
m
a,
Su
b
-
ac
u
te
s
tr
o
k
e,
Mu
ltip
le
e
m
b
o
lic
in
f
ar
ctio
n
s
,
Fatal
s
tr
o
k
e,
Mo
to
r
n
eu
r
o
n
d
is
ea
s
e,
P
ick
's
d
is
ea
s
e
an
d
Her
p
es
en
ce
p
h
alit
is
.
2
.
2
.
P
re
-
P
ro
ce
s
s
ing
:
M
RI I
m
a
g
e
deno
ing
T
h
e
Dis
cr
ete
W
av
e
let
T
r
an
s
f
o
r
m
s
(
DW
T
)
d
ec
o
m
p
o
s
iti
o
n
w
as
u
s
ed
alo
n
g
w
it
h
t
h
r
es
h
o
ld
in
g
tech
n
iq
u
es
[
2
]
f
o
r
e
f
f
icien
t
n
o
is
e
r
e
m
o
v
al.
T
h
e
M
A
T
L
A
B
w
av
ele
t
to
o
lb
o
x
w
a
s
u
s
ed
f
o
r
th
i
s
p
u
r
p
o
s
e.
T
h
e
w
a
v
elet
–
b
ased
m
et
h
o
d
s
u
s
ed
f
o
r
d
en
o
is
in
g
ar
e
d
ep
icted
in
Fi
g
u
r
e
1
b
elo
w
a
n
d
ca
n
b
e
s
u
m
m
ar
ized
as:
Dec
o
m
p
o
s
e:
C
h
o
o
s
e
a
w
av
e
le
t
an
d
a
d
ec
o
m
p
o
s
itio
n
le
v
el
N
.
C
o
m
p
u
te
th
e
w
a
v
elet
d
ec
o
m
p
o
s
itio
n
o
f
th
e
i
m
ag
e
d
o
w
n
to
le
v
el
N.
T
h
r
esh
o
ld
d
etail
co
ef
f
icie
n
ts
: Fo
r
ea
ch
lev
el
f
r
o
m
1
to
N,
th
r
esh
o
ld
th
e
d
etail
co
ef
f
icie
n
t
s
.
R
ec
o
n
s
tr
u
ct:
C
o
m
p
u
te
w
a
v
ele
t
r
ec
o
n
s
tr
u
ctio
n
u
s
i
n
g
th
e
o
r
ig
in
al
ap
p
r
o
x
i
m
atio
n
co
ef
f
icien
t
s
o
f
lev
el
N
an
d
th
e
m
o
d
i
f
ied
d
etail
co
ef
f
icie
n
ts
o
f
lev
el
s
f
r
o
m
1
to
N.
Fig
u
r
e
1
.
W
av
elet
I
m
ag
e
De
n
o
is
in
g
Af
ter
d
ec
o
m
p
o
s
i
n
g
t
h
e
o
r
ig
i
n
al
i
m
a
g
e
th
a
t
is
s
h
o
w
n
in
Fi
g
u
r
e
2
,
in
to
its
ap
p
r
o
x
i
m
a
tio
n
an
d
d
etail
co
ef
f
icie
n
t
s
as
s
h
o
w
n
i
n
Fi
g
u
r
e
3
,
all
th
e
d
etail
co
ef
f
icie
n
t
s
(
Ho
r
izo
n
tal,
d
iag
o
n
al
a
n
d
v
er
ti
ca
l
d
etails)
o
f
ea
c
h
lev
el
ar
e
t
h
r
es
h
o
ld
ed
ac
co
r
d
i
n
g
to
a
th
r
e
s
h
o
ld
i
n
g
m
et
h
o
d
an
d
a
t
h
r
esh
o
ld
i
n
g
v
al
u
e.
D
if
f
er
en
t
th
r
e
s
h
o
ld
m
et
h
o
d
s
an
d
d
if
f
er
en
t
th
r
es
h
o
ld
s
elec
tio
n
v
alu
e
s
av
a
ilab
le
i
n
M
A
T
L
A
B
DW
T
to
o
l
b
o
x
w
er
e
co
m
p
ar
ed
.
T
h
e
th
r
es
h
o
ld
m
et
h
o
d
s
a
v
ailab
le
ar
e:
Har
d
an
d
So
f
t
t
h
r
es
h
o
ld
,
w
h
ile
t
h
e
t
h
r
esh
o
ld
s
elec
tio
n
v
alu
e
s
ar
e:
Fix
ed
f
o
r
m
t
h
r
es
h
o
ld
,
P
en
alize
h
i
g
h
,
P
en
alize
m
ed
iu
m
,
P
en
aliz
e
lo
w
a
n
d
B
al.
s
p
ar
s
it
y
-
n
o
r
m
(
s
q
r
t)
.
T
h
e
n
o
is
e
co
r
r
u
p
tin
g
t
h
e
i
m
a
g
es
w
a
s
as
s
u
m
ed
to
b
e
w
h
ite
a
n
d
th
u
s
th
e
av
ailab
le
s
tr
u
ct
u
r
e
o
f
u
n
s
ca
l
ed
w
h
ite
n
o
is
e
w
a
s
co
n
s
id
er
ed
f
o
r
th
e
test
e
x
p
er
im
en
ts
o
f
t
h
i
s
w
o
r
k
.
MRI
B
r
ain
I
m
a
g
e
A
p
p
l
y
DW
T
A
p
p
l
y
I
n
v
er
s
e
DW
T
R
ec
o
n
s
tr
u
cted
Den
o
i
s
ed
MRI
B
r
ain
I
m
ag
e
R
e
m
o
v
e
n
o
is
e
f
r
o
m
d
etail
co
e
f
f
icien
ts
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
S
V
M C
la
s
s
if
ica
tio
n
o
f MR
I
B
r
a
in
I
ma
g
es fo
r
C
o
mp
u
ter
-
A
s
s
is
ted
Dia
g
n
o
s
is
(
Ma
d
in
a
Ha
mia
n
e
)
2557
Af
ter
d
e
n
o
is
i
n
g
,
th
e
t
h
r
esh
o
l
d
ed
d
etail
co
ef
f
icien
t
s
t
h
e
s
e
w
er
e
u
s
ed
to
g
et
h
er
w
i
th
t
h
e
o
r
ig
in
a
l
ap
p
r
o
x
im
a
tio
n
co
e
f
f
icien
t
to
r
ec
o
n
s
tr
u
ct
t
h
e
d
en
o
is
ed
i
m
a
g
e
as
s
h
o
w
n
i
n
F
ig
u
r
e.
4
.
T
h
e
ef
f
ec
tiv
e
n
e
s
s
o
f
t
h
e
d
en
o
is
in
g
p
r
o
ce
s
s
is
m
ea
s
u
r
e
d
th
r
o
u
g
h
t
h
e
u
s
e
o
f
th
e
t
h
r
ee
m
etr
ic
s
:
P
ea
k
Si
g
n
al
to
No
is
e
R
atio
(
P
SNR
)
,
Sig
n
al
to
No
is
e
R
at
io
(
SNR
)
a
n
d
th
e
Me
a
n
Sq
u
ar
ed
E
r
r
o
r
(
MSE
)
[
3
]
-
[
5
]
.
Fig
u
r
e
2
.
Or
ig
in
al
M
R
I
b
r
ain
i
m
ag
e
Fig
u
r
e
3
.
A
p
p
r
o
x
i
m
a
tio
n
an
d
d
etail
co
ef
f
icie
n
t
s
Fig
u
r
e
4
.
Den
o
is
ed
i
m
a
g
e
T
h
e
d
e
-
n
o
is
i
n
g
is
co
n
s
id
er
ed
ef
f
ec
tiv
e
w
h
e
n
t
h
e
h
i
g
h
e
s
t
v
a
lu
es
o
f
P
SNR
a
n
d
SN
R
a
n
d
t
h
e
lo
w
est
v
alu
e
o
f
MSE
ar
e
r
ea
c
h
ed
c
o
n
cu
r
r
en
tl
y
.
T
h
e
v
al
u
es
o
f
MSE
,
SN
R
a
n
d
P
SNR
o
b
tai
n
ed
f
r
o
m
d
en
o
i
s
in
g
a
s
a
m
p
le
n
o
r
m
al
MRI
b
r
ain
i
m
ag
e
b
y
ap
p
l
y
in
g
DW
T
ap
p
r
o
a
ch
w
it
h
d
i
f
f
er
e
n
t
w
a
v
elet
t
y
p
es
an
d
t
h
r
es
h
o
ld
in
g
tech
n
iq
u
es
ar
e
s
h
o
w
n
i
n
T
ab
le
1
,
T
a
b
le
2
,
T
a
b
le
3
an
d
T
a
b
le
4
.
T
h
e
w
av
ele
t
t
y
p
es
th
a
t
wer
e
u
s
ed
ar
e:
Haa
r
,
Dau
b
ec
h
ie
s
(
d
b
2
an
d
d
b
4
)
,
Sy
m
let
(
s
y
m
2
an
d
s
y
m
4
)
,
C
o
i
f
le
t
(
co
if
1
)
,
B
io
r
th
o
g
o
n
al
(
b
io
r
1
.
1
,
b
io
r
3
.
1
,
r
b
i
o
1
.
1
)
an
d
d
m
e
y
.
