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.
10
,
No
.
5
,
Octo
b
er
2
0
2
0
,
p
p
.
5
2
3
5
~
5
2
4
2
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
1
0
i
5
.
pp
5
2
3
5
-
5
2
4
2
5235
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m/in
d
ex
.
p
h
p
/I
JE
C
E
Co
m
pu
ter
-
a
ided
dia
g
no
sis
sy
ste
m
f
o
r breas
t
ca
nce
r
ba
sed o
n t
he
G
a
b
o
r f
ilter
t
e
chniqu
e
M
o
ha
m
m
e
d Y.
K
a
m
il
Co
ll
e
g
e
o
f
S
c
ien
c
e
s,
M
u
sta
n
siriy
a
h
Un
iv
e
rsity
,
Ira
q
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
r
2
5
,
2
0
2
0
R
ev
i
s
ed
A
p
r
2
5
,
2
0
2
0
A
cc
ep
ted
Ma
y
7
,
2
0
2
0
T
h
e
m
o
st
p
ro
m
in
e
n
t
re
a
so
n
f
o
r
th
e
d
e
a
th
o
f
w
o
m
e
n
a
ll
o
v
e
r
th
e
w
o
rld
is
b
re
a
st
c
a
n
c
e
r.
Earl
y
d
e
tec
ti
o
n
o
f
c
a
n
c
e
r
h
e
lp
s
to
lo
w
e
r
th
e
d
e
a
th
ra
te.
M
a
m
m
o
g
ra
p
h
y
sc
a
n
s
d
e
ter
m
i
n
e
br
e
a
st
tu
m
o
rs
in
th
e
f
irst
sta
g
e
.
A
s
th
e
m
a
m
m
o
g
ra
m
s
h
a
v
e
slig
h
t
c
o
n
tras
t,
th
u
s,
it
is
a
b
lu
r
t
o
th
e
ra
d
io
l
o
g
ist
to
re
c
o
g
n
ize
m
icro
g
ro
w
th
s.
A
c
o
m
p
u
ter
-
a
id
e
d
d
iag
n
o
stic
s
y
ste
m
is
a
p
o
w
e
r
f
u
l
to
o
l
f
o
r
u
n
d
e
rsta
n
d
in
g
m
a
m
m
o
g
ra
m
s.
A
lso
,
th
e
sp
e
c
ialist
h
e
lp
s
d
e
ter
m
in
e
th
e
p
re
se
n
c
e
o
f
th
e
b
re
a
st
les
io
n
a
n
d
d
isti
n
g
u
is
h
b
e
tw
e
e
n
th
e
n
o
rm
a
l
a
re
a
a
n
d
th
e
m
a
ss
.
In
th
is
p
a
p
e
r,
t
h
e
G
a
b
o
r
f
il
ter
is
p
r
e
se
n
ted
a
s
a
k
e
y
ste
p
in
b
u
il
d
in
g
a
d
iag
n
o
stic
sy
st
e
m
.
It
is
c
o
n
sid
e
re
d
a
su
ff
icie
n
t
m
e
th
o
d
to
e
x
trac
t
th
e
f
e
a
tu
re
s.
T
h
a
t
h
e
lp
s
u
s
to
a
v
o
id
tu
m
o
r
c
l
a
ss
if
i
c
a
ti
o
n
d
if
f
icu
lt
ies
a
n
d
f
a
lse
-
p
o
siti
v
e
re
d
u
c
ti
o
n
.
T
h
e
li
n
e
a
r
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
tec
h
n
iq
u
e
is
u
se
d
i
n
t
h
is
sy
ste
m
f
o
r
re
s
u
lt
s
c
las
sif
ic
a
ti
o
n
.
T
o
im
p
ro
v
e
th
e
re
su
lt
s,
a
d
a
p
ti
v
e
h
isto
g
ra
m
e
q
u
a
li
z
a
ti
o
n
p
re
-
p
ro
c
e
ss
in
g
p
r
o
c
e
d
u
re
is
e
m
p
lo
y
e
d
.
M
in
i
-
M
IA
S
d
a
tab
a
se
u
ti
li
z
e
d
to
e
v
a
lu
a
te
th
is
m
e
th
o
d
.
T
h
e
h
ig
h
e
st
a
c
c
u
ra
c
y
,
s
e
n
siti
v
it
y
,
a
n
d
sp
e
c
if
icit
y
a
c
h
iev
e
d
a
re
9
8
.
7
%
,
9
8
%
,
9
9
%
,
re
sp
e
c
ti
v
e
l
y
,
a
t
th
e
re
g
io
n
o
f
in
tere
st
(3
0
×
3
0
)
.
T
h
e
re
su
lt
s
h
a
v
e
d
e
m
o
n
stra
ted
th
e
e
f
f
i
c
a
c
y
a
n
d
a
c
c
u
ra
c
y
o
f
th
e
p
ro
p
o
se
d
m
e
th
o
d
o
f
h
e
l
p
in
g
th
e
ra
d
io
l
o
g
ist
o
n
d
iag
n
o
si
n
g
b
re
a
st ca
n
c
e
r
.
K
ey
w
o
r
d
s
:
B
r
ea
s
t c
an
ce
r
C
A
D
C
las
s
i
f
icatio
n
Gab
o
r
f
ilter
Ma
m
m
o
g
r
ap
h
y
Co
p
y
rig
h
t
©
2
0
2
0
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
:
Mo
h
a
m
m
ed
Y.
Ka
m
il,
C
o
lleg
e
o
f
Scien
ce
s
,
Mu
s
ta
n
s
ir
i
y
a
h
U
n
iv
er
s
it
y
,
B
ag
h
d
ad
,
I
r
aq
.
E
m
ail:
m
8
0
y
9
8
@
u
o
m
u
s
ta
n
s
ir
i
y
ah
.
ed
u
.
iq
1.
I
NT
RO
D
UCT
I
O
N
B
r
ea
s
t
ca
n
ce
r
is
th
e
ch
ief
ca
u
s
e
o
f
d
ea
th
l
ad
ies
in
th
eir
f
o
r
tie
s
th
r
o
u
g
h
o
u
t
th
e
w
o
r
ld
[
1
]
.
Di
ag
n
o
s
is
o
f
b
r
ea
s
t
ca
n
ce
r
ea
r
lier
is
n
ec
e
s
s
ar
y
f
o
r
i
m
p
r
o
v
i
n
g
ac
tiv
e
tr
ea
t
m
en
t
ap
p
r
o
ac
h
es
a
n
d
d
ec
r
ea
s
in
g
th
e
f
ata
lit
y
r
ate
[
2
]
.
I
m
a
g
i
n
g
s
y
s
te
m
s
b
ec
o
m
e
p
r
esen
ted
as
an
ess
en
tial
p
ar
t
o
f
ea
r
ly
d
iag
n
o
s
is
[
3
]
.
A
co
m
m
o
n
s
af
et
y
tech
n
iq
u
e
f
o
r
r
ec
o
g
n
izi
n
g
b
r
ea
s
t
tu
m
o
r
s
in
ea
r
l
y
-
s
tag
e
is
m
a
m
m
o
g
r
a
m
s
[
4
]
.
A
m
a
m
m
o
g
r
a
m
i
s
th
e
m
o
s
t
h
elp
f
u
l
s
cr
ee
n
in
g
tec
h
n
iq
u
e
f
o
r
id
en
tify
i
n
g
b
r
ea
s
t
tu
m
o
r
s
ea
r
lier
.
I
t
u
tili
ze
s
a
lo
w
er
d
o
s
ag
e
o
f
x
-
r
a
y
to
r
ec
o
g
n
ize
t
h
e
tu
m
o
r
[
5
]
.
T
h
e
s
p
ec
ialis
t
p
r
ac
tice
co
n
tr
ib
u
tes
t
o
in
cr
ea
s
i
n
g
t
h
e
ac
c
u
r
ac
y
o
f
u
s
in
g
m
a
m
m
o
g
r
a
m
s
to
d
eter
m
in
e
b
r
ea
s
t
ca
n
ce
r
.
T
o
in
cr
ea
s
es
th
e
p
atie
n
t
's
r
e
m
ai
n
d
er
p
r
o
b
ab
ilit
y
i
n
cl
u
d
in
g
t
h
e
id
ea
o
f
g
r
ea
ter
id
en
ti
f
icatio
n
o
f
b
r
ea
s
t,
m
a
m
m
o
g
r
ap
h
y
i
m
p
r
o
v
e
m
e
n
ts
b
y
t
h
e
co
m
b
in
at
io
n
o
f
th
e
co
m
p
u
ter
-
aid
ed
d
iag
n
o
s
i
s
(
C
A
Ds)
s
y
s
te
m
[
6
]
.
Pre
p
r
o
ce
s
s
in
g
,
f
e
atu
r
e
ex
tr
ac
ti
o
n
,
an
d
class
if
ica
ti
o
n
ar
e
th
e
th
r
ee
im
p
o
r
t
an
t
s
te
p
s
in
a
co
m
p
u
te
r
-
ai
d
e
d
d
et
ec
ti
o
n
te
ch
n
iq
u
e
[
7
]
.
T
e
x
tu
r
e
f
e
atu
r
e
ex
t
r
a
cti
o
n
t
ec
h
n
iq
u
es
c
an
b
e
u
ti
liz
e
d
t
o
d
en
o
t
e
m
ass
es
in
m
a
m
m
o
g
r
a
m
s
m
o
r
e
p
r
e
cise
ly
[
8
]
.
