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.
11
,
No
.
4
,
A
u
g
u
s
t
2021
,
p
p
.
3
0
5
9
~
3
0
6
9
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
1
1
i
4
.
pp
3
0
5
9
-
3
0
6
9
3059
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Brea
st cancer
diag
no
sis
sy
ste
m
usi
ng
hybrid su
ppo
r
t
v
ector
m
a
chine
-
a
rti
fic
i
a
l
neural ne
tw
o
rk
T
ze
Sh
eng
L
i
m
,
K
i
m
G
a
i
k
T
a
y
,
Audrey
H
uo
ng
,
Xia
ng
Y
a
ng
L
i
m
De
p
a
rt
m
e
n
t
o
f
El
e
c
tro
n
ic
E
n
g
in
e
e
rin
g
,
Un
iv
e
rsiti
T
u
n
Hu
ss
e
in
On
n
M
a
lay
sia
(U
T
HM)
,
M
a
la
y
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ju
l
20
,
2
0
2
0
R
ev
i
s
ed
Dec
13
,
2
0
2
0
A
cc
ep
ted
J
an
1
3
,
2
0
21
Bre
a
st
c
a
n
c
e
r
is
th
e
se
c
o
n
d
m
o
st
c
o
m
m
o
n
c
a
n
c
e
r
o
c
c
u
rrin
g
in
w
o
m
e
n
.
Early
d
e
tec
ti
o
n
th
r
o
u
g
h
m
a
m
m
o
g
ra
m
sc
re
e
n
in
g
c
a
n
sa
v
e
m
o
re
w
o
m
e
n
’s
li
v
e
s.
Ho
w
e
v
e
r,
e
v
e
n
se
n
io
r
ra
d
io
lo
g
ist
s
m
a
y
o
v
e
r
-
d
iag
n
o
se
th
e
c
li
n
ica
l
c
o
n
d
i
ti
o
n
.
M
a
c
h
in
e
lea
rn
in
g
(M
L
)
is
th
e
m
o
st
u
se
d
tec
h
n
i
q
u
e
in
t
h
e
d
iag
n
o
sis
o
f
c
a
n
c
e
r
to
h
e
l
p
re
d
u
c
e
h
u
m
a
n
e
rro
rs.
T
h
is
stu
d
y
is
a
i
m
e
d
to
d
e
v
e
lo
p
a
c
o
m
p
u
ter
-
a
id
e
d
d
e
tec
ti
o
n
(CA
D)
s
y
ste
m
u
sin
g
M
L
f
o
r
c
la
ss
i
f
ica
ti
o
n
p
u
rp
o
se
s.
In
th
is
w
o
rk
,
8
0
d
ig
it
a
l
m
a
m
m
o
g
r
a
m
s
o
f
n
o
rm
a
l
b
re
a
st
s,
4
0
o
f
b
e
n
ig
n
a
n
d
4
0
o
f
m
a
li
g
n
a
n
t
c
a
se
s
w
e
r
e
c
h
o
se
n
f
r
o
m
th
e
m
in
i
M
IA
S
d
a
tas
e
t.
T
h
e
se
i
m
a
g
e
s
w
e
r
e
d
e
n
o
ise
d
u
sin
g
m
e
d
ian
f
il
t
e
r
a
f
ter
th
e
y
w
e
r
e
s
e
g
m
e
n
ted
to
o
b
tain
a
re
g
io
n
o
f
in
tere
st
(ROI)
a
n
d
e
n
h
a
n
c
e
d
u
si
n
g
h
isto
g
ra
m
e
q
u
a
li
z
a
ti
o
n
.
T
h
is
w
o
rk
c
o
m
p
a
re
d
th
e
p
e
rf
o
r
m
a
n
c
e
o
f
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
(
A
N
N),
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(S
V
M
)
,
re
d
u
c
e
d
f
e
a
tu
re
s
o
f
S
V
M
a
n
d
t
h
e
h
y
b
rid
S
V
M
-
A
NN
f
o
r
c
la
ss
i
f
ica
ti
o
n
p
ro
c
e
ss
u
sin
g
th
e
sta
ti
stica
l
a
n
d
g
r
a
y
lev
e
l
c
o
-
o
c
c
u
rre
n
c
e
m
a
tri
x
(
GL
CM
)
f
e
a
tu
re
s
e
x
tra
c
te
d
f
ro
m
th
e
e
n
h
a
n
c
e
d
im
a
g
e
s.
It
is
f
o
u
n
d
th
a
t
th
e
h
y
b
rid
S
V
M
-
A
NN
g
iv
e
s
th
e
b
e
st
a
c
c
u
ra
c
y
o
f
9
9
.
4
%
a
n
d
1
0
0
%
in
d
if
fe
re
n
ti
a
ti
n
g
n
o
rm
a
l
f
ro
m
a
b
n
o
rm
a
l,
a
n
d
b
e
n
ig
n
f
ro
m
m
a
li
g
n
a
n
t
c
a
se
s,
re
sp
e
c
ti
v
e
l
y
.
T
h
is
h
y
b
rid
S
V
M
-
A
NN
m
o
d
e
l
wa
s
d
e
p
lo
y
e
d
in
d
e
v
e
lo
p
i
n
g
th
e
CA
D s
y
ste
m
w
h
ich
sh
o
w
e
d
re
lativ
e
l
y
g
o
o
d
a
c
c
u
ra
c
y
o
f
9
8
%
.
K
ey
w
o
r
d
s
:
A
N
N
B
r
ea
s
t c
an
ce
r
C
A
D
C
las
s
i
f
icatio
n
SVM
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Ki
m
Gai
k
T
ay
Dep
ar
t
m
en
t o
f
E
lectr
o
n
ic
E
n
g
in
ee
r
in
g
Un
i
v
er
s
iti T
u
n
H
u
s
s
ei
n
On
n
Ma
la
y
s
ia
(
UT
HM
)
8
6
4
0
0
P
a
r
it
R
aj
a,
B
atu
P
ah
at,
J
o
h
o
r
,
Ma
lay
s
ia
E
m
ail: ta
y
@
u
t
h
m
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
An
u
n
co
n
tr
o
lled
g
r
o
w
t
h
o
f
ce
lls
lead
s
to
th
e
f
o
r
m
a
tio
n
o
f
a
tu
m
o
r
,
w
h
ic
h
m
a
y
later
tr
an
s
f
o
r
m
i
n
to
ca
n
ce
r
.
I
f
it
h
ap
p
en
s
i
n
t
h
e
b
r
ea
s
t,
it
is
ter
m
ed
a
s
b
r
ea
s
t
ca
n
ce
r
.
A
t
u
m
o
r
ca
n
b
e
clas
s
i
f
i
ed
in
to
n
o
r
m
al
an
d
p
ath
o
lo
g
ical
(
o
r
ab
n
o
r
m
a
l)
.
An
ab
n
o
r
m
al
t
u
m
o
r
ca
n
b
e
o
f
n
o
n
-
ca
n
ce
r
o
u
s
(
b
en
i
g
n
)
o
r
ca
n
ce
r
o
u
s
(
m
a
lig
n
a
n
t)
.
Un
li
k
e
t
h
e
ca
s
e
o
f
t
h
e
m
ali
g
n
an
t
co
n
d
itio
n
,
a
b
en
i
g
n
t
u
m
o
r
is
lo
ca
lized
an
d
d
o
es
n
o
t
s
p
r
ea
d
to
s
u
r
r
o
u
n
d
in
g
ce
lls
o
r
o
r
g
an
s
.
B
r
ea
s
t
ca
n
ce
r
is
t
h
e
n
u
m
b
er
2
ca
u
s
e
o
f
m
o
r
t
alit
y
a
m
o
n
g
w
o
m
e
n
[
1
]
.
A
cc
o
r
d
in
g
to
t
h
e
Glo
b
al
C
an
ce
r
Statis
tics
2
0
1
8
,
b
r
ea
s
t
ca
n
ce
r
m
ad
e
u
p
ab
o
u
t
1
1
.
6
%
o
f
ca
n
ce
r
ca
s
es
i
n
b
o
th
s
ex
e
s
,
an
d
2
4
.
2
%
o
f
t
h
e
m
o
s
t
co
m
m
o
n
ca
n
ce
r
a
m
o
n
g
w
o
m
en
[2
]
.
B
r
ea
s
t
ca
n
ce
r
co
m
p
r
i
s
ed
ab
o
u
t
1
o
u
t
o
f
4
ca
n
ce
r
ca
s
es
d
iag
n
o
s
ed
a
m
o
n
g
w
o
m
e
n
[
2
]
.
A
cc
o
r
d
in
g
to
d
ata
co
llected
f
r
o
m
n
atio
n
al
ca
n
ce
r
r
eg
is
tr
y
(
N
C
R
)
co
n
d
u
cted
b
y
[
3
]
,
s
tag
e
1
to
s
ta
g
e
4
o
f
b
r
ea
s
t
ca
n
ce
r
h
as
t
h
e
b
est
s
u
r
v
iv
al
r
ate
o
f
8
1
.
7
%,
7
2
.
4
%,
3
9
.
9
%
an
d
1
2
.
9
%,
co
r
r
e
s
p
o
n
d
in
g
l
y
.
Stag
e
1
i
s
co
n
s
id
er
ed
as
th
e
b
eg
in
n
i
n
g
-
s
tag
e
w
h
er
ea
s
in
s
t
ag
e
4
ca
n
ce
r
m
eta
s
tasi
ze
s
to
o
th
er
o
r
g
an
s
/b
o
d
y
p
ar
ts
[
4
]
.
On
e
w
a
y
to
d
etec
t
b
r
ea
s
t
ca
n
c
er
ea
r
l
y
i
s
t
h
r
o
u
g
h
r
eg
u
lar
m
a
m
m
o
g
r
a
m
s
cr
ee
n
i
n
g
.
A
lo
w
-
d
o
s
e
X
-
r
a
y
is
u
s
ed
i
n
m
a
m
m
o
g
r
a
m
s
to
d
etec
t
ea
r
ly
m
etasta
s
es
i
n
b
r
ea
s
t
ca
n
ce
r
.
T
h
er
e
ar
e
th
r
ee
m
ain
t
y
p
es
o
f
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.
11
,
No
.
4
,
A
u
g
u
s
t 2
0
2
1
:
3
0
5
9
-
3069
3060
m
a
m
m
o
g
r
ap
h
y
n
a
m
e
l
y
s
cr
ee
n
-
f
il
m
i
n
g
,
d
i
g
ital
m
a
m
m
o
g
r
a
p
h
y
a
n
d
d
i
g
ital
b
r
ea
s
t
to
m
o
s
y
n
t
h
e
s
is
.
A
r
ec
en
t
s
tu
d
y
in
[
5
]
p
r
o
p
o
s
ed
a
co
m
b
i
n
atio
n
s
cr
ee
n
i
n
g
o
f
d
ig
ital
m
a
m
m
o
g
r
ap
h
y
an
d
d
ig
i
tal
b
r
ea
s
t
to
m
o
s
y
n
t
h
esi
s
f
o
r
th
e
d
iag
n
o
s
i
s
.
On
ce
ca
n
ce
r
is
d
etec
ted
,
tr
ea
tm
e
n
t
ca
n
b
e
g
iv
en
ea
r
l
y
to
s
to
p
o
r
s
lo
w
d
o
w
n
th
e
s
p
r
ea
d
o
f
th
e
ca
n
ce
r
o
u
s
(
m
ali
g
n
a
n
t)
ce
lls
.
Ma
m
m
o
g
r
a
m
s
cr
ee
n
i
n
g
is
an
ea
r
l
y
s
tep
in
b
r
ea
s
t
ca
n
ce
r
d
etec
tio
n
b
ef
o
r
e
g
o
in
g
i
n
to
d
iag
n
o
s
is
.
