I
n
d
on
e
s
ian
Jou
r
n
al
o
f
E
lec
t
r
ica
l
E
n
gin
e
e
r
in
g
a
n
d
Com
p
u
t
e
r
S
c
ience
Vo
l
.
21
,
N
o
.
3
,
M
a
r
c
h
2021
,
pp.
1435
~
1443
I
S
S
N:
25
02
-
4752,
DO
I
:
10
.
11591/i
j
e
e
c
s
.
v
21
.i
3
.
pp
1435
-
1443
1435
Jou
r
n
al
h
o
m
e
page
:
ht
tp:
//
ij
e
e
c
s
.
iaes
c
or
e
.
c
om
A
h
y
b
r
id
d
e
-
n
oi
si
n
g
m
e
t
h
o
d
f
or
m
a
m
m
ogr
a
m
i
m
age
s
Ras
h
id
M
e
h
m
ood
Gon
d
al
1
,
S
aim
a
Anwar
L
as
h
ar
i
2
,
M
u
r
t
aj
a
Al
i
S
aar
e
3
,
S
ar
i
Al
i
S
ar
i
4
1
D
e
p
art
men
t
o
f
C
o
m
p
u
t
e
r
S
c
i
en
ce
,
t
h
e
U
n
i
v
e
rs
i
t
y
o
f
L
a
h
o
r
e
,
Sar
g
o
d
h
a
,
Pak
i
s
t
an
2
Co
l
l
eg
e
o
f
Co
m
p
u
t
i
n
g
an
d
I
n
f
o
r
m
at
i
c
s
,
Sau
d
i
E
l
ec
t
ro
n
i
c
U
n
i
v
e
rs
i
t
y
,
D
a
mm
a
m
,
Sau
d
i
A
rab
i
a
3
Sch
o
o
l
o
f
C
o
m
p
u
t
i
n
g
,
U
n
i
v
e
rs
i
t
i
U
t
ara
Mal
a
y
s
i
a
,
K
a
d
a
h
,
Mal
a
y
s
i
a
4
Fac
u
l
t
y
o
f
Co
m
p
u
t
e
r
S
ci
e
n
ce
a
n
d
I
n
f
o
r
m
at
i
o
n
T
ech
n
o
l
o
g
y
U
n
i
v
e
rs
i
t
i
T
u
n
H
u
s
s
e
i
n
,
J
o
h
o
r,
Mal
a
y
s
i
a
Ar
t
ic
l
e
I
n
f
o
AB
S
T
RA
CT
A
r
ti
c
le
h
is
tor
y
:
R
e
c
e
i
ve
d
M
a
y
1
7
,
2020
R
e
vi
s
e
d
S
e
p
1
8
,
2020
A
c
c
e
pt
e
d
N
o
v
11
,
2020
I
n
g
en
e
ral
,
m
a
mmo
g
ra
m
i
m
a
g
e
s
are
co
n
t
a
m
i
n
at
ed
w
i
t
h
n
o
i
s
e
w
h
i
c
h
d
i
rec
t
l
y
affec
t
s
i
m
a
g
e
q
u
al
i
t
y
.
S
ev
e
ral
me
t
h
o
d
s
h
a
v
e
b
een
p
ro
p
o
s
e
d
t
o
d
e
-
n
o
i
s
e
t
h
e
s
e
i
m
ag
e
s
,
h
o
w
ev
e
r,
t
h
e
r
e
i
s
al
w
a
y
s
a
r
i
s
k
o
f
l
o
s
i
n
g
v
a
l
u
ab
l
e
i
n
fo
r
m
at
i
o
n
.
I
n
o
rd
e
r
t
o
o
v
e
r
co
me
t
h
e
l
o
s
s
o
f
i
n
fo
r
m
at
i
o
n
,
t
h
e
p
re
s
en
t
s
t
u
d
y
p
ro
p
o
s
ed
a
H
y
b
ri
d
d
en
o
i
s
i
n
g
me
t
h
o
d
f
o
r
m
a
mm
o
g
ra
m
i
m
ag
e
s
.
T
h
e
p
ro
p
o
s
e
d
h
y
b
ri
d
me
t
h
o
d
w
o
rk
s
i
n
t
w
o
s
t
e
p
s
:
Fi
rs
t
l
y
,
p
re
p
ro
ce
s
s
i
n
g
w
i
t
h
m
at
h
em
at
i
c
al
mo
rp
h
o
l
o
g
y
w
as
ap
p
l
i
e
d
fo
r
i
m
ag
e
e
n
h
an
cemen
t
.
Sec
o
n
d
l
y
,
a
g
l
o
b
al
u
n
s
y
mme
t
ri
c
al
t
ri
mme
d
med
i
a
n
fi
l
t
e
r
(G
U
T
M)
i
s
ap
p
l
i
e
d
t
o
a
de
-
n
o
i
s
e
i
m
ag
e
.
E
x
p
e
ri
men
t
al
r
e
s
u
l
t
s
p
ro
v
e
t
h
at
t
h
e
p
ro
p
o
s
ed
me
t
h
o
d
w
o
r
k
s
w
el
l
f
o
r
m
a
mm
o
g
ra
m
i
m
a
g
e
s
.
H
en
ce
,
t
h
e
s
t
u
d
y
p
ro
v
i
d
e
d
a
n
al
t
e
rn
at
i
v
e
me
t
h
o
d
f
o
r
d
en
o
i
s
i
n
g
m
a
mmo
g
ra
m
i
m
ag
e
s
.
K
e
y
w
o
r
d
s
:
B
r
e
a
s
t
c
a
n
c
e
r
G
l
o
b
a
l
u
n
s
ymm
e
t
r
i
c
a
l
t
r
i
m
m
e
d
m
e
d
i
a
n
H
y
b
r
i
d
de
n
o
i
s
i
ng
m
e
t
h
o
d
M
a
m
m
o
gr
a
m
i
m
a
ge
s
Th
i
s
i
s
a
n
o
p
en
a
c
ces
s
a
r
t
i
c
l
e
u
n
d
e
r
t
h
e
CC
B
Y
-
SA
l
i
cen
s
e.
C
or
r
e
s
pon
din
g
A
u
th
or
:
M
ur
t
a
j
a
Ali
S
a
a
r
e
S
c
h
o
o
l
o
f
C
o
m
put
i
n
g
Uni
ve
r
s
i
t
i
Ut
a
r
a
M
a
l
a
y
s
i
a
S
i
n
t
o
k
,
06010
B
uki
t
K
a
y
u
H
i
t
a
m
,
K
e
da
h
,
M
a
l
a
y
s
ia
E
m
a
i
l
:
mm
ur
t
a
j
a
88
@
g
m
a
il
.
c
o
m
1.
I
NT
RODU
C
T
I
ON
M
e
d
i
c
a
l
i
m
a
ge
s
c
a
r
r
y
v
a
l
ua
bl
e
i
nf
o
r
m
a
t
i
o
n
t
h
a
t
pl
a
y
s
a
vi
t
a
l
r
o
l
e
i
n
t
h
e
d
i
a
g
n
o
s
i
s
a
n
d
pr
o
gn
o
s
i
s
o
f
d
i
s
e
a
s
e
s
by
t
a
k
i
ng
s
i
g
nif
i
c
a
n
t
i
m
a
ge
s
o
f
t
h
e
h
u
m
a
n
b
o
d
y
.
I
t
i
nv
o
l
ve
s
im
a
ge
c
l
a
s
s
if
i
c
a
t
i
o
n
,
im
a
ge
s
e
g
m
e
n
t
a
t
i
o
n
[
1]
,
i
m
a
ge
m
a
t
c
hi
ng,
c
h
a
n
g
e
i
n
s
e
que
n
c
e
,
a
n
d
f
e
a
t
ur
e
e
x
t
r
a
c
t
i
o
n
.
M
o
s
t
l
y
t
h
e
r
a
d
i
o
l
o
g
y
de
pa
r
t
m
e
n
t
us
e
s
t
h
e
s
e
m
e
d
i
c
a
l
im
a
g
e
s
,
i
n
w
hi
c
h
d
i
a
g
n
o
s
i
s
a
n
d
pr
o
gn
o
s
i
s
o
f
t
h
e
d
i
s
e
a
s
e
a
r
e
do
n
e
a
r
e
x
-
r
a
y
,
c
o
m
put
e
d
to
m
o
gr
a
phy
(
C
T
)
,
po
s
i
t
r
o
n
e
mi
s
s
i
o
n
to
m
o
gr
a
phy
(
P
E
T
)
,
m
a
g
n
e
t
i
c
r
e
s
o
n
a
n
c
e
im
a
g
i
ng
(
M
R
I
)
,
u
l
t
r
a
s
o
un
d
,
a
n
d
d
i
g
i
t
a
l
m
a
m
m
o
gr
a
m
im
a
ge
s
.
A
m
a
mm
o
gr
a
m
i
s
o
n
e
o
f
t
h
e
m
a
j
o
r
t
y
p
e
s
o
f
m
e
d
i
c
a
l
im
a
ge
s
t
h
a
t
a
r
e
us
e
d
f
o
r
t
h
e
e
a
r
ly
de
t
e
c
t
i
o
n
o
f
b
r
e
a
s
t
c
a
n
c
e
r
i
n
wo
m
e
n
.
As
t
h
e
s
e
im
a
ge
s
a
r
e
c
o
n
t
a
m
i
na
t
e
d
w
it
h
n
o
i
s
e
dur
i
n
g
t
h
e
i
r
a
c
qu
i
s
i
t
i
o
n
.
D
i
f
f
e
r
e
n
t
t
y
pe
s
o
f
n
o
i
s
e
s
c
r
e
a
t
e
a
n
i
n
t
e
n
s
i
t
y
i
n
i
m
a
ge
s
w
hi
c
h
i
nc
l
ude
s
:
ga
u
s
s
i
a
n
n
o
i
s
e
,
s
p
e
c
k
l
e
n
o
i
s
e
,
s
a
l
t
a
n
d
pe
ppe
r
n
o
i
s
e
,
a
m
p
l
if
i
e
r
n
o
i
s
e
,
po
i
s
o
n
n
o
i
s
e
,
a
n
d
qua
n
t
i
z
a
t
i
o
n
.
I
m
a
ge
d
e
n
o
i
s
i
ng
i
s
t
h
e
t
e
c
hnique
us
e
d
to
a
v
o
i
d
t
h
e
pr
o
bl
e
m
s
o
f
i
m
a
ge
s
s
uc
h
a
s
s
i
g
n
a
l
d
is
to
r
t
i
o
n
a
n
d
u
n
wa
n
t
e
d
n
o
i
s
e
.
I
m
a
ge
de
n
o
i
s
i
ng
t
a
ke
s
a
vi
t
a
l
po
s
i
t
i
o
n
i
n
i
m
a
ge
pr
o
c
e
s
s
i
n
g.
I
m
a
g
e
de
-
n
o
i
s
i
ng
us
e
s
d
i
f
f
e
r
e
n
t
m
e
t
h
o
ds
s
uc
h
a
s
m
e
d
i
a
n
f
il
t
e
r
i
n
g,
m
e
a
n
f
i
l
t
e
r
i
n
g
,
a
n
d
w
i
nne
r
f
il
t
e
r
to
m
a
ke
t
h
e
i
m
a
g
e
s
c
l
e
a
r
a
n
d
f
i
ne
[
2]
.
B
a
s
i
c
a
ll
y
,
t
wo
t
y
pe
s
o
f
m
o
de
l
s
a
r
e
u
s
e
d
i
n
im
a
ge
de
n
o
i
s
i
n
g:
li
ne
a
r
a
n
d
n
o
nli
ne
a
r
f
il
t
e
r
i
ng.
