I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
38
,
No
.
3
,
J
u
n
e
20
25
,
p
p
.
1
681
~1
6
8
9
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
38.
i
3
.
p
p
1
6
81
-
1
6
8
9
1681
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
No
v
el
pro
sta
te
ca
ncer
de
tec
tion a
n
d clas
sifica
tion m
o
del using
supp
o
rt
v
ector
m
a
chine
K
a
nd
uk
uri Suja
t
a
1
,
B
o
kk
a
S
ridha
r
2
,
Av
a
la
M
a
llik
a
rj
un
a
P
ra
s
a
d
1
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
JN
TU
,
K
a
k
i
n
a
d
a
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
L
e
n
d
i
I
n
st
i
t
u
t
e
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
V
i
z
i
a
n
a
g
a
r
a
m,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
May
8
,
2
0
2
4
R
ev
is
ed
No
v
16
,
2
0
2
4
Acc
ep
ted
No
v
24
,
2
0
2
4
P
ro
sta
te
c
a
n
c
e
r
(P
Ca
)
is
o
n
e
o
f
t
h
e
m
o
st
c
o
m
m
o
n
a
n
d
d
e
a
d
li
e
st
c
a
n
c
e
rs
th
a
t
k
il
l
m
e
n
wo
rl
d
wid
e
with
h
ig
h
m
o
rtalit
y
a
n
d
p
re
v
a
len
c
e
e
sp
e
c
ially
in
d
e
v
e
lo
p
e
d
c
o
u
n
tri
e
s.
P
Ca
is
re
g
a
rd
e
d
a
s
o
n
e
o
f
th
e
m
o
st
p
re
v
a
len
t
c
a
n
c
e
rs
a
n
d
is
o
n
e
o
f
t
h
e
m
a
in
c
a
u
se
s
o
f
d
e
a
th
s
w
o
rld
wi
d
e
.
Early
d
e
tec
ti
o
n
o
f
P
Ca
d
ise
a
se
s
h
e
lp
s
in
m
a
k
i
n
g
d
e
c
isio
n
s
a
b
o
u
t
t
h
e
p
r
o
g
re
ss
io
n
s
th
a
t
s
h
o
u
l
d
h
a
v
e
o
c
c
u
rre
d
i
n
h
i
g
h
-
ris
k
p
a
ti
e
n
ts
d
e
c
re
a
se
th
e
ir
risk
s.
Th
e
re
c
e
n
t
d
e
v
e
lo
p
m
e
n
ts
in
tec
h
n
o
l
o
g
y
a
n
d
m
e
th
o
d
s
h
a
v
e
g
iv
e
n
r
ise
to
c
o
m
p
u
ter
a
id
e
d
d
iag
n
o
sis
(
CAD
).
Early
c
a
n
c
e
r
d
e
tec
ti
o
n
c
a
n
g
re
a
tl
y
i
n
c
re
a
se
th
e
c
h
a
n
c
e
o
f
su
rv
iv
a
l
th
ro
u
g
h
t
h
e
a
d
m
in
ist
ra
ti
o
n
o
f
t
h
e
p
ro
p
e
r
t
re
a
tme
n
t.
Du
e
to
th
e
e
m
e
rg
in
g
tren
d
s
a
n
d
a
v
a
il
a
b
le
d
a
tas
e
ts
in
st
a
te
-
of
-
a
rt
m
a
c
h
in
e
lea
rn
in
g
(M
L)
a
n
d
d
e
e
p
lea
rn
in
g
(DL)
t
e
c
h
n
iq
u
e
s,
t
h
e
re
h
a
s
b
e
e
n
si
g
n
ifi
c
a
n
t
g
r
o
wth
in
re
c
e
n
t
d
ise
a
se
p
re
d
ictio
n
a
n
d
c
las
sifica
ti
o
n
p
u
b
li
c
a
ti
o
n
s.
T
h
is
p
a
p
e
r
p
re
se
n
ts
a
u
n
iq
u
e
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
-
b
a
se
d
m
o
d
e
l
fo
r
P
Ca
d
e
tec
ti
o
n
a
n
d
c
las
sifica
ti
o
n
.
Th
is
a
n
a
ly
sis
a
ims
to
c
las
sify
th
e
P
Ca
u
sin
g
M
L
a
l
g
o
ri
th
m
a
n
d
to
d
e
term
in
e
th
e
risk
fa
c
to
rs.
S
u
p
p
o
r
t
v
e
c
to
r
m
a
c
h
in
e
s
(S
VM)
is
u
se
d
to
id
e
n
ti
fy
a
n
d
c
las
sify
th
e
P
Ca
.
Ac
c
u
ra
c
y
,
se
n
s
it
iv
it
y
,
sp
e
c
ifi
c
it
y
,
p
re
c
isio
n
,
a
n
d
F
1
-
sc
o
re
a
re
th
e
m
e
a
su
re
m
e
n
ts
u
se
d
to
e
v
a
lu
a
te
th
e
p
e
rfo
rm
a
n
c
e
o
f
th
e
p
re
se
n
ted
m
e
th
o
d
.
T
h
is
m
o
d
e
l
will
a
c
h
ie
v
e
a
c
c
u
ra
c
y
,
se
n
siti
v
it
y
,
sp
e
c
ifi
c
it
y
,
p
re
c
isio
n
,
a
n
d
F
1
-
sc
o
re
th
a
n
e
a
rli
e
r
m
o
d
e
ls.
K
ey
w
o
r
d
s
:
C
o
m
p
u
ter
aid
ed
d
iag
n
o
s
is
Dete
ctio
n
an
d
class
if
icatio
n
Ma
ch
in
e
lear
n
in
g
PC
a
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
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
:
Kan
d
u
k
u
r
i Su
jata
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics an
d
C
o
m
m
u
n
icatio
n
E
n
g
in
ee
r
i
n
g
,
J
NT
U
Kak
in
ad
a,
An
d
h
r
a
Pra
d
esh
,
I
n
d
ia
E
m
ail:
k
an
d
u
k
u
r
is
u
jata@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
I
n
th
e
wo
r
ld
,
m
en
ar
e
m
o
s
t
co
m
m
o
n
ly
af
f
ec
te
d
b
y
p
r
o
s
tate
ca
n
ce
r
(
P
C
a
)
,
wh
ich
is
als
o
th
e
f
if
th
lead
in
g
ca
u
s
e
o
f
d
ea
th
s
r
elate
d
to
ca
n
ce
r
.
I
t
is
ex
tr
em
ely
u
n
u
s
u
al
in
ch
ild
r
en
a
n
d
teen
a
g
er
s
,
with
ab
o
u
t
7
5
%
o
f
ca
s
es
d
etec
ted
b
ein
g
o
ld
er
th
an
6
5
.
T
h
e
i
n
cid
en
ce
an
d
d
ea
th
r
ates
ty
p
ically
in
cr
ea
s
e
with
ag
e.
Ag
e
a
n
d
f
am
ily
h
is
to
r
y
ar
e
th
e
two
m
ai
n
r
is
k
f
ac
to
r
s
[
1
]
.
W
ith
in
th
e
m
ale
r
ep
r
o
d
u
ctiv
e
s
y
s
tem
is
t
h
e
p
r
o
s
tate,
wh
ich
is
lo
ca
ted
in
th
e
p
elv
is
in
f
r
o
n
t
o
f
th
e
r
ec
tu
m
a
n
d
u
n
d
er
th
e
b
lad
d
er
.
I
t
ty
p
ically
weig
h
s
2
0
g
in
an
ad
u
lt
m
ale
an
d
is
ab
o
u
t
3
cm
l
o
n
g
,
s
u
r
r
o
u
n
d
in
g
an
ar
ea
o
f
t
h
e
u
r
et
h
r
a.
T
h
e
h
u
m
an
p
r
o
s
tate
is
an
o
r
g
an
th
at
h
elp
s
cr
ea
te
an
d
s
to
r
e
s
em
in
al
f
lu
id
.
I
t
also
ac
cu
m
u
lates
zin
c
an
d
p
r
o
d
u
ce
s
citr
ate.
T
wen
ty
p
er
ce
n
t
o
f
s
em
in
al
f
lu
id
is
p
r
o
d
u
ce
d
b
y
th
e
p
r
o
s
tate
g
lan
d
s
,
an
d
d
is
ea
s
es
o
f
th
e
p
r
o
s
tr
a
tes
im
p
air
u
r
in
atio
n
,
ejac
u
latio
n
,
an
d
d
ef
ec
atio
n
.
Par
ticu
lar
ly
in
th
e
ea
r
l
y
s
tag
es,
PC
a
s
y
m
p
to
m
s
f
r
eq
u
e
n
tly
o
v
er
lap
with
th
o
s
e
o
f
v
ar
io
u
s
d
is
ea
s
es [
2
]
.
I
n
d
icatio
n
s
a
n
d
s
y
m
p
to
m
s
o
f
PC
a
in
clu
d
e
b
lo
o
d
y
u
r
in
e,
p
el
v
ic
p
ain
,
u
r
in
atio
n
,
an
d
f
atig
u
e
f
r
o
m
lo
w
r
ed
b
lo
o
d
ce
ll
c
o
u
n
ts
.
PC
a
is
lin
k
ed
to
r
is
k
v
ar
ia
b
les
s
u
ch
as
r
ac
e,
ag
e
,
an
d
h
er
e
d
ity
.
T
h
is
s
u
g
g
ests
th
at
b
ec
au
s
e
PC
a
i
s
in
h
er
ited
,
th
e
r
is
k
is
in
cr
ea
s
ed
if
a
clo
s
e
r
el
at
iv
e
h
as
th
e
d
is
ea
s
e.
Fu
r
th
er
m
o
r
e,
a
n
u
m
b
er
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
38
,
No
.
3
,
J
u
n
e
20
25
:
1
6
8
1
-
1
6
8
9
1682
d
ietar
y
a
n
d
b
eh
a
v
io
r
al
r
is
k
f
ac
to
r
s
,
PC
a
h
as
b
ee
n
c
o
n
n
ec
ted
with
f
ac
to
r
s
lik
e
co
n
s
u
m
in
g
to
o
m
a
n
y
m
ilk
p
r
o
d
u
cts,
p
r
o
ce
s
s
ed
m
ea
t,
o
r
d
iets
lack
in
g
in
ce
r
tain
v
e
g
etab
l
es [
3
]
.
T
h
er
ef
o
r
e,
ac
cu
r
ately
d
iag
n
o
s
in
g
PC
a
a
s
s
o
o
n
as
p
o
s
s
ib
le
is
ess
en
tial
b
ec
au
s
e
it
ca
n
im
p
r
o
v
e
th
er
ap
y
an
d
r
ed
u
ce
th
e
r
is
k
o
f
d
ea
th
.
On
e
o
f
th
e
m
ain
is
s
u
es
in
r
esear
ch
th
ese
d
ay
s
is
ac
cu
r
ately
class
if
y
in
g
ca
n
ce
r
ty
p
es
an
d
id
e
n
tify
in
g
th
e
cr
iti
ca
l
g
en
es
r
elate
d
to
t
h
e
d
is
ea
s
e
[
4
]
.
W
ith
a
p
atien
t
’
s
d
iag
n
o
s
is
o
f
s
u
s
p
ec
ted
PC
a
b
ased
o
n
an
ab
n
o
r
m
al
s
cr
ee
n
i
n
g
d
i
g
ital
r
ec
tal
ex
am
in
atio
n
(
DR
E
)
o
r
a
h
ig
h
p
r
o
s
tate
-
s
p
e
cif
ic
an
tig
en
(
PS
A)
r
esu
lt,
cu
r
r
en
tl
y
,
r
a
n
d
o
m
s
y
s
tem
atic
(
s
ex
tan
t)
b
io
p
s
ies
p
er
f
o
r
m
ed
u
n
d
e
r
th
e
c
o
n
tr
o
l
o
f
tr
an
s
r
ec
tal
u
ltra
s
o
u
n
d
(
T
R
US)
is
th
e
ac
ce
p
ted
clin
ic
al
p
r
o
ce
d
u
r
e
f
o
r
d
ia
g
n
o
s
in
g
P
C
a
.
Dep
en
d
in
g
o
n
th
e
n
u
m
b
er
o
f
b
io
p
s
y
s
ites
,
th
e
p
h
y
s
ician
u
s
u
al
ly
d
iv
id
es
th
e
p
r
o
s
tate
in
to
m
an
y
r
e
g
io
n
s
.
Af
ter
th
at,
a
n
ee
d
le
is
p
lace
d
in
to
ea
ch
ar
ea
to
ex
tr
ac
t tis
s
u
e
s
am
p
l
es f
o
r
f
u
r
t
h
er
ex
am
in
atio
n
[
5
]
.
I
n
o
r
d
er
to
in
c
r
ea
s
e
th
e
d
etec
t
io
n
ac
cu
r
ac
y
,
in
ad
d
itio
n
to
t
h
e
s
ig
n
if
ican
t
f
alse
-
n
eg
ativ
e
r
at
e
(
i.e
.
,
th
e
p
o
s
s
i
b
ilit
y
o
f
i
n
co
r
r
ec
tly
d
ia
g
n
o
s
in
g
a
p
atien
t
with
PC
a
as
a
n
o
r
m
al
s
u
b
ject)
,
a
T
R
US
-
g
u
id
ed
b
io
p
s
y
f
o
r
p
r
o
s
tate
ca
n
ce
r
d
etec
tio
n
(
PC
D)
u
s
u
ally
n
ee
d
s
to
b
e
r
e
p
ea
t
ed
5
-
7
tim
es.
Ho
wev
er
,
T
R
U
S
-
g
u
id
ed
b
io
p
s
y
is
n
o
t
s
u
itab
le
f
o
r
s
cr
ee
n
i
n
g
a
lar
g
e
n
u
m
b
er
o
f
p
atien
ts
f
o
r
P
C
a
d
iag
n
o
s
is
b
ec
au
s
e
it
is
an
in
v
asiv
e
p
r
o
ce
d
u
r
e
[
6
]
.
