I
nte
rna
t
io
na
l J
o
urna
l o
f
I
nfo
r
m
a
t
ics a
nd
Co
mm
u
n
ica
t
io
n T
ec
hn
o
lo
g
y
(
I
J
-
I
CT
)
Vo
l.
10
,
No
.
2
,
A
u
g
u
s
t
2021
,
p
p
.
9
3
~
1
03
I
SS
N:
2252
-
8776
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ict.
v
1
0
i2
.
p
p
9
3
-
1
0
3
93
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ict.
ia
esco
r
e.
co
m
Da
ta
m
ining
t
e
ch
niques for
lung a
nd breas
t
ca
ncer
dia
g
no
sis
:
A
revi
ew
B
a
k
ha
n T
o
f
iq A
h
m
ed
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
,
T
e
c
h
n
ica
l
Co
ll
e
g
e
o
f
In
f
o
rm
a
ti
c
s,
S
u
laim
a
n
i
P
o
ly
tec
h
n
ic Un
iv
e
rsit
y
,
S
u
laim
a
n
i,
Ku
rd
istan
Re
g
io
n
,
Ira
q
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
1
2
,
2
0
2
0
R
ev
i
s
ed
Se
p
1
6
,
2
0
2
0
A
cc
ep
ted
D
e
c
2
9
,
2
0
2
0
T
o
d
a
y
,
c
a
n
c
e
r
is
c
o
u
n
ted
a
s
a
ris
k
ier
d
ise
a
se
th
a
n
o
t
h
e
r
d
ise
a
se
s
in
th
e
g
lo
b
e
.
T
h
e
re
a
r
e
m
a
n
y
c
a
n
c
e
r
f
o
r
m
s li
k
e
leu
k
e
m
ia,
s
k
in
c
a
n
c
e
r,
sto
m
a
c
h
c
a
n
c
e
r,
e
tc,
b
u
t
L
u
n
g
a
n
d
Bre
a
st
c
a
n
c
e
r
a
re
th
e
m
o
st
c
o
m
m
o
n
f
o
r
m
s
th
a
t
m
a
n
y
p
e
o
p
le
su
ff
e
re
d
f
ro
m
.
Ca
n
c
e
r
is
a
d
i
se
a
se
in
th
a
t
c
e
ll
s
h
a
v
e
g
ro
w
n
ra
p
id
ly
a
n
d
a
b
n
o
rm
a
ll
y
th
a
t
is
w
h
y
tre
a
ti
n
g
th
e
m
is
so
m
e
h
o
w
to
u
g
h
in
s
o
m
e
c
a
se
s
b
u
t
it
c
a
n
b
e
c
o
n
tro
l
led
if
th
e
y
d
e
tec
t
in
t
h
e
ir
i
n
it
ial
sta
g
e
.
Da
ta
-
m
in
in
g
c
las
si
f
ica
ti
o
n
a
lg
o
rit
h
m
s
h
a
d
a
v
it
a
l
ro
le
i
n
p
re
d
icti
n
g
a
n
d
re
c
o
g
n
i
z
in
g
b
o
t
h
b
e
n
ig
n
a
n
d
m
a
li
g
n
a
n
t
c
e
ll
s.
S
e
v
e
ra
l
c
las
si
f
iers
a
re
a
v
a
il
a
b
le
to
c
las
sify
th
e
u
su
a
l
a
n
d
u
n
u
su
a
l
c
e
ll
s
su
c
h
a
s
d
e
c
isio
n
-
tree
,
a
rti
f
icia
l
-
n
e
u
ra
l
n
e
t,
su
p
p
o
r
t
v
e
c
to
r
m
a
c
h
in
e
,
k
-
n
e
a
re
st
n
e
ig
h
b
o
r
,
e
tc.
T
h
is
p
a
p
e
r
p
re
se
n
ts
a
s
y
ste
m
a
ti
c
re
v
ie
w
o
f
th
e
m
o
st
w
e
ll
-
k
n
o
w
n
d
a
ta
-
m
in
in
g
c
las
sif
i
c
a
ti
o
n
a
lg
o
rit
h
m
s f
o
r
lu
n
g
a
n
d
b
re
a
st
c
a
n
c
e
r
d
iag
n
o
se
.
A
b
rief
re
v
ie
w
o
f
KD
D
a
n
d
th
e
d
a
ta
-
m
in
in
g
c
o
n
c
e
p
t
h
a
s
b
e
e
n
d
e
m
o
n
stra
ted
.
T
h
e
D
-
T
re
e
,
A
-
NN
,
S
V
M
,
a
n
d
Na
ïv
e
B
a
y
e
s
c
las
si
f
iers
t
h
a
t
a
re
w
id
e
l
y
u
ti
li
z
e
d
in
th
e
b
io
m
e
d
ica
l
f
ield
h
a
v
e
b
e
e
n
re
v
ie
w
e
d
a
lo
n
g
w
it
h
so
m
e
a
lg
o
rit
h
m
s
su
c
h
a
s
C4
.
5
,
Ca
rt,
a
n
d
it
e
ra
ti
v
e
-
d
ich
o
to
m
ise
r
3
‘ID3
’.
A
c
o
m
p
a
riso
n
h
a
s
b
e
e
n
d
o
n
e
a
m
o
n
g
v
a
rio
u
s
re
v
i
e
w
e
d
p
a
p
e
rs
in
ter
m
s
o
f
a
c
c
u
ra
c
y
th
a
t
u
se
d
v
a
rio
u
s
d
a
ta
-
m
in
in
g
c
las
si
f
ica
ti
o
n
a
lg
o
rit
h
m
s
to
p
ro
p
o
se
th
e
l
u
n
g
a
n
d
b
re
a
st
c
a
n
c
e
r
d
iag
n
o
sis
sy
ste
m
.
T
h
e
e
x
p
e
rim
e
n
tal
re
su
lt
s
o
f
th
e
re
v
i
e
w
e
d
p
a
p
e
rs
sh
o
w
e
d
th
a
t
th
e
M
u
lt
il
a
y
e
r
P
e
rc
e
p
tro
n
‘M
L
P
’
a
n
d
L
o
g
isti
c
Re
g
re
ss
io
n
‘L
R’
g
a
v
e
a
h
ig
h
e
r
a
c
c
u
ra
c
y
o
f
9
9
.
0
4
%
a
n
d
9
8
.
1
%
,
re
sp
e
c
t
iv
e
l
y
.
K
ey
w
o
r
d
s
:
A
N
N
Dec
is
io
n
t
r
ee
KDD
Naïv
e
B
a
y
es
Su
p
p
o
r
t v
ec
to
r
m
ac
h
i
n
e
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
:
B
ak
h
a
n
T
o
f
iq
A
h
m
ed
,
Dep
ar
t
m
en
t o
f
I
n
f
o
r
m
atio
n
T
e
ch
n
o
lo
g
y
,
Te
ch
n
ical
C
o
lleg
e
o
f
I
n
f
o
r
m
atic
s
Su
lai
m
a
n
i P
o
l
y
tech
n
ic
U
n
i
v
er
s
it
y
Su
lai
m
a
n
i,
Ku
r
d
is
tan
R
eg
i
o
n
,
I
r
aq
E
m
ail: b
ak
h
a
n
.
to
f
iq
.
a@
s
p
u
.
ed
u
.
iq
1.
I
NT
RO
D
UCT
I
O
N
No
w
ad
a
y
s
,
th
e
m
o
s
t
h
az
ar
d
o
u
s
d
is
ea
s
e
t
h
at
f
ac
ed
h
u
m
an
it
y
's
li
f
e
an
d
led
to
f
a
tal
d
ea
th
i
s
r
ef
er
r
ed
to
as
c
an
ce
r
[
1
]
.
C
an
ce
r
i
s
k
n
o
w
n
as
th
e
ab
n
o
r
m
ali
t
y
o
f
e
n
h
an
ci
n
g
h
u
m
a
n
ce
ll
s
an
d
co
n
v
er
tin
g
t
h
e
m
i
n
to
a
tu
m
o
r
[
2
]
.
Am
o
n
g
th
e
v
ar
io
u
s
f
o
r
m
s
o
f
ca
n
ce
r
,
l
u
n
g
a
n
d
b
r
ea
s
t
ca
n
ce
r
ar
e
en
u
m
er
ated
a
s
th
e
r
i
s
k
iest
w
h
e
n
co
m
p
ar
ed
to
th
e
o
th
er
t
y
p
es
a
r
o
u
n
d
th
e
g
lo
b
e.
B
r
ea
s
t
ca
n
ce
r
is
th
e
m
o
s
t
co
m
m
o
n
t
y
p
e
o
f
ca
n
ce
r
in
w
o
m
e
n
w
it
h
d
e
n
s
er
b
r
ea
s
t
tis
s
u
e
d
u
e
to
its
p
h
y
s
io
lo
g
ical
f
ea
tu
r
e
s
.
I
t
is
o
n
e
o
f
t
h
e
m
o
s
t
s
i
g
n
if
ica
n
t
r
ea
s
o
n
s
f
o
r
w
o
m
en
’
s
d
ea
th
.
A
cc
o
r
d
in
g
to
th
e
d
o
cto
r
'
s
v
ie
w
,
th
e
m
o
s
t
e
s
s
e
n
tial
f
ac
to
r
th
a
t
ca
u
s
es
l
u
n
g
-
ca
n
ce
r
i
s
to
b
ac
co
.
Am
o
n
g
g
e
n
d
er
s
,
t
h
e
m
ale
is
m
o
r
e
f
ac
ed
w
it
h
l
u
n
g
-
ca
n
ce
r
t
h
an
f
e
m
ale
d
u
e
to
t
h
e
h
i
g
h
er
r
atio
o
f
s
m
o
k
i
n
g
[
3
]
.
Fo
r
in
s
ta
n
ce
s
,
ac
co
r
d
in
g
to
a
r
ep
o
r
t
w
h
ic
h
s
h
o
w
ed
th
a
t
a
m
o
n
g
(
1
1
6
,
4
7
0
)
m
ale
s
an
d
(
1
0
9
,
6
9
0
)
f
e
m
ale
s
,
(
8
7
,
7
5
0
)
m
ales
an
d
(
7
2
,
5
9
0
)
f
e
m
ales
w
er
e
d
ied
b
ec
au
s
e
o
f
lu
n
g
-
ca
n
ce
r
.
I
n
t
h
e
w
o
r
ld
,
m
e
r
el
y
o
n
e
f
r
o
m
f
iv
e
d
ea
th
s
i
s
d
u
e
to
s
m
o
k
in
g
a
n
d
u
ti
lizi
n
g
to
b
ac
co
[
4
]
.
I
n
d
ee
d
,
t
h
er
e
ar
e
t
w
o
m
aj
o
r
t
y
p
es
o
f
lu
n
g
-
ca
n
ce
r
[
5
]
,
[
6
]
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8776
I
n
t J
I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
10
,
No
.
2,
A
u
g
u
s
t
20
21
:
9
3
–
1
0
3
94
th
e
f
ir
s
t
o
n
e
is
n
a
m
ed
n
o
n
-
s
m
all
-
ce
ll
ca
n
ce
r
o
f
lu
n
g
(
NS
C
C
L
)
t
h
is
t
y
p
e
f
u
r
th
er
ca
te
g
o
r
ized
in
to
s
q
u
a
m
o
u
s
-
ce
ll
ca
r
cin
o
m
a
w
h
ich
w
as
co
n
s
ti
tu
ted
ap
p
r
o
x
i
m
atel
y
2
5
%
to
3
0
%
o
f
all
lu
n
g
-
ca
n
ce
r
,
an
d
ad
en
o
ca
r
cin
o
m
a
w
h
ic
h
c
o
m
p
r
is
ed
o
f
n
ea
r
l
y
4
0
%
o
f
lu
n
g
ca
n
ce
r
.
T
h
is
is
co
u
n
ted
as
th
e
m
o
s
t
co
m
m
o
n
l
u
n
g
-
ca
n
ce
r
t
y
p
e
th
a
t
h
as b
ee
n
s
ee
n
i
n
p
eo
p
le
w
h
o
ar
e
n
o
t s
m
o
k
in
g
esp
ec
iall
y
w
o
m
en
a
n
d
y
o
u
th
p
eo
p
le
lik
e
tee
n
ag
er
s
an
d
ch
i
ld
r
en
,
an
d
lar
g
e
-
ce
ll c
ar
cin
o
m
a
w
h
ic
h
co
n
s
t
itu
ted
ab
o
u
t 1
0
-
1
5
% o
f
n
o
n
-
s
m
all
-
ce
ll c
a
n
ce
r
o
f
lu
n
g
.
Ho
w
e
v
er
,
th
e
s
ec
o
n
d
t
y
p
e
is
n
a
m
ed
s
m
all
-
ce
ll
ca
n
ce
r
o
f
lu
n
g
(
SC
C
L
)
.
Me
r
el
y
1
0
%
to
1
5
%
w
er
e
o
cc
u
p
ied
u
p
b
y
t
h
i
s
f
o
r
m
.
S
m
o
k
er
s
w
er
e
s
u
f
f
er
ed
m
o
s
t
f
r
o
m
t
h
i
s
k
i
n
d
o
f
l
u
n
g
-
ca
n
ce
r
[
7
]
.
T
h
e
p
r
o
ce
s
s
o
f
d
iag
n
o
s
i
n
g
lu
n
g
an
d
b
r
ea
s
t
ca
n
ce
r
is
th
e
m
a
in
p
r
o
b
le
m
an
d
ch
alle
n
g
i
n
g
tas
k
d
u
e
to
its
h
ig
h
co
s
t.
T
h
er
e
w
er
e
n
u
m
er
o
u
s
m
et
h
o
d
s
to
d
iag
n
o
s
e
lu
n
g
a
n
d
b
r
ea
s
t
ca
n
ce
r
s
u
ch
as
ch
e
s
t
-
r
ad
io
g
r
a
p
h
y
‘X
-
R
a
y
’
,
C
T
-
Scan
,
a
n
d
m
ag
n
etic
-
r
eso
n
an
ce
-
i
m
a
g
i
n
g
‘
MRI
-
Sca
n
’
[
8
]
.
C
o
n
v
er
s
e
l
y
,
m
o
s
t
o
f
t
h
e
s
e
m
et
h
o
d
s
w
er
e
co
s
tl
y
a
n
d
ti
m
e
s
p
en
d
in
g
.
Mo
r
eo
v
er
,
th
ese
m
e
th
o
d
s
w
er
e
id
en
ti
f
y
i
n
g
t
h
e
lu
n
g
an
d
b
r
ea
s
t
ca
n
ce
r
o
u
s
n
o
d
u
le
s
in
th
eir
ad
v
a
n
ce
d
p
er
io
d
s
,
s
o
th
e
s
u
r
v
i
v
al
r
ate
w
il
l
b
e
q
u
ite
lo
w
.
C
o
n
s
eq
u
e
n
tl
y
,
a
n
e
w
m
ac
h
in
er
y
to
o
l
w
a
s
q
u
i
te
n
ec
es
s
ar
y
to
di
ag
n
o
s
e
t
h
e
l
u
n
g
an
d
b
r
ea
s
t
c
an
ce
r
o
u
s
n
o
d
u
les i
n
t
h
eir
in
it
i
al
s
tag
e
s
[
9
]
.
T
h
e
m
o
s
t
cr
itical
ap
p
r
o
ac
h
f
o
r
p
r
ed
ictin
g
an
d
d
etec
tin
g
ca
n
c
er
ce
lls
is
to
u
tili
ze
th
e
m
ec
h
a
n
is
m
s
a
n
d
class
i
f
icatio
n
tec
h
n
iq
u
es
o
f
d
a
ta
-
m
i
n
in
g
w
h
ic
h
i
s
m
o
s
tl
y
u
s
e
d
to
d
ay
in
th
e
w
o
r
ld
b
y
d
o
cto
r
s
an
d
r
esear
c
h
er
s
.
