I
n
d
on
e
s
ian
Jou
r
n
al
o
f
E
lec
t
r
ica
l
E
n
gin
e
e
r
in
g
a
n
d
Com
p
u
t
e
r
S
c
ience
Vo
l
.
3
7
,
N
o
.
2
,
F
e
b
r
ua
r
y
20
2
5
,
pp.
1
07
7
~
1
08
4
I
S
S
N:
2
502
-
4
7
52
,
DO
I
:
10
.
11591/i
j
e
e
cs
.v
3
7
.
i
2
.
pp
1
07
7
-
1
08
4
1077
Jou
r
n
al
h
o
m
e
page
:
ht
tp:
//
ij
e
e
cs
.
iaes
c
or
e
.
c
om
L
u
n
g c
an
c
e
r
p
r
e
d
ic
t
io
n
w
ith
ad
v
an
c
e
d
gr
ap
h
n
e
u
r
al
n
e
t
w
o
r
k
s
B
in
e
e
s
h
M
ooz
h
ip
p
u
r
at
h
,
Jayap
an
d
ia
n
Nat
ar
aj
an
D
e
pa
r
tm
e
nt
of
C
o
mput
e
r
S
c
i
e
n
c
e
a
nd
E
ngi
n
e
e
r
in
g, S
c
h
oo
l
of
E
ngi
ne
e
r
in
g a
nd
T
e
c
hn
o
l
o
g
y
,
C
H
R
I
S
T
(
D
e
e
m
e
d t
o
b
e
U
ni
v
e
r
s
it
y
)
,
K
e
nge
r
i
C
a
mpus
, B
a
nga
lo
r
e
,
I
ndi
a
Ar
t
ic
l
e
I
n
f
o
AB
S
T
RA
CT
A
r
ti
c
le
h
is
tor
y
:
R
e
c
e
i
ve
d
M
a
r
23
,
202
4
R
e
vi
s
e
d
S
e
p
18
,
202
4
A
c
c
e
pt
e
d
S
e
p
30
,
202
4
T
h
i
s
re
s
e
ar
c
h
a
i
m
s
t
o
e
n
h
an
ce
l
u
n
g
c
an
ce
r
p
red
i
c
t
i
o
n
u
s
i
n
g
a
d
v
a
n
ced
m
a
c
h
i
n
e
l
e
arn
i
n
g
t
ec
h
n
i
q
u
e
s
.
T
h
e
m
a
j
o
r
f
i
n
d
i
n
g
i
s
t
h
at
i
n
t
e
g
rat
i
n
g
g
rap
h
c
o
n
v
o
l
u
t
i
o
n
al
n
e
t
w
o
rk
s
(G
CN
s
)
w
i
t
h
g
rap
h
at
t
en
t
i
o
n
n
e
t
w
o
rk
s
(G
A
T
s
)
s
i
g
n
i
fi
c
an
t
l
y
i
m
p
ro
v
e
s
p
r
e
d
i
c
t
i
v
e
a
cc
u
ra
cy
.
T
h
e
p
ro
b
l
em
ad
d
r
e
s
s
ed
i
s
t
h
e
n
eed
f
o
r
e
ar
l
y
a
n
d
a
cc
u
rat
e
d
e
t
ec
t
i
o
n
o
f
l
u
n
g
c
a
n
ce
r,
l
ev
e
rag
i
n
g
a
d
at
as
e
t
fro
m
K
ag
g
l
e
's
"
L
u
n
g
Ca
n
ce
r
Pr
ed
i
c
t
i
o
n
D
at
as
e
t
,
"
w
h
i
ch
i
n
c
l
u
d
e
s
3
0
9
i
n
s
t
an
ce
s
a
n
d
1
6
at
t
ri
b
u
t
e
s
.
T
h
e
p
ro
p
o
s
ed
A
-
G
CN
w
i
t
h
G
A
T
mo
d
el
i
s
me
t
i
c
u
l
o
u
s
l
y
en
g
i
n
ee
r
e
d
w
i
t
h
m
u
l
t
i
p
l
e
l
a
y
e
rs
a
n
d
h
i
d
d
en
u
n
i
t
s
,
o
p
t
i
m
i
z
ed
t
h
ro
u
g
h
h
y
p
e
rp
arame
t
e
r
a
d
j
u
s
t
me
n
t
s
,
e
ar
l
y
s
t
o
p
p
i
n
g
mec
h
a
n
i
s
m
s
,
a
n
d
A
d
a
m
o
p
t
i
mi
zat
i
o
n
t
ec
h
n
i
q
u
e
s
.
E
x
p
e
ri
men
t
al
re
s
u
l
t
s
d
emo
n
s
t
rat
e
t
h
e
m
o
d
e
l
's
s
u
p
e
ri
o
r
p
e
rfo
r
m
a
n
ce
,
a
c
h
i
e
v
i
n
g
an
a
ccu
ra
cy
o
f
0
.
9
4
5
4
,
p
re
ci
s
i
o
n
o
f
0
.
9
2
1
3
,
rec
al
l
o
f
0
.
9
7
4
3
,
an
d
an
F1
s
co
r
e
o
f
0
.
9
4
8
2
.
T
h
e
s
e
fi
n
d
i
n
g
s
h
i
g
h
l
i
g
h
t
t
h
e
mo
d
e
l
's
e
ff
i
c
a
cy
i
n
c
ap
t
u
ri
n
g
i
n
t
ri
c
at
e
p
at
t
e
rn
s
w
i
t
h
i
n
p
at
i
e
n
t
d
at
a,
fac
i
l
i
t
at
i
n
g
e
arl
y
i
n
t
e
rv
en
t
i
o
n
s
an
d
p
e
rs
o
n
a
l
i
z
ed
t
reat
m
en
t
p
l
a
n
s
.
T
h
i
s
re
s
e
ar
ch
u
n
d
e
rs
c
o
r
e
s
t
h
e
p
o
t
e
n
t
i
a
l
o
f
g
rap
h
-
b
as
e
d
me
t
h
o
d
o
l
o
g
i
e
s
i
n
med
i
c
a
l
re
s
e
ar
ch
,
p
art
i
c
u
l
arl
y
f
o
r
l
u
n
g
c
an
ce
r
p
red
i
c
t
i
o
n
,
u
l
t
i
m
at
e
l
y
a
i
m
i
n
g
t
o
i
m
p
ro
v
e
p
at
i
en
t
o
u
t
co
me
s
a
n
d
s
u
rv
i
v
a
l
rat
e
s
t
h
r
o
u
g
h
p
ro
ac
t
i
v
e
h
e
al
t
h
c
ar
e
i
n
t
e
r
v
e
n
t
i
o
n
s
.
K
e
y
w
o
r
d
s
:
Gr
a
ph
a
tt
e
n
t
i
o
n
n
e
t
wo
r
k
Gr
a
ph
ne
ur
a
l
n
e
t
wo
r
k
L
u
n
g
c
a
nc
e
r
M
a
c
hi
ne
l
e
a
r
ni
ng
P
r
e
d
i
c
t
i
o
n
Th
i
s
i
s
a
n
o
p
en
a
c
ces
s
a
r
t
i
c
l
e
u
n
d
e
r
t
h
e
CC
B
Y
-
SA
l
i
cen
s
e.
C
or
r
e
s
pon
din
g
A
u
th
or
:
B
i
n
e
e
s
h
M
o
o
z
hi
ppur
a
t
h
De
pa
r
t
m
e
n
t
o
f
C
o
m
put
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
ne
e
r
i
n
g
S
c
h
o
o
l
o
f
E
n
g
i
ne
e
r
i
n
g
a
n
d
T
e
c
hn
o
l
o
g
y
C
HR
I
S
T
(
De
e
m
e
d
to
b
e
Uni
ve
r
s
i
t
y
)
B
a
n
ga
l
o
r
e
,
I
n
d
i
a
E
m
a
i
l
:
bi
ne
e
s
h
.
m
@
r
e
s
.
c
h
r
i
s
t
uni
ve
r
s
i
t
y
.
i
n
1.
I
NT
RODU
C
T
I
ON
L
u
n
g
c
a
n
c
e
r
i
s
a
s
e
r
i
o
us
d
i
s
e
a
s
e
t
h
a
t
i
m
po
s
e
s
s
i
g
nif
i
c
a
n
t
f
i
na
nc
i
a
l
b
ur
de
ns
o
n
b
o
t
h
t
h
e
he
a
l
t
h
c
a
r
e
s
y
s
t
e
m
a
n
d
pa
t
i
e
n
t
s
g
l
o
b
a
ll
y
.
I
t
s
pr
e
v
a
l
e
nc
e
a
n
d
im
pa
c
t
o
n
publi
c
h
e
a
l
t
h
a
r
e
e
vi
de
n
t
,
a
s
i
t
r
a
n
ks
a
m
o
n
g
t
h
e
m
o
s
t
c
o
m
m
o
n
a
n
d
de
a
d
ly
m
a
l
i
g
na
n
c
i
e
s
wo
r
l
dw
i
d
e
.
T
h
e
a
l
a
r
m
i
ng
i
nc
r
e
a
s
e
i
n
l
u
n
g
c
a
n
c
e
r
c
a
s
e
s
u
n
d
e
r
s
c
o
r
e
s
t
h
e
i
m
po
r
t
a
n
c
e
o
f
e
f
f
e
c
t
i
ve
pr
e
v
e
n
t
i
o
n
,
e
a
r
l
y
de
t
e
c
t
i
o
n
,
a
n
d
c
utt
i
n
g
-
e
dge
t
r
e
a
t
m
e
n
t
t
e
c
hni
que
s
.
E
a
r
ly
i
de
n
t
i
f
i
c
a
t
i
o
n
i
s
c
r
uc
i
a
l
f
o
r
e
s
t
a
bl
i
s
hi
ng
a
pa
t
i
e
n
t
's
pr
o
gn
o
s
i
s
a
n
d
pot
e
n
t
i
a
l
o
ut
c
o
m
e
s
,
pa
r
t
i
c
u
l
a
r
ly
b
e
c
a
us
e
l
u
n
g
c
a
n
c
e
r
o
f
t
e
n
e
xhi
b
i
t
s
m
il
d
o
r
n
o
n
e
xi
s
t
e
n
t
s
y
m
pt
o
m
s
i
n
i
t
s
e
a
r
ly
s
t
a
ge
s
[
1]
.
T
i
m
e
ly
a
n
d
a
c
c
ur
a
t
e
l
u
n
g
c
a
nc
e
r
pr
e
d
i
c
t
i
o
n
p
l
a
y
s
a
p
i
v
o
t
a
l
r
o
l
e
i
n
i
de
n
t
i
f
yi
n
g
i
n
d
i
v
i
dua
l
s
a
t
hi
g
h
r
i
s
k
a
n
d
f
a
c
il
i
t
a
t
i
n
g
t
h
e
de
ve
l
o
p
m
e
n
t
o
f
i
n
d
i
v
i
dua
li
z
e
d
t
r
e
a
t
m
e
n
t
p
r
o
g
r
a
m
s
,
t
h
e
r
e
by
e
nh
a
n
c
i
ng
pa
t
i
e
n
t
qua
l
i
t
y
o
f
li
f
e
a
n
d
s
ur
vi
va
l
r
a
t
e
s
.
T
h
e
ut
i
li
z
a
t
i
o
n
o
f
m
o
de
r
n
t
e
c
hn
o
l
o
g
i
e
s
f
o
r
c
a
n
c
e
r
pr
e
d
i
c
t
i
o
n
,
i
n
c
l
ud
i
ng
c
o
m
put
a
t
i
o
n
a
l
m
e
t
h
o
ds
a
n
d
t
h
e
a
bun
da
n
c
e
o
f
bi
o
m
e
d
i
c
a
l
da
t
a
,
h
a
s
ga
i
n
e
d
m
o
m
e
n
t
u
m
[
2]
.
I
n
th
e
do
m
a
i
n
o
f
c
a
nc
e
r
pr
e
d
i
c
t
i
o
n
,
gr
a
ph
-
ba
s
e
d
de
e
p
l
e
a
r
ni
ng
t
e
c
h
ni
que
s
h
a
v
e
e
m
e
r
ge
d
a
s
pr
o
m
i
s
i
ng
t
oo
l
s
f
o
r
pr
o
c
e
s
s
i
n
g
c
o
m
p
l
e
x
bi
o
l
o
g
i
c
a
l
da
t
a
,
s
uc
h
a
s
ge
n
o
m
i
c
s
,
pr
ot
e
o
m
i
c
s
,
a
n
d
m
e
t
a
b
o
l
o
m
i
c
s
[
3]
.
T
h
e
s
e
t
e
c
hniques
e
n
a
bl
e
t
h
e
m
o
de
l
i
ng
o
f
i
n
t
r
i
c
a
t
e
de
pe
n
de
nc
i
e
s
a
n
d
i
n
t
e
r
a
c
t
i
o
n
s
i
nhe
r
e
n
t
i
n
bi
o
l
o
g
i
c
a
l
s
y
s
t
e
m
s
,
whi
c
h
o
f
t
e
n
e
xhi
b
i
t
a
gr
a
ph
-
l
i
ke
n
a
t
ur
a
l
s
t
r
uc
t
ur
e
[
4]
.
I
n
o
r
de
r
to
im
pr
o
v
e
t
h
e
pr
e
c
i
s
i
o
n
a
n
d
e
f
f
i
c
a
c
y
o
f
pr
e
d
i
c
t
i
ve
m
o
de
l
s
,
t
hi
s
r
e
s
e
a
r
c
h
t
a
r
ge
t
s
pr
e
di
c
t
i
n
g
l
u
n
g
c
a
n
c
e
r
us
i
n
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2
5
0
2
-
4
7
52
In
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
,
Vo
l
.
3
7
,
N
o
.