B
etter
PC
a
d
iag
n
o
s
is
a
n
d
th
er
ap
y
h
av
e
b
ee
n
m
ad
e
p
o
s
s
ib
le
b
y
r
ec
en
t
d
ev
elo
p
m
en
ts
in
co
m
p
lex
co
m
p
u
ter
s
an
d
alg
o
r
ith
m
s
.
T
h
e
ter
m
“
C
o
m
p
u
ter
-
aid
ed
d
iag
n
o
s
is
”
(
C
AD)
d
escr
ib
es
th
e
u
s
e
o
f
tech
n
o
lo
g
y
an
d
co
m
p
u
ter
al
g
o
r
ith
m
s
ar
e
to
h
el
p
m
ed
ical
p
er
s
o
n
n
el
d
ia
g
n
o
s
e
an
d
p
r
e
d
ict
p
atien
ts
[
7
]
.
Pre
cise
d
iag
n
o
s
is
o
p
tim
izes
th
e
h
ea
lth
ca
r
e
o
f
p
atien
t
an
d
av
o
id
s
th
e
u
n
n
ec
ess
ar
y
s
u
r
g
ical
tr
ea
tm
en
ts
.
Au
to
m
atic
C
AD
tech
n
iq
u
es
h
elp
to
im
p
r
o
v
e
th
e
PC
a
d
iag
n
o
s
tic
ac
cu
r
ac
y
an
d
r
ed
u
ce
th
e
d
if
f
er
en
ce
s
b
etwe
en
th
em
.
I
n
ad
d
itio
n
,
t
h
e
C
AD
ca
n
r
esu
lt
th
e
im
p
r
o
v
ed
r
ea
d
er
in
ter
p
r
etatio
n
o
f
PC
a
[
8
]
.
I
n
m
ed
ical
im
ag
in
g
f
ield
s
o
f
s
tu
d
y
,
th
ey
ar
e
f
r
eq
u
en
tly
u
s
ed
in
th
e
id
en
tific
atio
n
o
f
an
o
m
alies
o
r
to
h
elp
in
t
h
e
in
ter
p
r
etatio
n
a
n
d
an
aly
s
is
o
f
m
ed
ical
im
ag
es,
s
u
ch
as
co
m
p
u
ted
to
m
o
g
r
a
p
h
y
(
C
T
)
,
m
ag
n
etic
r
eso
n
an
ce
im
a
g
in
g
(
MRI)
,
X
-
r
a
y
,
an
d
m
am
m
o
g
r
a
p
h
y
s
ca
n
s
[
9
]
.
Acc
o
r
d
in
g
t
o
s
tu
d
ies,
MRI
is
an
ef
f
ec
tiv
e,
th
e
n
o
n
in
v
asiv
e
im
ag
in
g
to
o
l
th
at
ca
n
h
el
p
co
n
s
is
ten
tly
id
en
tify
o
r
d
iag
n
o
s
e
a
wid
e
r
a
n
g
e
o
f
d
is
ea
s
es
b
y
p
r
o
v
id
in
g
an
at
o
m
ic
al,
f
u
n
ctio
n
al,
an
d
m
etab
o
lic
MRI
in
f
o
r
m
atio
n
,
i
n
clu
d
in
g
Alzh
eim
er
’
s
d
is
ea
s
e
an
d
PC
a
[
1
0
]
.
T
h
ese
s
y
s
tem
s
r
ec
o
g
n
ize
s
p
ec
if
ic
f
ea
tu
r
es
o
r
p
atter
n
s
th
at
m
ig
h
t
d
em
o
n
s
tr
ate
th
e
ex
is
ten
ce
o
r
ab
s
en
ce
o
f
a
d
is
ea
s
e
o
r
co
n
d
it
io
n
u
s
in
g
m
ac
h
in
e
lear
n
in
g
(
ML
)
,
d
ee
p
lear
n
in
g
(
DL
)
,
an
d
p
atter
n
r
ec
o
g
n
itio
n
alg
o
r
ith
m
s
.
Acc
o
r
d
in
g
to
r
ese
ar
ch
,
PC
a
r
an
k
s
as
th
e
f
if
th
m
o
s
t
p
r
ev
alen
t
ca
u
s
e
o
f
d
ea
th
wo
r
ld
wid
e
an
d
th
e
s
ec
o
n
d
m
o
s
t c
o
m
m
o
n
ty
p
e
o
f
ca
n
ce
r
in
m
en
.
Ho
wev
er
,
co
m
p
ar
ed
to
all
o
th
er
ca
n
ce
r
ty
p
es,
it is
th
e
o
n
e
th
at
is
d
iag
n
o
s
ed
in
m
o
r
e
m
en
o
v
e
r
m
id
d
le
ag
e
in
b
o
th
d
ev
el
o
p
e
d
an
d
d
e
v
elo
p
in
g
c
o
u
n
t
r
ies
[
1
1
]
.
Ho
wev
er
,
s
till
th
er
e
ar
e
d
if
f
icu
lties
in
MRI
i
m
ag
in
g
o
f
PC
a
.
So
m
e
o
f
th
es
e
ch
allen
g
es
in
clu
d
e
n
o
is
e,
b
l
u
r
r
in
g
,
r
o
tatio
n
,
lo
w
p
r
ec
is
io
n
s
eg
m
en
tatio
n
a
n
d
c
lass
if
icatio
n
ap
p
r
o
ac
h
es
.
T
h
e
s
e
ch
allen
g
es
co
u
ld
im
p
ac
t
t
h
e
ex
ac
tn
ess
o
f
th
e
f
r
am
ewo
r
k
s
u
s
ed
to
a
n
aly
ze
PC
a
[
1
2
]
.
ML
is
a
ty
p
e
o
f
ar
tif
icial
in
tellig
en
ce
th
at
u
s
es
a
p
ar
ticu
lar
alg
o
r
ith
m
o
r
m
et
h
o
d
o
lo
g
y
to
f
in
d
p
atter
n
s
in
u
n
p
r
o
ce
s
s
ed
in
f
o
r
m
at
io
n
.
Allo
win
g
co
m
p
u
ter
s
y
s
tem
s
to
lear
n
f
r
o
m
ex
p
er
ien
ce
o
n
th
eir
o
wn
,
with
o
u
t
th
e
n
ee
d
f
o
r
ex
p
licit
p
r
o
g
r
am
m
in
g
o
r
h
u
m
an
in
te
r
ac
tio
n
,
is
th
e
m
ain
g
o
al
o
f
ML
.
I
n
m
u
ltip
le
f
ield
s
o
f
m
ed
icin
e,
ML
tech
n
iq
u
es
ar
e
f
r
eq
u
en
tly
u
s
ed
s
in
ce
th
ey
ar
e
f
as
ter
,
m
o
r
e
ac
cu
r
ate,
an
d
less
co
s
tly
f
o
r
d
ia
g
n
o
s
in
g
d
if
f
er
en
t
d
is
ea
s
es [
1
3
]
.
B
ec
au
s
e
ML
tech
n
iq
u
es
ca
n
m
an
ag
e
la
r
g
e
a
m
o
u
n
ts
o
f
d
ata
an
d
in
teg
r
ate
d
ata
f
r
o
m
m
u
ltip
le
s
o
u
r
ce
s
,
th
ey
im
p
r
o
v
e
p
r
ed
ictio
n
p
o
we
r
.
ML
’
s
class
if
icat
io
n
is
o
n
e
o
f
its
k
ey
f
u
n
ctio
n
s
.
W
h
en
th
e
o
u
tp
u
t
v
ar
iab
le
is
ca
teg
o
r
ical,
class
if
icatio
n
in
cl
u
d
es
m
eth
o
d
s
f
o
r
esti
m
atin
g
it
[
1
4
]
.
Fo
r
th
e
d
iag
n
o
s
is
o
f
PC
a
,
T
r
an
s
-
r
ec
tal
u
ltra
s
o
n
o
g
r
a
p
h
y
g
u
id
ed
b
i
o
p
s
y
(
T
R
US)
is
cu
r
r
en
tly
th
e
ac
ce
p
ted
s
tan
d
ar
d
,
h
o
we
v
er
it
ex
h
ib
its
h
ig
h
f
alse
-
n
eg
ativ
e
r
ate
an
d
p
r
o
p
e
n
s
ity
f
o
r
ca
u
s
in
g
d
is
co
m
f
o
r
t,
b
leed
in
g
,
an
d
in
f
lam
m
atio
n
.
T
h
er
e
f
o
r
e,
an
au
t
o
m
atic,
-
in
v
asiv
e
an
d
ac
cu
r
ate
PC
a
class
if
icatio
n
m
o
d
el
is
ess
en
tial
to
s
av
e
p
atie
n
ts
f
r
o
m
in
v
asi
v
e
b
io
p
s
ies
an
d
to
ch
o
o
s
e
th
e
b
est m
eth
o
d
o
f
tr
ea
tm
en
t [
1
5
]
.
A
h
ier
ar
ch
ical
class
if
icatio
n
an
d
h
ig
h
-
lev
el
r
ep
r
esen
tati
o
n
wer
e
d
esig
n
e
d
f
o
r
MRI
-
b
ased
PC
a
d
iag
n
o
s
is
.
A
DL
n
etwo
r
k
u
s
es
m
u
lti
-
p
ar
am
etr
ic
MR
im
a
g
es
as
in
p
u
t
d
ata
to
f
ir
s
t
lear
n
h
ig
h
-
lev
el
f
ea
tu
r
e
r
ep
r
esen
tatio
n
.
T
h
e
n
,
a
m
et
h
o
d
o
f
h
ier
ar
ch
ical
class
if
icatio
n
i
s
d
ev
elo
p
ed
b
y
u
tili
zin
g
th
e
h
ig
h
-
lev
el
p
r
o
p
er
ties
th
at
h
av
e
b
ee
n
lear
n
ed
,
in
wh
ich
th
e
PC
a
d
etec
tio
n
f
in
d
i
n
g
s
ar
e
iter
ativ
ely
r
ef
i
n
ed
b
y
d
ev
elo
p
i
n
g
n
u
m
er
o
u
s
r
an
d
o
m
f
o
r
est
class
if
ier
s
.
An
av
er
ag
ed
s
ec
tio
n
-
b
ased
ev
alu
atio
n
(
SB
E
)
o
f
8
9
.
9
0
%,
an
av
e
r
ag
ed
s
en
s
i
tiv
ity
o
f
9
1
.
5
1
%,
an
d
a
n
av
er
ag
e
s
p
ec
if
icity
o
f
8
8
.
4
7
%
ar
e
o
b
tain
e
d
u
s
in
g
th
e
s
u
g
g
ested
p
r
o
ce
d
u
r
e.
T
h
e
s
tu
d
ies we
r
e
co
n
d
u
cted
o
n
2
1
r
ea
l p
atien
t su
b
jects [
1
6
]
.
C
o
x
r
eg
r
ess
io
n
was
u
s
ed
to
p
r
ed
ict
th
e
ch
a
n
ce
s
o
f
s
u
r
v
iv
al
f
o
r
PC
a
in
p
atien
t
d
ata
f
r
o
m
p
u
b
lic
s
ec
to
r
u
n
d
er
tak
i
n
g
s
(
PSU
)
.
T
h
is
s
tu
d
y
co
n
tain
s
a
co
h
o
r
t
o
f
p
atien
ts
with
ag
es
r
an
g
in
g
f
r
o
m
4
0
to
8
9
.
B
etwe
en
2
0
1
5
an
d
2
0
1
8
,
t
h
e
d
ata
was
g
ath
er
ed
f
r
o
m
So
n
g
k
h
lan
ag
a
r
in
d
H
o
s
p
ital
in
ac
c
o
r
d
a
n
ce
with
g
o
o
d
clin
ical
p
r
ac
tice
(
GC
P)
s
t
an
d
ar
d
s
.
PC
a
p
atien
t
’
s
ch
an
ce
s
o
f
s
u
r
v
iv
al
ar
e
e
x
am
in
ed
u
s
in
g
C
OX
r
eg
r
ess
io
n
.
Acc
o
r
d
i
n
g
to
th
e
r
esu
lts
,
in
2
0
1
5
,
7
8
p
eo
p
le
wi
th
PC
a
wer
e
tr
ea
te
d
b
y
2
2
p
at
ien
ts
,
6
3
.
6
3
6
%
we
r
e
s
till
aliv
e
an
d
3
6
.
3
6
4
%
h
a
d
p
ass
ed
awa
y
.
T
h
er
e
wer
e
eig
h
teen
p
atien
ts
aliv
e
in
2
0
1
6
.
W
ith
a
d
o
cto
r
-
f
r
ien
d
ly
g
r
a
p
h
i
c
u
s
er
in
ter
f
ac
e,
th
is
r
esear
ch
aim
s
to
in
clu
d
e
tar
g
eted
th
er
a
p
y
f
ea
tu
r
es
o
r
r
ea
l
-
tim
e
o
cc
u
r
r
en
ce
s
to
d
is
p
lay
p
r
ec
is
e
p
r
ed
ictin
g
r
esu
lts
[
1
7
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
N
o
ve
l p
r
o
s
ta
te
ca
n
ce
r
d
etec
tio
n
a
n
d
cla
s
s
ifica
tio
n
mo
d
el
u
s
in
g
s
u
p
p
o
r
t v
ec
to
r
… (
K
a
n
d
u
k
u
r
i S
u
ja
ta
)
1683
PC
a2
8
g
en
e
Sig
n
atu
r
e
was
u
s
ed
to
b
e
a
p
r
ed
icto
r
o
f
PC
a
,
p
r
o
tein
-
p
r
o
tein
i
n
ter
ac
ti
o
n
n
etwo
r
k
a
n
d
g
en
o
m
e
-
wid
e
a
n
aly
s
is
to
f
in
d
p
o
ten
tial
g
en
es
f
o
r
PC
a
ea
r
ly
d
iag
n
o
s
tic
b
io
m
ar
k
e
r
s
.