T
h
is
to
p
ic
attr
ac
ted
s
ev
er
al
r
esear
ch
er
s
to
p
r
o
p
o
s
e
an
d
en
h
a
n
ce
an
i
n
tellec
tu
al
s
y
s
te
m
f
o
r
esti
m
atio
n
,
r
ec
o
g
n
itio
n
,
an
d
cla
s
s
i
f
icatio
n
o
f
n
o
n
-
m
a
lig
n
a
n
t
a
n
d
m
al
ig
n
an
t
ce
lls
b
ased
o
n
t
h
e
d
ata
-
m
i
n
in
g
m
ec
h
an
is
m
s
an
d
alg
o
r
ith
m
s
.
E
v
er
y
d
a
y
a
h
u
g
e
a
m
o
u
n
t
o
f
d
ata
ab
o
u
t
p
atien
ts
ar
e
s
to
r
ed
in
t
h
e
h
o
s
p
ital
d
atab
ases
,
s
o
ex
tr
ac
ti
n
g
p
o
ten
tia
l
p
atter
n
s
o
r
k
n
o
w
led
g
e
f
r
o
m
t
h
ese
m
as
s
iv
e
r
a
w
d
ata
i
s
ex
tr
e
m
el
y
s
i
g
n
i
f
ican
t
th
i
s
ca
n
b
e
d
o
n
e
w
ith
th
e
h
e
lp
o
f
n
e
w
s
cien
ce
t
h
at
i
s
r
e
f
er
r
ed
to
as
d
ata
-
m
in
i
n
g
[
1
0
]
.
A
d
ata
-
m
i
n
in
g
o
r
‘
D
-
M
’
is
a
n
u
m
er
ical
ap
p
r
o
ac
h
th
at
is
co
u
n
ted
as
a
u
s
er
-
f
r
ien
d
lier
in
r
e
p
o
r
ts
p
r
esen
tatio
n
an
d
er
r
o
r
r
e
d
u
ctio
n
.
I
n
s
e
v
er
al
s
ec
to
r
s
to
o
ls
o
f
d
ata
-
m
i
n
i
n
g
ar
e
u
tili
ze
d
in
tak
i
n
g
s
en
s
iti
v
e
d
ec
is
io
n
s
li
k
e
h
ea
lt
h
ca
r
e,
m
ar
k
etin
g
,
b
an
k
i
n
g
,
etc.
P
r
ed
ictio
n
,
d
etec
tio
n
,
an
d
class
if
ica
tio
n
ar
e
b
ased
o
n
tr
ain
i
n
g
s
o
m
e
k
n
o
w
n
v
ar
iab
les
to
est
i
m
ate
t
h
e
u
n
k
n
o
w
n
v
ar
iab
le.
T
h
e
w
id
el
y
u
tili
ze
d
m
ec
h
a
n
i
s
m
s
o
f
d
ata
-
m
i
n
i
n
g
in
al
m
o
s
t
all
t
h
e
s
ec
to
r
s
ar
e
en
u
m
er
ated
as
d
ec
is
io
n
tr
ee
o
r
d
-
tr
ee
,
ar
tif
icial
-
n
eu
r
al
n
et
w
o
r
k
,
o
r
n
et
s
h
o
r
ten
ed
i
n
t
o
A
-
NN,
Na
ïv
e
B
a
y
es
o
r
‘
N
-
B
’
,
s
u
p
p
o
r
t
-
v
ec
to
r
-
m
ac
h
in
e
o
r
‘
SVM
’
,
r
u
le
-
b
ased
class
i
f
ier
,
k
-
n
ea
r
est
n
ei
g
h
b
o
r
o
r
‘
K
-
NN
’
,
etc.
Data
-
m
i
n
i
n
g
i
s
a
cr
itical
s
tag
e
o
f
k
n
o
w
led
g
e
d
is
co
v
er
y
i
n
d
atab
ases
‘
KD
D
’
.
KDD
i
s
co
m
p
r
is
ed
o
f
s
ev
er
al
s
ta
g
es
s
u
c
h
a
s
clea
n
i
n
g
o
f
d
ata,
in
te
g
r
atin
g
o
f
d
ata,
s
elec
ti
n
g
r
elev
an
t
d
ata,
p
atter
n
e
v
al
u
ati
o
n
,
an
d
k
n
o
w
led
g
e
r
ec
o
g
n
itio
n
.
KDD
an
d
d
ata
-
m
i
n
in
g
w
er
e
u
tili
ze
d
alter
n
ate
l
y
[
1
1
]
.
T
h
e
m
ain
o
b
j
ec
tiv
e
o
f
t
h
is
s
t
u
d
y
is
to
g
i
v
e
a
s
y
s
te
m
atic
r
ev
i
e
w
o
f
t
h
e
u
p
-
to
-
d
ate
r
esear
ch
p
ap
er
s
th
at
p
r
o
p
o
s
ed
a
s
y
s
te
m
to
d
ia
g
n
o
s
e
lu
n
g
a
n
d
b
r
ea
s
t
ca
n
ce
r
b
y
u
s
in
g
t
h
e
m
o
s
t
e
s
s
e
n
tial
tec
h
n
i
q
u
es
a
n
d
class
i
f
ier
alg
o
r
ith
m
s
o
f
d
ata
-
m
in
in
g
.
T
h
is
r
ev
ie
w
ar
ticle
i
s
i
m
p
o
r
tan
t
f
o
r
n
e
w
r
esear
ch
er
s
w
h
o
i
n
ter
e
s
t
to
d
o
r
esear
ch
o
r
r
ev
ie
w
ar
ticles i
n
t
h
e
m
ed
ical
d
iag
n
o
s
i
s
er
a.
T
h
e
ar
r
an
g
e
m
e
n
t
o
f
t
h
e
o
t
h
er
s
ec
tio
n
s
is
as
f
o
llo
w
s
:
i
n
s
ec
t
i
o
n
2
th
e
o
th
er
r
esear
c
h
er
's
w
o
r
k
h
a
s
b
ee
n
r
ev
ie
w
ed
an
d
p
r
esen
ted
.
T
h
e
co
n
ce
p
t
o
f
d
ata
m
i
n
in
g
alo
n
g
w
it
h
k
n
o
w
led
g
e
d
is
co
v
er
y
i
n
d
atab
ases
h
as
b
ee
n
d
is
cu
s
s
ed
in
s
ec
tio
n
3
.
Secti
o
n
4
is
ab
o
u
t
th
e
m
o
s
t
r
en
o
w
n
ed
class
i
f
icatio
n
alg
o
r
it
h
m
s
in
d
ata
m
in
in
g
.
A
co
m
p
ar
is
o
n
b
et
w
ee
n
v
ar
io
u
s
class
if
ier
s
an
d
alg
o
r
ith
m
s
i
n
ter
m
s
o
f
ac
cu
r
ac
y
ar
e
d
r
a
w
n
in
s
ec
tio
n
5
.
Ulti
m
a
tel
y
,
s
ec
tio
n
6
is
t
h
e
p
ap
er
’
s
co
n
cl
u
s
io
n
.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
R
ec
en
t
l
y
,
m
an
y
r
esear
ch
er
s
p
r
o
p
o
s
ed
an
ef
f
icie
n
t
lu
n
g
an
d
b
r
ea
s
t
ca
n
ce
r
d
iag
n
o
s
is
s
y
s
te
m
to
p
r
ed
ict
an
d
d
etec
t
ca
n
ce
r
o
u
s
n
o
d
u
les
in
t
h
eir
in
i
tial
s
ta
g
es
an
d
a
s
s
i
s
t
th
e
d
o
cto
r
s
to
id
e
n
ti
f
y
ca
n
ce
r
o
u
s
n
o
d
u
les
ea
s
il
y
in
p
atien
t
’
s
lu
n
g
an
d
b
r
ea
s
ts
.
I
n
th
i
s
s
ec
tio
n
,
r
elev
a
n
t u
p
-
to
-
d
ate
r
esear
ch
p
ap
er
s
h
av
e
b
ee
n
r
ev
ie
w
ed
.
Z
u
b
i
an
d
Saad
,
[
1
2
]
in
t
h
is
p
a
p
er
s
ev
er
al
cr
itical
p
r
o
ce
s
s
es
o
f
m
ed
ical
i
m
a
g
e
m
i
n
i
n
g
w
er
e
ex
a
m
in
ed
s
u
c
h
as
p
r
e
-
p
r
o
ce
s
s
in
g
o
f
d
a
t
a,
ex
tr
ac
ti
n
g
o
f
f
ea
tu
r
e
s
,
o
r
ch
ar
ac
ter
is
tic
s
,
an
d
r
u
le
g
e
n
er
a
tin
g
w
it
h
t
h
e
m
o
s
t
i
m
p
o
r
tan
t
cla
s
s
i
f
ier
m
ec
h
an
is
m
w
h
ic
h
n
a
m
ed
n
e
u
r
al
n
et
w
o
r
k
.
T
h
e
m
ai
n
ai
m
o
f
t
h
is
s
t
u
d
y
w
as
to
clas
s
i
f
y
th
e
ch
est
x
-
r
a
y
an
d
ca
te
g
o
r
ized
in
to
t
w
o
cla
s
s
es
:
u
s
u
al
a
n
d
u
n
u
s
u
al.
A
s
a
co
n
s
eq
u
en
ce
,
i
f
t
h
e
ce
ll
w
as
n
o
r
m
al,
th
en
t
h
e
p
atie
n
t
w
a
s
h
ea
lt
h
y
.
On
t
h
e
o
t
h
er
h
an
d
,
t
h
e
ab
n
o
r
m
al
ce
l
l
i
n
d
icate
d
t
h
at
t
h
e
p
at
ien
t
w
as
u
n
h
ea
l
th
y
an
d
h
ad
a
f
o
r
m
o
f
l
u
n
g
ca
n
ce
r
.
T
h
is
ca
teg
o
r
izatio
n
h
elp
ed
d
o
cto
r
s
in
d
ec
id
in
g
a
s
i
g
n
i
f
ica
n
t
d
ec
is
io
n
ab
o
u
t
t
h
e
p
atien
t
’
s
h
ea
lt
h
a
n
d
also
i
n
cr
e
ase
th
e
r
ate
o
f
s
u
r
v
i
v
al.
F
u
r
th
er
m
o
r
e,
th
e
i
n
v
esti
g
atio
n
h
a
s
b
ee
n
d
o
n
e
ab
o
u
t
t
h
e
u
s
e
o
f
a
s
s
o
ciatio
n
r
u
les
i
n
t
h
e
is
s
u
e
o
f
ch
e
s
t
x
-
r
a
y
lab
elin
g
.
T
h
e
ch
est
x
-
r
a
y
h
ad
b
ee
n
o
b
tain
ed
an
d
co
llected
in
m
a
s
s
i
v
e
m
u
lti
m
ed
ia
d
atab
ases
w
h
ich
w
er
e
s
to
r
ied
f
o
r
th
e
m
ed
ical
in
ten
d
.
Kh
ar
y
a
,
[
1
3
]
d
if
f
er
en
t
clas
s
i
f
ier
m
ec
h
an
is
m
s
h
a
v
e
b
ee
n
p
r
o
p
o
s
ed
to
id
en
tify
a
n
d
est
i
m
ate
b
r
ea
s
t
-
ca
n
ce
r
.
T
h
ese
clas
s
i
f
ier
s
h
ad
b
ee
n
u
s
ed
A
NN,
C
4
.
5
,
Naïv
e
-
B
a
y
es,
a
n
d
D
-
T
r
ee
.
T
h
e
o
u
tco
m
e
ac
cu
r
ac
y
i
s
as
f
o
llo
w
ed
8
6
.
5
%,
8
6
.
7
%,
8
4
.
5
%,
an
d
9
3
.
6
2
%,
r
esp
ec
tiv
el
y
.
B
r
ea
s
t
-
C
a
n
ce
r
id
e
n
ti
f
icatio
n
i
s
ab
o
u
t
d
if
f
er
e
n
tiati
n
g
b
en
i
g
n
f
r
o
m
m
alig
n
an
t
b
r
ea
s
t
tu
m
o
r
s
,
w
h
ile
t
h
e
b
r
ea
s
t
-
ca
n
ce
r
est
i
m
a
tio
n
e
x
p
ec
ts
w
h
e
n
b
r
ea
s
t
-
ca
n
ce
r
is
r
ea
p
p
ea
r
ed
in
p
atien
ts
th
a
t
h
ad
ca
n
ce
r
t
u
m
o
r
p
r
ev
io
u
s
l
y
.
Se
v
er
al
d
if
f
er
e
n
t
s
u
r
v
e
y
s
an
d
p
r
ac
tica
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8776
Da
ta
min
in
g
tech
n
iq
u
es fo
r
lu
n
g
a
n
d
b
r
ea
s
t c
a
n
ce
r
d
ia
g
n
o
s
is
:
A
r
ev
iew
(
B
a
kh
a
n
To
fiq
A
h
med
)
95
ar
ticles
o
n
b
r
ea
s
t
-
ca
n
ce
r
d
iag
n
o
s
is
a
n
d
p
r
o
g
n
o
s
is
h
av
e
b
ee
n
r
ev
ie
w
ed
.
T
h
is
p
ap
er
co
n
ce
n
tr
ated
o
n
u
p
-
to
-
d
ate
r
esear
ch
es t
h
at
u
t
ilized
th
e
d
at
a
-
m
in
in
g
m
ec
h
a
n
is
m
s
to
i
m
p
r
o
v
e
th
e
b
r
ea
s
t
-
ca
n
ce
r
f
in
d
i
n
g
an
d
g
u
ess
in
g
.
C
h
a
n
d
r
a
et
a
l
.,
[
1
4
]
an
ef
f
ec
ti
v
e
as
s
o
ciativ
e
r
u
le
th
at
u
s
ed
t
h
e
g
en
etic
alg
o
r
it
h
m
f
o
r
p
r
ed
ictin
g
t
h
r
ee
d
if
f
er
e
n
t
d
is
ea
s
e
s
w
h
ic
h
w
er
e
d
iab
etes,
b
r
ea
s
t
-
ca
n
ce
r
,
an
d
h
ea
r
t
h
av
e
b
ee
n
m
o
d
eled
.
T
h
e
m
ai
n
in
s
p
ir
atio
n
f
o
r
u
s
i
n
g
th
e
g
e
n
etic
al
g
o
r
i
th
m
[
1
5
]
,
[
16]
w
as
to
d
is
co
v
er
p
r
ed
ictiv
e
r
u
le
s
t
h
at
w
er
e
h
i
g
h
l
y
u
n
d
er
s
ta
n
d
ab
le
an
d
g
iv
e
n
h
ig
h
p
r
ed
ictiv
e
ac
cu
r
a
c
y
.
T
h
e
o
u
tco
m
e
s
in
d
icate
d
th
at
m
o
s
t
o
f
th
e
clas
s
i
f
ier
r
u
les
p
r
ed
icted
h
ea
r
t
d
is
ea
s
e
w
ith
t
h
e
h
i
g
h
e
s
t
a
cc
u
r
ac
y
w
h
ic
h
w
as
9
8
%
w
h
en
co
m
p
ar
ed
w
it
h
d
iab
etes
an
d
b
r
e
ast
-
ca
n
ce
r
ac
cu
r
ac
y
w
h
ic
h
w
er
e
8
2
% a
n
d
8
4
.
8
%,
r
esp
ec
tiv
el
y
.
So
w
m
i
y
a
et
a
l
.
,
[
1
7
]
n
u
m
er
o
u
s
s
id
es
o
f
d
ata
-
m
i
n
i
n
g
m
et
h
o
d
s
h
av
e
b
ee
n
r
ev
is
ed
to
esti
m
ate
l
u
n
g
-
ca
n
ce
r
t
u
m
o
r
s
.
T
h
e
co
n
ce
p
ts
o
f
d
ata
-
m
in
i
n
g
ar
e
e
x
tr
e
m
e
l
y
h
elp
f
u
l
f
o
r
cla
s
s
i
f
y
in
g
ca
n
ce
r
o
u
s
an
d
n
o
n
-
ca
n
ce
r
o
u
s
t
u
m
o
r
s
.
T
h
e
an
t
-
c
o
lo
n
y
o
p
ti
m
izat
io
n
m
eth
o
d
h
ad
b
ee
n
test
ed
b
ec
au
s
e
i
t
w
a
s
a
q
u
ite
u
s
e
f
u
l
tech
n
iq
u
e
f
o
r
p
r
ed
ictin
g
d
is
ea
s
e.