A
s
r
eg
io
n
o
f
in
ter
ests
(
R
OI
s
)
s
h
o
w
tex
tu
r
e
in
v
ar
i
o
u
s
d
ir
e
cti
o
n
s
an
d
s
ca
l
es
,
s
o
it
c
an
b
e
d
es
cr
i
b
ed
ef
f
icien
t
ly
ap
p
ly
in
g
Gab
o
r
f
ilt
er
s
.
T
h
e
r
e
ar
e
s
ev
e
r
al
s
tu
d
i
es
in
th
e
f
iel
d
o
f
m
a
m
m
o
g
r
am
in
v
esti
g
ati
o
n
f
o
r
r
e
co
g
n
i
zin
g
t
h
e
tu
m
o
r
s
,
in
c
lu
d
in
g
th
e
Ga
b
o
r
f
il
te
r
tech
n
o
l
o
g
y
,
to
ex
t
r
ac
t
f
ea
tu
r
es
[
9
,
1
0
]
.
W
ei
et
al
.
,
[
1
1
]
in
tr
o
d
u
ce
d
to
co
m
p
u
te
f
ea
tu
r
e
s
to
d
escr
ib
e
th
e
te
x
tu
r
al
p
atter
n
o
f
t
h
e
m
a
m
m
o
g
r
a
m
b
y
t
h
e
Gab
o
r
f
ilter
.
A
l
s
o
,
t
h
is
s
t
u
d
y
h
a
s
s
h
o
w
n
t
h
at
d
is
cr
i
m
i
n
ated
f
ea
t
u
r
es
ca
n
e
f
f
e
ctiv
el
y
to
i
m
p
r
o
v
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
5
2
3
5
-
5242
5236
p
er
f
o
r
m
a
n
ce
in
th
e
i
m
ag
e
r
etr
iev
al
s
y
s
te
m
.
L
ah
m
ir
i
an
d
B
o
u
k
ad
o
u
m
[
1
2
]
o
f
f
er
ed
d
is
t
in
ct
tec
h
n
iq
u
e
s
t
o
ex
tr
ac
t
f
ea
t
u
r
es
f
r
o
m
m
a
m
m
o
g
r
a
m
s
d
ep
en
d
in
g
o
n
a
co
m
b
in
atio
n
o
f
t
h
e
DW
T
an
d
th
e
Gab
o
r
f
ilter
.
First,
th
e
t
w
o
-
d
i
m
en
s
io
n
al
DW
T
is
ap
p
lied
to
p
r
ep
ar
e
th
e
i
m
ag
e.
A
Gab
o
r
f
il
ter
is
e
m
p
lo
y
ed
o
n
th
e
m
a
m
m
o
g
r
a
m
s
at
v
ar
io
u
s
w
a
v
ele
n
g
t
h
s
a
n
d
d
ir
ec
tio
n
s
.
T
h
e
f
ea
tu
r
e
s
ar
e
co
m
p
u
ted
f
r
o
m
th
i
s
i
m
a
g
e.
L
as
tl
y
,
to
d
is
tin
g
u
is
h
n
o
r
m
al
an
d
t
u
m
o
r
i
m
ag
e
s
,
c
er
tain
f
ea
t
u
r
es
ar
e
p
r
o
v
id
ed
to
th
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM)
cla
s
s
i
f
ier
.
C
las
s
i
f
icatio
n
r
e
s
u
lt
s
p
r
o
v
e
t
h
e
ef
f
ec
ti
v
en
e
s
s
o
f
th
e
m
et
h
o
d
u
s
ed
.
H
u
s
s
a
in
et
a
l
.
,
[
1
3
]
p
r
e
s
en
ted
Gab
o
r
f
il
ter
b
an
k
s
f
o
r
d
er
iv
in
g
th
e
m
o
s
t
u
t
m
o
s
t
ch
ar
ac
ter
is
tic
a
n
d
d
is
ti
n
g
u
i
s
h
te
x
t
u
r
al
f
ea
tu
r
e
s
o
f
t
u
m
o
r
s
in
th
e
i
m
ag
e
at
d
if
f
er
e
n
t
d
ir
ec
tio
n
s
a
n
d
f
r
eq
u
en
cies
to
r
ed
u
ce
FP
an
d
FN.
T
h
e
m
et
h
o
d
is
esti
m
ated
o
n
5
1
2
R
OI
s
s
elec
te
d
f
r
o
m
d
ig
i
tal
i
m
a
g
es
o
f
th
e
D
DSM
d
atab
ase.
Gab
o
r
f
ilter
b
an
k
s
ap
p
lied
o
n
R
OI
at
v
ar
io
u
s
d
ir
ec
tio
n
s
a
n
d
w
a
v
ele
n
g
t
h
s
.
A
r
o
b
u
s
t
f
ea
tu
r
e
s
elec
tio
n
s
y
s
te
m
a
n
d
S
V
M
class
if
ier
u
s
ed
w
it
h
1
0
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
.
T
h
e
o
b
tain
ed
r
esu
lt
ac
h
ie
v
es
A
z
i
s
0
.
9
9
5
.
Kh
an
et
al
.
,
[
1
4
]
o
b
tain
ed
th
e
o
r
ien
tatio
n
o
f
tex
tu
r
al
ch
ar
ac
ter
is
tics
b
y
ap
p
l
y
i
n
g
a
s
eq
u
en
ce
o
f
Gab
o
r
f
ilter
s
at
v
ar
io
u
s
d
ir
ec
tio
n
s
an
d
w
a
v
ele
n
g
th
s
.
T
h
e
s
tr
u
ct
u
r
al
ch
ar
ac
ter
is
tic
s
o
f
tu
m
o
r
s
a
n
d
n
o
r
m
al
i
m
a
g
es
in
m
a
m
m
o
g
r
a
m
s
d
escr
ib
ed
b
y
th
e
o
r
ie
n
tatio
n
o
f
te
x
t
u
r
al
f
ea
tu
r
e
s
.
R
OI
s
s
elec
ted
f
r
o
m
t
h
e
MI
AS
d
atab
ase
ar
e
u
tili
ze
d
to
esti
m
ate
t
h
is
m
et
h
o
d
.
(
SEL
w
SVM)
is
e
m
p
lo
y
ed
to
class
i
f
y
m
a
m
m
o
g
r
a
m
s
.
T
h
e
m
ea
n
ac
c
u
r
ac
y
ac
h
ie
v
ed
b
y
t
h
is
s
y
s
te
m
v
ar
ies
f
r
o
m
6
8
to
1
0
0
%.
Z
h
en
g
[
1
5
]
s
u
g
g
ested
Gab
o
r
ca
n
ce
r
d
etec
tio
n
(
GC
D)
as
a
d
is
t
in
ct
b
r
ea
s
t
tu
m
o
r
d
iag
n
o
s
is
m
e
th
o
d
,
u
s
i
n
g
Gab
o
r
c
h
ar
ac
ter
is
tic
s
.
GC
D
m
et
h
o
d
in
cl
u
d
ed
th
r
ee
i
m
p
o
r
tan
t
le
v
els
ar
e
p
r
ep
r
o
ce
s
s
in
g
,
s
eg
m
e
n
tat
io
n
,
a
n
d
class
if
icatio
n
(
d
ec
r
ea
s
in
g
f
als
e
s
ig
n
al
s
)
.
T
o
d
ec
r
ea
s
e
th
e
f
alse
s
i
g
n
al
s
,
f
u
zz
y
C
-
m
ea
n
s
cl
u
s
t
er
in
g
s
y
s
te
m
a
n
d
(
KNN)
clas
s
if
ier
ar
e
e
m
p
lo
y
ed
.
T
h
e
b
est r
esu
lt o
f
G
C
D
alg
o
r
it
h
m
w
h
ic
h
ex
a
m
i
n
ed
o
n
t
h
e
D
DSM
d
atab
ase
is
9
0
%.
I
n
t
h
is
r
e
s
ea
r
ch
,
w
e
o
f
f
er
an
ap
p
r
o
ac
h
f
o
r
b
r
ea
s
t
m
ass
d
i
ag
n
o
s
is
b
y
e
x
a
m
in
i
n
g
t
h
e
lo
c
al
tex
t
u
r
al
ch
ar
ac
ter
is
tic
s
o
f
t
h
e
t
u
m
o
r
s
.
Fo
r
th
is
,
w
e
u
tili
ze
th
e
Gab
o
r
f
ilter
to
o
b
tain
t
h
e
te
x
tu
r
e
f
ea
t
u
r
es.
T
h
ese
f
ea
tu
r
e
s
ar
e
i
m
p
o
r
tan
t
f
o
r
ac
c
u
r
atel
y
r
ec
o
g
n
izi
n
g
tr
u
e
t
u
m
o
r
s
an
d
d
ec
r
ea
s
e
th
e
f
al
s
e
-
p
o
s
itiv
e
d
i
ag
n
o
s
is
.
W
e
ap
p
l
y
th
is
m
eth
o
d
o
n
a
s
et
o
f
R
OI
s
d
er
iv
ed
f
r
o
m
th
e
m
in
i
-
MI
AS
d
atab
ase.
