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.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
,
p
p
.
4
1
6
~
4
2
4
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
7
.
i
1
.
pp
4
1
6
-
4
2
4
416
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Lung
ca
ncer d
ete
ction using
hybri
d int
eg
ra
tion o
f
a
utoenco
der
feature
extractio
n
a
nd ML
te
chniq
ues
Annem
needi
L
a
k
s
hm
a
na
ra
o
1
,
Nirm
a
l G
o
pa
l
2
,
N
a
g
a
g
o
pira
j
u Vulla
m
3
,
M
a
nd
a
pa
t
i
Sridh
a
r
4
,
M
o
da
la
v
a
la
s
a
K
rish
na
K
a
nt
h
5
,
Um
a
M
a
hes
wa
ri
Ra
y
ud
u
6
1
D
e
p
a
r
t
me
n
t
o
f
I
T,
A
d
i
t
y
a
U
n
i
v
e
r
s
i
t
y
,
S
u
r
a
m
p
a
l
e
m
,
I
n
d
i
a
2
D
a
t
a
S
c
i
e
n
t
i
st
,
A
I
a
n
d
D
a
t
a
S
c
i
e
n
c
e
D
e
p
a
r
t
me
n
t
,
C
h
e
n
n
a
i
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
C
S
E
,
C
h
a
l
a
p
a
t
h
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
,
G
u
n
t
u
r
,
I
n
d
i
a
4
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
A
p
p
l
i
c
a
t
i
o
n
s,
R
.
V
.
R
.
a
n
d
J.
C
.
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
,
G
u
n
t
u
r
,
I
n
d
i
a
5
D
e
p
a
r
t
me
n
t
o
f
C
S
E
-
C
y
b
e
r
S
e
c
u
r
i
t
y
,
M
a
l
l
a
R
e
d
d
y
E
n
g
i
n
e
e
r
i
n
g
C
o
l
l
e
g
e
,
H
y
d
e
r
a
b
a
d
,
I
n
d
i
a
6
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
K
o
n
e
r
u
L
a
k
sh
m
a
i
a
h
E
d
u
c
a
t
i
o
n
F
o
u
n
d
a
t
i
o
n
,
G
u
n
t
u
r
,
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
Mar
10
,
2
0
2
4
R
ev
is
ed
Sep
4
,
202
4
Acc
ep
ted
Sep
29
,
2
0
2
4
Lu
n
g
c
a
n
c
e
r
p
o
se
d
a
si
g
n
ifi
c
a
n
t
g
lo
b
a
l
h
e
a
lt
h
c
h
a
ll
e
n
g
e
,
n
e
c
e
ss
it
a
ti
n
g
in
n
o
v
a
ti
v
e
a
p
p
ro
a
c
h
e
s
f
o
r
e
a
rly
d
e
tec
ti
o
n
a
n
d
a
c
c
u
ra
te
d
iag
n
o
s
is.
In
th
is
p
a
p
e
r,
CT
sc
a
n
ima
g
e
s
fo
r
l
u
n
g
c
a
n
c
e
r
with
t
h
re
e
c
las
se
s
n
a
m
e
ly
b
e
n
ig
n
,
m
a
li
g
n
a
n
t,
a
n
d
n
o
rm
a
l
a
re
c
o
ll
e
c
ted
fro
m
Ka
g
g
le.
We
in
it
iall
y
a
p
p
li
e
d
c
o
n
v
e
n
ti
o
n
a
l
m
a
c
h
in
e
lea
rn
i
n
g
(
ML
)
a
lg
o
rit
h
m
s
i
n
c
lu
d
in
g
su
p
p
o
rt
v
e
c
t
o
r
m
a
c
h
in
e
(
S
VM
)
,
ra
n
d
o
m
fo
re
sts
(RF
)
,
d
e
c
isio
n
tree
s
(DT)
,
lo
g
isti
c
re
g
re
ss
io
n
(LR)
,
n
a
i
v
e
b
a
y
e
s
(NB)
,
a
n
d
k
-
n
e
a
re
st
n
e
ig
h
b
o
r
fo
r
l
u
n
g
c
a
n
c
e
r
d
e
tec
ti
o
n
.
Th
e
re
su
l
ts
with
th
e
se
c
o
n
v
e
n
ti
o
n
a
l
a
lg
o
r
it
h
m
s
a
re
re
c
o
rd
e
d
.