I
n
th
i
s
s
t
u
d
y
,
b
o
th
d
ata
-
m
i
n
in
g
a
n
d
an
t
-
co
lo
n
y
o
p
ti
m
izat
io
n
m
et
h
o
d
s
h
a
v
e
b
ee
n
m
i
x
ed
f
o
r
g
e
n
er
ati
n
g
p
r
o
p
er
r
u
le
an
d
class
i
f
icatio
n
,
w
h
ic
h
w
as
e
x
p
er
i
m
e
n
tal
to
cr
ea
te
ac
cu
r
ate
lu
n
g
-
ca
n
ce
r
class
i
f
icat
io
n
s
.
Mo
r
eo
v
er
,
it
af
f
o
r
d
s
th
e
u
n
co
m
p
lic
ated
f
r
a
m
e
w
o
r
k
f
o
r
ad
d
itio
n
al
en
h
a
n
ce
m
en
t
i
n
m
ed
ical
an
al
y
s
is
o
n
l
u
n
g
-
ca
n
ce
r
.
T
h
e
id
ea
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
r
elied
o
n
r
ed
u
ce
d
-
o
r
d
er
co
n
s
tr
ain
ed
o
p
tim
izatio
n
‘
R
OC
O’
w
h
ic
h
w
a
s
an
o
p
ti
m
al
d
ata
-
m
in
i
n
g
m
eth
o
d
to
m
a
k
e
a
u
to
m
a
ti
c
an
d
q
u
ic
k
I
MRT
s
tr
ateg
ie
s
f
o
r
p
r
o
g
r
ess
iv
e
lu
n
g
-
ca
n
ce
r
id
e
n
ti
f
icatio
n
.
T
h
e
‘
R
OC
O
’
e
f
f
ic
ien
t
l
y
w
o
r
k
ed
w
it
h
th
e
c
u
r
e
p
lan
n
i
n
g
s
y
s
te
m
w
h
ic
h
w
a
s
u
til
ized
at
Slo
an
-
Ketter
i
n
g
C
en
ter
f
o
r
d
etec
tin
g
lu
n
g
-
ca
n
ce
r
.
P
an
p
ali
y
a
et
a
l.
,
[
1
8
]
p
r
o
p
o
s
e
d
an
o
n
lin
e
class
i
f
icat
io
n
s
y
s
t
e
m
f
o
r
b
o
th
p
r
ed
ictio
n
an
d
d
e
tectio
n
o
f
lu
n
g
m
ali
g
n
an
c
y
.
T
w
o
m
ai
n
co
n
ce
p
ts
h
a
v
e
b
ee
n
co
m
b
i
n
e
d
w
h
ich
ar
e
i
m
a
g
e
p
r
o
ce
s
s
in
g
an
d
d
ata
m
in
i
n
g
tech
n
iq
u
es.
His
to
g
r
a
m
eq
u
ali
za
tio
n
is
u
ti
lized
u
n
d
er
th
e
c
o
n
ce
p
t
o
f
i
m
ag
e
p
r
o
ce
s
s
in
g
f
o
r
f
ea
tu
r
e
e
x
tr
ac
tio
n
alo
n
g
w
it
h
a
n
ar
ti
f
icial
n
e
u
r
al
n
et
cla
s
s
if
ier
to
ch
ec
k
t
h
e
p
at
ien
t
’
s
s
tate
w
h
et
h
er
t
h
e
ce
ll
is
ca
n
ce
r
o
u
s
o
r
n
o
n
-
ca
n
ce
r
o
u
s
.
De
te
ctio
n
a
n
d
p
r
ed
ictio
n
o
f
a
ca
n
ce
r
o
u
s
ce
l
l
i
n
it
s
in
itial
s
ta
g
es
w
i
ll
h
elp
b
o
th
d
o
cto
r
s
an
d
p
atien
t
s
in
d
ec
id
i
n
g
tr
ea
t
m
en
t
a
n
d
d
i
m
in
is
h
i
n
g
t
h
e
d
i
s
ea
s
e
r
i
s
k
.
T
h
e
m
ai
n
ad
v
a
n
ta
g
es
o
f
th
is
p
r
o
p
o
s
ed
s
y
s
te
m
ar
e
co
s
t
i
m
p
r
ess
i
v
e
a
n
d
ti
m
e
-
s
a
v
i
n
g
.
P
au
l
et
a
l
.
,
[
1
9
]
th
is
r
e
s
ea
r
ch
,
ap
p
lied
th
e
tr
an
s
f
er
lear
n
i
n
g
c
o
n
ce
p
t
‘
T
L
C
’
to
lear
n
k
n
o
w
le
d
g
e
an
d
a
p
r
e
-
tr
ain
ed
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
et
‘
C
NN’
to
ex
tr
ac
t
d
ee
p
f
ea
tu
r
es
f
r
o
m
l
u
n
g
ca
n
ce
r
co
m
p
u
ted
to
m
o
g
r
ap
h
y
‘
C
T
’
i
m
a
g
es
an
d
later
t
h
e
cla
s
s
if
ier
h
a
s
b
ee
n
tr
ain
ed
to
p
r
ed
i
ct
th
e
s
u
r
v
i
v
o
r
s
.
T
h
e
o
u
tco
m
e
s
d
e
m
o
n
s
tr
ated
t
h
at
th
e
ac
cu
r
ac
y
o
f
7
7
.
5
%
h
as
b
ee
n
g
ai
n
ed
w
h
en
a
p
r
e
-
tr
ain
e
d
C
NN
is
u
tili
ze
d
w
ith
1
0
f
ea
tu
r
es.
A
f
ter
th
a
t,
h
ig
h
er
ac
c
u
r
ac
y
o
f
8
2
.
5
%
h
a
s
b
ee
n
o
b
tain
ed
w
h
e
n
u
p
p
er
5
f
ea
tu
r
es
f
r
o
m
b
o
th
a
p
r
e
-
tr
ain
ed
C
NN
a
n
d
th
e
KNN
‘
K
-
n
ea
r
est n
e
ig
h
b
o
r
w
e
r
e
m
er
g
ed
.
L
y
n
c
h
et
a
l
.,
[
2
0
]
u
n
s
u
p
er
v
is
e
d
m
ac
h
in
e
lear
n
i
n
g
a
n
d
cl
u
s
te
r
in
g
h
ad
b
ee
n
ap
p
lied
to
t
h
e
h
u
g
e
p
atien
t
ca
s
es
w
h
o
h
ad
l
u
n
g
-
ca
n
ce
r
p
r
ev
io
u
s
l
y
.
T
h
e
m
ain
ai
m
o
f
t
h
is
w
o
r
k
w
as
to
p
r
ed
ict
th
e
r
ate
o
f
s
u
r
v
i
v
al
o
f
p
atien
ts
.
Me
r
el
y
(
1
0
,
4
4
2
)
ca
s
es
h
a
v
e
b
ee
n
co
llected
f
o
r
t
h
i
s
ex
p
er
i
m
e
n
tal
s
tu
d
y
f
r
o
m
th
e
lar
g
es
t
US
A
d
ata
r
ep
o
s
ito
r
y
n
a
m
ed
Su
r
v
eilla
n
c
e
E
p
id
em
io
lo
g
y
E
n
d
R
es
u
lts
‘
SEE
R
’
d
atab
ase.
T
h
e
‘
SE
E
R
’
is
a
co
n
f
id
en
t
ca
n
c
er
r
ep
o
s
ito
r
y
i
n
th
e
U
S
A
.
An
o
th
er
o
b
j
ec
tiv
e
w
as
to
au
to
m
atica
ll
y
cla
s
s
i
f
y
lu
n
g
-
ca
n
ce
r
tu
m
o
r
s
in
to
co
llectio
n
s
ac
co
r
d
in
g
to
a
cli
n
ical
m
ea
s
u
r
e
to
p
r
ed
icate
s
u
r
v
iv
al
r
ate.
P
r
i
m
ar
ies
No
.
,
Ag
e,
C
a
n
ce
r
’
s
R
a
n
k
,
Size
o
f
L
u
m
p
,
a
n
d
Stag
e
w
er
e
v
ar
iab
les
t
h
at
w
er
e
s
e
lecte
d
a
s
th
e
m
ac
h
i
n
e
lear
n
i
n
g
in
p
u
ts
.
T
h
e
o
u
tco
m
e
w
a
s
u
s
ed
to
esti
m
ate
t
h
e
s
u
r
v
iv
a
l
p
er
io
d
.
A
f
ter
th
a
t,
a
l
in
ea
r
r
eg
r
ess
io
n
w
as
ca
r
r
ied
o
u
t
a
g
ai
n
s
t
ea
ch
u
n
s
u
p
er
v
i
s
ed
o
u
tco
m
e.
T
h
e
o
u
tco
m
e
s
h
av
e
b
ee
n
co
m
p
ar
ed
b
y
u
s
i
n
g
a
r
o
o
t
-
m
ea
n
-
s
q
u
ar
ed
-
er
r
o
r
‘
R
M
SE’
w
h
ic
h
w
as
a
n
ev
alu
a
tio
n
m
etr
ic.
T
h
e
o
u
tco
m
es
d
e
m
o
n
s
tr
ated
t
h
at
s
el
f
o
r
d
er
in
g
m
ap
s
‘
S
OM
’
g
av
e
th
e
b
est
p
er
f
o
r
m
a
n
ce
.
Ho
w
e
v
er
,
K
-
Me
a
n
s
co
u
n
ted
a
s
s
i
m
p
ler
class
i
f
ier
m
eth
o
d
s
.
O
m
ar
et
a
l
.,
[
2
1
]
p
r
o
p
o
s
ed
a
n
e
w
s
y
s
te
m
to
d
etec
t
an
d
p
r
e
d
ict
a
p
ar
ticu
lar
ca
n
ce
r
f
o
r
m
w
h
ic
h
w
a
s
lu
n
g
-
ca
n
ce
r
.
T
h
e
s
y
s
te
m
is
ca
l
led
lu
n
g
-
ca
n
ce
r
p
r
o
g
n
o
s
is
s
y
s
t
e
m
‘L
-
C
P
S’
.
T
h
r
ee
s
i
g
n
if
ican
t
m
et
h
o
d
s
h
ad
b
ee
n
ap
p
lied
w
h
ich
w
er
e
J
4
.
8
,
Naïv
e
-
B
a
y
es,
a
n
d
K
-
n
ea
r
es
t
n
e
ig
h
b
o
r
.
T
h
e
ac
cu
r
ac
y
g
ain
ed
f
r
o
m
t
h
ese
cla
s
s
i
f
ier
s
w
a
s
8
9
.
3
%,
8
0
.
2
%,
an
d
8
9
.
6
%,
r
esp
ec
tiv
el
y
.
T
h
e
m
a
in
o
b
j
ec
tiv
e
o
f
p
r
o
p
o
s
in
g
t
h
is
in
telli
g
en
t
s
y
s
te
m
w
a
s
to
h
elp
p
h
y
s
ician
s
w
i
th
an
ac
cu
r
ate
ass
e
s
s
m
e
n
t
o
f
t
h
e
p
atie
n
t
’
s
h
ea
lth
s
tatu
s
.
I
n
t
h
is
s
y
s
te
m
,
b
o
th
d
ata
-
m
i
n
i
n
g
an
d
ar
tific
ial
-
in
telli
g
en
c
e
w
er
e
ass
o
r
ted
to
cr
ea
te
a
u
s
er
-
f
r
ien
d
lier
to
o
l
f
o
r
s
u
p
p
l
y
in
g
in
f
o
r
m
atio
n
ab
o
u
t
a
p
atien
t
’
s
s
tat
u
s
w
h
ich
w
as
le
ad
in
g
to
e
n
h
a
n
ce
p
atie
n
t
cu
r
e
s
.
A
d
i
v
er
s
it
y
o
f
L
u
n
g
-
C
an
ce
r
d
atasets
co
u
ld
b
e
ad
m
itted
in
to
‘
L
-
C
P
S’
a
n
d
af
f
o
r
d
ed
p
h
y
s
icia
n
s
w
i
th
n
u
m
e
r
o
u
s
s
tati
s
tical
o
u
tco
m
es
co
n
t
ain
i
n
g
e
s
ti
m
atio
n
s
ab
o
u
t
th
eir
p
atien
ts
’
s
tat
u
s
.
A
d
d
itio
n
al
l
y
,
th
e
r
ec
o
r
d
s
o
f
th
e
p
atien
t
w
er
e
ea
s
il
y
m
a
n
ag
ed
b
y
‘
L
-
C
P
S
’
,
p
er
m
i
tted
th
e
m
to
v
ie
w
t
h
eir
s
u
m
m
ar
ie
s
,
an
d
co
m
p
r
is
i
n
g
p
r
ed
ictio
n
o
r
an
y
o
t
h
er
ex
p
la
n
ati
o
n
s
.
Fi
n
all
y
,
w
h
ile
th
e
‘
L
-
C
P
S
w
as
p
r
esen
tl
y
r
est
r
icted
to
a
p
ar
ticu
lar
c
an
ce
r
f
o
r
m
,
b
u
t
it
co
u
ld
b
e
m
ea
s
u
r
ed
as
a
p
r
o
to
ty
p
e
t
h
a
t
co
u
ld
b
e
im
p
r
o
v
ed
to
p
r
ed
ict
o
th
er
d
is
ea
s
es i
n
th
e
f
u
t
u
r
e.
B
h
ar
ati
et
a
l.
,
[
2
2
]
in
th
i
s
r
esear
ch
s
t
u
d
y
a
b
r
ea
s
t
ca
n
ce
r
d
iag
n
o
s
i
s
s
y
s
te
m
h
as
b
ee
n
p
r
o
p
o
s
ed
b
y
u
s
i
n
g
class
if
ier
s
li
k
e
Naïv
e
B
a
y
es
(
NB
)
,
r
an
d
o
m
f
o
r
est
(
R
F
)
,
lo
g
is
tic
r
eg
r
es
s
io
n
(
L
R
)
,
m
u
ltil
a
y
er
p
er
ce
p
tr
o
n
(
ML
P
)
,
an
d
k
-
n
ea
r
est
n
ei
g
h
b
o
r
s
(
KNN)
.
T
h
e
clas
s
if
ier
s
a
lg
o
r
ith
m
s
h
av
e
b
ee
n
i
m
p
le
m
en
ted
t
h
r
o
u
g
h
th
e
W
E
KA
d
ata
m
in
in
g
to
o
l.
T
h
e
i
m
a
g
e
d
atasets
h
a
v
e
b
ee
n
co
llected
f
r
o
m
t
h
e
UC
I
m
ac
h
in
e
l
ea
r
n
in
g
r
ep
o
s
ito
r
y
.
T
h
e
UC
I
co
n
s
is
t
s
o
f
2
8
6
in
s
t
an
ce
s
.
T
h
e
e
x
p
er
i
m
e
n
tal
r
esu
l
ts
s
h
o
w
ed
t
h
at
KNN
w
a
s
ac
c
u
r
ate
t
h
an
t
h
e
o
t
h
er
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8776
I
n
t J
I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
10
,
No
.
2,
A
u
g
u
s
t
20
21
:
9
3
–
1
0
3
96
class
i
f
ier
s
b
ec
au
s
e
it
co
r
r
ec
tl
y
class
i
f
ied
2
0
7
in
s
tan
ce
s
o
u
t
o
f
2
8
6
in
s
tan
ce
s
th
a
t
w
as
7
2
.
3
7
7
6
%
f
o
llo
w
ed
b
y
Naïv
e
B
a
y
e
s
,
r
an
d
o
m
f
o
r
est,
l
o
g
is
tic
r
e
g
r
ess
io
n
,
an
d
m
u
l
tila
y
er
p
er
ce
p
tr
o
n
th
at
attai
n
ed
7
1
.
6
7
8
3
%,
6
9
.
5
8
0
4
%,
6
8
.
8
8
1
1
%,
an
d
6
4
.
6
8
5
3
%
,
r
esp
ec
tiv
el
y
.
P
o
d
d
er
et
a
l
.