I
n
e
a
r
l
y
,
li
ne
r
f
il
t
e
r
s
s
uc
h
a
s
m
e
a
n
a
n
d
w
i
e
n
e
r
f
il
t
e
r
s
we
r
e
f
u
n
da
m
e
n
t
a
l
t
oo
l
s
f
o
r
i
m
a
ge
i
m
pr
o
v
e
m
e
nt.
T
h
e
s
e
t
e
c
h
ni
que
s
we
r
e
e
a
s
y
t
o
de
s
i
g
n
[
3]
a
n
d
i
m
p
l
e
m
e
n
t
.
T
h
e
s
e
f
i
l
t
e
r
s
h
a
v
e
s
a
t
i
s
f
y
i
ng
pe
r
f
o
r
m
a
n
c
e
i
n
m
a
ny
o
pe
r
a
t
i
o
n
s
s
uc
h
a
s
m
e
a
n
f
i
l
t
e
r
go
o
d
f
o
r
r
e
m
o
vi
n
g
gr
a
i
n
n
o
i
s
e
w
hil
e
w
i
e
n
e
r
f
il
t
e
r
goo
d
f
o
r
r
e
m
o
vi
ng
a
dd
i
t
i
v
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2502
-
4752
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
,
Vo
l
.
21
,
N
o
.
3
,
M
a
r
c
h
2021
:
1435
-
1443
1436
n
o
i
s
e
,
b
o
t
h
f
il
t
e
r
s
a
r
e
a
l
s
o
us
e
d
f
o
r
r
e
m
o
v
i
ng
n
o
i
s
e
,
h
o
we
v
e
r
,
s
o
m
e
t
i
m
e
s
i
t
h
a
s
po
o
r
r
e
s
ul
t
s
l
i
ke
li
n
e
a
r
f
i
l
t
e
r
m
o
s
t
l
y
t
e
n
d
t
o
bl
ur
t
h
e
e
dge
o
f
p
i
xe
l
a
n
d
d
i
d
n
’
t
r
e
m
o
v
e
t
h
e
G
a
u
s
s
i
a
n
n
o
i
s
e
a
n
d
mi
xe
d
n
o
i
s
e
[
4]
.
T
h
e
r
e
f
o
r
e
,
t
h
e
n
o
nl
i
ne
a
r
de
n
o
i
s
i
ng
t
e
c
hni
que
s
h
a
vi
ng
gr
e
a
t
e
r
c
o
e
f
f
i
c
i
e
n
t
s
whi
c
h
s
h
o
w
t
h
e
s
i
g
n
a
l
a
n
d
th
e
n
o
i
s
e
c
o
e
f
f
i
c
i
e
n
t
s
a
r
e
tr
i
e
d
to
r
e
duc
e
to
n
o
n
e
.
T
h
e
s
e
f
il
t
e
r
i
n
g
t
e
c
hni
que
s
h
a
v
e
v
a
r
i
o
us
a
d
v
a
n
t
a
ge
s
a
n
d
d
i
s
a
d
v
a
n
t
a
ge
s
[5
-
7]
.
Am
o
n
g
t
h
e
d
if
f
e
r
e
n
t
f
il
t
e
r
s
,
n
o
o
n
e
o
v
e
r
c
o
m
e
s
o
t
h
e
r
s
w
i
t
h
r
e
s
pe
c
t
to
c
o
m
put
a
t
i
o
n
a
l
c
o
s
t
,
d
e
n
o
i
s
i
n
g
,
a
n
d
e
nh
a
n
c
e
m
e
n
t
o
f
t
h
e
r
e
s
u
l
t
a
n
t
i
m
a
g
e
.
T
h
e
r
e
f
o
r
e
,
e
a
c
h
n
o
i
s
e
r
e
m
o
va
l
m
e
t
h
o
d
c
a
n
b
e
im
pr
o
v
e
d
f
u
r
t
h
e
r
a
n
d
s
t
i
ll
i
s
a
n
o
pe
n
r
e
s
e
a
r
c
h
a
r
e
a
.
S
a
wa
n
[
8]
pr
o
p
o
s
e
d
a
n
e
nh
a
n
c
e
m
e
n
t
m
e
t
h
o
d
f
o
r
m
e
d
i
c
a
l
i
m
a
ge
s
by
s
upe
r
-
r
e
s
o
l
ut
i
o
n
.
B
y
us
i
ng
d
i
f
f
e
r
e
n
t
f
il
t
e
r
s
s
u
c
h
a
s
tot
a
l
v
a
r
i
a
t
i
o
n
s
de
c
o
m
po
s
i
t
i
o
n
,
s
t
o
c
k
f
i
l
t
e
r
,
a
n
d
li
ne
a
r
i
n
t
e
r
po
l
a
t
i
o
n
.
T
h
e
s
t
o
c
k
f
i
l
t
e
r
wo
r
ks
f
o
r
e
dge
e
nh
a
n
c
e
m
e
n
t
a
n
d
s
e
g
m
e
n
t
a
t
i
o
n
.
I
n
l
i
ne
a
r
i
n
t
e
r
po
l
a
t
i
o
n
,
u
n
k
n
o
wn
l
o
c
a
t
i
o
ns
f
i
nd
o
ut
b
y
k
n
o
w
n
da
t
a
v
a
l
u
e
s
.
T
h
e
r
e
f
o
r
e
,
us
i
ng
t
h
e
m
e
d
i
a
n
,
f
r
o
s
t
,
a
n
d
w
i
e
n
e
r
a
l
o
t
o
f
n
o
i
s
e
is
r
e
duc
e
d.
K
a
n
ka
r
iy
a
a
n
d
Gupt
a
[
9]
pr
o
p
o
s
e
d
t
h
e
a
r
i
t
hm
e
t
i
c
m
e
a
n
f
il
t
e
r
i
ng
t
e
c
hni
q
ue
t
h
a
t
wo
r
k
s
a
u
to
m
a
t
i
c
a
l
ly
a
s
t
h
e
n
o
i
s
e
o
c
c
ur
s
.
T
hi
s
t
e
c
hni
que
wo
r
k
wh
e
n
t
h
e
p
i
xe
l
s
i
n
t
h
e
i
m
a
ge
a
r
e
f
o
u
n
de
d
c
o
r
r
up
t
e
d
,
i
t
r
e
m
o
v
e
s
t
h
e
p
i
xe
l
s
a
n
d
r
e
p
l
a
c
e
s
t
h
a
t
w
i
t
h
e
s
t
i
m
a
t
e
d
va
l
ue
s
.
J
a
i
s
wa
l
[
10]
pr
o
p
o
s
e
d
a
n
e
w
a
pp
r
o
a
c
h
e
d
f
o
r
t
h
e
r
e
duc
t
i
o
n
o
f
po
i
s
o
n
n
o
i
s
e
i
n
d
i
g
i
t
a
l
i
m
a
ge
s
.
F
o
r
de
n
o
i
s
i
n
g
m
e
d
i
a
n
f
il
t
e
r
,
w
i
e
n
e
r
f
il
t
e
r
,
t
h
r
e
s
ho
l
d
i
ng
t
e
c
hni
que
s
we
r
e
a
pp
l
i
e
d.
T
hi
s
t
e
c
h
ni
qu
e
wo
r
ks
o
n
im
a
ge
de
c
o
m
po
s
i
t
i
o
n
,
us
i
n
g
w
a
v
e
l
e
t
t
r
a
n
s
f
o
r
m
a
n
d
t
h
e
n
i
t
a
pp
li
e
s
h
a
r
d
t
h
r
e
s
h
o
l
d
i
ng
a
n
d
s
o
f
t
t
h
r
e
s
h
o
l
d
i
ng
t
e
c
h
ni
que
s
f
o
r
i
m
a
ge
s
de
n
o
i
s
i
ng.
T
hi
s
t
e
c
hni
que
wa
s
us
e
d
o
n
256
x
256
n
o
i
s
y
im
a
ge
s
.
S
o
t
h
e
b
e
s
t
r
e
s
u
l
t
wa
s
f
o
u
n
d
by
us
i
ng
t
h
e
c
o
m
bi
na
t
i
o
n
o
f
t
h
e
f
il
t
e
r
i
n
g
m
e
t
h
o
d
a
n
d
t
h
r
e
s
h
o
l
d
t
e
c
hni
que
s
.
E
v
e
n
t
h
o
ugh
s
o
m
e
e
xi
s
t
i
n
g
li
ne
a
r
a
n
d
n
o
n
-
li
ne
a
r
f
i
l
t
e
r
s
a
r
e
go
o
d
to
de
-
n
o
i
s
e
a
n
d
e
nh
a
nc
e
m
e
d
i
c
a
l
im
a
ge
s
,
h
o
we
ve
r
,
n
o
t
b
e
s
t
f
o
r
m
a
m
m
o
gr
a
m
im
a
g
e
s
[
11]
.
T
h
e
dr
a
wb
a
c
k
be
hi
nd
i
s
im
a
ge
m
a
y
ge
t
bl
ur
a
n
d
m
a
y
l
o
s
e
s
o
m
e
v
a
l
ua
bl
e
i
n
f
o
r
m
a
t
i
o
n
.
T
o
o
v
e
r
c
o
m
e
t
h
e
a
b
o
v
e
-
s
i
t
e
d
i
s
s
ue
,
a
hy
br
i
d
de
n
o
i
s
i
ng
m
e
t
h
o
d
b
a
s
e
d
o
n
a
g
l
o
ba
l
u
n
s
ymm
e
t
r
i
c
a
l
t
r
i
mm
e
d
m
e
d
i
a
n
f
il
t
e
r
(
GU
T
M
)
e
m
b
e
dde
d
w
i
t
h
s
a
l
t
&
pe
ppe
r
n
o
i
s
e
i
s
pr
o
po
s
e
d
i
n
t
hi
s
s
t
ud
y
.
B
a
s
e
d
o
n
t
h
e
r
e
s
e
a
r
c
h
b
a
c
kgr
o
un
d
a
n
d
t
h
e
r
e
l
a
t
e
d
i
s
s
u
e
s
,
t
h
e
o
bj
e
c
t
i
v
e
o
f
t
hi
s
r
e
s
e
a
r
c
h
h
a
s
b
e
e
n
f
o
r
m
u
l
a
t
e
d
a
s
:
a)
T
o
pr
o
p
o
s
e
a
hy
b
r
i
d
de
n
o
i
s
i
ng
m
e
t
h
o
d
b
a
s
e
d
o
n
a
g
l
o
b
a
l
u
n
s
ymm
e
t
r
i
c
a
l
t
r
i
mm
e
d
m
e
d
i
a
n
f
il
t
e
r
(
GU
T
M
)
f
o
r
de
n
o
i
s
i
ng
m
a
mm
o
gr
a
m
im
a
ge
s
.
b)
T
o
e
v
a
l
ua
t
e
hy
br
i
d
d
e
n
o
i
s
i
ng
m
e
t
h
o
d
by
u
s
i
ng
m
e
a
n
s
qua
r
e
e
r
r
o
r
(
M
S
E
)
[
12]
,
pe
a
k
-
s
i
g
n
a
l
-
to
-
n
o
i
s
e
r
a
t
i
o
(
P
S
NR
)
[
13
]
,
a
n
d
s
t
r
uc
t
ur
a
l
s
i
mi
l
a
r
i
t
y
i
nde
x
m
e
t
r
i
c
(
S
S
I
M
)
[
14
]
.
c)
T
o
v
a
l
i
da
t
e
t
h
e
pe
r
f
o
r
m
a
nc
e
o
f
t
h
e
pr
o
po
s
e
d
m
e
t
ho
d
wi
t
h
e
xi
s
t
i
n
g
t
e
c
hni
que
s
n
a
m
e
ly
m
e
a
n
,
m
e
d
i
a
n
a
n
d
w
i
nn
e
r
f
il
t
e
r
.