2
,
F
e
b
r
ua
r
y
20
2
5
:
1
07
7
-
1
08
4
1078
gr
a
ph
-
ba
s
e
d
de
e
p
l
e
a
r
ni
ng
t
e
c
hni
que
s
[
5]
,
s
pe
c
i
f
i
c
a
l
ly
s
e
e
k
i
n
g
t
o
de
v
e
l
o
p
a
r
o
b
us
t
pr
e
di
c
t
i
v
e
m
o
de
l
c
a
pa
bl
e
o
f
c
a
pt
ur
i
n
g
hi
dde
n
l
i
nk
a
ge
s
w
i
t
hi
n
t
h
e
da
t
a
us
i
n
g
t
h
e
pot
e
n
t
i
a
l
o
f
gr
a
ph
ne
ur
a
l
n
e
t
wo
r
ks
,
n
ot
a
bl
y
a
dv
a
n
c
e
d
-
gr
a
ph
c
o
nv
o
l
ut
i
o
n
n
e
t
wor
ks
(
a
dv
a
n
c
e
d
-
GC
N)
w
i
t
h
gr
a
p
h
a
t
t
e
n
t
i
o
n
n
e
t
wo
r
ks
(
GA
T
)
[
6
]
.
T
h
e
c
o
m
bin
a
t
i
o
n
o
f
t
h
e
s
e
t
e
c
hni
qu
e
s
a
im
s
t
o
e
n
ha
n
c
e
t
h
e
m
o
de
l
's
c
a
pa
c
i
t
y
f
o
r
pr
e
di
c
t
i
o
n
,
whi
c
h
c
o
u
l
d
r
e
v
o
l
ut
i
o
ni
z
e
t
h
e
a
bil
i
t
y
t
o
f
o
r
e
c
a
s
t
e
a
r
l
y
l
u
n
g
c
a
n
c
e
r
a
n
d,
a
s
a
r
e
s
u
l
t
,
h
a
ve
a
p
o
s
i
t
i
v
e
e
f
f
e
c
t
o
n
pa
t
i
e
n
t
o
u
t
c
o
m
e
s
.
I
n
t
hi
s
a
r
t
i
c
l
e
,
i
t
gi
v
e
s
a
c
o
m
pr
e
h
e
ns
i
ve
a
n
a
ly
s
i
s
o
f
t
h
e
pr
o
p
o
s
e
d
m
e
t
h
o
do
l
o
g
y
a
n
d
e
x
pe
r
i
m
e
n
t
a
l
f
i
nd
i
ng
s
,
s
h
e
dd
i
ng
l
i
g
h
t
o
n
t
h
e
pot
e
n
t
i
a
l
a
d
v
a
n
c
e
m
e
n
t
s
i
n
l
u
n
g
c
a
n
c
e
r
pr
e
d
i
c
t
i
o
n
e
n
a
bl
e
d
by
i
nn
o
v
a
t
i
v
e
gr
a
p
h
-
ba
s
e
d
de
e
p
l
e
a
r
ni
ng
a
l
go
r
i
t
hm
s
[
7]
.
D
ue
to
th
e
o
n
g
o
i
n
g
di
f
f
i
c
u
l
t
y
i
n
p
r
e
d
i
c
t
i
n
g
,
di
a
gn
o
s
i
n
g
,
a
n
d
tr
e
a
t
i
n
g
l
un
g
c
a
n
c
e
r
,
t
h
e
r
e
h
a
s
b
e
e
n
e
x
ten
s
i
v
e
r
e
s
e
a
r
c
h
a
n
d
t
h
e
us
e
o
f
v
a
r
i
o
us
c
o
m
pu
tat
i
o
n
a
l
te
c
h
ni
que
s
[
7
]
.
H
e
r
e
,
i
t
g
i
v
e
s
a
n
i
n
-
de
p
t
h
a
n
a
l
y
s
i
s
o
f
r
e
l
a
t
e
d
r
e
s
e
a
r
c
h
i
n
l
un
g
c
a
n
c
e
r
p
r
e
di
c
t
i
o
n
,
hi
ghl
i
g
h
t
i
n
g
v
a
r
i
ous
c
o
m
pu
ta
t
i
o
n
a
l
a
p
p
r
oa
c
h
e
s
th
a
t
h
a
v
e
b
e
e
n
us
e
d
to
i
m
pr
o
v
e
p
r
e
di
c
t
i
o
n
p
r
e
c
i
s
i
o
n
a
n
d
e
a
r
l
y
di
a
gn
o
s
i
s
[
8]
.
A
f
un
da
m
e
n
t
a
l
r
o
l
e
i
n
p
r
e
di
c
t
i
n
g
l
un
g
c
a
n
c
e
r
i
s
pl
a
y
e
d
by
s
i
m
p
l
e
m
a
c
hi
n
e
l
e
a
r
ni
n
g
tec
h
ni
que
s
,
whi
c
h
p
r
o
vi
de
e
f
f
i
c
i
e
n
t
too
l
s
f
or
da
ta
a
n
a
l
y
s
i
s
a
n
d
de
c
i
s
i
o
n
-
m
a
ki
n
g
[
9
]
.
P
r
e
di
c
t
i
v
e
m
ode
l
s
a
r
e
tr
a
i
n
e
d
us
i
n
g
s
up
e
r
v
i
s
e
d
l
e
a
r
ni
n
g
a
l
g
or
i
t
hm
s
,
a
f
un
da
m
e
n
ta
l
m
e
t
h
o
d
[
10
]
.
I
n
or
d
e
r
to
c
a
teg
or
i
z
e
l
un
g
c
a
n
c
e
r
t
y
pe
s
or
f
or
e
c
a
s
t
di
s
e
a
s
e
p
r
og
r
e
s
s
i
o
n
,
m
e
t
h
ods
l
i
ke
s
up
p
or
t
v
e
c
tor
m
a
c
hi
n
e
s
(
S
VM
)
a
n
d
r
a
n
d
o
m
f
or
e
s
ts
a
r
e
f
r
e
q
ue
n
t
l
y
us
e
d
[
11
]
.
T
h
e
s
e
m
e
t
h
o
ds
us
e
i
nf
or
m
a
t
i
o
n
d
e
r
i
v
e
d
f
r
o
m
m
e
d
i
c
a
l
i
m
a
g
i
n
g
or
g
e
n
o
m
i
c
da
ta
[
12
]
.
C
l
us
t
e
r
i
n
g
m
e
t
h
ods
l
i
ke
K
-
m
e
a
n
s
a
r
e
us
e
d
f
or
pa
t
i
e
n
t
c
a
te
g
or
i
z
a
t
i
o
n
i
n
un
s
u
pe
r
vi
s
e
d
l
e
a
r
ni
n
g,
wh
i
c
h
e
m
p
l
o
y
s
unl
a
b
e
l
e
d
d
a
ta
[
13
]
.
R
e
c
u
r
s
i
v
e
f
e
a
tur
e
e
l
i
m
i
n
a
t
i
o
n
i
s
o
n
e
o
f
t
h
e
f
e
a
tu
r
e
s
e
l
e
c
t
i
o
n
te
c
h
ni
que
s
t
h
a
t
h
e
l
ps
f
i
n
d
ke
y
p
r
e
di
c
tor
s
a
n
d
e
n
ha
n
c
e
m
o
de
l
p
e
r
f
or
m
a
n
c
e
[
1
4
]
.
T
h
e
s
e
f
un
da
m
e
n
ta
l
m
e
t
h
ods
o
f
f
e
r
a
vi
t
a
l
f
r
a
m
e
w
or
k
f
or
c
r
e
a
t
i
n
g
f
or
e
c
a
s
t
i
n
g
m
ode
l
s
a
n
d
d
r
a
w
i
n
g
vi
t
a
l
c
o
n
c
l
us
i
o
n
s
f
r
o
m
da
ta
on
l
un
g
c
a
n
c
e
r
[
15
]
.
E
n
h
a
n
c
i
n
g
p
r
e
di
c
t
i
o
n
a
c
c
u
r
a
c
y
t
h
r
ough
i
n
t
e
gr
a
t
i
o
n
wi
t
h
c
u
tt
i
n
g
-
e
dge
a
l
g
or
i
t
hm
s
a
n
d
m
u
l
t
i
-
m
oda
l
d
a
ta
i
s
a
p
r
o
m
i
s
i
n
g
wa
y
to
i
m
pr
o
v
e
l
un
g
c
a
n
c
e
r
p
r
o
gn
os
i
s
a
n
d
tr
e
a
t
m
e
n
t
p
l
a
n
ni
n
g
[
16
]
.
T
h
e
a
i
m
o
f
t
hi
s
r
e
s
e
a
r
c
h
[
17]
i
s
to
i
de
n
t
i
f
y
p
l
a
s
m
a
m
e
t
a
b
o
l
i
t
e
s
a
s
p
o
s
s
i
bl
e
l
u
n
g
c
a
n
c
e
r
di
a
g
n
o
s
t
i
c
bi
o
m
a
r
ke
r
s
,
e
s
pe
c
i
a
ll
y
i
n
t
h
e
C
hi
ne
s
e
po
pu
l
a
t
i
o
n
.
T
h
e
a
ut
h
o
r
s
e
x
a
mi
ne
d
a
da
t
a
s
e
t
t
h
a
t
i
nc
l
ude
d
11
0
pe
o
pl
e
w
i
t
h
l
u
n
g
c
a
nc
e
r
a
n
d
43
h
e
a
l
t
hy
pe
o
p
l
e
us
i
ng
a
c
u
tt
i
n
g
-
e
dge
m
u
l
t
i
d
i
s
c
i
p
li
na
r
y
s
t
r
a
t
e
gy
t
h
a
t
c
o
m
bi
ne
s
m
e
t
a
b
o
l
o
m
i
c
s
a
n
d
m
a
c
hi
ne
l
e
a
r
ni
n
g.
61
pl
a
s
m
a
m
e
t
a
b
o
l
i
t
e
s
we
r
e
f
o
un
d
by
t
h
e
a
ut
h
o
r
s
us
i
n
g
f
o
c
us
e
d
m
e
t
a
b
o
l
o
m
i
c
s
a
n
a
ly
s
i
s
[
18]
.
T
h
e
t
h
r
e
a
t
p
o
s
e
d
by
l
u
n
g
c
a
n
c
e
r
to
t
h
e
w
o
r
l
d
'
s
h
e
a
l
t
h
i
s
s
i
g
ni
f
i
c
a
n
t
,
c
a
ll
i
ng
f
o
r
s
pe
c
i
a
li
z
e
d
a
ppr
o
a
c
h
e
s
f
o
r
e
a
r
l
y
i
d
e
n
t
i
f
i
c
a
t
i
o
n
a
nd
e
f
f
i
c
i
e
n
t
t
r
e
a
t
m
e
n
t
[
19]
.
A
c
r
uc
i
a
l
s
t
r
a
t
e
gy
i
n
t
hi
s
e
f
f
o
r
t
h
a
s
a
r
i
s
e
n
i
n
r
e
c
e
n
t
y
e
a
r
s
w
i
t
h
t
h
e
i
n
t
e
gr
a
t
i
o
n
o
f
ge
n
o
m
e
s
a
n
d
m
o
l
e
c
u
l
a
r
da
t
a
[
20]
.
Un
de
r
s
t
a
n
d
in
g
l
u
n
g
c
a
nc
e
r
a
t
b
ot
h
t
h
e
ge
n
e
t
i
c
a
n
d
m
o
l
e
c
u
l
a
r
l
e
v
e
l
s
ha
s
b
e
e
n
c
o
m
p
l
e
t
e
l
y
t
r
a
n
s
f
o
r
m
e
d
by
g
e
n
o
m
i
c
s
[
21]
,
whi
c
h
i
s
t
h
e
s
t
udy
o
f
a
n
o
r
ga
ni
s
m
's
ge
n
e
s
a
n
d
t
h
e
i
r
a
c
t
i
vi
t
i
e
s
,
a
n
d
m
o
l
e
c
u
l
a
r
da
t
a
,
whi
c
h
c
o
n
t
a
i
ns
c
o
m
p
l
e
x
i
nf
o
r
m
a
t
i
o
n
a
b
o
ut
m
o
l
e
c
u
l
a
r
i
n
t
e
r
a
c
t
i
o
ns
[
22]
.
T
h
i
s
pa
r
a
d
i
g
m
s
hi
f
t
h
a
s
m
a
de
i
t
po
s
s
i
bl
e
to
i
de
n
t
i
f
y
ge
n
e
t
i
c
c
h
a
n
ge
s
,
bi
o
m
a
r
ke
r
s
,
a
n
d
m
o
l
e
c
u
l
a
r
pa
t
h
wa
y
s
t
h
a
t
a
r
e
c
l
o
s
e
ly
c
o
nn
e
c
t
e
d
to
t
h
e
o
n
s
e
t
,
pr
o
g
r
e
s
s
i
o
n
,
a
n
d
r
e
s
po
n
s
e
to
t
r
e
a
t
m
e
n
t
o
f
l
u
n
g
c
a
nc
e
r
[
23]
.
U
t
i
li
z
i
ng
ge
n
e
t
i
c
a
n
d
m
o
l
e
c
u
l
a
r
da
t
a
m
a
ke
s
i
t
e
a
s
i
e
r
t
o
c
r
e
a
t
e
p
r
e
d
i
c
t
i
v
e
m
o
de
l
s
,
e
n
a
bli
ng
l
u
n
g
c
a
n
c
e
r
e
a
r
l
y
de
t
e
c
t
i
o
n
a
n
d
a
c
c
ur
a
t
e
pr
o
gn
o
s
t
i
c
a
t
i
o
n
[
24]
.
B
y
e
n
a
bli
ng
pr
o
m
pt
i
n
t
e
r
v
e
n
t
i
o
n
s
a
n
d
o
p
t
i
mi
z
i
ng
t
r
e
a
t
m
e
n
t
pl
a
n
s
,
t
h
e
s
e
m
o
de
l
s
h
a
v
e
a
t
r
e
m
e
n
do
us
pot
e
n
t
i
a
l
to
i
m
pr
o
v
e
pa
t
i
e
n
t
o
u
t
c
o
m
e
s
a
n
d,
u
l
t
i
m
a
t
e
l
y
,
s
ur
vi
va
l
r
a
t
e
s
.