I
t
w
a
s
r
ep
o
r
ted
in
[
6
]
th
at
ar
o
u
n
d
6
5
%
–
9
0
%
o
f
p
o
s
iti
v
el
y
d
ia
g
n
o
s
ed
b
r
ea
s
t
m
a
m
m
o
g
r
a
m
s
w
h
ic
h
,
a
f
ter
u
n
d
er
g
o
i
n
g
a
b
io
p
s
y
,
ar
e
co
n
f
ir
m
ed
as
n
eg
a
tiv
e;
t
h
i
s
s
it
u
atio
n
is
k
n
o
w
n
a
s
f
al
s
e
p
o
s
iti
v
e
(
FP
)
.
FP
is
a
t
est
r
es
u
lt
i
n
w
h
ic
h
th
e
m
ed
ic
al
p
er
s
o
n
n
el
o
r
r
ad
io
lo
g
is
ts
w
r
o
n
g
l
y
d
iag
n
o
s
ed
t
h
e
p
r
esen
ce
o
f
a
p
ar
ticu
lar
c
o
n
d
itio
n
o
r
attr
ib
u
te
(
d
is
ea
s
e)
w
h
e
n
t
h
e
p
er
s
o
n
d
o
es n
o
t
h
av
e
i
t.
I
n
t
h
is
ca
s
e,
p
atien
ts
s
u
f
f
er
ed
f
r
o
m
u
n
n
ec
e
s
s
ar
y
p
ain
,
r
is
k
a
n
d
co
s
t
o
f
b
io
p
s
y
p
r
o
ce
d
u
r
e
f
o
r
s
u
s
p
ec
ted
lesi
o
n
s
.
A
n
o
th
er
r
ep
o
r
t
in
[
7
]
s
h
o
w
ed
t
h
at
6
5
%
-
7
5
%
o
f
p
o
s
i
tiv
e
b
r
ea
s
t
ca
n
ce
r
ca
s
es
ar
e
u
n
ab
le
to
b
e
d
etec
ted
d
u
e
to
th
e
d
if
f
icu
lt
y
i
n
i
n
ter
p
r
etin
g
m
a
m
m
o
g
r
a
m
s
,
e
v
e
n
f
o
r
ex
p
er
ien
ce
d
r
ad
io
lo
g
is
t
s
.
T
h
is
s
it
u
atio
n
is
co
n
s
id
er
ed
as
f
al
s
e
n
eg
ati
v
e
(
FN)
,
w
h
ich
r
ec
o
g
n
ized
n
o
r
m
a
lit
y
o
r
th
e
ab
s
en
ce
o
f
a
p
ar
ticu
lar
co
n
d
itio
n
o
r
d
is
ea
s
e
ev
e
n
w
h
e
n
th
e
p
er
s
o
n
is
w
it
h
th
e
d
is
ea
s
e
.
T
h
e
in
cid
en
ce
o
f
FN
ca
u
s
e
s
p
atien
t
s
to
m
is
s
th
e
g
o
ld
en
o
p
p
o
r
tu
n
it
y
to
f
i
g
h
t
b
r
ea
s
t
ca
n
ce
r
,
w
h
ich
m
a
y
b
e
lif
e
-
th
r
ea
te
n
i
n
g
[
8
]
.
Sev
er
al
co
m
p
u
ter
-
a
id
ed
d
esig
n
(
C
A
D)
d
etec
tio
n
s
y
s
te
m
s
h
av
e
b
ee
n
u
s
ed
b
y
r
ad
io
lo
g
i
s
ts
to
d
etec
t
b
r
ea
s
t
ca
n
ce
r
,
b
u
t th
e
y
h
a
v
e
y
et
to
r
ed
u
ce
th
e
r
ate
o
f
f
alse
-
p
o
s
iti
v
e
ca
s
es.
T
h
e
in
teg
r
atio
n
o
f
in
f
o
r
m
ati
o
n
an
d
co
m
m
u
n
icatio
n
tech
n
o
lo
g
ies
[
9
]
,
b
ig
d
ata
[
1
0
,
1
1
]
,
cy
b
er
-
p
h
y
s
ical
s
y
s
te
m
(
C
P
S)
[
1
2
]
an
d
m
ac
h
i
n
e
l
ea
r
n
i
n
g
(
ML
)
ca
n
h
elp
in
d
iag
n
o
s
i
s
an
d
p
r
o
g
n
o
s
is
o
f
b
r
ea
s
t
ca
n
ce
r
.
B
ig
d
ata
is
r
ef
er
r
ed
to
as
a
lar
g
e
v
o
lu
m
e
o
f
d
ata
w
h
ic
h
is
e
x
p
o
n
en
t
iall
y
g
r
o
w
in
g
[
1
3
]
.
B
ig
d
ata
in
th
i
s
s
tu
d
y
ca
n
b
e
o
b
tain
ed
f
r
o
m
m
ed
ical
s
cr
ee
n
i
n
g
,
p
at
h
o
lo
g
ical
d
ata
[
1
4
]
o
r
o
n
lin
e
m
ed
ical
d
atab
as
e.
C
P
S
is
a
p
h
y
s
ical
co
m
p
o
n
e
n
t
th
a
t
is
li
n
k
ed
w
i
t
h
t
h
e
s
i
m
u
lat
io
n
m
o
d
el,
w
h
il
e
ML
is
a
s
t
u
d
y
o
f
co
m
p
u
te
r
alg
o
r
ith
m
s
to
d
o
p
r
ed
ictio
n
,
p
atter
n
r
ec
o
g
n
itio
n
a
n
d
clas
s
if
icatio
n
.
T
h
e
m
an
ip
u
lat
io
n
o
f
b
ig
d
ata
u
s
i
n
g
a
n
o
p
ti
m
al
M
L
al
g
o
r
ith
m
i
n
t
h
e
d
ev
elo
p
m
e
n
t
o
f
a
C
A
D
s
y
s
te
m
ca
n
h
elp
r
ad
io
lo
g
is
ts
i
n
i
n
ter
p
r
etin
g
t
h
e
d
iag
n
o
s
is
o
f
ca
n
ce
r
,
an
d
r
ed
u
ce
th
e
m
o
r
tali
t
y
r
ate.
T
h
er
e
ar
e
s
u
p
er
v
is
ed
an
d
u
n
s
u
p
er
v
is
ed
lear
n
i
n
g
in
M
L
.
Su
p
er
v
is
ed
lear
n
in
g
w
o
u
ld
s
u
p
p
l
y
lab
eled
in
p
u
t
a
n
d
o
u
tp
u
t
f
o
r
th
e
m
ac
h
i
n
e
to
d
o
p
r
ed
ictio
n
o
r
class
if
ic
atio
n
,
w
h
ile
u
n
s
u
p
er
v
is
ed
lear
n
in
g
o
n
l
y
s
u
p
p
lies
lab
eled
in
p
u
t
to
th
e
m
ac
h
i
n
e
.
I
n
th
e
latter
s
tr
ate
g
y
,
t
h
e
m
ac
h
in
e
w
o
u
ld
lear
n
f
r
o
m
t
h
e
ex
p
er
ien
ce
i
n
it
s
class
i
f
icatio
n
.
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
s
(
A
N
N)
an
d
s
u
p
p
o
r
t
v
e
cto
r
m
ac
h
i
n
e
(
S
VM
)
ar
e
t
w
o
p
o
p
u
lar
ex
a
m
p
le
s
o
f
s
u
p
er
v
i
s
ed
ML
al
g
o
r
ith
m
s
.
A
N
N
is
i
n
s
p
ir
ed
b
y
n
et
w
o
r
k
s
o
f
h
u
m
an
b
r
ain
n
e
u
r
o
n
s
.
A
c
o
llectio
n
o
f
n
eu
r
o
n
f
o
r
m
s
a
la
y
er
.
AN
N
co
n
s
is
ts
o
f
a
n
i
n
p
u
t
la
y
er
,
h
i
d
d
en
la
y
er
a
n
d
o
u
tp
u
t
la
y
er
.
T
h
e
h
id
d
en
la
y
er
h
as
a
n
ac
ti
v
a
tio
n
f
u
n
ctio
n
t
h
at
co
n
n
ec
t
s
t
h
e
i
n
p
u
t
la
y
er
w
it
h
th
e
o
u
tp
u
t
la
y
er
.
E
ac
h
n
o
d
e
X
i
in
t
h
e
i
n
p
u
t
la
y
er
h
a
s
it
s
w
ei
g
h
t,
W
i
.
S
u
m
m
at
io
n
o
f
a
p
r
o
d
u
ct
o
f
ea
ch
n
o
d
e
w
it
h
its
w
e
ig
h
t
is
ca
lled
a
n
et
∑
[
1
5
]
.
T
h
e
n
et
is
in
p
u
tted
in
an
ac
tiv
atio
n
f
u
n
ctio
n
to
g
i
v
e
a
p
r
ed
ictio
n
o
r
class
if
icatio
n
a
s
f
o
llo
w
s
:
=
(
∑
)
SVM
ca
n
p
er
f
o
r
m
p
atter
n
r
ec
o
g
n
itio
n
,
clas
s
i
f
icatio
n
an
d
p
r
ed
ictio
n
b
ased
o
n
s
tati
s
tical
le
ar
n
in
g
a
n
d
th
e
p
r
in
cip
le
o
f
s
tr
u
ct
u
r
al
r
is
k
m
i
n
i
m
izat
io
n
.
T
h
e
SVM
was
in
v
en
ted
b
y
Vap
n
i
k
w
ith
c
o
llea
g
u
e
s
at
A
T
&
T
B
ell
L
ab
o
r
ato
r
ies
to
s
ea
r
ch
f
o
r
o
p
tim
al
h
y
p
er
p
lan
e
(
0
+
0
=
0
)
th
at
s
ep
ar
ates
a
s
et
o
f
tr
ai
n
i
n
g
d
ata
(
1
,
1
)
,
…
(
,
)
,
w
it
h
a
m
ax
i
m
u
m
m
ar
g
i
n
[
1
6
]
w
h
er
e
e
v
er
y
is
r
ea
l
p
atter
n
an
d
is
eith
er
1
o
r
-
1
.
W
h
en
=
1
,
th
e
r
ea
l
p
atter
n
is
i
n
cla
s
s
1
,
w
h
ile
=
−
1
,
th
e
r
ea
l p
atter
n
is
i
n
clas
s
2
.
T
h
e
r
ea
l p
atter
n
is
lin
ea
r
l
y
s
ep
ar
ab
le
if
⃗
⃗
∙
+
≥
1
,
if
=
1
⃗
⃗
∙
+
≤
−
1
,
if
=
−
1
T
h
e
ab
o
v
e
in
eq
u
al
it
y
ca
n
b
e
w
r
itte
n
a
s
(
⃗
⃗
∙
+
)
≥
1
,
=
1
…
.
T
h
e
o
p
ti
m
al
h
y
p
e
r
p
lan
e
ca
n
b
e
f
o
u
n
d
b
y
m
i
n
i
m
izi
n
g
|
w|
s
u
b
j
ec
t to
(
⃗
⃗
∙
+
)
≥
1
,
=
1
…
.
Hen
ce
,
th
e
li
n
ea
r
clas
s
i
f
ier
o
f
t
h
e
o
p
ti
m
al
h
y
p
er
p
lan
e
i
s
g
i
v
e
n
b
y
:
→
(
∙
+
)
Fo
u
r
m
o
d
els
(
b
ac
k
p
r
o
p
ag
atio
n
alg
o
r
it
h
m
,
r
ad
ial
b
asi
s
f
u
n
c
tio
n
n
et
w
o
r
k
s
,
lear
n
i
n
g
v
ec
to
r
q
u
an
tizat
io
n
(
L
V
Q)
an
d
co
m
p
etitiv
e
lear
n
in
g
n
et
w
o
r
k
)
o
f
th
e
A
NN
al
g
o
r
ith
m
s
w
er
e
e
m
p
l
o
y
ed
o
n
w
is
co
n
s
i
n
b
r
ea
s
t
ca
n
ce
r
d
atas
et
(
W
B
C
D)
in
[
1
7
]
.