T
h
e
v
alu
e
s
in
th
e
s
e
t
ab
les
r
esu
lt
f
r
o
m
t
h
e
ap
p
licatio
n
o
f
s
o
f
t
an
d
h
ar
d
th
r
es
h
o
ld
i
n
g
to
th
e
d
etails
o
f
th
e
f
ir
s
t a
n
d
s
ec
o
n
d
DW
T
lev
el
d
ec
o
m
p
o
s
itio
n
o
f
t
h
e
i
m
a
g
e.
C
o
m
p
ar
is
o
n
s
b
et
w
ee
n
t
h
e
d
e
-
n
o
i
s
i
n
g
r
e
s
u
l
ts
in
ter
m
s
o
f
t
h
e
co
m
p
u
ted
v
alu
e
s
o
f
MS
E
,
SNR
an
d
P
SNR
o
b
tain
ed
w
h
e
n
ap
p
l
y
i
n
g
h
ar
d
an
d
s
o
f
t
th
r
es
h
o
ld
s
o
n
th
e
d
etail
co
ef
f
icie
n
ts
r
esu
lti
n
g
f
r
o
m
t
h
e
f
ir
s
t
a
n
d
s
ec
o
n
d
le
v
el
DW
T
d
ec
o
m
p
o
s
itio
n
o
f
t
h
e
n
o
r
m
al
b
r
ain
i
m
a
g
es
in
d
icate
t
h
at
h
ar
d
t
h
r
esh
o
ld
in
g
I
s
b
etter
th
a
n
s
o
f
t
t
h
r
esh
o
ld
i
n
g
i
n
th
e
f
ir
s
t
an
d
s
ec
o
n
d
lev
el
s
o
f
DW
T
.
I
n
ad
d
itio
n
,
th
e
co
m
p
ar
is
o
n
b
et
w
ee
n
t
h
e
f
ir
s
t
a
n
d
s
ec
o
n
d
lev
e
l
m
etr
ics
v
al
u
es
o
b
tain
ed
w
it
h
h
ar
d
th
r
es
h
o
ld
in
g
o
f
th
e
d
etai
ls
g
a
v
e
b
etter
r
es
u
lts
in
th
e
f
ir
s
t
le
v
el
o
f
th
e
DW
T
d
ec
o
m
p
o
s
itio
n
,
e
s
p
ec
iall
y
w
i
th
t
h
e
s
elec
t
io
n
t
h
r
esh
o
ld
v
al
u
e
m
eth
o
d
o
f
B
al.
s
p
ar
s
it
y
-
n
o
r
m
(
s
q
r
t)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
5
,
Octo
b
er
2
0
1
7
:
2
5
5
5
–
2
5
6
4
2558
T
ab
le
1
.
So
f
t
T
h
r
esh
o
ld
o
f
th
e
First
L
ev
el
DW
T
F
i
x
e
d
F
o
r
m T
h
r
e
sh
o
l
d
B
a
l
.
s
p
a
r
s
i
t
y
-
n
o
r
m
(
sq
r
t
)
M
S
E
S
N
R
P
S
N
R
M
S
E
S
N
R
P
S
N
R
h
a
a
r
6
.
8
4
4
1
2
8
.
6
9
8
8
3
9
.
7
7
7
6
6
.
2
6
7
6
2
9
.
0
8
1
4
0
.
1
5
9
8
db2
7
.
0
2
4
9
2
8
.
5
8
5
6
3
9
.
6
6
4
4
1
2
.
2
7
7
5
2
6
.
1
6
0
9
3
7
.
2
3
9
7
db4
7
.
1
6
2
4
2
8
.
5
0
1
4
3
9
.
5
8
0
2
1
4
.
5
2
8
5
2
5
.
4
2
9
8
3
6
.
5
0
8
6
sy
m
2
7
.
0
2
4
9
2
8
.
5
8
5
6
3
9
.
6
6
4
4
1
2
.
2
7
7
5
2
6
.
1
6
0
9
3
7
.
2
3
9
7
sy
m
4
7
.
0
913
2
8
.
5
4
4
7
3
9
.
6
2
3
5
1
2
.
3
0
0
6
2
6
.
1
5
2
7
3
7
.
2
3
1
5
c
o
i
f
1
7
.
0
6
9
5
2
8
.
5
5
8
1
3
9
.
6
3
6
9
1
2
.
4
0
0
9
2
6
.
1
1
7
5
3
7
.
1
9
6
3
b
i
o
r
1
.
1
6
.
8
4
4
1
2
8
.
6
9
8
8
3
9
.
7
7
7
6
6
.
2
6
7
6
2
9
.
0
8
1
4
0
.
1
5
9
8
b
i
o
r
3
.
1
7
.
2
0
6
6
2
8
.
4
7
4
7
3
9
.
5
5
3
5
1
2
.
5
8
7
1
2
6
.
0
5
2
7
3
7
.
1
3
1
6
r
b
i
o
1
.
1
6
.
8
4
4
1
2
8
.
6
9
8
8
3
9
.
7
7
7
6
6
.
2
6
7
6
2
9
.
0
8
1
40
.
1
5
9
8
d
m
e
y
8
.
4
3
3
9
2
7
.
7
9
1
7
3
8
.
8
7
0
5
1
2
.
3
9
8
9
2
6
.
1
1
8
2
3
7
.
1
9
7
T
ab
le
2
.
Har
d
T
h
r
esh
o
ld
o
f
th
e
First L
e
v
el
DW
T
Fi
x
e
d
F
o
r
m
T
h
r
e
sh
o
l
d
B
a
l
.
sp
a
r
s
i
t
y
-
n
o
r
m
(
sq
r
t
)
M
S
E
S
N
R
P
S
N
R
M
S
E
S
N
R
P
S
N
R
H
a
a
r
6
.
0
7
4
5
2
9
.
2
1
6
9
4
0
.
2
9
5
7
6
.
0
5
5
2
2
9
.
2
3
0
7
4
0
.
3
0
9
5
db2
6
.
0
6
8
7
2
9
.
2
2
1
4
0
.
2
9
9
8
6
.
1
1
6
6
2
9
.
1
8
6
9
4
0
.
2
6
5
7
db4
6
.
0
9
7
3
2
9
.
2
0
0
6
4
0
.
2
7
9
4
6
.
2
4
1
2
9
.
0
9
9
4
4
0
.
1
7
8
2
sy
m
2
6
.
0
6
8
7
2
9
.
2
2
1
4
0
.
2
9
9
8
6
.
1
1
6
6
2
9
.
1
8
6
9
4
0
.
2
6
5
7
sy
m
4
6
.
0
9
8
4
2
9
.
1
9
9
8
4
0
.
2
7
8
7
6
.
1
7
8
3
2
9
.
1
4
3
3
4
0
.
2
2
2
1
c
o
i
f
1
6
.
0
9
7
9
2
9
.
2
0
0
2
4
0
.
2
7
9
6
.
1
8
9
4
2
9
.
1
3
5
5
4
0
.
2
1
4
3
b
i
o
r
1
.
1
6
.
0
7
4
5
2
9
.
2
1
6
9
4
0
.
2
9
5
7
6
.
0
5
5
2
2
9
.
2
3
0
7
4
0
.
3
0
9
5
b
i
o
r
3
.
1
6
.
1
2
2
1
2
9
.
1
8
3
4
0
.
2
6
1
8
6
.
2
4
6
1
2
9
.
0
9
5
9
4
0
.
1
7
4
7
r
b
i
o
1
.
1
6
.
0
7
4
5
2
9
.
2
1
6
9
4
0
.
2
9
5
7
6
.
0
5
5
2
2
9
.
2
3
0
7
4
0
.
3
0
9
5
d
m
e
y
6
.
1
0
6
8
2
9
.
1
9
3
8
4
0
.
2
7
2
7
6
.
1
9
8
1
2
9
.
1
2
9
4
4
0
.
2
0
8
2
T
ab
le
I
I
I
.
So
f
t th
r
es
h
o
ld
o
f
th
e
Seco
n
d
lev
el
DW
T
Fi
x
e
d
F
o
r
m
T
h
r
e
sh
o
l
d
B
a
l
.
sp
a
r
s
i
t
y
-
n
o
r
m
(
sq
r
t
)
MSE
S
N
R
PSN
R
MSE
S
N
R
PSN
R
h
a
a
r
7
.
5
3
5
9
2
8
.
2
8
0
6
3
9
.
3
5
9
5
1
6
.
1
7
4
4
2
4
.
9
6
3
7
3
6
.
0
4
2
5
db2
7
.
6
1
8
5
2
8
.
2
3
3
3
3
9
.
3
1
2
1
1
7
.
7
0
3
1
2
4
.
5
7
1
5
3
5
.
6
5
0
3
db4
7
.
5
6
6
1
2
8
.
2
6
3
3
3
9
.
3
4
2
1
1
7
.
7
0
3
1
2
4
.
8
1
1
3
3
5
.
6
5
0
3
sy
m
2
7
.
6
1
8
5
2
8
.
2
3
3
3
3
9
.
3
1
2
1
1
7
.
7
0
3
1
2
4
.
5
7
1
5
3
5
.
6
5
0
3
sy
m
4
7
.
6
4
2
2
8
.
2
1
9
9
3
9
.
2
9
8
7
1
8
.
0
9
2
9
2
4
.
4
7
6
9
3
5
.
5
5
5
7
c
o
i
f
1
7
.
6
2
5
8
2
8
.
2
2
9
1
3
9
.
3
0
7
9
2
0
.
0
7
4
4
2
4
.
0
2
5
6
3
5
.