T
h
e
r
e
s
e
a
r
c
h
c
o
n
duc
t
s
a
c
r
i
t
i
c
a
l
a
n
a
ly
s
i
s
o
f
l
u
n
g
c
a
n
c
e
r
,
a
wi
d
e
s
p
r
e
a
d
di
s
e
a
s
e
wi
th
s
i
gn
i
f
i
c
a
n
t
c
l
i
ni
c
a
l
,
h
i
s
to
l
ogi
c
a
l
,
a
n
d
m
o
l
e
c
ul
a
r
v
a
r
i
a
t
i
on
a
n
d
h
i
gh
m
or
ta
l
i
t
y
r
a
te
s
[
2
5
]
.
T
h
e
d
i
v
e
r
s
i
t
y
i
n
l
u
n
g
c
a
nc
e
r
un
de
r
s
c
o
r
e
s
t
h
e
n
e
e
d
f
o
r
pe
r
s
o
n
a
l
i
z
e
d
t
r
e
a
t
m
e
n
t
p
l
a
n
s
.
De
e
p
l
e
a
r
ni
ng
a
lgo
r
i
t
hm
s
h
a
v
e
r
e
v
o
l
ut
i
o
ni
z
e
d
l
u
n
g
c
a
n
c
e
r
pr
e
d
i
c
t
i
o
n
by
d
e
t
e
c
t
i
n
g
de
e
p
pa
tt
e
r
n
s
a
n
d
c
o
nn
e
c
t
i
o
n
s
i
n
v
a
s
t
,
c
o
m
p
l
e
x
da
t
a
s
e
t
s
,
pa
r
t
i
c
u
l
a
r
ly
i
n
ge
ne
t
i
c
s
a
n
d
m
e
d
i
c
a
l
im
a
g
i
ng.
T
h
e
y
e
x
c
e
l
a
t
e
x
t
r
a
c
t
i
n
g
c
r
i
t
i
c
a
l
i
nf
o
r
m
a
t
i
o
n
f
r
o
m
C
T
s
c
a
n
s
a
n
d
X
-
r
a
y
s
,
a
i
d
i
n
g
i
n
e
a
r
ly
de
t
e
c
t
i
o
n
a
n
d
d
i
a
gn
o
s
i
s
by
i
d
e
n
t
i
f
yi
ng
s
u
b
t
l
e
a
bn
o
r
m
a
li
t
i
e
s
o
f
t
e
n
m
i
s
s
e
d
b
y
t
h
e
h
u
m
a
n
e
y
e
.
A
dd
i
t
i
o
na
l
ly
,
de
e
p
l
e
a
r
ni
ng
m
o
de
l
s
i
n
t
e
gr
a
t
e
m
u
l
t
i
-
o
m
i
c
s
da
t
a
,
s
uc
h
a
s
pr
o
t
e
omi
c
s
a
n
d
ge
n
o
m
i
c
s
,
pr
o
v
i
d
i
ng
a
c
o
m
pr
e
h
e
ns
i
ve
un
d
e
r
s
t
a
n
d
in
g
o
f
t
h
e
m
o
l
e
c
u
l
a
r
c
a
us
e
s
o
f
l
u
n
g
c
a
n
c
e
r
,
whi
c
h
i
s
c
r
uc
i
a
l
f
o
r
t
a
i
l
o
r
i
n
g
t
r
e
a
t
m
e
n
t
pl
a
ns
a
n
d
i
m
pr
o
vi
ng
o
u
t
c
o
m
e
s
.
T
h
e
r
e
s
e
a
r
c
h
de
l
v
e
s
i
n
t
o
ge
n
e
-
e
nvir
o
nm
e
n
t
i
n
t
e
r
a
c
t
i
o
n
s
a
f
f
e
c
t
i
n
g
c
e
ll
u
l
a
r
h
o
m
e
o
s
t
a
s
i
s
a
n
d
c
a
n
c
e
r
de
v
e
l
o
p
m
e
n
t
,
hi
g
hli
g
h
t
i
n
g
t
h
e
po
t
e
n
t
i
a
l
o
f
bio
m
a
r
ke
r
s
a
s
e
a
r
l
y
i
nd
i
c
a
to
r
s
o
f
d
i
s
e
a
s
e
pr
o
gr
e
s
s
i
o
n
.
T
h
e
a
dv
e
n
t
o
f
hi
g
h
-
t
h
r
o
ugh
put
pr
o
f
i
li
ng
m
e
t
h
o
ds
,
l
i
ke
m
a
s
s
s
pe
c
t
r
o
m
e
t
r
y
a
n
d
R
N
A
s
e
qu
e
n
c
i
ng,
h
a
s
f
a
c
il
i
t
a
t
e
d
da
t
a
-
dr
i
ve
n
bi
o
m
a
r
ke
r
d
i
s
c
o
v
e
r
y
.
W
hil
e
t
r
a
d
i
t
i
o
n
a
l
s
t
a
t
i
s
t
i
c
a
l
m
e
t
h
o
ds
h
a
v
e
l
im
i
t
a
t
i
o
n
s
,
t
h
e
c
o
m
bi
na
t
i
o
n
o
f
m
a
c
hi
ne
l
e
a
r
ni
ng
(
M
L
)
a
n
d
de
e
p
l
e
a
r
ni
ng
(
DL
)
o
f
f
e
r
s
a
po
we
r
f
u
l
a
ppr
o
a
c
h
i
n
d
i
s
e
a
s
e
r
e
s
e
a
r
c
h
.
B
y
i
n
t
e
gr
a
t
i
n
g
M
L
/D
L
t
e
c
h
ni
que
s
a
n
d
o
pt
i
m
i
z
i
ng
t
h
e
m
a
c
r
o
s
s
m
u
l
t
i
-
o
m
i
c
s
da
t
a
s
e
t
s
,
r
o
b
us
t
pr
e
di
c
t
i
o
n
m
o
de
l
s
e
s
s
e
n
t
i
a
l
f
o
r
pr
e
c
i
s
i
o
n
m
e
d
i
c
i
ne
a
r
e
de
v
e
l
o
p
e
d.
T
h
e
pa
pe
r
e
x
p
l
a
i
ns
r
e
c
e
n
t
de
v
e
l
o
p
m
e
n
t
s
i
n
M
L
/D
L
m
e
t
h
o
ds
,
e
s
pe
c
i
a
ll
y
i
n
t
h
e
i
de
n
t
i
f
i
c
a
t
i
o
n
o
f
c
a
nc
e
r
-
r
e
l
a
t
e
d
bi
o
m
a
r
ke
r
s
a
n
d
t
h
e
i
r
us
e
i
n
pr
e
c
i
s
i
o
n
m
e
d
i
c
i
ne
.
T
h
e
p
o
t
e
n
t
i
a
l
f
o
r
i
n
d
i
v
i
dua
li
z
e
d
pa
t
i
e
n
t
tr
e
a
t
m
e
n
t
pl
a
n
s
ba
s
e
d
o
n
m
e
d
i
c
a
l
hi
s
t
o
r
i
e
s
a
n
d
d
i
a
g
n
o
s
t
i
c
s
h
a
s
b
e
e
n
s
ho
wn
by
t
h
e
w
i
de
r
a
n
ge
o
f
a
pp
l
i
c
a
t
i
o
ns
o
f
DL
t
e
c
hni
que
s
,
pa
r
t
i
c
u
l
a
r
l
y
i
n
t
h
e
d
i
a
g
n
o
s
i
s
a
n
d
t
r
e
a
t
m
e
n
t
o
f
c
a
nc
e
r
.
I
n
o
r
de
r
to
c
a
r
r
y
o
ut
pr
e
c
i
s
e
t
h
e
r
a
pe
ut
i
c
i
n
t
e
r
v
e
n
t
i
o
ns
f
o
r
c
a
n
c
e
r
,
t
h
e
r
e
vi
e
w
hi
g
hli
g
h
t
s
t
h
e
c
r
i
t
i
c
a
l
ne
e
d
f
o
r
DL
-
b
a
s
e
d
m
u
l
t
im
o
da
l
e
ns
e
m
b
l
e
t
e
c
hni
q
ue
s
t
h
a
t
i
n
t
e
gr
a
t
e
ge
n
e
-
pr
ot
e
i
n
-
m
e
t
a
b
o
l
i
t
e
i
n
t
e
r
a
c
t
i
o
ns
.
How
e
v
e
r
,
t
h
e
r
e
a
r
e
c
e
r
t
a
i
n
dr
a
wb
a
c
ks
to
DL
m
o
de
l
s
,
s
uc
h
a
s
s
m
a
l
l
s
a
m
p
l
e
s
i
z
e
s
,
d
i
f
f
i
c
u
l
t
i
e
s
w
i
t
h
i
n
t
e
r
pr
e
t
a
bil
i
t
y
,
t
h
e
de
m
a
n
d
f
o
r
p
r
o
c
e
s
s
i
ng
r
e
s
o
ur
c
e
s
,
a
n
d
t
h
e
r
e
qu
i
r
e
m
e
n
t
f
o
r
e
x
pe
r
t
kn
o
wl
e
dg
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
I
S
S
N:
2
5
0
2
-
4
7
52
L
ung
c
anc
e
r
pr
e
diction
w
it
h
adv
anc
e
d
gr
aph
ne
ur
al
ne
t
w
or
k
s
(
B
inee
s
h
M
ooz
hippur
ath
)
1079
Gr
a
ph
n
e
ur
a
l
n
e
t
wo
r
ks
(
GN
Ns
)
h
a
v
e
e
m
e
r
ge
d
a
s
a
pr
o
m
i
s
i
ng
a
ppr
o
a
c
h
f
o
r
pr
e
di
c
t
i
n
g
l
u
n
g
c
a
n
c
e
r
by
c
a
pt
ur
i
n
g
c
o
m
p
l
e
x
r
e
l
a
t
i
o
n
s
hi
p
s
w
i
t
hi
n
bi
o
l
o
g
i
c
a
l
s
y
s
t
e
m
s
.
R
e
pr
e
s
e
n
t
i
n
g
m
o
l
e
c
u
l
a
r
a
n
d
ge
n
e
t
i
c
da
t
a
a
s
gr
a
ph
s
—
w
he
r
e
n
o
de
s
a
r
e
bi
o
l
o
g
i
c
a
l
e
n
t
i
t
i
e
s
l
i
k
e
ge
n
e
s
o
r
p
r
ot
e
i
ns
,
a
n
d
e
dge
s
r
e
pr
e
s
e
n
t
t
h
e
i
r
i
n
t
e
r
a
c
t
i
o
n
s
—
GN
Ns
e
x
c
e
l
i
n
m
o
de
li
ng
t
h
e
i
n
t
r
i
c
a
t
e
m
o
l
e
c
u
l
a
r
ne
t
w
o
r
ks
a
n
d
pa
t
h
wa
y
s
c
r
i
t
i
c
a
l
t
o
l
u
n
g
c
a
nc
e
r
pr
o
g
r
e
s
s
i
o
n
.
T
h
e
y
c
a
n
i
d
e
n
t
i
f
y
ke
y
ge
n
e
s
o
r
p
r
ot
e
i
ns
a
s
s
o
c
i
a
t
e
d
w
i
t
h
l
u
n
g
c
a
n
c
e
r
,
pr
e
di
c
t
c
a
nc
e
r
c
e
l
l
b
e
h
a
vi
o
r
,
a
n
d
s
ugge
s
t
pot
e
n
t
i
a
l
t
r
e
a
t
m
e
n
t
t
a
r
ge
t
s
.
T
h
e
i
n
t
e
gr
a
t
i
o
n
o
f
m
u
l
t
i
-
o
m
i
c
s
da
t
a
,
e
n
c
o
m
pa
s
s
i
ng
ge
n
o
m
i
c
,
e
p
i
ge
n
e
t
i
c
,
a
n
d
pr
ot
e
o
m
i
c
i
nf
o
r
m
a
t
i
o
n
,
f
ur
t
h
e
r
e
nh
a
n
c
e
s
pr
e
d
i
c
t
i
o
n
a
c
c
ur
a
c
y
.
T
hi
s
s
t
udy
a
l
s
o
l
e
v
e
r
a
ge
s
m
e
d
i
c
a
l
im
a
ge
pr
o
c
e
s
s
i
n
g
t
e
c
hni
que
s
t
o
e
x
a
m
i
ne
i
n
t
e
r
n
a
l
a
n
a
t
omy
n
o
n
-
i
nv
a
s
i
ve
ly
,
a
i
d
i
ng
i
n
m
o
r
e
pr
e
c
i
s
e
d
i
a
g
no
s
e
s
a
n
d
b
e
t
t
e
r
t
r
e
a
t
m
e
n
t
pl
a
nni
ng.
S
pe
c
i
f
i
c
a
ll
y
,
t
h
e
r
e
s
e
a
r
c
h
f
o
c
us
e
s
o
n
l
u
n
g
t
um
o
r
pr
e
di
c
t
i
o
n
us
i
n
g
a
hy
b
r
i
d
e
v
o
l
ut
i
o
n
a
r
y
a
ppr
o
a
c
h
t
h
a
t
c
o
m
bi
ne
s
b
a
c
t
e
r
i
a
l
f
o
r
a
g
i
n
g
o
pt
i
mi
z
a
t
i
o
n
w
i
t
h
wha
l
e
o
p
t
i
mi
z
a
t
i
o
n
.