T
h
e
L
VQ
a
lg
o
r
it
h
m
w
a
s
co
n
c
lu
d
ed
as
th
e
b
est
m
o
d
el
w
it
h
9
5
.
8
2
%
ac
cu
r
ac
y
[
1
7
]
.
T
h
e
W
B
C
D
d
a
taset
co
n
ta
i
n
s
6
9
9
s
a
m
p
les
o
f
b
io
p
s
ies,
w
h
ich
co
m
p
r
i
s
es
o
f
4
5
8
m
ali
g
n
a
n
t
an
d
2
4
1
b
en
ig
n
ca
s
es
w
it
h
9
f
ea
t
u
r
es.
No
n
et
h
eles
s
,
t
h
is
d
ataset
h
as
1
6
m
i
s
s
i
n
g
ca
s
e
s
,
t
h
u
s
it
r
ed
u
ce
s
to
6
8
3
ca
s
e
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
B
r
ea
s
t c
a
n
ce
r
d
ia
g
n
o
s
is
s
ystem
u
s
in
g
h
yb
r
id
s
u
p
p
o
r
t v
ec
to
r
m
a
ch
in
e
-
a
r
tifi
cia
l n
eu
r
a
l
...
(
Tz
e
S
h
en
g
Lim)
3061
A
s
t
u
d
y
i
n
[
1
8
]
ap
p
lied
th
e
n
eu
r
al
n
et
w
o
r
k
p
atter
n
r
ec
o
g
n
itio
n
to
o
l
in
M
A
T
L
A
B
o
n
b
r
ea
s
t
ca
n
ce
r
d
ata
av
ailab
le
i
n
t
h
e
M
A
T
L
A
B
.
T
h
is
d
atab
ase
h
as
6
9
9
b
io
p
s
ied
s
a
m
p
le
s
,
ea
ch
w
i
th
9
f
ea
t
u
r
es
,
an
d
th
e
y
o
b
tain
ed
an
ac
cu
r
ac
y
o
f
9
7
.
6
%.
SVM
h
as
b
ee
n
b
r
o
ad
l
y
e
m
p
lo
y
ed
i
n
t
h
e
c
lass
if
ica
tio
n
o
f
ca
n
ce
r
d
u
e
to
it
s
h
i
g
h
ac
cu
r
ac
y
[
1
9
]
.
I
n
a
s
tu
d
y
d
o
n
e
b
y
[
2
0
]
o
n
W
B
C
D
,
it
is
s
h
o
w
n
th
at
SVM
g
i
v
es
9
7
.
2
%
ac
cu
r
ac
y
.
Ak
a
y
[
2
1
]
u
tili
ze
d
F
-
s
co
r
e
to
ch
o
o
s
e
s
i
g
n
i
f
ican
t
f
ea
tu
r
e
s
,
SVM
o
n
W
B
C
D
a
n
d
o
b
tain
ed
9
9
.
5
1
%
in
th
e
clas
s
if
icat
io
n
ac
cu
r
ac
y
.
T
h
e
r
esear
ch
er
[
2
2
]
u
tili
ze
d
K
-
m
ea
n
s
-
SVM
an
d
r
ed
u
ce
d
3
2
f
ea
t
u
r
es
to
6
o
n
W
B
C
D
,
w
h
ic
h
s
h
o
w
ed
a
class
i
f
icatio
n
ac
cu
r
ac
y
o
f
9
7
.
3
8
%.
C
h
tih
r
ak
k
a
n
n
a
n
[
2
3
]
u
s
ed
X
-
r
a
y
m
a
m
m
o
g
r
a
m
,
i
m
ag
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es,
w
av
e
let
tr
a
n
s
f
o
r
m
a
n
d
G
L
C
M
f
ea
t
u
r
es
e
x
t
r
ac
tio
n
i
n
t
h
eir
cla
s
s
i
f
icat
io
n
.
T
h
e
y
co
m
p
ar
ed
class
i
f
icatio
n
r
es
u
lt
s
f
r
o
m
ANN,
SVM,
K
-
n
ea
r
es
t
n
ei
g
h
b
o
r
(
KNN)
an
d
d
ee
p
n
eu
r
al
n
e
t
w
o
r
k
(
DNN)
.
T
h
e
y
co
n
clu
d
ed
th
at
DN
N
g
i
v
es t
h
e
b
est ac
cu
r
ac
y
o
f
9
6
.
3
%.
A
co
m
p
ar
is
o
n
o
f
th
e
p
er
f
o
r
m
an
ce
o
f
A
NN
an
d
SVM
u
s
in
g
6
4
b
en
ig
n
,
5
1
m
ali
g
n
a
n
t
an
d
7
0
n
o
r
m
a
l
i
m
a
g
es
r
a
n
d
o
m
l
y
c
h
o
s
e
n
f
r
o
m
t
h
e
MI
AS
d
ataset
w
as
ca
r
r
ied
o
u
t
i
n
[
2
4
]
.
SVM
y
ield
s
9
5
%
ac
cu
r
ac
y
as
co
m
p
ar
ed
to
A
NN
(
9
3
%).
A
b
r
ea
s
t c
an
ce
r
clas
s
i
f
icatio
n
u
s
in
g
W
B
C
D
an
d
M
L
al
g
o
r
ith
m
i
n
[
2
5
]
p
r
o
v
es
KNN
y
ield
s
9
7
.
5
1
%
ac
cu
r
ac
y
a
s
co
m
p
ar
ed
to
9
6
.
1
9
%
g
iv
e
n
b
y
t
h
e
n
ai
v
e
b
a
y
e
s
(
NB
)
clas
s
i
f
ie
r
.
A
co
m
p
ar
is
o
n
o
f
f
o
u
r
M
L
al
g
o
r
ith
m
s
n
a
m
el
y
SVM,
lo
g
i
s
tic
r
eg
r
e
s
s
io
n
(
L
R
)
,
NB
an
d
r
an
d
o
m
f
o
r
est
(
R
F
)
o
n
W
B
C
D
in
[
2
6
]
s
h
o
w
ed
th
at
R
F
g
i
v
es t
h
e
b
est
class
i
f
icatio
n
ac
cu
r
ac
y
o
f
9
9
.
7
6
%.
O
m
o
n
d
ia
g
b
e
et
al
.
[
2
7
]
ex
a
m
i
n
ed
th
e
clas
s
i
f
icatio
n
p
er
f
o
r
m
an
ce
o
n
SVM
u
s
in
g
a
r
ad
ial
b
asis
k
er
n
e
l
,
A
N
N
an
d
NB
o
n
W
B
C
D.
T
h
e
y
later
s
elec
ted
u
s
e
f
u
l
f
ea
t
u
r
es
u
s
i
n
g
co
r
r
elatio
n
-
b
ased
f
ea
tu
r
e
s
elec
tio
n
(
C
FS
)
an
d
r
ec
u
r
s
i
v
e
f
ea
tu
r
e
eli
m
i
n
atio
n
(
R
FE)
.
P
r
in
cip
al
co
m
p
o
n
en
t
an
a
l
y
s
is
(
P
C
A
)
an
d
lin
ea
r
d
is
cr
i
m
i
n
a
n
t
an
al
y
s
is
(
L
D
A
)
w
er
e
ad
o
p
ted
to
elim
i
n
ate
les
s
u
s
ef
u
l
f
ea
tu
r
es.
SVM
-
L
D
A
w
a
s
ch
o
s
e
n
as
th
e
b
est
class
if
ier
,
w
h
ic
h
r
esu
l
ts
i
n
9
8
.
8
2
%
ac
cu
r
ac
y
.
I
n
[
2
8
]
,
1
1
o
u
t
o
f
1
8
7
9
o
n
li
n
e
ar
ticles
w
er
e
s
elec
ted
,
an
d
th
e
p
er
f
o
r
m
a
n
c
e
o
f
f
i
v
e
d
if
f
er
en
t
M
L
al
g
o
r
ith
m
s
n
a
m
e
l
y
A
N
N,
SVM,
KN
N,
NB
an
d
d
ec
is
io
n
tr
ee
(
D
T
)
o
n
b
r
ea
s
t
c
an
ce
r
class
i
f
icatio
n
w
er
e
in
v
est
ig
ate
d
.
I
t w
a
s
co
n
cl
u
d
ed
th
at
SVM
o
u
tp
er
f
o
r
m
ed
th
e
o
t
h
er
s
.
I
n
an
o
t
h
er
w
o
r
k
,
ei
g
h
t
M
L
a
l
g
o
r
ith
m
s
w
er
e
ad
o
p
ted
o
n
W
B
C
D
in
[
2
9
]
.
T
h
ese
alg
o
r
ith
m
s
ar
e
L
R
,
b
ay
e
s
n
et
w
o
r
k
(
B
N)
,
m
u
l
tila
y
er
p
er
ce
p
tr
o
n
(
ML
P
)
,
s
eq
u
en
tial
m
i
n
i
m
al
o
p
ti
m
izat
io
n
(
S
MO
)
,
J
4
8
d
ec
is
io
n
tr
ee
,
NB
an
d
in
s
ta
n
ce
-
b
a
s
ed
lear
n
er
(
I
B
K)
.
I
t
w
a
s
co
n
cl
u
d
ed
th
at
B
N
g
iv
e
s
9
7
.
1
4
%
ac
cu
r
ac
y
.
Si
m
ilar
l
y
,
r
ec
en
tl
y
i
n
[
3
0
]
,
th
r
ee
ML
alg
o
r
ith
m
s
:
L
R
,
R
F,
an
d
DT
w
er
e
p
er
f
o
r
m
ed
o
n
W
B
C
D
an
d
it
w
as
s
h
o
w
ed
th
at
L
R
y
ield
s
t
h
e
b
est
ac
cu
r
ac
y
o
f
9
9
.
3
0
%.
Oth
er
r
esear
ch
er
s
[
3
1
]
p
r
o
p
o
s
ed
a
b
r
ea
s
t
ca
n
ce
r
d
iag
n
o
s
i
s
an
d
p
r
ed
ictio
n
s
y
s
te
m
u
s
in
g
th
e
b
est
p
r
ed
ictiv
e
m
o
d
el
f
r
o
m
t
h
e
6
M
L
al
g
o
r
ith
m
s
n
a
m
el
y
NB
,
R
F,
A
NN,
KNN,
SVM
an
d
DT
.
Gh
ar
ib
d
o
u
s
ti
[
3
2
]
ap
p
lied
P
C
A
,
D
A
a
n
d
L
R
f
o
r
f
ea
t
u
r
e
r
ed
u
ctio
n
to
g
et
h
er
w
ith
SVM,
NB
,
DT
,
L
R
an
d
ANN.
T
h
e
y
p
r
o
v
ed
th
at
D
A
-
L
R
p
er
f
o
r
m
s
th
e
b
est.
E
v
en
t
h
o
u
g
h
th
e
ab
o
v
e
-
m
en
tio
n
ed
p
r
ev
io
u
s
b
r
ea
s
t
ca
n
c
er
class
if
icatio
n
u
s
i
n
g
M
L
tech
n
iq
u
e
s
s
h
o
w
ed
p
r
o
m
i
s
i
n
g
c
la
s
s
i
f
icati
o
n
p
er
f
o
r
m
an
ce
,
t
h
o
s
e
w
o
r
k
s
w
er
e
co
n
d
u
cted
o
n
a
W
B
C
D
d
ataset,
w
h
ic
h
w
as
f
r
o
m
b
io
p
s
ies
o
f
ab
n
o
r
m
al
ce
l
ls
an
d
n
o
t
f
r
o
m
d
ig
i
tal
m
a
m
m
o
g
r
a
m
s
.