1
0
4
4
b
i
o
r
1
.
1
7
.
5
359
2
8
.
2
8
0
6
3
9
.
3
5
9
5
1
6
.
1
7
4
4
2
4
.
9
6
3
7
3
6
.
0
4
2
5
b
i
o
r
3
.
1
7
.
9
4
7
4
2
8
.
0
4
9
8
3
9
.
1
2
8
6
1
1
.
7
2
0
8
2
6
.
3
6
2
4
3
7
.
4
4
1
2
r
b
i
o
1
.
1
7
.
5
3
5
9
2
8
.
2
8
0
6
3
9
.
3
5
9
5
1
6
.
1
7
4
4
2
4
.
9
6
3
7
3
6
.
0
4
2
5
d
m
e
y
7
.
6
4
6
2
8
.
2
1
7
6
3
9
.
2
9
6
4
1
6
.
6
3
2
2
4
.
8
4
2
5
3
5
.
9
2
1
4
T
h
e
P
en
alize
h
ig
h
,
m
ed
i
u
m
an
d
lo
w
m
et
h
o
d
d
o
es
n
o
t
d
if
f
er
e
n
tiate
s
i
g
n
i
f
ican
tl
y
b
et
w
ee
n
t
h
e
d
if
f
er
e
n
t
d
ec
o
m
p
o
s
itio
n
le
v
el
s
,
th
e
d
if
f
er
en
t
w
a
v
elets
a
n
d
b
et
w
ee
n
th
e
t
h
r
esh
o
ld
i
n
g
m
et
h
o
d
s
as
it
g
av
e
t
h
e
s
a
m
e
m
etr
ic
s
v
alu
e
s
f
o
r
all
w
a
v
elet
s
an
d
b
o
th
lev
e
ls
o
f
DW
T
d
ec
o
m
p
o
s
itio
n
as
w
ell
as
th
e
s
a
m
e
m
etr
ics
va
lu
e
s
f
o
r
h
ar
d
a
n
d
s
o
f
t
t
h
r
es
h
o
ld
in
g
m
et
h
o
d
s
.
W
e
ca
n
t
h
er
ef
o
r
e
co
n
cl
u
d
e
th
at
t
h
is
th
r
es
h
o
ld
in
g
tec
h
n
iq
u
e
is
n
o
t
s
u
itab
le
f
o
r
d
en
o
is
in
g
o
f
MRI
b
r
ain
i
m
ag
e
s
th
a
t
w
er
e
u
s
ed
i
n
th
i
s
w
o
r
k
a
n
d
w
as
d
is
ca
r
d
ed
f
r
o
m
t
h
e
an
al
y
s
is
.
T
h
e
f
ir
s
t
lev
el
o
f
DW
T
d
en
o
is
in
g
w
it
h
h
ar
d
th
r
es
h
o
ld
in
g
a
n
d
w
i
th
t
h
e
“
B
al.
s
p
ar
s
it
y
-
n
o
r
m
(
s
q
r
t)
”
tech
n
iq
u
es
o
f
th
r
es
h
o
ld
in
g
g
a
v
e
t
h
e
b
est
r
esu
lts
.
Sin
ce
t
h
e
s
a
m
e
r
es
u
lt
s
w
er
e
o
b
tain
ed
f
o
r
th
e
Haa
r
,
B
io
r
an
d
R
b
io
w
av
e
lets
,
th
e
d
en
o
is
in
g
p
r
o
ce
s
s
w
as
th
u
s
r
ep
ea
ted
f
o
r
th
e
m
e
m
b
er
s
o
f
th
e
s
a
m
e
w
a
v
elets
an
d
th
e
r
esu
l
t
s
w
er
e
tab
u
lated
in
T
ab
le
5
w
h
i
ch
i
n
d
icate
s
t
h
at
i
n
B
io
r
1
.
3
g
av
e
t
h
e
m
in
i
m
u
m
MSE
,
h
i
g
h
e
s
t
SNR
a
n
d
h
ig
h
es
t
P
SNR
v
al
u
es
f
o
r
th
e
f
iv
e
i
m
a
g
es c
o
m
p
ar
ed
to
o
th
er
w
av
ele
t m
e
m
b
er
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
S
V
M C
la
s
s
if
ica
tio
n
o
f MR
I
B
r
a
in
I
ma
g
es fo
r
C
o
mp
u
ter
-
A
s
s
is
ted
Dia
g
n
o
s
is
(
Ma
d
in
a
Ha
mia
n
e
)
2559
T
ab
le
4.
Har
d
T
h
r
esh
o
ld
o
f
th
e
Seco
n
d
L
e
v
el
DW
T
Fi
x
e
d
F
o
r
m
T
h
r
e
sh
o
l
d
B
a
l
.
sp
a
r
s
i
t
y
-
n
o
r
m
(
sq
r
t
)
M
S
E
S
N
R
P
S
N
R
M
S
E
S
N
R
P
S
N
R
h
a
a
r
6
.
1
7
1
2
2
9
.
1
4
8
3
4
0
.
2
2
7
1
6
.
6
6
5
2
3
9
.
8
9
2
7
3
9
.
8
9
2
7
db2
6
.
2
0
3
6
2
9
.
1
2
5
5
4
0
.
2
0
4
4
8
.
3
3
5
1
2
7
.
8
4
2
9
3
8
.
9
2
1
7
db4
6
.
2
3
1
3
2
9
.
1
0
6
2
4
0
.
1
8
5
8
.
5
5
4
6
2
7
.
7
3
3
8
.
8
0
8
8
sy
m
2
6
.
2
0
3
6
2
9
.
1
2
5
5
4
0
.
2
0
4
4
8
.
3
3
5
1
2
7
.
8
4
2
9
3
8
.
9
2
1
7
sy
m
4
6
.
2
3
1
5
2
9
.
1
0
6
1
4
0
.
1
8
4
9
8
.
7
5
8
6
2
7
.
6
2
7
6
3
8
.
7
0
6
5
c
o
i
f
1
6
.
2
0
2
7
2
9
.
1
2
6
2
4
0
.
2
0
5
9
.
0
7
6
8
2
7
.
4
7
2
7
3
8
.
5
5
1
5
b
i
o
r
1
.
1
6
.
1
7
1
2
2
9
.
1
4
8
3
4
0
.
2
2
7
1
6
.
6
6
5
2
2
8
.
8
1
3
9
3
9
.
8
9
2
7
b
i
o
r
3
.
1
6
.
4
4
9
9
2
8
.
9
5
6
4
4
0
.
0
3
5
3
7
.
4
5
1
5
2
8
.
3
2
9
6
3
9
.
4
0
8
4
r
b
i
o
1
.
1
6
.
1
7
1
2
2
9
.
1
4
8
3
4
0
.
2
2
7
1
6
.
6
6
5
2
2
8
.
8
1
3
9
3
9
.
8
9
2
7
d
m
e
y
6
.
2
5
6
5
2
9
.
0
8
8
7
4
0
.
1
6
7
5
8
.
4
5
5
3
2
7
.
7
8
0
7
3
8
.
8
5
9
5
T
ab
le
5
.
Har
d
th
r
esh
o
ld
o
f
th
e
First L
e
v
el
DW
T
w
it
h
B
al.
Sp
ar
s
it
y
-
N
o
r
m
(
s
q
r
t)
M
eth
o
d
B
a
l
.
sp
a
r
s
i
t
y
-
n
o
r
m
(
sq
r
t
)
MSE
S
N
R
PSN
R
b
i
o
r
1
.
1
6
.
0
5
5
2
2
9
.
2
3
0
7
4
0
.
3
0
95
b
i
o
r
1
.
3
6
.
0
5
1
1
2
9
.
2
3
3
6
4
0
.
3
1
2
4
b
i
o
r
1
.
5
6
.
0
5
3
4
2
9
.
2
3
2
4
0
.
3
1
0
8
b
i
o
r
2
.
2
6
.
1
9
9
8
2
9
.
1
2
8
2
4
0
.
2
0
7
b
i
o
r
2
.
4
6
.
1
9
7
8
2
9
.
1
2
9
6
4
0
.
2
0
8
4
b
i
o
r
2
.
6
6
.
1
9
7
7
2
9
.
1
2
9
6
4
0
.
2
0
8
5
b
i
o
r
2
.
8
6
.
1
8
9
9
2
9
.
1
3
5
2
4
0
.
2
1
4
b
i
o
r
3
.
1
6
.
2
4
6
1
2
9
.
0
9
5
9
4
0
.
1
7
4
7
b
i
o
r
3
.
3
6
.
2
4
6
4
2
9
.
0
9
5
7
4
0
.
1
7
4
5
b
i
o
r
3
.
5
6
.
2
1
6
5
2
9
.
1
1
6
5
4
0
.
1
9
5
3
b
i
o
r
3
.
7
6
.
2
1
5
9
2
9
.
1
1
6
9
4
0
.
1
9
5
8
b
i
o
r
3
.
9
6
.
2
1
1
8
2
9
.
1
1
9
8
4
0
.
1
9
8
7
b
i
o
r
4
.
4
6
.
1
7
1
9
2
9
.
1
4
7
8
4
0
.
2
2
6
6
b
i
o
r
5
.
5
6
.
1
7
7
3
2
9
.
1
4
4
4
0
.
2
2
2
8
b
i
o
r
6
.
8
6
.
1
9
0
2
2
9
.
1
3
4
9
4
0
.