B
y
pr
e
pr
o
c
e
s
s
i
ng
a
n
d
s
e
g
m
e
n
t
i
n
g
150
C
T
i
m
a
ge
s
,
t
h
e
n
o
v
e
l
W
h
a
l
e
-
B
a
c
t
e
r
i
a
l
f
o
r
a
g
i
ng
o
p
t
i
mi
z
a
t
i
o
n
t
e
c
hni
que
i
s
a
pp
l
i
e
d
t
o
e
x
t
r
a
c
t
o
p
t
i
m
a
l
f
e
a
t
ur
e
s
,
de
m
o
ns
t
r
a
t
i
n
g
s
upe
r
i
o
r
pe
r
f
o
r
m
a
n
c
e
i
n
d
i
s
t
i
n
gu
i
s
hi
ng
b
e
t
we
e
n
c
a
n
c
e
r
o
us
a
n
d
n
o
n
-
c
a
n
c
e
r
o
us
n
o
du
l
e
s
c
o
m
pa
r
e
d
to
tr
a
di
t
i
o
n
a
l
m
e
t
h
o
ds
.
T
h
e
o
u
t
l
i
ne
o
f
t
h
e
pr
o
p
o
s
e
d
r
e
s
e
a
r
c
h
e
n
t
a
i
l
s
t
h
e
i
n
t
e
gr
a
t
i
o
n
o
f
gr
a
p
h
n
e
ur
a
l
n
e
t
wo
r
ks
(
GN
Ns
)
to
e
nh
a
nc
e
pr
e
c
i
s
i
o
n
a
n
d
e
a
r
l
y
d
i
a
g
n
o
s
i
s
i
n
l
u
n
g
c
a
n
c
e
r
pr
e
di
c
t
i
o
n
a
n
d
tr
e
a
t
m
e
n
t
.
T
hi
s
a
ppr
o
a
c
h
un
de
r
s
c
o
r
e
s
t
h
e
s
i
g
nif
i
c
a
n
c
e
o
f
pr
o
a
c
t
i
ve
pa
t
i
e
n
t
c
a
r
e
a
n
d
pe
r
s
o
n
a
li
z
e
d
t
r
e
a
t
m
e
n
t
pl
a
ns
i
n
im
pr
o
vi
ng
o
u
t
c
o
m
e
s
a
n
d
s
ur
vi
va
l
r
a
t
e
s
.
T
h
e
i
ni
t
i
a
l
hy
po
t
h
e
s
i
s
po
s
t
ul
a
t
e
s
t
h
a
t
by
i
n
t
e
gr
a
t
i
n
g
GN
Ns
,
pa
r
t
i
c
u
l
a
r
ly
t
h
e
A
-
GC
N
w
i
t
h
th
e
G
A
T
m
o
de
l
t
a
i
l
o
r
e
d
f
o
r
l
u
n
g
c
a
n
c
e
r
pr
e
d
i
c
t
i
o
n
,
i
n
c
r
e
a
s
e
d
a
c
c
ur
a
c
y
a
n
d
e
f
f
i
c
a
c
y
c
a
n
b
e
a
c
hi
e
v
e
d,
u
l
t
i
m
a
t
e
ly
l
e
a
d
i
ng
t
o
e
n
h
a
nc
e
d
pa
t
i
e
n
t
o
u
t
c
o
m
e
s
a
n
d
pr
o
a
c
t
i
ve
h
e
a
l
t
h
c
a
r
e
i
n
t
e
r
v
e
n
t
i
o
ns
.
2.
M
E
T
HO
D
T
h
e
l
u
n
g
c
a
n
c
e
r
pr
e
d
i
c
t
i
o
n
da
t
a
s
e
t
,
s
o
ur
c
e
d
f
r
om
K
a
gg
l
e
's
"
L
u
n
g
C
a
n
c
e
r
P
r
e
d
i
c
t
i
o
n
Da
t
a
s
e
t
,
"
c
o
m
pr
i
s
e
s
309
i
ns
t
a
n
c
e
s
w
i
t
h
16
a
tt
r
i
b
ut
e
s
,
i
n
c
l
ud
i
ng
de
m
o
gr
a
phi
c
a
n
d
l
if
e
s
t
y
l
e
f
a
c
t
or
s
s
uc
h
a
s
ge
nde
r
,
a
ge
,
s
m
o
k
i
n
g
h
a
bi
t
s
,
a
l
c
o
h
o
l
c
o
n
s
u
m
pt
i
o
n
,
a
n
d
pe
e
r
pr
e
s
s
ur
e
.
Da
t
a
pr
e
p
r
o
c
e
s
s
i
ng
i
s
a
c
r
i
t
i
c
a
l
s
t
e
p
a
im
e
d
a
t
e
nh
a
nc
i
n
g
t
h
e
s
u
i
t
a
bil
i
t
y
o
f
t
h
e
da
t
a
s
e
t
f
o
r
m
a
c
hi
n
e
l
e
a
r
ni
ng
a
l
go
r
i
t
hm
s
.
Dupl
i
c
a
t
e
e
n
t
r
i
e
s
we
r
e
i
de
n
t
if
i
e
d
a
n
d
r
e
m
o
v
e
d
to
m
a
i
n
t
a
i
n
da
t
a
i
n
t
e
gr
i
t
y
,
a
n
d
l
a
b
e
l
e
n
c
o
di
n
g
wa
s
a
pp
li
e
d
to
c
a
t
e
g
o
r
i
c
a
l
f
e
a
t
ur
e
s
l
i
ke
"
G
E
ND
E
R
"
us
i
n
g
s
c
i
k
i
t
-
l
e
a
r
n'
s
L
a
b
e
l
E
n
c
o
d
e
r
.
T
o
a
ddr
e
s
s
c
l
a
s
s
i
m
ba
l
a
n
c
e
,
R
a
n
do
m
O
ve
r
S
a
m
p
l
e
r
f
r
o
m
i
m
ba
l
a
nc
e
d
-
l
e
a
r
n
wa
s
ut
i
l
i
z
e
d
to
e
n
s
ur
e
a
b
a
l
a
n
c
e
d
t
r
a
i
ni
ng
s
e
t
.
T
o
h
a
r
n
e
s
s
t
h
e
r
e
l
a
t
i
o
n
a
l
i
n
f
o
r
m
a
t
i
o
n
i
nh
e
r
e
n
t
i
n
t
h
e
da
t
a
s
e
t,
a
n
a
d
j
a
c
e
n
c
y
m
a
t
r
i
x
wa
s
c
o
n
s
t
r
uc
t
e
d
to
r
e
p
r
e
s
e
n
t
pa
t
i
e
n
t
-
pa
t
i
e
n
t
r
e
l
a
t
i
o
n
s
hi
ps
.
T
h
e
m
a
t
r
i
x
va
l
ue
s
we
r
e
s
e
t
to
1
if
b
o
t
h
pa
t
i
e
n
t
s
h
a
d
l
u
n
g
c
a
n
c
e
r
a
n
d
0
ot
h
e
r
w
i
s
e
.
T
r
a
ns
f
o
r
m
i
ng
t
h
e
a
d
j
a
c
e
n
c
y
m
a
t
r
i
x
i
n
t
o
e
dge
i
n
d
i
c
e
s
a
l
l
o
we
d
f
o
r
t
h
e
u
t
i
li
z
a
t
i
o
n
o
f
gr
a
p
h
-
b
a
s
e
d
ne
ur
a
l
n
e
t
wor
k
a
r
c
hi
t
e
c
t
ur
e
s
,
e
nh
a
n
c
i
ng
t
h
e
a
n
a
ly
s
i
s
a
n
d
pr
e
d
i
c
t
i
o
n
c
a
pa
bi
li
t
i
e
s
.
T
h
e
f
i
na
l
pr
e
pr
o
c
e
s
s
i
ng
s
t
e
ps
i
nvo
l
v
e
d
c
o
nv
e
r
t
i
n
g
t
h
e
da
t
a
s
e
t
i
n
t
o
P
y
T
o
r
c
h
t
e
n
s
o
r
s
a
n
d
o
r
ga
ni
z
i
ng
i
t
i
n
t
o
da
t
a
o
bj
e
c
t
s
.
T
h
e
s
e
o
bj
e
c
t
s
,
n
a
m
e
ly
"
t
r
a
i
n
_da
t
a
"
a
n
d
"
t
e
s
t
_da
t
a
,
"
h
o
us
e
t
h
e
t
r
a
i
ni
ng
a
n
d
t
e
s
t
i
n
g
da
t
a
a
l
o
n
g
w
i
t
h
t
h
e
i
r
r
e
s
p
e
c
t
i
v
e
e
dge
in
d
i
c
e
s
.
F
i
gur
e
1
i
ll
us
t
r
a
t
e
s
t
h
e
ge
ne
r
a
l
s
t
r
uc
t
ur
e
o
f
t
h
e
pr
e
d
i
c
t
i
o
n
m
o
de
l
.
F
i
gur
e
1
.
S
tr
uc
t
ur
e
o
f
pr
e
d
i
c
t
i
o
n
m
o
de
l
A
c
r
uc
i
a
l
s
t
a
ge
i
n
o
ur
r
e
s
e
a
r
c
h
m
e
t
h
o
d
i
s
m
o
de
l
i
n
t
e
gr
a
t
i
o
n
,
whi
c
h
u
ni
t
e
s
d
i
s
pa
r
a
t
e
pr
e
d
i
c
t
i
ve
m
o
de
l
s
i
n
t
o
a
c
o
h
e
s
i
ve
f
r
a
m
e
wo
r
k
f
o
r
i
m
pr
o
v
e
d
l
un
g
c
a
nc
e
r
pr
e
d
i
c
t
i
o
n
.
E
ns
e
m
b
l
e
l
e
a
r
ni
ng
t
e
c
hni
q
ue
s
,
s
uc
h
a
s
s
t
a
c
k
i
n
g
o
r
a
v
e
r
a
g
i
n
g,
we
r
e
e
m
p
l
o
y
e
d
t
o
i
n
t
e
gr
a
t
e
t
h
e
o
u
t
pu
t
s
o
f
i
n
d
i
vi
du
a
l
m
o
de
l
s
a
n
d
r
e
duc
e
bi
a
s
e
s
.
R
i
go
r
o
us
v
a
l
i
d
a
t
i
o
n
a
n
d
c
r
o
s
s
-
v
a
l
i
d
a
t
i
o
n
pr
o
c
e
dur
e
s
we
r
e
c
o
n
duc
t
e
d
to
f
i
ne
-
t
un
e
t
h
e
e
n
s
e
m
bl
e
a
n
d
a
c
hi
e
ve
a
n
i
de
a
l
b
a
l
a
n
c
e
b
e
t
we
e
n
pr
e
d
i
c
t
i
v
e
po
we
r
a
n
d
m
o
de
l
v
a
r
i
e
t
y
.
F
i
gur
e
2
i
s
t
h
e
pr
o
p
o
s
e
d
a
dv
a
n
c
e
d
GC
N
w
i
t
h
GA
T
a
r
c
hi
t
e
c
t
ur
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2
5
0
2
-
4
7
52
In
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
,
Vo
l
.
3
7
,
N
o
.
2
,
F
e
b
r
ua
r
y
20
2
5
:
1
07
7
-
1
08
4
1080
F
i
gur
e
2
.
P
r
o
p
o
s
e
d
a
dv
a
n
c
e
d
GC
N
-
G
A
T
a
r
c
hi
t
e
c
tur
e
Gr
a
ph
c
o
n
v
o
l
ut
i
o
n
a
l
n
e
t
wo
r
ks
(
GC
Ns
)
a
n
d
g
r
a
ph
a
tt
e
n
t
i
o
n
n
e
t
wo
r
ks
(
GA
T
s
)
a
r
e
t
h
e
t
w
o
m
o
de
l
s
i
n
t
h
e
e
n
s
e
m
bl
e
t
h
a
t
s
h
o
w
di
s
t
i
n
c
t
a
dv
a
n
t
a
ge
s
i
n
iden
t
i
f
yi
ng
pa
tt
e
r
n
s
i
n
t
h
e
pa
t
i
e
n
t
da
t
a
s
e
t
.
T
h
e
pr
o
p
o
s
e
d
a
ppr
o
a
c
h
a
i
m
s
t
o
e
n
ha
n
c
e
t
h
e
gr
a
ph
c
o
nv
o
l
ut
i
o
n
a
l
n
e
t
wo
r
k
(
GC
N)
s
t
r
uc
t
u
r
e
a
n
d
c
o
m
bi
ne
i
t
w
i
t
h
G
AT
m
o
de
l
.
T
hi
s
c
o
m
pr
e
he
n
s
i
ve
m
e
t
h
o
do
l
o
gi
c
a
l
a
ppr
o
a
c
h
s
e
e
ks
to
pr
o
vi
de
a
hi
g
hly
a
d
v
a
n
c
e
d
a
n
d
de
pe
n
da
bl
e
t
oo
l
f
o
r
t
h
e
e
a
r
l
y
de
t
e
c
t
i
o
n
a
n
d
t
r
e
a
t
m
e
n
t
o
f
l
u
n
g
c
a
n
c
e
r
.
T
h
e
pr
o
p
o
s
e
d
m
o
de
l
s
t
r
uc
t
ur
e
i
s
e
l
u
c
i
d
a
t
e
d
i
n
t
h
e
f
o
r
m
o
f
ps
e
udo
c
o
de
i
n
t
h
e
s
u
b
s
e
que
n
t
s
e
c
t
i
o
n
.
A
l
go
r
i
t
hm
1.
GC
N
-
GA
T
m
o
de
l
de
f
i
ni
t
i
o
n
Initialize Model Parameters:
1.1. Set in_features: Number of input features.
1.2. Set hidden_dim: Dimension of the hidden layer.
1.3. Set out_features: Number of output features.
1.4. Set heads: Number of attention head
s in GAT (default: 4).
1.5. Set concat: Concatenate attention heads (default: True).
Define Model:
2.1. Create a class GCN_GAT that inherits from nn.Module.
2.2. Initialize the model parameters: in_features, hidden_dim, out_features, heads,
and concat.
Define Layers:
3.1. Define the first Graph Convolutional layer (GCN): gc1.
3.2. Define the second Graph Convolutional layer (GCN): gc2.
3.3. Define the Graph Attention layer (GAT): gat_layer.
3.4. Define an additional Graph Attention layer (GAT): gat_layer
1.