Late
r,
we
p
ro
p
o
se
d
a
n
o
v
e
l
h
y
b
rid
m
o
d
e
l
t
h
a
t
in
te
g
ra
ted
d
i
v
e
rse
m
a
c
h
in
e
lea
rn
in
g
a
lg
o
r
it
h
m
s
t
o
fu
r
th
e
r
e
n
h
a
n
c
e
a
c
c
u
ra
c
y
.
Ou
r
a
p
p
r
o
a
c
h
c
o
m
b
in
e
d
th
e
p
o
we
r
o
f
a
u
to
e
n
c
o
d
e
rs
f
o
r
fe
a
tu
r
e
e
x
trac
ti
o
n
.
Us
in
g
Au
to
e
n
c
o
d
e
r
tec
h
n
iq
u
e
,
fe
a
tu
re
s fro
m
ima
g
e
s a
r
e
e
x
trac
te
d
a
n
d
a
n
e
w fea
tu
re
v
e
c
to
r
is cre
a
ted
.
Late
r,
th
e
sa
m
e
c
o
n
v
e
n
ti
o
n
a
l
M
L
c
l
a
ss
ifi
e
rs
a
p
p
li
e
d
a
n
d
a
c
h
iev
e
d
e
n
h
a
n
c
e
d
p
e
rfo
rm
a
n
c
e
.
T
h
e
h
y
b
rid
m
o
d
e
l
d
e
m
o
n
stra
ted
re
m
a
rk
a
b
le
p
e
rfo
rm
a
n
c
e
i
n
id
e
n
ti
f
y
in
g
lu
n
g
c
a
n
c
e
r
c
a
se
s
wh
e
n
c
o
m
p
a
re
d
to
i
n
d
iv
i
d
u
a
l
c
las
sifiers
.
Th
ro
u
g
h
e
x
ten
si
v
e
e
x
p
e
rime
n
tat
io
n
,
we
sh
o
wc
a
se
d
th
e
e
ffica
c
y
o
f
o
u
r
in
teg
ra
ted
fra
m
e
wo
rk
,
a
c
h
iev
i
n
g
h
i
g
h
a
c
c
u
ra
c
y
,
p
re
c
isio
n
,
r
e
c
a
ll
a
n
d
F1
-
sc
o
re
m
e
tri
c
s
a
c
ro
ss
m
u
lt
ip
le
c
las
sifiers
.
Th
is
h
y
b
ri
d
a
p
p
r
o
a
c
h
re
p
re
se
n
ted
a
sig
n
if
ica
n
t
a
d
v
a
n
c
e
m
e
n
t
in
lu
n
g
c
a
n
c
e
r
d
e
tec
ti
o
n
,
o
ffe
rin
g
a
v
e
rsa
ti
le
a
n
d
ro
b
u
st
s
o
lu
t
io
n
fo
r
e
a
rly
d
iag
n
o
sis
a
n
d
p
e
rso
n
a
li
z
e
d
trea
tme
n
t
stra
teg
ies
in
c
li
n
ica
l
se
tt
in
g
s.
K
ey
w
o
r
d
s
:
Au
to
en
co
d
e
r
Featu
r
e
ex
tr
ac
tio
n
Kag
g
le
L
u
n
g
ca
n
ce
r
ML
tech
n
iq
u
es
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
:
An
n
em
n
ee
d
i L
a
k
s
h
m
an
ar
a
o
Dep
ar
tm
en
t
of
IT,
Ad
ity
a
Un
i
v
er
s
ity
Su
r
am
p
alem
,
I
n
d
ia
E
m
ail:
lax
m
an
1
2
1
6
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
L
u
n
g
ca
n
ce
r
p
lace
s
a
h
ea
v
y
s
tr
ain
o
n
co
m
m
u
n
ities
an
d
p
u
b
li
c
h
ea
lth
s
y
s
tem
s
.
I
m
ag
es f
r
o
m
C
T
s
ca
n
s
h
av
e
b
ec
o
m
e
an
im
p
o
r
tan
t
r
eso
u
r
ce
f
o
r
id
en
tify
in
g
a
n
d
ca
teg
o
r
izin
g
lu
n
g
ca
n
ce
r
b
ec
au
s
e
th
ey
p
r
o
v
id
e
co
m
p
r
eh
e
n
s
iv
e
in
f
o
r
m
atio
n
o
n
p
u
lm
o
n
ar
y
a
b
n
o
r
m
alities
.