B
esid
es,
t
h
ese
cla
s
s
i
f
icatio
n
w
o
r
k
s
w
er
e
m
ai
n
l
y
to
d
i
f
f
er
e
n
tiate
b
et
w
ee
n
b
en
ig
n
a
n
d
m
ali
g
n
a
n
t
ca
s
e
s
.
I
n
t
h
i
s
p
ap
er
,
w
e
m
ad
e
an
ex
t
r
a
ef
f
o
r
t
to
p
r
o
v
id
e
a
class
i
f
icatio
n
o
f
n
o
r
m
a
l
-
ab
n
o
r
m
al,
a
n
d
b
et
w
ee
n
b
en
i
g
n
an
d
m
ali
g
n
a
n
t
ca
s
es
f
r
o
m
d
i
g
ital
m
a
m
m
o
g
r
a
m
s
.
O
n
to
p
o
f
th
at,
p
r
ev
io
u
s
r
esear
ch
er
s
h
ad
n
o
t
test
ed
th
eir
alg
o
r
ith
m
s
o
n
n
e
w
/
u
n
s
ee
n
i
m
a
g
e
s
.
Fo
r
th
is
p
u
r
p
o
s
e,
a
ML
-
b
ased
C
AD
w
as
d
e
v
elo
p
ed
in
th
i
s
w
o
r
k
to
cla
s
s
i
f
y
if
a
d
i
g
ital
m
a
m
m
o
g
r
a
m
is
n
o
r
m
al,
b
en
ig
n
o
r
m
ali
g
n
a
n
t.
A
m
i
n
i
-
MI
A
S d
ata
b
ase
th
at
co
n
s
is
t
s
o
f
3
2
2
d
ig
it
al
m
a
m
m
o
g
r
a
m
s
o
f
n
o
r
m
al,
b
en
ig
n
a
n
d
m
ali
g
n
an
t
ca
s
es
w
as
c
h
o
s
en
.
A
co
m
p
ar
is
o
n
o
f
th
e
p
er
f
o
r
m
a
n
ce
o
f
SV
M
,
A
NN,
SV
M
w
ith
r
ed
u
ce
d
f
ea
t
u
r
es
an
d
h
y
b
r
id
SVM
-
ANN
clas
s
i
f
icatio
n
o
f
d
ig
ital
m
a
m
m
o
g
r
a
m
s
w
er
e
in
v
esti
g
ated
u
s
i
n
g
8
0
i
m
a
g
es
o
f
n
o
r
m
a
l
b
r
ea
s
t,
4
0
b
en
ig
n
a
n
d
4
0
m
al
ig
n
a
n
t
r
a
n
d
o
m
l
y
c
h
o
s
en
m
a
m
m
o
g
r
a
m
s
.
All
t
h
ese
w
o
r
k
s
w
er
e
ac
co
m
p
li
s
h
ed
u
s
in
g
MA
T
L
A
B
2019b
.
A
NN
an
d
SVM
w
er
e
ch
o
s
en
as
t
h
e
y
ar
e
th
e
m
o
s
t
co
m
m
o
n
l
y
u
s
ed
ML
tech
n
iq
u
e
s
to
p
r
ed
ict
ca
n
ce
r
[
2
0
]
.
I
t
m
u
s
t
al
s
o
b
e
m
e
n
tio
n
ed
th
at,
as
o
f
to
d
ay
’
s
d
ate,
n
o
t
m
u
ch
w
o
r
k
s
c
an
b
e
f
o
u
n
d
o
n
th
e
u
s
e
o
f
t
h
e
SV
M
class
if
icatio
n
to
o
l
in
MA
T
L
A
B
.
T
h
e
b
est
n
et
m
o
d
el
w
as
d
ep
lo
y
ed
f
o
r
u
s
e
in
t
h
e
d
ev
elo
p
ed
C
A
D
s
y
s
te
m
(
u
s
in
g
M
A
T
L
A
B
g
r
ap
h
ical
u
s
er
in
ter
f
ac
e,
GUI
p
r
o
g
r
a
m
)
to
class
if
y
i
f
a
m
a
m
m
o
g
r
a
m
is
n
o
r
m
al,
b
en
i
g
n
o
r
m
a
lig
n
a
n
t.
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
C
A
D
p
r
o
g
r
am
w
a
s
th
e
n
test
ed
w
it
h
an
o
t
h
er
1
0
0
n
e
w
i
m
a
g
es.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
is
s
tu
d
y
co
n
s
i
s
ts
o
f
t
w
o
p
h
ases
:
t
h
e
d
ata
tr
ain
i
n
g
p
h
a
s
e
a
n
d
th
e
d
ev
elo
p
m
e
n
t
o
f
t
h
e
C
A
D
s
y
s
te
m
f
o
r
f
ield
ap
p
licatio
n
u
s
in
g
M
A
T
L
A
B
R
2
0
1
9
b
.
T
h
e
d
ata
tr
ain
i
n
g
p
h
ase
i
s
s
h
o
w
n
in
Fi
g
u
r
e
1.
I
n
th
e
d
ata
tr
ain
i
n
g
p
h
ase,
t
h
e
1
6
0
m
a
m
m
o
g
r
a
m
s
(
8
0
n
o
r
m
al,
4
0
b
en
i
g
n
an
d
4
0
m
ali
g
n
an
t)
r
an
d
o
m
l
y
ch
o
s
en
f
r
o
m
m
i
n
i
-
MI
A
S
w
er
e
f
ir
s
t
s
eg
m
e
n
ted
to
lo
ca
te
th
e
r
eg
io
n
o
f
in
ter
es
t
(
R
OI
)
.
L
ater
th
e
R
OI
w
a
s
p
r
ep
r
o
ce
s
s
ed
u
s
i
n
g
m
ed
ian
f
ilter
i
n
g
to
r
e
m
o
v
e
th
e
n
o
is
e
a
n
d
en
h
a
n
ce
d
u
s
i
n
g
h
is
to
g
r
a
m
eq
u
a
lizatio
n
.
Ne
x
t,
s
t
atis
tical
an
d
g
r
a
y
lev
el
co
-
o
cc
u
r
r
en
ce
m
atr
i
x
(
GL
C
M)
f
ea
tu
r
e
s
o
f
th
ese
e
n
h
a
n
ce
d
R
OI
im
a
g
es
w
er
e
ex
tr
ac
te
d
b
ef
o
r
e
th
ey
w
er
e
u
s
ed
in
t
h
e
n
et
m
o
d
el
tr
ain
in
g
s
tag
e.
T
h
e
tr
ain
ed
n
et
w
o
u
ld
t
h
en
b
e
d
ep
lo
y
ed
f
o
r
u
s
e
i
n
th
e
C
A
D
s
y
s
te
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.
11
,
No
.
4
,
A
u
g
u
s
t 2
0
2
1
:
3
0
5
9
-
3069
3062
Fig
u
r
e
1
.
P
r
ep
a
r
atio
n
o
f
d
ata
f
o
r
tr
ain
in
g
o
f
M
L
m
o
d
els
T
h
e
s
eg
m
e
n
tat
io
n
w
as
b
ased
o
n
th
e
g
r
o
u
n
d
tr
u
t
h
p
r
o
v
id
ed
b
y
th
e
d
atab
ase
f
o
r
an
ab
n
o
r
m
a
l
ca
s
e,
an
d
b
y
lo
ca
ti
n
g
th
e
r
eg
io
n
o
f
Ma
m
m
o
g
r
a
m
s
th
at
w
as
co
n
s
id
er
ed
as
t
u
m
o
r
-
f
r
ee
f
o
r
t
h
e
n
o
r
m
al
ca
s
e
.
T
h
er
e
ar
e
a
to
tal
o
f
2
1
f
ea
t
u
r
es
g
i
v
en
f
r
o
m
f
iv
e
s
ta
tis
t
ical
f
ea
t
u
r
es
n
a
m
el
y
m
ea
n
,
v
ar
ia
n
ce
,
s
k
e
wn
es
s
,
k
u
r
to
s
i
s
,
a
n
d
en
tr
o
p
y
,
an
d
f
o
u
r
tex
t
u
r
e
f
ea
t
u
r
es
o
f
(
G
L
C
M)
(
i.e
.
,
co
n
tr
as
t,
en
er
g
y
,
co
r
r
elatio
n
a
n
d
h
o
m
o
g
e
n
eit
y
,
a
n
d
at
4
d
if
f
er
e
n
t
a
n
g
le
s
o
f
0
°,
4
5
°,
9
0
°
an
d
1
3
5
°)
co
n
s
id
er
ed
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
.
T
h
e
f
ea
t
u
r
es
a
r
r
an
g
e
m
en
t
s
tar
ted
f
r
o
m
co
n
tr
as
t,
en
er
g
y
,
co
r
r
elatio
n
an
d
h
o
m
o
g
e
n
eit
y
,
m
ea
n
,
v
ar
ian
ce
,
s
k
e
w
n
e
s
s
,
k
u
r
to
s
i
s
,
an
d
en
tr
o
p
y
.
F
ig
u
r
e
2
s
h
o
w
s
t
he
clas
s
i
f
icat
io
n
ca
r
r
ied
o
n
in
2
s
tag
e
s
v
ia
SVM
i
m
p
le
m
e
n
ted
u
s
in
g
cla
s
s
ifica
tio
n
lea
r
n
er
a
pp
an
d
A
NN
m
o
d
el
f
r
o
m
n
eu
r
a
l
n
et
w
o
r
k
p
a
tter
n
r
ec
o
g
n
itio
n
a
p
p
av
ailab
le
in
MA
T
L
A
B
R
2
0
1
9
b
.
T
h
e
f
ir
s
t
s
ta
g
e
i
s
to
clas
s
i
f
y
i
f
a
m
a
m
m
o
g
r
a
m
is
n
o
r
m
al
o
r
ab
n
o
r
m
al.
T
h
e
s
ec
o
n
d
s
ta
g
e
i
s
f
r
o
m
t
h
e
ab
n
o
r
m
a
l
tu
m
o
r
,
it
w
as
cla
s
s
i
f
ied
i
n
to
b
en
ig
n
a
n
d
m
ali
g
n
a
n
t.
T
h
e
SV
M
class
i
f
icat
io
n
w
a
s
co
n
d
u
c
t
ed
b
y
s
elec
ti
n
g
A
ll
S
V
Ms
i
n
Fi
g
u
r
e
2
to
r
u
n
lin
ea
r
,
q
u
a
d
r
a
tic
,
cu
b
ic
,
fin
e
g
a
u
s
s
ia
n
,
med
iu
m
g
a
u
s
s
ia
n
an
d
co
a
r
s
e
g
a
u
s
s
ia
n
m
o
d
el
s
o
f
S
VM
i
n
o
n
e
s
h
o
r
t
.
L
ater
,
th
e
o
p
timi
z
a
b
le
S
V
M
w
a
s
co
n
d
u
cted
to
o
.
T
h
e
h
ig
h
est
cla
s
s
i
f
icat
io
n
ac
cu
r
ac
y
m
o
d
el
w
a
s
s
elec
ted
.
T
h
e
2
-
la
y
er
ed
f
ee
d
f
o
r
w
ar
d
N
N
s
tr
u
ctu
r
e
w
as
cr
ea
ted
u
s
in
g
n
eu
r
a
l
n
etw
o
r
k
p
a
tter
n
r
ec
o
g
n
itio
n
a
p
p
is
s
h
o
w
n
i
n
Fi
g
u
r
e
3
.
T
h
e
in
p
u
t
co
n
tai
n
s
2
1
f
ea
t
u
r
es,
w
h
i
le
th
e
o
u
tp
u
t
is
t
h
e
clas
s
o
f
m
a
m
m
o
g
r
a
m
ei
th
er
n
o
r
m
al/ab
n
o
r
m
al
i
n
t
h
e
f
ir
s
t
s
tag
e,
w
h
ile
b
en
i
g
n
/
m
ali
g
n
a
n
t
in
t
h
e
s
ec
o
n
d
s
tag
e.