2
1
3
7
r
b
i
o
1
.
1
6
.
0
5
5
2
2
9
.
2
3
0
7
4
0
.
3
0
9
5
r
b
i
o
1
.
3
6
.
1
0
1
3
2
9
.
1
9
7
7
4
0
.
2
7
6
6
r
b
i
o
1
.
5
6
.
1
1
1
6
2
9
.
1
9
0
4
4
0
.
2
6
9
3
r
b
i
o
2
.
2
6
.
1
7
2
2
9
.
1
4
7
7
4
0
.
2
2
6
5
r
b
i
o
2
.
4
6
.
1
8
0
1
2
9
.
1
4
2
1
4
0
.
2
2
0
9
r
b
i
o
2
.
6
6
.
1
7
3
2
9
.
1
4
7
4
0
.
2
2
5
8
r
b
i
o
2
.
8
6
.
1
8
5
9
2
9
.
1
3
8
4
0
.
2
1
6
8
r
b
i
o
3
.
1
6
.
6
0
3
3
2
8
.
8
5
4
4
3
9
.
9
3
3
2
r
b
i
o
3
.
3
6
.
3
1
3
9
2
9
.
0
4
9
4
0
.
1
2
7
8
r
b
i
o
3
.
5
6
.
2
5
9
7
2
9
.
0
8
6
5
4
0
.
1
6
5
3
r
b
i
o
3
.7
6
.
2
4
7
2
2
9
.
0
9
5
1
4
0
.
1
7
3
9
r
b
i
o
3
.
9
6
.
2
4
4
1
2
9
.
0
9
7
3
4
0
.
1
7
6
1
r
b
i
o
4
.
4
6
.
2
3
0
2
2
9
.
1
0
7
4
0
.
1
8
5
8
r
b
i
o
5
.
5
6
.
2
3
2
1
2
9
.
1
0
5
7
4
0
.
1
8
4
5
r
b
i
o
6
.
8
6
.
1
8
5
9
2
9
.
1
3
8
4
0
.
2
1
6
8
Af
ter
tes
tin
g
t
h
e
ab
o
v
e
p
r
o
ce
d
u
r
e
o
n
all
n
o
r
m
al
b
r
ain
i
m
ag
es
an
d
id
en
ti
f
y
i
n
g
t
h
e
b
est
w
a
v
elet
t
y
p
e
,
b
est
DW
T
lev
el
alo
n
g
w
it
h
t
h
e
b
est
th
r
es
h
o
ld
in
g
tech
n
iq
u
e,
b
ased
o
n
th
e
ab
o
v
e
m
e
tr
ics,
t
h
e
s
a
m
e
p
r
o
ce
d
u
r
e
o
f
d
en
o
is
i
n
g
w
a
s
ap
p
lied
to
all
MRI
b
r
ain
i
m
a
g
es i
n
t
h
e
in
p
u
t d
ata
s
et.
2
.
3
.
I
m
a
g
e
Seg
m
e
nta
t
io
n
I
m
ag
e
s
eg
m
e
n
tatio
n
is
a
m
et
h
o
d
th
at
s
p
lit
an
i
m
a
g
e
to
a
g
r
o
u
p
o
f
n
o
n
-
o
v
er
lap
p
in
g
ar
e
as
[
6
]
.
T
h
e
u
n
i
f
ica
tio
n
o
f
th
e
s
e
ar
ea
s
is
t
h
e
w
h
o
le
i
m
ag
e
.
Ho
w
ev
er
,
t
h
e
b
o
u
n
d
ar
ies
o
f
v
ar
io
u
s
ti
s
s
u
es
i
n
b
r
ain
i
m
ag
e
s
ar
e
u
n
clea
r
an
d
th
e
i
n
te
n
s
itie
s
o
f
th
e
g
r
a
y
a
n
d
w
h
ite
tis
s
u
e
s
ar
e
alm
o
s
t
s
i
m
ilar
.
T
h
e
ad
j
ac
en
t
tis
s
u
es
ar
e
d
if
f
icu
l
t
to
b
e
s
ep
ar
ated
b
ec
au
s
e
th
e
b
o
u
n
d
ar
ies
ar
e
s
m
o
o
th
an
d
t
h
e
i
n
ten
s
it
y
d
o
es
n
o
t
c
h
a
n
g
e
to
o
m
u
c
h
b
et
w
ee
n
th
e
s
e
tis
s
u
es.
He
n
ce
,
ed
g
e
d
etec
tio
n
is
r
eq
u
ir
ed
p
r
io
r
to
th
e
i
m
a
g
e
s
eg
m
e
n
tat
io
n
.
I
m
ag
e
ed
g
es
w
er
e
d
etec
ted
b
y
u
s
i
n
g
th
e
C
a
n
n
y
m
et
h
o
d
to
f
in
d
t
h
e
b
i
n
ar
y
g
r
ad
ien
t
m
ask
[
7
]
as
s
h
o
w
n
i
n
Fi
g
u
r
e
5
.
T
o
d
e
tect
w
ea
k
a
n
d
s
tr
o
n
g
ed
g
e
s
,
th
i
s
m
et
h
o
d
u
s
e
s
t
w
o
t
h
r
es
h
o
ld
s
.
Hen
ce
,
th
e
C
a
n
n
y
m
et
h
o
d
is
m
o
r
e
li
k
el
y
to
d
etec
t
tr
u
e
w
ea
k
ed
g
es,
an
d
less
lik
e
l
y
t
h
a
n
th
e
o
th
er
m
et
h
o
d
s
to
b
e
d
is
p
er
s
ed
b
y
n
o
i
s
e.
Af
ter
d
ete
ctin
g
t
h
e
ed
g
e
s
,
t
h
ese
ed
g
es
wer
e
o
u
tli
n
ed
o
n
t
h
e
o
r
i
g
in
a
l
i
m
ag
e
to
d
i
f
f
er
e
n
tiate
b
et
w
ee
n
d
if
f
er
en
t t
is
s
u
es o
f
th
e
b
r
ain
.
Af
ter
o
u
t
lin
i
n
g
t
h
e
ed
g
es
o
n
th
e
i
m
ag
e,
g
lo
b
al
th
r
e
s
h
o
ld
u
s
in
g
Ot
s
u
’
s
m
e
th
o
d
[
8
]
w
as
ap
p
lied
to
id
en
ti
f
y
t
h
e
in
te
n
s
it
y
lev
e
l,
an
d
th
e
im
a
g
e
w
as
t
h
en
co
n
v
er
te
d
to
a
b
in
ar
y
i
m
a
g
e
an
d
th
r
es
h
o
ld
ed
ac
c
o
r
d
in
g
to
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
5
,
Octo
b
er
2
0
1
7
:
2
5
5
5
–
2
5
6
4
2560
v
alu
e
r
etu
r
n
ed
b
y
t
h
e
f
u
n
ctio
n
o
f
Ot
s
u
’
s
m
e
th
o
d
.
A
n
ex
a
m
p
le
o
f
t
h
e
t
h
r
es
h
o
ld
s
eg
m
e
n
tati
o
n
o
u
tp
u
t
is
s
h
o
w
n
in
Fi
g
u
r
e
6
.
Fig
u
r
e
5
.
B
in
ar
y
g
r
ad
ien
t
m
a
s
k
an
d
ab
n
o
r
m
al
b
r
ain
w
i
th
ed
g
es d
ete
cted
Fig
u
r
e
6
.
T
h
r
esh
o
ld
Seg
m
e
n
ta
tio
n
Fig
u
r
e
7
.
T
h
r
esh
o
ld
Seg
m
e
n
ta
tio
n
w
it
h
o
u
t E
d
g
e
Dete
ctio
n
T
h
e
th
r
esh
o
ld
ed
i
m
ag
e
o
b
tai
n
ed
b
y
ap
p
l
y
in
g
Ot
s
u
’
s
t
h
r
es
h
o
ld
b
u
t
w
ith
o
u
t
ed
g
e
d
etec
tio
n
is
s
h
o
w
n
in
Fi
g
u
r
e
7.
an
d
clea
r
l
y
in
d
ic
ates
th
at
t
h
e
ed
g
e
d
etec
ti
o
n
t
ec
h
n
iq
u
e
is
a
n
i
m
p
o
r
tan
t
s
tep
th
at
s
h
o
u
ld
n
o
t
b
e
s
u
p
p
r
ess
ed
w
h
e
n
ap
p
l
y
i
n
g
th
e
s
eg
m
e
n
tatio
n
s
tep
th
at
i
s
b
ase
d
o
n
in
ten
s
it
y
th
r
e
s
h
o
ld
i
n
g
.
Fig
u
r
e
8
.
T
u
m
o
r
T
h
r
esh
o
ld
Ma
s
k
Fig
u
r
e
9
.
E
x
tr
ac
ted
T
u
m
o
r
I
m
ag
e
Af
ter
t
h
r
esh
o
ld
i
n
g
t
h
e
i
m
a
g
e,
th
e
h
o
le
s
in
t
h
e
i
m
a
g
e
th
at
ar
e
th
e
s
a
m
e
as
t
h
e
b
ac
k
g
r
o
u
n
d
w
er
e
f
illed
.
