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.
8
,
No
.
1
,
Feb
r
u
ar
y
201
8
,
p
p
.
6
0
~6
9
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v8
i
1
.
p
p
6
0
-
69
60
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
Feature
Selec
tion
M
a
m
m
o
g
ra
m
b
a
s
ed on
B
reas
t
C
a
n
cer
M
ining
Sh
o
f
w
a
t
ul ‘
Uy
un
1
,
L
ina
Cho
rida
h
2
1
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
c
s,
F
a
c
u
lt
y
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
S
u
n
a
n
Ka
li
jag
a
S
tate
Isla
m
ic
Un
iv
e
rsit
y
,
Yo
g
y
a
k
a
rta,
In
d
o
n
e
sia
2
De
p
a
rtme
n
t
o
f
Ra
d
io
lo
g
y
,
F
a
c
u
lt
y
o
f
M
e
d
icin
e
,
G
a
d
jah
M
a
d
a
Un
i
v
e
rsit
y
,
Yo
g
y
a
k
a
rt
a
,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Mar
9
,
2
0
1
7
R
ev
i
s
ed
J
u
l
1
2
,
2
0
1
7
A
cc
ep
ted
J
u
l 3
0
,
2
0
1
7
T
h
e
v
e
r
y
d
e
n
se
b
re
a
st
o
f
m
a
m
m
o
g
ra
m
i
m
a
g
e
m
a
k
e
s
th
e
Ra
d
io
lo
g
ists
o
f
t
e
n
h
a
v
e
d
iff
icu
lt
ies
in
in
terp
re
ti
n
g
th
e
m
a
m
m
o
g
ra
p
h
y
o
b
jec
ti
v
e
l
y
a
n
d
a
c
c
u
ra
tel
y
.
On
e
o
f
th
e
k
e
y
su
c
c
e
ss
fa
c
to
rs
o
f
c
o
m
p
u
ter
-
a
id
e
d
d
iag
n
o
sis
(CA
D
x
)
s
y
ste
m
is
th
e
u
se
o
f
t
h
e
rig
h
t
fe
a
tu
re
s.
T
h
e
re
f
o
re
,
th
is
re
se
a
rc
h
e
m
p
h
a
siz
e
s
o
n
th
e
f
e
a
tu
re
se
lec
ti
o
n
p
ro
c
e
ss
b
y
p
e
rf
o
r
m
in
g
th
e
d
a
ta
m
in
in
g
o
n
t
h
e
re
su
lt
s
o
f
m
a
m
m
o
g
r
a
m
im
a
g
e
f
e
a
tu
re
e
x
trac
ti
o
n
.
T
h
e
re
a
re
tw
o
a
lg
o
rit
h
m
s
u
se
d
to
p
e
rf
o
rm
th
e
m
in
in
g
,
th
e
d
e
c
is
io
n
tree
a
n
d
t
h
e
ru
le
in
d
u
c
ti
o
n
.
F
u
rth
e
rm
o
re
,
th
e
se
lec
ted
f
e
a
tu
re
s
p
ro
d
u
c
e
d
b
y
th
e
a
lg
o
rit
h
m
s
a
r
e
tes
ted
u
sin
g
c
las
si
f
ica
ti
o
n
a
lg
o
rit
h
m
s:
k
-
n
e
a
re
st
n
e
ig
h
b
o
rs,
d
e
c
isio
n
tree
,
a
n
d
n
a
iv
e
b
a
y
e
sia
n
w
it
h
th
e
sc
h
e
m
e
o
f
1
0
-
f
o
ld
c
ro
ss
v
a
li
d
a
ti
o
n
u
sin
g
stra
ti
f
ied
s
a
m
p
li
n
g
w
a
y
.
T
h
e
re
a
re
f
i
v
e
d
e
sc
rip
to
rs
t
h
a
t
a
re
th
e
b
e
st
f
e
a
tu
re
s
a
n
d
h
a
v
e
c
o
n
tri
b
u
ted
i
n
d
e
term
in
in
g
th
e
c
las
sif
i
c
a
ti
o
n
o
f
b
e
n
ig
n
a
n
d
m
a
li
g
n
a
n
t
les
io
n
s
a
s
f
o
ll
o
w
s:
slice
,
in
teg
ra
ted
d
e
n
sity
,
a
re
a
f
ra
c
ti
o
n
,
m
o
d
e
l
g
ra
y
v
a
lu
e
,
a
n
d
c
e
n
ter
o
f
m
a
s
s.
T
h
e
b
e
st
c
l
a
ss
i
f
i
c
a
ti
o
n
re
su
lt
s
b
a
se
d
o
n
th
e
f
iv
e
fe
a
tu
re
s
a
re
g
e
n
e
ra
ted
b
y
th
e
d
e
c
isio
n
tree
a
lg
o
rit
h
m
w
it
h
a
c
c
u
ra
c
y
,
se
n
siti
v
it
y
,
sp
e
c
if
icit
y
,
F
P
R,
a
n
d
T
P
R
of
9
3
.
1
8
%
;
8
7
.
5
%
;
3
.
8
9
%
;
6
.
3
3
%
a
n
d
9
2
.
1
1
%
re
sp
e
c
ti
v
e
l
y
.
K
ey
w
o
r
d
:
Dec
is
io
n
tr
ee
Featu
r
e
s
elec
t
io
n
Ma
m
m
o
g
r
a
m
Min
i
n
g
R
u
le
i
n
d
u
c
tio
n
Co
p
y
rig
h
t
©
2
0
1
8
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
:
Sh
o
f
w
atu
l „
U
y
u
n
,
Dep
ar
t
m
en
t o
f
I
n
f
o
r
m
atic
s
,
Facu
lt
y
o
f
Sc
ien
ce
a
n
d
T
ec
h
n
o
lo
g
y
,
Su
n
an
Ka
lij
ag
a
State
I
s
la
m
ic
Un
i
v
er
s
it
y
,
J
l.
Ma
r
s
d
a
A
d
is
u
cip
to
No
.
1
Yo
g
y
a
k
ar
ta,
5
5
2
8
1
,
I
n
d
o
n
esia
.
E
m
ail: S
h
o
f
w
atu
l.u
y
u
n
@
u
in
-
s
u
k
a.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
B
r
ea
s
t
ca
n
ce
r
an
d
ce
r
v
ical
ca
n
ce
r
ar
e
t
y
p
es
o
f
ca
n
ce
r
t
h
at
ca
u
s
e
t
h
e
h
ig
h
e
s
t
m
o
r
tali
t
y
i
n
w
o
m
en
i
n
I
n
d
o
n
esia.
B
ased
o
n
d
ata
[
1
]
t
h
er
e
ar
e
3
3
0
,
0
0
0
ca
n
ce
r
p
atie
n
ts
i
n
I
n
d
o
n
es
ia
an
d
th
e
h
i
g
h
e
s
t
ca
n
ce
r
p
r
ev
alen
c
e
is
f
o
u
n
d
in
Yo
g
y
a
k
ar
ta
Sp
ec
ial
R
eg
io
n
o
f
4
.
1
%.
B
r
ea
s
t
ca
n
ce
r
h
as
es
tab
lis
h
ed
r
is
k
s
(
e.
g
.
f
a
m
il
y
h
i
s
to
r
y
,
o
b
esit
y
,
h
a
v
i
n
g
d
e
n
s
e
b
r
ea
s
t
)
an
d
e
m
er
g
i
n
g
r
is
k
s
(
e.
g
.
l
o
w
o
f
v
ita
m
i
n
D
le
v
els,
u
n
h
ea
lt
h
y
l
if
e
s
t
y
le)
;
th
er
ef
o
r
e,
th
e
ea
r
l
y
d
etec
tio
n
ca
n
b
e
co
n
d
u
cted
to
r
ed
u
ce
th
e
m
o
r
talit
y
o
f
b
r
ea
s
t
ca
n
ce
r
.
I
n
f
ac
t,
i
f
ca
n
ce
r
ar
e
f
o
u
n
d
i
n
t
h
e
ea
r
l
y
s
ta
g
e,
t
h
e
r
e
w
ill
b
e
a
g
r
ea
t
c
u
r
e
r
ate.
Ho
w
e
v
er
,
m
o
s
tl
y
t
h
e
ca
s
es
o
f
b
r
ea
s
t
ca
n
ce
r
i
n
I
n
d
o
n
esia
ar
e
f
o
u
n
d
in
t
h
e
ad
v
an
ce
s
tag
e
b
ec
au
s
e
o
f
lo
w
a
w
ar
e
n
ess
.
Ma
m
m
o
g
r
ap
h
y
is
o
n
e
o
f
th
e
i
m
ag
i
n
g
tech
n
o
lo
g
ies
t
h
at
ca
n
b
e
u
s
ed
b
o
th
f
o
r
s
cr
ee
n
in
g
an
d
f
o
r
th
e
d
iag
n
o
s
is
o
f
b
r
ea
s
t
ca
n
ce
r
.
B
ased
o
n
th
e
B
I
-
R
A
DS
lex
ico
n
s
f
o
r
Ma
m
m
o
g
r
ap
h
y
2
0
1
3
,
a
h
y
p
er
d
en
s
it
y
m
a
s
s
w
i
th
an
ir
r
eg
u
lar
s
h
ap
e
a
n
d
s
p
ik
u
lated
m
ar
g
i
n
is
as
s
o
ciate
d
w
ith
m
a
lig
n
a
n
c
y
.
Ot
h
er
s
u
s
p
icio
u
s
m
o
r
p
h
o
lo
g
y
i
s
a
m
o
r
p
h
o
u
s
,
co
ar
s
e
h
eter
o
g
e
n
o
u
s
,
f
i
n
e
p
leo
m
o
r
p
h
ic
a
n
d
f
i
n
e
li
n
ea
r
o
r
f
in
e
-
li
n
ea
r
b
r
an
ch
in
g
ca
lci
f
ic
atio
n
[
2
]
.
C
u
r
r
en
tl
y
a
co
m
p
u
ter
-
aid
ed
s
y
s
te
m
u
s
i
n
g
t
h
e
m
a
m
m
o
g
r
a
m
i
m
a
g
e
w
it
h
s
ev
er
al
d
i
f
f
er
en
t
p
u
r
p
o
s
es
h
as
b
ee
n
d
e
v
elo
p
ed
,
am
o
n
g
o
th
er
s
,
to
d
eter
m
i
n
e
th
e
lev
el
o
f
r
is
k
o
f
b
r
ea
s
t
ca
n
ce
r
[
3
]
,
to
d
etec
t
th
e
lo
ca
tio
n
co
n
s
id
er
ed
ab
n
o
r
m
al
i
n
t
h
e
i
m
ag
e
m
a
m
m
o
g
r
a
m
t
h
at
i
s
c
o
m
m
o
n
l
y
ca
lled
t
h
e
C
ADE
s
y
s
te
m
[
4
]
,
an
d
to
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
F
ea
tu
r
e
S
elec
tio
n
Ma
mmo
g
r
a
m
b
a
s
ed
o
n
B
r
ea
s
t Ca
n
ce
r
Mi
n
in
g
(
S
h
o
fw
a
tu
l ‘
Uyu
n
)
61
d
iag
n
o
s
e
t
h
e
t
y
p
e
o
f
b
r
ea
s
t
ca
n
ce
r
co
n
s
id
er
ed
as
R
o
I
o
n
t
h
e
m
a
m
m
o
g
r
a
m
i
m
a
g
e
t
h
at
i
s
c
o
m
m
o
n
l
y
ca
lled
th
e
C
A
D
x
s
y
s
te
m
.