3.5. Define the fully connected layer: fc.
Forward Pass:
4.1. Define the forward method to perform the forward pass.
4.2. Apply ReLU activation to the output of the first GCN layer (gc1).
4.3. Apply ReLU activation to the output of the second GCN layer
(gc2).
4.4. Apply dropout for regularization.
4.5. Apply the first Graph Attention layer (GAT) (gat_layer).
4.6. Apply the second Graph Attention layer (GAT) (gat_layer1).
4.7. Flatten the tensor before passing it to the fully connected layer.
4.8. Apply t
he fully connected layer (fc).
4.9. Apply the sigmoid activation for the output.
Return Output:
5.1. Return the sigmoid
-
activated output representing class probabilities.
I
n
t
e
r
e
s
t
i
n
g
ly
,
a
s
pe
c
if
i
c
c
o
l
l
e
c
t
i
o
n
o
f
s
i
x
m
e
t
a
b
o
l
i
c
v
a
r
i
a
bl
e
s
de
m
o
ns
t
r
a
t
e
d
e
x
c
e
pt
i
o
n
a
l
d
i
s
c
r
i
mi
na
t
i
n
g
po
we
r
,
e
f
f
e
c
t
i
v
e
ly
d
i
f
f
e
r
e
n
t
i
a
t
i
n
g
b
e
t
we
e
n
pa
t
i
e
n
t
s
w
i
t
h
s
t
a
ge
I
l
u
n
g
c
a
n
c
e
r
a
n
d
h
e
a
l
t
hy
c
o
n
t
r
o
l
s
(
A
UC
=
0.
989,
s
e
n
s
i
t
i
v
i
t
y
=
98.
1%
,
s
pe
c
if
i
c
i
t
y
=
100.
0%
)
.
F
ur
t
h
e
r
m
o
r
e
,
t
h
e
to
p
f
i
ve
m
e
t
a
b
o
l
ic
bi
o
m
a
r
ke
r
s
i
de
n
t
i
f
i
e
d
by
t
h
e
F
C
B
F
a
l
go
r
i
t
hm
de
mo
n
s
t
r
a
t
e
d
p
ot
e
n
t
i
a
l
a
s
s
c
r
e
e
ni
ng
bi
o
m
a
r
ke
r
s
f
o
r
l
u
ng
c
a
n
c
e
r
e
a
r
l
y
de
t
e
c
t
i
o
n
.
I
t
wa
s
pr
o
p
o
s
e
d
t
h
a
t
t
h
e
Na
i
v
e
B
a
y
e
s
a
l
go
r
i
t
hm
m
i
g
h
t
b
e
a
h
e
l
p
f
u
l
t
oo
l
f
o
r
e
a
r
l
y
l
u
ng
t
um
o
r
pr
e
d
i
c
t
i
o
n
.
T
hi
s
m
u
l
t
i
d
i
s
c
i
p
li
na
r
y
a
ppr
o
a
c
h
n
o
t
o
nl
y
va
l
i
d
a
t
e
s
bl
o
o
d
-
b
a
s
e
d
s
c
r
e
e
ni
ng
b
ut
a
l
s
o
of
f
e
r
s
a
n
a
c
c
ur
a
t
e
,
r
a
pi
d,
a
n
d
c
o
m
pr
e
h
e
n
s
i
ve
d
i
a
g
n
o
s
t
i
c
t
ool
f
o
r
e
a
r
l
y
l
u
n
g
c
a
n
c
e
r
d
i
a
g
n
o
s
i
s
.
B
e
y
o
n
d
l
u
n
g
c
a
n
c
e
r
,
t
hi
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
I
S
S
N:
2
5
0
2
-
4
7
52
L
ung
c
anc
e
r
pr
e
diction
w
it
h
adv
anc
e
d
gr
aph
ne
ur
al
ne
t
w
or
k
s
(
B
inee
s
h
M
ooz
hippur
ath
)
1081
i
n
t
e
r
d
i
s
c
i
p
li
na
r
y
m
e
t
h
o
do
l
o
g
y
'
s
pot
e
n
t
i
a
l
a
pp
li
c
a
t
i
o
n
s
o
pe
n
d
oor
s
f
o
r
i
m
pr
o
vi
ng
e
a
r
l
y
c
a
n
c
e
r
di
a
g
no
s
i
s
i
n
a
w
i
de
r
c
o
n
t
e
x
t
.
T
hi
s
s
t
ud
y
pr
o
v
i
d
e
d
a
gr
o
un
d
-
b
r
e
a
k
i
n
g
m
u
l
t
i
d
i
s
c
i
p
li
na
r
y
a
ppr
o
a
c
h
t
h
a
t
s
uc
c
e
s
s
f
u
l
ly
c
o
m
bi
ne
s
m
e
t
a
b
o
l
o
m
i
c
s
a
n
d
m
a
c
hi
ne
l
e
a
r
ni
ng
t
o
i
de
n
t
i
f
y
e
a
r
l
y
l
u
n
g
c
a
n
c
e
r
d
i
a
g
n
o
s
t
i
c
i
nd
i
c
a
t
or
s
.
T
h
e
d
i
s
c
o
v
e
r
e
d
m
e
t
a
b
o
l
i
c
i
n
d
i
c
a
t
o
r
s
e
x
hi
b
i
t
i
m
pr
e
s
s
i
ve
d
i
a
g
n
o
s
t
i
c
po
we
r
,
e
s
pe
c
i
a
l
ly
f
o
r
t
h
e
e
a
r
l
y
d
i
a
g
n
o
s
i
s
o
f
l
u
n
g
t
u
m
o
r
s
.
I
t
i
s
n
e
c
e
s
s
a
r
y
t
o
c
r
e
a
t
e
m
o
r
e
pr
e
c
i
s
e
pr
e
d
i
c
t
i
o
n
m
e
t
h
o
ds
b
e
c
a
us
e
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
c
ur
r
e
n
t
m
o
de
l
s
f
o
r
e
a
r
l
y
-
s
t
a
ge
l
u
n
g
c
a
n
c
e
r
de
t
e
c
t
i
o
n
de
p
e
n
d
i
n
g
o
n
g
e
r
m
li
ne
v
a
r
i
a
t
i
o
n
s
h
a
s
b
e
e
n
f
o
u
n
d
t
o
b
e
r
e
s
t
r
i
c
t
e
d.
T
hi
s
s
t
ud
y
us
e
d
a
m
u
l
t
i
c
e
n
t
e
r
c
a
s
e
-
c
o
n
t
r
o
l
s
t
ud
y
to
m
a
ke
a
po
we
r
f
u
l
pr
e
d
i
c
t
i
v
e
m
e
t
h
o
d
f
o
r
e
a
r
l
y
l
u
n
g
c
a
n
c
e
r
d
i
a
g
n
o
s
i
s
us
i
ng
t
h
e
p
o
we
r
f
u
l
m
a
c
hi
ne
l
e
a
r
ni
ng
t
e
c
h
ni
que
o
f
e
x
t
r
e
m
e
gr
a
d
i
e
n
t
b
oo
s
t
i
n
g
(
XG
B
oo
s
t)
.
T
h
e
f
i
nd
i
ngs
s
h
o
we
d
a
s
t
r
o
n
g
c
o
r
r
e
l
a
t
i
o
n
b
e
t
we
e
n
c
e
r
t
a
i
n
s
i
ng
l
e
n
uc
l
e
o
t
i
d
e
p
o
l
ym
o
r
p
hi
s
m
s
(
S
NPs
)
,
i
n
c
l
ud
i
ng
T
YM
S
r
s
3819102
a
n
d
B
AG
6
r
s
1077393,
a
n
d
t
h
e
c
h
a
nc
e
o
f
de
ve
l
o
p
i
n
g
lun
g
c
a
n
c
e
r
.
A
dd
i
t
i
o
na
l
ly
,
t
h
e
XG
B
o
o
s
t
m
o
de
l
'
s
p
r
e
d
i
c
t
i
v
e
pe
r
f
o
r
m
a
n
c
e
wa
s
gr
e
a
t
l
y
e
nh
a
nc
e
d
by
t
h
e
a
dd
i
t
i
o
n
o
f
S
NPs
a
n
d
e
p
i
de
mi
o
l
o
g
i
c
a
l
da
t
a
,
e
x
c
e
ll
i
ng
p
a
r
t
i
c
u
l
a
r
l
y
i
n
t
h
e
pr
e
d
i
c
t
i
o
n
o
f
s
qua
m
o
us
c
e
l
l
c
a
n
c
e
r
(
S
C
C
)
.
T
hi
s
c
ut
t
i
n
g
-
e
dg
e
m
u
l
t
im
o
da
l
s
t
r
a
t
e
gy
de
m
o
ns
t
r
a
t
e
s
a
pr
o
m
i
s
i
ng
r
o
u
t
e
f
o
r
i
m
pr
o
vi
ng
e
a
r
l
y
l
u
n
g
c
a
nc
e
r
d
i
a
g
n
o
s
i
s
a
n
d
j
u
s
t
i
f
i
e
s
a
dd
i
t
i
o
n
a
l
i
nve
s
t
i
ga
t
i
o
n
f
o
r
a
pp
l
i
c
a
t
i
o
ns
o
f
pr
e
c
i
s
i
o
n
m
e
d
i
c
i
ne
i
n
c
a
n
c
e
r
d
i
a
g
no
s
t
i
c
s
.
T
h
e
r
e
s
e
a
r
c
h
wa
s
c
a
r
e
f
u
ll
y
c
r
a
f
t
e
d
to
e
x
p
l
o
r
e
h
o
w
a
dv
a
n
c
e
d
gr
a
ph
-
b
a
s
e
d
n
e
ur
a
l
n
e
t
wo
r
ks
pe
r
f
o
r
m
i
n
pr
e
d
i
c
t
i
n
g
d
i
f
f
e
r
e
n
t
l
e
v
e
l
s
o
f
l
u
n
g
c
a
n
c
e
r
s
e
v
e
r
i
t
y
.
Ut
i
li
z
i
ng
t
h
e
l
u
n
g
c
a
n
c
e
r
da
t
a
s
e
t
c
o
m
pr
is
i
n
g
309
r
e
c
o
r
ds
,
t
h
e
e
x
pe
r
i
m
e
n
t
e
m
p
l
o
y
e
d
r
a
n
do
m
o
v
e
r
s
a
m
p
li
ng
t
e
c
h
ni
que
s
to
e
n
s
ur
e
da
t
a
r
o
b
us
t
n
e
s
s
.
T
h
e
t
r
a
i
ni
ng
da
t
a
s
e
t,
c
o
m
pr
i
s
i
ng
380
i
n
s
t
a
n
c
e
s
(
80%
)
,
a
n
d
t
h
e
t
e
s
t
i
n
g
da
t
a
s
e
t
,
wi
t
h
96
i
n
s
t
a
nc
e
s
(
20%
)
,
we
r
e
c
a
r
e
f
u
l
l
y
s
e
l
e
c
t
e
d.
T
o
e
n
c
o
de
t
h
e
da
t
a
,
a
l
a
b
e
l
e
n
c
o
d
i
n
g
a
p
pr
o
a
c
h
wa
s
a
do
p
t
e
d
,
a
n
d
m
o
de
l
s
we
r
e
c
o
n
s
t
r
uc
t
e
d
wi
t
h
2
l
a
y
e
r
s
e
a
c
h
f
o
r
GC
Ns
a
n
d
GA
T
s
,
a
l
o
n
g
w
i
t
h
a
n
e
m
b
e
dd
i
ng
d
i
m
e
ns
i
o
n
(
d
i
m
)
s
e
t
to
64.
T
r
a
i
ni
ng
i
t
e
r
a
t
i
o
n
s
s
pa
nn
e
d
100
e
po
c
h
s
,
ut
i
li
z
i
ng
a
n
i
n
i
t
i
a
l
l
e
a
r
ni
ng
r
a
t
e
o
f
0.
01
a
n
d
a
dr
o
p
o
u
t
r
a
t
e
o
f
0.
25.
T
h
e
e
x
pe
r
i
m
e
n
t
a
l
s
e
t
up
l
e
v
e
r
a
ge
d
P
y
t
h
o
n
v
e
r
s
i
o
n
3.
10.
12
a
n
d
P
y
T
o
r
c
h
2.
0
s
o
f
t
wa
r
e
,
e
x
e
c
ut
e
d
o
n
a
T
e
s
l
a
T
4
GPU
s
e
r
v
e
r
w
i
t
h
15
GB
o
f
GPU
m
e
m
o
r
y
,
o
pe
r
a
t
i
n
g
un
de
r
U
b
u
n
t
u
2
0.
04
L
T
S
.
3.
RE
S
UL
T
S
AN
D
DI
S
CU
S
S
I
ON
T
h
e
r
e
s
u
l
t
s
o
f
t
h
e
A
G
C
N
-
G
A
T
m
o
de
l
we
r
e
f
u
r
t
h
e
r
r
e
i
nf
o
r
c
e
d
by
i
n
t
e
gr
a
t
i
n
g
ot
h
e
r
m
o
de
l
s
to
e
s
t
a
bli
s
h
a
r
o
b
us
t
c
o
m
p
a
r
i
s
o
n
b
a
s
e
li
ne
f
o
r
a
t
h
o
r
o
ugh
a
n
a
ly
s
i
s
.
I
n
c
o
m
p
a
r
i
n
g
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
v
a
r
i
o
us
m
o
de
l
s
i
n
pr
e
d
i
c
t
i
n
g
l
u
n
g
c
a
n
c
e
r
r
i
s
k,
t
h
e
pr
o
p
o
s
e
d
a
dv
a
n
c
e
d
GC
N
e
m
e
r
ge
s
a
s
a
s
t
a
n
do
ut
pe
r
f
o
r
m
e
r
.