P
e
r
f
o
r
m
a
n
c
e
e
v
a
l
ua
t
i
o
n
s
o
f
pr
o
po
s
e
d
f
il
t
e
r
s
a
r
e
v
a
li
da
t
e
d
w
i
t
h
m
e
a
n
,
m
e
d
i
a
n
a
n
d
w
i
nn
e
r
f
i
l
t
e
r
t
h
e
r
e
s
ul
t
s
a
r
e
i
n
f
a
v
o
r
o
f
t
h
e
pr
o
p
o
s
e
d
m
e
t
h
o
d
w
i
t
h
r
e
s
pe
c
t
to
P
S
NR
,
M
S
E
,
a
n
d
S
S
I
M
.
2.
RE
S
E
ARCH
M
E
T
HO
DOL
OG
Y
T
h
e
m
e
t
h
o
do
l
o
g
y
us
e
d
i
n
t
h
e
pr
e
s
e
n
t
s
t
udy
c
o
m
po
s
e
d
o
f
e
i
g
h
t
s
t
e
ps
:
F
i
r
s
t
l
y
a
gr
a
y
s
c
a
l
e
m
a
mm
o
gr
a
m
im
a
ge
i
s
l
o
a
de
d
i
n
m
a
t
-
l
a
b
a
n
d
a
s
s
u
m
e
d
a
s
t
h
e
o
r
i
g
i
na
l
im
a
ge
a
f
t
e
r
t
h
a
t
i
m
a
ge
i
s
pa
s
s
e
d
t
h
r
o
ugh
s
o
m
e
pr
e
-
pr
o
c
e
s
s
i
n
g
s
uc
h
a
s
c
o
n
t
r
a
s
t
e
nh
a
n
c
e
m
e
nt
a
n
d
i
n
t
e
n
s
i
t
y
c
h
a
n
g
e
[
15]
.
W
h
e
n
t
h
e
pr
e
pr
o
c
e
s
s
in
g
p
ha
s
e
i
s
c
o
m
p
l
e
t
e
d
m
a
t
h
e
m
a
t
i
c
a
l
m
o
r
p
h
o
l
o
g
i
c
a
l
f
u
nc
t
i
o
n
e
r
o
s
i
o
n
i
s
a
pp
li
e
d
to
a
n
i
m
a
ge
.
L
a
t
e
r
o
n
,
s
a
l
t
&
pe
ppe
r
n
o
i
s
e
i
s
e
m
be
dde
d
i
n
t
h
e
a
b
o
v
e
i
m
a
g
e
a
n
d
t
h
e
im
a
ge
b
e
c
o
m
e
s
de
gr
a
de
a
n
d
n
o
i
s
y
.
F
o
r
de
n
o
i
s
i
ng
i
m
a
g
e
s
,
s
e
l
e
c
t
a
pr
o
c
e
s
s
i
n
g
w
i
n
do
w
s
i
z
e
f
o
r
t
h
e
pr
o
p
o
s
e
d
g
l
o
b
a
l
u
ns
ymm
e
t
r
i
c
a
l
t
r
i
m
m
e
d
m
e
d
i
a
n
f
il
t
e
r
(
GU
T
M
)
a
n
d
t
h
e
pr
o
p
o
s
e
d
m
e
t
h
o
d.
T
h
e
qua
li
t
y
o
f
t
h
e
pr
o
c
e
s
s
e
d
i
m
a
ge
i
s
e
va
l
ua
t
e
d
us
i
n
g
pe
a
k
s
i
g
n
a
l
t
o
n
o
i
s
e
r
a
t
i
o
(
P
S
NR
)
,
m
e
a
n
s
qua
r
e
e
r
r
o
r
(
M
S
E
)
s
tr
uc
t
ur
e
s
i
mi
lar
i
t
y
i
n
de
x
m
a
t
r
i
x
(
S
S
I
M
)
,
a
n
d
r
e
s
u
l
t
s
a
r
e
c
o
m
pa
r
e
d
w
i
t
h
e
xi
s
t
i
n
g
m
e
d
i
a
n
,
m
e
a
n
,
a
n
d
w
i
nne
r
f
il
t
e
r
t
e
c
h
ni
que
.
F
i
gur
e
1
i
ll
u
s
t
r
a
t
e
s
t
h
e
r
e
s
e
a
r
c
h
de
s
i
g
n
.
F
i
gur
e
1
.
R
e
s
e
a
r
c
h
d
e
s
i
g
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
I
S
S
N:
2502
-
4752
A
hy
br
id
de
-
nois
ing
me
thod
f
or
mam
mogr
am
image
s
(
R
as
hid
M
e
hmood
Gondal
)
1437
3.
DA
T
A
COL
L
E
C
T
I
ON
I
m
a
ge
s
f
o
r
t
hi
s
wo
r
k
a
r
e
t
a
ke
n
f
r
o
m
m
a
mm
o
gr
a
m
i
m
a
ge
s
a
n
a
ly
s
i
s
s
o
c
i
e
t
y
(
M
I
A
S
)
.
M
I
A
S
i
s
a
U
K
r
e
s
e
a
r
c
h
gr
o
up
or
ga
ni
z
a
t
i
o
n
t
h
a
t
is
i
n
t
e
r
e
s
t
e
d
i
n
m
a
mm
o
gr
a
m
s
a
n
d
h
a
s
ge
n
e
r
a
t
e
d
a
da
t
a
b
a
s
e
o
f
d
i
g
i
t
a
l
m
a
mm
o
gr
a
m
im
a
ge
s
.
T
h
e
s
e
i
m
a
ge
s
a
r
e
a
v
a
il
a
bl
e
f
r
e
e
o
f
c
o
s
t
on
t
h
e
M
I
A
S
we
b
s
i
t
e
.
M
I
A
’
s
da
t
a
s
e
t
c
o
n
t
a
i
n
s
322
i
m
a
ge
s
c
o
l
l
e
c
t
e
d
f
r
o
m
161
pa
t
i
e
n
t
s
o
f
b
o
t
h
l
e
f
t
a
n
d
r
i
g
h
t
b
r
e
a
s
t
s
.
All
t
h
e
im
a
g
e
s
a
r
e
gr
a
y
l
e
v
e
l
a
n
d
t
h
e
f
o
r
m
a
t
i
s
a
po
r
t
a
bl
e
gr
a
y
m
a
p
(
P
GM
)
[
16]
.
B
a
s
e
d
o
n
s
e
v
e
r
i
t
y
,
im
a
ge
s
a
r
e
c
l
a
s
s
i
f
i
e
d
i
n
t
o
t
h
r
e
e
c
a
t
e
g
o
r
i
e
s
de
s
c
r
i
be
d
i
n
T
a
bl
e
1.
T
a
bl
e
1.
I
m
a
ge
d
e
s
c
r
i
pt
i
o
n
S.
N
o
.
MI
A
S
D
e
s
c
ri
p
t
i
o
n
1
N
o
r
m
al
207
2
Be
n
i
g
n
61
3
Mal
i
g
n
an
t
54
4.
M
AT
HE
M
AT
I
CA
L
M
ORP
HO
L
OG
Y
M
a
t
h
e
m
a
t
i
c
a
l
m
o
r
ph
o
l
o
g
y
i
s
a
s
e
t
o
f
t
h
e
t
h
e
o
r
e
t
i
c
a
l
m
e
t
h
o
d
o
f
i
m
a
ge
a
n
a
ly
s
i
s
a
n
d
pr
o
vi
de
s
a
c
h
a
r
a
c
t
e
r
i
z
a
t
i
o
n
o
f
t
h
e
ge
o
m
e
t
r
i
c
a
l
s
t
r
uc
t
u
r
e
o
f
a
n
im
a
ge
[
17]
.
B
a
s
i
c
o
pe
r
a
t
i
o
n
a
l
s
t
e
ps
o
f
m
a
t
he
m
a
t
i
c
a
l
m
o
r
p
h
o
l
o
g
y
a
r
e
e
r
o
s
i
o
n
a
n
d
d
i
l
a
t
i
o
n
w
h
e
r
e
a
l
l
o
t
h
e
r
o
pe
r
a
t
i
o
ns
s
u
c
h
a
s
o
pe
ni
ng,
c
l
o
s
i
ng
a
r
e
de
r
i
ve
d
f
r
o
m
t
h
e
s
e
t
w
o
o
pe
r
a
t
i
o
n
s
.
C
o
m
bi
na
t
i
o
n
,
o
pe
ni
n
g,
a
n
d
c
l
o
s
i
ng
o
pe
r
a
t
i
o
n
s
a
r
e
us
e
d
to
f
o
r
m
a
t
r
a
d
i
t
i
o
n
a
l
m
o
r
p
h
o
l
o
g
i
c
a
l
f
il
t
e
r
.
S
uppo
s
e
t
h
e
d
i
s
c
r
e
t
e
i
n
put
s
ig
n
a
l
f
(
n
)
i
s
de
f
i
ne
d
a
s
F
=
{0,
1,
…….
.
,
X}
a
n
d
t
h
e
s
t
r
uc
t
u
r
a
l
e
l
e
m
e
n
t
g(
n
)
i
s
de
f
i
ne
d
a
s
G=
{0,
1,
….
.
,
Y}
Y≥
X,
t
h
e
n
t
he
e
r
o
s
i
o
n
a
n
d
d
il
a
t
i
o
n
o
pe
r
a
t
i
o
ns
a
r
e
de
f
i
ne
d
a
s
f
o
l
l
o
ws
[
18]
:
D
i
l
a
t
i
o
n
:
(
f
Og)
(
y
)
=
m
a
x
{
f
(
y
-
x
)
+
g(
x
)
}
(
1)
E
r
o
s
i
o
n
:
(
f
Og)
(
y
)
=
m
i
n{
f
(
y
-
x
)
+
g(
x
)
}
W
h
e
r
e
y
=
{0,
1,
…
.
,
Y
−
1}
a
n
d
x
=
{0,
1,
….
,
X
−
1}
.
5.
P
ROP
OS
E
D
T
E
CHNI
QUE
GUT
M
(
GL
OB
AL
UN
S
YM
M
E
T
RI
CA
L
T
R
I
M
M
E
D
M
E
DI
AN
F
I
L
T
E
R)
G
l
o
b
a
l
u
ns
y
mm
e
t
r
i
c
a
l
t
r
i
m
m
e
d
m
e
d
i
a
n
f
il
t
e
r
u
s
i
ng
s
a
l
t
a
n
d
pe
ppe
r
n
o
i
s
e
i
s
i
ll
u
s
t
r
a
t
e
d
i
n
F
i
gur
e
2
,
wh
e
r
e
t
h
e
gr
a
y
s
c
a
l
e
im
a
ge
i
s
l
o
a
de
d
i
n
a
n
d
3*3
-
k
e
r
n
e
l
s
i
z
e
i
s
s
e
l
e
c
t
e
d.
P
r
o
c
e
s
s
i
n
g
p
i
xe
l
P
(
i
,
j
)
i
s
a
n
a
ly
z
e
d
w
he
t
h
e
r
i
t
i
s
n
o
i
s
y
o
r
n
o
i
s
e
-
f
r
e
e
.
Ho
we
ve
r
,
i
f
t
h
e
pr
o
c
e
s
s
i
n
g
p
i
xe
l
i
s
i
n
b
e
t
we
e
n
t
h
e
mi
n
im
u
m
a
n
d
m
a
xim
u
m
v
a
l
ue
o
f
a
gr
a
y
s
c
a
l
e
i
m
a
ge
i
t
s
m
e
a
n
p
i
xe
l
i
s
n
o
i
s
e
-
f
r
e
e
a
n
d
l
e
f
t
unc
h
a
n
ge
d.