T
h
e
u
s
e
C
A
D
x
is
as
t
h
e
s
ec
o
n
d
o
p
in
io
n
in
d
iag
n
o
s
i
n
g
th
e
b
r
ea
s
t
ca
n
ce
r
b
ased
o
n
th
e
r
ea
d
in
g
o
f
th
e
m
a
m
m
o
g
r
a
m
i
m
a
g
e.
I
n
g
e
n
er
al,
th
er
e
ar
e
s
ev
er
al
s
tag
es
to
d
ev
elo
p
a
co
m
p
u
ter
-
aid
ed
d
iag
n
o
s
is
s
y
s
te
m
(
C
A
D
x
)
,
a
m
o
n
g
o
th
er
s
:
i
m
ag
e
ac
q
u
is
itio
n
,
p
r
etr
ea
t
m
e
n
t,
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
f
ea
tu
r
e
s
elec
t
io
n
,
clas
s
i
f
icat
io
n
an
d
test
i
n
g
.
A
t
ea
ch
s
ta
g
e,
it
n
ee
d
s
to
d
o
th
e
r
ig
h
t
c
h
o
ice
o
f
al
g
o
r
ith
m
i
n
o
r
d
er
to
b
e
ab
le
to
p
r
o
v
id
e
t
h
e
d
iag
n
o
s
is
r
e
s
u
l
t
ac
cu
r
atel
y
.
I
n
p
r
in
c
ip
le,
th
e
w
o
r
k
p
atter
n
o
f
C
A
D
x
s
y
s
te
m
f
o
llo
w
s
th
e
w
o
r
k
p
atter
n
o
f
p
atter
n
r
ec
o
g
n
itio
n
s
y
s
te
m
.
On
e
i
m
p
o
r
ta
n
t
f
ac
to
r
t
h
at
d
eter
m
in
e
s
t
h
e
s
u
cc
es
s
o
r
f
ail
u
r
e
i
n
p
a
tter
n
r
ec
o
g
n
it
io
n
s
y
s
te
m
i
s
t
h
e
u
s
e
o
f
th
e
r
ig
h
t
f
ea
t
u
r
es.
A
cc
o
r
d
in
g
to
[
5
]
th
e
r
ig
h
t
f
ea
t
u
r
e
s
elec
ti
o
n
is
a
cr
itical
s
tag
e
b
ec
au
s
e
th
e
r
ig
h
t
f
ea
tu
r
e
s
m
ak
e
s
t
h
e
p
atter
n
r
ec
o
g
n
itio
n
s
y
s
te
m
ca
p
ab
le
to
d
is
ti
n
g
u
is
h
b
et
w
ee
n
o
n
e
o
b
j
ec
t
f
r
o
m
a
n
o
th
er
o
n
e
i
n
ac
co
r
d
an
ce
w
it
h
t
h
e
c
h
ar
ac
ter
is
tics
o
f
t
h
e
o
b
j
ec
t
,
o
n
e
b
ased
o
n
i
m
p
r
o
v
ed
d
o
cu
m
en
t
f
r
e
q
u
en
c
y
f
o
r
th
e
te
x
t
class
i
f
icatio
n
[
6
]
.
T
h
er
ef
o
r
e,
it
is
n
ec
e
s
s
ar
y
to
d
o
t
h
e
f
ea
t
u
r
e
s
elec
tio
n
o
n
a
m
a
m
m
o
g
r
a
m
t
h
at
is
ab
le
t
o
d
is
tin
g
u
is
h
b
et
w
ee
n
b
en
ig
n
f
r
o
m
m
ali
g
n
an
t le
s
io
n
s
o
n
t
h
e
m
a
m
m
o
g
r
a
m
.
So
m
e
r
esear
ch
er
s
d
ev
elo
p
in
g
a
co
m
p
u
ter
-
aid
ed
s
y
s
te
m
ai
m
at
as
s
es
s
i
n
g
t
h
e
r
is
k
f
ac
to
r
s
,
d
etec
tio
n
an
d
d
iag
n
o
s
is
o
f
b
r
ea
s
t
ca
n
c
er
u
s
in
g
t
h
e
f
ea
t
u
r
es
f
o
u
n
d
o
n
th
e
m
a
m
m
o
g
r
a
m
,
i
n
cl
u
d
in
g
:
co
lo
r
f
ea
tu
r
e
[
7
]
,
tex
t
u
r
e
[
8
]
,
[
9
]
,
s
h
ap
e
[
1
0
]
a
n
d
a
co
m
b
i
n
atio
n
a
m
o
n
g
t
h
e
th
r
ee
[
1
1
]
.
T
h
e
u
s
e
o
f
th
e
r
i
g
h
t
f
ea
t
u
r
es
g
r
ea
tl
y
af
f
ec
ts
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
atter
n
r
ec
o
g
n
itio
n
s
y
s
te
m
.
I
n
co
m
p
u
tatio
n
,
it
is
ex
p
ec
ted
to
u
s
e
th
e
f
ea
tu
r
es
a
s
m
i
n
i
m
u
m
as
p
o
s
s
ib
le
a
n
d
to
b
e
ab
le
to
d
is
tin
g
u
i
s
h
b
et
w
ee
n
o
n
e
class
f
r
o
m
a
n
o
th
er
.
T
h
er
ef
o
r
e,
it
n
ee
d
s
an
alg
o
r
ith
m
t
h
at
ca
n
b
e
u
s
ed
to
ch
o
o
s
e
th
e
b
est
f
ea
t
u
r
es
a
m
o
n
g
s
o
m
an
y
f
ea
tu
r
es.
So
m
e
p
r
ev
io
u
s
r
esear
c
h
e
s
h
av
e
ap
p
lied
s
ev
er
al
al
g
o
r
ith
m
s
a
i
m
ed
at
th
e
f
ea
tu
r
e
s
elec
ti
o
n
,
a
m
o
n
g
o
t
h
er
s
:
th
e
b
r
a
n
ch
an
d
b
o
u
n
d
al
g
o
r
ith
m
[1
2
]
,
h
ill
c
li
m
b
i
n
g
a
lg
o
r
it
h
m
[
1
3
]
an
d
m
u
lt
i
s
tr
u
ctu
r
e
co
-
o
cc
u
r
r
en
ce
d
escr
ip
to
r
[
1
4
]
.
Ho
w
e
v
er
,
s
o
m
e
e
x
i
s
ti
n
g
r
ef
er
en
ce
s
ar
e
n
o
t
s
p
ec
if
ical
l
y
u
s
ed
y
et
to
s
elec
t
th
e
f
ea
t
u
r
es
in
th
e
m
a
m
m
o
g
r
a
m
i
m
ag
e
f
o
r
th
e
d
ev
elo
p
m
e
n
t
o
f
C
A
D
x
o
f
t
h
e
b
r
ea
s
t c
an
ce
r
s
y
s
te
m
.
T
h
is
r
esear
ch
p
r
o
p
o
s
es
t
h
e
u
s
e
o
f
s
e
v
er
al
m
eth
o
d
s
o
f
d
at
a
m
i
n
i
n
g
t
h
at
ar
e
u
s
ed
a
s
t
h
e
f
ea
t
u
r
e
s
elec
tio
n
alg
o
r
it
h
m
o
f
th
e
m
a
m
m
o
g
r
a
m
i
m
a
g
e.
T
h
e
alg
o
r
ith
m
s
u
s
ed
ar
e
th
e
d
ec
is
io
n
tr
ee
an
d
t
h
e
r
u
le
in
d
u
ctio
n
,
af
ter
w
ar
d
s
th
e
cla
s
s
if
ica
tio
n
is
p
er
f
o
r
m
ed
o
n
t
h
e
f
ea
tu
r
es
s
e
lecte
d
f
r
o
m
t
h
e
t
wo
alg
o
r
ith
m
s
u
s
in
g
s
ev
er
al
clas
s
if
icatio
n
al
g
o
r
ith
m
s
to
m
ea
s
u
r
e
th
e
p
er
f
o
r
m
a
n
ce
.
B
esid
es,
th
is
r
esear
ch
u
s
e
s
th
e
p
r
i
m
ar
y
d
ata,
w
h
ic
h
t
y
p
es
o
f
les
io
n
s
(
b
en
i
g
n
an
d
m
ali
g
n
an
t)
h
av
e
b
ee
n
cl
ass
i
f
ied
b
y
th
e
R
ad
io
lo
g
i
s
ts
n
o
t
o
n
l
y
b
ased
o
n
th
e
v
is
u
al
a
s
s
es
s
m
e
n
t
b
u
t
also
v
er
if
ied
b
ased
o
n
th
e
r
es
u
lts
o
f
lab
o
r
ato
r
y
test
s
an
d
as
s
es
s
m
e
n
t
u
s
i
n
g
o
th
er
i
m
a
g
in
g
tec
h
n
o
lo
g
y
t
h
at
i
s
u
ltr
aso
u
n
d
tec
h
n
o
lo
g
y
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
is
r
esear
ch
u
s
es t
h
e
s
i
x
-
s
ta
g
e
p
r
o
ce
s
s
f
o
r
d
ev
elo
p
in
g
a
co
m
p
u
ter
-
b
ased
s
y
s
te
m
f
o
r
th
e
d
iag
n
o
s
is
o
f
b
r
ea
s
t c
an
ce
r
,
in
cl
u
d
in
g
:
2
.
1
.
M
a
m
m
o
g
ra
ph
y
I
m
a
g
e
Acqu
is
it
io
n
T
h
is
r
esear
ch
u
s
es
th
e
p
r
i
m
ar
y
d
ata
i
n
t
h
e
f
o
r
m
o
f
m
a
m
m
o
g
r
a
m
i
m
a
g
e
p
r
o
d
u
ce
d
b
y
d
ig
i
tal
m
a
m
m
o
g
r
ap
h
y
i
m
ag
in
g
tec
h
n
o
lo
g
y
t
h
at
i
s
co
n
d
u
cted
in
Ko
tab
ar
u
On
co
lo
g
y
C
li
n
ic
Yo
g
y
a
k
ar
ta.
T
h
e
n
u
m
b
e
r
o
f
m
a
m
m
o
g
r
a
m
i
m
a
g
e
s
u
cc
es
s
f
u
ll
y
o
b
tain
ed
f
r
o
m
t
h
e
p
r
o
b
an
d
u
s
is
1
1
7
lesi
o
n
s
o
f
m
a
m
m
o
g
r
a
m
s
f
o
r
m
t
w
o
v
ie
w
s
,
C
C
(
C
r
an
io
C
a
u
d
al)
an
d
ML
O
(
m
ed
io
later
al
o
b
liq
u
e)
.
Fu
r
th
er
m
o
r
e,
th
e
R
ad
io
lo
g
i
s
t
s
in
t
h
is
ca
s
e
as t
h
e
r
esear
ch
er
s
,
co
n
d
u
ct
a
v
is
u
a
l
an
al
y
s
i
s
o
f
t
h
e
m
a
m
m
o
g
r
a
m
.