1
5
n
eu
r
o
n
s
w
er
e
s
et
i
n
t
h
e
h
id
d
en
la
y
er
a
n
d
1
n
e
u
r
o
n
was
s
et
in
th
e
o
u
tp
u
t
la
y
er
.
T
h
e
NN
w
a
s
tr
ai
n
ed
u
s
in
g
7
0
%
,
1
5
%
an
d
1
5
%
o
f
tr
ain
i
n
g
,
v
alid
atio
n
a
n
d
test
i
n
g
r
esp
ec
tiv
el
y
.
T
h
e
clas
s
i
f
icatio
n
r
es
u
lt
s
f
o
r
b
o
th
S
VM
an
d
N
N
w
it
h
2
1
f
ea
t
u
r
es
w
er
e
r
ec
o
r
d
ed
an
d
co
m
p
ar
ed
.
Fig
u
r
e
2
.
T
y
p
e
o
f
SVM
in
M
A
T
L
A
B
c
las
s
i
f
icatio
n
l
ea
r
n
er
a
pp
Fig
u
r
e
3
.
A
NN
s
tr
u
ct
u
r
e
T
o
im
p
r
o
v
e
th
e
SVM
cla
s
s
i
f
i
ca
tio
n
ac
cu
r
ac
y
,
t
h
e
fea
tu
r
es
s
elec
tio
n
tab
f
r
o
m
cla
s
s
ifica
ti
o
n
lea
r
n
er
app
w
h
ic
h
co
m
p
r
is
es
a
ll
2
1
f
ea
t
u
r
es
w
er
e
u
n
ch
ec
k
ed
all.
L
ater
,
th
e
f
ir
s
t
f
ea
t
u
r
e
w
as
ch
ec
k
ed
o
n
a
n
d
its
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
B
r
ea
s
t c
a
n
ce
r
d
ia
g
n
o
s
is
s
ystem
u
s
in
g
h
yb
r
id
s
u
p
p
o
r
t v
ec
to
r
m
a
ch
in
e
-
a
r
tifi
cia
l n
eu
r
a
l
...
(
Tz
e
S
h
en
g
Lim)
3063
class
i
f
icatio
n
ac
c
u
r
ac
y
w
a
s
r
ec
o
r
d
ed
.
T
h
e
s
ec
o
n
d
f
ea
t
u
r
e
w
a
s
c
h
ec
k
ed
o
n
n
e
x
t
a
n
d
t
h
e
ac
cu
r
ac
y
f
o
r
b
o
th
f
ea
t
u
r
es
w
as
r
ec
o
r
d
ed
an
d
co
m
p
ar
ed
w
it
h
o
n
l
y
th
e
f
ir
s
t
f
e
atu
r
e.
I
f
t
h
e
n
e
w
l
y
ad
d
ed
f
ea
tu
r
e
in
cr
ea
s
es
t
h
e
ac
cu
r
ac
y
t
h
en
t
h
i
s
n
e
w
l
y
ad
d
ed
f
ea
tu
r
e
w
as
k
ep
t,
o
th
er
w
is
e
i
t
w
a
s
r
e
m
o
v
ed
.
T
h
e
p
r
o
ce
s
s
w
as
r
ep
ea
ted
f
o
r
th
e
s
u
b
s
eq
u
en
t
f
ea
tu
r
e
s
u
n
til
t
h
e
last
f
ea
tu
r
e
to
g
e
t
t
h
e
h
i
g
h
e
s
t
ac
c
u
r
ac
y
.
T
h
e
h
i
g
h
est
ac
c
u
r
ac
y
w
i
t
h
s
elec
ted
f
ea
t
u
r
es
w
a
s
r
ec
o
r
d
ed
last
l
y
.
T
h
e
r
ed
u
ce
d
f
ea
t
u
r
es
w
i
ll
b
e
in
p
u
t
i
n
to
A
NN
to
g
et
a
h
y
b
r
id
SVM
-
A
NN
n
e
t
m
o
d
el.
Fig
u
r
e
4
s
h
o
w
s
th
e
f
lo
w
d
ia
g
r
a
m
o
f
th
e
p
r
ed
ictio
n
u
s
in
g
th
e
d
ev
elo
p
ed
C
A
D
s
y
s
te
m
.
T
h
e
f
u
n
ctio
n
s
o
f
th
i
s
C
AD
s
y
s
te
m
ar
e
al
m
o
s
t
s
i
m
ilar
t
o
th
at
o
f
t
h
e
tr
ain
i
n
g
p
h
ase,
th
is
i
s
,
h
o
w
ev
er
,
w
i
th
th
e
ad
d
itio
n
o
f
t
h
e
b
in
ar
izatio
n
o
f
t
h
e
i
m
ag
e
to
r
e
m
o
v
e
u
n
w
a
n
ted
o
b
j
ec
ts
to
d
is
p
lay
t
h
e
lar
g
est
d
etec
ted
r
eg
io
n
,
a
n
d
t
h
r
esh
o
ld
i
n
g
p
r
o
ce
s
s
to
s
h
o
w
p
o
s
s
ib
le
t
u
m
o
r
r
eg
io
n
f
o
r
s
eg
m
en
tatio
n
.
T
h
e
p
r
o
ce
s
s
o
f
th
e
C
AD
s
tar
ted
w
it
h
i
m
p
o
r
ti
n
g
t
h
e
SVM
-
ANN
-
tr
ain
ed
n
et
f
o
llo
wed
b
y
a
r
an
d
o
m
s
e
lectio
n
o
f
1
0
0
d
ig
ital
m
a
m
m
o
g
r
a
m
s
f
r
o
m
th
e
d
ir
ec
to
r
y
.
T
h
i
s
is
f
o
llo
w
ed
b
y
t
h
e
f
i
lter
in
g
o
f
t
h
e
s
elec
ted
m
a
m
m
o
g
r
a
m
u
s
in
g
a
m
ed
ia
n
f
il
ter
b
ef
o
r
e
t
h
e
f
il
ter
ed
i
m
a
g
e
i
s
b
in
ar
ized
to
r
e
m
o
v
e
u
n
w
a
n
te
d
o
b
j
ec
ts
lik
e
tag
in
th
e
m
a
m
m
o
g
r
a
m
s
.
Nex
t,
th
e
lar
g
es
t
d
etec
ted
r
eg
io
n
w
a
s
cr
o
p
p
e
d
.
A
f
ter
th
at,
a
th
r
es
h
o
l
d
v
alu
e
w
a
s
ap
p
lied
to
th
is
r
eg
io
n
;
i
m
a
g
e
p
ix
els
o
f
h
ig
h
i
n
te
n
s
it
y
(
w
h
i
te
r
eg
io
n
)
(
h
ig
h
er
th
a
n
th
at
o
f
th
e
t
h
r
es
h
o
ld
v
alu
e)
w
ill
b
e
s
h
o
w
n
a
s
th
e
p
o
s
s
ib
le
tu
m
o
r
r
eg
io
n
s
.
T
h
is
g
u
id
es
its
u
s
er
s
to
click
t
h
e
m
a
m
m
o
g
r
a
m
r
eg
io
n
w
it
h
s
u
g
g
e
s
ti
v
e
tu
m
o
r
lesi
o
n
s
.
On
ce
a
p
o
in
t
o
f
i
n
ter
est
w
a
s
s
elec
ted
f
r
o
m
t
h
e
p
o
s
s
ib
le
tu
m
o
r
r
eg
io
n
,
th
e
R
O
I
w
o
u
ld
b
e
s
eg
m
e
n
ted
.
L
ater
,
a
h
is
to
g
r
a
m
eq
u
aliza
tio
n
w
as
ad
o
p
ted
t
o
en
h
an
ce
th
e
R
OI
f
o
llo
w
ed
b
y
f
ea
t
u
r
es
ex
tr
ac
tio
n
a
n
d
last
l
y
clas
s
if
ica
tio
n
u
s
in
g
t
h
e
i
m
p
o
r
ted
h
y
b
r
i
d
SVM
-
A
NN
f
r
o
m
th
e
d
ata
tr
ain
in
g
p
r
o
ce
s
s
.
T
h
e
p
er
f
o
r
m
a
n
ce
s
o
f
th
e
tr
ai
n
i
n
g
an
d
test
in
g
p
h
ases
w
er
e
ev
al
u
ated
b
ased
o
n
th
e
ca
lcu
latio
n
o
f
t
h
e
co
n
f
u
s
io
n
m
at
r
ix
as s
h
o
w
n
i
n
T
ab
le
1
.
Fig
u
r
e
4
.
Op
er
atio
n
f
lo
w
d
ia
g
r
a
m
o
f
t
h
e
d
ev
elo
p
ed
C
A
D
s
y
s
te
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.
11
,
No
.
4
,
A
u
g
u
s
t 2
0
2
1
:
3
0
5
9
-
3069
3064
T
ab
le
1
.
C
o
n
f
u
s
io
n
m
atr
i
x
N
o
n
-
c
a
n
c
e
r
o
u
s
C
a
n
c
e
r
o
u
s
N
e
g
a
t
i
v
e
d
i
a
g
n
o
si
s
TN
FN
N
e
g
a
t
i
v
e
P
r
e
c
i
si
o
n
=
+
P
o
si
t
i
v
e
d
i
a
g
n
o
si
s
FP
TP
P
o
si
t
i
v
e
P
r
e
c
i
si
o
n
=
+
S
p
e
c
i
f
i
c
i
t
y
=
+
S
e
n
si
t
i
v
i
t
y
=
+
A
c
c
u
r
a
c
y
=
+
+
+
+
3.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
N
T
ab
le
2
s
h
o
w
s
t
h
e
co
m
p
ar
is
o
n
o
f
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
S
VM
,
ANN,
SV
M
w
it
h
r
ed
u
ce
d
f
e
atu
r
es
a
n
d
h
y
b
r
id
S
VM
-
ANN
m
o
d
els.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
SVM
m
o
d
el
i
n
t
h
e
cla
s
s
i
f
icat
io
n
o
f
n
o
r
m
al
a
n
d
ab
n
o
r
m
al
ca
s
es
is
7
8
.
8
%,
w
h
ile
b
et
w
ee
n
b
en
i
g
n
a
n
d
m
al
ig
n
a
n
t
is
7
1
.
3
%.
On
th
e
o
t
h
er
h
an
d
,
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
A
N
N
m
o
d
el
f
o
r
n
o
r
m
al
a
n
d
ab
n
o
r
m
al
clas
s
i
f
icatio
n
w
o
r
k
is
s
li
g
h
tl
y
h
ig
h
er
,
w
h
ic
h
i
s
8
3
.
1
%,
b
u
t
th
er
e
is
a
r
ed
u
ctio
n
in
i
ts
p
er
f
o
r
m
a
n
ce
i
n
th
e
cla
s
s
i
f
icat
io
n
o
f
b
en
i
g
n
a
n
d
m
ali
g
n
an
t to
7
8
.
8
%.
T
ab
le
2
.
C
o
m
p
ar
is
o
n
o
f
p
er
f
o
r
m
an
ce
o
f
SVM,
A
NN,
S
VM
w
it
h
r
ed
u
ce
d
f
ea
t
u
r
es a
n
d
h
y
b
r
id
SVM
-
A
NN
m
o
d
els
S
V
M
mo
d
e
l
A
N
N
mo
d
e
l
S
V
M
mo
d
e
l
(
r
e
d
u
c
e
d
f
e
a
t
u
r
e
s)
H
y
b
r
i
d
S
V
M
-
A
N
N
mo
d
e
l
N
o
r
mal
/
A
b
n
o
r
mal
7
8
.