Ho
we
v
e
r
,
i
f
t
h
e
p
i
xe
l
t
a
ke
s
a
mi
n
im
u
m
a
n
d
m
a
xim
u
m
gr
a
y
l
e
v
e
l
va
l
ue
i
t
s
m
e
a
n
p
i
x
e
l
i
s
c
o
r
r
up
t
e
d
w
i
t
h
s
a
l
t
o
r
pe
ppe
r
n
o
i
s
e
a
n
d
pr
o
c
e
s
s
e
d
a
c
c
o
r
di
n
g
t
o
t
h
e
pr
o
p
o
s
e
d
m
e
t
h
o
d.
F
i
gur
e
2
i
ll
us
t
r
a
t
es
t
h
e
pr
o
p
o
s
e
d
t
e
c
h
ni
que
.
P
r
o
p
o
s
e
d
T
e
c
hni
qu
e
:
S
t
e
p
1
:
S
e
l
e
c
t
a
2D
w
i
ndo
w
h
a
vi
ng
s
i
z
e
3*3
A
s
s
u
mi
ng
t
h
a
t
t
h
e
pr
o
c
e
s
s
i
n
g
p
i
xe
l
P
(
i
,
j
)
i
s
li
e
s
a
t
t
h
e
c
e
n
t
e
r
o
f
t
h
e
pi
xe
l
.
St
e
p
2
:
C
h
e
c
k
f
o
r
t
h
e
pr
o
c
e
s
s
i
n
g
p
i
x
e
l
i
s
c
o
r
r
up
t
e
d
or
un
c
or
r
up
t
e
d.
S
t
e
p
3
:
I
f
0
<
P
(
i
,
j
)
<
255
m
e
a
n
pr
o
c
e
s
s
i
ng
p
i
xe
l
li
e
b
e
t
we
e
n
mi
nim
u
m
a
n
d
m
a
xim
u
m
s
o
i
t
i
s
u
nc
o
r
r
up
t
e
d
a
n
d
l
e
f
t
un
c
h
a
n
ge
d.
S
t
e
p
4
:
I
f
t
h
e
pr
o
c
e
s
s
i
n
g
p
i
xe
l
P
(
i
,
j
)
=
0
or
P
(
i
,
j
)
=
255
th
e
n
i
t
i
s
t
a
ke
n
a
s
n
o
i
s
y
a
n
d
pr
o
c
e
s
s
e
d
by
t
h
e
n
e
x
t
i
ns
t
r
uc
t
i
o
n
.
S
t
e
p
5
:
A
r
r
a
n
ge
t
h
e
p
i
x
e
l
v
a
l
ue
i
n
t
h
e
c
ur
r
e
n
t
pr
o
c
e
s
s
i
ng
w
i
ndo
w
i
n
a
s
c
e
n
d
i
n
g
o
r
de
r
.
S
t
e
p
6
:
C
h
e
c
k
t
h
e
No
o
f
a
n
o
n
-
n
o
i
s
y
p
i
xe
l
i
n
t
h
e
w
i
ndo
w
a
n
d
s
t
or
e
tot
a
l
n
o
i
n
a
v
a
r
i
a
bl
e
c
a
ll
e
d
‘
N
’
S
t
e
p
7
:
B
a
s
e
d
o
n
t
h
e
v
a
l
ue
o
f
‘
N
’
t
h
e
r
e
a
r
e
t
h
e
f
o
l
l
o
w
i
ng
po
s
s
i
bl
e
c
a
s
e
s
.
S
t
e
p
8
:
I
f
t
h
e
v
a
l
ue
o
f
‘
N’
i
s
z
e
r
o
i
t
s
m
e
a
n
w
i
nd
o
w
di
d
n
o
t
c
o
n
t
a
i
n
a
n
d
n
o
i
s
e
-
f
r
e
e
p
i
xe
l
s
o
t
h
e
r
e
a
r
e
t
h
r
e
e
po
s
s
i
bl
e
c
a
s
e
s
o
r
g
o
to
s
t
e
p
9.
C
as
e
I
:
if
t
h
e
w
i
ndo
w
c
o
n
t
a
i
n
s
a
ll
t
h
e
e
l
e
m
e
n
t
‘
0
’
pe
pp
e
r
n
o
i
s
e
t
h
e
n
r
e
p
l
a
c
e
t
h
e
n
o
i
s
y
p
i
xe
l
P
(
i
,
j
)
w
i
t
h
s
a
l
t
n
o
i
s
e
(
e
.
g.
255)
tr
i
mm
e
d
G
l
o
ba
l
U
ns
y
mm
e
t
r
i
c
a
l
M
e
d
i
a
n
f
il
t
e
r
o
f
t
h
e
e
n
t
i
r
e
i
m
a
g
e
.
Cas
e
I
I
:
if
t
h
e
w
i
n
do
w
c
o
n
t
a
i
n
s
a
ll
t
h
e
e
l
e
m
e
n
t
‘
255’
s
a
l
t
n
o
i
s
e
t
h
e
n
r
e
p
l
a
c
e
t
h
e
n
o
i
s
y
p
i
xe
l
P
(
i
,
j
)
w
i
t
h
pe
ppe
r
no
i
s
e
(
e
.
g.
0)
tr
i
mm
e
d
G
l
o
ba
l
U
ns
y
mm
e
t
r
i
c
a
l
M
e
d
i
a
n
f
il
t
e
r
o
f
t
h
e
e
n
t
i
r
e
i
m
a
ge
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2502
-
4752
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
,
Vo
l
.
21
,
N
o
.
3
,
M
a
r
c
h
2021
:
1435
-
1443
1438
Cas
e
I
I
I
:
i
f
t
h
e
w
i
ndo
w
c
o
n
t
a
i
n
s
a
ll
t
h
e
e
l
e
m
e
n
t
s
‘
0
’
&
‘
255
’
o
r
N
<
=
4
t
he
n
r
e
p
l
a
c
e
t
h
e
n
o
i
s
y
p
i
x
e
l
P
(
i
,
j
)
w
i
t
h
t
h
e
m
e
d
i
a
n
o
f
t
h
e
s
e
l
e
c
t
e
d
w
i
n
do
w.
Cas
e
I
V
:
I
f
t
he
va
l
ue
o
f
‘
N
’
i
s
gr
e
a
t
e
r
or
e
qua
l
t
o
f
i
ve
t
h
e
n
t
a
ke
a
n
u
ns
y
mm
e
t
r
i
c
a
l
t
r
i
m
m
e
d
m
e
d
ian
o
f
t
h
e
s
e
l
e
c
t
e
d
w
i
n
do
w
a
n
d
r
e
p
l
a
c
e
t
h
e
pr
o
c
e
s
s
i
n
g
p
i
xe
l
.
S
t
e
p
9
:
M
o
v
e
to
t
h
e
n
e
x
t
pi
x
e
l
a
n
d
r
e
pe
a
t
f
r
o
m
s
t
e
p
1
to
10
f
o
r
a
r
e
m
a
i
n
i
ng
p
i
xe
l
i
n
t
he
w
i
n
do
w.
F
i
gur
e
2
.
F
l
o
w
c
h
a
r
t
o
f
t
h
e
pr
o
p
o
s
e
d
t
e
c
hni
qu
e
6.
I
L
L
UST
RA
T
I
ON
OF
P
ROP
OS
E
D
M
E
T
HO
DOL
OG
Y
I
n
t
hi
s
s
e
c
t
i
o
n
,
t
wo
di
f
f
e
r
e
n
t
m
a
t
r
i
c
e
s
w
i
ll
b
e
d
i
s
c
u
s
s
e
d.
T
h
e
b
i
gge
r
m
a
t
r
i
x
s
h
o
ws
t
h
e
i
m
a
ge
s
e
g
m
e
n
t
dur
i
n
g
t
h
e
e
x
pe
r
i
m
e
n
t
f
r
o
m
t
h
e
o
r
i
g
i
na
l
im
a
ge
,
a
n
d
a
3*3
m
a
t
r
i
x
s
h
o
ws
t
h
e
pr
o
c
e
s
s
i
n
g
w
i
ndo
w.
E
l
e
m
e
n
t
c
i
r
c
l
e
d
o
n
t
h
e
l
e
f
t
s
i
de
a
r
e
t
a
ke
n
a
s
pr
o
c
e
s
s
i
n
g
p
ix
e
l
P
(
i
,
j
)
a
n
d
o
n
t
h
e
r
i
g
h
t
s
i
de
,
t
h
e
m
a
t
r
i
x
is
t
a
ke
n
a
s
a
r
e
s
to
r
e
d
pi
xe
l
.
T
h
e
s
qua
r
e
b
o
x
r
e
f
e
r
s
t
o
t
h
e
c
ur
r
e
n
t
pr
o
c
e
s
s
i
n
g
w
i
ndo
w.
I
f
pr
o
c
e
s
s
e
d
P
i
x
e
l
i
s
b
e
t
we
e
n
0
&
255
s
o
i
t
’
s
m
e
a
n
n
o
t
n
o
i
s
y
a
n
d
r
e
m
a
i
n
s
u
n
c
h
a
n
ge
d.
I
n
t
hi
s
c
a
s
e
P
(
i
,
j
)
h
o
l
d
t
h
e
v
a
l
ue
5
w
hi
c
h
i
s
n
o
t
e
qua
l
t
o
0
o
r
255
a
n
d
i
s
c
o
n
s
i
de
r
e
d
n
o
n
-
n
o
i
s
y
,
a
n
d
i
s
ke
pt
un
c
ha
n
ge
d.
F
i
gur
e
3
i
ll
us
t
r
a
t
e
s
t
h
e
pr
o
c
e
s
s
to
f
i
n
d
w
he
t
h
e
r
t
h
e
p
i
x
e
l
i
s
n
o
i
s
y
o
r
n
ot
.
Cas
e
I
:
T
h
e
P
(
i
,
j
)
i
s
n
o
i
s
y
‘
0’
a
n
d
a
l
l
i
t
s
n
e
i
ghb
o
r
i
n
t
h
e
s
e
l
e
c
ted
w
i
n
d
o
w
a
r
e
‘
0’
a
s
a
l
l
th
e
p
i
x
e
l
i
n
th
e
w
i
n
d
o
w
a
r
e
z
e
r
o
(
p
e
p
pe
r
n
o
i
s
e
)
s
o
i
n
t
h
i
s
c
a
s
e
,
c
h
e
c
k
t
h
e
wh
o
l
e
i
m
a
g
e
a
n
d
r
e
m
o
v
e
a
l
l
s
a
l
t
n
o
i
s
e
f
r
o
m
t
h
e
wh
o
l
e
i
m
a
ge
a
n
d
tak
e
th
e
m
e
d
i
a
n
o
f
r
e
a
m
i
n
g
p
i
x
e
l
s
i
n
e
n
t
i
r
e
i
m
a
ge
a
n
d
r
e
pl
a
c
e
wi
t
h
c
u
r
r
e
n
t
p
i
x
e
l
.
F
i
gu
r
e
4
i
l
l
us
t
r
a
te
s
c
a
s
e
I
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
I
S
S
N:
2502
-
4752
A
hy
br
id
de
-
nois
ing
me
thod
f
or
mam
mogr
am
image
s
(
R
as
hid
M
e
hmood
Gondal
)
1439
F
i
gur
e
3.
I
l
l
u
s
t
r
a
t
i
o
n
to
f
i
nd
t
h
e
n
o
i
s
y
p
i
xe
l
F
i
gur
e
4.
I
l
l
u
s
t
r
a
t
i
o
n
o
f
t
h
e
c
a
s
e
I
I
n
F
i
gur
e
4
s
e
l
e
c
t
e
d
w
i
ndo
w
c
o
n
t
a
i
n
a
ll
t
h
e
p
i
x
e
l
p
e
ppe
r
n
o
i
s
e
‘
0
’
s
o
t
a
ke
a
l
l
t
h
e
e
l
e
m
e
n
t
o
f
im
a
ge
a
n
d
c
h
a
n
g
e
2D
a
r
r
a
y
i
n
t
o
1D
(
6
9
0
0
0
0
0
0
0
0
255
4
0
0
0
13
4
7
9
11
6
255
3
255
5)
n
o
w
t
r
i
m
t
h
e
s
a
l
t
n
o
i
s
e
(
e
.
g.