,
[
2
3
]
in
th
is
p
ap
er
a
lu
n
g
ca
n
ce
r
d
iag
no
s
is
s
y
s
te
m
w
as
p
r
o
p
o
s
ed
t
o
p
r
ed
ict
an
d
d
etec
t
ca
n
ce
r
o
u
s
n
o
d
u
les.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
b
ased
o
n
t
h
e
d
if
f
er
en
t c
lass
if
ier
s
li
k
e
Naïv
e
B
a
y
es (
NB
)
,
k
n
ea
r
est
n
eig
h
b
o
r
s
(
KNN)
,
lo
g
is
tic
r
eg
r
ess
io
n
(
L
R
)
,
tr
ee
,
r
an
d
o
m
f
o
r
est
(
R
F),
an
d
n
e
u
r
al
n
et
w
o
r
k
(
NN)
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
clas
s
if
ier
s
h
as
b
ee
n
te
s
ted
b
y
u
s
i
n
g
t
h
e
o
r
a
n
g
e
d
ata
m
i
n
i
n
g
to
o
l.
T
h
e
ex
p
er
i
m
e
n
ta
l
o
u
tco
m
es
i
n
d
icate
d
th
at
Naï
v
e
B
ay
es
(
NB
)
p
r
o
v
id
ed
th
e
h
ig
h
e
s
t
ac
cu
r
ac
y
o
f
5
7
.
0
4
7
%
f
o
llo
w
ed
b
y
r
a
n
d
o
m
f
o
r
e
s
t
(
R
F)
t
h
at
o
b
tain
ed
4
9
.
8
3
2
%
o
f
ac
cu
r
a
cy
.
I
n
ad
d
itio
n
,
th
i
s
s
t
u
d
y
i
m
p
le
m
e
n
ted
p
r
in
cip
al
co
m
p
o
n
e
n
t
an
al
y
s
is
(
P
C
A
)
,
clas
s
i
f
icatio
n
tr
ee
,
m
u
lt
id
i
m
e
n
s
io
n
al
s
ca
li
n
g
(
MD
S),
an
d
h
ier
ar
ch
ical
cl
u
s
t
er
in
g
(
H
C
)
.
A
b
ie
n
,
[
2
4
]
in
t
h
i
s
s
t
u
d
y
a
c
o
m
p
ar
is
o
n
o
f
s
i
x
m
ac
h
i
n
e
le
ar
n
in
g
al
g
o
r
ith
m
s
h
av
e
b
ee
n
p
r
esen
ted
n
a
m
e
l
y
,
g
ated
r
ec
u
r
r
en
t
u
n
it
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
‘
G
R
U
-
SVM
’
,
li
n
ea
r
r
eg
r
ess
io
n
‘
L
R
’
,
m
u
lti
la
y
er
p
er
ce
p
tr
o
n
‘
M
L
P
’
,
k
-
n
ea
r
est
n
ei
g
h
b
o
r
‘
K
-
NN
’
,
s
o
f
t
m
ax
r
eg
r
ess
io
n
‘
SR
’
,
a
n
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
‘
SVM
’
.
T
h
ese
alg
o
r
ith
m
s
ar
e
ap
p
lied
to
a
p
u
b
lic
d
ataset
n
a
m
ed
th
e
W
is
co
n
s
i
n
d
iag
n
o
s
tic
b
r
ea
s
t
ca
n
ce
r
‘
W
DB
C
’
.
Fo
r
t
h
e
i
m
p
le
m
e
n
t
atio
n
o
f
t
h
ese
alg
o
r
it
h
m
s
,
t
h
e
d
ataset
w
a
s
s
p
lit
i
n
to
t
w
o
p
h
ase
s
:
7
0
%
f
o
r
t
h
e
tr
ain
i
n
g
p
h
ase,
an
d
3
0
%
f
o
r
th
e
test
i
n
g
p
h
a
s
e.
E
x
p
er
i
m
en
tal
o
u
tco
m
e
s
s
h
o
w
ed
t
h
at
all
t
h
e
p
r
ese
n
ted
alg
o
r
ith
m
s
p
er
f
o
r
m
ed
v
er
y
w
ell
t
h
at
w
er
e
ex
ce
ed
ed
n
e
ar
l
y
9
0
%
ac
cu
r
ac
y
,
b
u
t
th
e
‘
ML
P
’
alg
o
r
ith
m
o
u
tp
er
f
o
r
m
s
all
t
h
e
o
th
er
s
w
it
h
an
ac
c
u
r
ac
y
o
f
9
9
.
0
4
%.
Mo
n
d
al
et
a
l.
,
[
2
5
]
in
th
is
s
tu
d
y
a
s
y
s
te
m
atic
s
u
r
v
e
y
ab
o
u
t
th
e
ar
tif
icial
n
e
u
r
al
n
et
w
o
r
k
(
ANN)
b
ased
m
o
d
el
s
f
o
r
th
e
d
iag
n
o
s
is
o
f
b
r
ea
s
t
ca
n
ce
r
v
ia
m
a
m
m
o
g
r
a
p
h
y
h
a
s
b
ee
n
p
r
o
v
id
ed
.
T
h
e
m
ai
n
b
en
ef
i
ts
an
d
w
ea
k
n
ess
o
f
v
ar
io
u
s
A
NN
m
o
d
el
s
li
k
e
s
p
ik
i
n
g
n
e
u
r
al
n
et
w
o
r
k
(
S
NN)
,
d
ee
p
b
elief
n
et
w
o
r
k
(
DB
N)
,
co
n
v
o
lu
tio
n
al
n
e
u
r
al
n
et
w
o
r
k
(
C
NN)
,
m
u
l
tila
y
er
n
e
u
r
al
n
et
w
o
r
k
(
ML
NN)
,
s
tac
k
ed
a
u
to
e
n
co
d
er
s
(
S
A
E
)
,
an
d
s
tack
ed
d
en
o
is
i
n
g
au
to
en
co
d
er
s
(
SDA
E
)
h
av
e
b
ee
n
r
ev
ie
w
ed
an
d
p
r
esen
ted
.
T
h
is
r
ev
ie
w
s
t
u
d
y
also
p
r
esen
te
d
a
co
m
p
r
eh
e
n
s
i
v
e
lit
er
atu
r
e
r
ev
ie
w
ab
o
u
t
th
e
s
t
u
d
i
es
r
elate
d
to
a
b
r
ea
s
t
ca
n
ce
r
d
i
ag
n
o
s
is
t
h
at
ap
p
lied
v
ar
io
u
s
d
ee
p
lear
n
in
g
m
o
d
els
to
s
ev
er
al
p
u
b
licl
y
d
atasets
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
r
ev
ie
w
ed
s
t
u
d
ies
w
a
s
co
m
p
ar
ed
ac
co
r
d
in
g
to
v
ar
io
u
s
m
etr
ics
l
ik
e
ac
c
u
r
a
c
y
,
p
r
ec
is
io
n
,
an
d
r
ec
all.
T
h
e
co
m
p
ar
is
o
n
in
d
icate
d
th
a
t
th
e
b
est
p
er
f
o
r
m
a
n
ce
w
as
ac
h
iev
ed
b
y
R
es
id
u
al
Ne
u
r
al
Net
w
o
r
k
(
R
es
Net
-
5
0
an
d
R
es
Net
-
1
0
1
)
m
o
d
els
o
f
t
h
e
C
NN
al
g
o
r
ith
m
.
Mu
h
a
m
m
et,
[
2
6
]
t
h
is
p
ap
er
p
r
o
p
o
s
ed
an
d
test
ed
v
ar
io
u
s
d
at
a
m
i
n
i
n
g
tec
h
n
iq
u
es
f
o
r
th
e
d
etec
tio
n
o
f
b
r
ea
s
t
ca
n
ce
r
.
T
h
e
tech
n
iq
u
e
s
w
er
e
lo
g
is
tic
r
eg
r
e
s
s
io
n
‘
L
R
’
,
k
-
n
ea
r
est
n
ei
g
h
b
o
r
s
‘K
-
N
N’
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
‘
SVM
’
,
Naïv
e
B
a
y
e
s
‘
NB
’
,
d
ec
is
io
n
tr
ee
‘
DT
’
,
r
an
d
o
m
f
o
r
est
’
R
F
’
,
an
d
r
o
tatio
n
f
o
r
est
‘
R
F
’
.
T
h
ese
tech
n
iq
u
es
w
er
e
ap
p
lied
to
p
u
b
lic
d
ata
ab
o
u
t
b
r
ea
s
t
ca
n
ce
r
tu
m
o
r
s
f
r
o
m
Dr
.
W
illi
a
m
H.
W
alb
er
g
o
f
th
e
Un
i
v
er
s
it
y
o
f
W
is
co
n
s
i
n
Ho
s
p
ital.
T
h
e
r
esu
lts
g
ain
ed
w
it
h
t
h
e
‘
L
R
’
s
h
o
w
ed
th
e
h
ig
h
es
t a
cc
u
r
ac
y
o
f
9
8
.
1
%.
B
ased
o
n
th
e
liter
atu
r
e
r
e
v
ie
w
,
i
t
is
f
o
u
n
d
t
h
at
c
lass
if
ica
tio
n
al
g
o
r
ith
m
s
in
d
ata
m
in
i
n
g
h
a
v
e
a
s
ig
n
i
f
ica
n
t
r
o
le
i
n
p
r
o
p
o
s
in
g
e
f
f
icien
t
l
u
n
g
an
d
b
r
ea
s
t
ca
n
ce
r
d
iag
n
o
s
is
s
y
s
te
m
to
i
n
cr
ea
s
e
th
e
s
u
r
v
i
v
al
r
ate
i
n
th
e
w
o
r
ld
.
L
u
n
g
ca
n
ce
r
f
o
r
m
s
ar
e
s
h
o
w
n
i
n
Fi
g
u
r
e
1
,
b
u
t Fig
u
r
e
2
s
h
o
w
s
t
h
e
d
escr
ip
tio
n
o
f
b
r
ea
s
t c
an
ce
r
.
Fig
u
r
e
1
.
T
h
e
f
o
r
m
s
o
f
l
u
n
g
-
c
an
ce
r
[
2
7
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8776
Da
ta
min
in
g
tech
n
iq
u
es fo
r
lu
n
g
a
n
d
b
r
ea
s
t c
a
n
ce
r
d
ia
g
n
o
s
is
:
A
r
ev
iew
(
B
a
kh
a
n
To
fiq
A
h
med
)
97
Fig
u
r
e
2
.
T
h
e
d
escr
ip
tio
n
o
f
b
r
ea
s
t c
an
ce
r
[
2
8
]
.
3.
T
H
E
CO
NC
E
P
T
O
F
DA
T
A
M
I
NING
& K
DD
I
n
t
h
is
s
ec
tio
n
,
a
b
r
ie
f
i
n
tr
o
d
u
ctio
n
ab
o
u
t
k
n
o
w
led
g
e
d
is
co
v
er
y
an
d
d
ata
-
m
i
n
i
n
g
h
a
s
b
ee
n
p
r
o
v
id
ed
.
T
h
e
m
ai
n
s
tep
s
an
d
tas
k
s
o
f
‘
KDD’
a
n
d
d
ata
-
m
i
n
in
g
also
r
e
v
ea
led
s
h
o
r
tl
y
.
3
.
1
.
T
he
m
et
ho
d o
f
k
no
w
ledg
e
dis
co
v
er
y
B
o
th
‘
K
DD
’
a
n
d
‘
D
-
M
’
ar
e
u
tili
ze
d
o
f
te
n
alter
n
atel
y
.
T
h
e
m
et
h
o
d
o
f
ch
a
n
g
in
g
o
r
co
n
v
er
tin
g
r
a
w
d
ata
in
to
k
n
o
w
led
g
e
is
k
n
o
w
n
as
k
n
o
w
led
g
e
d
is
co
v
er
y
p
r
o
ce
s
s
.
I
n
ad
d
itio
n
,
‘
KDD
’
is
th
e
p
r
o
ce
s
s
o
f
ta
k
i
n
g
o
u
t
th
e
n
o
n
-
tr
i
v
ial
i
m
p
lici
t,
p
r
ev
io
u
s
l
y
u
n
f
a
m
iliar
,
a
n
d
cr
iticall
y
b
e
n
ef
icial
k
n
o
w
led
g
e
f
r
o
m
tr
e
m
en
d
o
u
s
d
ata
ac
cu
m
u
lated
i
n
d
atab
ase
s
.
I
n
s
ev
er
al
ca
s
e
s
,
b
o
th
‘
KDD
’
a
n
d
‘
D
-
M
’
ar
e
d
escr
ib
ed
as
an
eq
u
i
v
ale
n
t
w
o
r
d
,
w
h
i
le
in
r
ea
lit
y
;
t
h
e
y
ar
e
d
i
f
f
er
e
n
t
b
ec
au
s
e
‘
D
-
M
’
i
s
th
e
s
i
g
n
i
f
ica
n
t
s
ta
g
e
i
n
‘
KD
D’
a
f
ter
t
h
e
p
r
e
-
p
r
o
ce
s
s
i
n
g
s
tag
e.
Ge
n
er
all
y
,
‘
KDD
’
i
n
c
lu
d
es
t
h
r
ee
p
h
ase
s
n
a
m
e
l
y
,
p
r
e
-
p
r
o
ce
s
s
i
n
g
,
Data
-
Mi
n
i
n
g
,
an
d
p
o
s
t
-
p
r
o
ce
s
s
i
n
g
[
7
]
.
I
n
co
n
tr
ast,
‘
KDD
’
in
d
etails
co
m
p
r
is
es
o
f
th
ese
s
tag
e
s
[
2
6
]
:
3
.
1
.
1
.
Clea
nin
g
o
f
da
t
a
I
t
also
is
k
n
o
w
n
a
s
d
ata
clea
n
s
in
g
,
i
n
t
h
i
s
s
tag
e
n
o
i
s
e,
u
n
r
el
ated
,
an
d
o
u
tl
ier
d
ata
s
h
o
u
ld
b
e
r
e
m
o
v
ed
f
r
o
m
t
h
e
p
o
o
l.
3
.
1
.
2
.
I
nte
g
ra
t
ing
o
f
da
t
a
T
h
e
r
aw
d
ata
ar
e
co
llected
f
r
o
m
v
ar
io
u
s
s
o
u
r
ce
s
;
t
h
e
y
m
a
y
b
e
h
eter
o
g
en
eo
u
s
s
o
th
e
y
s
h
o
u
ld
b
e
u
n
i
f
ied
to
g
e
th
er
.
T
h
is
w
ill b
e
d
o
n
e
at
th
is
s
tep
.
3
.
1
.
3
.
Select
ing
o
f
da
t
a
I
n
th
is
p
h
a
s
e,
th
e
r
elev
a
n
t
d
ata
s
h
o
u
ld
b
e
r
eg
ain
ed
f
r
o
m
t
h
e
d
ata
p
o
o
l
w
h
ic
h
is
r
elev
a
n
t
f
o
r
th
e
an
al
y
s
is
.
3
.
1
.
4
.
T
ra
ns
f
o
r
m
ing
o
f
da
t
a
So
m
eti
m
es
i
t
is
al
s
o
ca
lled
d
ata
co
n
s
o
lid
atio
n
b
ec
au
s
e
th
e
d
esig
n
ated
d
ata
s
h
o
u
ld
b
e
co
n
v
er
ted
in
to
an
ap
p
r
o
p
r
iate
f
o
r
m
at
to
b
e
u
s
ef
u
l f
o
r
th
e
p
r
o
ce
d
u
r
e
o
f
m
i
n
i
n
g
.
3
.
1
.
5
.
M
ini
ng
o
f
da
t
a
I
t a
ls
o
is
k
n
o
w
n
as
d
ata
-
m
i
n
i
n
g
,
it
is
e
n
u
m
er
ated
as
th
e
p
o
ten
tial
s
ta
g
e
i
n
‘
KD
D’
b
ec
au
s
e
i
n
tellect
u
al
s
y
s
te
m
s
ar
e
p
er
f
o
r
m
ed
to
tak
e
o
u
t u
s
e
f
u
l
k
n
o
w
led
g
e.