8
%
8
3
.
1
%
8
0
%
9
9
.
4
%
B
e
n
i
g
n
/
M
a
l
i
g
n
a
n
t
7
1
.
3
%
7
8
.
8
%
7
3
.
8
%
1
0
0
%
So
m
e
o
f
t
h
e
f
ea
tu
r
es
w
er
e
th
en
r
e
m
o
v
ed
to
i
m
p
r
o
v
e
t
h
e
a
cc
u
r
ac
y
o
f
t
h
e
SV
M
f
o
r
clas
s
if
icatio
n
o
f
th
e
n
o
r
m
a
l
an
d
ab
n
o
r
m
al
ca
s
e
s
.
T
h
is
is
th
r
o
u
g
h
m
an
u
al
id
e
n
ti
f
icatio
n
o
f
1
2
u
n
w
an
ted
f
e
atu
r
es
th
a
t
ca
u
s
ed
a
d
ec
lin
e
in
ac
cu
r
ac
y
;
th
e
s
e
f
ea
t
u
r
es
w
er
e
r
e
m
o
v
ed
leav
i
n
g
9
(
th
ir
d
f
ea
tu
r
e
o
f
co
n
tr
as
t,
f
ir
s
t
to
th
ir
d
f
ea
tu
r
es
o
f
en
er
g
y
,
f
ir
s
t,
s
ec
o
n
d
an
d
f
o
u
r
th
f
ea
tu
r
es
o
f
h
o
m
o
g
e
n
eit
y
,
s
k
e
w
n
es
s
,
a
n
d
e
n
tr
o
p
y
)
f
ea
tu
r
es
r
e
m
ai
n
ed
.
Me
an
w
h
ile,
1
0
f
ea
t
u
r
es
t
h
at
ca
u
s
ed
a
d
ec
lin
e
i
n
ac
c
u
r
ac
y
(
in
d
if
f
er
en
t
iati
n
g
b
e
n
ig
n
f
r
o
m
m
ali
g
n
a
n
t)
w
er
e
r
e
m
o
v
ed
,
w
h
ile
t
h
e
o
t
h
er
1
1
f
ea
t
u
r
es
(
co
n
tr
a
s
t,
f
ir
s
t
to
th
ir
d
f
ea
tu
r
e
s
o
f
e
n
er
g
y
,
f
ir
s
t
a
n
d
th
ir
d
f
ea
t
u
r
e
o
f
co
r
r
elatio
n
,
th
ir
d
f
ea
tu
r
e
o
f
h
o
m
o
g
en
eit
y
an
d
k
u
r
to
s
i
s
)
w
er
e
k
ep
t
f
o
r
th
e
tr
ain
in
g
m
o
d
el
u
s
ed
in
th
e
class
i
f
icatio
n
o
f
b
e
n
ig
n
a
n
d
m
ali
g
n
a
n
t
ca
s
es.
T
h
e
k
ep
t
f
ea
tu
r
es
ca
n
b
e
r
ef
er
r
ed
to
as
g
i
v
en
i
n
Fi
g
u
r
e
5
.
T
h
e
h
ig
h
e
s
t
ac
cu
r
ac
ies
o
b
tain
ed
f
o
r
th
e
SVM
m
o
d
el
w
it
h
r
ed
u
ce
d
f
ea
tu
r
es
ar
e
g
iv
e
n
b
y
8
0
%
an
d
7
3
.
8
%
f
o
r
class
i
f
icatio
n
o
f
n
o
r
m
al
-
ab
n
o
r
m
al
an
d
b
en
i
g
n
-
m
a
lig
n
a
n
t c
as
es,
r
esp
ec
tiv
el
y
as d
is
p
la
y
in
F
ig
u
r
e
6
.
(
a)
(
b
)
Fig
u
r
e
5
.
Featu
r
e
s
elec
tio
n
o
f
:
(
a)
N
o
r
m
al
-
ab
n
o
r
m
al
ca
s
es
,
(
b
)
B
en
ig
n
-
m
ali
g
n
an
t c
a
s
es
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
B
r
ea
s
t c
a
n
ce
r
d
ia
g
n
o
s
is
s
ystem
u
s
in
g
h
yb
r
id
s
u
p
p
o
r
t v
ec
to
r
m
a
ch
in
e
-
a
r
tifi
cia
l n
eu
r
a
l
...
(
Tz
e
S
h
en
g
Lim)
3065
(
a)
(
b
)
Fig
u
r
e
6
.
A
cc
u
r
ac
y
o
f
r
ed
u
ce
d
f
ea
tu
r
e
s
:
(
a)
N
o
r
m
al
-
ab
n
o
r
m
a
l c
ases
,
(
b
)
B
en
ig
n
-
m
ali
g
n
a
n
t
ca
s
es
L
ast
l
y
,
t
h
e
r
ed
u
ce
d
f
ea
tu
r
ed
o
b
tain
ed
f
r
o
m
SVM
w
er
e
s
u
p
p
lied
in
to
A
NN
to
g
iv
e
a
h
y
b
r
id
SVM
-
A
N
N
m
o
d
el.
T
h
is
h
y
b
r
id
m
o
d
el
ac
h
ie
v
ed
th
e
h
i
g
h
e
s
t
p
er
f
o
r
m
an
ce
r
e
s
u
l
ts
,
w
h
ic
h
ar
e
9
9
.
4
%
f
o
r
clas
s
i
f
icatio
n
o
f
n
o
r
m
a
l
an
d
ab
n
o
r
m
al
ca
s
es
w
h
er
ea
s
t
h
e
ac
cu
r
ac
y
o
f
1
0
0
%
i
s
o
b
tain
ed
f
o
r
b
en
ig
n
an
d
m
ali
g
n
a
n
t
class
i
f
icatio
n
.
T
h
er
ef
o
r
e,
th
e
h
y
b
r
id
SVM
-
ANN
m
o
d
el
w
as c
h
o
s
en
a
s
th
e
n
et
m
o
d
el
i
n
th
e
C
A
D
s
y
s
te
m
.
I
n
th
e
ef
f
o
r
ts
to
test
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
C
A
D
s
y
s
te
m
,
1
0
0
m
a
m
m
o
g
r
a
m
s
th
a
t
h
av
e
n
o
t
in
v
o
l
v
ed
in
t
h
e
tr
ain
i
n
g
p
h
a
s
e
w
er
e
r
an
d
o
m
l
y
c
h
o
s
e
n
f
o
r
class
if
icatio
n
.
T
h
e
u
s
e
o
f
t
h
e
C
A
D
s
y
s
te
m
in
t
h
e
class
i
f
icatio
n
o
f
n
o
r
m
al,
b
en
i
g
n
a
n
d
m
ali
g
n
a
n
t
b
r
ea
s
ts
is
s
h
o
w
n
i
n
Fi
g
u
r
e
s
7
-
9
.
T
h
e
lef
t
s
id
e
o
f
th
e
GUI
s
h
o
w
s
t
h
e
f
u
n
ctio
n
al
it
y
b
u
t
to
n
s
,
w
h
ich
s
tar
t
s
f
r
o
m
i
m
a
g
e
lo
ad
in
g
(
s
elec
t
ma
mmo
g
r
am
)
to
p
r
ep
r
o
ce
s
s
in
g
(
filt
er
,
b
in
a
r
iz
a
tio
n
,
r
emo
va
l
o
f
u
n
w
a
n
ted
o
b
ject
s
a
s
s
h
o
wn
in
Fi
g
u
r
e
1
0
,
la
r
g
e
r
eg
io
n
ex
tr
a
ctio
n
,
p
o
s
s
ib
le
tu
mo
r
r
eg
io
n
)
,
to
s
eg
m
en
ta
ti
o
n
o
f
2
5
6
x
2
5
6
p
ix
els
o
f
R
OI
an
d
a
d
ju
s
t
ima
g
e
co
n
tr
a
s
t
o
f
th
e
R
OI
b
ef
o
r
e
ex
tr
ac
ti
n
g
t
h
e
f
ea
t
u
r
es.
O
n
ce
al
l
th
e
p
r
ep
r
o
ce
s
s
i
n
g
f
u
n
c
ti
o
n
s
o
n
t
h
e
le
f
t,
s
eg
men
ta
tio
n
an
d
a
d
ju
s
t
ima
g
e
co
n
tr
a
s
t
p
an
el
h
av
e
b
ee
n
ex
ec
u
ted
,
th
e
p
r
o
ce
s
s
ed
/r
esu
lti
n
g
f
ig
u
r
e
w
o
u
ld
b
e
d
is
p
lay
ed
o
n
th
e
r
ig
h
t
s
id
e
o
f
th
e
GUI
.
T
h
e
d
ef
au
lt
th
r
es
h
o
ld
in
g
v
alu
e
is
s
et
0
.
6
5
as
s
h
o
w
n
in
th
e
GUI
.
On
ce
a
d
ju
s
t
ima
g
e
co
n
tr
a
s
t
is
click
ed
,
th
e
fea
tu
r
e
ex
tr
a
ctio
n
b
u
tto
n
lo
ca
ted
o
n
t
h
e
le
f
t
b
o
tto
m
p
a
n
el
w
o
u
ld
e
n
ab
le
it
s
u
s
er
s
to
v
ie
w
all
2
1
o
f
th
e
v
alu
e
s
o
f
t
h
e
ca
lcu
lated
f
ea
t
u
r
es.
L
ast
l
y
i
n
t
h
e
class
if
ica
tio
n
p
an
el,
t
h
e
r
esu
l
ts
w
o
u
ld
i
n
d
icate
w
h
eth
er
t
h
e
m
a
m
m
o
g
r
a
m
i
s
n
o
r
m
al,
b
en
i
g
n
o
r
m
ali
g
n
a
n
t a
f
ter
th
e
cla
s
s
if
ica
tio
n
b
u
tto
n
is
p
r
ess
ed
.
Fig
u
r
e
7
.
An
ex
a
m
p
le
o
f
t
h
e
d
ev
elo
p
ed
C
AD
ap
p
licatio
n
in
i
d
en
tify
i
n
g
n
o
r
m
al
b
r
ea
s
t
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.
11
,
No
.
4
,
A
u
g
u
s
t 2
0
2
1
:
3
0
5
9
-
3069
3066
Fig
u
r
e
8
.
An
ill
u
s
tr
atio
n
o
f
C
A
D
d
etec
tio
n
r
esu
l
t f
o
r
b
en
i
g
n
ca
s
e
Fig
u
r
e
9
.
An
ill
u
s
tr
atio
n
o
f
C
A
D
d
etec
tio
n
r
esu
l
t f
o
r
m
al
ig
n
an
t
ca
s
e
On
ce
th
e
S
eg
men
ta
tio
n
b
u
tto
n
is
clic
k
ed
,
t
w
o
i
m
ag
e
s
ap
p
ea
r
w
it
h
th
e
b
in
ar
y
m
a
s
k
ed
i
m
ag
e
o
n
th
e
lef
t
a
n
d
t
h
e
o
r
ig
in
al
lar
g
e
s
t
e
x
tr
ac
ted
b
r
ea
s
t
r
eg
io
n
o
n
t
h
e
r
ig
h
t
as
s
ee
n
i
n
Fi
g
u
r
e
1
1
.
Ot
h
er
t
h
an
th
at,
th
er
e
w
il
l
b
e
a
cr
o
s
s
h
air
o
r
g
u
id
in
g
ax
i
s
f
o
r
th
e
u
s
er
s
to
lo
ca
te
an
d
s
elec
t
t
h
e
p
o
s
s
ib
le
t
u
m
o
r
r
eg
io
n
.
On
ce
,
t
h
e
p
o
s
s
ib
le
t
u
m
o
r
r
e
g
io
n
i
s
clic
k
ed
,
a
2
5
6
x
2
5
6
R
OI
w
ill b
e
s
e
g
m
en
ted
as see
n
o
n
to
p
o
f
t
h
e
S
eg
men
ta
tio
n
b
u
tto
n
in
Fi
g
u
r
es 7
-
9.