T
h
e
d
er
iv
ed
f
e
atu
r
es
ar
e
p
r
o
v
id
ed
as
in
f
o
r
m
atio
n
to
th
e
clas
s
i
f
ier
to
ex
a
m
in
e
t
h
e
in
p
u
t
R
OI
s
an
d
class
i
f
y
th
e
m
i
n
to
ex
ac
t
m
a
s
s
e
s
an
d
n
o
r
m
al
ti
s
s
u
es.
2.
G
AB
O
R
F
I
L
T
E
R
T
h
e
tex
tu
r
e
is
th
e
e
s
s
e
n
tial
f
ea
t
u
r
e
f
o
r
d
is
t
in
g
u
is
h
i
n
g
th
e
R
OI
s
o
f
d
i
f
f
er
en
t
c
lass
e
s
o
f
i
m
a
g
es.
T
ex
tu
r
e
in
v
esti
g
atio
n
is
n
ec
es
s
ar
y
f
o
r
co
m
p
u
ter
ized
an
al
y
s
i
s
f
o
r
d
is
tr
ib
u
t
io
n
[
1
6
]
.
T
u
m
o
r
s
in
a
R
OI
s
i
n
cl
u
d
e
m
icr
o
-
p
atter
n
s
i
n
v
ar
io
u
s
f
r
e
q
u
en
cie
s
an
d
d
ir
ec
tio
n
s
.
T
h
ese
p
atter
n
s
ar
e
i
m
p
o
r
tan
t
i
n
t
h
e
id
en
t
if
ica
tio
n
o
f
d
estru
cti
v
e
r
eg
io
n
s
i
n
a
C
o
m
p
u
ter
-
aid
ed
d
ia
g
n
o
s
is
s
y
s
te
m
.
Gab
o
r
f
ilter
s
ca
n
b
e
e
f
f
icie
n
tl
y
u
tili
ze
d
to
id
en
ti
f
y
th
ese
p
atter
n
s
[
1
7
]
.
Gab
o
r
f
ilter
s
ar
e
lin
ea
r
f
ilter
s
u
tili
ze
d
i
n
m
an
y
e
m
p
lo
y
m
en
t
s
in
t
h
e
d
o
m
ai
n
s
o
f
co
m
p
u
ter
v
is
io
n
p
r
o
b
le
m
s
,
s
u
ch
as
i
n
t
ex
tu
r
e
an
al
y
s
is
,
f
ac
e
id
en
ti
f
ic
atio
n
,
a
n
d
ca
n
ce
r
d
ia
g
n
o
s
is
[
1
8
]
.
A
n
i
m
p
r
e
s
s
i
v
e
ch
ar
ac
ter
is
tic
o
f
Gab
o
r
f
ilter
s
h
as
th
e
b
est
co
m
b
in
ed
lo
c
aliza
tio
n
i
n
f
r
eq
u
e
n
c
y
an
d
s
p
atial
d
o
m
ain
s
[
1
9
]
.
T
o
o
b
tain
th
e
v
alu
e
o
f
m
a
m
m
o
g
r
a
m
,
Gab
o
r
f
ilter
s
o
f
d
is
t
in
g
u
i
s
h
ed
d
ir
ec
tio
n
u
s
ed
to
tr
an
s
f
er
m
a
m
m
o
g
r
a
m
b
y
d
eter
m
i
n
i
n
g
th
e
b
es
t
m
ag
n
i
tu
d
e
o
f
Gab
o
r
f
ilter
p
a
r
a
m
eter
s
,
a
n
d
th
e
n
o
r
m
al
ize
d
m
a
m
m
o
g
r
a
m
is
th
e
o
u
tp
u
t
[
2
0
]
.
I
n
th
is
w
o
r
k
,
w
e
o
f
f
er
ed
th
e
m
ag
n
it
u
d
e
o
f
t
h
e
Gab
o
r
f
ilter
in
f
i
g
u
r
e
.
T
h
es
e
f
ilter
s
r
ep
r
esen
ted
in
co
m
p
le
x
m
at
h
e
m
atic
s
as:
=
e
xp
[
−
(
x
c
os
θ
+
y
s
in
θ
)
2
+
γ
2
(
yc
os
θ
−
xsin
θ
)
2
2
σ
2
]
.
e
xp
[
i
[
2π
(
xc
os
θ
+
ys
in
θ
)
+
Ø
]
]
(
1
)
w
h
er
e
θ
is
th
e
f
i
lter
o
r
ien
tatio
n
,
γ
is
th
e
s
p
atial
asp
ec
t
r
atio
,
λ
is
th
e
s
i
n
u
s
o
id
al
w
av
ele
n
g
t
h
,
σ
is
th
e
s
tan
d
ar
d
d
ev
iatio
n
o
f
Ga
u
s
s
ia
n
f
u
n
ctio
n
,
an
d
Ø
is
t
h
e
p
h
ase
o
f
f
s
et.
3.
P
RO
P
O
SE
D
M
E
T
H
O
D
I
n
th
is
p
ar
t,
w
e
h
a
n
d
le
e
v
er
y
s
tep
o
f
o
u
r
ap
p
r
o
ac
h
to
t
h
e
d
ia
g
n
o
s
is
o
f
a
b
r
ea
s
t
m
a
s
s
.
T
h
e
i
n
itial
s
ta
g
e
in
cl
u
d
es
t
h
e
m
a
m
m
o
g
r
a
m
ac
q
u
is
itio
n
,
f
o
llo
w
in
g
w
e
e
x
tr
ac
t
R
OI
f
r
o
m
th
e
m
a
m
m
o
g
r
a
m
,
a
f
ter
t
h
a
t
th
e
e
n
h
a
n
ce
m
en
t
p
r
o
ce
s
s
is
e
m
p
lo
y
i
n
g
to
d
ev
elo
p
m
a
m
m
o
g
r
a
m
s
.
T
h
e
f
ea
t
u
r
e
ex
tr
ac
t
io
n
s
tep
in
v
o
lv
e
s
Gab
o
r
f
ilter
s
f
o
r
th
e
r
ep
r
esen
tati
v
e
R
OI
at
v
ar
io
u
s
w
a
v
ele
n
g
t
h
s
an
d
d
ir
ec
tio
n
s
.
Fin
al
l
y
,
R
OI
s
class
i
f
icatio
n
i
n
to
n
o
r
m
al
a
n
d
ab
n
o
r
m
al.
T
h
e
m
a
m
m
o
g
r
a
m
s
ar
e
co
lle
cted
f
r
o
m
t
h
e
m
i
n
i
-
MI
A
S
d
atab
ase
[
2
1
]
.
T
h
is
d
atab
ase
co
n
tai
n
s
322
m
a
m
m
o
g
r
a
m
s
f
r
o
m
1
6
1
w
o
m
en
;
m
i
n
i
-
MI
A
S
i
n
cl
u
d
e
n
o
r
m
al
a
n
d
ab
n
o
r
m
al
m
a
m
m
o
g
r
a
m
s
,
th
e
ab
n
o
r
m
al
m
a
m
m
o
g
r
a
m
s
ca
te
g
o
r
ized
to
b
en
ig
n
an
d
ca
n
ce
r
o
u
s
.
T
h
e
d
ataset
p
r
ese
n
ts
a
r
ep
o
r
t
ab
o
u
t
esti
m
ated
th
e
p
o
s
itio
n
an
d
r
ad
i
u
s
(
i
n
p
i
x
els)
o
f
t
h
e
m
as
s
i
n
d
icate
d
b
y
th
e
r
ad
io
lo
g
i
s
t
(
g
r
o
u
n
d
tr
u
th
)
.
T
h
e
m
a
m
m
o
g
r
a
m
d
i
m
en
s
io
n
(
i
m
ag
e
s
ize)
is
1
0
2
4
⨯
1
0
2
4
p
ix
els.
T
h
is
d
atab
ase
in
clu
d
e
s
i
n
f
o
r
m
atio
n
a
b
o
u
t
m
a
m
m
o
g
r
a
m
s
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
C
o
mp
u
ter
-
a
id
ed
d
ia
g
n
o
s
is
s
ystem
fo
r
b
r
ea
s
t c
a
n
ce
r
b
a
s
ed
o
n
th
e
Ga
b
o
r
filt
er
...
(
Mo
h
a
mm
ed
Y.
K
a
mil
)
5237
f
o
r
in
s
ta
n
ce
,
t
h
e
k
i
n
d
o
f
m
as
s
:
ill
-
d
e
f
in
ed
(
ild
.
)
,
as
y
m
m
etr
y
(
as
y
.
)
,
ar
ch
itect
u
r
al
d
is
to
r
tio
n
(
ar
ch
.
)
,
s
p
icu
lated
(
s
p
i.)
,
cir
cu
m
s
cr
ib
ed
(
cir
.
)
,
an
d
ca
lcif
icatio
n
(
ca
l.)
.
T
h
e
tu
m
o
r
zo
n
es
s
elec
ted
b
as
ed
o
n
t
h
e
m
i
n
i
-
MI
A
S
tu
m
o
r
,
i
n
d
icatin
g
w
h
ich
r
ep
r
esen
t
s
t
h
e
s
p
ec
ialis
t
an
al
y
z
in
g
an
d
s
h
o
w
t
h
e
x
-
ax
i
s
an
d
y
-
ax
is
f
o
r
a
s
p
ec
if
ic
tu
m
o
r
in
th
e
m
a
m
m
o
g
r
a
m
[
2
2
]
.