Du
e
to
th
eir
p
r
ec
is
e
v
iews
o
f
th
e
lu
n
g
s
an
d
ass
o
ciate
d
tis
s
u
es,
C
T
s
ca
n
s
a
r
e
u
s
ef
u
l
f
o
r
lu
n
g
ca
n
ce
r
s
cr
ee
n
in
g
.
Hig
h
-
r
eso
lu
tio
n
C
T
s
ca
n
s
m
ay
d
etec
t
lu
n
g
ca
n
ce
r
n
o
d
u
les
an
d
m
ass
es.
T
o
ac
q
u
ir
e
tis
s
u
e
s
am
p
les
f
o
r
p
ath
o
lo
g
y
,
C
T
im
a
g
es
h
elp
g
u
i
d
e
b
io
p
s
y
n
ee
d
les.
T
h
is
h
elp
s
co
n
f
ir
m
lu
n
g
ca
n
c
er
d
iag
n
o
s
is
an
d
id
en
tify
its
f
ea
tu
r
es
f
o
r
th
er
ap
y
p
la
n
n
in
g
.
I
n
th
is
p
ap
er
,
lu
n
g
ca
n
ce
r
C
T
s
ca
n
im
ag
es
ar
e
co
llected
f
r
o
m
Kag
g
le,
ca
teg
o
r
ized
th
em
in
to
b
en
ig
n
,
m
ali
g
n
an
t,
an
d
n
o
r
m
al
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
Lu
n
g
ca
n
ce
r
d
etec
tio
n
u
s
in
g
h
yb
r
id
in
teg
r
a
tio
n
o
f
a
u
to
e
n
co
d
er
…
(
A
n
n
emn
ee
d
i La
ksh
ma
n
a
r
a
o
)
417
class
es.
I
n
itial
ly
,
we
u
s
ed
tr
ad
itio
n
al
m
ac
h
in
e
lea
r
n
i
n
g
alg
o
r
ith
m
s
f
o
r
d
etec
tio
n
,
th
en
in
tr
o
d
u
ce
d
a
h
y
b
r
id
m
o
d
el
co
m
b
in
in
g
v
ar
io
u
s
M
L
alg
o
r
ith
m
s
an
d
au
t
o
en
co
d
e
r
s
f
o
r
f
ea
t
u
r
e
ex
t
r
ac
tio
n
.
T
h
i
s
ap
p
r
o
ac
h
y
ield
ed
s
u
p
er
io
r
p
er
f
o
r
m
a
n
ce
in
id
en
t
if
y
in
g
lu
n
g
ca
n
ce
r
ca
s
es
co
m
p
ar
ed
to
in
d
i
v
id
u
al
class
if
ier
s
,
s
h
o
wca
s
i
n
g
h
ig
h
ac
cu
r
ac
y
an
d
o
f
f
er
in
g
a
s
ig
n
if
i
ca
n
t le
ap
f
o
r
war
d
in
ea
r
ly
d
ia
g
n
o
s
is
an
d
tr
ea
tm
en
t stra
teg
ies.
R
aja
et
a
l.
[
1
]
p
r
esen
ted
a
lu
n
g
C
T
s
ca
n
-
b
ased
lu
n
g
ca
n
ce
r
d
etec
tio
n
s
y
s
tem
.
L
u
n
g
ca
n
ce
r
d
etec
tio
n
m
o
d
u
le
u
s
ed
T
r
a
n
s
f
er
L
ea
r
n
i
n
g
with
Ad
aDe
n
s
eNe
t
an
d
Pro
x
-
SMOT
E
to
b
o
o
s
t
ac
cu
r
ac
y
.
VGG
-
1
6
ex
tr
ac
ted
f
ea
tu
r
es
an
d
an
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
in
e
(
SVM
)
class
if
ier
class
if
ied
th
em
in
th
e
ca
r
d
i
o
-
v
ascu
lar
d
is
ea
s
es
(
C
VD
)
p
r
ed
ictio
n
m
o
d
u
le.
W
e
f
o
u
n
d
th
at
lu
n
g
ca
n
ce
r
an
d
C
VD
ar
e
in
ter
d
e
p
en
d
e
n
t
,
with
lu
n
g
ca
n
ce
r
d
etec
tio
n
ac
cu
r
ac
y
o
f
9
8
.