255)
f
r
o
m
A
r
r
a
y
a
n
d
a
r
r
a
n
ge
r
e
a
m
i
ng
i
n
a
s
c
e
n
d
i
ng
o
r
de
r
.
(
0
0
0
0
0
0
0
0
0
0
0
3
4
4
5
6
6
7
9
9
11
13)
.
F
i
nd
t
h
e
m
e
d
i
a
n
o
f
1D
a
r
r
a
y
a
s
t
h
e
c
e
n
t
e
r
e
l
e
m
e
n
t
s
o
f
s
o
r
t
e
d
a
r
r
a
y
a
r
e
0
a
n
d
3
s
o
m
e
d
i
a
n
i
s
(
0+
3)
/2=
1.
5
a
l
m
o
s
t
2.
N
o
w
r
e
pl
a
c
e
t
h
e
pr
o
c
e
s
s
i
n
g
p
i
x
e
l
w
i
t
h
2
a
s
i
n
Fi
gur
e
4
o
n
r
i
g
h
t
s
i
de
.
Cas
e
I
I
:
T
h
e
P
(
i
,
j
)
i
s
n
o
i
s
y
‘
255’
a
n
d
a
ll
i
t
'
s
n
e
i
g
hb
o
r
i
n
a
s
e
l
e
c
t
e
d
w
i
ndo
w
a
r
e
‘
255
’
a
s
a
ll
t
h
e
p
i
xe
l
i
n
t
h
e
w
i
n
do
w
a
r
e
255
(
s
a
l
t
n
o
i
s
e
)
s
o
i
n
t
hi
s
c
a
s
e
,
c
he
c
k
t
h
e
wh
o
l
e
i
m
a
g
e
a
n
d
r
e
m
o
v
e
a
ll
pe
ppe
r
n
o
i
s
e
f
r
o
m
t
h
e
wh
o
l
e
i
m
a
ge
a
n
d
t
a
ke
t
h
e
m
e
d
i
a
n
o
f
r
e
a
mi
ng
p
i
xe
ls
i
n
e
n
t
i
r
e
im
a
ge
a
n
d
r
e
p
l
a
c
e
w
i
t
h
pr
o
c
e
s
s
i
ng
p
i
xe
l.
F
i
gur
e
5
i
ll
u
s
t
r
a
t
e
s
c
a
s
e
I
I
.
F
i
gur
e
5
.
I
l
l
u
s
t
r
a
t
i
o
n
o
f
c
a
s
e
II
I
n
F
i
gur
e
5
s
e
l
e
c
t
e
d
w
i
n
do
w
c
o
n
t
a
i
n
a
ll
t
h
e
p
i
xe
l
s
a
l
t
n
o
i
s
e
‘
255
’
s
o
t
a
ke
a
l
l
t
h
e
e
l
e
m
e
n
t
s
o
f
t
h
e
im
a
ge
a
n
d
c
h
a
n
g
e
t
h
e
2D
a
r
r
a
y
i
n
t
o
1D
(
255
255
255
3
9
255
255
255
7
2
255
255
255
0
0)
n
o
w
t
r
i
m
t
h
e
pe
ppe
r
n
o
i
s
e
(
e
.
g.
0)
f
r
o
m
A
r
r
a
y
a
n
d
a
r
r
a
n
ge
t
o
r
e
m
a
i
n
i
n
a
s
c
e
n
d
i
ng
o
r
de
r
.
(
2
2
3
3
4
4
5
6
7
9
9
255
255
255
255
255
255
255
255
255
255
255)
.
F
i
nd
t
h
e
m
e
d
i
a
n
o
f
t
h
e
1D
a
r
r
a
y
a
s
t
h
e
c
e
n
t
r
a
l
el
e
m
e
n
t
s
o
f
t
he
s
o
r
t
e
d
a
r
r
a
y
a
r
e
9
a
n
d
255
s
o
t
h
e
m
e
d
i
a
n
i
s
(
9+
255)
/2=132.
No
w
r
e
pl
a
c
e
t
h
e
pr
o
c
e
s
s
i
ng
p
i
xe
l
w
i
t
h
132
a
s
i
n
F
i
gur
e
5
o
n
t
h
e
r
i
g
h
t
s
i
de
.
Cas
e
I
I
I
:
T
h
e
P
(
i
,
j
)
i
s
n
o
i
s
y
‘
0’
o
r
‘
255’
,
a
n
d
i
t
'
s
ne
i
g
hb
o
r
i
n
a
s
e
l
e
c
t
e
d
w
i
n
do
w
a
r
e
n
o
i
s
y
a
n
d
n
o
n
-
n
o
i
s
y
.
No
w
c
h
e
c
k
a
n
d
c
o
un
t
n
o
n
-
n
o
i
s
y
p
i
xe
l
if
t
h
e
s
e
a
r
e
l
e
s
s
o
r
e
qua
l
to
4
a
r
r
a
n
ge
a
l
l
t
h
e
e
l
e
m
e
n
t
s
i
n
a
w
in
do
w
i
n
a
s
c
e
n
d
i
ng
o
r
de
r
a
n
d
f
i
nd
t
h
e
m
e
d
i
a
n
a
n
d
r
e
p
l
a
c
e
w
i
t
h
pr
o
c
e
s
s
i
n
g
p
i
xe
l
.
F
i
gur
e
6
i
ll
us
t
r
a
t
e
c
a
s
e
I
I
I
.
F
i
gur
e
6
.
I
l
l
u
s
t
r
a
t
i
o
n
o
f
c
a
s
e
I
I
I
I
n
t
h
e
F
i
gur
e
6
,
pr
o
c
e
s
s
i
n
g
p
i
xe
l
P
(
i
,
j
)
i
s
0
s
e
l
e
c
t
e
d
w
i
n
do
w
c
o
n
t
a
i
n
p
i
x
e
l
n
o
i
s
y
a
n
d
n
o
n
-
n
o
i
s
y
.
No
w
c
o
un
t
a
n
u
m
b
e
r
o
f
n
o
n
-
n
o
i
s
y
p
i
xe
l
s
a
n
d
s
t
or
e
i
n
v
a
r
i
a
bl
e
‘
N’
.
A
s
i
n
t
hi
s
s
i
t
ua
t
i
o
n
‘
N
’
i
s
e
qua
l
t
o
4
.
C
h
a
n
ge
t
h
e
e
l
e
m
e
n
t
o
f
t
h
e
s
e
l
e
c
t
e
d
w
i
n
do
w
f
r
o
m
2D
a
r
r
a
y
t
o
1D
(
4
255
3
3
0
255
0
4
0)
A
r
r
a
n
ge
e
l
e
m
e
n
t
s
i
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2502
-
4752
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
,
Vo
l
.
21
,
N
o
.
3
,
M
a
r
c
h
2021
:
1435
-
1443
1440
a
s
c
e
n
d
i
ng
o
r
de
r
.
(
0
0
0
3
3
4
4
255
255)
.
F
i
n
d
t
h
e
m
e
d
i
a
n
o
f
t
h
e
1
D
a
r
r
a
y
a
s
t
h
e
c
e
n
t
r
a
l
e
l
e
m
e
n
t
s
o
f
a
s
o
r
t
e
d
a
r
r
a
y
i
s
3
s
o
t
h
e
m
e
d
i
a
n
i
s
3.
No
w
r
e
pl
a
c
e
t
h
e
pr
o
c
e
s
s
i
ng
p
i
xe
l
‘
0’
w
i
t
h
‘
3’
a
s
i
n
F
i
gur
e
6
o
n
t
h
e
r
i
g
h
t
s
i
d
e
.
Cas
e
I
V:
T
h
e
P
(
i
,
j
)
i
s
n
o
i
s
y
‘
0
’
o
r
‘
255’
,
a
n
d
i
t
s
n
e
i
g
hb
o
r
s
i
n
t
h
e
s
e
l
e
c
t
e
d
wi
n
do
w
a
r
e
n
o
i
s
y
a
n
d
n
o
n
-
n
o
i
s
y
.
No
w
c
h
e
c
k
a
n
d
c
o
un
t
n
o
n
-
n
o
i
s
y
p
i
xe
l
i
f
t
h
e
s
e
a
r
e
gr
e
a
t
e
r
o
r
e
qua
l
to
5
a
r
r
a
n
ge
a
l
l
t
h
e
e
l
e
m
e
n
t
s
i
n
a
w
i
n
do
w
i
n
a
s
c
e
n
d
i
ng
o
r
de
r
tr
i
m
‘
0
’
a
n
d
‘
255
’
f
i
nd
t
h
e
m
e
d
i
a
n
o
f
r
e
m
a
i
ni
ng
to
r
e
pl
a
c
e
w
i
t
h
pr
o
c
e
s
s
i
ng
p
i
x
e
l
.
F
i
gur
e
7
il
l
us
t
r
a
t
e
s
c
a
s
e
I
V.
F
i
gur
e
7
.
I
l
l
u
s
t
r
a
t
i
o
n
o
f
c
a
s
e
I
V
I
n
t
h
e
F
i
gur
e
7
pr
o
c
e
s
s
i
n
g
p
i
xe
l
P
(
i
,
j
)
i
s
255
s
e
l
e
c
t
e
d
wi
n
do
w
s
c
o
n
t
a
i
n
p
i
xe
l
n
o
i
s
y
a
n
d
n
o
n
-
n
o
i
s
y
.
No
w
c
o
un
t
t
h
e
n
u
m
be
r
o
f
n
o
n
-
n
o
i
s
y
p
i
xe
l
s
a
n
d
s
to
r
e
i
n
v
a
r
i
a
bl
e
‘
N’
.
As
i
n
t
hi
s
s
i
t
ua
t
i
o
n
‘
N’
i
s
e
q
ua
l
to
7
gr
e
a
t
e
r
t
h
a
n
5.
C
h
a
n
ge
t
h
e
e
l
e
m
e
n
t
o
f
t
h
e
s
e
l
e
c
t
e
d
w
i
n
do
w
f
r
o
m
2D
a
r
r
a
y
t
o
1D
(
3
3
3
3
255
3
3
3
0)
A
r
r
a
n
ge
e
l
e
m
e
n
t
s
i
n
a
s
c
e
n
d
i
ng
o
r
de
r
.
(
0
3
3
3
3
3
3
3
255)
.
T
r
i
m
‘
0
’
a
n
d
‘
255
’
f
r
o
m
t
h
e
a
r
r
a
y
a
n
d
f
i
nd
t
h
e
m
e
d
i
a
n
o
f
r
e
a
m
i
ng
a
r
r
a
y
(
3
3
3
3
3
3
3)
a
s
t
h
e
c
e
n
t
r
a
l
e
l
e
m
e
n
t
s
o
f
a
s
o
r
t
e
d
a
r
r
a
y
i
s
3
s
o
m
e
d
i
a
n
i
s
3.
No
w
r
e
p
l
a
c
e
t
h
e
pr
o
c
e
s
s
i
n
g
p
i
x
e
l
‘
255
’
w
i
t
h
‘
3’
a
s
i
n
F
i
gur
e
7
o
n
t
h
e
r
i
g
h
t
s
i
de
.
7.
RE
S
UL
T
S
AN
D
DI
S
CU
S
S
I
ON
T
hi
s
s
e
c
t
i
o
n
de
s
c
r
i
b
e
s
t
h
e
v
a
li
da
t
i
o
n
s
c
e
n
a
r
i
o
s
o
f
t
h
e
pr
o
p
o
s
e
d
m
e
t
h
o
do
l
o
g
y
w
i
t
h
m
a
t
h
e
m
a
t
i
c
a
l
m
o
r
p
h
o
l
o
g
y
(
M
M
)
a
n
d
i
n
t
h
e
a
bs
e
n
c
e
o
f
M
M
.