Me
an
w
h
ile,
th
e
ac
cu
r
ac
y
,
s
p
ec
if
icit
y
,
s
e
n
s
iti
v
it
y
,
n
e
g
ati
v
e
p
r
ec
is
io
n
an
d
p
o
s
itiv
e
p
r
ec
is
io
n
o
b
tain
ed
f
o
llo
w
in
g
v
alid
atio
n
o
f
t
h
e
s
y
s
te
m
u
s
i
n
g
t
h
e
u
n
s
ee
n
1
0
0
m
a
m
m
o
g
r
a
m
s
ar
e
g
i
v
e
n
b
y
9
8
%
(
i.e
.
,
9
8
/1
0
0
*
1
0
0
)
,
9
7
.
7
0
%
(
8
5
/8
7
*
1
0
0
%),
1
0
0
%
(
1
3
/1
3
*
1
0
0
%),
1
0
0
%
(
8
5
/8
5
*
1
0
0
%)
a
n
d
8
6
.
6
7
%
(
1
3
/1
5
*
1
0
0
%)
as
g
iv
e
n
i
n
T
ab
le
3
.
T
h
e
d
eta
il o
f
n
o
r
m
a
l,
b
en
ig
n
an
d
m
ali
g
n
a
n
t c
la
s
s
i
f
ic
atio
n
ca
n
b
e
r
ef
er
r
ed
to
in
T
ab
le
4
.
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
B
r
ea
s
t c
a
n
ce
r
d
ia
g
n
o
s
is
s
ystem
u
s
in
g
h
yb
r
id
s
u
p
p
o
r
t v
ec
to
r
m
a
ch
in
e
-
a
r
tifi
cia
l n
eu
r
a
l
...
(
Tz
e
S
h
en
g
Lim)
3067
(
a)
(
b
)
Fig
u
r
e
1
0
.
R
e
m
o
v
al
o
f
u
n
w
a
n
t
ed
o
b
j
ec
t
:
(
a)
B
ef
o
r
e
,
(
b
)
A
f
ter
Fig
u
r
e
1
1
.
Seg
m
e
n
tatio
n
o
f
t
u
m
o
r
r
eg
io
n
u
s
i
n
g
a
cr
o
s
s
h
air
T
ab
le
3
.
C
o
n
f
u
s
io
n
m
atr
i
x
o
f
C
A
D
p
r
o
g
r
a
m
’
s
p
er
f
o
r
m
an
ce
N
o
n
c
a
n
c
e
r
o
u
s
C
a
n
c
e
r
o
u
s
N
e
g
a
t
i
v
e
d
i
a
g
n
o
si
s
85
0
N
e
g
a
t
i
v
e
P
r
e
c
i
si
o
n
100%
P
o
si
t
i
v
e
d
i
a
g
n
o
s
i
s
2
13
P
o
si
t
i
v
e
P
r
e
c
i
si
o
n
86
.
67%
S
p
e
c
i
f
i
c
i
t
y
97
.
70%
S
e
n
si
t
i
v
i
t
y
100%
A
c
c
u
r
a
c
y
98%
T
ab
le
4
.
C
lass
if
icatio
n
r
es
u
lt
s
o
f
C
A
D
p
r
o
g
r
a
m
’
s
p
er
f
o
r
m
an
ce
R
e
a
l
N
o
r
mal
B
e
n
i
g
n
M
a
l
i
g
n
a
n
t
P
r
e
d
i
c
t
e
d
N
o
r
mal
62
0
0
B
e
n
i
g
n
0
23
0
M
a
l
i
g
n
a
n
t
0
2
13
4.
CO
NCLU
SI
O
N
I
n
th
is
s
tu
d
y
,
a
co
m
p
ar
is
o
n
o
f
th
e
p
er
f
o
r
m
an
ce
o
f
S
VM
,
A
NN,
SVM
w
it
h
r
ed
u
ce
d
f
ea
tu
r
es
an
d
h
y
b
r
id
SVM
-
A
NN
m
o
d
el
i
n
th
e
b
r
ea
s
t
ca
n
ce
r
d
iag
n
o
s
i
s
w
a
s
ca
r
r
ied
o
ut
.
T
h
e
h
y
b
r
id
SVM
-
A
NN
n
et
m
o
d
el
w
a
s
ch
o
s
e
n
to
b
e
i
m
p
o
r
ted
in
t
o
th
e
C
A
D
s
y
s
te
m
f
o
r
th
e
test
in
g
o
f
t
h
e
n
e
w
d
ata
o
w
i
n
g
to
its
h
i
g
h
ac
cu
r
ac
y
o
f
99
.
4
%
an
d
1
0
0
%
f
o
r
cla
s
s
i
f
icatio
n
o
f
n
o
r
m
al
-
ab
n
o
r
m
al
an
d
b
en
i
g
n
-
m
al
ig
n
a
n
t
ca
s
es
,
r
e
s
p
ec
tiv
el
y
.
T
h
e
d
ev
elo
p
ed
C
A
D
s
y
s
te
m
s
tar
ts
w
it
h
t
h
e
f
u
n
ctio
n
s
s
elec
t
ma
mmo
g
r
a
m
,
filt
er
,
b
in
a
r
iz
a
tio
n
,
r
emo
va
l
o
f
u
n
w
a
n
ted
o
b
jects
,
la
r
g
e
r
eg
io
n
ex
tr
a
ctio
n
,
p
o
s
s
ib
le
tu
mo
r
r
eg
io
n
,
s
eg
men
ta
tio
n
,
a
d
j
u
s
t
ima
g
e
co
n
tr
a
s
t
,
fea
tu
r
e
ex
tr
a
ctio
n
an
d
cla
s
s
ifi
ca
tio
n
.
T
h
is
s
y
s
te
m
ca
n
clas
s
if
y
a
t
u
m
o
r
i
m
ag
e
i
n
to
eit
h
er
n
o
r
m
al,
b
en
i
g
n
o
r
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.
11
,
No
.
4
,
A
u
g
u
s
t 2
0
2
1
:
3
0
5
9
-
3069
3068
m
ali
g
n
a
n
t.
T
h
is
w
as
co
n
f
ir
m
e
d
u
s
in
g
10
0
r
an
d
o
m
l
y
c
h
o
s
e
n
n
e
w
s
a
m
p
les
;
t
h
e
r
esu
lt
s
s
h
o
w
ed
r
elativ
e
l
y
g
o
o
d
p
er
f
o
r
m
a
n
ce
o
f
9
8
%,
9
7
.
7
0
%,
1
0
0
%,
100
%
an
d
8
6
.
6
7
%
f
o
r
ac
cu
r
ac
y
,
s
p
ec
i
f
icit
y
,
s
en
s
iti
v
it
y
,
n
e
g
ati
v
e
p
r
ec
is
io
n
an
d
p
o
s
itiv
e
p
r
ec
is
io
n
,
r
esp
ec
tiv
el
y
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
W
e
ar
e
g
r
atef
u
l
to
Un
iv
er
s
iti
T
u
n
Hu
s
s
ein
O
n
n
Ma
la
y
s
ia
f
o
r
f
in
a
n
ciall
y
s
u
p
p
o
r
tin
g
th
i
s
w
o
r
k
u
n
d
er
T
iER 1
2
0
1
8
g
r
an
t n
u
m
b
er
H2
5
8
an
d
f
u
n
d
a
m
e
n
tal
r
esear
ch
g
r
an
t sch
e
m
e
F
R
G
S
/1
/2
0
1
8
/tk
0
4
/u
th
m
/0
2
/1
3
.
RE
F
E
R
E
NC
E
S
[1
]
L
.
A
.
T
o
rre
,
F
.
Isla
m
i,
R.
L
.
S
ieg
e
l,
El
.
M
.
W
a
rd
,
a
n
d
A
.
Je
m
a
l,
“
G
lo
b
a
l
Ca
n
c
e
r
in
W
o
m
e
n
:
Bu
rd
e
n
a
n
d
T
re
n
d
s,”
Ca
n
c
e
r E
p
i
d
e
mio
l
o
g
y
,
Bi
o
m
a
rk
e
rs
a
n
d
Pre
v
e
n
ti
o
n
,
v
o
l
.
2
6
,
n
o
.
4
,
p
p
.
4
4
4
–
4
5
7
,
2
0
1
7
.
[2
]
F
.
Bra
y
,
J.
F
e
rla
y
,
I.
S
o
e
rj
o
m
a
ta
ra
m
,
R.
L
.
S
ieg
e
l,
L
.
A
.
T
o
rre
,
a
n
d
A
.
Je
m
a
l,
“
G
lo
b
a
l
Ca
n
c
e
r
S
tatisti
c
s
2
0
1
8
:
GL
OBO
C
AN
Esti
m
a
tes
o
f
In
c
id
e
n
c
e
a
n
d
M
o
r
talit
y
W
o
rld
w
id
e
fo
r
3
6
Ca
n
c
e
rs
in
1
8
5
Co
u
n
tri
e
s,”
CA:
A
Ca
n
c
e
r
J
o
u
rn
a
l
f
o
r Cli
n
icia
n
s
,
v
o
l.
6
8
,
n
o
.
6,
pp
.
3
9
4
–
4
2
4
,
2
0
1
8
.
[3
]
C.
H.
Yip
,
N.
A
.
M
o
h
d
T
a
ib
,
a
n
d
I.
M
o
h
a
m
e
d
,
“
Ep
id
e
m
io
lo
g
y
o
f
B
re
a
st Can
c
e
r
in
M
a
la
y
sia
,
”
Asia
n
Pa
sifi
c
jo
u
rn
a
l
o
f
c
a
n
c
e
r p
re
v
e
n
ti
o
n
:
AP
J
CP
,
v
o
l
.
7
,
n
o
.
3
,
p
p
.
3
6
9
–
3
7
4
,
2
0
0
5
.
[4
]
S
.
K.
M
.
Ha
m
o
u
d
a
,
H
.
R
A
b
o
El
-
Ezz
,
a
n
d
M
.
E
W
a
h
e
d
,
“
In
telli
g
e
n
t
S
y
ste
m
f
o
r
P
re
d
icti
n
g
,
Dia
g
n
o
sis
a
n
d
T
re
a
t
m
e
n
t
o
f
Bre
a
st Can
c
e
r,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Bi
o
me
d
ica
l
Da
ta
M
in
in
g
,
v
o
l.
6
,
n
o
.
2
,
p
p
.
1
–
9
,
2
0
1
7
.
[5
]
E.
S
.
M
c
Do
n
a
l
d
,
A
.
Ou
stim
o
v
,
S
.
P
.
W
e
in
ste
in
,
a
n
d
M
.
B.
S
y
n
n
e
stv
e
d
t,
“
Eff
e
c
ti
v
e
n
e
ss
o
f
Dig
it
a
l
Bre
a
st
T
o
m
o
s
y
n
th
e
sis
Co
m
p
a
re
d
w
it
h
Dig
it
a
l
M
a
m
m
o
g
ra
p
h
y
Ou
tco
m
e
A
n
a
l
y
sis
f
ro
m
3
Ye
a
rs
o
f
Bre
a
st
Ca
n
c
e
r
S
c
re
e
n
in
g
,
”
J
AM
A
On
c
o
lo
g
y
, v
o
l.
2
,
n
o
.
6
,
p
p
.
7
3
7
–
7
4
3
,
2
0
1
6
.
[6
]
H.
D.
Ch
e
n
g
,
X.
J.
S
h
i,
R.
M
i
n
,
L
.
M
.
Hu
,
X.
P
.
Ca
i,
a
n
d
H.
N.