T
h
ese
in
d
icat
io
n
s
ar
e
g
r
o
u
n
d
tr
u
t
h
(
GT
)
an
d
d
eter
m
in
ed
as
a
r
ec
tan
g
u
lar
r
eg
io
n
.
T
o
im
p
r
o
v
e
clas
s
i
f
icatio
n
ac
c
u
r
ac
y
,
R
OI
cr
o
p
p
ed
m
an
u
all
y
i
n
s
id
e
GT
[
2
3
]
.
R
OI
estab
lis
h
ed
as
a
s
q
u
ar
e
r
eg
io
n
.
T
h
e
n
o
r
m
al
m
a
m
m
o
g
r
a
m
,
R
OI
s
elec
ted
m
an
u
all
y
f
r
o
m
ar
b
itra
r
y
lo
ca
ti
o
n
s
.
E
x
tr
ac
t R
OI
h
as
s
h
o
w
n
in
F
ig
u
r
e
1
.
I
n
o
r
d
er
to
im
p
r
o
v
e
th
e
f
e
atu
r
es
an
d
to
s
h
ar
p
en
th
e
d
etail
s
in
th
e
i
m
ag
e.
T
h
u
s
,
w
e
o
b
tain
h
ig
h
-
p
er
f
o
r
m
a
n
ce
r
es
u
lt
s
a
n
d
i
n
cr
ea
s
e
t
h
e
ac
c
u
r
ac
y
o
f
t
h
e
d
i
ag
n
o
s
is
.
T
h
e
en
h
a
n
ce
m
en
t
s
te
p
in
C
AD
s
y
s
te
m
is
o
n
e
o
f
th
e
i
m
p
o
r
tan
t
s
ta
g
es
t
h
at
d
eter
m
in
e
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
al
g
o
r
ith
m
[
2
4
]
.
Her
e,
w
e
u
s
ed
th
e
ad
ap
ti
v
e
h
is
to
g
r
a
m
eq
u
a
lizatio
n
(
A
HE
)
m
eth
o
d
to
en
h
a
n
ce
R
OI
.
A
H
E
ass
is
t
s
in
i
m
p
r
o
v
i
n
g
t
h
e
co
n
tr
ast
o
f
ea
ch
p
ix
el.
T
h
is
tech
n
iq
u
e
ca
lcu
la
tes
t
h
e
v
ar
io
u
s
h
is
to
g
r
a
m
s
,
in
d
i
v
id
u
al
l
y
id
en
tical
to
th
e
d
is
tin
g
u
is
h
e
d
P
a
r
t
o
f
th
e
i
m
a
g
e
id
en
ti
f
ied
as
tiles
.
E
v
er
y
tile
's
co
n
tr
ast
is
i
m
p
r
o
v
ed
to
r
ed
is
tr
ib
u
te
th
e
g
r
a
y
s
ca
le
o
f
t
h
e
i
m
ag
e.
T
h
e
ad
j
ac
en
t
tiles
later
co
n
n
ec
ted
u
til
izin
g
b
ilin
ea
r
in
ter
p
o
latio
n
to
r
ed
u
ce
ar
tif
iciall
y
p
r
o
d
u
ce
d
ed
g
es.
Fig
u
r
e
2
ex
p
o
s
es
t
h
e
R
OI
b
ef
o
r
e
an
d
af
ter
im
p
le
m
e
n
ti
n
g
th
e
AHE
s
y
s
te
m
.
T
h
e
l
in
ea
r
SVM
(
L
SV
M)
is
e
m
p
lo
y
ed
as
a
class
i
f
ier
.
T
h
e
lin
ea
r
f
u
n
ctio
n
b
asis
o
f
t
h
e
p
r
ac
tice
o
f
L
SV
M
in
a
h
ig
h
d
i
m
en
s
io
n
al
c
h
ar
ac
ter
is
tic
ter
m
th
at
g
ets
a
n
o
p
ti
m
al
s
ep
ar
atin
g
h
y
p
er
p
lan
e
[
2
5
]
.
T
h
e
SVM
p
r
o
d
u
ce
s
g
r
ea
t
ac
cu
r
ac
y
co
m
p
a
r
ed
w
i
th
o
th
er
s
et
s
o
f
s
y
s
te
m
s
.
Fig
u
r
e
1
.
Gr
o
u
n
d
tr
u
t
h
,
R
OI
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
2
.
(
a)
Or
ig
in
al
R
OI
w
i
t
h
(
b
)
its
h
is
to
g
r
a
m
; a
n
d
(
c)
R
OI
en
h
a
n
ce
d
w
ith
(
d
)
its
h
is
to
g
r
a
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
5
2
3
5
-
5242
5238
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
NS
T
h
e
s
u
g
g
e
s
ted
m
e
th
o
d
is
tes
ted
b
y
th
e
m
in
i
-
MI
AS
d
atab
ase.
I
n
m
i
n
i
-
MI
A
S,
t
u
m
o
r
r
e
g
io
n
s
ar
e
s
elec
ted
(
g
r
o
u
n
d
tr
u
t
h
)
,
th
e
s
e
r
eg
io
n
s
ar
e
m
a
n
u
all
y
cr
o
p
p
ed
to
g
en
er
ate
R
OI
s
w
ith
in
t
h
e
g
r
o
u
n
d
tr
u
t
h
in
t
h
r
ee
d
i
m
en
s
io
n
s
(
1
0
×1
0
,
2
0
×2
0
,
3
0
×3
0
)
p
ix
els
b
ase
o
n
th
e
d
i
m
e
n
s
io
n
s
o
f
t
u
m
o
r
in
m
a
m
m
o
g
r
a
m
s
.
R
OI
s
ar
e
d
ef
in
ed
m
a
n
u
al
l
y
f
r
o
m
o
p
tio
n
al
r
eg
io
n
s
in
n
o
r
m
al
ca
s
e
s
w
ith
th
e
s
a
m
e
d
i
m
en
s
io
n
s
o
f
ab
n
o
r
m
al
ca
s
es.
I
n
t
h
e
p
r
ep
r
o
ce
s
s
in
g
s
tep
,
th
e
A
HE
m
e
th
o
d
ap
p
lied
to
en
h
a
n
ce
R
OI
a
n
d
r
aise
t
h
e
ac
c
u
r
ac
y
o
f
t
h
e
a
n
al
y
s
is
o
f
b
r
ea
s
t
tu
m
o
r
s
.
A
f
ter
th
at,
w
e
e
m
p
lo
y
ed
t
h
e
Gab
o
r
f
ilter
f
o
r
all
m
a
m
m
o
g
r
a
m
s
to
ex
tr
ac
t
tex
t
u
r
e
f
ea
tu
r
es.
I
n
th
is
r
esear
c
h
,
4
o
r
ien
tatio
n
s
(
0
,
4
5
,
9
0
,
1
3
5
)
an
d
3
w
av
elen
g
t
h
s
(
3
0
,
5
0
,
7
0
)
u
s
ed
.
T
h
e
Gab
o
r
f
ilter
i
m
p
le
m
en
ta
tio
n
r
ep
r
esen
ted
i
n
Fig
u
r
e
3.
wa
v
ele
n
g
t
h
Or
ien
tatio
n
0˚
45˚
90˚
135˚
30
50
70
Fig
u
r
e
3
.
T
h
e
m
a
g
n
i
tu
d
e
o
f
t
h
e
Gab
o
r
f
ilter
f
o
r
an
i
m
a
g
e
s
el
ec
ted
f
r
o
m
d
atab
ase
Fo
u
r
f
ea
t
u
r
es
w
e
d
er
iv
ed
w
h
e
n
i
m
p
le
m
e
n
ti
n
g
t
h
e
Gab
o
r
f
ilt
er
s
ar
e
co
n
tr
ast,
co
r
r
elatio
n
,
en
er
g
y
,
an
d
h
o
m
o
g
en
eit
y
.
T
h
e
R
OI
is
ch
a
r
ac
ter
ized
as
n
o
r
m
al
o
r
m
as
s
b
y
u
tili
zi
n
g
th
e
L
SV
M
class
i
f
ier
.
T
h
e
L
SVM
i
s
tr
ain
ed
w
it
h
th
e
d
er
i
v
ed
f
ea
t
u
r
es
an
d
u
s
in
g
t
h
e
p
r
ac
ticed
m
ag
n
i
tu
d
es.
T
esti
n
g
f
ea
t
u
r
es
r
e
co
g
n
ize
t
h
e
n
o
r
m
al
tis
s
u
e
a
n
d
t
h
e
t
u
m
o
r
.
T
ab
les
1
-
3
s
h
o
w
t
h
e
r
ep
r
ese
n
tatio
n
o
f
t
h
e
Ga
b
o
r
d
esig
n
w
i
th
L
SV
M
a
n
d
5
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
.
T
ab
le
1
s
h
o
w
s
th
e
h
ig
h
es
t
ac
cu
r
ac
y
,
9
8
.
7
%
o
b
tain
ed
in
t
h
e
R
OI
(
3
0
×3
0
)
at
w
a
v
elen
g
th
5
0
an
d
o
r
ien
tatio
n
s
0
˚
f
o
r
ill
-
d
ef
i
n
ed
d
is
ea
s
e.
W
h
i
le,
t
h
e
lo
w
es
t
ac
c
u
r
ac
y
is
7
2
.