T
h
e
th
r
es
h
o
ld
ed
i
m
a
g
e
w
a
s
t
h
en
co
n
v
er
ted
to
a
b
i
n
ar
y
i
m
a
g
e
an
d
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
s
w
er
e
ap
p
lied
to
r
e
m
o
v
e
i
s
o
lated
p
ix
e
ls
w
h
ic
h
ar
e
i
n
d
i
v
id
u
al
1
s
t
h
at
ar
e
s
u
r
r
o
u
n
d
ed
b
y
0
s
.
Nex
t,
an
o
th
er
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
w
as
ap
p
lied
th
at
p
er
f
o
r
m
s
er
o
s
io
n
f
o
llo
w
ed
b
y
d
ilatio
n
.
E
r
o
s
io
n
r
e
m
o
v
e
s
p
ix
els
o
n
o
b
j
ec
t
b
o
u
n
d
ar
ies
w
h
ile
d
ilatio
n
ad
d
s
p
ix
els
to
t
h
e
b
o
u
n
d
ar
ies
o
f
o
b
j
ec
ts
in
an
i
m
ag
e.
T
h
e
r
eg
io
n
s
o
f
i
n
ter
es
t
(
R
OI
)
w
er
e
s
u
b
s
eq
u
en
t
l
y
e
x
tr
ac
ted
f
r
o
m
th
e
b
in
ar
y
i
m
ag
e
a
s
s
h
o
w
n
in
F
ig
u
r
e
8
d
is
p
la
y
in
g
a
t
u
m
o
r
m
as
k
.
T
h
e
tu
m
o
r
w
a
s
e
x
tr
ac
ted
f
r
o
m
t
h
e
b
r
ai
n
i
m
ag
e
b
y
as
s
ig
n
i
n
g
a
v
al
u
e
o
f
0
to
all
p
i
x
els
ex
ce
p
t
th
e
p
ix
el
s
o
f
t
h
e
t
u
m
o
r
m
a
s
k
as sh
o
w
n
i
n
Fi
g
u
r
e
9
.
2
.
4
.
I
m
a
g
e
F
ea
t
ure
E
x
t
ra
ct
io
n
Var
io
u
s
tec
h
n
iq
u
es
f
o
r
e
x
t
r
a
ctin
g
f
ea
tu
r
e
s
f
r
o
m
M
R
I
b
r
ain
i
m
a
g
es
h
a
v
e
b
ee
n
r
ep
o
r
ted
in
t
h
e
liter
atu
r
e,
t
h
e
m
o
s
t
co
m
m
o
n
a
r
e:
Dis
cr
ete
W
av
ele
t
T
r
an
s
f
o
r
m
(
DW
T
)
[
9
]
,
Gab
o
r
f
ilter
s
[
1
0
]
an
d
Gr
ay
L
ev
el
Co
-
o
cc
u
r
r
en
ce
Ma
tr
ix
(
G
L
C
M)
[
1
1
]
.
B
o
th
DW
T
an
d
Gab
o
r
Fil
ter
m
et
h
o
d
s
p
r
o
d
u
ce
f
ea
tu
r
e
v
ec
to
r
s
w
i
th
a
lar
g
e
n
u
m
b
er
o
f
ele
m
en
ts
w
h
i
ch
n
ec
e
s
s
i
tates
t
h
e
u
s
e
o
f
s
ize
r
ed
u
ctio
n
tec
h
n
iq
u
es
p
r
io
r
to
f
ee
d
in
g
t
h
e
f
ea
tu
r
e
v
ec
to
r
s
to
th
e
cla
s
s
i
f
ier
.
O
n
th
e
o
th
er
h
an
d
,
T
h
e
Gr
a
y
L
ev
e
l
C
o
-
o
cc
u
r
r
en
ce
Ma
tr
ix
(
G
L
C
M)
h
as
p
r
o
v
en
to
b
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
S
V
M C
la
s
s
if
ica
tio
n
o
f MR
I
B
r
a
in
I
ma
g
es fo
r
C
o
mp
u
ter
-
A
s
s
is
ted
Dia
g
n
o
s
is
(
Ma
d
in
a
Ha
mia
n
e
)
2561
s
u
p
er
io
r
in
ter
m
s
th
e
d
i
m
e
n
s
io
n
o
f
t
h
e
f
ea
tu
r
e
v
ec
to
r
s
an
d
th
u
s
is
m
o
r
e
ap
p
r
o
p
r
iat
e
f
o
r
MRI
i
m
a
g
e
class
i
f
icatio
n
.
GL
C
M
i
s
a
s
tati
s
tical
tec
h
n
iq
u
e
f
o
r
ex
tr
ac
t
in
g
te
x
t
u
r
e
f
ea
t
u
r
es
f
r
o
m
i
m
a
g
es
[
1
1
]
.
I
t
as
s
u
m
es
th
a
t
t
h
e
tex
t
u
r
e
o
f
n
o
r
m
al
ti
s
s
u
es
i
s
v
er
y
d
i
f
f
er
e
n
t
f
r
o
m
th
e
te
x
t
u
r
e
o
f
tu
m
o
r
tis
s
u
e
s
.
T
h
e
tex
tu
r
e
f
ea
tu
r
es
e
x
tr
ac
ted
f
r
o
m
t
h
e
G
L
C
M
m
atr
ix
ar
e:
co
n
tr
ast,
co
r
r
elatio
n
,
en
er
g
y
,
h
o
m
o
g
en
ei
t
y
.
Selecti
n
g
a
g
o
o
d
s
et
o
f
f
ea
t
u
r
e
s
i
m
p
r
o
v
e
t
h
e
p
r
o
ce
s
s
o
f
cla
s
s
i
f
icatio
n
.
A
d
d
itio
n
al
f
ea
t
u
r
es
w
er
e
al
s
o
ex
tr
ac
ted
f
r
o
m
t
h
is
m
atr
i
x
w
h
ic
h
ar
e
:
me
an
,
s
tan
d
ar
d
d
ev
iatio
n
,
en
t
r
o
p
y
,
r
o
o
t
m
ea
n
s
q
u
ar
e,
v
ar
ia
n
ce
,
k
u
r
to
s
is
,
s
k
e
w
n
ess
.
A
ll
f
ea
tu
r
es
u
s
ed
in
th
is
w
o
r
k
ar
e
lis
ted
i
n
T
ab
le
6
.
T
h
e
se
f
ea
tu
r
e
s
w
er
e
ex
tr
ac
ted
f
r
o
m
t
h
e
t
w
en
t
y
n
o
r
m
al
i
m
ag
es
f
o
r
m
i
n
g
class
I
i
m
a
g
es
a
n
d
t
h
e
t
h
ir
t
y
i
m
a
g
es
o
f
ab
n
o
r
m
a
l
r
eg
i
o
n
s
o
f
in
ter
e
s
t
f
o
r
m
in
g
c
lass
I
I
i
m
ag
e
s
.
T
h
e
av
er
ag
ed
f
ea
t
u
r
es
v
alu
e
s
ar
e
s
h
o
w
n
i
n
T
ab
le
7
.
T
ab
le
6
.
GL
C
M
Featu
r
e
s
Fe
a
t
u
r
e
s
E
q
u
a
t
i
o
n
C
o
n
t
r
a
st
∑
(
,
)
|
−
|
2
−
1
,
=
0
C
o
r
r
e
l
a
t
i
o
n
∑
∑
[
(
,
)
]
−
E
n
e
r
g
y
∑
(
,
)
2
−
1
,
=
0
Ho
m
o
g
e
n
e
i
t
y
∑
∑
(
,
)
1
+
|
+
|
M
e
a
n
∑
(
,
)
−
1
,
−
1
S
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
√
1
∑
(
−
)
2
=
1
E
n
t
r
o
p
y
−
∑
∑
(
,
)
ln
(
,
)
R
M
S
√
1
∑
|
|
2
=
1
V
a
r
i
a
n
c
e
∑
∑
(
−
1
−
1
−
)
2
(
,
)
Ku
r
t
o
si
s
=
∑
(
−
)
4
=
1
(
∑
(
−
)
2
=
1
)
2
S
k
e
w
n
e
ss
√
∑
(
−
)
3
=
1
(
∑
(
−
)
2
=
1
)
3
/
2
T
ab
le
7.
E
x
tr
ac
ted
f
ea
tu
r
es o
f
n
o
r
m
al
an
d
ab
n
o
r
m
a
l i
m
a
g
e
s
C
l
a
ss
/
Fe
a
t
u
r
e
C
l
a
ss I
(
N
o
r
m
a
l
)
C
l
a
ss I
(
A
b
o
r
m
a
l
)
C
o
n
t
r
a
st
0
.
1
6
1
7
8
0
.
0
5
3
0
0
2
C
o
r
r
e
l
a
t
i
o
n
0
.
9
6
9
4
5
0
.
9
5
6
9
6
En
e
r
g
y
0
.
4
8
2
7
9
8
0
.
9
3
5
9
6
1
H
o
mo
g
e
n
e
i
t
y
0
.
9
5
2
3
9
0
.
9
9
2
5
3
M
e
a
n
4
0
8
8
1
0
2
0
S
t
a
n
d
a
r
d
D
e
v
i
a
t
i
o
n
2
2
5
2
7
.
9
7
2
7
8
8
8
.
4
7
4
En
t
r
o
p
y
0
.
4
5
7
0
8
5
0
.
9
2
3
R
M
S
1
0
6
0
6
.
1
3
2
8
5
4
.
7
1
8
V
a
r
i
a
n
c
e
5
.
1
3
E+
0
8
6
2
2
9
3
2
3
6
K
u
r
t
o
si
s
5
9
.