E
xpe
r
i
m
e
n
t
s
we
r
e
c
o
n
duc
t
e
d
o
n
di
f
f
e
r
e
n
t
n
o
r
m
a
l
,
b
e
ni
g
n
,
a
n
d
m
a
li
g
n
a
n
t
m
a
m
m
o
gr
a
m
i
m
a
ge
s
.
I
m
a
ge
s
we
r
e
e
m
be
dde
d
w
i
t
h
s
a
l
t
a
n
d
pe
ppe
r
n
o
i
s
e
.
E
x
pe
r
i
m
e
n
t
s
we
r
e
pe
r
f
o
r
m
e
d
a
n
d
r
e
s
u
l
t
s
a
r
e
c
o
m
pa
r
e
d
w
i
t
h
o
t
h
e
r
e
xi
s
t
i
n
g
de
n
o
i
s
i
ng
t
e
c
hni
que
s
s
uc
h
a
s
;
m
e
a
n
f
il
t
e
r
,
m
e
d
i
a
n
f
i
l
t
e
r
,
a
n
d
W
i
e
n
e
r
f
il
t
e
r
.
R
e
s
u
l
t
s
i
nd
i
c
a
t
e
t
h
a
t
t
h
e
pr
o
p
o
s
e
d
GU
T
M
t
e
c
h
ni
qu
e
e
xh
i
bi
t
s
b
e
t
t
e
r
qua
n
t
i
t
a
t
i
v
e
m
e
a
s
ur
e
m
e
n
t
s
i
n
t
h
e
f
o
r
m
o
f
P
S
NR
,
M
S
E
.
S
S
I
M
[
19]
.
A.
P
e
a
k
S
i
g
na
l
-
to
-
N
o
i
s
e
R
a
t
i
o
(
P
S
NR
)
=
10
log
10
(
2
)
=
20
log
10
(
M
a
x
I
)
-
-
-
-
-
-
-
-
-
[
12
]
B.
M
e
a
s
ur
e
m
e
n
t
o
f
M
S
E
T
h
e
M
S
E
i
s
de
f
i
ne
d
a
s
:
=
∑
[
(
,
)
−
(
,
)
]
2
=
=
1
/
2
-
-
-
-
-
-
-
-
-
[
20]
C.
S
tr
uc
t
ur
a
l
S
i
mi
l
a
r
i
t
y
I
n
de
x
M
e
t
r
i
c
(
S
S
I
M
)
T
h
e
S
S
I
M
i
s
c
o
m
put
e
s
a
s
:
(
,
)
=
(
2
×
̅
̅
+
1
)
(
2
×
+
2
)
(
2
+
2
+
2
)
×
(
(
̅
)
2
+
(
̅
)
2
+
1
)
-
-
-
-
-
-
-
-
-
[
21]
W
h
e
r
e
̅
∶
ℎ
,
̅
∶
ℎ
,
∶
ℎ
.
C
o
m
pa
r
i
s
o
n
o
f
d
if
f
e
r
e
n
t
t
e
c
h
ni
que
s
s
uc
h
a
s
m
e
a
n
f
il
t
e
r
,
w
i
nn
e
r
f
il
t
e
r
,
m
e
d
i
a
n
f
il
t
e
r
,
m
e
d
i
a
n
f
il
t
e
r
wi
t
h
m
a
t
h
e
m
a
t
i
c
a
l
m
o
r
p
h
o
l
o
g
y
,
g
l
o
b
a
l
u
n
s
ymm
e
t
r
i
c
a
l
t
r
i
m
m
e
d
m
e
d
i
a
n
f
il
t
e
r
,
a
n
d
pr
o
p
o
s
e
d
hy
br
i
d
G
UT
M
i
s
s
h
o
w
n
i
n
t
h
e
T
a
bl
e
2
.
R
e
s
u
l
t
s
s
h
o
w
t
h
a
t
t
h
e
pr
o
p
os
e
d
t
e
c
hni
que
wo
r
k
s
b
e
t
t
e
r
f
o
r
m
a
mm
o
gr
a
m
i
m
a
ge
s
h
a
vi
ng
P
S
NR
52.
31
a
n
d
M
S
E
0.
37
a
n
d
S
S
I
M
0.
99.
T
a
b
l
e
2
s
h
o
w
s
a
c
o
m
pa
r
i
s
o
n
o
f
t
h
e
pr
o
p
o
s
e
d
t
e
c
h
nique
w
i
t
h
e
xi
s
t
i
n
g.
F
i
gur
e
s
8
-
10
s
h
o
ws
P
S
NR
,
M
S
E
,
a
n
d
S
S
I
M
f
o
r
m
a
mm
o
gr
a
m
i
m
a
ge
.
F
i
gur
e
s
11
-
13
i
ll
u
s
t
r
a
t
e
t
h
e
gr
a
phi
c
a
l
r
e
pr
e
s
e
n
t
a
t
i
o
n
o
f
P
S
NR
,
M
S
E
,
S
S
I
M
v
a
lue
s
f
o
r
s
e
v
e
r
a
l
m
a
mm
o
gr
a
m
im
a
ge
s
r
e
s
pe
c
t
i
v
e
ly
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
I
S
S
N:
2502
-
4752
A
hy
br
id
de
-
nois
ing
me
thod
f
or
mam
mogr
am
image
s
(
R
as
hid
M
e
hmood
Gondal
)
1441
T
a
bl
e
2
.
S
h
o
ws
t
h
e
P
S
NR
,
M
S
E
,
S
S
I
M
v
a
l
ue
f
o
r
n
o
r
m
a
l
,
b
e
ni
g
n
,
a
n
d
m
a
li
g
n
a
n
t
i
m
a
ge
s
T
e
s
t
T
y
p
e
S
e
ve
r
it
y
of
I
ma
ge
I
ma
ge
N
a
me
M
e
a
n
F
il
te
r
W
in
ne
r
F
il
te
r
M
e
di
a
n
F
il
te
r
M
e
di
a
n F
il
t
e
r
W
it
h M
M
G
U
T
M
G
U
T
M
w
it
h
MM
P
S
N
R
N
o
r
ma
l
mdb322
28.78
20.99
36.2
39.58
45.32
52.31
B
e
n
ig
n
mdb188
28.28
20.52
38.31
39.2
47.92
49.65
M
a
li
gna
nt
mdb216
28.62
20.95
35.29
37.62
43.29
48.44
M
S
E
N
o
r
ma
l
mdb322
86.05
517.25
9.32
7.14
0.98
0.37
B
e
n
ig
n
M
db005
76.91
483.8
3.45
8.64
1.52
0.53
M
a
li
gna
nt
mdb256
83.14
495.08
16.01
10.48
1.24
0.5
S
S
I
M
N
o
r
ma
l
mdb018
0.19
0.12
0.89
0.94
0.98
0.99
B
e
n
ig
n
mdb001
0.25
0.16
0.95
0.95
0.99
0.99
M
a
li
gna
nt
mdb216
0.36
0.23
0.89
0.94
0.98
0.99
F
i
gur
e
8
.
C
o
m
pa
r
i
s
o
n
o
f
P
S
NR
f
o
r
n
o
r
m
a
l
i
m
a
ge
F
i
gur
e
9
.
C
o
m
pa
r
i
s
o
n
o
f
M
S
E
f
o
r
b
e
ni
g
n
im
a
ge
F
i
gur
e
10
.
C
o
m
pa
r
i
s
o
n
o
f
S
S
I
M
f
o
r
m
a
li
g
n
a
n
t
i
m
a
ge
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2502
-
4752
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
,
Vo
l
.
21
,
N
o
.
3
,
M
a
r
c
h
2021
:
1435
-
1443
1442
F
i
gur
e
11
.
Gr
a
phi
c
a
l
r
e
pr
e
s
e
n
t
a
t
i
o
n
o
f
P
S
NR
f
o
r
n
o
r
m
a
l
,
b
e
ni
g
n
,
a
n
d
m
a
li
g
n
a
n
t
i
m
a
ge
F
i
gur
e
12
.
Gr
a
phi
c
a
l
r
e
pr
e
s
e
n
t
a
t
i
o
n
o
f
M
S
E
f
o
r
n
o
r
m
a
l
,
b
e
ni
g
n
,
a
n
d
m
a
li
g
n
a
n
t
i
m
a
ge
F
i
gur
e
13
.
Gr
a
phi
c
a
l
r
e
pr
e
s
e
n
t
a
t
i
o
n
o
f
S
S
I
M
f
o
r
n
o
r
m
a
l
,
b
e
ni
g
n
,
a
n
d
m
a
li
g
n
a
n
t
i
m
a
ge
8.
COM
P
AR
I
S
ON
OF
E
XI
S
T
I
NG
T
E
CHNI
Q
UE
WI
T
H
P
ROP
OS
E
D
HYB
RI
D
D
E
NOI
S
I
NG
M
E
T
HO
D
I
n
t
hi
s
s
e
c
t
i
o
n
,
a
c
o
m
pa
r
i
s
o
n
o
f
d
i
f
f
e
r
e
n
t
t
e
c
h
niques
n
a
m
e
ly
a
da
pt
i
v
e
m
e
d
i
a
n
f
il
t
e
r
,
m
e
a
n
f
i
l
t
e
r
,
hy
br
i
d
m
e
d
i
a
n
f
il
t
e
r
,
m
o
vi
ng
a
ve
r
a
ge
f
il
t
e
r
a
n
d
ga
us
s
i
a
n
l
o
w
pa
s
s
f
il
t
e
r
i
s
pe
r
f
o
r
m
e
d
w
i
t
h
t
h
e
pr
o
p
o
s
e
d
h
y
br
i
d
GU
T
M
m
e
t
h
o
d.
R
e
s
u
l
t
s
s
h
o
w
t
h
a
t
t
h
e
pr
o
p
o
s
e
d
t
e
c
hni
que
wo
r
k
s
b
e
t
t
e
r
f
o
r
m
a
mm
o
gr
a
m
im
a
ge
s
h
a
vi
ng
P
S
NR
52.
31
a
n
d
M
S
E
0.
37.
T
a
bl
e
3
s
h
o
w
s
t
h
e
c
o
m
p
a
r
i
s
o
n
o
f
t
h
e
pr
o
p
o
s
e
d
t
e
c
h
ni
que
w
i
t
h
r
e
l
a
t
e
d
wo
r
k
.
T
a
bl
e
3.
C
o
m
pa
r
i
s
o
n
o
f
P
S
NR
a
n
d
M
S
E
v
a
l
ue
f
o
r
m
a
mm
o
gr
a
m
im
a
ge
T
e
c
hni
qu
e
Y
e
a
r
No
is
e
T
y
p
e
P
S
N
R
M
S
E
D
b3 W
a
v
e
l
e
t
T
r
a
ns
f
o
r
m
[
22
]
2014
G
a
us
s
a
in
N
o
is
e
48.79
0.85
H
A
A
R
W
a
ve
le
t
T
r
a
ns
f
o
r
m
[
22]
2014
G
a
us
s
a
in
N
o
is
e
48.30
0.96
M
e
di
a
n F
I
L
t
e
r
A
nd C
L
A
H
E
[
23]
2015
M
ix
N
o
is
e
50.67
0.90
F
a
s
t
D
is
c
r
e
t
e
C
ur
ve
l
e
t
T
r
a
ns
f
o
r
m
v
ia
U
ne
qi
S
pa
c
e
d F
a
s
t
F
o
ur
i
e
r
T
r
a
ns
f
or
m
[
24]
2017
S
e
ve
r
a
l
n
o
is
e
39.42
7.43
M
ul
ti
pl
e
d
e
s
c
r
ip
t
i
o
n G
a
us
s
ia
n no
is
e
c
ha
nn
e
l
[
25
]
2017
G
a
us
s
ia
n
N
o
is
e
37.87
10.63
M
ov
in
g A
v
e
r
a
ge
F
il
te
r
[
26]
2018
S
a
lt
& P
e
pp
e
r
35
3.4
G
a
us
s
ia
n L
o
w
pa
s
s
f
il
te
r
[
27]
2018
S
a
lt
& P
e
pp
e
r
38
1.3
T
r
is
ta
t
e
f
il
t
e
r
(
T
S
F
)
[
24]
2019
S
a
lt
& P
e
pp
e
r
44.71
2.4
H
y
br
id
D
e
n
o
is
in
g
M
e
th
o
d ba
s
e
d
o
n
G
U
T
M
(
P
r
o
p
o
s
e
d M
e
th
o
d)
2020
S
a
lt
& P
e
pp
e
r
a
nd
G
a
us
a
in
52.31
0.37
9.