7
%
in
th
e
R
OI
(
3
0
×3
0
)
at
w
a
v
ele
n
g
th
5
0
an
d
o
r
ien
tatio
n
s
4
5
˚
f
o
r
ar
ch
itect
u
r
al
d
is
to
r
tio
n
d
is
ea
s
e.
T
h
e
h
ig
h
est
s
e
n
s
iti
v
it
y
a
n
d
s
p
ec
if
icit
y
ac
h
ie
v
ed
b
y
ap
p
ly
i
n
g
th
e
p
r
o
p
o
s
ed
class
if
i
ca
tio
n
is
1
0
0
%.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
C
o
mp
u
ter
-
a
id
ed
d
ia
g
n
o
s
is
s
ystem
fo
r
b
r
ea
s
t c
a
n
ce
r
b
a
s
ed
o
n
th
e
Ga
b
o
r
filt
er
...
(
Mo
h
a
mm
ed
Y.
K
a
mil
)
5239
T
ab
le
1
.
T
h
e
ac
cu
r
ac
y
p
r
o
v
id
e
d
b
y
u
s
i
n
g
t
h
e
L
SVM
cla
s
s
i
f
ie
r
at
w
av
e
len
g
t
h
s
(
3
0
,
5
0
,
7
0
)
a
n
d
o
r
ien
tatio
n
s
(
0
,
4
5
,
9
0
,
1
3
5
)
A
c
c
u
r
a
c
y
%
t
y
p
e
R
O
I
a
r
c
h
.
a
sy
.
c
a
l
.
c
i
r
.
i
l
d
.
sp
i
.
w
a
v
e
l
e
n
g
t
h
O
r
i
e
n
t
a
t
i
o
n
=
0
˚
1
0
×
1
0
8
4
.
6
8
2
.
7
8
1
.
4
7
6
.
7
8
5
.
5
7
9
.
5
30
2
0
×
2
0
9
8
.
1
9
5
.
5
9
3
.
9
9
6
.
7
93
9
8
.
1
3
0
×
3
0
9
4
.
7
8
6
.
4
8
6
.
8
90
93
9
3
.
1
1
0
×
1
0
8
2
.
9
8
4
.
5
85
7
6
.
7
8
5
.
5
8
4
.
6
50
2
0
×
2
0
9
6
.
4
90
9
0
.
4
9
8
.
3
9
6
.
8
9
6
.
4
3
0
×
3
0
8
6
.
3
8
4
.
5
8
1
.
4
8
6
.
7
9
8
.
7
8
6
.
3
1
0
×
1
0
8
6
.
3
8
6
.
4
7
9
.
6
7
6
.
7
8
5
.
5
8
1
.
2
70
2
0
×
2
0
8
4
.
7
90
8
1
.
4
95
9
4
.
9
9
1
.
4
3
0
×
3
0
8
9
.
7
8
2
.
7
7
9
.
6
8
8
.
3
8
7
.
4
8
9
.
7
O
r
i
e
n
t
a
t
i
o
n
=
4
5
˚
1
0
×
1
0
7
9
.
5
9
1
.
8
8
1
.
4
8
8
.
3
8
5
.
5
7
7
.
8
30
2
0
×
2
0
7
7
.
8
9
5
.
5
8
8
.
6
8
8
.
3
8
7
.
4
8
9
.
7
3
0
×
3
0
7
7
.
8
8
2
.
7
85
8
3
.
3
8
5
.
5
7
7
.
8
1
0
×
1
0
7
9
.
5
90
85
8
6
.
7
8
7
.
4
7
7
.
8
50
2
0
×
2
0
7
9
.
5
8
4
.
5
85
8
6
.
7
8
9
.
2
8
4
.
6
3
0
×
3
0
7
2
.
7
8
2
.
7
85
85
8
5
.
5
8
4
.
6
1
0
×
1
0
7
4
.
4
8
4
.
5
8
1
.
4
8
8
.
3
8
5
.
5
7
7
.
8
70
2
0
×
2
0
7
9
.
5
8
4
.
5
8
8
.
6
90
93
7
7
.
8
3
0
×
3
0
8
1
.
2
8
2
.
7
8
1
.
4
80
8
5
.
5
8
2
.
9
O
r
i
e
n
t
a
t
i
o
n
=
9
0
˚
1
0
×
1
0
7
9
.
5
8
4
.
5
8
1
.
4
7
8
.
3
9
1
.
1
7
9
.
5
30
2
0
×
2
0
8
2
.
9
9
1
.
8
8
1
.
4
7
8
.
3
9
6
.
8
8
4
.
6
3
0
×
3
0
8
6
.
3
7
9
.
5
8
3
.
2
7
8
.
3
9
1
.
1
8
9
.
7
1
0
×
1
0
8
1
.
2
8
4
.
5
8
3
.
2
7
8
.
3
8
9
.
2
7
9
.
5
50
2
0
×
2
0
8
6
.
3
8
6
.
4
85
85
9
4
.
9
8
6
.
3
3
0
×
3
0
88
9
3
.
6
8
1
.
4
85
8
9
.
2
8
2
.
9
1
0
×
1
0
7
7
.
8
8
6
.
4
8
1
.
4
7
6
.
7
8
7
.
4
7
7
.
8
70
2
0
×
2
0
9
1
.
4
8
4
.
5
8
3
.
2
85
9
4
.
9
9
1
.
4
3
0
×
3
0
8
3
.
1
9
5
.
5
8
1
.
4
8
1
.
7
9
1
.
1
88
O
r
i
e
n
t
a
t
i
o
n
=
1
3
5
˚
1
0
×
1
0
7
4
.
4
8
4
.
5
8
1
.
4
85
8
5
.
5
7
9
.
5
30
2
0
×
2
0
7
5
.
1
8
8
.
2
8
8
.
6
85
8
5
.
5
7
7
.
8
3
0
×
3
0
7
6
.
1
8
8
.
2
8
3
.
2
80
8
5
.
5
8
1
.
2
1
0
×
1
0
7
4
.
5
8
0
.
9
8
1
.
4
7
6
.
7
8
5
.
5
7
9
.
5
50
2
0
×
2
0
7
7
.
8
8
4
.
5
8
3
.
2
8
8
.
3
8
5
.
5
8
4
.
6
3
0
×
3
0
7
6
.
1
8
4
.
5
8
1
.
4
8
6
.
7
8
9
.
2
7
7
.
8
1
0
×
1
0
7
9
.
5
8
2
.
7
7
6
.
1
80
93
7
9
.
5
70
2
0
×
2
0
8
0
.
9
8
4
.
5
8
3
.
2
8
6
.
7
8
5
.
5
8
1
.
2
3
0
×
3
0
7
7
.
8
8
6
.
4
8
6
.
8
85
8
5
.
5
7
7
.
8
T
ab
le
2
.
T
h
e
s
en
s
iti
v
it
y
p
r
o
v
i
d
ed
b
y
u
s
in
g
t
h
e
L
SVM
clas
s
i
f
ier
at
w
av
ele
n
g
t
h
s
(
3
0
,
5
0
,
7
0
)
an
d
o
r
ien
tatio
n
s
(
0
,
4
5
,
9
0
,
1
3
5
)
S
e
n
si
t
i
v
i
t
y
%
t
y
p
e
R
O
I
a
r
c
h
.
a
sy
.
c
a
l
.
c
i
r
.
i
l
d
.
sp
i
.
w
a
v
e
l
e
n
g
t
h
O
r
i
e
n
t
a
t
i
o
n
=
0
˚
1
0
×
1
0
42
23
35
25
27
26
30
2
0
×
2
0
84
77
73
80
41
84
3
0
×
3
0
95
23
29
60
64
78
1
0
×
1
0
63
30
29
18
79
47
50
2
0
×
2
0
84
57
66
90
97
84
3
0
×
3
0
73
43
23
80
98
78
1
0
×
1
0
42
30
23
20
28
47
70
2
0
×
2
0
84
83
85
95
72
68
3
0
×
3
0
84
43
29
65
33
68
O
r
i
e
n
t
a
t
i
o
n
=
4
5
˚
1
0
×
10
73
67
45
65
28
25
30
2
0
×
2
0
57
87
51
85
58
78
3
0
×
3
0
52
32
39
45
28
28
1
0
×
1
0
52
87
33
85
35
28
50
2
0
×
2
0
52
73
64
70
66
68
3
0
×
3
0
31
40
39
80
30
57
1
0
×
1
0
36
67
51
85
28
25
70
2
0
×
2
0
52
53
76
80
58
52
3
0
×
3
0
41
67
33
45
33
67
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
5
2
3
5
-
5242
5240
T
ab
le
2
.