First,
u
s
in
g
two
s
ep
ar
ate
s
o
u
r
ce
s
,
th
e
au
th
o
r
s
g
ath
er
e
d
g
en
e
ex
p
r
ess
io
n
d
atasets
o
f
1
4
5
PC
a
s
am
p
les f
r
o
m
th
e
g
en
e
ex
p
r
ess
io
n
o
m
n
ib
u
s
(
GE
O)
.
T
h
ese
s
am
p
les
in
clu
d
ed
b
o
th
th
e
tu
m
o
r
a
n
d
th
e
ass
o
ciate
d
n
o
r
m
al
tis
s
u
es.
I
n
tu
m
o
r
s
am
p
les,
th
e
g
en
es
th
at
wer
e
co
n
s
id
er
ab
ly
s
tr
o
n
g
ly
an
d
wea
k
l
y
ex
p
r
ess
ed
,
r
esp
ec
tiv
ely
,
wer
e
f
o
u
n
d
b
y
th
e
au
th
o
r
s
to
b
e
1
5
8
an
d
2
6
8
.
Ad
d
itio
n
ally
,
p
r
ed
ictio
n
s
co
r
es
(
P
S)
an
d
clu
s
t
er
s
co
r
es
(
C
S)
ar
e
d
escr
ib
ed
t
o
ch
o
o
s
e
2
8
g
e
n
es
(
r
ef
er
r
e
d
to
as PC
a2
8
)
ass
o
cia
ted
with
PC
a
.
T
h
e
f
in
d
in
g
s
s
h
o
w
th
at
PC
a2
8
is
s
p
ec
if
ic
to
P
C
a
h
as th
e
ab
ilit
y
to
d
if
f
er
en
tiate
b
etwe
en
n
o
r
m
al
a
n
d
tu
m
o
r
o
u
s
tis
s
u
es [
1
8
]
.
PC
a
r
is
k
p
r
ed
ictio
n
u
s
in
g
a
n
e
n
h
an
ce
d
h
y
b
r
id
alg
o
r
ith
m
was
d
escr
ib
ed
.
T
h
is
s
tu
d
y
p
r
e
p
r
o
c
ess
es
th
e
d
ata,
p
r
esen
ts
th
e
clin
ical
d
i
ag
n
o
s
is
f
ea
tu
r
es
o
f
PC
a
,
an
d
d
ev
elo
p
s
a
law
b
y
ex
am
in
i
n
g
th
e
co
n
n
ec
tio
n
b
etwe
en
PC
a
,
PS
A,
an
d
o
th
er
in
d
icato
r
s
u
s
in
g
p
atien
t
d
at
a
f
r
o
m
p
atien
ts
with
b
en
ig
n
p
r
o
s
tate
d
is
ea
s
e
an
d
PC
a
f
r
o
m
th
e
Natio
n
al
C
en
te
r
f
o
r
C
lin
ical
Me
d
ical
Scien
ce
Data
(
3
0
1
Ho
s
p
ital)
is
co
n
t
ain
s
a
PC
a
d
ataset.
As
th
e
p
r
ed
ictio
n
m
o
d
el,
a
class
if
ier
co
m
b
in
in
g
th
e
Ad
aBo
o
s
t
an
d
r
an
d
o
m
f
o
r
est
alg
o
r
ith
m
s
ar
e
ch
o
s
en
b
ased
o
n
cr
o
s
s
-
v
alid
atio
n
o
n
th
e
tr
ai
n
in
g
s
et.
T
h
e
r
atio
s
o
f
a
g
e,
P
SA
(
f
r
ee
)
,
an
d
PS
A
(
to
tal)
h
a
v
e
a
g
r
ea
t
c
h
an
ce
o
f
d
etec
tin
g
PC
,
ac
co
r
d
in
g
to
r
e
s
ea
r
ch
co
n
d
u
cted
b
y
th
e
au
th
o
r
s
.
PC
a
i
s
al
s
o
af
f
ec
ted
d
if
f
er
en
tly
b
y
d
iag
n
o
s
tic
f
ea
tu
r
es
s
u
ch
as
b
r
ain
n
atr
iu
r
e
tic
p
ep
tid
e
p
r
ec
u
r
s
o
r
,
f
r
ee
ca
l
ciu
m
,
ap
o
lip
o
p
r
o
tein
E
r
atio
,
ap
o
lip
o
p
r
o
tein
A1
,
an
d
cr
ea
tin
e
p
r
o
tein
T
ch
lo
r
i
d
e
[
1
9
]
.
T
h
e
d
etec
tio
n
o
f
p
r
o
s
tate
tu
m
o
r
Glea
s
o
n
s
co
r
es
an
d
ca
n
ce
r
tr
ea
t
m
en
t
u
s
in
g
r
ea
l
-
ti
m
e
f
o
r
m
al
v
er
if
icatio
n
was
d
escr
ib
ed
.
T
h
is
ap
p
r
o
ac
h
u
s
es
f
o
r
m
al
m
e
th
o
d
s
to
d
if
f
er
th
e
Glea
s
o
n
s
co
r
e
an
d
th
e
PC
a
tr
ea
tm
en
t.
B
ec
au
s
e
it
d
o
esn
’
t
in
v
o
lv
e
a
b
io
p
s
y
,
th
e
s
u
g
g
ested
p
r
o
ce
d
u
r
e
is
th
u
s
n
o
n
-
in
v
asiv
e.
Usi
n
g
a
co
llectio
n
o
f
tem
p
o
r
al
l
o
g
ic
f
ea
tu
r
es,
th
ey
ass
ig
n
th
e
Gle
aso
n
s
co
r
e
an
d
th
e
r
elativ
e
t
r
ea
tm
en
t
to
p
atien
t
m
ag
n
etic
r
eso
n
an
ce
p
ictu
r
es
b
y
m
o
d
elin
g
th
em
as
tim
ed
au
t
o
m
ata
n
etwo
r
k
s
.
I
n
th
e
Glea
s
o
n
s
co
r
e
in
f
er
en
ce
,
ea
ch
ass
ess
ed
ca
s
e
h
ad
a
s
en
s
itiv
ity
an
d
s
p
ec
if
icity
o
f
1
,
an
d
in
th
e
t
h
er
ap
y
p
r
e
d
ictio
n
,
th
e
co
r
r
esp
o
n
d
in
g
v
alu
es
wer
e
0
.
9
4
a
n
d
1
,
r
esp
ec
tiv
ely
,
th
is
s
u
g
g
ested
m
eth
o
d
’
s
ef
f
ec
tiv
en
ess
is
co
n
f
ir
m
ed
b
y
th
e
ex
p
e
r
im
en
tal
s
tu
d
y
,
wh
ich
v
alid
ates th
e
q
u
a
liti
es o
n
3
6
d
if
f
e
r
en
t p
atien
ts
[
2
0
]
.
Me
d
ical
im
ag
e
p
r
o
ce
s
s
in
g
was
u
s
ed
to
r
e
co
n
s
tr
u
ct
tis
s
u
e
p
r
o
p
er
ties
f
o
r
ca
n
ce
r
s
cr
ee
n
i
n
g
.
A
n
ew
ap
p
r
o
ac
h
f
o
r
d
eter
m
in
in
g
th
e
r
elativ
e
tis
s
u
e
elast
icity
p
ar
am
eter
s
is
p
r
esen
ted
,
b
ased
o
n
b
o
th
g
eo
m
etr
ic
an
d
p
h
y
s
ical
r
estrictio
n
s
.
A
s
tati
s
tically
b
ased
clas
s
if
ier
th
at
au
to
m
atica
lly
g
en
er
ates
a
clin
ical
T
-
s
tag
e
an
d
Glea
s
o
n
s
co
r
e
b
ased
o
n
th
e
elasticity
v
alu
es
r
ec
o
n
s
tr
u
cted
f
r
o
m
CT
im
ag
es
ar
e
p
r
o
p
o
s
ed
b
y
th
e
au
th
o
r
s
.
Ma
k
in
g
u
s
e
o
f
a
f
ea
tu
r
e
s
et
in
clu
d
in
g
p
atien
t
ag
e
i
n
f
o
r
m
atio
n
an
d
r
ec
o
n
s
tr
u
cte
d
r
elativ
e
el
asti
city
p
ar
am
eter
s
,
with
u
p
to
8
5
%
ac
cu
r
ac
y
f
o
r
c
an
ce
r
s
tag
in
g
an
d
u
p
to
7
7
%
a
cc
u
r
ac
y
f
o
r
ca
n
c
er
g
r
ad
i
n
g
,
th
e
r
elativ
e
elastic
ity
ch
ar
ac
ter
is
tics
wer
e
u
tili
ze
d
to
p
r
ed
ict
ca
n
ce
r
g
r
a
d
in
g
a
n
d
s
ta
g
in
g
[
2
1
]
.
A
DL
ap
p
r
o
ac
h
was
em
p
l
o
y
e
d
to
PC
a
d
etec
tio
n
u
s
in
g
tar
g
e
ted
co
n
t
r
ast
-
en
h
an
ce
d
u
ltra
s
o
u
n
d
.
I
n
th
is
s
tu
d
y
,
a
DL
s
y
s
tem
f
o
r
id
en
t
if
y
in
g
PC
a
in
c
o
n
s
ec
u
tiv
e
C
o
n
tr
ast
-
en
h
an
ce
d
u
ltra
-
s
o
u
n
d
(
C
E
US)
im
ag
es
is
p
r
esen
ted
.
T
h
r
o
u
g
h
th
r
ee
-
d
im
en
s
io
n
al
co
n
v
o
lu
tio
n
o
p
er
atio
n
s
,
th
e
s
u
g
g
ested
m
eth
o
d
co
n
s
is
ten
tly
r
ec
o
v
er
s
f
ea
tu
r
es
f
r
o
m
b
o
th
t
h
e
s
p
ati
al
an
d
tem
p
o
r
al
d
im
en
s
io
n
s
,
th
en
ca
p
tu
r
in
g
th
e
d
y
n
am
ic
in
f
o
r
m
atio
n
o
f
t
h
e
p
er
f
u
s
io
n
p
r
o
ce
s
s
s
to
r
ed
in
m
an
y
ad
jace
n
t
f
r
am
es
f
o
r
t
h
e
i
d
en
tific
atio
n
o
f
PC
a
.
T
ests
d
em
o
n
s
tr
ated
th
at
t
h
e
DL
tech
n
iq
u
e
o
u
t
p
er
f
o
r
m
ed
p
r
ev
io
u
s
ly
r
e
p
o
r
ted
m
eth
o
d
s
an
d
im
p
lem
en
tatio
n
s
,
o
b
tai
n
in
g
ap
p
r
o
x
im
ately
9
1
%
s
p
ec
if
icity
an
d
9
0
%
av
er
a
g
e
ac
cu
r
ac
y
f
o
r
th
e
d
ia
g
n
o
s
is
o
f
PC
a
in
th
e
tar
g
eted
C
E
US
im
ag
es
(
p
<0
.
0
5
)
.
T
h
e
am
o
u
n
t
o
f
th
e
av
ailab
le
d
ata
was
co
n
s
tr
ain
ed
b
y
th
e
u
s
e
o
f
ex
p
er
im
en
tal
tar
g
eted
c
o
n
tr
ast
ag
en
t
in
th
e
C
E
US v
id
eo
s
u
s
ed
f
o
r
th
is
r
es
ea
r
ch
[
2
2
]
.
A
m
o
d
el
was
d
esig
n
ed
th
at
c
an
d
if
f
er
e
n
tiates
b
etwe
en
PC
a
an
d
b
en
i
g
n
p
r
o
s
tatic
h
y
p
er
p
lasi
a
u
s
in
g
ML
-
ba
s
ed
p
r
o
s
tate
-
s
p
ec
if
ic
a
n
tig
en
d
en
s
ity
(
PS
AD
)
in
a
s
in
g
le
-
ce
n
ter
r
etr
o
s
p
ec
tiv
e
r
es
ea
r
ch
co
n
d
u
cted
in
C
h
in
a.
W
h
en
c
o
m
b
in
e
d
with
ag
e
an
d
th
e
p
r
o
s
tate
’
s
o
p
p
o
s
ite
d
iam
eter
,
PS
AD
d
em
o
n
s
tr
ated
a
g
o
o
d
a
b
ilit
y
to
id
en
tify
PC
a
,
ac
co
r
d
in
g
to
a
d
ec
is
io
n
tr
ee
p
r
ed
ictio
n
m
o
d
el
th
at
was
d
ev
elo
p
ed
t
o
aid
in
t
h
e
d
iag
n
o
s
is
o
f
th
e
d
is
ea
s
e.
Patien
t
s
with
a
s
m
a
ll
p
r
o
s
tate
tr
an
s
v
er
s
e
d
iam
et
er
s
h
o
u
ld
b
e
clo
s
ely
m
o
n
ito
r
ed
b
y
p
h
y
s
ician
s
d
u
e
to
th
eir
in
c
r
ea
s
ed
r
is
k
o
f
PC
a
.
Fo
r
PC
a
s
cr
ee
n
in
g
,
d
iag
n
o
s
is
,
p
r
o
g
n
o
s
is
,
an
d
f
o
llo
w
-
u
p
,
th
is
wo
r
k
o
f
f
er
ed
an
ex
ce
llen
t
d
iag
n
o
s
is
an
d
tr
ea
tm
en
t
m
eth
o
d
th
at
s
u
p
p
o
r
ted
m
ed
ical
p
r
o
f
ess
io
n
als
in
m
ak
in
g
th
e
b
est
s
elec
tio
n
[
2
3
]
.