0
1
6
6
6
6
1
.
9
6
6
7
S
k
e
w
n
e
ss
7
.
5
3
3
6
4
6
7
.
8
0
6
5
6
7
2
.
5
.
I
m
a
g
e
Cla
s
s
if
ica
t
io
n
C
las
s
i
f
icatio
n
is
t
h
e
p
r
o
ce
s
s
o
f
ca
teg
o
r
izin
g
a
g
iv
e
n
in
p
u
t
b
y
a
p
r
o
p
e
r
class
if
ier
.
T
h
e
o
b
j
ec
tiv
e
o
f
class
i
f
icatio
n
is
to
g
i
v
e
a
lab
el
to
ea
ch
MR
b
r
ain
i
m
a
g
e
b
ase
d
o
n
s
o
m
e
i
m
a
g
e
’
s
f
ea
t
u
r
es.
T
h
e
s
tr
u
c
tu
r
e
la
y
o
u
t
an
d
d
esig
n
o
f
a
class
i
f
ica
tio
n
s
y
s
te
m
i
n
v
o
lv
e
s
th
e
c
h
o
ice
an
d
ca
lcu
latio
n
o
f
f
ea
tu
r
e
s
f
r
o
m
th
e
i
m
ag
e
s
t
h
at
w
e
w
a
n
t to
class
if
y
as
s
h
o
w
n
in
F
ig
u
r
e
1
0
[
6
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
5
,
Octo
b
er
2
0
1
7
:
2
5
5
5
–
2
5
6
4
2562
Su
p
p
o
r
t
Vec
to
r
Ma
ch
i
n
e
(
SV
M)
class
i
f
ier
w
a
s
u
s
ed
i
n
th
i
s
w
o
r
k
as
i
t
h
as
s
h
o
w
n
to
r
e
s
u
l
t
in
g
r
ea
ter
ac
cu
r
ac
y
co
m
p
ar
ed
to
o
t
h
er
cl
ass
i
f
ier
s
tr
u
ct
u
r
es
i
n
t
h
e
cla
s
s
i
f
icatio
n
o
f
M
R
I
i
m
a
g
es
[
1
2
]
-
[
1
3
]
.
T
h
e
Su
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
(
SVM)
is
a
s
u
p
er
v
is
ed
lear
n
i
n
g
tech
n
iq
u
e
t
h
at
u
s
es
a
s
et
o
f
lab
elled
tr
ain
in
g
d
ata
as
i
n
p
u
t
to
tr
ain
th
e
cla
s
s
i
f
ier
a
n
d
p
r
o
d
u
c
e
in
p
u
t
-
o
u
t
p
u
t
m
ap
p
in
g
f
u
n
ct
i
o
n
s
.
Fig
u
r
e
1
0
.
I
m
a
g
e
C
las
s
i
f
icati
o
n
S
y
s
te
m
s
tr
u
c
tu
r
e
[
6
]
Fo
r
MRI
i
m
a
g
es,
t
h
e
S
VM
o
u
tp
u
t
is
a
h
y
p
er
p
lan
e
t
h
at
cla
s
s
i
f
ies
n
e
w
M
R
I
i
m
ag
e
s
.
Fo
r
th
e
ca
s
e
o
f
th
e
t
w
o
clas
s
-
clas
s
i
f
icatio
n
u
s
ed
in
th
i
s
w
o
r
k
,
t
h
e
p
r
o
ce
s
s
o
f
th
e
SVM
tech
n
iq
u
e
is
to
f
i
n
d
th
e
h
y
p
er
p
lan
e
t
h
a
t
p
r
o
v
id
es th
e
lar
g
es
t
m
i
n
i
m
u
m
d
is
tan
ce
to
th
e
tr
ai
n
i
n
g
d
ata
as
s
h
o
w
n
i
n
Fi
g
u
r
e
1
1
.
[
1
4
]
-
[
1
5
]
Fig
u
r
e
1
1
.
Op
tim
a
l h
y
p
er
p
la
n
e
in
SVM
[
1
5
]
T
h
e
SVM
class
i
f
ier
u
s
ed
in
t
h
is
w
o
r
k
p
r
o
v
id
es
th
e
p
o
s
s
ib
il
i
t
y
o
f
c
h
o
o
s
in
g
t
h
e
k
er
n
e
l
f
u
n
c
tio
n
[
1
3
]
.
T
h
e
k
er
n
el
f
u
n
c
tio
n
c
h
o
s
en
i
s
‘
R
B
F
’
th
a
t
r
ep
r
esen
ts
t
h
e
Ga
u
s
s
ian
R
ad
ial
B
asis
F
u
n
ctio
n
k
er
n
el.
T
h
is
ch
o
ice
w
a
s
b
ased
o
n
t
h
e
ex
ce
llen
t
p
er
f
o
r
m
an
ce
o
f
t
h
is
SVM
k
er
n
e
l
f
u
n
ct
io
n
as
r
ep
o
r
ted
in
t
h
e
li
ter
atu
r
e.
T
h
e
in
p
u
t
d
ata
s
et
w
a
s
d
iv
id
ed
i
n
t
w
o
s
u
b
s
et
s
,
a
tr
ain
i
n
g
s
et
co
n
s
is
t
in
g
o
f
te
n
n
o
r
m
a
l
i
m
a
g
e
s
an
d
f
if
tee
n
ab
n
o
r
m
al
i
m
a
g
es
a
n
d
a
tes
t
in
g
s
et
co
n
s
is
ti
n
g
o
f
t
h
e
r
e
m
a
in
i
n
g
te
n
n
o
r
m
al
an
d
f
i
f
teen
ab
n
o
r
m
al
i
m
ag
e
s
.
T
h
e
S
u
p
p
o
r
t
Ve
cto
r
Ma
ch
in
e
(
SVM)
cla
s
s
i
f
ier
w
as
tr
ai
n
ed
af
ter
ex
tr
ac
ti
n
g
th
e
f
ea
t
u
r
es a
n
d
lab
els
f
r
o
m
th
e
tr
ain
in
g
s
et
.
Af
ter
tr
ai
n
i
n
g
th
e
clas
s
i
f
ier
,
t
h
e
te
s
ti
n
g
s
et
w
as
u
s
ed
to
test
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
clas
s
i
f
ier
a
n
d
its
ab
ilit
y
to
ac
c
u
r
atel
y
c
lass
if
y
t
h
e
MRI
i
m
a
g
es
a
s
eit
h
er
n
o
r
m
al
o
r
ab
n
o
r
m
al.
T
o
ev
alu
ate
o
u
r
SVM
cla
s
s
i
f
ier
,
a
co
n
f
u
s
io
n
m
atr
i
x
w
as
b
u
ilt
as
s
h
o
w
n
i
n
T
ab
le
8.
an
d
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
clas
s
i
f
ier
ev
a
lu
ated
as
s
h
o
w
n
in
T
ab
le
IX
.
I
n
th
e
test
in
g
test
,
ten
i
m
a
g
es
w
er
e
lab
elled
as
No
r
m
al
an
d
th
e
r
e
m
a
in
i
n
g
f
if
tee
n
i
m
a
g
es
w
er
e
lab
elled
as
A
b
n
o
r
m
al.
As
in
d
icate
d
in
T
ab
le
9
,
th
e
class
i
f
i
er
s
u
cc
ee
d
ed
to
class
i
f
y
MRI
b
r
ain
i
m
a
g
es
i
n
to
n
o
r
m
al
a
n
d
ab
n
o
r
m
al
.
T
ab
le
8
.
C
o
n
f
u
s
io
n
Ma
tr
i
x
Pr
e
d
i
c
t
e
d
N
o
r
m
a
l
A
b
n
o
r
m
a
l
T
r
u
t
h
N
o
r
m
a
l
20
0
A
b
n
o
r
m
a
l
0
30
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
S
V
M C
la
s
s
if
ica
tio
n
o
f MR
I
B
r
a
in
I
ma
g
es fo
r
C
o
mp
u
ter
-
A
s
s
is
ted
Dia
g
n
o
s
is
(
Ma
d
in
a
Ha
mia
n
e
)
2563
T
ab
le
9.
P
er
f
o
r
m
an
ce
o
f
R
B
F
SVM
class
i
f
ier
C
l
a
ss
e
s
N
o
.
o
f
i
m
a
g
e
s
c
l
a
ssi
f
i
e
d
N
o
.
o
f
i
m
a
g
e
s
m
i
scl
a
ssi
f
i
e
d
S
e
n
si
t
i
v
i
t
y
sp
e
c
i
f
i
c
i
t
y
A
c
c
u
r
a
c
y
C
l
a
ss I
(N
o
r
m
a
l
)
2
0
0
1
0
0
%
1
0
0
%
1
0
0
%
C
l
a
ss I
I
(A
b
n
o
r
m
a
l
)
3
0
0
1
0
0
%
1
0
0
%
1
0
0
%
3.
SUM
M
ARY
O
F
RE
SUL
T
S
I
n
th
is
w
o
r
k
,
t
h
e
t
w
o
d
i
m
en
s
i
o
n
al
w
a
v
elet
to
o
lb
o
x
o
f
MA
T
L
A
B
w
a
s
u
s
ed
f
o
r
th
e
p
r
e
-
p
r
o
ce
s
s
i
n
g
o
f
th
e
i
m
a
g
es
b
y
ap
p
l
y
i
n
g
DW
T
to
r
e
m
o
v
e
th
e
n
o
is
e
f
r
o
m
M
R
I
b
r
ain
i
m
ag
e
s
.