T
h
e
s
en
s
iti
v
it
y
p
r
o
v
i
d
ed
b
y
u
s
in
g
t
h
e
L
SVM
clas
s
i
f
ier
at
w
av
ele
n
g
t
h
s
(
3
0
,
5
0
,
7
0
)
an
d
o
r
ien
tatio
n
s
(
0
,
4
5
,
9
0
,
1
3
5
)
(
c
o
n
tin
u
e
)
S
e
n
si
t
i
v
i
t
y
%
t
y
p
e
R
O
I
a
r
c
h
.
a
sy
.
c
a
l
.
c
i
r
.
i
l
d
.
sp
i
.
w
a
v
e
l
e
n
g
t
h
O
r
i
e
n
t
a
t
i
o
n
=
9
0
˚
1
0
×
1
0
57
60
45
50
66
46
30
2
0
×
2
0
41
80
58
30
82
73
3
0
×
3
0
52
36
45
35
58
78
1
0
×
1
0
31
33
26
30
66
36
50
2
0
×
2
0
83
47
70
70
74
73
3
0
×
3
0
67
87
26
60
51
73
1
0
×
1
0
31
80
28
25
66
25
70
2
0
×
2
0
99
47
26
70
89
78
3
0
×
3
0
62
87
51
60
58
73
O
r
i
e
n
t
a
t
i
o
n
=
1
3
5
˚
1
0
×
1
0
31
73
26
85
25
73
30
2
0
×
2
0
25
67
58
85
28
28
3
0
×
3
0
41
73
39
65
32
57
1
0
×
1
0
25
67
58
65
30
36
50
2
0
×
2
0
25
67
26
95
28
78
3
0
×
3
0
25
40
33
95
58
46
1
0
×
1
0
62
33
45
75
74
25
70
2
0
×
2
0
53
60
45
75
28
62
3
0
×
3
0
67
60
51
1
0
0
35
32
T
ab
le
3
.
T
h
e
s
p
ec
if
icit
y
p
r
o
v
i
d
ed
b
y
u
s
in
g
t
h
e
L
SVM
clas
s
i
f
ier
at
w
av
ele
n
g
t
h
s
(
3
0
,
5
0
,
7
0
)
an
d
o
r
ien
tatio
n
s
(
0
,
4
5
,
9
0
,
1
3
5
)
S
p
e
c
i
f
i
c
i
t
y
%
t
y
p
e
R
O
I
a
r
c
h
.
a
sy
.
c
a
l
.
c
i
r
.
i
l
d
.
sp
i
.
w
a
v
e
l
e
n
g
t
h
O
r
i
e
n
t
a
t
i
o
n
=
0
˚
1
0
×
1
0
95
95
60
70
99
95
30
2
0
×
2
0
95
93
93
95
99
95
3
0
×
3
0
88
1
0
0
1
0
0
95
93
90
1
0
×
1
0
83
95
98
1
0
0
98
93
50
2
0
×
2
0
93
93
90
93
1
0
0
93
3
0
×
3
0
83
90
93
80
99
80
1
0
×
1
0
98
98
93
95
1
0
0
88
70
2
0
×
2
0
90
83
70
85
93
93
3
0
×
3
0
83
80
90
73
95
90
O
r
i
e
n
t
a
t
i
o
n
=
4
5
˚
1
0
×
1
0
78
95
80
95
1
0
0
98
30
2
0
×
2
0
83
93
98
85
90
90
3
0
×
3
0
85
1
0
0
98
98
1
0
0
1
0
0
1
0
×
1
0
88
85
1
0
0
83
98
1
0
0
50
2
0
×
2
0
88
83
88
90
90
90
3
0
×
3
0
88
83
98
83
1
0
0
93
1
0
×
1
0
88
85
88
85
98
98
70
2
0
×
20
88
90
88
90
98
85
3
0
×
3
0
95
70
90
93
1
0
0
85
O
r
i
e
n
t
a
t
i
o
n
=
9
0
˚
1
0
×
1
0
85
88
63
88
93
90
30
2
0
×
2
0
98
90
93
98
95
85
3
0
×
3
0
98
95
93
95
95
90
1
0
×
1
0
1
0
0
98
1
0
0
98
90
95
50
2
0
×
2
0
83
95
85
88
95
88
3
0
×
3
0
93
90
80
93
95
83
1
0
×
1
0
95
83
98
1
0
0
88
98
70
2
0
×
2
0
83
93
1
0
0
88
90
93
3
0
×
3
0
85
93
88
88
95
90
O
r
i
e
n
t
a
t
i
o
n
=
1
3
5
˚
1
0
×
1
0
90
83
88
80
1
0
0
78
30
2
0
×
2
0
95
90
95
80
1
0
0
1
0
0
3
0
×
3
0
88
88
95
83
1
0
0
88
1
0
×
1
0
93
80
85
78
1
0
0
95
50
2
0
×
2
0
98
85
1
0
0
80
1
0
0
83
3
0
×
3
0
95
95
93
78
93
88
1
0
×
1
0
83
88
83
78
93
1
0
0
70
2
0
×
2
0
85
88
93
88
1
0
0
85
3
0
×
3
0
78
90
95
73
1
0
0
1
0
0
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
C
o
mp
u
ter
-
a
id
ed
d
ia
g
n
o
s
is
s
ystem
fo
r
b
r
ea
s
t c
a
n
ce
r
b
a
s
ed
o
n
th
e
Ga
b
o
r
filt
er
...
(
Mo
h
a
mm
ed
Y.
K
a
mil
)
5241
5.
CO
NCLU
SI
O
N
I
n
th
i
s
s
t
u
d
y
,
w
e
h
a
v
e
ex
a
m
i
n
ed
th
e
Gab
o
r
f
ilter
as
a
tech
n
iq
u
e
f
o
r
av
o
id
in
g
tu
m
o
r
class
i
f
icatio
n
d
if
f
ic
u
lt
ies
a
n
d
FP
r
ed
u
ctio
n
.
T
h
is
m
et
h
o
d
h
as
e
m
p
lo
y
ed
to
ex
ce
r
p
t
th
e
f
ea
t
u
r
es
f
r
o
m
te
x
t
u
r
al
R
OI
s
at
v
ar
io
u
s
w
a
v
ele
n
g
t
h
s
an
d
o
r
ien
tatio
n
s
.
T
h
e
f
ea
tu
r
es
o
b
ta
in
ed
b
ased
o
n
th
e
Gab
o
r
f
ilter
s
h
o
w
n
to
s
tr
o
n
g
l
y
d
is
tin
g
u
is
h
b
et
w
ee
n
t
h
e
n
o
r
m
al
a
n
d
ab
n
o
r
m
al
t
is
s
u
e
s
u
ti
lized
in
th
e
tes
ts
a
n
d
i
m
p
r
o
v
es
t
h
e
id
e
n
ti
f
icatio
n
r
ate
o
f
th
e
b
r
ea
s
t
tu
m
o
r
d
iag
n
o
s
is
s
y
s
te
m
.
T
h
is
f
ilter
es
ti
m
ated
u
p
o
n
R
OI
m
a
m
m
o
g
r
a
m
s
d
er
iv
ed
f
r
o
m
t
h
e
m
i
n
i
-
MI
A
S
d
atab
ase.
A
H
E
h
as
u
s
ed
as
a
p
r
e
-
p
r
o
ce
s
s
in
g
p
r
o
ce
d
u
r
e
to
en
h
an
ce
lo
ca
l
g
r
a
y
lev
e
ls
v
al
u
e
s
o
f
R
OI
s
.
T
o
r
ec
o
g
n
ize
R
OI
as
n
o
r
m
al
o
r
m
ass
,
L
S
VM
i
s
e
m
p
lo
y
ed
.
T
h
is
clas
s
i
f
ier
p
r
o
d
u
ce
s
th
e
m
o
s
t
ap
p
r
o
v
in
g
r
esu
lts
at
R
OI
(
3
0
×3
0
)
,
o
r
ien
tatio
n
0
˚
,
an
d
w
a
v
ele
n
g
t
h
5
0
,
w
h
er
e
t
h
e
ac
cu
r
ac
y
,
s
e
n
s
iti
v
it
y
,
s
p
ec
if
icit
y
i
s
9
8
.
7
%,
9
8
%,
9
9
%,
r
esp
ec
tiv
el
y
.
I
n
t
h
e
C
AD
s
y
s
te
m
,
t
h
e
an
a
l
y
s
is
o
f
b
r
ea
s
t
m
as
s
ca
n
b
e
d
ev
elo
p
ed
b
y
th
e
co
m
b
i
n
atio
n
Gab
o
r
f
ilter
m
eth
o
d
w
it
h
o
th
e
r
f
ea
tu
r
e
ex
tr
ac
tio
n
tec
h
n
iq
u
es
.
RE
F
E
R
E
NC
E
S
[1
]
A
.
Un
n
i
,
N.
Eg
,
S
.
V
in
o
d
,
a
n
d
L
.
S
.
Na
ir,
“
T
u
m
o
u
r
d
e
tec
ti
o
n
in
d
o
u
b
le
th
re
sh
o
l
d
se
g
m
e
n
ted
m
a
m
m
o
g
r
a
m
s
u
sin
g
o
p
ti
m
ize
d
GL
CM
fe
a
tu
re
s
f
e
d
S
V
M
,
”
in
2
0
1
8
i
n
ter
n
a
t
io
n
a
l
c
o
n
fer
e
n
c
e
o
n
a
d
v
a
n
c
e
s in
c
o
mp
u
ti
n
g
,
c
o
mm
u
n
ica
ti
o
n
s
a
n
d
in
fo
rm
a
t
ics
(
ICACCI)
,
p
p
.
5
5
4
-
5
59
,
2
0
1
8
.
[2
]
N
.
F
.
L
a
tt
o
o
f
i,
e
t
a
l
.
,
“
M
e
lan
o
m
a
S
k
in
Ca
n
c
e
r
De
tec
ti
o
n
Ba
se
d
o
n
A
BCD
Ru
le,
”
2
0
1
9
Fi
rs
t
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
f
C
o
mp
u
ter
a
n
d
Ap
p
li
e
d
S
c
ien
c
e
s (
CAS
)
,
p
p
.