I
n
as
s
es
s
in
g
t
h
e
m
a
m
m
o
g
r
a
m
i
m
ag
e,
t
h
e
R
ad
io
lo
g
is
t
s
d
o
n
o
t
o
n
l
y
i
n
ter
p
r
et
th
e
m
a
m
m
o
g
r
a
m
i
m
ag
e,
b
u
t
also
m
atc
h
t
h
e
i
n
ter
p
r
etat
io
n
r
es
u
lt
w
i
th
th
e
in
ter
p
r
etatio
n
o
f
th
e
i
m
a
g
e
th
at
is
th
e
i
m
a
g
i
n
g
r
esu
lt
s
w
it
h
o
th
er
tech
n
o
lo
g
ies,
in
t
h
i
s
ca
s
e
u
s
i
n
g
u
ltra
s
o
u
n
d
tech
n
o
lo
g
y
a
n
d
t
h
e
r
es
u
lts
o
f
p
ath
o
lo
g
y
test
s
.
I
n
t
h
e
a
n
al
y
s
is
o
f
t
h
e
m
a
m
m
o
g
r
a
m
i
m
a
g
e,
th
e
R
ad
io
lo
g
is
t
s
n
ee
d
to
cr
o
s
s
c
h
ec
k
to
s
o
m
e
te
s
t
r
es
u
lt
s
u
s
i
n
g
o
t
h
er
d
ata
i
n
o
r
d
er
to
p
r
o
v
id
e
th
e
v
alid
a
n
n
o
tatio
n
s
o
n
p
ar
ts
t
h
at
ar
e
co
n
s
id
er
ed
as
t
h
e
d
i
s
o
r
d
er
s
/
ca
n
ce
r
,
h
er
ein
a
f
ter
r
e
f
er
r
ed
to
as
R
o
I
(
R
e
g
io
n
o
f
I
n
ter
est)
.
B
esid
es
p
r
o
v
id
in
g
R
o
I
an
n
o
tat
io
n
o
n
th
e
m
a
m
m
o
g
r
a
m
i
m
a
g
e,
th
e
R
ad
io
lo
g
i
s
t
s
clas
s
if
y
i
t
in
to
t
w
o
ca
teg
o
r
i
es
as
b
en
ig
n
le
s
io
n
s
an
d
m
ali
g
n
a
n
t
lesi
o
n
s
.
Data
o
f
1
1
7
m
a
m
m
o
g
r
a
m
s
is
d
iv
id
ed
in
to
b
en
ig
n
l
esio
n
s
am
o
u
n
ted
7
9
b
en
ig
n
m
a
m
m
o
g
r
a
m
a
n
d
m
ali
g
n
a
n
t
lesi
o
n
s
a
m
o
u
n
ted
3
8
m
a
m
m
o
g
r
a
m
s
.
T
h
e
r
esu
lti
n
g
i
m
a
g
e
o
f
m
a
m
m
o
g
r
ap
h
y
i
m
a
g
in
g
h
a
s
t
h
e
s
a
m
e
s
ize
t
h
at
i
s
2
4
2
4
x
3
2
9
6
p
ix
els,
b
u
t
th
e
i
m
ag
e
o
f
t
h
e
cr
o
p
p
in
g
r
esu
lt
s
,
w
h
ic
h
i
s
th
e
an
n
o
tatio
n
s
o
f
R
ad
io
lo
g
is
t
s
,
h
as
th
e
v
er
y
v
ar
io
u
s
s
izes
b
ec
a
u
s
e
i
t
d
ep
en
d
s
o
n
t
h
e
le
v
el
o
f
th
e
v
ast
n
es
s
o
f
t
h
e
ar
ea
o
f
R
o
I
its
elf
.
2
.
2
.
P
ra
pro
ce
s
s
ing
I
n
ter
p
r
etin
g
th
e
m
a
m
m
o
g
r
a
m
i
m
a
g
e
i
s
a
v
er
y
d
i
f
f
icu
l
t
j
o
b
b
ec
au
s
e
t
h
e
i
m
ag
e
r
esu
lti
n
g
f
r
o
m
t
h
e
m
a
m
m
o
g
r
ap
h
y
tech
n
o
lo
g
y
h
a
s
a
v
er
y
lo
w
q
u
alit
y
.
O
n
e
o
f
t
h
e
ch
ar
ac
ter
s
is
h
a
v
in
g
a
v
er
y
l
o
w
le
v
el
o
f
co
n
tr
ast
th
at
i
s
v
er
y
d
if
f
ic
u
lt
to
d
is
ti
n
g
u
i
s
h
b
et
w
ee
n
t
h
e
R
o
I
f
r
o
m
t
h
e
f
a
tt
y
t
is
s
u
e.
T
h
er
ef
o
r
e,
b
ef
o
r
e
p
er
f
o
r
m
i
n
g
t
h
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
th
e
m
a
m
m
o
g
r
a
m
i
m
ag
e
q
u
alit
y
n
ee
d
s
to
b
e
i
m
p
r
o
v
ed
,
h
er
ein
a
f
t
er
r
ef
er
r
ed
to
as
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.
8
,
No
.
1
,
Feb
r
u
ar
y
2
0
1
8
:
6
0
–
69
62
p
r
etr
ea
tm
e
n
t
p
r
o
ce
s
s
th
a
t
aim
s
to
g
et
t
h
e
b
etter
q
u
ali
f
ie
d
im
a
g
e.
So
m
e
p
r
o
ce
s
s
es
p
er
f
o
r
m
ed
at
th
i
s
s
ta
g
e
in
cl
u
d
e:
n
o
r
m
aliza
tio
n
o
f
m
a
m
m
o
g
r
a
m
i
m
a
g
e
s
ize
to
b
e
2
5
6
x
2
5
6
p
ix
els
w
i
th
b
ili
n
ea
r
i
n
te
r
p
o
latio
n
; r
e
m
o
v
in
g
th
e
b
ac
k
g
r
o
u
n
d
o
f
m
a
m
m
o
g
r
a
m
i
m
a
g
e
w
it
h
a
r
o
llin
g
b
all
r
a
d
iu
s
o
f
5
0
p
ix
el
s
;
r
e
m
o
v
i
n
g
th
e
n
o
is
e
b
y
m
ed
ia
n
f
ilter
i
n
g
w
i
th
a
r
ad
iu
s
o
f
2
p
ix
els;
i
m
p
r
o
v
i
n
g
t
h
e
i
m
ag
e
co
n
tr
ast
u
s
i
n
g
C
L
A
HE
(
C
o
n
tr
as
t
-
L
i
m
ited
A
d
ap
tiv
e
His
to
g
r
a
m
E
q
u
al
izatio
n
)
m
et
h
o
d
w
i
th
b
lo
c
k
s
ize
o
f
1
2
7
,
h
is
to
g
r
a
m
b
i
n
s
o
f
2
5
6
an
d
m
ax
i
m
u
m
s
lo
p
e
o
f
3
;
b
esid
es
u
s
i
n
g
C
L
A
HE
to
i
m
p
r
o
v
e
th
e
i
m
a
g
e
co
n
tr
a
s
t
also
u
s
i
n
g
eq
u
aliza
tio
n
h
i
s
to
g
r
a
m
w
it
h
s
a
tu
r
ated
p
ix
el
o
f
0
.
4
%.
T
h
e
r
esu
lt
s
o
f
ea
ch
s
t
ag
e
o
f
p
r
etr
ea
t
m
e
n
t a
r
e
s
h
o
w
n
in
Fi
g
u
r
e
1
an
d
Fi
g
u
r
e
2
.
(
a)
(
b
)
(
c)
(
d
)
(
e)
(
f
)
Fig
u
r
e
1
.
(
a)
o
r
ig
i
n
al
i
m
a
g
e
w
i
th
v
ie
w
C
C
,
(
b
)
R
esize
R
o
I
,
(
c)
b
ac
k
g
r
o
u
n
d
r
e
m
o
v
al,
(d
-
f)
th
e
h
is
to
g
r
a
m
(
a)
(
b
)
(
c)
(
d
)
(
e)
(
f
)
Fig
u
r
e
2
.
(
a)
m
ed
ian
f
ilter
i
n
g
,
(
b
)
C
L
A
HE
,
(
c)
eq
u
aliza
tio
n
h
is
to
g
r
a
m
,
(
d
-
f
)
t
h
e
h
i
s
to
g
r
a
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
F
ea
tu
r
e
S
elec
tio
n
Ma
mmo
g
r
a
m
b
a
s
ed
o
n
B
r
ea
s
t Ca
n
ce
r
Mi
n
in
g
(
S
h
o
fw
a
tu
l ‘
Uyu
n
)
63
2
.
3
.
F
ea
t
ure
E
x
t
ra
ct
io
n
On
e
k
e
y
to
th
e
s
u
cc
e
s
s
o
f
a
p
atter
n
r
ec
o
g
n
i
tio
n
s
y
s
te
m
,
w
h
ich
in
t
h
i
s
ca
s
e
is
C
A
D
x
s
y
s
t
e
m
,
is
t
h
e
r
ig
h
t
u
s
e
o
f
f
ea
t
u
r
es
t
h
at
ar
e
a
b
le
to
d
is
tin
g
u
i
s
h
b
et
w
ee
n
b
e
n
ig
n
le
s
io
n
s
f
r
o
m
m
ali
g
n
a
n
t
l
esio
n
s
.
T
h
er
ef
o
r
e,
it
is
n
ec
ess
ar
y
to
s
tu
d
y
t
h
e
u
s
e
o
f
al
g
o
r
ith
m
s
t
h
at
ca
n
b
e
u
s
ed
to
s
elec
t
a
n
d
ev
a
lu
ate
t
h
e
u
s
e
o
f
f
ea
t
u
r
es
p
r
ec
is
el
y
.
I
n
g
en
er
al,
t
h
is
r
e
s
e
ar
ch
p
er
f
o
r
m
s
t
h
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
o
n
a
m
a
m
m
o
g
r
a
m
i
m
a
g
e
u
s
i
n
g
t
w
o
t
y
p
es
o
f
f
ea
t
u
r
e
d
o
m
ain
,
s
h
ap
e
d
o
m
ai
n
(
1
4
d
escr
ip
to
r
s
)
an
d
tex
tu
r
e
d
o
m
ain
u
s
i
n
g
th
e
eq
u
atio
n
s
h
o
w
n
i
n
T
ab
le
1
an
d
T
ab
le
2
.
T
h
e
u
s
e
o
f
f
ea
t
u
r
es
o
n
th
e
te
x
tu
r
e
d
o
m
ai
n
(
2
4
d
escr
ip
to
r
s
)
co
n
s
i
s
ts
o
f
th
e
f
i
r
s
t
o
r
d
er
s
tatis
tics
an
d
th
e
s
ec
o
n
d
o
r
d
er
s
tatis
tic
s
co
m
m
o
n
l
y
ca
l
led
GL
C
M
(
g
r
a
y
le
v
el
co
-
o
cc
u
r
r
en
ce
m
at
r
ix
)
.
T
h
e
f
ea
tu
r
e
o
f
GL
C
M
u
s
es
f
o
u
r
d
ir
ec
ti
os
(
,
,
)
an
d
th
e
a
v
er
ag
e
v
alu
e
f
o
r
ea
ch
f
ea
tu
r
e
w
i
th
t
h
e
f
o
u
r
d
ir
ec
ti
os
.
T
ab
le
1
.