T
h
e
p
r
o
ce
s
s
f
i
r
s
t
d
ec
o
m
p
o
s
es
t
h
e
i
m
a
g
e,
th
e
n
ap
p
lies
t
h
r
es
h
o
l
d
to
th
e
d
etail
co
ef
f
icie
n
ts
a
n
d
af
ter
t
h
at
r
ec
o
n
s
tr
u
ct
s
t
h
e
n
o
is
e
-
f
r
ee
i
m
a
g
e.
Dif
f
er
en
t
w
a
v
elets,
th
r
e
s
h
o
ld
in
g
tec
h
n
iq
u
es
w
it
h
v
ar
io
u
s
th
r
es
h
o
ld
s
elec
tio
n
t
y
p
es
wer
e
in
v
esti
g
ated
to
ch
o
o
s
e
th
e
b
est
w
a
v
elet
t
y
p
e
an
d
d
ec
o
m
p
o
s
itio
n
le
v
el
a
lo
n
g
w
i
th
t
h
e
b
est
t
h
r
es
h
o
ld
in
g
tech
n
iq
u
e.
T
h
e
ev
alu
a
tio
n
w
a
s
d
o
n
e
b
ased
o
n
th
e
v
al
u
es
o
f
th
e
t
h
r
ee
m
et
r
ics
MSE
,
SN
R
an
d
P
SNR
.
B
io
r
1
.
3
w
a
v
elet
h
as
p
r
o
v
en
to
b
e
th
e
b
est
w
a
v
elet
alo
n
g
w
it
h
t
h
e
f
ir
s
t
lev
e
l
o
f
d
ec
o
m
p
o
s
i
tio
n
,
h
ar
d
th
r
e
s
h
o
ld
i
n
g
an
d
B
al.
s
p
ar
s
it
y
-
n
o
r
m
(
s
q
r
t)
as
th
e
m
et
h
o
d
o
f
t
h
r
es
h
o
ld
s
elec
tio
n
v
alu
e.
B
io
r
1
.
3
w
av
e
let
w
a
s
ap
p
lied
o
n
all
im
a
g
e
s
th
at
w
er
e
u
s
ed
in
t
h
i
s
w
o
r
k
.
MA
T
L
A
B
f
u
n
ct
io
n
s
f
r
o
m
t
h
e
I
m
ag
e
p
r
o
ce
s
s
in
g
a
n
d
t
h
e
b
io
i
n
f
o
r
m
atics
to
o
lb
o
x
es
w
er
e
th
e
n
u
s
ed
i
n
th
e
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
p
h
ase.
E
d
g
e
d
etec
tio
n
w
a
s
ap
p
lied
a
s
t
h
e
f
ir
s
t
s
tep
to
d
etec
t
t
h
e
e
d
g
es
o
f
MRI
b
r
ai
n
i
m
a
g
es.
C
a
n
n
y
m
et
h
o
d
w
as
t
h
en
u
s
ed
w
h
ic
h
g
a
v
e
v
er
y
g
o
o
d
r
esu
lt
s
.
T
h
e
ed
g
e
s
w
er
e
o
u
tl
in
ed
o
n
t
h
e
o
r
ig
i
n
al
i
m
a
g
e
to
d
i
f
f
er
e
n
tiate
b
et
w
ee
n
t
h
e
v
ar
io
u
s
tis
s
u
es
o
f
t
h
e
b
r
ain
,
an
d
t
h
e
n
t
h
e
b
r
ain
i
m
ag
es
w
er
e
s
e
g
m
e
n
ted
b
ased
o
n
in
te
n
s
it
y
s
e
g
m
e
n
tati
o
n
b
y
u
s
in
g
O
t
s
u
’
s
m
e
th
o
d
as
a
s
ec
o
n
d
s
tep
.
T
h
e
last
s
tep
o
f
i
m
ag
e
p
r
o
ce
s
s
i
n
g
w
a
s
to
ap
p
ly
t
h
e
m
o
r
p
h
o
lo
g
ic
al
o
p
er
atio
n
s
o
f
er
o
s
io
n
an
d
d
ilatio
n
to
ex
tr
ac
t t
h
e
r
eg
io
n
o
f
i
n
ter
est.
T
h
e
s
tep
s
u
s
ed
i
n
p
r
o
ce
s
s
i
n
g
t
h
e
M
R
I
b
r
ain
i
m
a
g
es
h
a
v
e
s
h
o
w
n
e
f
f
ec
t
iv
e
e
x
tr
ac
tio
n
o
f
th
e
r
eg
io
n
o
f
in
ter
est
f
r
o
m
t
h
e
t
w
en
t
y
n
o
r
m
al
an
d
t
h
ir
t
y
ab
n
o
r
m
al
i
m
a
g
e
s
.
T
h
e
ex
tr
ac
ted
r
e
g
io
n
o
f
in
ter
e
s
t
w
a
s
t
h
e
n
u
s
ed
i
n
th
e
p
o
s
t
p
r
o
ce
s
s
i
n
g
s
tep
f
o
r
th
e
e
x
tr
ac
tio
n
o
f
t
h
eir
f
ea
tu
r
es.
G
L
C
M
w
as
u
s
ed
to
cr
ea
t
e
a
g
r
a
y
lev
e
l
co
-
o
cc
u
r
r
en
ce
m
atr
i
x
f
r
o
m
i
m
a
g
es
.
G
L
C
M
y
ield
ed
1
1
d
is
tin
ct
f
ea
t
u
r
es
t
h
at
w
er
e
s
u
b
s
e
q
u
en
tl
y
u
s
ed
in
th
e
class
i
f
icatio
n
s
tep
.
T
h
e
f
ea
t
u
r
es
w
er
e
ex
tr
ac
ted
f
r
o
m
ea
c
h
o
f
t
h
e
f
if
t
y
b
r
ai
n
i
m
ag
e
s
to
f
o
r
m
t
h
e
f
ea
tu
r
e
m
atr
i
x
ch
ar
ac
ter
is
i
n
g
t
h
e
i
m
ag
e
.
C
las
s
if
ica
tio
n
w
as
p
er
f
o
r
m
ed
u
s
i
n
g
Su
p
p
o
r
t
Vec
to
r
m
ac
h
i
n
e
w
i
th
Gau
s
s
i
a
n
R
ad
ial
B
asis
Fu
n
ctio
n
k
er
n
el
w
h
ich
r
esu
lted
i
n
an
e
f
f
ec
ti
v
e
class
i
f
i
ca
tio
n
o
f
all
i
m
ag
e
s
w
it
h
1
0
0
% a
cc
u
r
ac
y
.
4.
CO
NCLU
SI
O
N
MRI
i
m
a
g
es
h
a
v
e
m
a
n
y
a
d
v
an
ta
g
es
i
n
b
io
m
ed
ical
en
g
in
ee
r
i
n
g
co
m
p
ar
ed
to
o
th
e
r
im
a
g
i
n
g
tech
n
iq
u
es.
T
h
i
s
w
o
r
k
f
o
c
u
s
ed
o
n
b
r
ain
i
m
a
g
es
b
ec
au
s
e
lar
g
e
ar
ea
s
o
f
th
e
o
r
g
an
p
r
o
ce
s
s
ar
e
af
f
ec
ted
b
y
b
r
ai
n
in
j
u
r
ies.
Mo
s
t
m
o
v
e
m
en
t a
n
d
b
o
d
y
f
u
n
ctio
n
s
ar
e
co
n
tr
o
lled
an
d
co
o
r
d
in
ated
b
y
th
e
b
r
ain
.
De
-
n
o
is
i
n
g
o
f
M
R
I
b
r
ain
i
m
ag
es
w
a
s
o
n
e
o
f
th
e
o
b
j
ec
tiv
es
o
f
th
i
s
w
o
r
k
.
I
t
w
as
f
o
u
n
d
th
at
MRI
b
r
ain
i
m
a
g
es
ca
n
b
e
ef
f
ic
ien
t
l
y
d
e
n
o
is
ed
u
s
in
g
t
h
e
Dis
cr
ete
W
av
elet
T
r
a
n
s
f
o
r
m
s
(
DW
T
)
w
ith
t
h
r
esh
o
ld
i
n
g
a
s
co
n
f
ir
m
ed
b
y
th
e
o
p
ti
m
al
m
et
r
ics
v
al
u
es
o
b
tain
ed
.
Fu
r
t
h
er
en
h
a
n
ce
m
en
t
o
f
th
e
i
m
a
g
es
w
a
s
o
b
tain
ed
th
r
o
u
g
h
th
e
u
s
e
o
f
ed
g
e
d
etec
tio
n
a
n
d
th
r
es
h
o
ld
s
e
g
m
en
ta
tio
n
.
I
t
was
s
h
o
w
n
th
a
t
e
li
m
i
n
atio
n
o
f
th
e
ed
g
e
d
etec
tio
n
s
tep
r
esu
l
ted
in
s
eg
m
e
n
tatio
n
in
ac
c
u
r
ac
i
es.
I
n
ad
d
itio
n
,
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
s
w
er
e
u
s
ed
to
e
x
tr
ac
t
t
h
e
r
eg
io
n
o
f
i
n
ter
est i
n
t
h
e
i
m
a
g
e.