T
h
e
a
dv
a
nc
e
d
GC
N
de
m
o
ns
t
r
a
t
e
s
s
upe
r
i
o
r
pr
e
di
c
t
i
v
e
c
a
pa
bil
i
t
i
e
s
w
i
t
h
a
n
a
c
c
ur
a
c
y
o
f
0.
9454,
pr
e
c
i
s
i
o
n
o
f
0.
9213,
r
e
c
a
l
l
o
f
0.
9743,
a
n
d
a
n
F
1
s
c
o
r
e
o
f
0.
9482,
o
u
tper
f
o
r
m
i
ng
m
o
de
l
s
li
ke
l
i
ne
a
r
r
e
gr
e
s
s
i
o
n
,
K
NN
,
r
a
n
do
m
f
o
r
e
s
t
,
a
n
d
n
e
ur
a
l
n
e
t
wo
r
ks
.
N
ot
a
bl
y
,
whil
e
l
i
ne
a
r
r
e
gr
e
s
s
i
o
n
a
c
hi
e
v
e
d
hi
g
h
pr
e
c
i
s
i
o
n
,
i
t
f
a
l
t
e
r
e
d
i
n
r
e
c
a
l
l
,
i
nd
i
c
a
t
i
n
g
po
t
e
n
t
i
a
l
li
mi
t
a
t
i
o
n
s
i
n
c
a
pt
ur
i
n
g
a
ll
r
e
l
e
v
a
n
t
i
n
s
t
a
n
c
e
s
.
S
i
mi
l
a
r
l
y
,
K
NN
e
xhi
b
i
t
e
d
c
o
m
p
a
r
a
t
i
v
e
ly
l
o
we
r
a
c
c
ur
a
c
y
a
n
d
pr
e
c
i
s
i
o
n
,
s
ugge
s
t
i
n
g
a
l
e
s
s
r
o
b
us
t
p
r
e
di
c
t
i
ve
pe
r
f
o
r
m
a
n
c
e
.
R
a
n
do
m
f
o
r
e
s
t
a
n
d
n
e
ur
a
l
n
e
t
wo
r
k
m
o
de
l
s
de
m
o
n
s
t
r
a
t
e
d
c
o
m
m
e
n
d
a
bl
e
o
v
e
r
a
l
l
pe
r
f
o
r
m
a
nc
e
,
y
e
t
t
h
e
i
r
a
c
c
ur
a
c
y
a
n
d
pr
e
c
i
s
i
o
n
f
e
ll
s
h
o
r
t
o
f
t
h
e
a
dv
a
n
c
e
d
GC
N.
T
a
bl
e
1
i
s
de
l
i
be
r
a
t
e
t
h
e
e
xpe
r
i
m
e
n
t
a
l
s
e
t
up
de
t
a
i
l
s
.
T
a
bl
e
1.
E
x
pe
r
i
m
e
n
t
a
l
s
e
t
up
pa
r
a
m
e
t
e
r
s
P
a
r
a
me
t
e
r
s
V
a
lu
e
s
D
a
ta
s
e
t
L
ung C
a
n
c
e
r
D
a
ta
s
e
t
D
a
ta
s
e
t
s
iz
e
309 r
e
c
o
r
ds
D
a
ta
O
v
e
r
s
a
mpl
in
g
R
a
ndo
m Ove
r
s
a
mpl
in
g
T
r
a
in
in
g &
T
e
s
ti
ng da
ta
s
e
t
s
iz
e
380 (
80%
)
& 96 (
20
%
)
N
umbe
r
of
G
C
N
l
a
y
e
r
s
& Att
e
nt
i
o
n l
a
y
e
r
s
2
E
mbe
ddi
ng D
i
me
ns
i
o
n (
di
m)
64
N
umbe
r
of
tr
a
in
in
g i
t
e
r
a
ti
o
ns
100
I
ni
ti
a
l
le
a
r
n
in
g r
a
t
e
& Dr
o
p
o
ut
r
a
t
e
0.01 & 0.25
S
of
twa
r
e
P
y
th
o
n 3.10.12,
P
y
T
or
c
h 2.0
T
h
e
a
dv
a
nc
e
d
GC
N
m
o
de
l
's
e
x
c
e
pt
i
o
na
l
pe
r
f
o
r
m
a
n
c
e
u
n
de
r
s
c
o
r
e
s
i
t
s
e
f
f
e
c
t
i
v
e
ne
s
s
i
n
c
a
pt
ur
i
n
g
i
n
t
r
i
c
a
t
e
pa
tt
e
r
n
s
a
n
d
r
e
l
a
t
i
o
n
s
hi
ps
w
i
t
hi
n
t
h
e
l
u
n
g
c
a
n
c
e
r
pr
e
d
i
c
t
i
o
n
da
t
a
s
e
t
,
s
h
o
wc
a
s
i
n
g
i
t
s
po
ten
t
i
a
l
f
o
r
e
nh
a
nc
i
n
g
e
a
r
l
y
de
t
e
c
t
i
o
n
e
f
f
o
r
t
s
a
n
d
pe
r
s
o
n
a
li
z
e
d
r
i
s
k
a
s
s
e
s
s
m
e
n
t
s
.
T
h
e
s
e
r
e
s
u
l
t
s
hi
g
hli
g
h
t
t
h
e
pr
o
m
i
s
e
o
f
a
dv
a
nc
e
d
gr
a
ph
-
b
a
s
e
d
m
e
t
h
o
do
l
o
gi
e
s
i
n
m
e
d
i
c
a
l
r
e
s
e
a
r
c
h
,
pa
r
t
i
c
u
l
a
r
ly
i
n
t
h
e
r
e
a
l
m
o
f
l
u
n
g
c
a
n
c
e
r
pr
e
d
i
c
t
i
o
n
,
o
pe
ni
n
g
a
v
e
n
u
e
s
f
o
r
f
ur
t
h
e
r
e
x
p
l
o
r
a
t
i
o
n
a
n
d
de
v
e
l
o
p
m
e
n
t
o
f
pr
e
d
i
c
t
i
v
e
m
o
de
l
s
f
o
r
pr
o
a
c
t
i
v
e
he
a
l
t
h
c
a
r
e
i
n
t
e
r
v
e
n
t
i
o
n
s
.
T
a
bl
e
2
i
s
a
de
li
be
r
a
t
e
pe
r
f
o
r
m
a
n
c
e
a
n
a
ly
s
i
s
o
f
t
h
e
e
xi
s
t
i
n
g
a
n
d
pr
o
po
s
e
d
m
o
de
l
s
.
F
igur
e
3
i
s
de
l
i
be
r
a
t
e
c
o
m
p
a
r
i
s
o
n
b
e
t
we
e
n
a
c
c
ur
a
c
y
a
n
d
pr
e
c
i
s
i
o
n
l
e
v
e
l
s
.
F
i
gur
e
4
s
h
o
ws
t
h
e
de
l
i
be
r
a
t
e
r
e
c
a
l
l
v
a
l
ue
i
n
c
o
m
pa
r
i
ng
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
v
a
r
i
o
us
m
o
de
l
s
i
n
pr
e
d
i
c
t
i
n
g
l
u
n
g
c
a
n
c
e
r
r
i
s
k
;
F
i
gur
e
5
s
h
o
ws
t
h
e
pr
o
p
o
s
e
d
m
o
de
l
’
s
pr
e
c
i
s
i
o
n
,
r
e
c
a
l
l
,
a
n
d
F
1
s
c
o
r
e
pe
r
f
o
r
m
a
n
c
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2
5
0
2
-
4
7
52
In
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
,
Vo
l
.
3
7
,
N
o
.
2
,
F
e
b
r
ua
r
y
20
2
5
:
1
07
7
-
1
08
4
1082
T
a
bl
e
2
.
P
e
r
f
o
r
m
a
nc
e
a
na
ly
s
i
s
o
f
e
xi
s
t
i
n
g
a
n
d
pr
o
p
o
s
e
d
m
o
de
l
M
o
de
l
A
c
c
u
r
a
c
y
P
r
e
c
is
i
o
n
R
e
c
a
ll
F
1 S
c
or
e
L
in
e
a
r
r
e
g
r
e
s
s
io
n
0.91
0.90
1.00
0.95
K
N
N
0.79
0.79
1.00
0.88
R
a
ndo
m
f
o
r
e
s
t
0.89
0.90
0.98
0.93
N
e
ur
a
l
n
e
tw
o
r
k
0.89
0.91
0.95
0.93
A
dv
a
nc
e
d
G
C
N
-
G
A
T
0.95
0.92
0.97
0.95
F
i
gur
e
3
.
A
c
c
ur
a
c
y
a
n
d
pr
e
c
i
s
i
o
n
l
e
v
e
l
c
o
m
pa
r
i
s
o
n
F
i
gur
e
4
.
R
e
c
a
l
l
a
n
d
F
1
s
c
o
r
e
c
o
m
p
a
r
i
s
o
n
F
i
gur
e
5
.
P
r
o
p
o
s
e
d
A
GC
N
-
GA
T
m
o
de
l
pe
r
f
o
r
m
a
nc
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
I
S
S
N:
2
5
0
2
-
4
7
52
L
ung
c
anc
e
r
pr
e
diction
w
it
h
adv
anc
e
d
gr
aph
ne
ur
al
ne
t
w
or
k
s
(
B
inee
s
h
M
ooz
hippur
ath
)
1083
T
h
e
a
d
v
a
n
c
e
d
GC
N
m
o
de
l
's
e
x
c
e
pt
i
o
na
l
pe
r
f
o
r
m
a
n
c
e
u
n
de
r
s
c
o
r
e
s
i
t
s
e
f
f
e
c
t
i
v
e
n
e
s
s
i
n
c
a
pt
ur
i
n
g
i
n
t
r
i
c
a
t
e
pa
tt
e
r
n
s
a
n
d
r
e
l
a
t
i
o
n
s
hi
ps
w
i
t
hi
n
t
h
e
l
u
n
g
c
a
n
c
e
r
pr
e
d
i
c
t
i
o
n
da
t
a
s
e
t
,
s
h
o
wc
a
s
i
n
g
i
t
s
po
ten
t
i
a
l
f
o
r
e
nh
a
nc
i
n
g
e
a
r
l
y
de
t
e
c
t
i
o
n
e
f
f
o
r
t
s
a
n
d
pe
r
s
o
n
a
li
z
e
d
r
i
s
k
a
s
s
e
s
s
m
e
n
t
s
.
T
h
e
s
e
r
e
s
u
l
t
s
hi
g
hli
g
h
t
t
h
e
pr
o
m
i
s
e
o
f
a
dv
a
nc
e
d
gr
a
ph
-
b
a
s
e
d
m
e
t
h
o
do
l
o
gi
e
s
i
n
m
e
d
i
c
a
l
r
e
s
e
a
r
c
h
,
pa
r
t
i
c
u
l
a
r
ly
i
n
t
h
e
r
e
a
l
m
o
f
l
u
n
g
c
a
n
c
e
r
pr
e
d
i
c
t
i
o
n
,
o
pe
ni
n
g
a
v
e
n
u
e
s
f
o
r
f
ur
t
h
e
r
e
x
p
l
o
r
a
t
i
o
n
a
n
d
de
v
e
l
o
p
m
e
n
t
o
f
pr
e
d
i
c
t
i
v
e
m
o
de
l
s
f
o
r
pr
o
a
c
t
i
v
e
he
a
l
t
h
c
a
r
e
i
n
t
e
r
v
e
n
t
i
o
n
s
.
F
ut
ur
e
r
e
s
e
a
r
c
h
s
h
o
u
l
d
f
o
c
us
o
n
e
x
pa
n
d
i
ng
da
t
a
s
e
t
s
to
i
n
c
l
ude
d
i
ve
r
s
e
pa
t
i
e
n
t
p
o
p
u
l
a
t
i
o
n
s
,
i
n
t
e
gr
a
t
i
n
g
m
u
l
t
i
-
o
m
i
c
s
da
t
a
f
o
r
i
m
pr
o
v
e
d
pr
e
d
i
c
t
i
v
e
po
we
r
,
de
v
e
l
o
p
i
n
g
i
n
t
e
r
pr
e
t
a
bi
li
t
y
f
r
a
m
e
w
o
r
ks
f
o
r
GN
Ns
,
a
n
d
c
o
n
duc
t
i
n
g
l
o
n
g
i
t
ud
i
na
l
s
t
ud
i
e
s
t
o
a
s
s
e
s
s
r
e
a
l
-
wo
r
l
d
e
f
f
i
c
a
c
y
.
K
e
y
e
x
pe
r
im
e
n
t
s
s
h
o
u
l
d
v
a
l
i
da
t
e
t
h
e
m
o
de
l
o
n
e
x
t
e
r
n
a
l
da
t
a
s
e
t
s
,
o
p
t
i
m
i
z
e
GN
N
a
r
c
hi
t
e
c
t
ur
e
s
a
n
d
hy
pe
r
pa
r
a
m
e
t
e
r
s
,
i
n
t
e
gr
a
t
e
c
l
i
n
i
c
a
l
t
e
x
t
da
t
a
w
i
t
h
s
t
r
uc
t
ur
e
d
da
t
a
,
a
n
d
pe
r
f
o
r
m
a
bl
a
t
i
o
n
s
t
ud
i
e
s
to
un
de
r
s
t
a
n
d
t
h
e
A
GC
N
-
G
A
T
m
o
de
l
's
c
o
m
po
n
e
n
t
s
.
De
s
p
i
t
e
pr
o
m
i
s
i
ng
r
e
s
u
l
t
s
,
l
i
mi
t
a
t
i
o
ns
i
n
c
l
ude
r
e
l
ian
c
e
o
n
a
s
m
a
l
l
d
a
t
a
s
e
t
,
s
i
g
nif
i
c
a
n
t
c
o
m
put
a
t
i
o
n
a
l
r
e
s
o
ur
c
e
r
e
qu
i
r
e
m
e
n
t
s
,
a
n
d
c
ha
l
l
e
nge
s
i
n
i
n
t
e
r
pr
e
t
a
bi
li
t
y
.