So
m
e
f
ea
t
u
r
es
f
o
r
s
h
a
p
e
d
o
m
ain
F
i
t
u
r
E
x
p
r
e
s
si
o
n
A
r
e
a
A
r
e
a
o
f
se
l
e
c
t
i
o
n
i
n
s
q
u
a
r
e
p
i
x
e
l
s
C
e
n
t
e
r
o
f
M
a
ssa
t
h
e
b
r
i
g
h
t
n
e
ss
-
w
e
i
g
h
t
e
d
a
v
e
r
a
g
e
o
f
t
h
e
x
a
n
d
y
c
o
o
r
d
i
n
a
t
e
s a
l
l
p
i
x
e
l
s i
n
t
h
e
i
mag
e
o
r
se
l
e
c
t
i
o
n
M
o
d
a
l
g
r
a
y
v
a
l
u
e
t
h
e
h
i
g
h
e
st
p
e
a
k
i
n
t
h
e
h
i
st
o
g
r
a
m
C
e
n
t
r
o
i
d
t
h
e
a
v
e
r
a
g
e
o
f
t
h
e
x
a
n
d
y
c
o
o
r
d
i
n
a
t
e
s o
f
a
l
l
o
f
t
h
e
p
i
x
e
l
s i
n
t
h
e
i
mag
e
o
r
se
l
e
c
t
i
o
n
P
e
r
i
me
t
e
r
T
h
e
l
e
n
g
t
h
o
f
t
h
e
o
u
t
si
d
e
b
o
u
n
d
a
r
y
o
f
t
h
e
se
l
e
c
t
i
o
n
I
n
t
e
g
r
a
t
e
d
d
e
n
si
t
y
T
h
e
su
m o
f
t
h
e
v
a
l
u
e
s o
f
t
h
e
p
i
x
e
l
s i
n
t
h
e
i
m
a
g
e
o
r
se
l
e
c
t
i
o
n
M
e
d
i
a
n
T
h
e
me
d
i
a
n
v
a
l
u
e
o
f
t
h
e
p
i
x
e
l
s i
n
t
h
e
i
mag
e
o
r
se
l
e
c
t
i
o
n
A
r
e
a
f
r
a
c
t
i
o
n
F
o
r
t
h
r
e
sh
o
l
d
e
d
i
m
a
g
e
s
i
s
t
h
e
p
e
r
c
e
n
t
a
g
e
o
f
p
i
x
e
l
s
i
n
t
h
e
i
mag
e
o
r
se
l
e
c
t
i
o
n
t
h
a
t
h
a
v
e
b
e
e
n
h
i
g
h
l
i
g
h
t
e
d
.
F
o
r
n
o
n
-
t
h
r
e
sh
o
l
d
e
d
i
m
a
g
e
s i
s t
h
e
p
e
r
c
e
n
t
a
g
e
o
f
n
o
n
-
z
e
r
o
p
i
x
e
l
s
S
t
a
c
k
p
o
si
t
i
o
n
T
h
e
p
o
si
t
i
o
n
(
sl
i
c
e
,
c
h
a
n
n
e
l
a
n
d
f
r
a
me
)
i
n
t
h
e
st
a
c
k
o
r
h
y
p
e
r
st
a
c
k
o
f
t
h
e
se
l
e
c
t
i
o
n
C
i
r
c
u
l
a
r
i
t
y
C
i
r
c
u
l
a
r
i
t
y
=
x
(
a
r
e
a
)
(
p
e
r
i
me
t
e
r
A
sp
e
c
t
R
a
t
i
o
(
A
R
)
T
h
e
a
sp
e
c
t
r
a
t
i
o
o
f
t
h
e
p
a
r
t
i
c
l
e
‟
s fi
t
t
e
d
e
l
l
i
p
se
R
o
u
n
d
n
e
ss
t
h
e
i
n
v
e
r
se
o
f
Asp
e
c
t
R
a
t
i
o
S
o
l
i
d
i
t
y
S
o
l
i
d
i
t
y
=
T
ab
le
2
.
So
m
e
f
ea
t
u
r
es
f
o
r
tex
tu
r
e
d
o
m
ain
F
i
t
u
r
E
x
p
r
e
s
si
o
n
M
e
a
n
(
)
∑
S
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
(
)
∑
S
k
e
w
n
e
ss
∑
K
u
r
t
o
si
s
∑
C
o
n
t
r
a
st
(
C
O
N
T
)
C
O
N
T
_
d
_
∑
∑
C
o
r
r
e
l
a
t
i
o
n
(
C
O
R
R
)
∑
∑
En
e
r
g
y
En
e
r
g
y
=
∑
∑
H
o
mo
g
e
n
e
i
t
y
(
H
O
M
O
)
H
o
mo
∑
∑
Af
ter
p
r
ap
r
o
ce
s
s
in
g
,
t
h
e
s
h
ap
e
an
d
tex
tu
r
e
d
o
m
ai
n
s
ar
e
ex
t
r
ac
ted
o
n
th
e
m
a
m
m
o
g
r
a
m
i
m
ag
e.
T
h
er
e
ar
e
th
r
ee
s
ce
n
ar
io
s
o
f
e
x
p
er
i
m
en
ts
co
n
d
u
cted
as
f
o
llo
w
s
:
fir
s
t
,
u
s
i
n
g
all
t
h
e
f
ea
t
u
r
es
o
f
s
h
ap
e
an
d
te
x
tu
r
e
a
m
o
u
n
ted
3
8
d
escr
ip
to
r
s
s
i
m
u
ltan
eo
u
s
l
y
,
s
ec
o
n
d
,
u
s
i
n
g
t
h
e
s
h
ap
e
f
ea
tu
r
e
w
it
h
1
4
d
escr
ip
to
r
s
,
an
d
th
ir
d
,
u
s
in
g
th
e
tex
tu
r
e
f
ea
tu
r
e
w
it
h
2
4
d
escr
ip
to
r
s
.
Sch
e
m
e
o
f
f
ea
t
u
r
e
u
s
e
f
o
r
b
o
th
d
o
m
ai
n
s
ar
e
s
h
o
w
n
in
T
ab
le
3
.
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.
8
,
No
.
1
,
Feb
r
u
ar
y
2
0
1
8
:
6
0
–
69
64
T
ab
le
3
.
T
h
e
u
s
e
o
f
f
ea
t
u
r
e
d
escr
ip
to
r
f
o
r
ex
p
er
im
e
n
t
N
o
d
e
F
e
a
t
u
r
e
D
e
sk
r
i
p
t
o
r
1
S
h
a
p
e
a
n
d
t
e
x
t
u
r
e
f
e
a
t
u
r
e
s
38
2
S
h
a
p
e
f
e
a
t
u
r
e
14
3
T
e
x
t
u
r
e
f
e
a
t
u
r
e
24
2
.
4
.
F
ea
t
ure
Select
io
n
T
h
e
p
r
o
p
e
r
u
s
e
o
f
th
e
f
ea
tu
r
es
m
a
y
p
r
o
v
id
e
t
h
e
o
p
ti
m
al
cla
s
s
i
f
icat
io
n
r
es
u
lt
s
,
b
esid
es,
i
n
co
m
p
u
tatio
n
,
it
m
a
y
a
ls
o
r
ed
u
ce
th
e
b
u
r
d
en
o
f
p
r
o
ce
s
s
o
r
f
o
r
u
n
i
m
p
o
r
ta
n
t
d
ata
p
r
o
ce
s
s
in
g
.
T
h
er
ef
o
r
e,
in
th
i
s
r
esear
ch
t
h
e
r
esear
c
h
er
s
co
n
d
u
ct
t
h
e
d
ata
m
in
i
n
g
a
s
t
h
e
r
es
u
lts
o
f
f
ea
t
u
r
e
ex
tr
ac
t
io
n
w
i
th
t
h
r
ee
n
o
d
es
as
n
o
ted
in
T
ab
le
3
.
T
o
p
er
f
o
r
m
t
h
e
f
e
atu
r
e
s
elec
t
io
n
,
t
h
e
m
a
m
m
o
g
r
a
m
i
m
a
g
e
u
s
es
t
w
o
al
g
o
r
ith
m
s
th
o
s
e
ar
e
d
ec
is
io
n
tr
ee
an
d
r
u
le
i
n
d
u
c
tio
n
.
Dec
i
s
i
o
n
tr
ee
is
a
p
o
w
er
f
u
l
an
d
p
o
p
u
lar
alg
o
r
ith
m
f
o
r
clas
s
i
f
icatio
n
an
d
p
r
ed
ictio
n
.
I
ts
o
th
er
ad
v
an
ta
g
e
is
b
ein
g
ab
le
to
r
ep
r
esen
t
s
o
m
e
r
u
les
t
h
at
ar
e
ea
s
il
y
u
n
d
er
s
to
o
d
b
y
t
h
e
h
u
m
an
s
an
d
th
e
k
n
o
w
led
g
e
ca
n
b
e
u
s
ed
as
th
e
d
ata
in
th
e
d
atab
ase
[
1
6
]
.
W
h
ile
th
e
r
u
le
in
d
u
ctio
n
al
g
o
r
ith
m
is
o
n
e
o
f
t
h
e
alg
o
r
ith
m
s
i
m
p
le
m
en
ted
o
n
m
ac
h
in
e
lear
n
in
g
th
a
t
is
ab
le
to
f
o
r
m
u
late
s
o
m
e
r
u
le
s
ex
tr
ac
te
d
f
r
o
m
a
co
llectio
n
o
f
o
b
s
er
v
atio
n
d
ata.
T
h
e
r
es
u
l
ts
o
f
d
ata
e
x
tr
ac
tio
n
in
t
h
e
f
o
r
m
o
f
a
r
u
le
ar
e
t
h
e
d
ata
m
o
d
el
in
t
h
e
s
c
ien
t
if
ic
f
o
r
m
t
h
at
r
ep
r
ese
n
ts
s
o
m
e
d
at
a
p
atter
n
s
[
1
7
]
.
T
h
e
ex
a
m
p
le
o
f
th
e
u
s
e
o
f
d
ec
i
s
io
n
tr
ee
a
n
d
r
u
le
in
d
u
ctio
n
f
o
r
th
e
f
ir
s
t n
o
d
e
w
it
h
3
8
d
escr
ip
to
r
s
is
s
h
o
w
n
in
Fig
u
r
e
3
an
d
T
ab
le
4
.
So
m
e
i
m
p
o
r
ta
n
t
f
ea
tu
r
e
s
ar
e
o
b
tain
ed
b
as
ed
o
n
th
e
r
es
u
lts
o
f
m
i
n
i
n
g
u
s
in
g
d
ec
is
io
n
tr
e
e
an
d
r
u
le
in
d
u
ctio
n
f
o
r
th
e
3
8
d
escr
ip
to
r
s
o
f
m
a
m
m
o
g
r
a
m
i
m
ag
e
s
.
T
h
e
i
m
p
o
r
tan
t
f
ea
t
u
r
es
g
e
n
er
ated
b
y
t
h
e
d
ec
is
io
n
tr
ee
alg
o
r
ith
m
(
s
ee
T
ab
le
5
,
s
ce
n
ar
io
I
)
in
clu
d
e:
k
u
r
to
s
is
,
ar
ea
f
r
ac
tio
n
an
d
m
ea
n
,
w
h
ile
t
h
e
i
m
p
o
r
tan
t
f
ea
t
u
r
es
g
en
er
ated
b
y
t
h
e
r
u
le
in
d
u
cti
o
n
alg
o
r
ith
m
(
s
ee
T
ab
le
5
,
s
ce
n
ar
io
I
I
)
in
clu
d
e:
s
lice,
m
ea
n
,
ar
ea
f
r
ac
tio
n
an
d
co
n
tr
ast
w
it
h
th
e
an
g
le
1
3
5
.