T
h
e
ap
p
licatio
n
o
f
th
e
B
ay
esian
n
etwo
r
k
ap
p
r
o
ac
h
was
d
esig
n
ed
to
f
in
d
th
e
r
elatio
n
s
h
i
p
b
etwe
en
th
e
m
o
r
p
h
o
lo
g
ical
f
ea
tu
r
es
tak
en
f
r
o
m
im
ag
es
o
f
PC
a
.
A
B
ay
esian
n
etwo
r
k
an
aly
s
is
ap
p
r
o
ac
h
is
u
s
ed
in
th
is
s
tu
d
y
to
m
ea
s
u
r
e
th
e
s
tr
en
g
t
h
o
f
t
h
e
r
elatio
n
s
h
ip
b
etwe
en
v
ar
io
u
s
f
ea
t
u
r
es
an
d
to
s
u
m
m
ar
ize
th
e
im
ag
in
g
p
r
o
f
ile
o
f
p
atien
ts
f
r
o
m
th
e
PC
a
im
a
g
in
g
d
atab
ase
u
s
in
g
a
wid
e
r
an
g
e
o
f
m
o
r
p
h
o
lo
g
ical
f
ea
tu
r
es.
T
h
r
o
u
g
h
th
e
u
s
e
o
f
m
u
tu
al
in
f
o
r
m
atio
n
,
K
u
llb
ac
k
-
L
ieb
ler
,
an
d
Pear
s
o
n
’
s
co
r
r
elatio
n
,
a
n
an
al
y
s
is
was
m
ad
e
to
d
eter
m
i
n
e
th
e
n
o
d
es
s
tr
en
g
th
o
f
ass
o
c
iatio
n
.
Mu
ltip
le
f
ea
tu
r
e
co
n
n
ec
tio
n
s
wer
e
d
eter
m
in
e
d
to
b
e
th
e
s
tr
o
n
g
est.
Ad
d
itio
n
ally
,
th
e
im
p
ac
t
o
f
n
o
d
e
co
n
n
ec
tio
n
s
a
n
d
n
o
d
e
f
o
r
ce
wer
e
ca
lcu
lated
.
T
h
is
r
esear
ch
ca
n
f
u
r
th
e
r
im
p
r
o
v
e
d
etec
tio
n
p
er
f
o
r
m
a
n
ce
b
y
id
en
tify
i
n
g
t
h
e
f
ea
t
u
r
es
th
at
ar
e
m
o
r
e
d
o
m
i
n
an
t
i
n
estab
lis
h
in
g
th
e
co
n
n
ec
tio
n
[
2
4
]
.
MRI
-
b
ased
co
m
p
u
te
r
-
aid
ed
PC
a
id
en
tific
atio
n
was
d
em
o
n
s
tr
ated
.
T
h
e
two
-
s
tag
e
co
m
p
letely
au
to
m
ated
c
o
m
p
u
ter
-
aid
e
d
d
etec
tio
n
s
y
s
tem
was
ex
am
i
n
ed
b
y
th
e
wr
iter
s
o
f
th
is
r
esear
ch
.
Usi
n
g
v
o
x
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
38
,
No
.
3
,
J
u
n
e
20
25
:
1
6
8
1
-
1
6
8
9
1684
f
ea
tu
r
e
ex
tr
ac
tio
n
,
class
if
icatio
n
,
lo
ca
l
m
ax
im
a
d
etec
tio
n
,
a
n
d
m
u
lti
-
atlas
-
b
ased
p
r
o
s
tate
s
eg
m
en
tatio
n
,
th
ey
id
en
tify
f
ir
s
t
ca
n
d
id
ates
in
th
e
f
ir
s
t
s
tep
.
T
h
e
b
ases
f
o
r
p
e
r
f
o
r
m
an
ce
ev
al
u
atio
n
ar
e
lesi
o
n
-
b
ased
f
r
ee
-
r
esp
o
n
s
e
r
ec
eiv
er
o
p
er
atin
g
ch
ar
ac
ter
is
tic
cu
r
v
es
an
d
p
atien
t
-
b
ased
ev
alu
atio
n
s
o
f
r
ec
eiv
er
o
p
e
r
at
in
g
ch
ar
ac
ter
is
tics
.
Fu
r
th
er
m
o
r
e
,
a
co
m
p
ar
is
o
n
is
m
ad
e
b
etwe
en
th
e
s
y
s
tem
an
d
r
ad
io
l
o
g
is
ts
p
r
ed
icte
d
clin
ical
p
er
f
o
r
m
an
ce
.
T
h
e
s
e
n
s
i
t
i
v
i
t
y
,
f
o
r
0
.
1
,
1
,
a
n
d
1
0
f
a
l
s
e
p
o
s
i
t
i
v
e
s
p
e
r
n
o
r
m
a
l
c
a
s
e
,
i
s
0
.
4
2
,
0
.
7
5
,
a
n
d
0
.
8
9
,
a
c
c
o
r
d
i
n
g
t
o
t
h
e
r
e
s
u
l
t
s
[
2
5
]
.
C
las
s
if
icatio
n
o
f
PC
a
u
s
in
g
wav
elet
n
eu
r
al
n
etwo
r
k
(
W
NN
)
was
d
escr
ib
ed
.
Mo
r
let
f
u
n
ctio
n
was
em
p
lo
y
ed
as
a
n
ac
tiv
atio
n
f
u
n
ctio
n
o
f
W
NN
an
d
b
ac
k
p
r
o
p
ag
atio
n
(
BP
)
was
ap
p
lied
f
o
r
tr
ain
in
g
th
e
W
NN.
T
h
e
W
NN
clas
s
if
ied
th
e
PC
a
b
ased
o
n
th
r
ee
f
ac
to
r
s
s
u
ch
as
p
r
o
s
tate
v
o
lu
m
e,
a
g
e
o
f
p
atien
t
an
d
lev
el
o
f
PS
A.
T
h
e
p
er
f
o
r
m
a
n
ce
r
esu
lts
s
h
o
wed
th
at
th
e
W
NN
h
as lo
w
m
ea
n
s
q
u
ar
e
er
r
o
r
(
MSE
)
[
2
6
]
.
T
o
ad
d
r
ess
th
e
ab
o
v
e
-
m
en
ti
o
n
ed
lim
itatio
n
,
th
is
p
ap
er
p
r
esen
ts
a
n
o
v
el
PC
a
d
etec
tio
n
an
d
class
if
icatio
n
m
o
d
el
b
ased
o
n
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e.
T
h
e
s
ec
tio
n
2
p
r
esen
ts
,
n
o
v
el
PC
a
d
etec
tio
n
an
d
class
if
icatio
n
m
o
d
el
u
s
in
g
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e.
T
h
e
s
ec
tio
n
3
e
v
alu
ates
th
e
r
esu
lt
an
aly
s
is
.
Sectio
n
4
r
ep
r
esen
ts
th
e
wo
r
k
f
in
al
co
n
c
lu
s
io
n
.
2.
NO
VE
L
P
CA
DE
T
E
C
T
I
O
N
AND
CL
A
SS
I
F
I
CA
T
I
O
N
M
O
DE
L
I
n
th
is
s
ec
tio
n
,
n
o
v
el
PC
a
d
etec
tio
n
an
d
class
if
icatio
n
m
o
d
el
u
s
in
g
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
in
e
is
p
r
esen
ted
.
Fig
u
r
e
1
d
is
p
lay
s
th
e
p
r
esen
ted
m
o
d
el
’
s
b
lo
c
k
d
iag
r
am
.
Firstl
y
,
th
e
d
ataset
is
co
llected
f
r
o
m
k
ag
g
le
h
ea
lth
ca
r
e
r
ep
o
s
itiry
a
s
co
m
m
a
s
ep
er
ated
v
alu
es
(
.
csv
)
f
iles
.
Pre
tr
ea
tm
en
t
d
ata
f
o
r
PC
a
p
atien
ts
is
in
clu
d
ed
in
th
e
d
atab
ase.
Ser
u
m
,
s
eled
i
lip
id
p
r
o
f
ile,
a
n
d
g
en
er
al
b
ac
k
g
r
o
u
n
d
d
ata
wer
e
co
m
b
in
ed
in
to
o
n
e.
T
h
is
lab
elled
d
ataset,
wh
ich
co
m
p
r
is
es
2
5
0
f
ea
tu
r
es
an
d
o
n
e
class
o
f
f
ea
tu
r
es
was
ex
tr
ac
ted
f
r
o
m
m
ed
ical
ex
am
in
atio
n
r
ec
o
r
d
s
o
f
p
atien
ts
wh
o
ar
e
s
u
s
p
ec
ted
o
f
h
av
i
n
g
PC
a
.
Patien
ts
b
ac
k
g
r
o
u
n
d
d
ata
in
clu
d
e
d
ag
e
,
r
ac
e,
b
o
d
y
m
ass
in
d
ex
(
B
MI
)
,
an
d
f
am
ily
h
is
to
r
y
;
o
th
er
in
f
o
r
m
atio
n
in
clu
d
e
d
b
lo
o
d
in
s
em
en
,
er
ec
tile
d
y
s
f
u
n
ctio
n
,
u
r
i
n
e
d
if
f
ic
u
lties
,
an
d
u
r
in
e
s
tr
ea
m
f
o
r
ce
.
Pre
p
r
o
ce
s
s
in
g
is
d
o
n
e
o
n
t
h
e
d
ataset
to
g
et
r
em
o
v
al
o
f
n
o
is
e,
in
co
m
p
leten
ess
,
class
im
b
alan
ce
,
an
d
o
th
er
ir
r
e
g
u
lar
ities
.
T
h
e
p
r
ep
r
o
ce
s
s
in
g
in
v
o
lv
ed
th
e
f
o
llo
win
g
s
tep
s
:
n
o
r
m
aliza
tio
n
,
d
is
cr
etiza
tio
n
,
r
esam
p
lin
g
,
an
d
d
ata
clea
n
in
g
.
I
n
o
r
d
er
to
elim
in
ate
s
p
ar
s
el
y
d
is
tr
ib
u
ted
r
ec
o
r
d
s
an
d
c
o
lu
m
n
s
f
ill
in
m
is
s
in
g
v
alu
es,
d
ata
clea
n
i
n
g
was
p
er
f
o
r
m
e
d
.
Miss
in
g
,
in
c
o
n
s
is
ten
t,
an
d
I
n
c
o
m
p
lete
v
alu
es
wer
e
s
u
cc
ess
f
u
lly
elim
in
ated
f
r
o
m
th
e
d
ataset
b
y
d
ata
clea
n
in
g
,
wh
ich
ad
d
r
ess
ed
o
v
er
-
an
d
u
n
d
e
r
s
am
p
lin
g
p
r
o
b
lem
s
c
o
n
n
ec
te
d
to
class
im
b
alan
ce
,
r
esam
p
lin
g
was
im
p
lem
en
ted
.
I
f
ch
a
r
ac
ter
is
tics
o
f
a
class
ar
e
d
is
tr
ib
u
ted
o
r
r
ep
r
esen
ted
d
if
f
er
en
tly
,
th
e
r
e
is
an
im
b
alan
ce
.
PC
a
an
d
n
o
n
-
PC
a
wer
e
t
h
e
tar
g
et
cla
s
s
f
ea
tu
r
es
tak
en
i
n
to
co
n
s
id
er
atio
n
i
n
th
is
ex
am
in
atio
n
.
T
h
e
im
b
alan
ce
d
d
ataset
p
r
o
b
lem
is
s
o
lv
ed
b
y
u
p
s
am
p
le
th
e
m
in
o
r
ity
class
an
d
d
o
wn
s
am
p
le
th
e
m
ajo
r
ity
class
.
B
y
s
u
b
s
titu
tin
g
n
u
m
er
ical
e
q
u
iv
alen
c
y
f
o
r
n
o
m
in
al
v
alu
es,
th
e
d
ataset
was
d
is
cr
etize
d
.
B
y
p
er
f
o
r
m
in
g
th
is
,
th
e
am
o
u
n
t
o
f
d
ata
is
d
ec
r
ea
s
ed
an
d
th
e
n
u
m
b
er
o
f
p
o
s
s
ib
le
v
ar
iatio
n
s
in
ea
ch
PC
a
f
ea
tu
r
e
is
m
o
d
er
ate
d
.
T
h
e
m
is
s
in
g
v
alu
es
a
r
e
f
illed
in
u
s
in
g
th
is
p
r
o
ce
d
u
r
e.
I
t
also
m
ak
es
t
h
e
ML
w
o
r
k
f
aster
an
d
ea
s
ier
.
Fig
u
r
e
1
.
B
lo
ck
d
iag
r
am
o
f
n
o
v
el
PC
a
d
etec
tio
n
an
d
class
if
icatio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
N
o
ve
l p
r
o
s
ta
te
ca
n
ce
r
d
etec
tio
n
a
n
d
cla
s
s
ifica
tio
n
mo
d
el
u
s
in
g
s
u
p
p
o
r
t v
ec
to
r
… (
K
a
n
d
u
k
u
r
i S
u
ja
ta
)
1685
I
n
ter
m
s
o
f
d
is
tan
ce
m
ea
s
u
r
e,
m
in
i
mum
-
m
ax
im
u
m
n
o
r
m
aliza
tio
n
m
ak
es
s
u
r
e
th
at
th
e
P
C
a
d
ataset
f
ea
tu
r
e
is
n
o
t
o
v
er
wh
elm
ed
b
y
o
th
er
ch
ar
ac
ter
is
tics
.
T
h
e
v
alu
es
ar
e
m
o
d
if
ie
d
in
t
h
is
p
r
o
ce
d
u
r
e
to
a
r
an
g
e,
wh
ich
is
ty
p
ically
b
etwe
en
0
a
n
d
1
.