CONC
L
USI
ON
I
n
t
hi
s
wo
r
k,
a
h
y
br
i
d
de
n
o
i
s
i
ng
m
e
t
h
o
d
i
s
pr
o
p
o
s
e
d
f
o
r
m
a
mm
o
gr
a
m
im
a
ge
s
.
M
a
mm
o
gr
a
m
c
o
n
t
a
i
ns
us
e
f
u
l
i
n
f
o
r
m
a
t
i
o
n
a
b
o
ut
t
h
e
d
i
a
g
n
o
s
i
s
a
nd
pr
o
gn
o
s
i
s
o
f
b
r
e
a
s
t
c
a
n
c
e
r
i
n
wo
m
e
n
.
Ho
we
v
e
r
,
n
o
i
s
e
in
m
a
mm
o
gr
a
m
o
f
t
e
n
d
i
s
t
ur
b
i
m
a
ge
i
m
po
r
t
a
n
t
i
nf
o
r
m
a
t
i
o
n
a
n
d
m
a
ke
i
t
d
i
f
f
i
c
u
l
t
f
o
r
t
h
e
r
a
d
i
o
l
o
g
i
s
t
to
d
i
a
g
n
o
s
i
s
.
T
h
e
p
r
o
p
o
s
e
d
hy
b
r
i
d
m
e
t
h
o
d
i
s
us
e
d
to
de
-
n
o
i
s
e
t
h
e
i
m
a
g
e
a
n
d
t
o
e
nh
a
n
c
e
t
h
e
i
m
a
ge
qua
l
i
t
y
by
ke
e
p
i
n
g
im
a
ge
im
po
r
t
a
n
t
i
nf
o
r
m
a
t
i
o
n
u
n
c
ha
n
ge
d.
D
i
f
f
e
r
e
n
t
e
x
pe
r
im
e
n
t
a
l
s
e
t
up
s
we
r
e
de
s
i
g
n
e
d
t
o
o
b
t
a
i
n
P
S
N
R
,
M
S
E
,
a
n
d
S
S
I
M
.
L
a
t
e
r
,
v
a
l
i
d
a
t
e
d
w
i
t
h
e
xi
s
t
i
n
g
de
n
o
i
s
i
n
g
t
e
c
hni
qu
e
s
na
m
e
ly
m
e
a
n
f
a
l
t
e
r
,
w
i
e
n
e
r
f
il
t
e
r
,
a
nd
m
e
d
i
a
n
f
i
l
t
e
r
.
R
e
s
u
l
t
s
s
h
o
w
t
h
a
t
t
h
e
pr
o
p
o
s
e
d
m
e
t
h
o
d
pe
r
f
o
r
m
s
w
e
ll
f
o
r
de
n
o
i
s
i
ng
m
a
mm
o
gr
a
m
im
a
ge
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
I
S
S
N:
2502
-
4752
A
hy
br
id
de
-
nois
ing
me
thod
f
or
mam
mogr
am
image
s
(
R
as
hid
M
e
hmood
Gondal
)
1443
RE
F
E
R
E
NC
E
S
[1
]
S.
A
.
Sar
i
an
d
K
.
M
.
Mo
h
a
m
ad
,
“
A
R
e
v
i
ew
o
f
G
rap
h
T
h
e
o
r
e
t
i
c
a
n
d
W
e
i
g
h
t
ag
e
T
ec
h
n
i
q
u
e
s
i
n
Fi
l
e
Carv
i
n
g
,
”
i
n
Jo
u
r
n
a
l
o
f
P
h
ys
i
cs
:
Co
n
f
e
r
en
ce
S
er
i
es
,
2
0
2
0
,
v
o
l
.
1
5
2
9
,
n
o
.
5
,
p
.
5
2
0
1
1
.
[2
]
L
.
S
h
ao
,
R.
Y
an
,
X
.
L
i
,
an
d
Y
.
L
i
u
,
“
Fro
m
h
e
u
r
i
s
t
i
c
o
p
t
i
m
i
zat
i
o
n
t
o
d
i
c
t
i
o
n
ar
y
l
e
ar
n
i
n
g
:
A
r
ev
i
ew
an
d
c
o
m
p
r
e
h
en
s
i
v
e
c
o
m
p
ari
s
o
n
o
f
i
m
ag
e
d
e
n
o
i
s
i
n
g
al
g
o
r
i
t
h
m
s
,
”
I
E
E
E
Tr
a
n
s
.
Cyb
er
n
.
,
v
o
l
.
4
4
,
n
o
.
7
,
p
p
.
1
0
0
1
-
1
0
1
3
,
2
0
1
3
.
[3
]
M.
A
.
A
l
-
S
h
ar
ee
d
a
,
M.
A
n
b
ar,
S.
Man
i
c
k
a
m
an
d
A
.
A
.
Y
as
s
i
n
,
‘V
PPCS
:
V
A
N
E
T
-
Bas
ed
Pri
v
a
cy
-
Pr
e
s
e
r
v
i
n
g
Co
mm
u
n
i
c
at
i
o
n
S
ch
eme
,
’
i
n
IE
E
E
A
cce
s
s
,
d
o
i
:
1
0
.
1
1
0
9
/
A
CCE
SS.
2
0
2
0
.
3
0
1
7
0
1
8
.
[4
]
D
.
S
em
ra
u
,
R.
I
.
K
i
l
l
ey
,
a
n
d
P.
Ba
y
v
el
,
“
T
h
e
G
au
s
s
i
an
n
o
i
s
e
mo
d
el
i
n
t
h
e
p
re
s
e
n
ce
o
f
i
n
t
e
r
-
c
h
a
n
n
el
s
t
i
mu
l
a
t
e
d
Ram
an
s
c
at
t
e
r
i
n
g
,
”
J.
Li
g
h
t
.
Tech
n
o
l
.
,
v
o
l
.
3
6
,
n
o
.
1
4
,
p
p
.
3
0
4
6
-
3
0
5
5
,
2
0
1
8
.
[5
]
K
.
A
k
i
l
a,
L
.
S.
J
a
y
as
h
r
ee,
an
d
A
.
V
as
u
k
i
,
“
Mammo
g
rap
h
i
c
i
m
a
g
e
en
h
a
n
cem
en
t
u
s
i
n
g
i
n
d
i
r
ec
t
c
o
n
t
ras
t
e
n
h
an
cemen
t
t
ech
n
i
q
u
e
s
–
a
c
o
m
p
arat
i
v
e
s
t
u
d
y
,
”
P
r
o
ced
i
a
Co
m
p
u
t
.
S
ci
.
,
v
o
l
.
4
7
,
p
p
.
2
5
5
-
2
6
1
,
2
0
1
5
.
[6
]
M.
A
.
A
l
-
S
h
ar
ee
d
a,
M.
A
n
b
ar,
I
.
H
.
H
as
b
u
l
l
a
h
,
S.
Ma
n
i
c
k
a
m,
an
d
S.
M
.
H
a
n
s
h
i
,
“
E
ffi
c
i
en
t
co
n
d
i
t
i
o
n
a
l
p
ri
v
acy
p
re
s
e
rv
at
i
o
n
w
i
t
h
m
u
t
u
a
l
a
u
t
h
e
n
t
i
c
at
i
o
n
i
n
v
eh
i
c
u
l
ar
a
d
h
o
c
n
e
t
w
o
r
k
s
,
”
IE
E
E
A
cces
s
,
2
0
2
0
.
[7
]
M.
A
l
S
h
ar
ee
d
a
,
A
.
K
h
a
l
i
l
,
a
n
d
W
.
Fa
h
s
,
“
Re
al
i
s
t
i
c
h
e
t
e
ro
g
e
n
eo
u
s
g
en
e
t
i
c
-
b
as
e
d
RS
U
p
l
a
ceme
n
t
s
o
l
u
t
i
o
n
f
o
r
V
2
I
n
e
t
w
o
rk
s
.
,
”
In
t
.
A
r
a
b
J.
In
f
.
Tech
n
o
l
.
,
v
o
l
.
1
6
,
n
o
.
3
A
,
p
p
.
5
4
0
-
5
4
7
,
2
0
1
9
.
[8
]
A
.
S.
Sa
w
a
n
,
S.
S
.
K
a
md
i
,
D
.
M.
K
h
at
ri
,
D
.
S
.
U
r
h
e
k
ar,
an
d
C.
D
.
B
o
h
ra,
“
N
o
v
e
l
f
i
l
t
e
r
d
e
s
i
g
n
i
n
g
f
o
r
e
n
h
an
ceme
n
t
o
f
me
d
i
c
al
i
m
a
g
e
s
u
s
i
n
g
s
u
p
e
r
-
r
e
s
o
l
u
t
i
o
n
,
”
i
n
2
0
1
7
In
t
e
r
n
a
t
i
o
n
a
l
Co
n
f
er
e
n
ce
o
n
S
i
g
n
a
l
P
r
o
ces
s
i
n
g
a
n
d
Co
m
m
u
n
i
c
a
t
i
o
n
(ICS
P
C)
,
p
p
.
2
5
3
-
2
5
7
,
2
0
1
7
.
[9
]
C.
K
a
n
k
ar
i
y
a
an
d
S.
G
u
p
t
a,
“
A
n
E
ffi
ci
e
n
t
A
l
g
o
r
i
t
h
m
fo
r
Rem
o
v
al
o
f
Sal
t
an
d
P
e
p
p
e
r
N
o
i
s
e
fro
m
Im
ag
e
s
,
”
In
t
.
J.
Co
m
p
u
t
.
A
p
p
l
.
,
v
o
l
.
1
1
8
,
n
o
.
1
8
,
2
0
1
5
.
[1
0
]
A
.
J
ai
s
w
al
,
J
.
P.
U
p
ad
h
y
a
y
,
R.
M
o
h
a
n
,
a
n
d
S
.
P.
B
o
h
r
e
,
“
A
N
o
v
e
l
A
p
p
ro
ach
fo
r
R
e
d
u
c
t
i
o
n
o
f
Po
i
s
s
o
n
N
o
i
s
e
i
n
D
i
g
i
t
al
Im
a
g
e
s
,
”
In
t
.
J.
E
n
g
.
R
es
.
A
p
p
l
.
,
v
o
l
.
3
,
n
o
.
5
,
p
p
.
1
2
7
5
-
1
2
7
9
,
2
0
1
3
.
[1
1
]
X
.
G
u
o
,
J
.
J
i
an
g
,
L
.
T
an
,
an
d
S.
D
u
,
“
I
m
p
ro
v
e
d
a
d
ap
t
i
v
e
rec
u
rs
i
v
e
ev
e
n
mi
rro
r
Fo
u
ri
e
r
n
o
n
l
i
n
e
ar
fi
l
t
e
r
fo
r
n
o
n
l
i
n
e
ar
ac
t
i
v
e
n
o
i
s
e
c
o
n
t
ro
l
,
”
A
p
p
l
.
A
co
u
s
t
.
,
v
o
l
.
1
4
6
,
p
p
.
3
1
0
-
3
1
9
,
2
0
1
9
.