T
h
e
s
a
m
e
t
h
i
n
g
is
ap
p
lied
to
n
o
d
e
2
an
d
3
u
s
in
g
d
ec
is
io
n
tr
ee
an
d
r
u
le
in
d
u
ctio
n
alg
o
r
ith
m
s
,
i
n
w
h
ic
h
t
h
e
m
i
n
i
n
g
r
es
u
lts
ar
e
s
h
o
w
n
i
n
T
ab
le
5
(
s
ce
n
ar
io
I
I
I
a
n
d
I
V)
f
o
r
n
o
d
e
2
an
d
T
ab
le
5
(
s
ce
n
ar
io
V
a
n
d
VI
)
f
o
r
n
o
d
e
3
.
T
h
e
f
ea
t
u
r
es
u
s
ed
in
th
e
ex
p
er
i
m
e
n
t
w
it
h
s
ce
n
ar
io
s
VI
I
is
a
n
i
m
p
o
r
tan
t
f
ea
t
u
r
e
g
en
er
ated
b
y
th
e
f
ir
s
t
n
o
d
e
u
s
in
g
b
o
th
th
e
d
ec
is
io
n
tr
ee
al
g
o
r
ith
m
a
n
d
th
e
r
u
le
in
d
u
ctio
n
alg
o
r
it
h
m
.
T
h
e
s
am
e
t
h
in
g
is
ap
p
lied
to
s
ce
n
ar
io
VI
I
I
an
d
I
X
u
s
in
g
th
e
b
est
f
ea
t
u
r
es
o
f
th
e
ex
p
e
r
i
m
en
tal
r
esu
lt
s
o
f
n
o
d
e
I
I
an
d
I
I
I
.
T
h
e
d
etailed
r
esu
lt
s
o
f
e
x
p
er
i
m
e
n
t c
an
b
e
s
e
en
in
T
ab
le
5
.
Fig
u
r
e
3
.
T
h
e
g
r
ap
h
o
f
th
e
r
es
u
lt o
f
d
ec
is
io
n
tr
ee
alg
o
r
it
h
m
T
ab
l
e
4
.
T
h
e
r
u
le
g
en
er
ated
b
y
th
e
r
u
le
i
n
d
u
ctio
n
f
o
r
cl
a
s
s
if
i
c
a
tio
n
o
f
b
en
i
g
n
d
an
m
a
lig
n
a
n
t
lesi
o
n
s
u
s
in
g
38
d
es
c
r
ip
to
r
s
N
o
d
e
R
u
l
e
1
2
3
i
f
S
l
i
c
e
>
3
8
5
0
0
t
h
e
n
B
e
n
i
g
n
(
0
/
4
1
)
i
f
M
e
a
n
>
1
0
9
6
0
0
a
n
d
A
r
e
a
F
r
a
c
t
i
o
n
≤
9
9
7
3
0
t
h
e
n
M
a
l
i
g
n
a
n
t
(
1
9
/
0
)
i
f
A
r
e
a
F
r
a
c
t
i
o
n
≤
9
9
7
8
5
a
n
d
C
o
n
t
r
a
s
t
_
1
3
5
≤
0
.
3
7
3
t
h
e
n
B
e
n
i
g
n
(
3
/
3
0
)
e
l
se
G
a
n
a
s
(
1
4
/
7
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
F
ea
tu
r
e
S
elec
tio
n
Ma
mmo
g
r
a
m
b
a
s
ed
o
n
B
r
ea
s
t Ca
n
ce
r
Mi
n
in
g
(
S
h
o
fw
a
tu
l ‘
Uyu
n
)
65
T
ab
l
e
5
.
T
h
e
s
elec
ted
f
ea
tu
r
es
r
esu
lti
n
g
f
r
o
m
s
o
m
e
s
ce
n
ar
io
s
o
f
ex
p
er
i
m
e
n
t
s
u
s
in
g
d
ec
is
io
n
tr
ee
an
d
r
u
le
in
d
u
ctio
n
alg
o
r
it
h
m
s
S
c
e
n
a
r
i
o
D
e
scri
p
t
o
r
D
e
c
i
si
o
n
T
r
e
e
S
c
e
n
a
r
i
o
D
e
scri
p
t
o
r
R
u
l
e
I
n
d
u
c
t
i
o
n
I
3
K
u
r
t
o
si
s,
a
r
e
a
f
r
a
c
t
i
o
n
,
me
a
n
II
3
S
l
i
c
e
,
me
a
n
,
a
r
e
a
f
r
a
c
t
i
o
n
,
c
o
n
t
r
a
st
_
1
3
5
III
6
A
r
e
a
f
r
a
c
t
i
o
n
,
me
d
i
a
n
,
i
n
t
e
g
r
a
t
e
d
d
e
n
si
t
y
,
sl
i
c
e
,
mo
d
a
l
g
r
a
y
v
a
l
u
e
,
c
e
n
t
e
r
o
f
massa
IV
5
S
l
i
c
e
,
i
n
t
e
g
r
a
t
e
d
d
e
n
si
t
y
,
A
r
e
a
f
r
a
c
t
i
o
n
,
mo
d
a
l
g
r
a
y
v
a
l
u
e
,
c
e
n
t
e
r
o
f
massa
V
2
K
u
r
t
o
si
s,
me
a
n
VI
4
M
e
a
n
,
k
u
r
t
o
s
i
s,
c
o
n
t
r
a
st
_
0
,
e
n
e
r
g
y
_
4
5
,
c
o
r
r
e
l
a
t
i
o
n
_
4
5
V
I
I
2
A
r
e
a
f
r
a
c
t
i
o
n
,
me
a
n
V
I
I
I
5
S
l
i
c
e
,
i
n
t
e
g
r
a
t
e
d
d
e
n
si
t
y
,
A
r
e
a
f
r
a
c
t
i
o
n
,
mo
d
a
l
g
r
a
y
v
a
l
u
e
,
c
e
n
t
e
r
o
f
massa
IX
2
K
u
r
t
o
si
s,
me
a
n
X
8
S
l
i
c
e
,
me
a
n
,
a
r
e
a
f
r
a
c
t
i
o
n
,
c
o
n
t
r
a
st
_
1
3
5
,
i
n
t
e
g
r
a
t
e
d
d
e
n
si
t
y
,
mo
d
a
l
g
r
a
y
v
a
l
u
e
,
c
e
n
t
e
r
o
f
massa
,
k
u
r
t
o
si
s
2
.
5
.
Cla
s
s
if
ica
t
io
n
Hav
i
n
g
o
b
tain
ed
s
o
m
e
o
f
th
e
s
elec
ted
f
ea
t
u
r
es
f
o
r
ea
ch
s
ce
n
ar
io
b
ased
o
n
th
e
d
ec
is
io
n
tr
ee
an
d
r
u
le
in
d
u
ctio
n
alg
o
r
it
h
m
s
,
t
h
en
t
h
e
r
esear
ch
er
s
co
n
d
u
ct
a
clas
s
i
f
icatio
n
p
r
o
ce
s
s
o
f
m
a
m
m
o
g
r
a
m
i
m
ag
e
i
n
to
t
w
o
class
es,
b
e
n
i
g
n
lesi
o
n
s
a
n
d
m
ali
g
n
a
n
t
lesi
o
n
s
.
I
n
th
is
cl
ass
i
f
icatio
n
s
ta
g
e,
t
h
e
r
esear
ch
er
s
u
s
e
s
ev
er
al
alg
o
r
ith
m
s
,
a
m
o
n
g
o
th
er
s
:
k
-
n
ea
r
est
n
ei
g
h
b
o
r
s
(
KNN)
,
d
e
cisi
o
n
tr
ee
(
D
T
)
an
d
Naiv
e
B
ay
e
s
ian
(
NB
)
th
at
f
u
r
t
h
er
w
ill
b
e
ex
p
r
ess
ed
in
t
h
e
p
o
in
ts
o
f
d
is
c
u
s
s
io
n
.
B
ase
d
o
n
th
e
f
ea
tu
r
e
s
elec
tio
n
p
r
o
ce
s
s
in
t
h
e
p
r
ev
io
u
s
p
r
o
ce
s
s
,
th
er
e
w
i
ll
b
e
a
class
i
f
icatio
n
p
r
o
ce
s
s
o
n
ten
s
ce
n
ar
io
s
p
r
ed
ef
in
ed
p
r
ev
io
u
s
l
y
to
m
ea
s
u
r
e
t
h
e
p
er
f
o
r
m
a
n
ce
.
2
.
6
.
E
v
a
lua
t
io
n
T
o
ev
alu
ate
t
h
e
r
e
s
u
l
ts
o
f
c
l
ass
i
f
icatio
n
o
f
s
o
m
e
f
ea
t
u
r
es
b
ased
o
n
th
e
s
elec
ted
f
ea
tu
r
e
in
ea
ch
s
ce
n
ar
io
,
th
e
d
ata
is
a
u
to
m
at
i
ca
ll
y
d
iv
id
ed
u
s
in
g
t
h
e
k
-
f
o
ld
cr
o
s
s
v
alid
atio
n
(
w
it
h
1
0
k
n
u
m
b
er
)
in
s
tr
atif
ied
s
a
m
p
li
n
g
w
a
y
.
B
esid
es,
th
is
r
esear
ch
al
s
o
u
s
es
f
iv
e
s
ta
tis
t
ical
p
ar
a
m
eter
s
th
a
t
ar
e
co
m
m
o
n
l
y
u
s
ed
i
n
m
ed
ica
l
d
iag
n
o
s
t
ic
r
es
u
lt
test
in
cl
u
d
i
n
g
:
ac
c
u
r
ac
y
,
s
en
s
iti
v
it
y
,
s
p
ec
if
icit
y
,
f
alse
p
o
s
iti
v
e
r
ate
(
FP
R
)
an
d
tr
u
e
p
o
s
it
iv
e
r
ate
(
T
P
R
)
.
T
h
e
ai
m
o
f
u
s
i
n
g
th
e
f
iv
e
p
ar
a
m
eter
s
is
to
k
n
o
w
h
o
w
r
el
iab
le
an
d
co
n
s
i
s
te
n
t
a
s
y
s
te
m
to
m
ak
e
d
iag
n
o
s
i
s
o
f
b
r
ea
s
t
ca
n
ce
r
.
Acc
u
r
ac
y
i
s
th
e
a
m
o
u
n
t
o
f
d
at
a
th
at
is
s
u
cc
e
s
s
f
u
ll
y
p
r
ed
ict
ed
co
r
r
ec
tly
b
y
t
h
e
class
i
f
icatio
n
s
y
s
te
m
eit
h
er
n
eg
ati
v
el
y
o
r
p
o
s
itiv
e
l
y
,
i
n
w
h
ich
th
e
s
en
s
iti
v
it
y
is
a
m
ea
s
u
r
e
o
f
s
u
cc
es
s
o
f
t
h
e
class
i
f
icatio
n
s
y
s
te
m
i
n
id
en
ti
f
y
in
g
t
h
e
p
o
s
iti
v
e
d
ata
co
r
r
ec
tl
y
an
d
t
h
e
s
p
ec
i
f
icit
y
is
a
m
e
asu
r
e
o
f
s
u
cc
e
s
s
o
f
th
e
cla
s
s
i
f
icatio
n
s
y
s
te
m
in
id
en
ti
f
y
in
g
t
h
e
n
eg
at
iv
e
d
ata
co
r
r
ec
tly
.