T
h
e
p
r
esen
t stu
d
y
u
s
ed
t
h
e
m
in
im
u
m
-
m
ax
im
u
m
(
m
in
-
m
ax
)
n
o
r
m
aliza
tio
n
ap
p
r
o
ac
h
,
as sh
o
wn
in
(
1
)
:
(
)
=
−
(
)
m
ax
(
)
−
m
i
n
(
)
(
1
)
wh
er
e
m
in
an
d
m
ax
r
ep
r
esen
t th
e
v
ar
iab
le
’
s
(
f
ea
tu
r
e
x
’
s
)
r
an
g
e
’
s
m
in
im
al
a
n
d
m
ax
im
u
m
v
alu
es,
r
esp
ec
tiv
ely
.
W
h
en
a
d
ataset
’
s
v
alu
es
ar
e
s
im
p
lifie
d
to
a
s
ca
le
b
etwe
en
0
an
d
1
,
th
i
s
is
r
ef
er
r
ed
to
as
f
ea
tu
r
e
s
ca
lin
g
.
Pre
p
r
o
ce
s
s
in
g
p
r
o
d
u
ce
s
clea
n
,
n
o
is
e
-
f
r
ee
,
c
o
n
s
is
ten
t,
an
d
n
o
r
m
alize
d
f
in
al
o
u
t
p
u
t.
R
elev
an
t
ch
ar
ac
ter
is
tics
ar
e
f
o
u
n
d
af
te
r
th
e
PC
a
clin
ical
d
ataset
h
as
b
ee
n
clea
n
ed
,
r
esam
p
led
,
d
is
cr
etize
d
,
an
d
n
o
r
m
alize
d
.
Prin
cip
al
co
m
p
o
n
en
t
a
n
aly
s
is
(
PC
A)
is
al
s
o
u
s
ed
in
f
ea
tu
r
e
e
x
tr
ac
tio
n
to
p
r
ev
en
t
d
ata
lo
s
s
.
T
h
e
tar
g
et
class
is
m
ain
tain
ed
a
n
d
th
e
d
ataset
h
as
less
d
im
en
s
io
n
s
as
th
e
r
esu
lt.
T
h
e
1
2
m
o
s
t
r
elev
an
t
f
ea
t
u
r
es
wer
e
ch
o
s
en
af
ter
f
ea
tu
r
es
wer
e
r
ated
i
n
r
el
atio
n
to
th
e
PC
a
d
at
aset.
T
h
e
p
r
o
ce
s
s
o
f
ch
o
o
s
in
g
th
e
s
u
b
s
et
o
f
th
e
m
o
s
t
r
elate
d
an
d
a
p
p
r
o
p
r
iate
f
ea
t
u
r
es
to
b
e
in
clu
d
e
d
in
th
e
ML
m
o
d
el
’
s
co
n
s
tr
u
ctio
n
ar
e
k
n
o
wn
as
f
ea
tu
r
e
s
elec
tio
n
.
Ad
d
in
g
th
e
s
ig
n
if
ica
n
t
f
ea
tu
r
es
to
th
e
d
ataset
an
d
r
em
o
v
i
n
g
th
e
u
n
im
p
o
r
tan
t
ch
ar
ac
ter
is
tics
is
th
e
ir
r
elev
an
t
f
ea
tu
r
e
s
elec
tio
n
is
ca
r
r
ied
o
u
t.
W
r
ap
p
er
a
n
d
f
ilter
(
o
n
e
-
way
ANOV
A)
ar
e
two
-
s
tep
f
ea
tu
r
e
s
elec
tio
n
m
et
h
o
d
s
th
at
ar
e
u
s
ed
to
s
elec
t
im
p
o
r
tan
t
f
ea
tu
r
es
f
r
o
m
th
o
s
e
ex
tr
ac
ted
.
T
h
er
e
a
r
e
in
s
tan
ce
s
in
wh
ich
lear
n
in
g
alg
o
r
ith
m
s
p
er
f
o
r
m
p
o
o
r
ly
in
te
r
m
s
o
f
p
r
ed
ictio
n
b
ec
au
s
e
o
f
in
s
ig
n
if
ican
t
in
p
u
t
f
ea
tu
r
es.
As
a
r
esu
lt,
f
ea
tu
r
e
s
elec
tio
n
wh
ich
ch
o
o
s
es
ar
tific
ia
l
in
tellig
en
ce
(
AI
)
-
b
ased
class
if
icatio
n
id
en
tify
in
g
th
e
m
o
s
t
u
s
ef
u
l
c
h
ar
ac
ter
is
tics
f
o
r
a
d
ataset.
W
ith
th
e
u
s
e
o
f
an
r
ec
u
r
s
iv
e
f
ea
tu
r
e
elim
in
atio
n
(
R
FE
)
tech
n
iq
u
e,
wh
ich
b
u
ild
s
b
aselin
e
m
o
d
els
co
n
tin
u
o
u
s
l
y
an
d
ch
o
o
s
es
th
e
f
ea
tu
r
e
th
at
p
er
f
o
r
m
s
th
e
b
est
ea
ch
tim
e
u
n
til
all
f
ea
tu
r
es
ar
e
class
if
ied
,
th
e
b
est
f
ea
tu
r
es
ar
e
f
ir
s
t
s
elec
ted
.
T
h
is
s
tu
d
y
u
tili
ze
d
a
b
aselin
e
m
o
d
el
is
a
g
r
ad
ie
n
t
b
o
o
s
tin
g
class
if
ier
,
to
p
er
f
o
r
m
th
e
R
FE
p
r
o
ce
d
u
r
e.
Featu
r
es
th
u
s
g
et
o
r
d
e
r
ed
f
r
o
m
s
tr
o
n
g
est to
wea
k
est in
a
d
esc
en
d
in
g
o
r
d
e
r
.
T
h
e
f
ea
tu
r
e
s
ig
n
if
ican
ce
(
F
-
v
alu
e
an
d
p
-
v
alu
e)
a
n
d
ef
f
ec
t
s
ize
(
eta
s
q
u
ar
e
d
)
o
f
th
e
s
am
p
l
es
ch
o
s
en
u
s
in
g
R
FE
is
d
eter
m
in
ed
u
s
in
g
a
o
n
e
-
way
a
n
aly
s
is
o
f
v
ar
ia
n
ce
(
ANOVA
)
s
tatis
tical
tes
t.
B
ased
o
n
th
e
eta
s
q
u
ar
ed
an
d
ef
f
ec
tiv
e
s
ize,
th
e
m
ag
n
itu
d
e
d
if
f
er
e
n
ce
s
b
etw
ee
n
th
e
two
g
r
o
u
p
s
(
m
alig
n
an
t
an
d
b
e
n
ig
n
)
wer
e
ex
am
in
ed
.
T
h
e
d
if
f
er
en
ce
b
et
wee
n
th
e
two
g
r
o
u
p
s
is
s
h
o
wn
to
b
e
in
s
ig
n
if
ican
t,
less
r
elev
an
t,
im
p
o
r
tan
t b
y
th
e
tin
y
,
m
ed
iu
m
,
an
d
h
ig
h
e
f
f
ec
t
s
izes.
Data
u
s
ed
f
o
r
test
in
g
an
d
tr
ain
in
g
ar
e
tr
ea
ted
u
s
in
g
t
h
e
ch
o
s
en
f
ea
t
u
r
es.
T
r
ain
in
g
an
d
test
in
g
d
ata
is
p
r
esen
ted
to
th
e
ch
o
s
en
f
ea
t
u
r
es.
A
s
u
p
er
v
is
ed
ML
ap
p
r
o
ac
h
ca
lled
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SVM)
is
f
in
d
s
th
e
m
ax
im
u
m
-
m
ar
g
in
h
y
p
e
r
p
lan
e
f
o
r
b
i
n
ar
y
class
if
icatio
n
,
s
ep
ar
atin
g
k
n
o
wn
class
if
ied
d
ata
p
o
in
ts
f
r
o
m
u
n
k
n
o
wn
d
ata
p
o
in
ts
.
Pre
d
ictin
g
n
ew
d
ata
s
ets
is
f
as
ter
th
an
with
o
th
er
p
r
ed
ictiv
e
m
o
d
els,
r
eg
ar
d
less
o
f
th
e
s
ize
o
f
th
e
tr
ain
in
g
s
et
in
th
e
d
o
m
ain
.
W
h
en
g
iv
en
a
n
u
n
k
n
o
wn
PC
a
tu
p
le
with
o
u
t
its
co
r
r
esp
o
n
d
in
g
o
u
tp
u
t
class
,
th
e
SVM
m
o
d
el
lo
o
k
s
f
o
r
t
h
e
K
tr
ai
n
in
g
tu
p
les
th
at
a
r
e
m
o
s
t
s
im
ilar
to
th
e
u
n
k
n
o
wn
tu
p
le
in
th
e
p
atter
n
s
p
ac
e.
B
y
ap
p
ly
in
g
class
ical
s
tati
s
tical
lear
n
in
g
th
eo
r
y
,
th
e
SVM
p
r
o
d
u
ce
s
a
m
o
d
el
th
at
ca
n
b
e
ea
s
ily
u
n
d
er
s
to
o
d
an
d
p
r
o
v
i
d
es
g
o
o
d
g
en
e
r
aliza
tio
n
o
f
n
ew
in
f
o
r
m
atio
n
.
Sin
ce
th
ey
s
u
p
p
o
r
t
t
h
e
p
lace
m
en
t
o
f
th
e
d
iv
id
in
g
h
y
p
er
p
la
n
es,
th
e
clo
s
est
p
o
in
ts
ar
e
k
n
o
wn
as
s
u
p
p
o
r
t
v
ec
to
r
s
.
I
t
also
s
u
g
g
est
s
th
at
th
e
h
y
p
er
p
lan
es
ca
n
n
o
t
b
e
ch
an
g
e
d
b
y
c
h
an
g
i
n
g
th
e
n
o
n
s
u
p
p
o
r
t
v
ec
t
o
r
s
,
an
d
v
ice
v
er
s
a.
Fin
d
in
g
th
e
o
p
tim
u
m
h
y
p
e
r
p
lan
e
th
at
m
ax
im
izes
th
e
m
ar
g
in
b
etwe
en
tw
o
class
es
is
th
e
g
o
al
o
f
s
u
p
er
v
is
ed
ML
alg
o
r
ith
m
s
ca
lled
s
u
p
er
v
is
ed
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es,
o
r
SVMs.
B
ec
au
s
e
o
f
th
eir
well
-
d
ev
el
o
p
ed
m
at
h
em
atica
l
f
o
r
m
u
latio
n
,
f
lex
ib
ilit
y
,
h
ig
h
ac
cu
r
ac
y
,
s
tr
o
n
g
th
eo
r
etica
l
s
u
p
p
o
r
t,
d
ir
ec
t
g
eo
m
etr
ic
in
ter
p
r
etatio
n
,
an
d
th
e
n
u
m
b
er
o
f
s
o
f
twar
e
im
p
lem
e
n
tatio
n
s
,
SVMs
h
av
e
b
ee
n
ex
t
en
s
iv
ely
u
s
ed
f
o
r
th
e
d
etec
tio
n
an
d
class
if
icatio
n
o
f
PC
a.
T
h
e
SVM
d
etec
ts
th
e
p
r
esen
ce
an
d
a
b
s
en
ce
o
f
PC
a.
I
f
P
C
a
is
d
etec
ted
th
en
it
class
if
ies
th
e
PC
a
asn
ad
en
o
ca
r
cin
o
m
as
,
s
m
all
c
ell
ca
r
cin
o
m
a
(
s
m
all
ce
ll
n
e
u
r
o
en
d
o
cr
in
e
ca
r
ci
n
o
m
a)
,
o
t
h
er
n
eu
r
o
en
d
o
cr
in
e
tu
m
o
r
s
(
in
clu
d
in
g
b
ig
ce
ll
ca
r
cin
o
m
a)
,
tr
an
s
itio
n
al
ce
ll
ca
r
cin
o
m
a,
a
n
d
s
ar
co
m
as,
th
e
S
VM
d
etec
ts
PC
a
as
eith
er
n
o
r
m
al
o
r
PC
a.
Ad
en
o
ca
r
cin
o
m
as
ac
co
u
n
t
f
o
r
n
ea
r
ly
all
ca
s
es
o
f
PC
a
.
T
h
e
p
r
o
s
tate
’
s
g
lan
d
ce
lls
,
wh
ich
p
r
o
d
u
ce
th
e
f
lu
id
th
at
’
s
ad
d
e
d
to
s
em
en
,
a
r
e
th
e
ca
u
s
e
o
f
th
ese
tu
m
o
r
s
.
As
a
r
esu
lt,
th
is
an
aly
s
is
h
as
e
x
tr
em
ely
ac
cu
r
ately
r
ec
o
g
n
ized
a
n
d
class
if
ied
.
T
h
e
m
o
d
el
’
s
p
er
f
o
r
m
an
ce
is
v
er
i
f
ied
in
ter
m
s
o
f
ac
cu
r
ac
y
,
s
en
s
i
tiv
ity
,
s
p
ec
if
icity
,
p
r
ec
is
io
n
an
d
F1
-
s
co
r
e
a
n
d
ar
e
d
ef
in
ed
as f
o
llo
ws:
T
h
e
(
2
)
d
e
f
in
es th
e
ac
cu
r
ac
y
as
:
=
+
+
+
+
×
100
(
2
)
T
h
e
p
e
r
ce
n
tag
e
o
f
th
o
s
e
with
th
e
tar
g
et
c
o
n
d
itio
n
an
d
p
o
s
itiv
e
test
r
esu
lts
is
r
ef
er
r
e
d
t
o
as
s
en
s
itiv
ity
,
o
r
“
p
o
s
itiv
ity
in
PC
a
d
is
ea
s
e
”
.
T
h
e
s
en
s
itiv
ity
is
ex
p
r
ess
ed
in
(
3
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
38
,
No
.