[1
2
]
Y
.
Z
h
a
n
g
et
a
l
.
,
“
A
p
o
i
s
s
o
n
-
g
au
s
s
i
an
d
e
n
o
i
s
i
n
g
d
at
as
e
t
w
i
t
h
r
e
al
fl
u
o
r
e
s
ce
n
ce
mi
c
ro
s
c
o
p
y
i
m
a
g
e
s
,
”
i
n
P
r
o
ceed
i
n
g
s
o
f
t
h
e
IE
E
E
Co
n
f
er
en
ce
o
n
Co
m
p
u
t
e
r
V
i
s
i
o
n
a
n
d
P
a
t
t
er
n
R
eco
g
n
i
t
i
o
n
,
2
0
1
9
,
p
p
.
1
1
7
1
0
-
1
1
7
1
8
.
[1
3
]
K.
-
S.
L
u
,
A
.
O
rt
e
g
a,
D
.
Mu
k
h
e
r
j
ee
,
an
d
Y
.
Ch
en
,
“
Pe
rce
p
t
u
al
l
y
i
n
s
p
i
red
w
e
i
g
h
t
e
d
MS
E
o
p
t
i
m
i
zat
i
o
n
u
s
i
n
g
i
rreg
u
l
ari
t
y
-
a
w
ar
e
g
rap
h
Fo
u
ri
e
r
t
ran
s
fo
r
m,
”
a
r
X
i
v
P
r
ep
r
.
a
r
X
i
v
2
0
0
2
.
0
8
5
5
8
,
2
0
2
0
.
[1
4
]
J
.
W
an
g
,
N
.
Z
h
e
n
g
,
B.
C
h
e
n
,
an
d
J
.
C.
Pr
i
n
ci
p
e
,
“
A
s
s
o
ci
at
i
o
n
s
amo
n
g
i
m
a
g
e
as
s
e
s
s
me
n
t
s
as
c
o
s
t
fu
n
c
t
i
o
n
s
i
n
l
i
n
e
ar
d
eco
m
p
o
s
i
t
i
o
n
:
MSE
,
SS
I
M,
a
n
d
Co
rr
e
l
at
i
o
n
C
o
e
ff
i
c
i
en
t
,
”
a
r
X
i
v
P
r
ep
r
.
a
r
X
i
v
1
7
0
8
.
0
1
5
4
1
,
2
0
1
7
.
[1
5
]
G
.
Bi
cch
i
e
ra
i
et
a
l
.
,
“
Ro
l
e
o
f
c
o
n
t
ras
t
-
e
n
h
a
n
ce
d
s
p
ec
t
ral
m
a
mmo
g
rap
h
y
i
n
t
h
e
p
o
s
t
b
i
o
p
s
y
m
an
a
g
eme
n
t
o
f
B3
l
e
s
i
o
n
s
:
p
rel
i
mi
n
ar
y
r
e
s
u
l
t
s
,
”
Tu
m
o
r
i
J.
,
v
o
l
.
1
0
5
,
n
o
.
5
,
p
p
.
3
7
8
-
3
8
7
,
2
0
1
9
.
[1
6
]
R.
V
i
j
a
y
araj
e
s
w
ar
i
,
P.
Part
h
as
arat
h
y
,
S.
V
i
v
ek
an
a
n
d
a
n
,
an
d
A
.
A
.
Bas
h
a,
“
Cl
as
s
i
fi
c
at
i
o
n
o
f
m
a
mmo
g
ra
m
fo
r
e
a
rl
y
d
e
t
ec
t
i
o
n
o
f
b
re
as
t
c
an
ce
r
u
s
i
n
g
S
V
M
c
l
as
s
i
fi
e
r
a
n
d
H
o
u
g
h
t
ran
s
fo
r
m
,
”
M
ea
s
u
r
em
en
t
,
v
o
l
.
1
4
6
,
p
p
.
8
0
0
-
8
0
5
,
2
0
1
9
.
[1
7
]
T
.
X
u
,
G
.
W
an
g
,
H
.
W
an
g
,
T
.
Y
u
an
,
an
d
Z
.
Z
h
o
n
g
,
“
G
ap
m
e
as
u
r
emen
t
o
f
p
o
i
n
t
m
a
c
h
i
n
e
u
s
i
n
g
ad
ap
t
i
v
e
w
a
v
el
e
t
t
h
re
s
h
o
l
d
an
d
m
at
h
em
at
i
c
al
m
o
rp
h
o
l
o
g
y
,
”
S
en
s
o
r
s
,
v
o
l
.
1
6
,
n
o
.
1
2
,
p
.
2
0
0
6
,
2
0
1
6
.
[1
8
]
X
.
Z
h
an
g
,
W
.
Q
i
,
Y
.
C
e
n
,
H
.
L
i
n
,
an
d
N
.
W
a
n
g
,
“
D
en
o
i
s
i
n
g
v
e
g
e
t
at
i
o
n
s
p
ec
t
ra
b
y
c
o
m
b
i
n
i
n
g
m
at
h
em
at
i
c
a
l
-
mo
rp
h
o
l
o
g
y
a
n
d
w
av
el
e
t
-
t
ran
s
fo
rm
-
b
as
ed
fi
l
t
e
rs
,
”
J
.
A
p
p
l
.
R
em
o
t
e
S
en
s
.
,
v
o
l
.
1
3
,
n
o
.
1
,
p
.
1
6
5
0
3
,
2
0
1
9
.
[1
9
]
E
.
Sh
i
mel
e
s
,
G
.
A
b
e
b
e
,
an
d
A
.
R
e
g
as
a,
“
Co
m
p
ari
n
g
t
h
e
P
e
rf
o
rm
a
n
ce
o
f
V
ari
o
u
s
Sp
eck
l
e
R
e
d
u
c
t
i
o
n
Fi
l
t
e
rs
o
n
U
l
t
ras
o
u
n
d
K
i
d
n
ey
St
o
n
e
Im
ag
e
s
.
”
H
ara
m
a
y
a
U
n
i
v
e
rs
i
t
y
,
2
0
1
7
.
[2
0
]
R.
K
o
c
h
h
e
r,
G
.
Mark
en
,
a
n
d
A
.
O
b
e
ro
i
,
“
Mam
mo
g
ra
m
R
e
s
t
o
rat
i
o
n
u
n
d
e
r
Im
p
u
l
s
i
v
e
N
o
i
s
e
s
u
s
i
n
g
P
ee
r
G
r
o
u
p
-
Fu
zz
y
N
o
n
-
L
i
n
e
ar
D
i
ff
u
s
i
o
n
F
i
l
t
e
r.
”
[2
1
]
S.
K
an
n
an
,
N
.
P.
S
u
b
i
ra
m
an
i
y
a
m
,
A
.
T
.
Raj
a
m
an
i
c
k
a
m,
an
d
A
.
Bal
a
mu
ru
g
an
,
“
Pe
rf
o
r
m
an
ce
c
o
m
p
ari
s
o
n
o
f
n
o
i
s
e
re
d
u
c
t
i
o
n
i
n
m
a
mmo
g
ra
m
i
m
a
g
e
s
,
”
Im
a
g
e
(IN)
.
,
v
o
l
.
1
,
n
o
.
3
x
3
,
p
.
5
x
5
,
2
0
1
6
.
[2
2
]
S.
A
.
L
as
h
ari
,
R.
I
b
rah
i
m
,
a
n
d
N
.
S
en
an
,
“
D
e
-
n
o
i
s
i
n
g
an
al
y
s
i
s
o
f
m
a
mmo
g
ra
m
i
m
ag
e
s
i
n
t
h
e
w
av
el
e
t
d
o
m
ai
n
u
s
i
n
g
h
ard
an
d
s
o
ft
t
h
re
s
h
o
l
d
i
n
g
,
”
i
n
2
0
1
4
4
t
h
W
o
r
l
d
Co
n
g
r
es
s
o
n
In
f
o
r
m
a
t
i
o
n
a
n
d
Co
m
m
u
n
i
ca
t
i
o
n
Tec
h
n
o
l
o
g
i
es
(W
ICT
2
0
1
4
)
,
p
p
.
3
5
3
-
3
5
7
,
2
0
1
4
.
[2
3
]
A
.
Mak
a
n
d
ar
an
d
B.
H
a
l
al
l
i
,
“
Bre
as
t
c
an
ce
r
i
m
ag
e
en
h
a
n
cemen
t
u
s
i
n
g
me
d
i
an
fi
l
t
e
r
a
n
d
C
L
A
H
E
,
”
In
t
.
J.
S
ci
.
E
n
g
.
R
es
.
,
v
o
l
.
6
,
n
o
.
4
,
p
p
.
4
6
2
-
4
6
5
,
2
0
1
5
.
[2
4
]
B.
Sen
t
h
i
l
k
u
m
ar,
R.
G
o
w
ri
s
h
a
n
k
ar,
M
.
V
a
i
s
h
n
a
v
i
,
a
n
d
S.
G
o
k
i
l
a,
“
Co
m
b
i
n
at
i
o
n
o
f
n
o
i
s
e
r
em
o
v
al
a
n
d
co
n
t
ras
t
e
n
h
an
cemen
t
me
t
h
o
d
s
fo
r
t
h
e
p
r
e
p
ro
ce
s
s
i
n
g
o
f
m
a
mmo
g
ra
m
i
m
ag
e
s
-
t
o
w
ar
d
s
t
h
e
d
e
t
ec
t
i
o
n
o
f
b
re
as
t
c
a
n
ce
r,
”
B
i
o
s
c
i
.
J.
,
v
o
l
.
3
3
,
n
o
.
6
,
2
0
1
7
.
[2
5
]
J
.
Ø
s
t
e
r
g
aard
,
Y
.
K
o
c
h
m
a
n
,
an
d
R.
Z
a
mi
r,
“
A
n
A
s
y
mme
t
ri
c
D
i
ff
e
r
e
n
ce
Mu
l
t
i
p
l
e
D
e
s
c
ri
p
t
i
o
n
G
au
s
s
i
an
N
o
i
s
e
Ch
an
n
el
,
”
i
n
2
0
1
7
D
a
t
a
Co
m
p
r
es
s
i
o
n
C
o
n
f
er
e
n
ce
(D
CC)
,
p
p
.
3
6
0
-
3
6
9
,
2
0
1
7
.
[2
6
]
Y
.
G
h
e
rg
h
o
u
t
,
Y
.
T
l
i
l
i
,
a
n
d
L
.
S
o
u
i
ci
,
“
Cl
as
s
i
fi
c
at
i
o
n
o
f
b
re
as
t
m
as
s
i
n
m
a
mm
o
g
rap
h
y
u
s
i
n
g
an
i
s
o
t
ro
p
i
c
d
i
ffu
s
i
o
n
fi
l
t
e
r
b
y
s
el
ec
t
i
n
g
a
n
d
a
g
g
r
eg
at
i
n
g
mo
rp
h
o
l
o
g
i
c
al
an
d
t
ex
t
u
ral
fe
at
u
r
e
s
,
”
E
vo
l
.
S
ys
t
.
,
p
p
.
1
-
3
0
,
2
0
1
9
.
[2
7
]
X
.
D
u
a
n
et
a
l
.
,
“
A
m
u
l
t
i
s
c
a
l
e
c
o
n
t
ras
t
e
n
h
an
cemen
t
fo
r
m
a
mm
o
g
ra
m
u
s
i
n
g
d
y
n
a
mi
c
u
n
s
h
arp
m
as
k
i
n
g
i
n
L
ap
l
a
ci
an
p
y
ra
m
i
d
,
”
I
E
E
E
Tr
a
n
s
.
R
a
d
i
a
t
.
P
l
a
s
m
a
M
ed
.
S
ci
.
,
v
o
l
.
3
,
n
o
.
5
,
p
p
.
5
5
7
-
5
6
4
,
2
0
1
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.