Du
,
“
A
p
p
ro
a
c
h
e
s
f
o
r
a
u
to
m
a
ted
d
e
tec
ti
o
n
a
n
d
c
las
si
f
ica
ti
o
n
o
f
m
a
ss
e
s
in
m
a
m
m
o
g
r
a
m
s,”
T
h
e
J
o
u
rn
a
l
o
f
t
h
e
P
a
tt
e
rn
Rec
o
g
n
it
io
n
S
o
c
iety
,
v
ol
.
3
9
,
p
p
.
6
4
6
–
6
6
8
,
2
0
0
5
,
d
o
i:
1
0
.
1
0
1
6
/
j.
p
a
tco
g
.
2
0
0
5
.
0
7
.
0
0
6
.
[7
]
P
.
S
k
a
a
n
e
,
K.
En
g
e
d
a
l,
a
n
d
A
.
S
k
jen
n
a
ld
,
“
In
tero
b
se
rv
e
r
v
a
riati
o
n
i
n
th
e
in
terp
re
tatio
n
o
f
b
re
a
st
ima
g
in
g
,
”
Acta
Ra
d
i
o
l
,
v
o
l.
3
8
,
p
p
.
4
9
7
–
5
0
2
,
1
9
9
7
,
d
o
i:
1
0
.
1
0
8
0
%
2
F
0
2
8
4
1
8
5
9
7
0
9
1
7
4
3
7
5
.
[8
]
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
th
,
“
Im
a
g
e
p
ro
c
e
ss
in
g
a
n
d
m
a
c
h
in
e
lea
r
n
in
g
tec
h
n
iq
u
e
s
u
se
d
in
c
o
m
p
u
ter
-
a
id
e
d
d
e
tec
ti
o
n
s
y
ste
m
f
o
r
m
a
m
m
o
g
r
a
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
m
p
u
ter
E
n
g
i
n
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
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jec
e
.
v
1
0
i3
.
p
p
2
3
3
6
-
2
3
4
8
.
[9
]
J.
W
u
,
S
.
G
u
o
,
H.
Hu
a
n
g
,
W
.
L
iu
,
a
n
d
Y.
X
ian
g
,
“
I
n
f
o
rm
a
ti
o
n
a
n
d
Co
m
m
u
n
ica
ti
o
n
s
T
e
c
h
n
o
lo
g
ies
f
o
r
S
u
sta
in
a
b
le
De
v
e
lo
p
m
e
n
t
G
o
a
ls:
S
tate
-
of
-
th
e
-
A
rt,
Ne
e
d
s
a
n
d
P
e
rsp
e
c
ti
v
e
s,”
IEE
E
Co
mm
u
n
ica
ti
o
n
s
S
u
rv
e
y
s
&
T
u
to
ria
ls
,
v
o
l.
2
0
,
n
o
.
3
,
p
p
.
2
3
8
9
–
2
4
0
6
,
2
0
1
8
.
[1
0
]
J.
W
u
,
S
.
G
u
o
,
J.
L
i,
a
n
d
D.
Zen
g
,
“
Big
Da
ta
M
e
e
t
G
r
e
e
n
Ch
a
ll
e
n
g
e
s:
Big
Da
ta
to
w
a
rd
G
re
e
n
A
p
p
li
c
a
ti
o
n
s
,
”
IEE
E
S
y
ste
ms
J
o
u
rn
a
l
, v
o
l.
1
0
,
n
o
.
3
,
p
p
.
1
–
1
3
,
2
0
1
6
.
[1
1
]
J.
W
u
,
S
.
G
u
o
,
J.
L
i,
a
n
d
D.
Zen
g
,
“
Big
D
a
ta
M
e
e
t
G
re
e
n
Ch
a
ll
e
n
g
e
s:
G
re
e
n
in
g
Bi
g
Da
ta
,
”
IEE
E
S
y
ste
ms
J
o
u
rn
a
l
,
v
o
l.
1
0
,
n
o
.
3
,
p
p
.
1
–
1
5
,
2
0
1
6
.
[1
2
]
R.
A
tat
,
L
.
L
iu
,
J.
W
u
,
G
.
L
i,
C.
Ye
,
a
n
d
Y.
Yi,
“
Bi
g
Da
t
a
M
e
e
t
C
y
b
e
r
-
P
h
y
sic
a
l
S
y
ste
m
s:
A
P
a
n
o
ra
m
ic
S
u
rv
e
y
,
”
IEE
E
Acc
e
ss
, v
o
l.
6
,
p
p
.
7
3
6
0
3
–
7
3
6
3
6
,
2
0
1
8
.
[1
3
]
K.
S
h
a
il
a
ja,
B.
S
e
e
t
h
a
ra
m
u
lu
,
a
n
d
M.
A
.
Ja
b
b
a
r,
“
P
re
d
ictio
n
o
f
Bre
a
st
Ca
n
c
e
r
Us
in
g
Big
Da
ta
A
n
a
l
y
ti
c
s,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
in
e
e
rin
g
&
T
e
c
h
n
o
lo
g
y
,
v
o
l,
7
,
n
o
.
4
.
4
6
,
p
p
.
2
2
3
–
2
2
6
,
2
0
1
8
.
[1
4
]
I.
Ib
n
o
u
h
se
in
,
S
.
Ja
n
k
o
w
sk
i
,
K.
N
e
u
b
e
rg
e
r
,
a
n
d
C.
M
a
th
e
l
in
,
“
T
h
e
Big
Da
ta Re
v
o
lu
ti
o
n
f
o
r
Bre
a
st Can
c
e
r
P
a
ti
e
n
ts,”
Eu
ro
p
e
a
n
J
o
u
rn
a
l
o
f
Bre
a
st
Ca
n
c
e
r
,
v
o
l
1
4
,
n
o
.
2,
p
p
.
61
–
6
2
,
2
0
1
8
.
[1
5
]
H.
Ero
l
,
N.
Öz
ç
e
li
k
k
a
n
,
A
.
T
o
k
g
ö
z
,
S
.
Öz
e
l,
S
.
Zaim
,
a
n
d
O.
F
.
De
m
irel,
“
F
o
re
c
a
stin
g
El
e
c
tri
c
it
y
Co
n
s
u
m
p
ti
o
n
o
f
T
u
rk
e
y
Us
in
g
T
i
m
e
S
e
rie
s
M
e
th
o
d
s
a
n
d
Ne
u
ra
l
Ne
tw
o
rk
,
”
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
in
M
a
th
e
ma
t
ics
2
0
1
2
,
A
l
A
in
,
Un
it
e
d
A
ra
b
Em
irate
s Un
iv
e
rsit
y
,
2
0
1
2
,
p
p
.
1
1
8
–
1
2
7
.
[1
6
]
Co
rtes
a
n
d
V
.
V
a
p
n
ik
,
“
S
u
p
p
o
r
t
-
V
e
c
to
r
Ne
tw
o
rk
,
”
M
a
c
h
in
e
L
e
a
m
in
g
,
v
o
l.
2
0
,
p
p
.
2
7
3
–
2
9
7
,
1
9
9
5
.
[1
7
]
R.
R.
Ja
n
g
h
e
l,
A
.
S
h
u
k
la,
R.
T
i
w
a
ri,
a
n
d
R.
Ka
la,
“
Bre
a
st
Ca
n
c
e
r
Dia
g
n
o
sis
u
sin
g
A
rti
f
icia
l
N
e
u
ra
l
Ne
t
w
o
rk
M
o
d
e
ls
,
”
T
h
e
3
r
d
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
s a
n
d
In
ter
a
c
t
io
n
S
c
ien
c
e
s
,
2
0
1
0
,
p
p
.
8
9
–
9
4.
[1
8
]
H.
Jo
u
n
i,
M
.
Iss
a
,
A
.
Ha
rb
,
G
.
Ja
c
q
u
e
m
o
d
,
a
n
d
Y.
L
e
d
u
c
,
“
N
e
u
ra
l
Ne
tw
o
rk
A
rc
h
it
e
c
tu
r
e
f
o
r
Bre
a
st
Ca
n
c
e
r
De
tec
ti
o
n
a
n
d
Clas
sif
ica
ti
o
n
,
”
2
0
1
6
IEE
E
In
ter
n
a
ti
o
n
a
l
M
u
lt
i
d
isc
i
p
li
n
a
ry
Co
n
fer
e
n
c
e
o
n
En
g
in
e
e
ri
n
g
T
e
c
h
n
o
l
o
g
y
(
IM
CET
)
,
2
0
1
6
,
p
p
.
1
–
5.
[1
9
]
K.
Ko
u
ro
u
,
T
.
P
.
Ex
a
rc
h
o
s,
K.
P
.
Ex
a
rc
h
o
s,
M
.
V
.
Ka
ra
m
o
u
z
is,
a
n
d
D.
I.
F
o
ti
a
d
is,
“
M
a
c
h
in
e
lea
rn
i
n
g
a
p
p
li
c
a
ti
o
n
s
in
c
a
n
c
e
r
p
r
o
g
n
o
sis a
n
d
p
re
d
ictio
n
,
”
Co
m
p
u
t
a
ti
o
n
a
l
a
n
d
S
tr
u
c
tu
ra
l
Bi
o
tec
h
n
o
l
o
g
y
J
o
u
rn
a
l
,
v
o
l.
1
3
,
p
p
.
8
–
1
7
,
2
0
1
5
.
[2
0
]
K.
P
.
Be
n
n
e
tt
a
n
d
J.
A
.
Blu
e
,
“
A
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
a
p
p
ro
a
c
h
to
d
e
c
isio
n
tree
s
,
”
Pro
c
e
e
d
in
g
s
o
f
IEE
E
In
ter
n
a
t
io
n
a
l
J
o
in
t
Co
n
fer
e
n
c
e
o
n
Ne
u
ra
l
Ne
two
rk
s
,
1
9
9
8
,
p
p
.
2
3
9
6
–
2
4
0
1
.
[2
1
]
M
.
F
.
A
k
a
y
,
“
S
u
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
s
c
o
m
b
in
e
d
w
it
h
f
e
a
tu
r
e
se
lec
ti
o
n
f
o
r
b
re
a
st
c
a
n
c
e
r
d
i
a
g
n
o
sis,”
Exp
e
rt
S
y
ste
ms
wit
h
Ap
p
li
c
a
ti
o
n
s
,
v
o
l
.
3
6
,
n
o
.
2
,
p
p
.
3
2
4
0
–
3
2
4
7
,
2
0
0
9
.
[2
2
]
Zh
e
n
g
,
S
.
W
.
Yo
o
n
,
a
n
d
S
.
S
.
L
a
m
,
“
Bre
a
st
c
a
n
c
e
r
d
iag
n
o
sis
b
a
se
d
o
n
f
e
a
tu
re
e
x
trac
ti
o
n
u
sin
g
a
h
y
b
rid
o
f
K
-
m
e
a
n
s
a
n
d
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
a
lg
o
rit
h
m
s,”
Exp
e
rt S
y
ste
ms
wit
h
Ap
p
li
c
a
ti
o
n
s
,
v
o
l.
4
1
,
n
o
.
4
,
p
p
.
1
4
7
6
–
1
4
8
2
,
2
0
1
4
.
[2
3
]
R.
Ch
ti
h
ra
k
k
a
n
n
a
n
,
P
.
Ka
v
it
h
a
,
T
.
M
a
n
g
a
y
a
rk
a
ra
si,
a
n
d
R.
Ka
rth
ik
e
y
a
n
,
“
Bre
a
st
Ca
n
c
e
r
De
tec
ti
o
n
u
sin
g
M
a
c
h
in
e
L
e
a
rn
in
g
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
n
o
v
a
ti
v
e
T
e
c
h
n
o
l
o
g
y
a
n
d
Exp
l
o
rin
g
En
g
in
e
e
rin
g
,
v
o
l.
8
,
n
o
.
1
1
,
pp.
3
1
2
3
–
3
1
2
6
,
2
0
1
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.