3
,
J
u
n
e
20
25
:
1
6
8
1
-
1
6
8
9
1686
=
+
×
100
(
3
)
T
h
e
p
er
ce
n
ta
g
e
am
o
n
g
th
o
s
e
with
o
u
t
th
e
tar
g
et
d
is
ea
s
e
wh
o
h
ad
n
eg
ativ
e
test
r
esu
lts
is
k
n
o
wn
as
s
p
ec
if
icity
,
o
r
“
n
eg
ativ
ity
in
PC
a
d
is
ea
s
e
”
.
T
h
e
ex
p
r
ess
io
n
f
o
r
Sp
ec
if
icity
is
d
ef
in
ed
i
n
(
4
)
.
=
+
×
100
(
4
)
Pre
cisi
o
n
:
T
h
e
p
r
ec
is
io
n
ca
n
b
e
d
ef
in
ed
as
th
e
s
u
m
o
f
tr
u
e
p
o
s
itiv
es
an
d
f
alse
p
o
s
it
iv
es,
o
r
th
e
n
u
m
b
er
o
f
tr
u
e
p
o
s
itiv
es d
iv
id
ed
b
y
th
e
to
tal
n
u
m
b
er
o
f
p
o
s
itiv
e
p
r
e
d
ictio
n
s
.
T
h
e
(
5
)
d
e
f
in
es th
e
p
r
ec
is
io
n
.
=
+
×
100
(
5
)
T
h
e
F1
-
s
co
r
e
in
d
icate
s
th
at
th
e
m
o
d
el
d
etec
ts
p
o
s
itiv
e
c
ases
wh
ile
r
ed
u
cin
g
f
alse
p
o
s
itiv
es
an
d
f
alse
n
eg
ativ
es.
T
h
e
(
6
)
e
x
p
r
ess
ed
t
h
e
F1
-
s
co
r
e.
1
−
=
2
×
×
+
(
6
)
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
,
n
o
v
el
PC
a
d
e
tectio
n
an
d
class
if
icatio
n
m
o
d
el
u
s
in
g
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
is
im
p
lem
en
ted
.
T
h
is
p
ar
t
ev
alu
ates
th
e
m
o
d
el
’
s
r
esu
lts
an
aly
s
is
th
at
was
p
r
esen
ted
.
T
h
e
p
er
f
o
r
m
a
n
ce
m
etr
ics
u
s
ed
to
ev
al
u
ate
th
e
p
r
o
p
o
s
ed
PC
a
m
o
d
el
ar
e
F1
-
s
co
r
e,
s
p
e
c
if
icity
,
ac
cu
r
ac
y
,
s
en
s
itiv
ity
,
an
d
p
r
ec
is
io
n
.
T
h
e
ev
alu
atio
n
o
f
p
er
f
o
r
m
a
n
ce
is
p
r
esen
ted
in
T
ab
le
1
.
C
o
m
p
ar
ed
to
Naïv
e
b
a
y
es
(
NB
)
clas
s
if
ier
,
SVM
clas
s
if
i
er
h
as
o
b
tain
ed
b
etter
p
er
f
o
r
m
an
ce
.
T
h
e
Fig
u
r
e
2
s
h
o
ws
th
e
p
er
f
o
r
m
an
ce
m
etr
ics
c
o
m
p
ar
ativ
e
g
r
ap
h
s
.
T
h
e
Fig
u
r
es 2
(
a)
a
n
d
2
(
b
)
s
h
o
ws
s
en
s
itiv
ity
an
d
s
p
ec
if
icity
co
m
p
ar
is
o
n
r
esp
ec
tiv
ely
.
T
ab
le
1
.
Per
f
o
r
m
an
ce
co
m
p
a
r
is
o
n
M
e
t
r
i
c
s
/
a
l
g
o
r
i
t
h
m
N
a
ï
v
e
b
a
y
e
s
S
V
M
P
r
e
c
i
s
i
o
n
(
%)
91
9
5
.
2
3
S
e
n
s
i
t
i
v
i
t
y
(
%)
9
0
.
2
3
9
4
.
5
7
S
p
e
c
i
f
i
c
i
t
y
(
%)
9
2
.
3
9
5
.
9
A
c
c
u
r
a
c
y
(
%)
9
0
.
4
5
9
5
.
6
7
F1
-
sc
o
r
e
(
%)
8
9
.
6
2
9
5
.
2
3
(
a)
(
b
)
Fig
u
r
e
2
.
Per
f
o
r
m
an
c
e
co
m
p
ar
ativ
e
g
r
ap
h
f
o
r
(
a)
s
en
s
itiv
ity
an
d
(
b
)
s
p
ec
if
icity
I
n
Fig
u
r
e
2
(
a)
,
th
e
x
-
ax
is
in
d
icate
s
ML
class
if
ier
s
an
d
y
-
ax
is
in
d
icate
s
p
er
f
o
r
m
an
c
e
in
ter
m
s
o
f
p
er
ce
n
tag
e.
T
h
e
SVM
h
as
s
h
o
wn
b
etter
p
er
f
o
r
m
a
n
ce
f
o
r
s
en
s
itiv
ity
an
d
s
p
ec
if
icity
th
an
NB
class
if
ier
.
T
h
e
Fig
u
r
e
3
s
h
o
ws
th
e
p
er
f
o
r
m
a
n
ce
co
m
p
a
r
is
o
n
g
r
ap
h
s
.
T
h
e
Fig
u
r
e
s
3(
a)
a
n
d
3
(
b
)
s
h
o
ws
p
r
e
cisi
o
n
an
d
ac
cu
r
ac
y
co
m
p
ar
is
o
n
.
C
o
m
p
ar
e
d
to
NB
class
if
ier
,
SVM
h
as
ac
h
iev
ed
b
etter
p
r
ec
is
io
n
f
o
r
PC
a
d
etec
tio
n
an
d
class
if
icatio
n
.
T
h
e
SVM
class
if
ier
h
as
o
b
tain
ed
b
etter
ac
cu
r
ac
y
th
an
NB
.
T
h
e
Fig
u
r
e
4
s
h
o
ws
F1
-
s
co
r
e
co
m
p
ar
is
o
n
.
Fro
m
Fig
u
r
e
4
,
it
is
clea
r
th
at,
th
e
SVM
h
as
h
ig
h
F1
-
s
co
r
e
t
h
a
n
o
th
e
r
class
if
ier
s
.
Hen
ce
p
r
esen
ted
m
o
d
el
h
as
ef
f
ec
tiv
e
ly
d
etec
ted
an
d
class
if
ied
th
e
PC
a
.
W
h
en
PC
a
is
id
en
tifie
d
ea
r
ly
o
n
,
v
ar
i
o
u
s
s
tr
ateg
ies f
o
r
tr
ea
tm
en
t c
an
b
e
im
p
lem
en
ted
a
n
d
th
e
d
is
ea
s
e
’
s
p
r
o
g
r
ess
io
n
m
a
y
b
e
p
r
ev
en
te
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
N
o
ve
l p
r
o
s
ta
te
ca
n
ce
r
d
etec
tio
n
a
n
d
cla
s
s
ifica
tio
n
mo
d
el
u
s
in
g
s
u
p
p
o
r
t v
ec
to
r
… (
K
a
n
d
u
k
u
r
i S
u
ja
ta
)
1687
(
a)
(
b
)
Fig
u
r
e
3
.
Per
f
o
r
m
an
c
e
co
m
p
ar
ativ
e
g
r
ap
h
s
(
a
)
p
r
ec
is
io
n
p
er
f
o
r
m
an
ce
c
o
m
p
ar
is
o
n
an
d
(
b
)
a
cc
u
r
ac
y
p
er
f
o
r
m
an
ce
co
m
p
ar
is
o
n
Fig
u
r
e
4
.
F1
-
s
co
r
e
p
er
f
o
r
m
a
n
c
e
co
m
p
ar
is
o
n
4.
CO
NCLU
SI
O
N
I
n
th
is
wo
r
k
,
n
o
v
el
PC
a
d
e
tectio
n
an
d
class
if
icatio
n
m
o
d
el
u
s
in
g
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
in
e
is
p
r
esen
ted
.
T
h
e
SVM
is
u
tili
z
ed
in
t
h
e
ea
r
l
y
s
tag
es
o
f
PC
a
d
if
f
er
en
tial
d
iag
n
o
s
is
.
T
o
id
e
n
tify
an
d
ca
teg
o
r
ize
p
eo
p
le
with
an
d
with
o
u
t
PC
a,
SVM
is
u
tili
ze
d
.
Am
o
n
g
th
e
v
ar
iab
les
tak
en
in
to
c
o
n
s
id
er
ati
o
n
in
th
is
s
tu
d
y
ar
e
r
ac
e,
ag
e,
B
o
d
y
m
ass
in
d
e
x
(
B
MI
)
,
o
b
esit
y
,
f
am
ily
h
is
to
r
y
,
p
r
o
b
lem
s
tr
o
u
b
le
u
r
in
atin
g
,
b
lo
o
d
in
s
em
en
,
u
r
in
e
s
tr
ea
m
f
o
r
ce
,
b
o
n
e
p
ain
,
a
n
d
er
ec
tile
d
y
s
f
u
n
ctio
n
.
Pre
p
r
o
ce
s
s
in
g
is
d
o
n
e
o
n
t
h
e
d
ataset
to
ad
d
r
ess
d
im
en
s
io
n
ality
r
e
d
u
ctio
n
an
d
class
im
b
alan
ce
.
An
aly
zin
g
a
n
d
ca
teg
o
r
izin
g
th
e
im
p
o
r
ta
n
t
f
ea
tu
r
es
in
o
r
d
e
r
to
d
etec
t
PC
a
is
th
e
aim
o
f
f
ea
tu
r
e
s
elec
tio
n
.
T
o
ch
o
o
s
e
ess
en
tial
ch
ar
ac
ter
is
tics
,
th
e
two
-
s
tep
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
is
u
s
ed
.
T
h
e
ef
f
ec
tiv
en
ess
o
f
th
is
s
y
s
tem
i
s
m
e
as
u
r
ed
in
ter
m
s
o
f
F1
-
s
co
r
e
,
Pre
cisi
o
n
,
Sen
s
itiv
ity
,
Acc
u
r
ac
y
,
an
d
Sp
ec
if
icity
.
T
h
e
SVM
class
if
ier
h
as
ac
h
iev
ed
im
p
r
o
v
ed
ac
cu
r
ac
y
in
P
C
a
d
etec
tio
n
an
d
class
if
icatio
n
wh
en
co
m
p
ar
ed
to
p
r
ev
io
u
s
m
o
d
els.
Me
d
ica
l
p
r
o
f
ess
io
n
als
ca
n
u
s
e
th
is
ap
p
r
o
ac
h
f
o
r
ea
r
ly
de
tectio
n
an
d
class
if
icatio
n
o
f
PC
a,
m
in
im
izin
g
d
ea
th
r
a
te,
s
av
in
g
tim
e
an
d
c
o
s
t.
I
n
f
u
tu
r
e,
h
y
b
r
id
ML
tech
n
iq
u
es will b
e
u
s
ed
to
f
u
r
t
h
er
im
p
r
o
v
e
th
e
p
er
f
o
r
m
an
ce
o
f
PC
a
ca
n
ce
r
d
etec
tio
n
a
n
d
d
iag
n
o
s
is
.
F
U
N
DI
N
G
I
N
F
O
RM
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
A
U
T
H
O
R
C
O
NT
R
I
B
UT
I
O
N
S
ST
AT
E
M
E
NT
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Kan
d
u
k
u
r
i Su
jata
✓
✓
✓
✓
✓
✓
✓
✓
B
okka
Srid
h
ar
✓
✓
✓
✓
✓
✓
✓
A
v
ala
M
allik
ar
ju
n
a
Pra
s
ad
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
38
,
No
.
3
,
J
u
n
e
20
25
:
1
6
8
1
-
1
6
8
9
1688
C
O
N
F
L
I
CT
O
F
I
NT
E
RE
ST
S
T
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
D
A
T
A
AV
A
I
L
A
B
I
L
I
T
Y
-
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
o
p
en
l
y
av
ailab
le
in
[
Sit
i
Sar
ah
et.
a
l.,
]
at
h
ttp
://
1
0
.
1
1
5
9
1
/ijece.
v
1
3
i6
.
p
p
6
8
6
2
-
6871
.
o
r
g
/[
1
0
.
1
1
5
9
1
/ijece.
v
1
3
i
6
.
p
p
6
8
6
2
-
6
8
7
1
]
,
[
4
]
.
-
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
o
p
en
l
y
av
ailab
le
in
[
Ham
za
Ab
u
e
t.
a
l.,
]
at
h
ttp
://
1
0
.
1
1
5
9
1
/ijece.
v
1
4
i2
.
p
p
2
2
3
4
-
2241
.
o
r
g
/[
1
0
.
1
1
5
9
1
/ijece.
v
1
4
i
2
.
p
p
2
2
3
4
-
2
2
4
1
],
[
6
]
.
-
T
h
e
d
ata
t
h
at
s
u
p
p
o
r
t
th
e
f
i
n
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
o
p
e
n
ly
av
ailab
le
in
[
Kim
C
H
et.
a
l.,
]
at
h
ttp
://
1
0
.
3
3
9
0
/can
ce
r
s
1
3
0
7
1
5
2
4
.
o
r
g
/[
1
0
.
3
3
9
0
/can
ce
r
s
1
3
0
7
1
5
2
4
]
,
[
1
4
]
.
-
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
t
h
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
will
b
e
av
ailab
le
in
[
I
E
E
E
]
[
DOI
:
1
0
.
1
1
0
9
/AC
C
E
SS
.
2
0
2
3
.
3
3
2
6
8
8
2
]
allo
w
f
o
r
t
h
e
co
m
m
e
r
cializa
tio
n
o
f
r
esear
c
h
f
in
d
i
n
g
s
.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
K
a
r
a
g
o
z
,
D
.
A
l
i
s
,
M
.
E
.
S
e
k
e
r
,
G
.
Ze
y
b
e
l
,
M
.