FP
R
s
h
o
w
s
th
e
a
v
er
ag
e
o
f
p
o
s
iti
v
e
ca
s
e
s
id
en
ti
f
ied
as
th
e
w
r
o
n
g
o
n
e
a
n
d
T
P
R
f
o
r
th
e
o
p
p
o
s
ite
ca
s
e.
A
s
s
o
ciatio
n
s
b
et
w
ee
n
FP
R
a
n
d
T
P
R
p
ar
am
eter
s
ca
n
b
e
r
ep
r
esen
ted
g
r
ap
h
icall
y
th
at
is
ca
lled
th
e
R
O
C
cu
r
v
e.
T
h
e
u
s
e
o
f
th
e
R
O
C
cu
r
v
es
is
to
ass
is
t
i
n
m
a
k
i
n
g
d
ec
is
io
n
in
th
e
s
ea
r
ch
f
o
r
th
e
b
est
m
o
d
el
f
o
r
th
e
d
ia
g
n
o
s
is
o
f
b
r
ea
s
t
c
an
ce
r
.
T
h
e
ca
lc
u
latio
n
o
f
t
h
e
f
i
v
e
p
ar
am
eter
s
is
s
h
o
w
n
i
n
T
ab
le
6
.
I
llu
s
tr
atio
n
:
T
P
(
T
r
u
e
P
o
s
itiv
e)
;
T
N
(
T
r
u
e
Neg
ativ
e)
;
FN
(
F
alse
Ne
g
ati
v
e)
;
FP
(
Fals
e
P
o
s
i
tiv
e)
;
f
als
e
p
o
s
itiv
e
r
ate
(
FP
R
)
d
an
tr
u
e
p
o
s
itiv
e
r
ate
(
T
P
R
)
.
Gen
er
al
d
escr
ip
tio
n
f
o
r
ea
ch
s
t
ag
e
is
s
h
o
w
n
in
F
ig
u
r
e
4
.
Fig
u
r
e
4
.
Gen
er
al
d
escr
ip
tio
n
o
f
r
esear
ch
s
ta
g
es
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.
8
,
No
.
1
,
Feb
r
u
ar
y
2
0
1
8
:
6
0
–
69
66
T
ab
l
e
6
.
Fo
r
m
u
la
to
o
b
tain
t
h
e
v
alu
e
s
o
f
s
e
n
s
itiv
it
y
,
s
p
ec
if
ici
t
y
d
an
ac
cu
r
c
y
No
F
o
r
mu
l
a
1
2
3
4
5
⁄
⁄
⁄
F
P
R
=
F
P
/
(
F
P
+
T
N
)
T
P
R
=
T
P
/
(
T
P
+
F
N
)
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
T
h
e
p
u
r
p
o
s
e
o
f
th
i
s
r
esear
ch
i
s
to
f
i
n
d
t
h
e
b
est
f
ea
t
u
r
es
t
h
at
ar
e
u
s
ed
to
d
ev
elo
p
th
e
C
A
D
x
s
y
s
te
m
f
o
r
b
r
ea
s
t c
an
ce
r
o
n
a
m
a
m
m
o
g
r
a
m
i
m
a
g
e.
T
h
er
ef
o
r
e,
in
th
is
r
esear
ch
,
th
e
r
esear
c
h
er
s
h
a
v
e
co
n
d
u
cted
s
ev
er
al
ex
p
er
i
m
e
n
ts
w
it
h
ten
s
ce
n
ar
i
o
s
,
in
w
h
ich
ea
c
h
s
ce
n
ar
io
co
n
s
is
ts
o
f
s
i
x
s
tag
e
s
o
f
r
esear
ch
th
at
h
a
s
b
ee
n
d
escr
ib
ed
as sh
o
w
n
i
n
Fi
g
u
r
e
4
.
A
s
a
n
e
x
a
m
p
le
f
o
r
e
x
p
er
i
m
en
t
w
it
h
t
h
e
f
ir
s
t
s
ce
n
ar
io
,
af
te
r
s
h
o
o
tin
g
u
s
i
n
g
t
h
e
m
a
m
m
o
g
r
ap
h
y
tec
h
n
o
lo
g
y
,
t
h
e
r
esear
ch
er
s
co
n
d
u
cted
s
ev
er
al
ti
m
es
a
p
r
etr
ea
t
m
e
n
t
p
r
o
ce
s
s
th
a
t
h
as
b
ee
n
d
escr
ib
ed
in
d
etail
in
s
ec
t
io
n
2
.
b
.
T
h
e
o
u
tp
u
t
o
f
t
h
ese
s
ta
g
e
s
is
t
h
e
o
b
tain
m
e
n
t
o
f
m
a
m
m
o
g
r
a
m
i
m
a
g
es
w
it
h
b
etter
q
u
alit
y
,
s
o
t
h
at
v
i
s
u
a
ll
y
t
h
e
R
ad
io
lo
g
i
s
ts
ca
n
d
if
f
er
en
tia
te
b
et
w
ee
n
f
att
y
ti
s
s
u
e
a
n
d
f
a
t,
w
h
ic
h
p
r
ev
io
u
s
l
y
i
t
w
a
s
v
er
y
d
if
f
ic
u
l
t
to
d
is
ti
n
g
u
is
h
b
et
w
ee
n
t
h
e
s
e
t
w
o
ar
ea
s
b
ec
au
s
e
it
is
a
v
er
y
th
i
n
n
et
w
o
r
k
w
i
th
n
o
m
u
ch
d
i
f
f
er
e
n
t
in
ten
s
it
y
.
T
h
e
n
ex
t
s
ta
g
e
is
to
p
er
f
o
r
m
th
e
f
ea
tu
r
e
e
x
tr
ac
tio
n
o
f
3
8
d
escr
ip
t
o
r
s
(
a
co
m
b
i
n
atio
n
o
f
s
h
ap
e
an
d
te
x
tu
r
e
f
ea
t
u
r
es);
th
e
n
th
e
r
esu
lts
o
f
t
h
e
f
ea
t
u
r
e
ex
tr
ac
t
io
n
a
r
e
s
elec
ted
u
s
i
n
g
a
d
ec
is
io
n
tr
ee
(
s
ce
n
ar
io
I
)
.
T
h
e
r
esu
lts
o
f
th
e
m
i
n
i
n
g
p
r
o
ce
s
s
u
s
i
n
g
a
d
ec
is
io
n
tr
ee
is
a
f
ac
t
t
h
at
n
o
t
all
f
ea
t
u
r
es
ar
e
ab
le
t
o
co
n
tr
ib
u
te
in
d
eter
m
i
n
in
g
t
h
e
class
o
f
b
r
ea
s
t
ca
n
ce
r
(
b
en
ig
n
an
d
m
ali
g
n
an
t)
.
T
h
er
e
ar
e
o
n
ly
t
h
r
ee
d
escr
ip
to
r
s
th
at
co
n
tr
ib
u
te
as
s
h
o
w
n
i
n
T
ab
le
5
.
T
h
e
n
ex
t
p
r
o
ce
s
s
is
th
e
s
ta
g
e
o
f
m
a
m
m
o
g
r
a
m
les
io
n
class
i
f
icatio
n
in
to
t
w
o
cla
s
s
es
(
b
en
ig
n
an
d
m
a
lig
n
a
n
t)
u
s
i
n
g
th
e
alg
o
r
it
h
m
o
f
K
-
Nea
r
es
t
Neig
h
b
o
r
(
KNN)
,
d
ec
is
io
n
T
r
ee
(
D
T
)
an
d
Naiv
e
B
ay
esia
n
(
NB
)
.
A
class
i
f
ica
tio
n
is
p
er
f
o
r
m
ed
in
th
e
u
s
e
o
f
f
ea
t
u
r
es
f
o
r
ea
ch
s
ce
n
ar
io
u
s
i
n
g
th
r
ee
cla
s
s
i
f
i
ca
tio
n
al
g
o
r
ith
m
s
a
n
d
t
h
er
e
is
an
ev
al
u
atio
n
p
r
o
ce
s
s
u
s
in
g
1
0
-
f
o
ld
cr
o
s
s
v
alid
atio
n
.
T
h
e
co
m
p
lete
r
es
u
lts
f
o
r
ea
ch
s
ta
g
e
o
f
t
h
e
ev
a
lu
atio
n
ar
e
s
h
o
w
n
i
n
T
ab
le
7
.
T
h
e
h
ig
h
e
s
t
a
cc
u
r
ac
y
v
alu
e
i
s
o
b
tain
ed
at
th
e
C
AD
x
s
y
s
te
m
to
clas
s
i
f
y
b
et
w
ee
n
b
en
ig
n
an
d
m
ali
g
n
an
t
lesi
o
n
s
in
s
ce
n
ar
io
I
V
an
d
VI
I
I
(
u
s
in
g
t
h
e
f
i
v
e
d
escr
ip
t
o
r
s
as
s
h
o
w
n
i
n
T
ab
le
5
)
w
i
th
th
e
clas
s
i
f
icatio
n
alg
o
r
ith
m
o
f
Dec
is
io
n
T
r
ee
a
m
o
u
n
ted
9
3
.
1
8
%.
T
h
e
u
s
e
o
f
th
e
f
i
v
e
d
escr
ip
to
r
s
also
p
r
o
v
id
e
v
alu
e
s
o
f
FP
R
,
T
P
R
,
P
r
ec
i
s
io
n
an
d
R
ec
a
ll
o
f
6
%;
9
2
%;
8
8
%
an
d
9
2
%,
w
h
ile
t
h
e
r
u
le
ca
n
b
e
u
s
ed
to
class
i
f
y
b
o
th
t
y
p
e
s
o
f
b
r
ea
s
t
ca
n
ce
r
as
s
h
o
w
n
i
n
T
ab
le
8
.
T
ab
l
e
7
.