1
5
4
-
1
5
7
,
2
0
1
9
.
[3
]
M
.
Y.
Ka
m
il
,
“
M
o
rp
h
o
lo
g
ica
l
g
ra
d
ien
t
in
b
ra
in
m
a
g
n
e
ti
c
re
s
o
n
a
n
c
e
im
a
g
in
g
b
a
se
d
o
n
in
t
u
i
ti
o
n
ist
ic
f
u
z
z
y
a
p
p
ro
a
c
h
,
”
in
2
0
1
6
Al
-
S
a
d
e
q
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
M
u
lt
i
d
is
c
ip
li
n
a
ry
in
IT
a
n
d
Co
mm
u
n
ica
ti
o
n
S
c
ien
c
e
a
n
d
Ap
p
li
c
a
ti
o
n
s (
AIC
-
M
IT
CS
A)
,
p
p
.
1
-
3
,
2
0
1
6
.
[4
]
S
.
B.
Y.
T
a
sd
e
m
ir,
K.
Tas
d
e
m
ir
,
a
n
d
Z.
Ay
d
in
,
“
ROI
De
tec
ti
o
n
in
M
a
m
m
o
g
r
a
m
I
m
a
g
e
s
Us
in
g
W
a
v
e
let
-
Ba
s
e
d
Ha
ra
li
c
k
a
n
d
HO
G
F
e
a
tu
re
s,
”
in
2
0
1
8
1
7
th
IEE
E
I
n
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
M
a
c
h
in
e
L
e
a
rn
i
n
g
a
n
d
Ap
p
li
c
a
t
io
n
s
(
ICM
L
A)
,
p
p
.
1
0
5
-
1
0
9
,
2
0
1
8
.
[5
]
C.
A
b
ira
m
i
,
R.
Ha
rik
u
m
a
r,
a
n
d
S
.
S
.
C
h
a
k
ra
v
a
rth
y
,
“
P
e
rf
o
rm
a
n
c
e
a
n
a
ly
sis
a
n
d
d
e
tec
ti
o
n
o
f
m
i
c
ro
c
a
lcif
i
c
a
ti
o
n
i
n
d
ig
it
a
l
m
a
m
m
o
g
r
a
m
s
u
sin
g
w
a
v
e
let
f
e
a
tu
re
s,
”
in
2
0
1
6
In
ter
n
a
t
i
o
n
a
l
Co
n
fer
e
n
c
e
o
n
W
ire
les
s
C
o
mm
u
n
ic
a
ti
o
n
s,
S
ig
n
a
l
Pro
c
e
ss
in
g
a
n
d
Ne
tw
o
rk
in
g
(
W
iS
PNE
T
)
,
p
p
.
2
3
2
7
-
2
3
3
1
,
2
0
1
6
.
[6
]
S.
P
a
sh
o
u
ta
n
,
S
.
B
.
S
h
o
k
o
u
h
i
,
a
n
d
M
.
P
a
sh
o
u
tan
,
“
A
u
to
m
a
ti
c
Bre
a
st
T
u
m
o
r
Clas
sif
ic
a
ti
o
n
Us
i
n
g
a
L
e
v
e
l
S
e
t
M
e
th
o
d
a
n
d
F
e
a
tu
re
Ex
trac
ti
o
n
in
M
a
m
m
o
g
ra
p
h
y
,
”
in
2
0
1
7
2
4
t
h
Na
t
io
n
a
l
a
n
d
2
n
d
In
ter
n
a
ti
o
n
a
l
Ira
n
i
a
n
Co
n
fer
e
n
c
e
o
n
Bi
o
me
d
ica
l
En
g
in
e
e
rin
g
(
ICBM
E)
,
p
p
.
1
-
6
,
2
0
1
7
.
[7
]
F.
S
a
k
i
,
A
.
T
a
h
m
a
sb
i,
H.
S
o
lt
a
n
ian
-
Zad
e
h
,
a
n
d
S
.
B
.
S
h
o
k
o
u
h
i,
“
F
a
st
o
p
p
o
site
w
e
ig
h
t
lea
rn
in
g
ru
les
w
it
h
a
p
p
li
c
a
ti
o
n
i
n
b
re
a
st ca
n
c
e
r
d
iag
n
o
sis,
”
Co
mp
u
ter
s in
b
i
o
lo
g
y
a
n
d
me
d
icin
e
,
v
o
l.
4
3
,
n
o
.
1
,
p
p
.
3
2
-
4
1
,
2
0
1
3
.
[8
]
X
.
L
lad
ó
,
A
.
Oliv
e
r,
J.
F
re
ix
e
n
e
t,
R.
M
a
rtí
,
a
n
d
J.
M
a
rtí
,
“
A
te
x
tu
ra
l
a
p
p
ro
a
c
h
f
o
r
m
a
ss
f
a
ls
e
p
o
siti
v
e
re
d
u
c
t
io
n
in
m
a
m
m
o
g
r
a
p
h
y
,
”
Co
mp
u
ter
ize
d
M
e
d
ica
l
Ima
g
in
g
a
n
d
Gr
a
p
h
ics
,
v
o
l.
3
3
,
n
o
.
6
,
p
p
.
4
1
5
-
4
2
2
,
2
0
0
9
.
[9
]
S.
Ba
g
c
h
i
,
K.
G
.
T
a
y
,
A
.
Hu
o
n
g
,
a
n
d
S
.
K.
De
b
n
a
t
h
,
“
Im
a
g
e
p
ro
c
e
ss
in
g
a
n
d
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
iq
u
e
s
u
se
d
i
n
c
o
m
p
u
ter
-
a
id
e
d
d
e
tec
ti
o
n
sy
ste
m
f
o
r
m
a
m
m
o
g
ra
m
s
c
re
e
n
in
g
-
a
re
v
ie
w
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
ter
E
n
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
1
0
,
n
o
.
3
,
p
p
.
2
3
3
6
-
2
3
4
8
,
2
0
2
0
.
[1
0
]
A
.
P
ra
d
e
e
p
a
n
d
X.
F
.
Jo
se
p
h
,
“
Bin
a
ry
o
p
e
ra
ti
o
n
b
a
se
d
h
a
rd
e
x
u
d
a
te
d
e
tec
ti
o
n
a
n
d
f
u
z
z
y
b
a
se
d
c
las
si
f
ica
ti
o
n
i
n
d
iab
e
ti
c
re
ti
n
a
l
f
u
n
d
u
s
im
a
g
e
s
f
o
r
re
a
l
ti
m
e
d
iag
n
o
sis
a
p
p
li
c
a
ti
o
n
s,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
ter
E
n
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
1
0
,
n
o
.
3
,
p
p
.
2
3
0
5
-
2
3
1
2
,
2
0
2
0
.
[1
1
]
C.
-
H.
W
e
i,
Y.
L
i,
a
n
d
C.
-
T
.
L
i
,
“
Eff
e
c
ti
v
e
e
x
trac
ti
o
n
o
f
Ga
b
o
r
f
e
a
tu
re
s
f
o
r
a
d
a
p
ti
v
e
m
a
m
m
o
g
ra
m
r
e
tri
e
v
a
l,
”
in
2
0
0
7
IE
EE
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
M
u
lt
ime
d
ia
a
n
d
Exp
o
,
p
p
.
1
5
0
3
-
1
5
0
6
,
2
0
0
7
.
[1
2
]
S.
L
a
h
m
iri
a
n
d
M
.
Bo
u
k
a
d
o
u
m
,
“
H
y
b
rid
d
isc
re
te
wa
v
e
l
e
t
tran
sf
o
r
m
a
n
d
Ga
b
o
r
f
il
ter
b
a
n
k
s
p
ro
c
e
ss
in
g
f
o
r
m
a
m
m
o
g
r
a
m
fe
a
tu
re
s
e
x
trac
ti
o
n
,
”
in
2
0
1
1
IEE
E
9
th
I
n
ter
n
a
ti
o
n
a
l
Ne
w
Circ
u
it
s
a
n
d
sy
ste
ms
c
o
n
fer
e
n
c
e
,
p
p
.
5
3
-
56
,
2
0
1
1
.
[1
3
]
M.
Hu
ss
a
in
,
S
.
Kh
a
n
,
G
.
M
u
h
a
m
m
a
d
,
M
.
Be
rb
a
r,
a
n
d
G
.
Be
b
is
,
“
M
a
ss
d
e
te
c
ti
o
n
in
d
ig
it
a
l
m
a
m
m
o
g
ra
m
s
u
sin
g
G
a
b
o
r
f
il
ter b
a
n
k
,
”
IET
Co
n
fer
e
n
c
e
o
n
Ima
g
e
Pro
c
e
ss
in
g
(
IPR
2
0
1
2
),
2
0
1
2
.
[1
4
]
S.
Kh
a
n
,
M
.
H
u
ss
a
in
,
H.
A
b
o
a
lsa
m
h
,
a
n
d
G
.
Be
b
is,
“
A
c
o
m
p
a
riso
n
o
f
d
iff
e
re
n
t
Ga
b
o
r
f
e
a
tu
re
e
x
tr
a
c
t
io
n
a
p
p
r
o
a
c
h
e
s
f
o
r
m
a
ss
c
la
ss
i
f
ica
ti
o
n
in
m
a
m
m
o
g
ra
p
h
y
,
”
M
u
lt
ime
d
ia
T
o
o
ls a
n
d
A
p
p
li
c
a
ti
o
n
s,
v
o
l
.