Y
e
r
g
i
n
,
I
.
O
k
su
z
,
a
n
d
E
.
K
a
r
a
a
r
s
l
a
n
,
“
A
n
a
t
o
mi
c
a
l
l
y
g
u
i
d
e
d
s
e
l
f
a
d
a
p
t
i
n
g
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
c
l
i
n
i
c
a
l
l
y
s
i
g
n
i
f
i
c
a
n
t
P
C
a
d
e
t
e
c
t
i
o
n
o
n
b
i
p
a
r
a
me
t
r
i
c
M
R
I
:
a
mu
l
t
i
c
e
n
t
e
r
s
t
u
d
y
,
”
I
n
s
i
g
h
t
s
i
n
t
o
I
m
a
g
i
n
g
,
v
o
l
.
1
4
,
n
o
.
1
1
0
,
p
p
.
1
-
1
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
8
6
/
s1
3
2
4
4
-
0
2
3
-
0
1
4
3
9
-
0
.
[
2
]
A
.
R
a
mm
a
l
,
R
.
A
ssaf,
A
.
G
o
u
p
i
l
,
M
.
K
a
c
i
m
a
n
d
,
V
.
V
r
a
b
i
e
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
o
n
h
o
mo
l
o
g
i
c
a
l
p
e
r
si
st
e
n
c
e
f
e
a
t
u
r
e
s
f
o
r
P
C
a
d
i
a
g
n
o
si
s
,
”
BM
C
B
i
o
i
n
f
o
rm
a
t
i
c
s,
v
o
l
.
2
3
,
p
p
.
1
-
2
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
8
6
/
s1
2
8
5
9
-
0
2
2
-
0
4
9
9
2
-
5
.
[
3
]
J.
H
e
r
p
e
t
a
l
.
,
“
M
o
d
e
l
i
n
g
o
f
e
l
e
c
t
r
o
n
i
c
h
e
a
l
t
h
r
e
c
o
r
d
s
f
o
r
t
i
me
-
v
a
r
i
a
n
t
e
v
e
n
t
l
e
a
r
n
i
n
g
b
e
y
o
n
d
b
i
o
-
mar
k
e
r
s
—
a
c
a
se
s
t
u
d
y
i
n
P
C
a
,
”
in
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
5
0
2
9
5
-
5
0
3
0
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
7
2
7
4
5
.
[
4
]
S
.
S
.
M
d
N
o
h
,
N
.
I
b
r
a
h
i
m
,
M
.
M
.
M
a
n
s
o
r
,
a
n
d
M
.
Y
u
so
f
f
,
“
H
y
b
r
i
d
f
i
l
t
e
r
i
n
g
me
t
h
o
d
s
f
o
r
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
i
n
h
i
g
h
-
d
i
me
n
si
o
n
a
l
c
a
n
c
e
r
d
a
t
a
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
ri
n
g
(
I
J
E
C
E)
,
v
o
l
.
1
3
,
n
o
.
6
,
p
p
.
6
8
6
2
-
6
8
7
1
,
D
e
c
e
mb
e
r
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
3
i
6
.
p
p
6
8
6
2
-
6
8
7
1
.
[
5
]
M
.
O
g
i
n
o
,
Z
.
Li
,
a
n
d
A
.
S
h
i
mi
z
u
,
“
A
u
g
m
e
n
t
e
d
r
a
d
i
o
l
o
g
y
:
f
e
a
t
u
r
e
s
p
a
c
e
t
r
a
n
sf
e
r
mo
d
e
l
f
o
r
P
C
a
st
a
g
e
p
r
e
d
i
c
t
i
o
n
,
”
in
I
EEE
A
c
c
e
ss
,
v
o
l
.
9
,
p
p
.
1
0
2
5
5
9
-
1
0
2
5
6
6
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
9
8
0
3
8
.
[
6
]
H
.
A
.
O
w
i
d
a
,
M
.
R
.
H
a
ssa
n
,
A
.
M
.
A
l
i
,
F
.
A
l
n
a
i
m
a
t
,
A
.
A
.
S
h
a
r
a
h
,
S
.
A
b
u
o
w
a
i
d
a
,
a
n
d
N
.
A
l
s
h
d
a
i
f
a
t
,
“
T
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
i
n
p
r
o
st
a
t
e
ma
g
n
e
t
i
c
r
e
s
o
n
a
n
c
e
i
m
a
g
i
n
g
s
c
r
e
e
n
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
l
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
ri
n
g
(
I
J
E
C
E)
,
v
o
l
.
1
4
,
n
o
.
2
,
p
p
.
2
2
3
4
-
2
2
4
1
,
A
p
r
i
l
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
4
i
2
.
p
p
2
2
3
4
-
224
1
.
[
7
]
P
.
F
.
R
.
W
i
l
so
n
e
t
a
l
.
,
“
S
e
l
f
-
s
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
w
i
t
h
l
i
m
i
t
e
d
l
a
b
e
l
e
d
d
a
t
a
f
o
r
P
C
a
d
e
t
e
c
t
i
o
n
i
n
h
i
g
h
-
f
r
e
q
u
e
n
c
y
u
l
t
r
a
so
u
n
d
,
”
i
n
I
EE
E
T
ra
n
s
a
c
t
i
o
n
s
o
n
U
l
t
r
a
so
n
i
c
s,
Fe
r
ro
e
l
e
c
t
ri
c
s,
a
n
d
Fre
q
u
e
n
c
y
C
o
n
t
r
o
l
,
v
o
l
.
7
0
,
n
o
.
9
,
p
p
.
1
0
7
3
-
1
0
8
3
,
S
e
p
t
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
TU
F
F
C
.
2
0
2
3
.
3
2
9
7
8
4
0
.
[
8
]
J.
T
a
n
g
,
X
.
Zh
e
n
g
,
X
.
W
a
n
g
,
Q
.
M
a
o
,
L.
X
i
e
a
n
d
R
.
W
a
n
g
,
"
C
o
m
p
u
t
e
r
-
a
i
d
e
d
d
e
t
e
c
t
i
o
n
o
f
p
r
o
s
t
a
t
e
c
a
n
c
e
r
i
n
e
a
r
l
y
s
t
a
g
e
s
u
s
i
n
g
mu
l
t
i
-
p
a
r
a
m
e
t
e
r
M
R
I
:
A
p
r
o
mi
s
i
n
g
a
p
p
r
o
a
c
h
f
o
r
e
a
r
l
y
d
i
a
g
n
o
si
s
,
"
T
e
c
h
n
o
l
o
g
y
a
n
d
H
e
a
l
t
h
C
a
re
,
v
o
l
.
3
2
,
n
o
.
1
,
p
p
.
1
2
5
-
1
3
3
,
Jan
u
a
r
y
2
0
2
4
,
d
o
i
:
1
0
.
3
2
3
3
/
TH
C
-
2
4
8
0
1
1
.
[
9
]
D
.
Li
,
X
.
H
a
n
,
J
.
G
a
o
,
Q
.
Zh
a
n
g
,
H
.
Y
a
n
g
,
S
.
Li
a
o
,
H
.
G
u
o
,
a
n
d
B
.
Zh
a
n
g
,
“
D
e
e
p
L
e
a
r
n
i
n
g
i
n
P
C
a
d
i
a
g
n
o
s
i
s
u
s
i
n
g
m
u
l
t
i
p
a
r
a
met
r
i
c
mag
n
e
t
i
c
r
e
so
n
a
n
c
e
i
m
a
g
i
n
g
w
i
t
h
w
h
o
l
e
-
m
o
u
n
t
h
i
st
o
p
a
t
h
o
l
o
g
y
r
e
f
e
r
e
n
c
e
d
d
e
l
i
n
e
a
t
i
o
n
s
,
”
Fr
o
n
t
i
e
rs
i
n
Me
d
i
c
i
n
e
,
v
o
l
.
8
,
p
p
.
1
-
9
,
Jan
u
a
r
y
2
0
2
2
,
d
o
i
:
1
0
.
3
3
8
9
/
f
me
d
.
2
0
2
1
.
8
1
0
9
9
5
.
[
1
0
]
M
d
.
R
.
H
a
ss
a
n
,
M
d
.
F
.
I
sl
a
m
,
M
d
.
Z
.
U
d
d
i
n
,
G
.
G
h
o
s
h
a
l
,
M
.
M
.
H
a
ssa
n
,
S
.
H
u
d
a
,
G
.
F
o
r
t
i
n
o
,
“
P
C
a
c
l
a
ss
i
f
i
c
a
t
i
o
n
f
r
o
m
u
l
t
r
a
s
o
u
n
d
a
n
d
M
R
I
i
mag
e
s
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
b
a
s
e
d
e
x
p
l
a
i
n
a
b
l
e
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
,
”
F
u
t
u
r
e
G
e
n
e
ra
t
i
o
n
C
o
m
p
u
t
e
r S
y
st
e
m
s,
v
o
l
.
1
2
7
,
p
p
.
4
6
2
-
4
7
2
,
F
e
b
r
u
a
r
y
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
u
t
u
r
e
.
2
0
2
1
.
0
9
.
0
3
0
.
[
1
1
]
O
.
O
z
h
a
n
a
n
d
F
.
H
.
Y
a
g
i
n
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
P
C
a
b
a
s
e
d
o
n
c
l
i
n
i
c
a
l
b
i
o
mar
k
e
r
s
,
”
T
h
e
J
o
u
rn
a
l
o
f
C
o
g
n
i
t
i
v
e
S
y
s
t
e
m
s (
J
C
S
)
,
v
o
l
.
7
,
n
o
.
2
,
p
p
.
1
7
-
2
0
,
2
0
2
2
,
d
o
i
:
1
0
.
5
2
8
7
6
/
j
c
s.
1
2
2
1
4
2
5
.
[
1
2
]
L
.
Z
h
a
n
g
,
L
.
Li
,
M
.
T
a
n
g
,
Y
.
H
u
a
n
,
X
.
Z
h
a
n
g
,
a
n
d
X
.
Z
h
e
,
“
A
n
e
w
a
p
p
r
o
a
c
h
t
o
d
i
a
g
n
o
s
i
n
g
P
C
a
t
h
r
o
u
g
h
ma
g
n
e
t
i
c
r
e
so
n
a
n
c
e
i
ma
g
i
n
g
,
”
Al
e
x
a
n
d
r
i
a
E
n
g
i
n
e
e
r
i
n
g
J
o
u
rn
a
l
,
v
o
l
.
6
0
,
n
o
.
1
,
p
p
.
8
9
7
-
9
0
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
j
.
2
0
2
0
.
1
0
.
0
1
8
.
[
1
3
]
E
.
G
r
e
s
s
e
r
e
t
a
l
.
,
“
P
e
r
f
o
r
m
a
n
c
e
v
a
r
i
a
b
i
l
i
t
y
o
f
r
a
d
i
o
m
i
c
s
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
t
h
e
d
e
t
e
c
t
i
o
n
o
f
c
l
i
n
i
c
a
l
l
y
s
i
g
n
i
f
i
c
a
n
t
P
C
a
i
n
h
e
t
e
r
o
g
e
n
e
o
u
s
M
R
I
d
a
t
a
s
e
t
s
,
”
Q
u
a
n
t
I
m
a
g
i
n
g
M
e
d
S
u
r
g
,
v
o
l
.
1
2
,
n
o
.
1
1
,
p
p
.
4
9
9
0
-
5
0
0
3
,
2
0
2
2
,
d
o
i
:
1
0
.
2
1
0
3
7
/
q
i
m
s
-
22
-
2
6
5
.
[
1
4
]
C
.
H
.
K
i
m,
S
.
B
h
a
t
t
a
c
h
a
r
j
e
e
,
D
.
P
r
a
k
a
sh
,
S
.
K
a
n
g
,
N
.
H
.
C
h
o
,
H
.
C
.
K
i
m,
a
n
d
H
.
K
.
C
h
o
i
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
t
e
c
h
n
i
q
u
e
s
f
o
r
P
C
a
d
e
t
e
c
t
i
o
n
t
h
r
o
u
g
h
d
u
a
l
-
c
h
a
n
n
e
l
t
i
ss
u
e
f
e
a
t
u
r
e
e
n
g
i
n
e
e
r
i
n
g
.
c
a
n
c
e
r
s
(
B
a
se
l
)
,
v
o
l
.
1
3
,
n
o
.
7
,
p
p
.
1
-
1
6
,
M
a
r
c
h
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
c
a
n
c
e
r
s
1
3
0
7
1
5
2
4
.
[
1
5
]
J.
A
.
A
l
z
a
t
e
-
G
r
i
sa
l
e
s,
A
.
M
o
r
a
-
R
u
b
i
o
,
F
.
G
a
r
c
í
a
-
G
a
r
c
í
a
,
R
.
Ta
b
a
r
e
s
-
S
o
t
o
,
a
n
d
M
.
D
.
L
.
I
g
l
e
s
i
a
-
V
a
y
á
,
“
S
A
M
-
U
N
ETR
:
C
l
i
n
i
c
a
l
l
y
si
g
n
i
f
i
c
a
n
t
P
C
a
se
g
me
n
t
a
t
i
o
n
u
s
i
n
g
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
f
r
o
m
l
a
r
g
e
mo
d
e
l
,
”
in
I
EEE
A
c
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
1
1
8
2
1
7
-
1
1
8
2
2
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
3
2
6
8
8
2
.
[
1
6
]
Y
.
Zh
u
,
L
.
W
a
n
g
,
M
.
Li
u
,
C
.
Q
i
a
n
,
A
.
Y
o
u
su
f
,
A
.
O
t
o
,
a
n
d
D
.
S
h
e
n
,
“
M
R
I
-
b
a
se
d
P
C
a
d
e
t
e
c
t
i
o
n
w
i
t
h
h
i
g
h
-
l
e
v
e
l
r
e
p
r
e
s
e
n
t
a
t
i
o
n
a
n
d
h
i
e
r
a
r
c
h
i
c
a
l
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
Me
d
P
h
y
s
,
v
o
l
.