2
8
%
an
d
C
VD
p
r
ed
ictio
n
ac
cu
r
ac
y
o
f
9
1
%.
Sait
[
2
]
cr
ea
ted
a
c
o
n
v
o
lu
ti
o
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN
)
m
o
d
el
with
Den
s
eNe
t
-
1
2
1
f
ea
t
u
r
e
e
x
tr
ac
t
io
n
an
d
d
ee
p
a
u
to
en
c
o
d
er
s
f
o
r
d
i
m
e
n
s
io
n
ality
r
ed
u
ctio
n
.
Mo
b
ileNet
V3
-
Sm
all
r
ec
o
g
n
ized
lu
n
g
ca
n
ce
r
k
in
d
s
f
r
o
m
th
ese
ch
ar
ac
ter
is
tics
.
Q
u
an
tizatio
n
-
awa
r
e
tr
ain
in
g
an
d
ea
r
ly
h
altin
g
r
e
d
u
ce
d
p
r
o
ce
s
s
in
g
p
o
wer
a
n
d
e
n
h
an
ce
d
a
cc
u
r
ac
y
.
Alq
ah
tan
i
et
a
l.
[
3
]
i
n
tr
o
d
u
ce
d
th
e
im
p
r
o
v
ed
wate
r
s
tr
id
e
r
a
lg
o
r
ith
m
with
a
u
to
en
co
d
er
.
I
t
aim
ed
to
d
etec
t
l
u
n
g
ca
n
ce
r
,
u
tili
zin
g
m
e
d
ian
f
ilter
in
g
(
MF)
f
o
r
n
o
is
e
r
e
m
o
v
al
an
d
Mo
b
ileNetv
2
as
a
f
ea
tu
r
e
ex
tr
ac
to
r
with
I
W
SA
-
b
ased
h
y
p
er
p
a
r
am
eter
o
p
tim
izatio
n
.
T
h
e
tec
h
n
iq
u
e
,
em
p
lo
y
in
g
a
co
n
v
o
lu
tio
n
a
l
au
to
en
co
d
e
r
(
C
AE
)
,
d
em
o
n
s
tr
ated
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
t
h
r
o
u
g
h
s
im
u
lati
o
n
s
co
m
p
a
r
ed
t
o
alter
n
ativ
e
ap
p
r
o
ac
h
es.
Gao
et
a
l.
[
4
]
e
x
p
lo
r
ed
v
ar
i
o
u
s
AI
tech
n
iq
u
es
f
o
r
lu
n
g
ca
n
ce
r
d
etec
tio
n
.
T
h
e
au
t
h
o
r
s
cla
im
ed
th
at
aI
tech
n
iq
u
es
o
v
er
co
m
es
tr
ad
itio
n
al
ap
p
r
o
ac
h
es f
o
r
l
u
n
g
ca
n
ce
r
d
et
ec
tio
n
.
J
awa
id
et
a
l.
[
5
]
u
s
ed
im
a
g
e
p
r
o
ce
s
s
in
g
,
s
eg
m
en
tatio
n
,
an
d
ca
n
ce
r
s
tag
in
g
t
o
id
en
tif
y
lu
n
g
ca
n
ce
r
in
C
T
im
ag
es.
I
t
s
im
p
lifie
d
d
iag
n
o
s
tics
with
9
6
.
5
%
ac
cu
r
ac
y
an
d
ea
r
ly
d
etec
tio
n
u
s
in
g
An
d
r
o
id
d
ev
ices
an
d
a
n
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN
)
.
R
ao
a
n
d
Ar
s
h
ad
et
a
l.
[
6
]
s
u
g
g
ested
a
n
eu
r
al
n
etwo
r
k
f
o
r
im
a
g
e
c
o
llectin
g
,
p
r
ep
r
o
ce
s
s
in
g
,
p
ix
el
en
h
an
ce
m
en
t,
s
eg
m
en
tatio
n
,
an
d
f
ea
t
u
r
e
ex
tr
ac
tio
n
.
Ma
ch
i
n
e
lear
n
in
g
is
ess
en
tial
f
o
r
ac
cu
r
ate
an
d
co
s
t
-
ef
f
ec
tiv
e
lu
n
g
ca
n
ce
r
d
iag
n
o
s
is
an
d
tr
ea
tm
en
t,
ac
co
r
d
in
g
to
cu
r
r
en
t
s
tu
d
ies.