E
v
alu
atio
n
r
es
u
lt o
f
t
h
e
u
s
e
o
f
s
elec
ted
f
ea
tu
r
e
s
(
b
ased
o
n
th
e
al
g
o
r
it
h
m
s
o
f
d
ec
i
s
i
o
n
t
r
ee
d
an
r
u
le
in
d
u
ctio
n
)
in
ac
co
r
d
an
ce
w
it
h
th
e
s
ce
n
ar
io
C
l
a
ssi
f
i
c
a
t
i
o
n
M
e
t
h
o
d
A
c
c
(
%)
S
e
n
s (%)
S
p
e
c
(
%)
F
P
R
(
%)
T
P
R
(
%)
S
C
EN
A
R
I
O
I
K
N
N
7
6
,
2
9
6
3
,
1
6
1
7
,
7
2
1
7
,
7
2
6
3
,
1
6
DT
8
2
,
0
5
7
2
,
9
7
1
3
,
7
5
1
2
,
6
6
7
1
,
0
5
NB
6
0
,
8
3
4
4
,
7
4
9
,
7
6
5
3
,
1
6
8
9
,
4
7
S
C
EN
A
R
I
O
I
I
K
N
N
7
6
,
2
9
6
2
,
5
1
6
,
8
8
1
8
,
9
9
6
5
,
7
9
DT
8
8
,
2
6
7
6
,
0
9
4
,
2
3
1
3
,
9
2
9
2
,
1
1
NB
7
7
,
0
5
5
9
,
0
2
3
,
5
7
3
1
,
6
5
9
4
,
7
4
S
C
EN
A
R
I
O
I
I
I
K
N
N
7
1
,
3
6
5
6
,
2
5
2
3
,
5
3
1
7
,
7
2
4
7
,
3
7
DT
9
0
,
6
1
8
1
,
3
9
4
,
0
5
1
0
,
1
3
9
2
,
1
1
NB
7
7
,
1
2
5
9
,
6
5
6
,
6
7
2
9
,
1
1
8
9
,
4
7
S
C
EN
A
R
I
O
I
V
a
n
d
V
I
I
I
K
N
N
7
1
,
3
6
5
6
,
2
5
2
3
,
5
3
1
7
,
7
2
4
7
,
3
7
DT
9
3
,
1
8
8
7
,
5
3
,
8
9
6
,
3
3
9
2
,
1
1
NB
7
5
,
3
5
7
,
6
3
6
,
8
9
3
1
,
6
5
8
9
,
4
7
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
F
ea
tu
r
e
S
elec
tio
n
Ma
mmo
g
r
a
m
b
a
s
ed
o
n
B
r
ea
s
t Ca
n
ce
r
Mi
n
in
g
(
S
h
o
fw
a
tu
l ‘
Uyu
n
)
67
C
l
a
ssi
f
i
c
a
t
i
o
n
M
e
t
h
o
d
A
c
c
(
%)
S
e
n
s (%)
S
p
e
c
(
%)
F
P
R
(
%)
T
P
R
(
%)
S
C
EN
A
R
I
O
V
a
n
d
I
X
K
N
N
7
7
,
2
7
6
4
,
8
7
1
7
,
5
1
6
,
4
6
6
3
,
1
6
DT
7
6
,
0
6
7
2
,
7
3
2
3
,
1
6
7
,
5
9
4
2
,
1
1
NB
7
0
,
1
5
5
2
,
8
3
1
5
,
6
3
3
1
,
6
5
7
3
,
6
8
S
C
EN
A
R
I
O
V
I
K
N
N
7
7
,
2
7
6
4
,
8
6
1
7
,
5
1
6
,
4
6
6
3
,
1
6
DT
7
5
,
2
3
68
2
2
,
8
3
1
0
,
1
3
4
4
,
7
4
NB
6
2
,
5
4
5
,
7
1
1
2
,
7
7
4
8
,
1
0
8
4
,
2
1
S
C
EN
A
R
I
O
V
I
I
K
N
N
7
9
,
7
7
6
7
,
5
1
4
,
2
9
1
6
,
4
6
7
1
,
0
5
DT
8
3
,
0
3
7
2
,
5
1
1
,
6
9
1
3
,
9
2
7
6
,
3
2
NB
6
1
,
7
4
4
5
,
5
7
5
,
2
6
5
4
,
4
3
8
5
,
7
1
S
K
EN
A
R
I
O
X
K
N
N
7
1
,
3
6
2
,
3
5
3
,
2
1
7
,
7
2
4
7
,
3
7
DT
8
4
,
5
5
7
7
.
7
8
0
,
5
2
1
0
,
1
3
7
3
,
6
8
NB
7
6
,
2
1
5
8
.
6
2
0
,
3
3
0
,
3
8
8
9
,
4
7
T
ab
l
e
8
.
T
h
e
r
u
le
r
esu
lti
n
g
i
n
t
h
e
r
u
le
i
n
d
u
ctio
n
f
o
r
th
e
cla
s
s
i
f
icatio
n
o
f
b
en
i
g
n
a
n
d
m
al
ig
n
a
n
t le
s
io
n
s
u
s
i
n
g
f
i
v
e
d
es
c
r
ip
to
r
s
(
s
elec
ted
f
ea
tu
r
es o
f
th
e
r
es
u
lt o
f
s
ce
n
ar
io
I
V
an
d
VI
I
I
)
N
o
d
e
R
u
l
e
1
2
3
4
5
6
7
i
f
S
l
i
c
e
>
3
8
5
0
0
t
h
e
n
B
e
n
i
g
n
(
0
/
4
1
)
i
f
I
n
t
e
g
r
a
t
e
d
D
e
n
si
t
y
>
7
1
7
1
5
0
0
0
0
0
a
n
d
A
r
e
a
F
r
a
c
t
i
o
n
≤
9
9
7
3
0
t
h
e
n
M
a
l
i
g
n
a
n
t
(
1
9
/
0
)
i
f
A
r
e
a
F
r
a
c
t
i
o
n
≤
9
9
7
8
5
a
n
d
A
r
e
a
F
r
a
c
t
i
o
n
>
9
9
7
0
5
t
h
e
n
B
e
n
i
g
n
(
0
/
1
8
)
i
f
A
r
e
a
F
r
a
c
t
i
o
n
≤
9
9
6
9
5
a
n
d
A
r
e
a
F
r
a
c
t
i
o
n
>
9
9
6
1
0
t
h
e
n
B
e
n
i
g
n
(
0
/
1
3
)
i
f
M
o
d
a
l
G
r
a
y
V
a
l
u
e
>
1
7
5
0
0
t
h
e
n
M
a
l
i
g
n
a
n
t
(
1
8
/
2
)
i
f
C
e
n
t
e
r
o
f
M
a
ss
a
≤
1
3
1
6
5
0
t
h
e
n
B
e
n
i
g
n
(
0
/
5
)
e
l
s
e
M
a
l
i
g
n
a
n
t
(
0
/
0
)
C
las
s
i
f
icatio
n
al
g
o
r
ith
m
(
KN
N,
DT
an
d
NB
)
is
u
s
ed
f
o
r
t
h
e
d
ev
elo
p
m
e
n
t
o
f
C
A
D
x
s
y
s
te
m
w
i
th
s
elec
ted
f
ea
tu
r
es
(
f
i
v
e
d
e
s
cr
ip
to
r
s
)
;
f
u
r
t
h
er
,
t
h
e
te
s
ti
n
g
is
p
er
f
o
r
m
ed
w
it
h
1
0
-
f
o
ld
cr
o
s
s
v
alid
atio
n
an
d
v
is
u
alize
d
u
s
i
n
g
R
o
C
c
u
r
v
e
a
s
s
h
o
w
n
i
n
Fi
g
u
r
e
5
.
DT
alg
o
r
ith
m
p
er
f
o
r
m
s
b
est
p
er
f
o
r
m
a
n
ce
w
h
e
n
co
m
p
ar
ed
to
th
e
o
th
er
t
w
o
al
g
o
r
ith
m
s
.
Fig
u
r
e
5
.
T
h
e
test
in
g
r
es
u
lt o
f
f
ea
t
u
r
e
u
s
e
:
s
lice,
in
teg
r
ated
d
en
s
it
y
,
A
r
ea
f
r
ac
tio
n
,
m
o
d
al
g
r
a
y
v
al
u
e
an
d
ce
n
ter
o
f
m
a
s
s
a
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.
8
,
No
.
1
,
Feb
r
u
ar
y
2
0
1
8
:
6
0
–
69
68
4
.
CO
NCLU
SI
O
N
B
ased
o
n
th
e
r
es
u
lts
o
f
e
x
p
er
i
m
en
ts
a
n
d
tes
ts
,
i
t
ca
n
b
e
co
n
clu
d
ed
t
h
at
d
ec
i
s
io
n
tr
ee
an
d
r
u
le
in
d
u
ctio
n
,
w
h
ic
h
i
s
o
n
e
o
f
t
h
e
m
i
n
i
n
g
alg
o
r
it
h
m
s
,
ca
n
b
e
u
s
ed
as
a
n
alter
n
at
iv
e
m
et
h
o
d
f
o
r
s
e
lectio
n
o
f
f
ea
t
u
r
es
o
n
t
h
e
m
a
m
m
o
g
r
a
m
i
m
ag
e
.
T
h
e
r
es
u
lts
o
f
f
ea
tu
r
e
s
elec
tio
n
co
n
d
u
c
ted
w
ith
ten
s
c
en
ar
io
s
o
b
tain
f
i
v
e
d
escr
ip
to
r
s
th
at
h
a
v
e
co
n
tr
ib
u
t
ed
in
th
e
m
a
m
m
o
g
r
a
m
i
m
ag
e
class
i
f
icatio
n
i
n
to
t
w
o
c
lass
e
s
,
b
en
ig
n
les
io
n
s
a
n
d
m
ali
g
n
a
n
t
le
s
io
n
s
.
T
h
e
b
est
class
i
f
icatio
n
r
esu
l
ts
b
ased
o
n
th
e
f
i
v
e
f
ea
tu
r
es
(
s
l
ice,
in
te
g
r
ated
d
en
s
it
y
,
A
r
ea
f
r
ac
tio
n
,
g
r
a
y
ca
p
ital
v
al
u
e,
ce
n
ter
o
f
m
as
s
)
ar
e
g
e
n
er
ate
d
b
y
t
h
e
d
ec
is
io
n
tr
ee
alg
o
r
i
th
m
w
it
h
ac
c
u
r
ac
y
,
s
en
s
iti
v
it
y
,
s
p
ec
if
ic
it
y
,
FP
R
a
n
d
T
P
R
o
f
9
3
.
1
8
%; 8
7
.
5
%; 3
.
8
9
%; 6
.
3
3
% a
n
d
9
2
.
1
1
%.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
is
r
esear
ch
is
s
u
p
p
o
r
ted
b
y
th
e
R
e
s
ea
r
ch
I
n
s
tit
u
te
a
n
d
C
o
m
m
u
n
it
y
Ser
v
ice
-
Su
n
a
n
Kal
ij
ag
a
State
I
s
la
m
ic
U
n
i
v
er
s
it
y
,
Yo
g
y
ak
ar
t
a,
I
n
d
o
n
esia
.
RE
F
E
R
E
NC
E
S
[1
]
Ba
d
a
n
P
e
n
e
li
ti
a
n
d
a
n
P
e
n
g
e
m
b
a
n
g
a
n
Ke
se
h
a
tan
,
“
Rise
t
Ke
se
h
a
ta
n
Da
sa
r”
,
Ke
me
n
ter
ia
n
k
e
sa
h
a
t
a
n
RI
,
p
p
.
8
5
-
86
,
2
0
1
3
.
[2
]
Am
e
rica
n
Co
ll
e
g
e
o
f
Ra
d
io
lo
g
y
,
“
A
C
R
BI
-
RAD
S
A
tl
a
s F
i
f
th
Ed
it
i
o
n
”
,
o
n
l
in
e
h
tt
p
s:/
/www
.
a
c
r.
o
rg
/
[3
]
S
.
Uy
u
n
a
n
d
S
.
Ha
rtati,
“
M
o
d
e
l
Ko
m
p
u
tas
i
P
e
n
e
n
t
u
a
n
F
a
k
to
r
R
e
sik
o
Ka
n
k
e
r
P
a
y
u
d
a
ra
Be
rd
a
sa
rk
a
n
P
o
la
d
a
n
P
e
rse
n
tas
e
De
n
sitas
M
a
m
o
g
ra
f
i”,
Do
c
to
ra
l
d
isse
rta
ti
o
n
,
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
,
2
0
1
4
.
[4
]
S
.
Uy
u
n
,
e
t
a
l.
,
“
Im
p
ro
v
e
m
e
n
t
o
f
S
a
m
p
le
S
e
lec
ti
o
n
:
A
Ca
sc
a
d
e
-
B
a
se
d
A
p
p
ro
a
c
h
f
o
r
L
e
sio
n
A
u
to
m
a
ti
c
De
tec
ti
o
n
,
”
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
S
c
ie
n
c
e
a
n
d
A
p
p
li
c
a
t
io
n
s,
v
o
l.
7
,
n
o
.
4
,
p
p
.
1
7
5
-
1
8
2
,
2
0
1
6
.