3
.
1
.
6
.
E
v
a
lua
t
io
n
o
f
pa
t
t
er
n
T
h
is
p
h
ase
is
ab
o
u
t id
en
ti
f
y
i
n
g
th
e
atte
n
ti
v
e
p
atter
n
s
ac
co
r
d
in
g
to
s
o
m
e
m
ea
s
u
r
e
m
e
n
ts
.
3
.
1
.
7
.
Repre
s
ent
i
ng
t
he
k
no
w
ledg
e
I
t
is
t
h
e
las
t
s
ta
g
e
i
n
t
h
e
‘
KD
D’
p
r
o
ce
s
s
i
n
w
h
ic
h
t
h
e
g
ai
n
e
d
p
atter
n
s
ar
e
s
h
o
w
n
v
i
s
u
all
y
to
th
e
e
n
d
-
u
s
er
w
it
h
t
h
e
h
elp
o
f
t
h
e
v
is
u
aliza
tio
n
m
ec
h
a
n
is
m
s
s
u
ch
as
b
o
x
p
lo
t
an
d
h
i
s
to
g
r
a
m
to
h
elp
th
e
e
n
d
-
u
s
er
to
elu
cid
ate
th
e
r
es
u
lt
s
[
2
9
]
.
A
m
a
j
o
r
s
tep
o
f
‘
KDD
’
h
a
s
s
h
o
w
n
in
Fi
g
u
r
e.
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8776
I
n
t J
I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
10
,
No
.
2,
A
u
g
u
s
t
20
21
:
9
3
–
1
0
3
98
Fig
u
r
e
3
.
Kn
o
w
led
g
e
d
is
co
v
er
y
s
tep
s
[
3
]
.
3
.
2
.
Da
t
a
-
m
ini
ng
co
ncept
s
&
m
et
ho
ds
Data
-
m
i
n
i
n
g
i
s
th
e
m
o
s
t
s
i
g
n
if
ica
n
t
s
ta
g
e
in
t
h
e
p
r
o
ce
s
s
o
f
‘
K
DD
’
in
w
h
ic
h
th
e
cr
u
cia
l
p
atter
n
is
tak
en
o
u
t
f
r
o
m
m
ass
iv
e
u
n
p
r
o
ce
s
s
ed
d
ata.
T
h
e
ex
tr
ac
ted
k
n
o
w
led
g
e
r
elied
o
n
t
h
e
ta
s
k
s
o
f
‘
D
-
M
’
t
h
a
t
p
er
f
o
r
m
ed
o
n
t
h
e
u
n
p
r
o
ce
s
s
e
d
d
ata.
I
n
g
en
er
al,
‘
D
-
M
’
h
a
s
t
w
o
m
aj
o
r
ta
s
k
s
:
d
e
s
cr
ip
tiv
e
tas
k
s
o
r
d
u
tie
s
i
n
w
h
ic
h
th
e
g
en
er
al
c
h
ar
ac
ter
is
tics
o
f
th
e
e
x
is
tin
g
d
ata
ar
e
d
ep
icted
.
Ho
w
e
v
er
,
th
e
s
ec
o
n
d
d
u
t
y
is
ca
lled
th
e
p
r
ed
ictiv
e
tas
k
t
h
at
e
n
d
ea
v
o
r
s
to
p
r
ed
ict
u
n
k
n
o
w
n
d
ata
t
h
at
r
elied
o
n
th
e
k
n
o
w
n
d
ata.
Un
p
r
o
ce
s
s
ed
d
ata
m
a
y
b
e
in
t
h
e
f
o
r
m
at
o
f
n
u
m
er
ic,
tex
t,
i
m
a
g
e
th
at
m
in
in
g
ca
n
b
e
d
o
n
e
o
n
t
h
e
m
.
C
h
ar
ac
ter
izatio
n
,
d
is
t
in
ctio
n
,
ass
o
ciatio
n
o
r
r
elatio
n
s
h
ip
,
cl
ass
i
f
icatio
n
,
cl
u
s
ter
i
n
g
o
r
g
r
o
u
p
in
g
,
a
n
d
an
al
y
s
is
o
f
tr
e
n
d
ar
e
th
e
m
ai
n
‘
D
-
M
’
f
u
n
ctio
n
alitie
s
.
No
w
ad
a
y
s
,
m
an
y
s
ec
to
r
s
s
u
ch
a
s
m
ed
ical
a
r
ea
s
,
ed
u
ca
tio
n
,
an
d
b
an
k
i
n
g
u
tili
ze
‘
D
-
M
’
to
o
ls
[
1
0
]
.
Data
-
Min
in
g
li
k
e
‘
KDD
’
en
co
m
p
as
s
es so
m
e
s
ta
g
es
w
h
i
ch
ar
e
b
r
ief
l
y
i
n
tr
o
d
u
ce
d
b
elo
w
[
3
0
]
.
3
.
2
.
1
.
Def
ini
ng
t
he
pro
ble
m
T
h
is
s
ta
g
e
i
s
v
er
y
i
m
p
o
r
tan
t
b
ec
au
s
e
t
h
e
m
ai
n
g
o
al
s
h
o
u
ld
b
e
id
en
tifie
d
an
d
r
e
v
ea
led
.
A
c
co
r
d
in
g
to
th
e
g
o
al
t
h
e
co
r
r
ec
ted
to
o
l is p
er
f
o
r
m
ed
o
n
th
e
u
n
p
r
o
ce
s
s
ed
d
ata
to
co
n
s
tr
u
ct
th
e
d
es
ir
ed
m
o
d
el.
3
.
2
.
2
.
E
x
plo
ring
a
nd
co
llect
ing
t
he
da
t
a
T
h
is
s
tag
e
is
ab
o
u
t
co
llecti
n
g
an
d
s
ea
r
ch
i
n
g
f
o
r
ap
p
r
o
p
r
iate
d
ata
in
w
h
ic
h
th
e
q
u
alit
y
o
f
d
ata
m
u
s
t
b
e
s
u
itab
le
f
o
r
th
e
p
r
o
ce
s
s
o
f
m
in
in
g
a
n
d
an
al
y
zi
n
g
to
ta
k
e
o
u
t t
h
e
b
est f
ea
t
u
r
e.
3
.
2
.
3
.
T
he
prepa
ra
t
io
n o
f
da
t
a
T
w
o
m
ai
n
ta
s
k
s
ca
n
b
e
d
o
n
e
i
n
t
h
is
s
tep
,
w
h
ic
h
i
s
d
ata
clea
n
s
i
n
g
a
n
d
tr
an
s
f
o
r
m
in
g
to
f
ill
th
e
m
i
s
s
ed
an
d
illeg
al
v
al
u
es to
o
b
tain
ac
cu
r
ate,
co
n
s
i
s
ten
t,
an
d
r
o
b
u
s
t r
esu
lt
s
.
3
.
2
.
4
.
Co
ns
t
ruct
ing
t
he
no
del
T
h
is
is
t
h
e
f
in
al
s
ta
g
e
i
n
th
e
‘
D
-
M
’
p
r
o
ce
s
s
i
n
w
h
ich
a
n
ap
p
r
o
p
r
iate
m
o
d
el
ca
n
b
e
b
u
ilt
f
o
r
an
al
y
s
is
ac
co
r
d
in
g
to
th
e
d
ata
an
d
th
e
d
esire
d
r
esu
lts
.
T
h
e
m
o
d
el
ca
n
b
e
co
n
s
tr
u
cted
b
y
co
m
b
i
n
in
g
b
o
th
class
ica
l
an
d
m
o
d
er
n
‘
D
-
M
’
tec
h
n
iq
u
es li
k
e
s
tatis
tic
s
,
D
-
T
r
ee
,
A
-
NN,
K
-
NN,
an
d
SVM,
etc.
4.
CL
AS
SI
F
I
CAT
I
O
N
AL
G
O
RIT
H
M
S IN DA
T
A
M
I
NIN
G
T
h
e
class
if
ica
tio
n
al
g
o
r
ith
m
s
in
d
ata
m
i
n
i
n
g
h
av
e
a
v
ital
r
o
le
in
ex
tr
ac
tin
g
p
o
ten
tial
p
atter
n
s
o
r
k
n
o
w
led
g
e
f
r
o
m
r
a
w
d
ata
to
p
r
o
p
o
s
e
an
ac
cu
r
ate
a
n
d
e
f
f
ic
ien
t
d
ia
g
n
o
s
is
s
y
s
te
m
to
p
r
ed
ict
an
d
d
etec
t
L
u
n
g
an
d
B
r
ea
s
t
ca
n
ce
r
o
u
s
n
o
d
u
le
s
in
a
lo
w
co
s
t
an
d
m
i
n
i
m
u
m
ti
m
e.
I
n
th
is
s
ec
tio
n
,
s
o
m
e
o
f
th
e
r
en
o
w
n
ed
class
i
f
icatio
n
alg
o
r
it
h
m
s
i
n
d
ata
m
i
n
in
g
h
av
e
b
ee
n
r
e
v
ie
w
ed
en
lis
ted
as th
e
f
o
llo
w
in
g
:
4
.
1
.
Dec
is
io
n
t
re
e
(
D
-
T
re
e)
c
la
s
s
i
f
ier
I
t
is
s
h
o
r
ten
ed
in
to
D
-
T
r
ee
an
d
co
u
n
ted
as
th
e
m
o
d
er
n
ef
f
e
ctiv
e
alg
o
r
it
h
m
f
o
r
class
i
f
icati
o
n
a
m
o
n
g
th
e
o
th
er
clas
s
i
f
ier
.
I
t
g
ain
ed
p
o
p
u
lar
it
y
w
h
e
n
th
e
d
ata
ar
e
g
r
o
w
n
s
p
ec
i
f
icall
y
in
t
h
e
i
n
f
o
r
m
atio
n
s
y
s
te
m
ar
ea
.
Ma
n
y
r
e
n
o
w
n
ed
alg
o
r
it
h
m
s
b
elo
n
g
to
th
is
clas
s
i
f
ier
,
f
o
r
ex
a
m
p
le,
I
D
-
3
,
C
4
.
5
,
J
4
.
8
,
C
5
,
etc.
Fro
m
t
h
e
n
a
m
e,
th
is
c
lass
if
ier
i
s
li
k
e
a
tr
ee
th
at
s
p
lits
t
h
e
attr
ib
u
tes
r
ec
u
r
s
i
v
el
y
b
a
s
ed
o
n
s
o
m
e
m
at
h
e
m
a
tics
al
g
o
r
ith
m
s
li
k
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8776
Da
ta
min
in
g
tech
n
iq
u
es fo
r
lu
n
g
a
n
d
b
r
ea
s
t c
a
n
ce
r
d
ia
g
n
o
s
is
:
A
r
ev
iew
(
B
a
kh
a
n
To
fiq
A
h
med
)
99
en
tr
o
p
y
,
g
i
n
i
-
i
n
d
ex
,
a
n
d
ch
i
-
s
q
u
ar
e
to
class
i
f
y
i
n
co
n
s
tan
t
an
d
m
a
tch
ed
t
h
r
esh
o
ld
f
o
r
t
h
e
in
co
n
s
ta
n
t
th
a
t
d
iv
id
e
th
e
in
p
u
t
attr
ib
u
te
in
to
t
w
o
o
r
m
o
r
e
s
u
b
d
iv
is
io
n
s
.
T
h
ese
s
u
b
d
iv
id
in
g
w
i
ll
b
e
r
ep
ea
ted
u
n
til
th
e
tr
ee
is
b
u
ilt.
T
h
e
g
o
al
o
f
t
h
i
s
s
ep
ar
atio
n
al
g
o
r
ith
m
i
s
to
d
ed
u
ce
a
th
r
es
h
o
ld
th
at
i
n
cr
ea
s
es
th
e
h
o
m
o
g
e
n
eit
y
o
r
u
n
i
f
o
r
m
it
y
b
et
w
ee
n
t
h
e
s
u
b
g
r
o
u
p
s
[
2
6
]
.
So
m
e
o
f
t
h
e
w
ell
-
k
n
o
w
n
D
-
T
r
ee
alg
o
r
ith
m
s
h
a
v
e
b
ee
n
d
is
cu
s
s
ed
w
h
i
c
h
w
er
e
C
4
.
5
,
C
ar
t,
an
d
I
D
-
3
[
7
]
.
A
n
ex
a
m
p
le
o
f
a
D
-
T
r
ee
is
d
ep
icted
in
Fig
u
r
e
4
.
Fig
u
r
e
4
.
Dec
is
io
n
t
r
ee
(
D
-
T
r
ee
)
[
3
1
]
.
4
.
1
.
1
.
C4
.
5
-
a
lg
o
rit
h
m
T
h
is
alg
o
r
ith
m
i
s
w
id
el
y
u
tili
ze
d
.
C
4
.
5
s
elec
ts
o
n
l
y
o
n
e
f
ea
tu
r
e
o
f
t
h
e
d
ata
th
at
h
as
t
h
e
h
i
g
h
e
s
t
g
a
i
n
r
atio
to
ef
f
icie
n
tl
y
s
ep
ar
ate
th
e
s
a
m
p
le
s
et
s
in
to
s
u
b
s
ec
t
io
n
s
in
o
n
e
o
r
m
o
r
e
class
es.
I
n
o
th
er
w
o
r
d
s
,
th
e
C
4
.
5
alg
o
r
ith
m
d
ep
en
d
s
o
n
ca
lc
u
lat
in
g
t
h
e
g
ain
r
atio
o
f
ea
ch
n
o
d
e
in
th
e
tr
ee
to
d
o
s
ep
ar
atio
n
am
o
n
g
th
e
at
tr
ib
u
tes.
C
o
n
s
eq
u
en
tl
y
,
w
h
ic
h
attr
ib
u
te
o
b
tain
ed
th
e
h
i
g
h
er
g
ai
n
r
ati
o
w
ill
b
e
ch
o
s
e
n
b
y
t
h
e
al
g
o
r
ith
m
to
ef
f
ec
ti
v
el
y
s
p
lit th
e
d
ata.
4
.
1
.
2
.
Ca
rt
-
a
lg
o
ri
t
h
m
I
t
is
en
u
m
er
ated
as
a
n
o
n
-
p
a
r
a
m
etr
ic
al
g
o
r
ith
m
u
s
ed
to
c
r
ea
te
eith
er
clas
s
i
f
icatio
n
o
r
r
eg
r
ess
io
n
(
r
ev
er
s
io
n
)
tr
ee
,
b
ased
o
n
w
h
e
th
er
th
e
v
ar
iab
le
is
ca
teg
o
r
ical
o
r
n
u
m
er
ic.
A
co
llectio
n
o
f
r
u
les
ar
e
u
tili
ze
d
to
co
n
s
tr
u
ct
t
h
e
tr
ee
t
h
at
d
ep
en
d
s
o
n
t
h
e
v
ar
iab
les
’
v
al
u
es
i
n
t
h
e
g
iv
e
n
d
ata
s
et.
T
h
e
s
elec
ti
o
n
o
f
r
u
les
is
r
elied
o
n
v
ar
iab
les
’
v
al
u
es
o
n
h
o
w
t
o
s
ep
ar
ate
th
e
at
tr
ib
u
tes
w
ell
b
y
ca
lcu
lati
n
g
Gin
i
-
in
d
e
x
.
E
ac
h
n
o
d
e
is
d
i
v
id
ed
in
to
t
w
o
o
r
m
o
r
e
at
tr
ib
u
tes
w
h
en
ev
er
t
h
e
r
u
le
i
s
c
h
o
s
en
; t
h
e
p
r
o
ce
s
s
w
o
u
ld
b
e
r
e
p
ea
ted
f
o
r
ea
ch
n
o
d
e
u
n
til t
h
e
f
u
ll
tr
ee
i
s
p
r
o
d
u
ce
d
.
C
ar
t
s
el
ec
ts
t
h
e
attr
ib
u
te
th
a
t
h
a
s
t
h
e
s
m
al
lest
G
in
i
-
i
n
d
ex
as
t
h
e
s
p
litt
in
g
attr
ib
u
te.