4
4
,
n
o
.
3
,
p
p
.
1
0
2
8
-
1
0
3
9
,
M
a
r
c
h
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
0
2
/
mp
.
1
2
1
1
6
.
[
1
7
]
N
.
T
h
o
n
g
p
i
m,
C
.
C
h
o
k
s
u
c
h
a
t
,
T
.
B
e
j
r
a
n
a
n
d
a
,
a
n
d
S
.
M
a
t
a
y
o
n
g
,
“
O
n
p
r
e
d
i
c
t
i
n
g
s
u
r
v
i
v
a
l
o
p
p
o
r
t
u
n
i
t
i
e
s
f
o
r
P
C
a
by
C
O
X
r
e
g
r
e
ssi
o
n
i
n
P
S
U
p
a
t
i
e
n
t
s
d
a
t
a
,
”
2
0
2
0
1
7
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
/
El
e
c
t
ro
n
i
c
s,
C
o
m
p
u
t
e
r,
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
E
C
T
I
-
C
O
N
)
,
P
h
u
k
e
t
,
Th
a
i
l
a
n
d
,
2
0
2
0
,
p
p
.
7
7
5
-
7
7
8
,
d
o
i
:
1
0
.
1
1
0
9
/
E
C
TI
-
C
O
N
4
9
2
4
1
.
2
0
2
0
.
9
1
5
8
3
1
8
.
[
1
8
]
J.
-
Y
.
Le
e
e
t
a
l
.,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
t
h
e
P
C
a
2
8
g
e
n
e
si
g
n
a
t
u
r
e
a
s
a
p
r
e
d
i
c
t
o
r
i
n
P
C
a
,
”
2
0
1
8
I
E
EE
1
8
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Bi
o
i
n
f
o
rm
a
t
i
c
s
a
n
d
Bi
o
e
n
g
i
n
e
e
r
i
n
g
(
B
I
BE)
,
Ta
i
c
h
u
n
g
,
Ta
i
w
a
n
,
2
0
1
8
,
p
p
.
1
5
5
-
1
5
8
,
d
o
i
:
1
0
.
1
1
0
9
/
B
I
B
E.
2
0
1
8
.
0
0
0
3
7
.
[
1
9
]
M
.
Li
,
X
.
F
u
,
a
n
d
C
.
M
e
n
g
,
“
T
h
e
r
i
sk
p
r
e
d
i
c
t
i
o
n
o
f
P
C
a
b
a
s
e
d
o
n
a
i
mp
r
o
v
e
d
h
y
b
r
i
d
a
l
g
o
r
i
t
h
m
,
”
2
0
2
0
I
E
EE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
m
a
rt
C
l
o
u
d
(
S
m
a
r
t
C
l
o
u
d
)
,
W
a
s
h
i
n
g
t
o
n
,
D
C
,
U
S
A
,
2
0
2
0
,
p
p
.
9
4
-
9
9
,
d
o
i
:
1
0
.
1
1
0
9
/
S
mar
t
C
l
o
u
d
4
9
7
3
7
.
2
0
2
0
.
0
0
0
2
6
.
[
2
0
]
L.
B
r
u
n
e
se
,
F
.
M
e
r
c
a
l
d
o
,
A
.
R
e
g
i
n
e
l
l
i
,
a
n
d
A
.
S
a
n
t
o
n
e
,
“
P
r
o
st
a
t
e
g
l
e
a
s
o
n
sco
r
e
d
e
t
e
c
t
i
o
n
a
n
d
c
a
n
c
e
r
t
r
e
a
t
me
n
t
t
h
r
o
u
g
h
r
e
a
l
-
t
i
me
f
o
r
mal
v
e
r
i
f
i
c
a
t
i
o
n
,
”
in
I
EEE
A
c
c
e
ss
,
v
o
l
.
7
,
p
p
.
1
8
6
2
3
6
-
1
8
6
2
4
6
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
6
1
7
5
4
.
[
2
1
]
S
.
Y
a
n
g
,
J.
L
i
a
n
g
,
V
.
Jo
j
i
c
,
J.
Li
a
n
,
R
.
C
.
C
h
e
n
,
a
n
d
M
.
C
.
L
i
n
,
“
R
e
c
o
n
st
r
u
c
t
i
n
g
T
i
ss
u
e
p
r
o
p
e
r
t
i
e
s
f
r
o
m
me
d
i
c
a
l
i
ma
g
e
s
w
i
t
h
a
p
p
l
i
c
a
t
i
o
n
i
n
c
a
n
c
e
r
scre
e
n
i
ng,
”
in
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
Me
d
i
c
a
l
Ro
b
o
t
i
c
s
a
n
d
B
i
o
n
i
c
s
,
v
o
l
.
1
,
n
o
.
1
,
p
p
.
6
-
1
3
,
F
e
b
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
T
M
R
B
.
2
0
1
9
.
2
8
9
5
7
8
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
N
o
ve
l p
r
o
s
ta
te
ca
n
ce
r
d
etec
tio
n
a
n
d
cla
s
s
ifica
tio
n
mo
d
el
u
s
in
g
s
u
p
p
o
r
t v
ec
to
r
… (
K
a
n
d
u
k
u
r
i S
u
ja
ta
)
1689
[
2
2
]
Y
.
F
e
n
g
e
t
a
l
.
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
t
a
r
g
e
t
e
d
c
o
n
t
r
a
st
-
e
n
h
a
n
c
e
d
u
l
t
r
a
s
o
u
n
d
b
a
se
d
P
C
a
d
e
t
e
c
t
i
o
n
,
”
i
n
I
EEE
/
A
C
M
T
ra
n
s
a
c
t
i
o
n
s
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
Bi
o
l
o
g
y
a
n
d
B
i
o
i
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
6
,
n
o
.
6
,
p
p
.
1
7
9
4
-
1
8
0
1
,
1
N
o
v
.
-
D
e
c
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
TC
B
B
.
2
0
1
8
.
2
8
3
5
4
4
4
.
[
2
3
]
Y
.
-
Y
.
Zh
a
n
g
,
Q
.
L
i
,
Y
.
X
i
n
,
a
n
d
W
.
-
Q
.
Lv
,
“
D
i
f
f
e
r
e
n
t
i
a
t
i
n
g
P
C
a
f
r
o
m
b
e
n
i
g
n
p
r
o
st
a
t
i
c
h
y
p
e
r
p
l
a
si
a
u
si
n
g
P
S
A
D
b
a
s
e
d
o
n
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
:
s
i
n
g
l
e
-
c
e
n
t
e
r
r
e
t
r
o
sp
e
c
t
i
v
e
s
t
u
d
y
i
n
C
h
i
n
a
,
”
i
n
I
EEE
/
A
C
M
T
ra
n
s
a
c
t
i
o
n
s
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
B
i
o
l
o
g
y
a
n
d
Bi
o
i
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
6
,
n
o
.
3
,
p
p
.
9
3
6
-
9
4
1
,
1
M
a
y
-
J
u
n
e
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
T
C
B
B
.
2
0
1
8
.
2
8
2
2
6
7
5
.
[
2
4
]
L.
H
u
ssa
i
n
e
t
a
l
.
,
“
A
p
p
l
y
i
n
g
b
a
y
e
si
a
n
n
e
t
w
o
r
k
a
p
p
r
o
a
c
h
t
o
d
e
t
e
r
m
i
n
e
t
h
e
a
ss
o
c
i
a
t
i
o
n
b
e
t
w
e
e
n
m
o
r
p
h
o
l
o
g
i
c
a
l
f
e
a
t
u
r
e
s
e
x
t
r
a
c
t
e
d
f
r
o
m
P
C
a
i
ma
g
e
s
,
”
i
n
I
EEE
Ac
c
e
ss
,
v
o
l
.
7
,
p
p
.
1
5
8
6
-
1
6
0
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
8
.
2
8
8
6
6
4
4
.
[
2
5
]
G
.
Li
t
j
e
n
s,
O
.
D
e
b
a
t
s
,
J.
B
a
r
e
n
t
s
z
,
N
.
K
a
r
ss
e
me
i
j
e
r
,
a
n
d
H
.
H
u
i
sma
n
,
“
C
o
mp
u
t
e
r
-
a
i
d
e
d
d
e
t
e
c
t
i
o
n
o
f
P
C
a
i
n
M
R
I
,
”
in
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
M
e
d
i
c
a
l
I
m
a
g
i
n
g
,
v
o
l
.
3
3
,
n
o
.
5
,
p
p
.
1
0
8
3
-
1
0
9
2
,
M
a
y
2
0
1
4
,
d
o
i
:
1
0
.
1
1
0
9
/
T
M
I
.
2
0
1
4
.
2
3
0
3
8
2
1
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
K
a
n
d
u
k
u
r
i
S
u
ja
t
a
r
e
se
a
rc
h
sc
h
o
lar
in
t
h
e
De
p
a
rtme
n
t
o
f
ECE
a
t
J
N
T
U
Ka
k
in
a
d
a
,
An
d
h
ra
P
ra
d
e
sh
,
I
n
d
ia.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
a
n
d
u
k
u
risu
jata
@g
m
a
il
.
c
o
m
.
Dr
.
B
o
k
k
a
S
r
id
h
a
r
o
b
tain
e
d
P
h
.
D
.
d
e
g
re
e
in
m
e
d
ica
l
ima
g
e
p
r
o
c
e
ss
in
g
fro
m
t
h
e
JN
T
Un
iv
e
rsit
y
Ka
k
i
n
a
d
a
i
n
th
e
y
e
a
r
2
0
1
5
.
He
h
a
s
jo
in
e
d
th
e
El
e
c
tro
n
ics
a
n
d
c
o
m
m
u
n
ica
ti
o
n
En
g
i
n
e
e
rin
g
De
p
a
rtme
n
t
a
t
Len
d
i
I
n
stit
u
te
o
f
E
n
g
i
n
e
e
rin
g
a
n
d
Tec
h
n
o
lo
g
y
i
n
2
0
1
1
a
n
d
c
o
n
ti
n
u
e
s
to
wo
r
k
a
s
P
ro
fe
ss
o
r.
His
r
e
se
a
r
c
h
in
tere
sts
a
re
M
e
d
ica
l
Im
a
g
e
P
ro
c
e
ss
in
g
,
M
a
c
h
i
n
e
Lea
rn
in
g
a
n
d
Op
t
ica
l
c
o
m
m
u
n
ica
ti
o
n
s
a
n
d
Ne
two
rk
s.
He
is
a
li
fe
m
e
m
b
e
r
o
f
IET
E,
IE.
He
h
a
s
a
stro
n
g
b
a
sic
k
n
o
wle
d
g
e
o
n
ima
g
e
p
r
o
c
e
ss
in
g
tec
h
n
i
q
u
e
s
u
si
n
g
a
d
v
a
n
c
e
d
a
n
d
h
y
b
rid
m
e
th
o
d
s
in
b
o
th
sp
a
ti
a
l
a
n
d
fre
q
u
e
n
c
y
d
o
m
a
in
.
He
a
lso
p
o
ss
e
ss
e
s
g
o
o
d
k
n
o
wle
d
g
e
o
n
n
e
u
ra
l
n
e
two
rk
s
a
n
d
d
e
e
p
lea
rn
i
n
g
m
e
th
o
d
s,
g
o
o
d
p
r
o
g
ra
m
m
in
g
sk
il
ls
u
si
n
g
M
AT
LAB,
P
HY
TON
a
p
p
li
e
d
o
n
m
e
d
ica
l
ima
g
e
d
a
ta
se
ts.
He
h
a
s
p
u
b
li
s
h
e
d
5
3
re
se
a
rc
h
p
a
p
e
rs
in
h
ig
h
in
d
e
x
,
Na
ti
o
n
a
l,
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
ls s
o
fa
r.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
srib
1
0
5
@g
m
a
il
.
c
o
m
.
Dr
.
A
v
a
la
M
a
ll
i
k
a
r
ju
n
a
Pra
s
a
d
P
ro
fe
ss
o
r
i
n
E.
C.
E
is
wo
r
k
in
g
a
t
JN
TU
K
,
Ka
k
in
a
d
a
fo
r
th
e
p
a
st
1
1
y
e
a
rs.
He
h
a
s
wo
n
th
e
b
e
st
tea
c
h
e
r
a
w
a
rd
in
th
e
y
e
a
r
2
0
0
8
a
n
d
n
o
w
h
e
is
th
e
P
r
o
fe
ss
o
r
o
f
th
e
d
e
p
a
rt
m
e
n
t
o
f
ECE
,
Un
i
v
e
rsity
C
o
ll
e
g
e
,
JN
TUK,
d
i
d
h
is
B
.
Tec
h
i
n
ECE
fro
m
Na
g
a
rju
n
a
Un
i
v
e
rsity
,
d
u
ri
n
g
1
9
8
4
-
8
8
.
H
e
d
id
h
is
M
.
Tec
h
in
El
e
c
tro
n
ics
a
n
d
In
stru
m
e
n
tati
o
n
fro
m
A
n
d
h
ra
Un
i
v
e
rsity
in
1
9
9
2
a
n
d
c
o
m
p
lete
d
h
is
P
h
.
D.
in
2
0
0
9
fr
o
m
JN
TU
in
t
h
e
field
o
f
A
n
ten
n
a
s.
He
h
a
s
j
o
in
e
d
JN
T
Un
i
v
e
rsity
se
rv
ice
a
s
As
so
c
iate
P
ro
fe
ss
o
r
o
f
ECE
in
Ju
n
e
2
0
0
3
.
He
g
o
t
p
ro
m
o
ted
a
s
P
ro
fe
ss
o
r
in
EC
E
d
u
rin
g
No
v
2
0
1
1
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
_
m
a
ll
i6
5
@y
a
h
o
o
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.