[5
]
R.
O.
Du
d
a
,
e
t
a
l.
,
“
P
a
tt
e
r
n
c
las
sifica
ti
o
n
”
,
Jo
h
n
W
il
e
y
&
S
o
n
s,
2
0
1
2
.
[6
]
Zh
e
n
g
,
e
t
a
l.
,
"
F
e
a
tu
re
S
e
lec
ti
o
n
M
e
th
o
d
Ba
se
d
o
n
Im
p
ro
v
e
d
Do
c
u
m
e
n
t
F
re
q
u
e
n
c
y
,
"
T
EL
KOM
NIKA
(
T
e
lec
o
mm
u
n
ica
ti
o
n
Co
mp
u
ti
n
g
El
e
c
tro
n
ics
a
n
d
C
o
n
tro
l)
,
v
o
l.
1
2
,
n
o
.
4
,
p
p
.
9
0
5
-
9
1
0
,
2
0
1
4
.
[7
]
M.
L
a
n
g
a
riza
d
e
h
a
n
d
R.
M
a
h
m
u
d
,
“
Bre
a
st
De
n
sity
Clas
sif
i
c
a
ti
o
n
Us
in
g
Histo
g
ra
m
-
Ba
s
e
d
F
e
a
tu
re
s
”,
Ira
n
i
a
n
J
o
u
rn
a
l
o
f
M
e
d
ica
l
I
n
f
o
rm
a
ti
c
s
,
v
o
l.
1
,
n
o
.
1
,
2
0
1
2
.
[8
]
D.
A
.
Ch
a
n
d
y
,
e
t
a
l.
,
“
Tex
tu
re
fe
a
tu
re
e
x
tra
c
ti
o
n
u
sin
g
g
ra
y
lev
e
l
sta
ti
stica
l
m
a
tri
x
f
o
r
c
o
n
ten
t
-
b
a
se
d
m
a
m
m
o
g
r
a
m
re
tri
e
v
a
l”,
M
u
lt
ime
d
ia
to
o
ls
a
n
d
a
p
p
li
c
a
ti
o
n
s
,
V
o
l.
7
2
,
No
.
2
,
p
p
.
2
0
1
1
-
2
0
2
4
,
2
0
1
4
.
[9
]
S
.
K
a
v
it
h
a
a
n
d
K.
K.
T
h
y
a
g
h
a
ra
jan
,
“
F
e
a
tu
re
s
b
a
se
d
m
a
m
m
o
g
r
a
m
i
m
a
g
e
c
las
si
f
ica
ti
o
n
u
sin
g
we
ig
h
ted
f
e
a
tu
re
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
”
.
In
Glo
b
a
l
T
re
n
d
s
in
In
fo
rm
a
t
io
n
S
y
ste
ms
a
n
d
S
o
ft
w
a
re
A
p
p
li
c
a
ti
o
n
s,
S
p
rin
g
e
r
Be
rl
i
n
He
id
e
lb
e
rg
,
p
p
.
3
2
0
-
3
2
9
,
2
0
1
2
.
[1
0
]
B.
S
u
re
n
d
iran
a
n
d
A
.
V
a
d
iv
e
l,
“
A
n
e
w
f
e
a
tu
re
r
e
d
u
c
ti
o
n
m
e
th
o
d
f
o
r
m
a
m
m
o
g
ra
m
m
a
ss
c
las
si
f
ic
a
ti
o
n
”
.
In
Co
n
tro
l
,
Co
mp
u
t
a
ti
o
n
a
n
d
I
n
fo
rm
a
ti
o
n
S
y
ste
ms
,
S
p
rin
g
e
r
Be
rli
n
He
id
e
lb
e
rg
,
p
p
.
3
0
3
-
3
1
1
,
2
0
1
1
.
[1
1
]
D.
A
.
Ch
a
n
d
y
,
D.
A
.
,
e
t
a
l.
,
“
Ne
ig
h
b
o
u
r
h
o
o
d
se
a
rc
h
f
e
a
tu
re
se
lec
ti
o
n
m
e
th
o
d
f
o
r
c
o
n
ten
t
-
b
a
se
d
m
a
m
m
o
g
ra
m
re
tri
e
v
a
l
”
.
M
e
d
ica
l
&
b
io
lo
g
ica
l
e
n
g
i
n
e
e
rin
g
&
c
o
mp
u
ti
n
g
,
v
o
l.
1
,
n
o
.
1
3
,
2
0
1
6
.
[1
2
]
Z.
W
a
n
g
,
e
t
a
l.
,
“
A
n
im
p
ro
v
e
d
b
ra
n
c
h
&
b
o
u
n
d
a
lg
o
rit
h
m
in
f
e
a
tu
re
se
lec
ti
o
n
”
.
In
I
n
ter
n
a
t
io
n
a
l
W
o
rk
sh
o
p
o
n
Ro
u
g
h
S
e
ts,
F
u
zz
y
S
e
ts,
D
a
ta
M
in
in
g
,
a
n
d
Gr
a
n
u
l
a
r
-
S
o
ft
C
o
mp
u
ti
n
g
,
S
p
rin
g
e
r
Be
rli
n
He
id
e
lb
e
rg
,
p
p
.
5
4
9
-
5
5
6
,
2
0
0
3
.
[1
3
]
C.
M
.
Nu
n
e
s,
e
t
a
l.
,
“
F
e
a
t
u
re
su
b
se
t
se
lec
ti
o
n
u
si
n
g
a
n
o
p
ti
m
ize
d
h
il
l
c
li
m
b
in
g
a
lg
o
rit
h
m
f
o
r
h
a
n
d
w
rit
ten
c
h
a
ra
c
ter
re
c
o
g
n
it
io
n
”
.
In
J
o
i
n
t
IA
PR
I
n
ter
n
a
ti
o
n
a
l
W
o
rk
sh
o
p
s
o
n
S
t
a
ti
stic
a
l
T
e
c
h
n
i
q
u
e
s
in
Pa
tt
e
rn
Rec
o
g
n
it
io
n
(
S
PR
)
a
n
d
S
tru
c
tu
r
a
l
a
n
d
S
y
n
ta
c
ti
c
P
a
tt
e
rn
Rec
o
g
n
it
io
n
(
S
S
PR
)
,
S
p
rin
g
e
r
Be
rli
n
He
id
e
l
b
e
rg
,
p
p
.
1
0
1
8
-
1
0
2
5
,
2
0
0
4
.
[1
4
]
M
in
a
rn
o
,
e
t
a
l.
,
"
I
m
a
g
e
Re
tri
e
v
a
l
Ba
se
d
o
n
M
u
lt
i
S
tru
c
t
u
re
Co
-
o
c
c
u
rre
n
c
e
De
sc
rip
to
r"
,
T
EL
KOM
NIKA
(
T
e
lec
o
mm
u
n
ica
ti
o
n
Co
mp
u
ti
n
g
El
e
c
tro
n
ics
a
n
d
C
o
n
tro
l),
v
o
l.
1
4
,
n
o
.
3
,
p
p
.
1
1
7
5
-
1
1
8
2
.
2
0
1
6
.
[1
5
]
G
.
A
lk
a
a
n
d
R.
P
a
tel.
"
P
e
rf
o
rm
a
n
c
e
A
n
a
l
y
sis
o
f
S
M
C
P
ro
to
c
o
ls
f
o
r
De
c
isio
n
T
re
e
Clas
sif
ica
ti
o
n
Ru
le
M
in
i
n
g
.
"
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
S
imu
l
a
ti
o
n
--
S
y
ste
ms
,
S
c
ien
c
e
&
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
13
,
n
o
.
6
,
2
0
1
2
.
[1
6
]
B.
Je
rz
y
,
e
t
a
l.
,
"
S
e
q
u
e
n
ti
a
l
c
o
v
e
rin
g
ru
le
in
d
u
c
ti
o
n
a
lg
o
rit
h
m
f
o
r
v
a
riab
le
c
o
n
siste
n
c
y
ro
u
g
h
se
t
a
p
p
ro
a
c
h
e
s."
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
s
,
v
o
l.
1
8
1
,
n
o
.
5
,
9
8
7
-
1
0
0
2
,
2
0
1
1
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Dr
.
S
h
o
fw
a
tu
l
‘Uy
u
n
,
S
.
T.
,
M
.
K
o
m
is
a
F
u
ll
T
i
m
e
L
e
c
tu
re
r
a
t
th
e
d
e
p
a
rtm
e
n
t
o
f
In
f
o
rm
a
ti
c
s
a
n
d
He
a
d
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
a
n
d
Da
tab
a
se
,
S
tate
Isla
m
ic
U
n
iv
e
rsity
(UIN
)
S
u
n
a
n
Ka
li
jag
a
in
Yo
g
y
a
k
a
rta,
In
d
o
n
e
sia
.
S
h
e
o
b
tai
n
e
d
h
e
r
Ba
c
h
e
lo
r
d
e
g
re
e
in
In
f
o
r
m
a
ti
c
s
f
ro
m
Isla
m
i
c
Un
iv
e
rsit
y
o
f
I
n
d
o
n
e
sia
.
S
h
e
re
c
e
iv
e
d
h
e
r
M
.
K
o
m
.
a
n
d
Dr
in
C
o
m
p
u
ter
S
c
ien
c
e
f
ro
m
th
e
G
a
d
jah
M
a
d
a
Un
iv
e
rsit
y
.
He
r
re
se
a
rc
h
in
tere
sts a
re
p
a
tt
e
rn
re
c
o
g
n
it
io
n
,
a
rti
f
icia
l
in
telli
g
e
n
c
e
a
n
d
m
e
d
ica
l
ima
g
e
p
ro
c
e
ss
in
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
F
ea
tu
r
e
S
elec
tio
n
Ma
mmo
g
r
a
m
b
a
s
ed
o
n
B
r
ea
s
t Ca
n
ce
r
Mi
n
in
g
(
S
h
o
fw
a
tu
l ‘
Uyu
n
)
69
Dr
.
d
r
.
Lin
a
C
h
o
r
id
a
h
,
S
p
.
R
a
d
(K
)
is
He
a
d
o
f
Ra
d
io
lo
g
y
De
p
a
rtme
n
t,
F
a
c
u
lt
y
o
f
M
e
d
icin
e
,
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
.
S
h
e
o
b
tai
n
e
d
h
e
r
Ba
c
h
e
l
o
r
d
e
g
re
e
(M
D/M
e
d
ica
l
D
o
c
to
r
),
Ra
d
i
o
lo
g
i
st
(S
p
.
Ra
d
)
,
Bre
a
st
Ima
g
i
n
g
C
o
n
s
u
l
ta
n
(
S
p
.
Ra
d
(K)
)
a
n
d
Dr
in
M
e
d
i
c
in
e
f
ro
m
F
a
c
u
lt
y
o
f
M
e
d
icin
e
th
e
G
a
d
jah
M
a
d
a
Un
iv
e
rsit
y
.
S
t
a
rti
n
g
in
2
0
0
4
a
s
th
e
f
ield
o
f
Ra
d
io
l
o
g
y
th
e
b
re
a
st
a
n
d
w
a
s
a
m
e
m
b
e
r
o
f
tea
m
On
c
o
lo
g
y
e
sp
e
c
iall
y
Bre
a
st
Ca
n
c
e
r
F
a
c
u
lt
y
o
f
M
e
d
icin
e
s T
h
e
G
a
d
jah
M
a
d
a
Un
iv
e
rsit
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.