A
ddr
e
s
s
i
ng
t
h
e
s
e
li
mi
t
a
t
i
o
ns
i
nv
o
l
v
e
s
e
nh
a
n
c
i
n
g
m
o
de
l
i
n
t
e
r
pr
e
t
a
bi
li
t
y
,
e
f
f
i
c
i
e
n
c
y
,
a
n
d
v
a
li
da
t
i
o
n
a
c
r
o
s
s
l
a
r
ge
r
,
m
o
r
e
d
i
v
e
r
s
e
da
t
a
s
e
t
s
.
4.
CONC
L
USI
ON
T
hi
s
r
e
s
e
a
r
c
h
i
n
t
r
o
duc
e
s
a
n
i
nn
o
v
a
t
i
v
e
a
ppr
o
a
c
h
t
o
l
u
n
g
c
a
n
c
e
r
pr
e
d
i
c
t
i
o
n
,
a
i
mi
ng
t
o
e
n
h
a
nc
e
a
c
c
ur
a
c
y
a
n
d
e
f
f
i
c
a
c
y
i
n
t
h
e
e
a
r
l
y
de
t
e
c
t
i
o
n
o
f
l
un
g
c
a
nc
e
r
.
B
y
i
n
t
e
gr
a
t
i
n
g
a
n
a
d
v
a
n
c
e
d
GC
N
wi
t
h
GA
T
a
r
c
hi
t
e
c
t
ur
e
,
t
h
e
pr
o
p
o
s
e
d
m
o
de
l
e
xhi
b
i
t
s
r
e
m
a
r
ka
bl
e
pe
r
f
o
r
m
a
n
c
e
i
m
pr
o
v
e
m
e
n
t
s
o
v
e
r
e
xi
s
t
i
n
g
m
o
d
e
l
s
,
w
i
t
h
a
s
i
g
nif
i
c
a
n
t
i
n
c
r
e
a
s
e
i
n
a
c
c
ur
a
c
y
by
6%
a
n
d
pr
e
c
i
s
i
o
n
by
2%
,
c
o
m
pa
r
e
d
t
o
t
h
e
b
e
s
t
-
pe
r
f
o
r
m
i
ng
b
a
s
e
li
ne
m
o
de
l
.
T
hi
s
a
d
v
a
n
c
e
m
e
n
t
h
o
l
d
s
s
i
g
nif
i
c
a
n
t
pr
o
m
i
s
e
f
o
r
i
m
pr
o
vi
ng
pa
t
i
e
n
t
o
u
t
c
o
m
e
s
a
n
d
f
a
c
il
i
t
a
t
i
n
g
pr
o
a
c
t
i
v
e
h
e
a
l
t
h
c
a
r
e
i
n
t
e
r
v
e
n
t
i
o
ns
.
T
h
e
s
uc
c
e
s
s
f
u
l
i
n
t
e
gr
a
t
i
o
n
o
f
GC
N
a
n
d
GA
T
m
e
t
h
o
do
l
o
g
i
e
s
de
m
o
ns
t
r
a
t
e
s
t
h
e
pot
e
n
t
i
a
l
f
o
r
gr
a
ph
-
b
a
s
e
d
a
ppr
o
a
c
h
e
s
to
t
a
c
kl
e
c
o
m
p
l
e
x
m
e
d
i
c
a
l
pr
e
d
i
c
t
i
o
n
t
a
s
ks
,
e
x
t
e
n
d
i
n
g
b
e
yo
n
d
l
u
n
g
c
a
nc
e
r
to
ot
h
e
r
d
i
s
e
a
s
e
s
w
i
t
h
i
n
t
r
i
c
a
t
e
da
t
a
s
t
r
uc
t
u
r
e
s
.
T
h
e
s
e
im
pr
o
v
e
m
e
n
t
s
s
ugge
s
t
a
c
r
uc
i
a
l
r
o
l
e
f
o
r
gr
a
ph
-
b
a
s
e
d
m
o
de
l
s
i
n
p
e
r
s
o
n
a
li
z
e
d
m
e
d
i
c
i
ne
,
e
na
bl
i
ng
e
a
r
l
i
e
r
a
n
d
m
o
r
e
a
c
c
ur
a
t
e
r
i
s
k
i
d
e
n
t
i
f
i
c
a
t
i
o
n
a
n
d
t
a
i
l
o
r
e
d
i
n
t
e
r
v
e
n
t
i
o
n
s
.
T
hi
s
s
t
ud
y
u
n
de
r
s
c
o
r
e
s
t
h
e
t
r
a
n
s
f
o
r
m
a
t
i
v
e
po
t
e
n
t
i
a
l
o
f
a
d
v
a
n
c
e
d
m
a
c
hi
ne
l
e
a
r
ni
ng
t
e
c
hni
que
s
i
n
m
e
d
i
c
a
l
r
e
s
e
a
r
c
h
,
s
e
tt
i
n
g
t
h
e
s
t
a
ge
f
o
r
f
ut
ur
e
i
nno
v
a
t
i
o
n
s
i
n
o
nc
o
l
o
g
y
a
n
d
b
e
y
o
n
d
.
RE
F
E
R
E
NC
E
S
[
1]
C.
M
.
R
udi
n,
E
.
B
r
a
mbi
ll
a
,
C
.
F
a
iv
r
e
-
F
in
n,
a
nd
J
.
S
a
ge
,
“
S
ma
l
l
-
c
e
ll
lu
ng
c
a
nc
e
r
,”
N
at
ur
e
R
e
v
ie
w
s
D
is
e
as
e
P
r
ime
r
s
,
v
o
l.
7,
n
o
.1,
pp. 1
-
12, 2021
, do
i
:1
0.1038/s
41572
-
020
-
00235
-
0.
[
2]
A
. S
ha
r
ma
a
nd
R
. R
a
ni
, “
A
s
y
s
t
e
ma
ti
c
r
e
v
i
e
w
of
a
ppl
i
c
a
ti
o
ns
of
ma
c
hi
n
e
l
e
a
r
ni
ng
in
c
a
n
c
e
r
p
r
e
di
c
ti
o
n
a
nd dia
gno
s
is
,”
A
r
c
hi
v
e
s
o
f
C
om
put
at
io
nal
M
e
th
ods
i
n E
ngi
ne
e
r
in
g
, vo
l.
28, n
o
.7, pp.4875
-
4896, 2021, do
i:
10.1007/s
11831
-
021
-
09556
-
z.
[
3]
D
.
A
.
-
A
r
is
ti
z
a
ba
l,
M
.
A
.
A
r
mi
n,
S
.
D
e
nma
n,
C
.
F
oo
k
e
s
,
a
nd
L
.
P
e
te
r
s
s
o
n,
“
A
s
ur
ve
y
o
n
gr
a
ph
-
ba
s
e
d
d
e
e
p
l
e
a
r
ni
ng
f
or
c
o
mput
a
ti
o
na
l
hi
s
t
o
pa
th
o
l
o
g
y
,”
C
om
put
e
r
iz
e
d
M
e
di
c
al
I
m
agi
ng
and
G
r
aphi
c
s
,
vo
l.
95,
n
o
.1,
pp.
102027
-
1002039,
2022,
do
i:
10.1016/j
.c
o
mpm
e
di
ma
g.2021.102027.
[
4]
S
.
T
a
g
o
r
e
,
N
.
C
h
o
w
dhur
y
,
a
nd
R.
K
.
D
e
,
“
A
na
l
y
z
in
g
m
e
th
o
d
s
f
o
r
pa
th
mi
ni
ng
w
it
h
a
ppl
i
c
a
ti
o
ns
in
m
e
ta
b
o
l
o
mi
c
s
,”
G
e
ne
,
vo
l.
534, no
. 2, pp. 125
-
138, 2014
, d
o
i
:
10.1016/j
.g
e
ne
.2013.10.056.
[
5]
W
.
Z
ha
ng,
J
.
C
hi
e
n,
J
.
Y
o
ng,
a
nd
R
.
K
ua
ng,
“
N
e
twor
k
-
ba
s
e
d
ma
c
hi
n
e
l
e
a
r
ni
ng
a
nd
gr
a
ph
th
e
o
r
y
a
lg
o
r
it
hms
f
or
pr
e
c
is
io
n
o
n
c
o
l
o
g
y
,”
N
P
J
pr
e
c
is
io
n onc
ol
ogy
,
v
o
l.
1, n
o
. 1, pp. 25
-
35, 20
17
, do
i:
10.1038/s
41698
-
017
-
0029
-
7.
[
6]
P
.
W
a
ng
a
nd
Z
.
Z
ha
o
,
“
I
mpr
ov
in
g
c
o
nt
e
x
t
a
nd
s
y
nt
a
c
ti
c
d
e
p
e
nd
e
nc
y
f
or
a
s
pe
c
t
-
ba
s
e
d
s
e
n
ti
m
e
nt
a
na
l
y
s
is
us
in
g
a
f
us
e
d
gr
a
ph
a
tt
e
nt
i
o
n n
e
tw
o
r
k,”
E
v
ol
ut
io
nar
y
I
nt
e
ll
ig
e
nc
e
,
vol
. 17, n
o
.1, pp.
589
-
598, 2023
,
do
i
:
10.1007/s
12065
-
023
-
00845
-
z.
[
7]
X
.
L
u
o
,
X
.
Z
a
ng,
L
.
Y
a
ng,
J
.
H
ua
ng,
F
.
L
ia
ng,
J
.
R
o
dr
ig
ue
z
-
C
a
na
le
s
,
a
nd
G
.
X
ia
o
,
“
C
o
mpr
e
h
e
ns
i
ve
c
o
mput
a
ti
o
na
l
pa
th
o
l
ogi
c
a
l
im
a
ge
a
na
l
y
s
is
pr
e
di
c
ts
lu
ng
c
a
nc
e
r
p
r
o
gn
o
s
is
,”
J
our
nal
of
T
hor
ac
ic
O
nc
ol
ogy
,
v
o
l.
12,
n
o
.
3,
pp.
50
1
-
509
,
2017,
do
i:
10.1016/j
.j
th
o
.2016.10.017.
[
8]
S
.
G
upt
a
a
nd
M
.
K
.
G
upt
a
,
“
A
c
o
mpa
r
a
ti
ve
a
na
l
y
s
is
of
de
e
p
le
a
r
ni
ng
a
ppr
o
a
c
h
e
s
f
or
p
r
e
di
c
ti
ng
br
e
a
s
t
c
a
n
c
e
r
s
ur
v
i
v
a
bi
l
it
y
,”
A
r
c
hi
v
e
s
o
f
C
om
put
at
io
nal
M
e
th
ods
i
n E
ngi
ne
e
r
in
g
,
v
o
l.
29, n
o. 5, pp. 2959
-
2975,
2022,
do
i
:
10.1007/s
11831
-
021
-
09679
-
3.
[
9]
F
.
J
.
S
ha
ik
h,
a
nd
D.
S
.
R
a
o
,
“
P
r
e
di
c
ti
o
n
of
c
a
n
c
e
r
di
s
e
a
s
e
us
in
g
ma
c
hi
n
e
l
e
a
r
ni
ng
a
ppr
o
a
c
h,”
M
at
e
r
ia
ls
T
oday
:
P
r
oc
e
e
di
ngs
,
vo
l.
50, no
. 1, pp. 40
-
47, 20
22, d
o
i
:
10.1016/j
.ma
tp
r
.2021.03.625.
[
10]
Y
.
L
in
,
K
.
Z
h
o
u,
a
nd
J
.
L
i,
“
P
r
e
d
i
c
ti
o
n
of
s
l
o
p
e
s
ta
bi
li
t
y
us
in
g
f
o
u
r
s
upe
r
v
is
e
d
le
a
r
ni
ng
m
e
th
o
ds
,”
I
E
E
E
A
c
c
e
s
s
,
vo
l.
6,
n
o
.
1,
pp.
31169
-
31179, 2018, do
i
:1
0.1109/a
c
c
e
s
s
.2018.2843787.
[
11]
A
.
K
u
r
a
ni
,
P
.
D
o
s
hi
,
A
.
V
a
kha
r
ia
,
a
nd
M
.
S
ha
h,
“
A
c
o
mp
r
e
h
e
ns
iv
e
c
o
mpa
r
a
ti
v
e
s
tu
d
y
of
a
r
ti
f
i
c
ia
l
ne
u
r
a
l
n
e
tw
o
r
k
(
A
N
N
)
a
nd
s
uppo
r
t
ve
c
t
o
r
ma
c
hi
n
e
s
(
S
V
M
)
o
n
s
t
oc
k
f
or
e
c
a
s
ti
ng,”
A
n
nal
s
of
D
at
a
Sc
ie
nc
e
,
vo
l.
10,
n
o
.
1,
pp.
183
-
208,
2023,
do
i:
10.1007/s
40745
-
021
-
00344
-
x.
[
12]
M.
L
.
G
ig
e
r
,
“
M
a
c
hi
ne
l
e
a
r
ni
ng
in
m
e
di
c
a
l
im
a
gi
ng,”
J
our
nal
of
th
e
A
m
e
r
ic
an
C
ol
le
ge
of
R
adi
ol
ogy
,
vo
l.
15,
n
o
.
3,
pp.
512
-
520,
2018
, do
i:
10.1016/j
.
ja
c
r
.2017.12.028.
[
13]
C.
M
.
E
c
kha
r
dt
e
t
al
.
,
“
U
ns
upe
r
v
is
e
d
ma
c
hi
n
e
l
e
a
r
ni
ng
m
e
th
ods
a
nd
e
m
e
r
gi
ng
a
ppl
i
c
a
ti
o
ns
in
he
a
lt
h
c
a
r
e
,”
K
ne
e
Sur
ge
r
y
,
Spor
t
s
T
r
aum
at
ol
ogy
, A
r
th
r
os
c
op
y
,
v
ol
. 31, n
o
. 2, pp. 376
-
381, 2023,
do
i:
10.1007/s
00167
-
022
-
07233
-
7.