T
h
e
p
r
o
ce
s
s
o
f
s
ep
ar
atio
n
is
co
n
tin
u
ed
an
d
s
to
p
p
ed
w
h
e
n
t
h
e
C
ar
t
-
al
g
o
r
ith
m
d
etec
ted
t
h
at
n
o
m
o
r
e
d
iv
is
io
n
co
u
ld
be
m
ad
e
o
n
th
e
n
o
d
e.
T
h
e
m
ain
id
ea
b
eh
in
d
th
i
s
alg
o
r
it
h
m
w
as
to
en
h
an
ce
t
h
e
tr
ee
b
y
s
elec
tin
g
a
s
ep
ar
ate
a
m
o
n
g
all
o
f
t
h
e
o
t
h
er
s
ep
ar
ates
at
ea
ch
n
o
d
e
to
p
r
o
d
u
ce
th
e
p
u
r
est
n
o
d
e.
I
n
C
ar
t
-
al
g
o
r
ith
m
,
o
n
l
y
u
n
i
v
ar
iate
d
is
tr
ib
u
tio
n
w
a
s
m
ea
s
u
r
ed
.
4
.
1
.
3
.
I
t
er
a
t
i
v
e
dicho
t
o
m
is
er
(
I
D3
)
-
a
lg
o
rit
h
m
I
t
is
also
k
n
o
w
n
as
I
D3
-
Alg
o
r
ith
m
.
I
n
1
9
7
0
,
J
.
Qu
in
la
n
esta
b
lis
h
ed
an
d
in
tr
o
d
u
ce
d
th
i
s
alg
o
r
ith
m
.
I
n
th
is
al
g
o
r
it
h
m
,
t
h
e
s
p
lit
tin
g
at
tr
ib
u
tes
ar
e
s
elec
ted
t
h
at
h
a
v
e
th
e
h
ig
h
est
in
f
o
r
m
atio
n
g
a
in
as
co
m
p
ar
ed
to
th
e
o
th
er
attr
ib
u
te
’
s
i
n
f
o
r
m
atio
n
g
ain
.
A
m
at
h
e
m
at
ical
al
g
o
r
ith
m
li
k
e
en
tr
o
p
y
is
u
s
ed
to
m
ea
s
u
r
e
t
h
e
i
n
f
o
r
m
atio
n
g
ain
i
n
ea
ch
n
o
d
e
in
th
e
tr
ee
.
T
h
e
co
n
s
tr
u
cted
tr
ee
is
s
h
o
r
ter
an
d
th
o
s
e
attr
ib
u
tes
t
h
at
h
a
v
e
s
m
aller
en
tr
o
p
ies
ar
e
u
s
u
al
l
y
p
lace
d
clo
s
e
to
th
e
r
o
o
t in
th
e
tr
ee
.
4
.
2
.
Ar
t
if
icia
l
neura
l net
o
r
net
wo
rk
(A
-
NN)
c
la
s
s
if
ier
I
t
is
a
ca
lcu
lated
m
o
d
el
th
a
t
r
elied
o
n
b
io
lo
g
ical
n
e
u
r
al
n
ets.
I
t
i
n
v
o
lv
es
a
n
i
n
ter
r
ela
ted
s
et
o
f
ar
tif
icial
n
e
u
r
o
n
s
.
I
n
t
h
e
A
-
NN
class
i
f
ier
,
t
h
e
in
f
o
r
m
a
tio
n
is
ca
lc
u
lated
b
y
u
s
i
n
g
a
c
o
n
n
ec
tio
n
is
t
m
et
h
o
d
.
N
eu
r
o
n
s
w
er
e
s
y
s
te
m
a
tized
i
n
to
la
y
er
s
.
T
h
e
i
n
p
u
t la
y
er
r
ep
r
esen
t
s
t
h
e
r
ea
l d
ata
b
u
t t
h
e
o
u
t
p
u
t la
y
er
r
ep
r
esen
t
s
th
e
clas
s
es.
T
h
er
e
ar
e
m
a
n
y
h
id
d
en
la
y
er
s
b
et
w
ee
n
t
h
e
i
n
p
u
t
an
d
o
u
tp
u
t
la
y
er
s
.
A
n
e
u
r
al
n
et
is
a
n
ef
f
ec
ti
v
e
lear
n
in
g
m
et
h
o
d
in
w
h
ic
h
d
at
a
ex
a
m
p
le
s
w
er
e
d
ep
icted
o
n
ly
o
n
e
ti
m
e
to
th
e
n
et,
an
d
th
e
class
lab
eli
n
g
co
u
ld
b
e
p
r
ed
icted
b
y
ad
j
u
s
tin
g
th
e
w
e
ig
h
ts
.
A
-
NN
h
as
t
w
o
b
en
ef
its
;
th
e
f
ir
s
t
o
n
e
is
t
h
at
it
g
i
v
es
th
e
h
i
g
h
es
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8776
I
n
t J
I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
10
,
No
.
2,
A
u
g
u
s
t
20
21
:
9
3
–
1
0
3
100
to
ler
an
ce
to
n
o
is
y
d
ata.
T
h
e
s
ec
o
n
d
is
t
h
at
t
h
e
A
-
NN
cla
s
s
if
ier
ca
n
clas
s
i
f
y
u
n
t
r
ai
n
ed
k
n
o
w
led
g
e
[
1
3
]
.
A
n
ex
a
m
p
le
o
f
A
-
NN
h
a
s
s
h
o
w
n
i
n
Fi
g
u
r
e
5
.
Fig
u
r
e
5
.
A
r
ti
f
icial
n
eu
r
al
n
et
(
A
NN)
[
1
3
]
.
4
.
2
.
1
.
F
ee
d
-
f
o
rwa
rd
neura
l net
w
o
r
k
I
t
is
also
r
ef
er
r
ed
to
as
FF
NN.
I
t
is
th
e
s
i
m
p
les
t
f
o
r
m
o
f
A
-
NN
in
w
h
ic
h
th
e
in
f
o
r
m
a
tio
n
p
ass
e
s
u
n
id
ir
ec
tio
n
al
b
et
w
ee
n
la
y
er
s
an
d
d
o
es
n
o
t
cr
ea
te
th
e
cy
cle
i
n
th
e
n
e
t.
I
t
co
n
tain
s
t
h
r
ee
la
y
er
s
s
u
c
h
as
an
in
p
u
t
la
y
er
,
a
h
id
d
en
la
y
er
,
an
d
an
o
u
tp
u
t
la
y
er
.
U
n
its
ar
e
cr
ea
ted
i
n
ea
ch
la
y
er
.
W
h
e
n
a
v
al
u
e
was
m
o
v
ed
f
r
o
m
t
h
e
in
p
u
t
la
y
er
to
th
e
h
id
d
en
la
y
er
an
d
th
en
to
t
h
e
o
u
tp
u
t
la
y
er
i
s
r
ef
er
r
ed
to
as
Feed
Fo
r
w
ar
d
b
ec
au
s
e
n
o
v
al
u
es
r
etu
r
n
ed
to
t
h
e
ea
r
lier
la
y
er
.
T
h
e
i
n
p
u
t
s
w
er
e
f
ed
co
n
c
u
r
r
en
t
l
y
i
n
to
t
h
e
u
n
its
th
at
w
er
e
m
a
d
e
u
p
o
f
t
h
e
i
n
p
u
t
-
la
y
er
.
T
h
e
d
ata
is
p
ass
ed
t
h
r
o
u
g
h
t
h
e
i
n
p
u
t
la
y
er
a
n
d
t
h
en
w
ei
g
h
ted
an
d
f
ed
co
n
c
u
r
r
en
tl
y
to
t
h
e
u
p
co
m
in
g
la
y
er
w
h
ic
h
i
s
ca
lled
th
e
h
id
d
en
la
y
er
.
T
h
e
h
id
d
en
la
y
er
o
u
tp
u
ts
co
u
ld
b
e
i
n
p
u
t to
t
h
e
n
e
x
t
h
id
d
en
la
y
er
.
I
t
is
a
r
ec
u
r
s
iv
e
p
r
o
ce
d
u
r
e.
T
h
e
o
u
tp
u
t
la
y
er
i
s
co
n
s
tr
u
cted
b
y
t
h
e
h
id
d
en
la
y
er
o
u
tp
u
t
s
.
I
t
is
c
ateg
o
r
ized
in
to
t
w
o
f
o
r
m
s
s
u
ch
a
s
s
i
n
g
le
-
la
y
er
p
er
ce
p
tr
o
n
an
d
m
u
lti
-
la
y
er
p
er
ce
p
tr
o
n
.
T
h
e
ab
o
v
e
d
iag
r
a
m
is
a
f
ee
d
-
f
o
r
w
ar
d
w
h
ic
h
is
co
m
p
r
is
ed
o
f
th
r
ee
la
y
er
s
s
u
ch
as i
n
p
u
t,
h
id
d
e
n
,
an
d
o
u
tp
u
t a
n
d
n
o
v
al
u
es r
et
u
r
n
to
th
e
e
ar
lier
lay
er
[
3
2
]
.
4
.
3
.
Su
pp
o
rt
-
v
ec
t
o
r
-
m
a
chine c
la
s
s
if
ier
I
t is a
s
u
p
er
v
is
ed
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
e
to
ex
a
m
i
n
e
d
a
t
a
an
d
d
is
ti
n
g
u
is
h
k
n
o
w
led
g
e
u
tili
ze
d
f
o
r
class
i
f
icatio
n
an
d
r
ev
er
s
io
n
s
t
u
d
y
.
S
u
p
p
o
r
t
-
v
ec
to
r
m
ac
h
i
n
e
i
s
an
al
g
o
r
ith
m
t
h
at
w
o
r
k
s
o
n
d
is
co
v
er
in
g
a
li
n
ea
r
d
iv
id
er
o
r
‘
h
y
p
er
p
lan
e
’
b
et
w
e
en
th
e
d
ata
-
p
o
i
n
ts
o
f
2
class
e
s
in
m
u
lti
-
d
i
m
en
s
io
n
al
s
p
ac
e.
SVM
class
i
f
ier
ca
n
co
n
s
tr
u
ct
a
p
r
ed
ictio
n
m
o
d
el
to
esti
m
ate
cla
s
s
es
f
o
r
n
e
w
s
a
m
p
les
i
f
th
e
d
ataset
h
as
b
o
th
f
ea
t
u
r
es
a
n
d
class
lab
els
b
ec
au
s
e
SV
M
is
s
u
p
er
v
is
ed
m
ac
h
i
n
e
lear
n
in
g
.
A
s
a
r
esu
lt,
it
d
is
tr
ib
u
tes
n
e
w
s
a
m
p
les
to
o
n
e
o
f
t
h
e
class
es.
L
in
ea
r
a
n
d
n
o
n
-
lin
ea
r
SVM
cla
s
s
i
f
ier
s
ar
e
th
e
t
w
o
t
y
p
e
s
o
f
s
u
p
p
o
r
t
-
v
ec
to
r
m
ac
h
i
n
e
clas
s
i
f
ier
s
.
S
VM
co
u
ld
b
e
tr
ain
ed
b
y
t
h
e
u
n
co
m
p
licated
an
d
s
w
i
f
t
al
g
o
r
ith
m
w
h
ic
h
is
n
a
m
ed
s
eq
u
e
n
tia
l
m
in
i
m
al
o
p
ti
m
iza
tio
n
[
3
1
]
.
4
.
4
.
Na
ïv
e
-
B
a
y
es
c
la
s
s
if
ier
I
t
is
a
s
w
i
f
t
tec
h
n
iq
u
e
u
s
ed
f
o
r
co
n
s
tr
u
cti
n
g
s
tati
s
tical
p
r
ed
ictiv
e
m
o
d
els.
Naï
v
e
-
B
a
y
es
r
el
ies
o
n
th
e
B
ay
e
s
ian
th
eo
r
e
m
.
T
h
is
clas
s
if
ier
e
x
a
m
in
e
s
t
h
e
as
s
o
ciatio
n
b
et
w
ee
n
ea
ch
f
ea
t
u
r
e
an
d
t
h
e
clas
s
.
Fo
r
ea
c
h
s
a
m
p
le
e
x
tr
ac
ted
a
co
n
d
itio
n
a
l
p
r
o
b
a
b
ilit
y
f
o
r
t
h
e
ass
o
ciati
o
n
s
a
m
o
n
g
th
e
f
ea
t
u
r
e
v
al
u
es
an
d
th
e
clas
s
.
T
h
e
class
es
’
p
r
o
b
ab
ilit
y
is
ca
lc
u
lat
ed
b
y
en
u
m
er
atin
g
h
o
w
m
a
n
y
ti
m
e
s
it
o
cc
u
r
s
in
t
h
e
ex
er
ci
s
i
n
g
d
ataset
w
h
e
n
t
h
e
class
es
w
er
e
tr
ai
n
ed
.
T
h
is
is
n
a
m
ed
th
e
p
r
io
r
-
p
r
o
b
ab
ilit
y
[
2
9
]
.
5.
RE
S
U
L
T
S AN
D
D
I
SCU
SS
I
O
N
Data
m
in
i
n
g
tec
h
n
iq
u
e
s
h
av
e
a
v
ital
r
o
le
i
n
p
r
ed
ictin
g
a
n
d
d
etec
tin
g
s
ev
er
al
v
ar
io
u
s
d
is
ea
s
es
s
u
c
h
as
lu
n
g
-
ca
n
ce
r
,
b
r
ea
s
t
-
ca
n
ce
r
,
s
k
in
-
ca
n
ce
r
,
h
ea
r
t,
d
iab
etes
,
e
tc.
Ma
n
y
r
esear
ch
er
s
p
r
o
p
o
s
ed
n
u
m
er
o
u
s
u
s
e
f
u
l
d
ata
-
m
in
i
n
g
m
e
th
o
d
s
to
esti
m
a
te
L
u
n
g
a
n
d
B
r
ea
s
t
ca
n
ce
r
.
I
n
m
y
o
p
in
io
n
,
th
e
tec
h
n
iq
u
es
o
f
d
ata
-
m
i
n
in
g
ar
e
ex
tr
e
m
e
l
y
u
s
e
f
u
l
i
n
s
ev
er
al
a
r
ea
s
s
p
ec
i
f
icall
y
i
n
th
e
m
ed
ical
ar
ea
to
d
is
co
v
er
q
u
i
te
s
ig
n
if
ica
n
t
k
n
o
w
led
g
e
f
r
o
m
r
a
w
d
ata.
I
n
th
is
s
u
r
v
e
y
,
s
ev
er
al
r
esear
c
h
er
s
’
w
o
r
k
s
h
a
v
e
b
ee
n
r
e
v
ie
w
ed
t
h
at
u
s
ed
A
-
NN,
Naï
v
e
-
B
a
y
e
s
,
D
-
T
r
ee
,
etc,
to
p
r
o
p
o
s
e
a
p
r
e
d
icted
an
d
d
etec
ted
s
y
s
te
m
f
o
r
lu
n
g
a
n
d
b
r
ea
s
t
ca
n
ce
r
.
T
h
ese
class
if
ier
s
w
er
e
d
if
f
er
e
n
t
in
ter
m
s
o
f
ac
cu
r
ac
y
a
n
d
th
e
f
o
r
m
o
f
ca
n
ce
r
.
T
h
e
d
etails
o
f
t
h
ese
p
r
ese
n
ted
w
o
r
k
s
h
a
v
e
b
ee
n
d
em
o
n
s
tr
ated
a
n
d
co
m
p
ar
ed
i
n
ter
m
s
o
f
ac
cu
r
ac
y
as s
h
o
w
n
in
T
ab
le
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8776
Da
ta
min
in
g
tech
n
iq
u
es fo
r
lu
n
g
a
n
d
b
r
ea
s
t c
a
n
ce
r
d
ia
g
n
o
s
is
:
A
r
ev
iew
(
B
a
kh
a
n
To
fiq
A
h
med
)
101
T
ab
le
1
.
C
o
m
p
ar
is
o
n
o
f
v
ar
io
u
s
d
ata
m
in
i
n
g
clas
s
if
ier
s
an
d
alg
o
r
ith
m
s
i
n
ter
m
s
o
f
ac
c
u
r
ac
y
f
o
r
d
etec
tin
g
an
d
p
r
ed
ictin
g
l
u
n
g
an
d
b
r
ea
s
t c
an
ce
r
.