Sev
er
al
f
ea
t
u
r
es
w
er
e
e
x
tr
ac
t
ed
f
r
o
m
t
h
e
e
n
h
a
n
ce
d
MRI
i
m
ag
e
s
a
n
d
w
er
e
u
s
ed
t
o
tr
ai
n
an
SVM
class
i
f
ier
w
it
h
R
B
F
k
er
n
el
w
h
ich
s
u
cc
ee
d
ed
in
cla
s
s
i
f
y
i
n
g
t
h
e
MRI
b
r
ain
i
m
a
g
e
s
as
n
o
r
m
al
o
r
ab
n
o
r
m
al.
T
h
e
ac
cu
r
ac
y
o
f
th
e
S
VM
m
o
d
el
w
a
s
f
o
u
n
d
to
b
e
1
0
0
%
w
h
ic
h
o
u
tp
er
f
o
r
m
s
r
es
u
lt
s
r
ep
o
r
ted
in
th
e
liter
at
u
r
e.
Th
is
ac
cu
r
ate
class
if
ica
tio
n
o
f
t
h
e
SVM
class
i
f
ier
ca
n
b
e
u
s
e
d
b
y
n
e
u
r
o
lo
g
i
s
ts
to
h
elp
t
h
e
m
to
id
en
ti
f
y
th
e
ab
n
o
r
m
alit
y
th
a
t
m
i
g
h
t b
e
h
id
d
en
,
d
u
e
to
th
e
lar
g
e
n
u
m
b
er
o
f
s
lice
s
th
a
t a
r
e
o
b
tain
ed
f
r
o
m
MRI
b
r
ain
i
m
a
g
es.
RE
F
E
R
E
NC
E
S
[
1
]
K.
&
Be
c
k
e
r
J.,
T
h
e
W
h
o
le Brain
A
tl
a
s [
h
tt
p
:/
/w
ww
.
m
e
d
.
h
a
rv
a
rd
.
e
d
u
/
a
a
n
li
b
/
h
o
m
e
.
h
tm
l]
[
2
]
A
.
Dix
it
,
&
P
.
S
h
a
rm
a
,
“
A
C
o
m
p
a
ra
ti
v
e
S
tu
d
y
o
f
W
a
v
e
l
e
t
Th
re
sh
o
l
d
in
g
f
o
r
Im
a
g
e
D
e
n
o
isin
g
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ima
g
e
,
Gr
a
p
h
ics
a
n
d
S
ig
n
a
l
Pro
c
e
ss
in
g
,
39
-
4
6
.
,
2
0
1
4
.
[
3
]
A
.
G
e
o
rg
,
&
A
.
P
ra
b
a
v
a
th
y
,
“
A
S
u
rv
e
y
On
Di
ff
e
re
n
t
A
p
p
ro
a
c
h
e
s
Us
e
d
In
Im
a
g
e
Qu
a
li
ty
As
se
ss
m
e
n
t”,
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Eme
rg
i
n
g
T
e
c
h
n
o
l
o
g
y
a
n
d
Ad
v
a
n
c
e
d
En
g
i
n
e
e
rin
g
,
Vo
lu
m
e
3
,
Iss
u
e
2
,
2
0
1
3
.
[
4
]
C.
V
a
rn
a
n
,
A
.
Ja
g
a
n
,
J.
Ka
u
r,
D
.
J
y
o
ti
,
&
D.
Ra
o
,
“
I
m
a
g
e
Qu
a
l
it
y
A
ss
e
ss
m
e
n
t
T
e
c
h
n
iq
u
e
s
p
n
S
p
a
ti
a
l
Do
m
a
in
”
,
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
Vo
l.
2
,
Iss
u
e
3
,
2
0
1
1
.
[
5
]
S
.
Nish
a
,
“
Im
a
g
e
Qu
a
li
t
y
A
ss
e
s
s
m
e
n
t
T
e
c
h
n
iq
u
e
s”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
Res
e
a
r
c
h
in
Co
mp
u
ter
S
c
ien
c
e
a
n
d
S
o
ft
w
a
re
En
g
in
e
e
rin
g
,
V
o
l
u
m
e
3
,
Iss
u
e
7
,
2
0
1
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
5
,
Octo
b
er
2
0
1
7
:
2
5
5
5
–
2
5
6
4
2564
[
6
]
O.
M
a
rq
u
e
s,
P
ra
c
ti
c
a
l
Im
a
g
e
a
n
d
V
id
e
o
P
r
o
c
e
ss
in
g
Us
in
g
M
A
TL
AB,
b
y
Jo
h
n
W
il
e
y
&
S
o
"
n
s,
In
c
.
,
2
0
1
1
.
[
7
]
A
.
Ku
lk
a
rn
i,
&
R.
K
a
m
a
th
e
,
“
M
RI
Bra
in
Im
a
g
e
S
e
g
m
e
n
tatio
n
b
y
Ed
g
e
De
te
c
ti
o
n
a
n
d
Re
g
io
n
S
e
lec
ti
o
n
”
,
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
T
e
c
h
n
o
lo
g
y
a
n
d
S
c
ien
c
e
,
Iss
u
e
.
2
,
V
o
l.
1
,
2
0
1
4
[
8
]
G
.
E
v
e
li
n
S
u
jj
i
,
Y.
V
.
S
.
L
a
k
sh
m
i
,
&
G
.
W
ise
li
n
Ji,
“
M
RI
Bra
in
I
m
a
g
e
S
e
g
m
e
n
tatio
n
b
a
se
d
o
n
T
h
re
sh
o
ld
in
g
”
,
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
Co
m
p
u
ter
Res
e
a
rc
h
,
Vo
l.
3
,
No
.
1
,
Iss
u
e
8
,
2
0
1
3
.
[
9
]
Ic
k
e
,
G
u
z
id
e
,
Ka
m
a
rth
i,
V.S
a
g
a
r
,
“
F
e
a
tu
re
e
x
trac
ti
o
n
th
r
o
u
g
h
d
isc
r
e
te wa
v
e
l
e
t
tran
sf
o
r
m
c
o
e
ff
icie
n
ts”
,
In
telli
g
e
n
t
S
y
ste
ms
in
De
sig
n
a
n
d
M
a
n
u
f
a
c
tu
rin
g
VI
,
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
S
PI
E
,
Vo
lu
m
e
5
9
9
9
,
p
p
.
2
7
-
3
5
,
2
0
0
5
.
[
1
0
]
S
.
S
h
a
h
,
&
N C
h
a
u
h
a
n
,
“
Clas
sif
ic
a
ti
o
n
o
f
Bra
in
M
RI
Im
a
g
e
s u
sin
g
Co
m
p
u
tatio
n
a
l
I
n
telli
g
e
n
t
T
e
c
h
n
i
q
u
e
s”
,
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
Ap
p
l
ica
ti
o
n
s
,
Vo
l
u
m
e
1
2
4
,
N
o
.
1
4
.
2
0
1
5
.
[
1
1
]
Zu
lp
e
,
N.
&
P
a
w
a
r,
V
.
,
“
G
L
C
M
T
e
x
tu
ra
l
F
e
a
tu
re
s
f
o
r
Bra
in
T
u
m
o
r
Clas
sif
ic
a
ti
o
n
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
mp
u
ter
S
c
ien
c
e
Iss
u
e
s
,
Vo
l.
9
,
Iss
u
e
3
,
No
3
,
2
0
1
2
[
1
2
]
V
.
Jo
se
p
h
in
e
,
&
P
.
L
a
th
a
,
“
S
VM
-
Ba
se
d
A
u
to
m
a
ti
c
M
e
d
ica
l
De
c
isi
o
n
S
u
p
p
o
rt
S
y
ste
m
F
o
r
M
e
d
ica
l
Im
a
g
e
”
,
J
o
u
rn
a
l
o
f
T
h
e
o
re
ti
c
a
l
a
n
d
A
p
p
l
ied
I
n
fo
r
ma
ti
o
n
T
e
c
h
n
o
l
o
g
,
V
o
l.
6
6
No
.
3
.
,
2
0
1
4
.
[
1
3
]
A
Yu
n
iarti,
"
Clas
si
f
ica
ti
o
n
a
n
d
n
u
m
b
e
rin
g
o
f
d
e
n
tal
ra
d
io
g
ra
p
h
s
f
o
r
a
n
a
u
to
m
a
ted
h
u
m
a
n
id
e
n
ti
f
ica
ti
o
n
sy
ste
m
,
”
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
0
,
n
o
.
1
,
p
p
.
1
3
7
-
1
4
6
,
2
0
1
2
.
[
1
4
]
D.
Bo
sw
e
ll
,
In
tro
d
u
c
ti
o
n
to
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
i
n
e
s,
a
v
a
il
a
b
le at:
h
tt
p
:/
/
d
u
stw
e
ll
.
c
o
m
/P
a
stW
o
rk
/In
tro
T
o
S
V
M
.
p
d
f
[
1
5
]
Op
e
n
CV,
In
tr
o
d
u
c
ti
o
n
t
o
S
u
p
p
o
rt
M
a
c
h
in
e
s,
a
v
a
il
a
b
le
a
t:
h
tt
p
:/
/d
o
c
s.o
p
e
n
c
v
.
o
rg
/2
.
4
/
d
o
c
/t
u
to
r
ials/m
l/
in
tro
d
u
c
t
io
_
to
_
sv
m
/i
n
tro
d
u
c
ti
o
n
_
to
_
sv
m
.
h
tm
l
Evaluation Warning : The document was created with Spire.PDF for Python.