[
14]
X
.
H
ua
ng,
L
.
Z
ha
ng,
B
.
W
a
ng,
F
.
L
i,
a
nd
Z
.
Z
ha
ng,
“
F
e
a
tu
r
e
c
lu
s
t
e
r
in
g
-
ba
s
e
d
s
uppo
r
t
ve
c
t
o
r
ma
c
hi
n
e
r
e
c
ur
s
i
v
e
f
e
a
tu
r
e
e
li
mi
na
ti
o
n
f
or
g
e
ne
s
e
l
e
c
t
i
o
n,”
A
ppl
ie
d I
nt
e
ll
ig
e
nc
e
,
vol
. 48, n
o
.1, p
p. 594
-
607
, 2018, d
o
i
:
10.1007/s
10489
-
017
-
0992
-
2.
[
15]
A.
B
.
P
a
w
a
r
e
t
al
.,
“
I
mpl
e
me
nt
a
ti
o
n
of
bl
o
c
k
c
ha
in
t
e
c
hn
ol
o
g
y
us
in
g
e
x
t
e
nde
d
C
N
N
f
o
r
lu
ng
c
a
n
c
e
r
pr
e
d
ic
t
i
o
n,”
M
e
as
ur
e
m
e
nt
:
Se
ns
or
s
,
v
ol
. 24, n
o
.1, pp
. 100530
-
100545, 2022, d
o
i:
10.1016/j
.me
a
s
e
n.2022.100530.
[
16]
G
.
H
o
u
e
t
al
.
,
“
D
e
e
p
l
e
a
r
ni
ng
a
ppr
o
a
c
h
f
o
r
pr
e
di
c
ti
ng
l
y
mph
n
o
d
e
m
e
ta
s
ta
s
is
in
no
n
-
s
ma
ll
c
e
ll
lu
ng
c
a
nc
e
r
b
y
f
us
in
g
im
a
g
e
–
ge
n
e
da
ta
,”
E
ngi
ne
e
r
in
g
A
ppl
ic
at
io
ns
of
A
r
ti
f
ic
ia
l
I
nt
e
ll
ig
e
nc
e
,
vo
l.
122,
n
o
.1,
pp.
106140
-
106153
,
2023,
do
i:
10.1016/j
.e
nga
ppa
i.
2023.106140.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2
5
0
2
-
4
7
52
In
do
n
e
s
i
a
n
J
E
l
e
c
E
n
g
&
C
o
m
p
S
c
i
,
Vo
l
.
3
7
,
N
o
.
2
,
F
e
b
r
ua
r
y
20
2
5
:
1
07
7
-
1
08
4
1084
[
17]
Y
.
X
ie
e
t
al
.
,
“
E
a
r
l
y
lu
ng
c
a
n
c
e
r
d
ia
gno
s
ti
c
bi
oma
r
ke
r
di
s
c
ov
e
r
y
b
y
ma
c
hi
n
e
l
e
a
r
ni
ng
me
th
o
ds
,”
T
r
ans
la
ti
onal
onc
ol
ogy
,
vo
l.
14,
no
. 1, pp:
100907
-
100918, 2021, d
oi
:
10.1016/j
.t
r
a
n
o
n.2020.10
0907.
[
18]
Y
.
Z
ha
o
e
t
al
.
,
“
M
e
ta
bo
li
c
pr
of
i
le
s
c
ha
r
a
c
t
e
r
i
z
in
g
di
f
f
e
r
e
nt
phe
n
o
t
y
p
e
s
of
p
o
l
y
c
y
s
ti
c
ov
a
r
y
s
y
ndr
o
m
e
:
pl
a
s
ma
me
ta
bo
l
omi
c
s
a
na
l
y
s
is
,”
B
M
C
m
e
di
c
in
e
,
v
ol
. 10, n
o
.1, pp. 1
-
12
, 2012, d
o
i:
10.
1186/1741
-
7015
-
10
-
153.
[
19]
A
. K
e
r
p
e
l
-
F
r
o
ni
us
e
t
al
.,
“
S
c
r
e
e
ni
ng
f
o
r
l
ung
c
a
n
c
e
r
i
n i
ndi
vi
du
a
ls
w
ho
ne
ve
r
s
m
o
k
e
d:
a
n i
nt
e
r
na
ti
o
na
l
a
s
s
oc
ia
ti
o
n
f
or
t
h
e
s
tu
d
y
of
lu
ng
c
a
nc
e
r
e
a
r
l
y
de
te
c
ti
o
n
a
nd
s
c
r
e
e
ni
ng
c
o
mm
it
t
e
e
r
e
p
o
r
t,
”
J
our
nal
of
T
hor
ac
ic
O
nc
ol
ogy
,
v
o
l.
17,
no
.
1,
pp.
56
-
66,
2022,
do
i:
10.1016/j
.j
th
o
.2021.07.031.
[
20]
M.
U
.
A
h
s
a
n,
Q
.
L
iu
,
J
.
E
.
P
e
r
do
mo
,
L
.
F
a
n
g,
a
nd
K
.
W
a
n
g,
“
A
s
u
r
v
e
y
of
a
l
go
r
it
hm
s
f
o
r
t
he
de
te
c
ti
o
n
o
f
ge
no
mi
c
s
tr
uc
tu
r
a
l
v
a
r
ia
n
t
s
f
r
o
m l
o
n
g
-
r
e
a
d
s
e
que
nc
in
g
da
ta
,
”
N
at
u
r
e
M
e
th
od
s
,
v
o
l.
2
0,
no
.
8
, p
p
.
11
43
-
11
58
,
20
23
,
do
i:
10
.1
03
8/
s
41
59
2
-
0
23
-
0
19
32
-
w.
[
21]
A
.
R
a
v
i
e
t
al
.
,
“
G
e
n
o
mi
c
a
nd
tr
a
ns
c
r
ip
t
o
mi
c
a
na
l
y
s
is
of
c
he
c
k
po
in
t
b
l
o
c
ka
d
e
r
e
s
p
o
ns
e
in
a
dv
a
n
c
e
d
n
o
n
-
s
ma
ll
c
e
ll
lu
ng
c
a
n
c
e
r
,”
N
at
ur
e
ge
ne
ti
c
s
,
v
o
l.
55, n
o
. 5, pp. 807
-
819, 2023,
d
o
i:
10.1038
/s
41588
-
023
-
01355
-
5.
[
22]
X
.
H
u,
Z
.
Z
e
ng,
J
.
Z
ha
ng,
D
.
W
u,
H
.
L
i,
a
nd
F
.
G
e
ng,
“
M
ol
e
c
ul
a
r
d
y
na
mi
c
s
s
im
ul
a
ti
o
n
of
th
e
in
te
r
a
c
ti
o
n
of
f
oo
d
pr
ot
e
in
s
w
it
h
s
ma
ll
mo
l
e
c
u
le
s
,”
F
ood C
he
m
is
tr
y
,
v
ol
. 405, n
o
.1, pp. 134824
-
134838, 2023, do
i:
10.1016/j
.
f
ood
c
he
m.2022.134824.
[
23]
J
.
H
ua
ng
e
t
al
.
,
“
I
d
e
nt
i
f
ic
a
ti
o
n
of
a
di
s
ul
f
id
pt
o
s
is
-
r
e
la
t
e
d
g
e
n
e
s
s
ig
na
tu
r
e
f
or
p
r
o
gn
o
s
ti
c
i
mpl
i
c
a
ti
o
n
in
lu
ng
a
de
n
oc
a
r
c
in
oma
,”
C
om
put
e
r
s
i
n B
io
lo
gy
and M
e
di
c
in
e
,
v
o
l.
165, n
o
.1, pp. 107402
-
107423
, 2023, do
i
:
10.1016/j
.
c
o
mpbi
o
m
e
d.2023.107402.
[
24]
L
.
M
a
nga
na
r
o
e
t
al
.
,
“
C
o
ns
e
ns
us
c
lu
s
t
e
r
in
g
m
e
th
o
d
o
l
o
g
y
t
o
im
pr
ov
e
m
ol
e
c
ul
a
r
s
tr
a
ti
f
ic
a
ti
o
n
of
n
o
n
-
s
ma
ll
c
e
l
l
lu
ng
c
a
nc
e
r
,”
Sc
ie
nt
if
ic
R
e
por
t
s
,
v
o
l.
13, n
o
. 1, pp. 7759
-
7772, 2023, d
o
i:
10.
1038/s
41598
-
023
-
33954
-
x.
[
25]
M.
S
.
H
us
s
a
in
e
t
al
.
,
“
L
o
ng
n
o
n
-
c
o
di
ng
R
N
A
s
in
lu
ng
c
a
n
c
e
r
:
U
n
r
a
ve
li
ng
th
e
m
o
le
c
ul
a
r
m
o
dul
a
t
o
r
s
of
M
A
P
K
s
ig
na
li
ng,”
P
a
th
ol
ogy
-
R
e
s
e
ar
c
h and P
r
ac
ti
c
e
,
vo
l.
249, n
o
. 1, pp. 154738
-
154750, 2023, do
i:
10.1016/j
.p
r
p.2023.154738.
B
I
OG
RA
P
HI
E
S
OF
AU
T
HO
RS
Bi
n
e
e
s
h
M
o
o
z
h
i
ppu
r
a
th
i
s
c
u
rre
n
t
l
y
p
u
r
s
u
i
n
g
a
Ph
.
D
.
i
n
t
h
e
d
e
p
ar
t
m
e
n
t
o
f
c
o
m
p
u
t
e
r
s
c
i
e
n
ce
an
d
e
n
g
i
n
e
e
ri
n
g
a
t
Ch
ri
s
t
U
n
i
v
e
r
s
i
t
y
,
B
an
g
al
o
re
,
fo
c
u
s
i
n
g
o
n
c
an
c
e
r
p
re
d
i
c
t
i
o
n
u
s
i
n
g
m
e
t
a
b
o
l
o
m
i
c
s
&
m
ac
h
i
n
e
l
e
a
rn
i
n
g
.
H
e
c
o
m
p
l
e
t
e
d
h
i
s
M.
E
.
(
c
o
m
p
u
t
e
r
an
d
c
o
mm
u
n
i
c
at
i
o
n
)
f
ro
m
A
n
n
a
U
n
i
v
e
r
s
i
t
y
,
T
am
i
l
N
ad
u
i
n
2
0
1
1
.
Bi
n
e
e
s
h
h
o
l
d
s
a
b
ac
h
e
l
o
r'
s
d
e
g
re
e
i
n
I
n
fo
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(B
.
T
e
c
h
.
)
f
ro
m
Co
c
h
i
n
U
n
i
v
e
r
s
i
t
y
o
f
Sc
i
e
n
ce
an
d
T
e
c
h
n
o
l
o
g
y
,
K
e
ral
a
i
n
2
0
0
6
.
H
i
s
re
s
e
a
rc
h
i
n
t
e
re
s
t
s
i
n
c
l
u
d
e
m
ac
h
i
n
e
l
e
arn
i
n
g
,
g
r
a
p
h
n
e
u
ral
n
e
t
w
o
rk
s
,
an
d
m
e
t
a
b
o
l
o
m
i
c
s
.
H
e
c
an
b
e
c
o
n
t
ac
t
e
d
a
t
e
m
ai
l
:
b
i
n
e
e
s
h
.
m
@
re
s
.
c
h
ri
s
t
u
n
i
v
e
r
s
i
t
y
.
i
n
.
J
a
y
a
pa
n
di
a
n
N
a
ta
ra
j
a
n
i
s
cu
rr
e
n
t
l
y
w
o
rk
i
n
g
a
s
as
s
o
c
i
at
e
p
ro
f
e
s
s
o
r
i
n
t
h
e
d
e
p
art
men
t
o
f
c
o
m
p
u
t
e
r
s
c
i
en
ce
a
n
d
e
n
g
i
n
ee
ri
n
g
at
Ch
ri
s
t
U
n
i
v
e
rs
i
t
y
,
Ba
n
g
a
l
o
r
e
.
H
e
h
as
rece
i
v
e
d
h
i
s
Ph
.
D
.
fro
m
A
n
n
a
U
n
i
v
e
rs
i
t
y
,
Ch
e
n
n
ai
.
H
e
i
s
a
c
t
i
v
e
l
i
f
e
m
em
b
e
r
o
f
I
ST
E
.
H
e
i
s
c
u
rr
en
t
l
y
d
o
i
n
g
h
i
s
re
s
e
arch
i
n
m
a
c
h
i
n
e
l
e
ar
n
i
n
g
a
n
d
c
l
o
u
d
c
o
m
p
u
t
i
n
g
.
In
h
i
s
1
5
y
e
ars
o
f
t
e
ach
i
n
g
e
x
p
e
ri
en
ce
a
n
d
o
n
e
y
e
ar
o
f
i
n
d
u
s
t
ry
e
x
p
e
r
i
en
ce
.
H
i
s
r
e
s
e
ar
ch
i
n
t
e
r
e
s
t
s
are
g
ri
d
c
o
m
p
u
t
i
n
g
a
n
d
c
l
o
u
d
c
o
m
p
u
t
i
n
g
.
H
e
h
as
p
u
b
l
i
s
h
e
d
i
n
4
b
o
o
k
c
h
ap
t
e
rs
,
3
5
I
n
t
e
r
n
at
i
o
n
al
J
o
u
rn
a
l
art
i
c
l
e
s
,
1
0
0
i
n
t
e
r
n
at
i
o
n
al
a
n
d
N
at
i
o
n
al
C
o
n
f
e
r
en
ce
s
.
H
e
c
a
n
b
e
co
n
t
a
c
t
ed
at
em
a
i
l
:
j
a
y
ap
an
d
i
an
.
n
@
c
h
r
i
s
t
u
n
i
v
e
rs
i
t
y
.
i
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.