R
e
f
.
Y
e
a
r
D
i
se
a
se
s
C
l
a
ssi
f
i
e
r
s
A
l
g
o
r
i
t
h
ms
A
c
c
u
r
a
c
y
[
1
3
]
2
0
1
2
B
r
e
a
st
-
C
a
n
c
e
r
A
N
N
,
N
a
ï
v
e
B
a
y
e
s,
D
-
T
r
e
e
.
C
4
.
5
8
6
.
5
%,
8
4
.
5
%
,
9
3
.
6
2
%
,
8
6
.
7
%.
[
1
4
]
2
0
1
3
B
r
e
a
st
-
C
a
n
c
e
r
J4
.
8
,
N
a
ï
v
e
B
a
y
e
s
G
e
n
e
t
i
c
7
4
.
2
%,
7
1
.
6
7
%,
8
4
.
8
%
.
[
1
9
]
2
0
1
6
L
u
n
g
-
C
a
n
c
e
r
C
o
n
v
o
l
u
t
i
o
n
a
l
N
e
u
r
a
l
N
e
t
,
K
-
NN
7
7
.
5
%,
8
2
.
5
%
.
[
2
1
]
2
0
1
8
L
u
n
g
-
C
a
n
c
e
r
J4
.
8
,
N
B
,
K
-
NN
9
3
%,
8
0
.
2
%
,
8
9
.
6
%.
[
2
2
]
2
0
1
8
B
r
e
a
st
-
C
a
n
c
e
r
K
N
N
,
N
a
ï
v
e
B
a
y
e
s,
R
a
n
d
o
m F
o
r
e
st
,
L
o
g
i
st
i
c
R
e
g
r
e
ssi
o
n
,
M
u
l
t
i
l
a
y
e
r
P
e
r
c
e
p
t
r
o
n
7
2
.
3
7
7
6
%,
7
1
.
6
7
8
3
%,
6
9
.
5
8
0
4
%,
6
8
.
8
8
1
1
%,
6
4
.
6
8
5
3
%.
[
2
3
]
2
0
1
8
L
u
n
g
-
C
a
n
c
e
r
N
a
ï
v
e
B
a
y
e
s,
R
a
n
d
o
m F
o
r
e
st
,
N
e
u
r
a
l
N
e
t
w
o
r
k
,
K
N
N
,
L
o
g
i
st
i
c
R
e
g
r
e
ssi
o
n
,
T
r
e
e
.
5
7
.
0
4
7
%,
4
9
.
8
3
2
%
4
7
.
3
1
5
%
4
6
.
9
8
%
4
2
.
6
1
7
%
3
5
.
5
7
%
.
[
2
4
]
2
0
1
8
B
r
e
a
st
-
C
a
n
c
e
r
G
R
U
-
S
V
M
,
L
R
,
K
-
N
N
,
S
R
,
S
V
M
,
M
L
P
.
9
0
%
9
9
.
0
4
%
[
2
6
]
2
0
2
0
B
r
e
a
st
-
C
a
n
c
e
r
R
F
,
K
-
N
N
,
S
V
M
,
N
B
,
D
T
,
R
F
,
L
R
.
9
8
.
1
%
6.
CO
NCLU
SI
O
N
T
h
e
class
i
f
icatio
n
a
lg
o
r
it
h
m
s
in
d
ata
m
in
in
g
h
av
e
a
s
i
g
n
if
ic
an
t
r
o
le
in
th
e
m
ed
ical
s
ec
to
r
in
h
elp
in
g
d
o
cto
r
s
an
d
p
h
y
s
ician
s
to
d
ia
g
n
o
s
e
v
ar
io
u
s
f
o
r
m
s
o
f
d
i
s
ea
s
es
ef
f
ec
ti
v
el
y
at
lo
w
co
s
t
a
n
d
s
h
o
r
t
ti
m
e.
I
n
t
h
i
s
p
ap
er
,
a
co
m
p
r
eh
en
s
iv
e
r
ev
i
e
w
o
f
t
h
e
m
o
s
t
cr
itical
clas
s
if
ica
tio
n
alg
o
r
it
h
m
s
i
n
d
ata
m
in
i
n
g
h
ad
b
ee
n
p
r
esen
ted
.
Ma
n
y
u
p
-
to
-
d
ate
r
elev
an
t
s
t
u
d
ies
h
a
v
e
b
ee
n
r
ev
ie
w
ed
t
h
at
u
tili
ze
d
d
i
f
f
er
en
t
clas
s
i
f
icatio
n
alg
o
r
ith
m
s
i
n
t
h
is
er
a
to
p
r
o
p
o
s
e
an
ac
cu
r
ate
lu
n
g
an
d
b
r
ea
s
t
ca
n
ce
r
d
iag
n
o
s
e
s
y
s
t
e
m
to
p
r
ed
ict
an
d
d
etec
t
ca
n
ce
r
o
u
s
n
o
d
u
les
i
n
t
h
eir
i
n
itial
s
tag
e
s
.
B
ased
o
n
th
e
r
ev
ie
w
ed
p
ap
er
s
m
an
y
d
if
f
e
r
en
t
class
if
icatio
n
alg
o
r
ith
m
s
h
ad
b
ee
n
ap
p
lied
f
o
r
clas
s
i
f
y
i
n
g
ca
n
ce
r
o
u
s
an
d
n
o
n
-
ca
n
ce
r
o
u
s
ce
ll
s
.
I
t
i
s
f
o
u
n
d
th
at
a
m
o
n
g
t
h
e
class
i
f
ier
s
,
M
L
P
g
ai
n
ed
a
h
ig
h
er
ac
cu
r
ac
y
t
h
an
th
e
o
t
h
er
s
f
o
l
lo
w
ed
b
y
L
R
an
d
D
-
T
r
ee
,
w
h
i
ch
w
er
e
(
9
9
.
0
4
%),
(
9
8
.
1
%),
an
d
(
9
3
.
6
2
%),
r
esp
ec
tiv
el
y
.
Ho
w
e
v
er
,
a
m
o
n
g
t
h
e
alg
o
r
it
h
m
s
,
C
4
.
5
o
b
tain
ed
(
8
6
.
7
%)
ac
cu
r
ac
y
f
o
llo
w
ed
b
y
t
h
e
Ge
n
etic
A
l
g
o
r
ith
m
th
a
t a
ttai
n
ed
ap
p
r
o
x
im
a
te
l
y
(
8
4
.
8
%)
ac
cu
r
ac
y
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
I
w
o
u
ld
lik
e
to
th
a
n
k
th
e
ed
ito
r
an
d
r
ev
ie
w
er
s
f
o
r
th
eir
co
m
m
en
ts
an
d
s
u
g
g
e
s
tio
n
s
d
u
r
in
g
th
e
r
ev
ie
w
p
r
o
ce
s
s
.
RE
F
E
R
E
NC
E
S
[1
]
S
.
S
.
P
r
iy
a
,
B.
Ra
m
a
m
u
rth
y
,
"
Lu
n
g
c
a
n
c
e
r
d
e
tec
ti
o
n
u
sin
g
i
m
a
g
e
p
ro
c
e
ss
in
g
tec
h
n
iq
u
e
s,"
Res
e
a
rc
h
J
o
u
rn
a
l
o
f
Ph
a
rm
a
c
y
T
e
c
h
n
o
l
o
g
y
v
o
l
.
1
1
,
n
o
.
5
,
p
p
.
2
0
4
5
-
2
0
4
9
,
2
0
1
8
.
DO
I:1
0
.
5
9
5
8
/
0
9
7
4
-
3
6
0
X
.
2
0
1
8
.
0
0
3
7
9
.
7
,
[
O
n
li
n
e
].
Av
a
il
a
b
le:h
tt
p
s://
se
a
rc
h
.
p
r
o
q
u
e
st.
c
o
m
/o
p
e
n
v
ie
w
/4
7
6
0
9
5
a
a
6
7
9
b
2
0
5
2
1
8
d
4
b
4
f
a
5
9
e
7
1
1
1
f
/1
?
p
q
o
rig
site=
g
sc
h
o
lar&
c
b
=
1
0
9
6
4
4
1
.
[2
]
V
.
A
.
G
a
jd
h
a
n
e
,
L
.
De
sh
p
a
n
d
e
,
"
De
tec
ti
o
n
o
f
lu
n
g
c
a
n
c
e
r
st
a
g
e
s
o
n
CT
sc
a
n
i
m
a
g
e
s
b
y
u
sin
g
v
a
rio
u
s
im
a
g
e
p
ro
c
e
ss
in
g
tec
h
n
iq
u
e
s,"
IOS
R
J
o
u
rn
a
l
o
f
Co
mp
u
ter
En
g
in
e
e
rin
g
(
IOS
R
-
J
CE)
,
v
o
l.
1
6
,
n
o
.
5
,
p
p
.
2
8
-
3
5
,
2
0
1
4
.
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s://
p
d
f
s.se
m
a
n
ti
c
sc
h
o
lar.o
rg
/f
3
4
6
/a1
a
c
c
8
5
0
b
0
1
8
3
8
6
e
f
5
0
b
1
c
d
1
5
6
e
2
8
e
5
d
d
3
6
f
.
p
d
f
.
[3
]
K.
Ba
lac
h
a
n
d
ra
n
,
R.
A
n
it
h
a
,
"
Clas
sif
ier
s
b
a
se
d
A
p
p
ro
a
c
h
f
o
r
P
re
-
Dia
g
n
o
sis
o
f
L
u
n
g
Ca
n
c
e
r
Dise
a
se
,
"
in
In
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
f
Co
m
p
u
ter
Ap
p
li
c
a
t
io
n
s
(
IJ
CA)(
0
9
7
5
-
8
8
8
7
)
Pro
c
e
e
d
i
n
g
s
o
n
Na
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Eme
rg
in
g
T
re
n
d
s
in
In
fo
rm
a
ti
o
n
&
Co
mm
u
n
ica
ti
o
n
T
e
c
h
n
o
l
o
g
y
(
NCET
ICT
2
0
1
3
):
Cit
e
se
e
r
,
p
p
.
1
-
5
,
2
0
1
3
.
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
:/
/cites
e
e
rx
.
ist.
p
su
.
e
d
u
/v
iew
d
o
c
/d
o
w
n
lo
a
d
?
d
o
i=1
0
.
1
.
1
.
6
6
3
.
3
9
0
4
&
re
p
=
re
p
1
&
t
y
p
e
=
p
d
f
.
[4
]
B.
T
.
A
h
m
e
d
,
"
L
u
n
g
Ca
n
c
e
r
P
re
d
ictio
n
a
n
d
De
tec
ti
o
n
Us
in
g
Im
a
g
e
P
r
o
c
e
ss
in
g
M
e
c
h
a
n
ism
s:
A
n
O
v
e
rv
ie
w
,
"
S
ig
n
a
l
Ima
g
e
Pro
c
e
ss
in
g
L
e
tt
e
rs
,
v
o
l.
1
,
n
o
.
3
,
p
p
.
2
0
-
3
1
,
2
0
1
9
.
h
tt
p
:
//
d
x
.
d
o
i.
o
rg
/
1
0
.
3
1
7
6
3
/sim
p
le.v
1
i3
.
1
1
.
[5
]
B.
G
u
p
ta,
S
.
T
iwa
ri,
"
L
u
n
g
c
a
n
c
e
r
d
e
tec
ti
o
n
u
si
n
g
c
u
rv
e
let
tran
sf
o
rm
a
n
d
n
e
u
ra
l
n
e
tw
o
rk
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Co
mp
u
ter
A
p
p
li
c
a
ti
o
n
s
,
v
o
l.
8
6
,
n
o
.
1
,
p
p
.
1
5
-
1
7
,
2
0
1
4
.
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
:
//
c
it
e
se
e
rx
.
ist.
p
su
.
e
d
u
/v
iew
d
o
c
/d
o
w
n
lo
a
d
?
d
o
i=
1
0
.
1
.
1
.
4
2
9
.
1
2
4
6
&
re
p
=
re
p
1
&
ty
p
e
=
p
d
f
.
[6
]
M
.
P
.
C
h
a
n
d
e
r,
M
.
V.
Ra
o
,
T
.
R
a
ji
n
ik
a
n
th
,
"
De
tec
ti
o
n
o
f
lu
n
g
c
a
n
c
e
r
u
sin
g
d
ig
it
a
l
im
a
g
e
p
ro
c
e
ss
i
n
g
tec
h
n
iq
u
e
s:
a
c
o
m
p
a
ra
ti
v
e
stu
d
y
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
M
e
d
ica
l
Im
a
g
in
g
,
v
o
l.
5
,
n
o
.
4
,
p
p
.
5
8
-
6
2
,
2
0
1
7
.
d
o
i
:
1
0
.
1
1
6
4
8
/j
.
i
jm
i.
2
0
1
7
0
5
0
5
.
1
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8776
I
n
t J
I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
10
,
No
.
2,
A
u
g
u
s
t
20
21
:
9
3
–
1
0
3
102
[7
]
D.
S
.
Ku
m
a
r,
G
.
S
a
th
y
a
d
e
v
i,
S
.
S
iv
a
n
e
sh
,
"
De
c
isio
n
su
p
p
o
rt
sy
ste
m
f
o
r
m
e
d
ica
l
d
iag
n
o
sis
u
sin
g
d
a
ta
m
in
in
g
,
"
In
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
f
Co
mp
u
ter
S
c
ien
ce
,
v
o
l.
8
,
n
o
.
3
,
p
p
.
1
4
7
-
1
5
3
,
2
0
1
1
.
[
O
n
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
:
//
c
it
e
se
e
rx
.
ist.
p
su
.
e
d
u
/v
iew
d
o
c
/d
o
w
n
lo
a
d
?
d
o
i=
1
0
.
1
.
1
.
4
4
2
.
8
6
6
5
&
re
p
=
re
p
1
&
ty
p
e
=
p
d
f
#
p
a
g
e
=
1
6
1
.
[8
]
K.
Dim
il
il
e
r,
B.
Ug
u
r,
Y.
Ev
e
r,
"
T
u
m
o
r
d
e
tec
ti
o
n
o
n
CT
lu
n
g
im
a
g
e
s
u
sin
g
i
m
a
g
e
e
n
h
a
n
c
e
m
e
n
t,
"
T
h
e
On
li
n
e
J
o
u
rn
a
l
o
f
S
c
ien
c
e
T
e
c
h
n
o
lo
g
y
,
v
o
l.
7
,
n
o
.
1
,
p
p
.
1
3
3
-
1
3
8
,
2
0
1
7
.
[
O
n
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/t
o
jsa
t.
n
e
t/
j
o
u
r
n
a
ls/t
o
jsa
t/
v
o
lu
m
e
s/to
jsa
t
-
v
o
lu
m
e
0
7
-
i0
1
.
p
d
f
#
p
a
g
e
=
1
4
2
.
[9
]
A
d
a
,
R.
Ka
u
r,
"
E
a
rl
y
De
t
e
c
ti
o
n
a
n
d
P
re
d
icti
o
n
o
f
L
u
n
g
Ca
n
c
e
r
S
u
rv
iv
a
l
u
sin
g
Ne
u
ra
l
Ne
t
w
o
rk
C
las
si
f
ier,
"
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
A
p
p
li
c
a
ti
o
n
o
r I
n
n
o
v
a
ti
o
n
i
n
En
g
in
e
e
rin
g
&
M
a
n
a
g
e
me
n
t
,
v
o
l
.
2
,
n
o
.
6
,
p
p
.
3
7
5
-
3
8
3
,
2
0
1
3
.
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s://
ww
w
.
s
e
m
a
n
ti
c
sc
h
o
lar.o
rg
/p
a
p
e
r/
Early
-
De
tec
ti
o
n
-
a
n
d
-
P
re
d
icti
o
n
-
of
-
L
u
n
g
-
Ca
n
c
e
r
-
u
sin
g
-
A
d
a
-
Ka
u
r/a4
7
6
3
3
4
c
9
7
9
7
2
6
1
d
7
1
f
8
9
b
c
5
c
0
c
9
e
d
6
c
e
6
5
d
7
4
1
8
.