7
6
,
n
o
.
1
,
p
p
.
3
3
-
5
7
,
2
0
1
7
.
[1
5
]
Y.
Zh
e
n
g
,
“
Bre
a
st
c
a
n
c
e
r
d
e
tec
ti
o
n
w
it
h
g
a
b
o
r
f
e
a
tu
re
s
f
ro
m
d
ig
it
a
l
m
a
m
m
o
g
ra
m
s,
”
Al
g
o
rith
ms
,
v
o
l.
3
,
n
o
.
1
,
p
p
.
4
4
-
6
2
,
2
0
1
0
.
[1
6
]
N.
P
o
n
ra
j
a
n
d
M
.
M
e
rc
y
,
“
T
e
x
tu
re
a
n
a
l
y
sis
o
f
m
a
m
m
o
g
ra
m
f
o
r
th
e
d
e
tec
ti
o
n
o
f
b
re
a
st
c
a
n
c
e
r
u
sin
g
L
BP
a
n
d
L
G
P
:
A
Co
m
p
a
riso
n
,
”
in
2
0
1
6
Ei
g
h
t
h
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
A
d
v
a
n
c
e
d
Co
mp
u
ti
n
g
(
ICo
AC)
,
p
p
.
1
8
2
-
1
8
5
,
2
0
1
7
.
[1
7
]
S.
Kh
a
n
,
M
.
Hu
ss
a
in
,
H.
A
b
o
a
lsa
m
h
,
H.
M
a
th
k
o
u
r,
G
.
Be
b
is,
a
n
d
M
.
Zak
a
riah
,
“
Op
ti
m
ize
d
G
a
b
o
r
fe
a
tu
re
s f
o
r
m
a
ss
c
las
si
f
ica
ti
o
n
in
m
a
m
m
o
g
ra
p
h
y
,
”
Ap
p
li
e
d
S
o
ft
Co
mp
u
ti
n
g
,
v
o
l.
4
4
,
p
p
.
2
6
7
-
2
8
0
,
2
0
1
6
.
[1
8
]
Z.
L
e
i
,
S
.
Z.
L
i,
R.
C
h
u
,
a
n
d
X
.
Zh
u
,
“
F
a
c
e
re
c
o
g
n
it
io
n
w
it
h
lo
c
a
l
g
a
b
o
r
tex
to
n
s,
”
i
n
I
n
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
Bi
o
me
trics
,
p
p
.
4
9
-
57
,
2
0
0
7
.
[1
9
]
M
.
Hu
ss
a
in
,
S
.
Kh
a
n
,
G
.
M
u
h
a
m
m
a
d
,
I.
A
h
m
a
d
,
a
n
d
G
.
B
e
b
is,
“
Eff
e
c
ti
v
e
e
x
trac
ti
o
n
o
f
G
a
b
o
r
fe
a
tu
re
s
f
o
r
fa
lse
p
o
siti
v
e
re
d
u
c
ti
o
n
a
n
d
m
a
ss
c
la
ss
i
f
ica
ti
o
n
in
m
a
m
m
o
g
r
a
p
h
y
,
”
Ap
p
l.
M
a
th
,
v
o
l.
8
,
n
o
.
1
L
,
p
p
.
3
9
7
-
4
1
2
,
2
0
1
4
.
[2
0
]
A
.
K
a
m
ra
,
V
.
Ja
in
,
a
n
d
S
.
S
in
g
h
,
“
Ex
trac
ti
o
n
o
f
o
rien
tatio
n
f
ield
u
sin
g
G
a
b
o
r
F
il
ter
a
n
d
G
r
a
d
ien
t
b
a
se
d
a
p
p
ro
a
c
h
f
o
r
th
e
d
e
tec
ti
o
n
o
f
su
b
tl
e
sig
n
s
in
m
a
m
m
o
g
ra
m
s,
”
J
o
u
rn
a
l
o
f
M
e
d
ica
l
Ima
g
i
n
g
a
n
d
He
a
lt
h
In
fo
r
ma
ti
c
s,
v
o
l.
4
,
n
o
.
3
,
p
p
.
3
7
4
-
3
8
1
,
2
0
1
4
.
[2
1
]
M
.
Y.
Ka
m
il
a
n
d
A
.
M
.
S
a
li
h
,
“
M
a
m
m
o
g
r
a
p
h
y
I
m
a
g
e
s
S
e
g
m
e
n
tatio
n
v
ia
F
u
z
z
y
C
-
m
e
a
n
a
n
d
K
-
m
e
a
n
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
I
n
telli
g
e
n
t
E
n
g
i
n
e
e
rin
g
a
n
d
S
y
ste
ms
,
v
o
l.
1
2
,
n
o
.
1
,
p
p
.
2
2
-
2
9
,
2
0
1
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
5
2
3
5
-
5242
5242
[2
2
]
K.
C.
T
a
ti
k
o
n
d
a
,
C.
M
.
B
h
u
m
a
,
a
n
d
S
.
K.
S
a
m
a
y
a
m
a
n
tu
la,
“
T
h
e
A
n
a
l
y
si
s
o
f
Dig
it
a
l
M
a
m
m
o
g
r
a
m
s
Us
in
g
HOG
a
n
d
G
L
CM
F
e
a
tu
re
s,
”
in
2
0
1
8
9
th
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Co
mp
u
ti
n
g
,
Co
mm
u
n
ica
t
io
n
a
n
d
Ne
two
rk
in
g
T
e
c
h
n
o
l
o
g
ies
(
ICCCNT
)
,
p
p
.
1
-
7
,
2
0
1
8
.
[2
3
]
F
.
S
.
S
.
d
e
Oliv
e
ira,
A
.
O.
d
e
Ca
r
v
a
lh
o
F
il
h
o
,
A
.
C.
S
il
v
a
,
A
.
C.
d
e
P
a
iv
a
,
a
n
d
M
.
G
a
tt
a
ss
,
“
Clas
si
f
ic
a
ti
o
n
o
f
b
re
a
st
re
g
io
n
s
a
s
m
a
s
s
a
n
d
n
o
n
-
m
a
ss
b
a
se
d
o
n
d
ig
it
a
l
m
a
m
m
o
g
ra
m
s
u
sin
g
tax
o
n
o
m
ic
in
d
e
x
e
s
a
n
d
S
V
M
,
”
Co
mp
u
ter
s
in
b
io
l
o
g
y
a
n
d
me
d
ici
n
e
,
v
o
l.
5
7
,
p
p
.
42
-
5
3
,
2
0
1
5
.
[2
4
]
A
.
A
l
Qo
u
d
a
n
d
M
.
A
.
Ja
ff
a
r,
“
H
y
b
rid
g
a
b
o
r
b
a
se
d
lo
c
a
l
b
in
a
ry
p
a
tt
e
rn
s
tex
tu
re
f
e
a
tu
re
s
f
o
r
c
las
si
f
i
c
a
ti
o
n
o
f
b
re
a
st
m
a
m
m
o
g
r
a
m
s,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
S
c
ien
c
e
a
n
d
Ne
t
wo
rk
S
e
c
u
rity,
v
o
l.
1
6
,
n
o
.
4
,
p
p
.
1
6
,
2
0
1
6
.
[2
5
]
F.
S
h
iraz
i
a
n
d
E.
R
a
sh
e
d
i
,
“
De
tec
ti
o
n
o
f
c
a
n
c
e
r
tu
m
o
rs
in
m
a
m
m
o
g
ra
p
h
y
i
m
a
g
e
s
u
sin
g
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
a
n
d
m
i
x
e
d
g
r
a
v
it
a
ti
o
n
a
l
se
a
r
c
h
a
lg
o
rit
h
m
,
”
in
2
0
1
6
1
st
c
o
n
fer
e
n
c
e
o
n
swa
rm
in
telli
g
e
n
c
e
a
n
d
e
v
o
lu
ti
o
n
a
ry
c
o
mp
u
ta
ti
o
n
(
CS
IEC)
,
p
p
.
9
8
-
1
0
1
,
2
0
1
6
.
B
I
O
G
RAP
H
Y
O
F
AUTHO
R
M
o
h
a
m
m
e
d
Y.
K
a
m
il
o
b
tain
e
d
h
is
M
.
S
c
.
i
n
Op
ti
c
s
f
ro
m
M
u
sta
n
siriy
a
Un
iv
e
rsit
y
,
Co
ll
e
g
e
o
f
S
c
ien
c
e
,
P
h
y
sic
s
d
e
p
a
rt
m
e
n
t,
Ira
q
,
in
2
0
0
5
.
He
re
c
e
iv
e
d
h
is
P
h
.
D.
in
d
ig
it
a
l
im
a
g
e
p
ro
c
e
ss
in
g
f
ro
m
M
u
sta
n
siriy
a
Un
iv
e
rsit
y
in
2
0
1
1
.
He
is
in
tere
ste
d
i
n
m
e
d
ica
l
im
a
g
e
p
ro
c
e
ss
in
g
,
c
o
m
p
u
ter
v
isio
n
,
a
n
d
A
rti
f
icia
l
In
telli
g
e
n
c
e
.
He
is a m
e
m
b
e
r
o
f
th
e
IEE
E
Ira
q
se
c
ti
o
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.