[1
0
]
D.
Ch
a
u
h
a
n
,
V
.
Ja
isw
a
l,
"
A
n
e
ff
icie
n
t
d
a
ta
m
in
in
g
c
las
si
f
ica
ti
o
n
a
p
p
r
o
a
c
h
f
o
r
d
e
tec
ti
n
g
lu
n
g
c
a
n
c
e
r
d
ise
a
se
,
"
In
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
mm
u
n
ica
ti
o
n
a
n
d
El
e
c
tro
n
ics
S
y
ste
ms
(
ICCES
)
,
Co
im
b
a
to
re
,
In
d
ia,
p
p
.
1
-
8
,
2
0
1
6
.
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s://
iee
e
x
p
lo
re
.
iee
e
.
o
rg
/ab
stra
c
t/
d
o
c
u
m
e
n
t/
7
8
8
9
8
7
2
.
[1
1
]
D.
Ka
lad
h
a
r,
B.
Ch
a
n
d
a
n
a
,
a
n
d
P
.
B.
Ku
m
a
r,
"
P
re
d
ictin
g
c
a
n
c
e
r
su
rv
iv
a
b
il
it
y
u
sin
g
Clas
si
f
ica
ti
o
n
a
lg
o
rit
h
m
s,"
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Res
e
a
r
c
h
Rev
iews
in
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l.
2
,
n
o
.
2
,
p
p
.
3
4
0
-
3
4
3
,
2
0
1
1
.
[
O
n
li
n
e
].
Av
a
il
a
b
le:
h
tt
p
s://
w
ww
.
re
s
e
a
rc
h
g
a
te.n
e
t/
p
ro
f
il
e
/Bh
a
ra
th
_
Ku
m
a
r1
6
/
p
u
b
li
c
a
ti
o
n
/2
1
3
5
8
8
9
4
1
.
[1
2
]
Z.
S
.
Zu
b
i,
R
.
A
.
S
a
a
d
,
"
Us
in
g
so
m
e
d
a
ta
m
in
in
g
tec
h
n
iq
u
e
s
f
o
r
e
a
rly
d
iag
n
o
sis
o
f
lu
n
g
c
a
n
c
e
r,
"
in
Pro
c
e
e
d
in
g
s
o
f
th
e
1
0
th
W
S
EA
S
I
n
t
e
rn
a
ti
o
n
a
l
o
n
fer
e
n
c
e
o
n
Arti
fi
c
i
a
l
i
n
telli
g
e
n
c
e
Kn
o
wled
g
e
En
g
i
n
e
e
rin
g
a
n
d
Da
t
a
Ba
se
s
,
2
0
1
1
,
p
p
.
3
2
-
3
7
.
[1
3
]
S
.
Kh
a
ry
a
,
"
Us
in
g
d
a
ta
m
in
in
g
te
c
h
n
iq
u
e
s
f
o
r
d
iag
n
o
sis
a
n
d
p
ro
g
n
o
sis
o
f
c
a
n
c
e
r
d
ise
a
se
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
mp
u
ter
S
c
ien
c
e
,
En
g
in
e
e
rin
g
a
n
d
In
f
o
r
ma
ti
o
n
T
e
c
h
n
o
lo
g
y
IJ
CS
EIT
,
v
o
l.
2
,
n
o
.
2
,
p
p
.
5
5
-
6
6
,
2
0
1
2
.
[
O
n
li
n
e
].
Av
a
il
a
b
le:
h
tt
p
s://
a
rx
iv
.
o
rg
/ab
s/1
2
0
5
.
1
9
2
3
.
[1
4
]
M
.
A
.
J
a
b
b
a
r,
B.
L
.
De
e
k
sh
a
tu
lu
,
P
.
Ch
a
n
d
ra
,
"
He
a
rt
d
ise
a
se
p
re
d
ictio
n
u
si
n
g
laz
y
a
ss
o
c
iati
v
e
c
las
si
f
ica
ti
o
n
,
"
2
0
1
3
In
ter
n
a
t
io
n
a
l
M
u
tl
i
-
C
o
n
fer
e
n
c
e
o
n
Au
t
o
ma
ti
o
n
,
Co
m
p
u
t
in
g
,
C
o
mm
u
n
ica
ti
o
n
,
Co
n
tro
l
a
n
d
Co
m
p
re
ss
e
d
S
e
n
sin
g
(
iM
a
c
4
s)
,
Ko
tt
a
y
a
m
,
In
d
ia,
p
p
.
4
0
-
4
6
,
2
0
1
3
.
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/i
e
e
e
x
p
lo
re
.
iee
e
.
o
rg
/ab
stra
c
t/
d
o
c
u
m
e
n
t/
6
5
2
6
3
8
1
.
[1
5
]
B.
T
.
A
h
m
e
d
a
n
d
O.
Y.
A
b
d
u
lh
a
m
e
e
d
,
"
F
in
g
e
rp
rin
t
re
c
o
g
n
it
io
n
b
a
se
d
o
n
sh
a
rk
sm
e
ll
o
p
ti
m
iza
ti
o
n
a
n
d
g
e
n
e
ti
c
a
lg
o
rit
h
m
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
s
in
I
n
telli
g
e
n
t
I
n
fo
rm
a
t
ics
,
v
o
l.
6
,
n
o
.
2
,
p
p
.
1
2
3
-
1
3
4
,
2
0
2
0
.
h
tt
p
s:/
/d
o
i.
o
rg
/1
0
.
2
6
5
5
5
/i
jai
n
.
v
6
i
2
.
5
0
2
.
[1
6
]
B.
T
.
A
h
m
e
d
a
n
d
O.
Y.
A
b
d
u
lh
a
m
e
e
d
,
"
F
in
g
e
rp
rin
t
A
u
th
e
n
ti
c
a
ti
o
n
u
si
n
g
S
h
a
rk
S
m
e
ll
Op
ti
m
iza
ti
o
n
A
lg
o
rit
h
m
,
"
UH
D
J
o
u
rn
a
l
o
f
S
c
i
e
n
c
e
T
e
c
h
n
o
lo
g
y
,
v
o
l.
4
,
n
o
.
2
,
p
p
.
2
8
-
3
9
,
2
0
2
0
.
h
tt
p
s:/
/d
o
i.
o
rg
/1
0
.
2
1
9
2
8
/
u
h
d
jst.
v
4
n
2
y
2
0
2
0
.
p
p
2
8
-
39
[1
7
]
T
.
S
o
wm
i
y
a
,
M
.
G
o
p
i,
B.
Ne
w
,
a
n
d
R.
T
h
o
m
a
s,
"
Op
ti
m
iz
a
ti
o
n
o
f
lu
n
g
c
a
n
c
e
r
u
sin
g
m
o
d
e
rn
d
a
ta
m
in
in
g
tec
h
n
iq
u
e
s,"
In
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
f
E
n
g
in
e
e
rin
g
Res
e
a
rc
h
,
v
o
l
.
3
,
n
o
.
5
,
p
p
.
3
0
9
-
1
4
,
2
0
1
4
.
[1
8
]
N.
P
a
n
p
a
li
y
a
,
N.
T
a
d
a
s,
S
.
Bo
b
a
d
e
,
R.
A
g
la
w
e
,
a
n
d
A
.
G
u
d
a
d
h
e
,
"
A
su
rv
e
y
o
n
e
a
rly
d
e
te
c
ti
o
n
a
n
d
p
re
d
icti
o
n
o
f
lu
n
g
c
a
n
c
e
r,
"
In
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
f
Co
m
p
u
ter
S
c
ien
c
e
M
o
b
il
e
C
o
mp
u
t
in
g
,
v
o
l
.
4
,
n
o
.
1
,
p
p
.
1
7
5
-
1
8
4
,
2
0
1
5
.
[1
9
]
R.
P
a
u
l
,
S
.
H.
Ha
w
k
in
s,
L
.
O.
Ha
ll
,
D.
B.
G
o
ld
g
o
f
,
a
n
d
R.
J.
G
il
li
e
s,
"
Co
m
b
in
in
g
d
e
e
p
n
e
u
r
a
l
n
e
tw
o
rk
a
n
d
trad
it
io
n
a
l
im
a
g
e
f
e
a
tu
re
s
to
im
p
ro
v
e
su
rv
iv
a
l
p
re
d
ictio
n
a
c
c
u
ra
c
y
f
o
r
lu
n
g
c
a
n
c
e
r
p
a
ti
e
n
ts
f
ro
m
d
iag
n
o
stic
CT
,
"
in
2
0
1
6
IE
EE
I
n
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
S
y
ste
ms
,
M
a
n
,
a
n
d
Cy
b
e
rn
e
ti
c
s (
S
M
C)
,
IEE
E
,
2
0
1
6
,
p
p
.
0
0
2
5
7
0
-
0
0
2
5
7
5
.
[2
0
]
C.
M
.
L
y
n
c
h
,
V
.
H
.
v
a
n
Be
rk
e
l,
a
n
d
H.
B.
F
rie
b
o
e
s,
"
A
p
p
li
c
a
ti
o
n
o
f
u
n
su
p
e
rv
ise
d
a
n
a
ly
sis
tec
h
n
iq
u
e
s
to
l
u
n
g
c
a
n
c
e
r
p
a
ti
e
n
t
d
a
ta,"
Pl
o
s On
e
,
v
o
l.
1
2
,
n
o
.
9
,
p
.
e
0
1
8
4
3
7
0
,
2
0
1
7
.
h
t
tp
s://
d
o
i.
o
rg
/1
0
.
1
3
7
1
/j
o
u
r
n
a
l.
p
o
n
e
.
0
1
8
4
3
7
0
[2
1
]
Y.
O
m
a
r,
A
.
T
a
sle
e
m
,
M
.
P
a
sq
u
ier,
a
n
d
A
.
S
a
g
a
h
y
ro
o
n
,
"
L
u
n
g
Ca
n
c
e
r
P
ro
g
n
o
sis
S
y
ste
m
u
sin
g
Da
ta
M
in
in
g
T
e
c
h
n
iq
u
e
s,"
in
Pro
c
e
e
d
in
g
s
o
f
t
h
e
1
1
th
In
ter
n
a
ti
o
n
a
l
J
o
i
n
t
Co
n
f
e
re
n
c
e
o
n
Bi
o
me
d
ica
l
En
g
in
e
e
rin
g
S
y
ste
ms
a
n
d
T
e
c
h
n
o
l
o
g
ies
,
v
o
l.
5
,
2
0
1
8
,
p
p
.
3
6
1
-
3
6
8
.
[2
2
]
S
.
Bh
a
ra
ti
,
M
.
A
.
Ra
h
m
a
n
,
a
n
d
P
.
P
o
d
d
e
r,
"
Bre
a
st
c
a
n
c
e
r
p
re
d
ictio
n
a
p
p
ly
in
g
d
if
fe
re
n
t
c
las
si
f
ica
ti
o
n
a
lg
o
rit
h
m
w
it
h
c
o
m
p
a
ra
ti
v
e
a
n
a
l
y
sis
u
sin
g
WE
KA
,
"
in
2
0
1
8
4
th
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
El
e
c
trica
l
En
g
i
n
e
e
rin
g
a
n
d
In
fo
rm
a
t
io
n
&
Co
mm
u
n
ica
ti
o
n
T
e
c
h
n
o
l
o
g
y
(
iCE
Ei
CT
),
2
0
1
8
,
p
p
.
5
8
1
-
5
8
4
,
h
tt
p
s:/
/d
o
i
.
o
rg
/1
0
.
1
1
0
9
/CE
EICT
.
2
0
1
8
.
8
6
2
8
0
8
4
:
IE
EE
.
[2
3
]
S
.
Bh
a
ra
ti
,
P
.
P
o
d
d
e
r,
R.
M
o
n
d
a
l
,
A
.
M
a
h
m
o
o
d
,
a
n
d
M
.
Ra
i
h
a
n
-
Al
-
M
a
su
d
,
"
Co
m
p
a
ra
ti
v
e
p
e
r
f
o
r
m
a
n
c
e
a
n
a
ly
sis
o
f
d
if
fe
re
n
t
c
las
si
f
ic
a
ti
o
n
a
lg
o
rit
h
m
f
o
r
th
e
p
u
rp
o
se
o
f
p
re
d
ictio
n
o
f
lu
n
g
c
a
n
c
e
r,
"
in
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
In
telli
g
e
n
t
S
y
ste
ms
De
sig
n
a
n
d
Ap
p
li
c
a
ti
o
n
s
,
S
p
rin
g
e
r
,
2
0
1
8
,
p
p
.
4
4
7
-
4
5
7
,
h
tt
p
s:
//
d
o
i.
o
rg
/1
0
.
1
0
0
7
/9
7
8
-
3
-
0
3
0
-
1
6
6
6
0
-
1
_
4
4
.
[2
4
]
A
.
F
.
M
.
A
g
a
ra
p
,
"
On
b
re
a
st
c
a
n
c
e
r
d
e
tec
ti
o
n
:
a
n
a
p
p
l
ica
ti
o
n
o
f
m
a
c
h
in
e
lea
rn
in
g
a
lg
o
rit
h
m
s
o
n
th
e
w
isc
o
n
sin
d
iag
n
o
stic
d
a
tas
e
t,
"
in
Pr
o
c
e
e
d
in
g
s
o
f
t
h
e
2
n
d
In
ter
n
a
ti
o
n
a
l
C
o
n
fe
re
n
c
e
o
n
M
a
c
h
in
e
L
e
a
rn
i
n
g
a
n
d
S
o
ft
Co
m
p
u
ti
n
g
,
2
0
1
8
,
p
p
.
5
-
9.
[2
5
]
S
.
Bh
a
ra
ti
,
P
.
P
o
d
d
e
r,
a
n
d
M
.
M
o
n
d
a
l,
"
A
rti
f
icia
l
N
e
u
ra
l
Ne
tw
o
rk
B
a
se
d
Bre
a
st
Ca
n
c
e
r
S
c
re
e
n
in
g
:
A
Co
m
p
re
h
e
n
siv
e
Re
v
ie
w
,
"
a
rXiv p
re
p
rin
t
a
rX
iv:.0
1
7
6
7
,
p
p
. 1
-
1
3
,
2
0
2
0
.
[2
6
]
M
.
F
.
A
k
,
"
A
Co
m
p
a
ra
ti
v
e
A
n
a
ly
sis
o
f
Br
e
a
st
C
a
n
c
e
r
De
te
c
ti
o
n
a
n
d
Dia
g
n
o
sis
Us
in
g
Da
ta
V
isu
a
li
z
a
ti
o
n
a
n
d
M
a
c
h
in
e
L
e
a
rn
in
g
A
p
p
li
c
a
ti
o
n
s,"
in
He
a
lt
h
c
a
re
,
M
u
lt
i
d
isc
ip
li
n
a
r
y
Dig
it
a
l
P
u
b
l
ish
i
n
g
In
stit
u
te
,
v
o
l
.
8
,
n
o
.
2
,
p
p
.
1
1
1
,
2
0
2
0
.
[2
7
]
L
u
n
g
Ca
n
c
e
r
Fo
rm
s
,
S
p
rin
g
e
r
Na
tu
re
,
S
e
p
2
0
2
0
,
[
On
li
n
e
]
A
v
a
il
a
b
le:
h
tt
p
s:/
/www
.
g
o
o
g
le.co
m
/se
a
r
c
h
?
q
=
lu
n
g
+
c
a
n
c
e
r+
f
o
r
m
&
rlz=
1
C1
GK
L
C_
e
n
IQ8
6
7
IQ8
6
7
&
so
u
rc
e
=
ln
m
s&
tb
m
=
isc
h
&
sa
=
X
&
v
e
d
=
2
a
h
UK
E
w
io
o
-
3
Hp
O3
rA
h
UlS
h
UIH
Yv
IA
7
k
Q_
AU
o
A
X
o
ECA
sQ
Aw
&
b
iw
=
1
5
3
6
&
b
ih
=
7
5
4
#
im
g
rc
=
9
c
DIV
Erd
BW
p
z
IM
.
Evaluation Warning : The document was created with Spire.PDF for Python.