Gu
p
ta
an
d
Dawn
[
7
]
p
r
o
p
o
s
ed
a
C
NN
-
b
ased
lu
n
g
C
T
s
ca
n
ca
n
ce
r
p
r
e
d
ictio
n
an
d
class
if
icatio
n
m
et
h
o
d
.
Au
g
m
en
tatio
n
co
r
r
ec
ted
class
im
b
alan
ce
af
ter
p
ictu
r
e
p
r
ep
r
o
ce
s
s
in
g
an
d
r
esizin
g
.
Ma
h
u
m
an
d
Salm
an
et
a
l
.
[
8
]
s
u
g
g
ested
L
u
n
g
-
R
etin
aNe
t
,
an
ef
f
ec
tiv
e
R
etin
aNe
t
-
b
ased
lu
n
g
tu
m
o
r
d
etec
to
r
.
T
o
en
h
an
ce
tu
m
o
u
r
lo
ca
lizatio
n
,
it
u
s
ed
a
m
u
lti
-
s
ca
le
f
ea
tu
r
e
f
u
s
io
n
m
o
d
u
le
a
n
d
a
d
ilated
an
d
lig
h
tweig
h
t
co
n
tex
t
ap
p
r
o
ac
h
.
T
h
e
tec
h
n
iq
u
e
o
u
tp
er
f
o
r
m
ed
o
t
h
er
s
m
o
d
els
.
B
h
ar
ath
y
et
a
l
.
[
9
]
tr
ain
e
d
t
h
e
d
atase
t
u
s
in
g
s
u
p
p
o
r
t
v
ec
to
r
cl
ass
if
icatio
n
(
SVC
)
,
k
-
n
ea
r
est n
eig
h
b
o
r
(
KNN
)
,
d
e
cisi
o
n
tr
ee
,
lo
g
is
tic
r
eg
r
ess
io
n
(
L
R
)
,
an
d
r
an
d
o
m
f
o
r
es
t
(
R
F)
.
T
h
e
m
o
s
t a
cc
u
r
ate
alg
o
r
ith
m
was
RF
,
with
8
8
.
5
%
p
er
f
o
r
m
a
n
ce
.
Ku
m
a
r
i
et
a
l
.
[
1
0
]
r
ec
o
m
m
en
d
e
d
p
r
ec
e
d
e
n
ce
-
b
ased
m
ac
h
i
n
e
lear
n
in
g
m
eth
o
d
s
f
o
r
ce
r
v
ical
an
d
b
r
ea
s
t
ca
n
ce
r
p
r
e
d
ictio
n
.
Af
ter
tr
ain
in
g
th
e
f
u
n
d
am
en
t
al
m
o
d
els,
r
an
k
in
g
-
b
ased
m
eth
o
d
s
p
r
e
d
icted
ac
cu
r
ac
y
.
E
x
p
e
r
im
en
tal
f
i
n
d
in
g
s
o
n
two
d
atasets
s
h
o
wed
th
at
th
e
s
u
g
g
ested
f
r
am
ewo
r
k
d
etec
ted
ca
n
c
er
ac
cu
r
ately
.
C
o
m
p
u
ter
v
is
io
n
a
nd
d
ee
p
lea
r
n
in
g
(
DL
)
,
esp
ec
ially
s
ec
o
n
d
-
an
d
th
ir
d
-
n
eu
r
al
n
etwo
r
k
co
n
v
er
g
e
n
ce
,
wer
e
u
s
ed
in
[
1
1
]
.
E
ac
h
s
ite
h
ad
to
elim
in
ate
g
ab
o
r
f
ilter
-
in
d
u
ce
d
wh
ite
g
au
s
s
ian
s
ca
n
im
ag
e
n
o
is
e
an
d
p
h
ase
th
e
r
esp
ir
ato
r
y
o
r
g
a
n
u
s
in
g
tw
in
tr
ee
co
m
p
le
x
m
o
v
in
g
r
i
d
g
e
r
ewo
r
k
d
u
al
-
tr
ee
co
m
p
lex
wa
v
elet
tr
an
s
f
o
r
m
a
n
d
d
is
cr
ete
co
s
in
e
tr
an
s
f
o
r
m
(
DT
C
W
T
)
tech
n
o
lo
g
y
.
SVM
f
o
u
n
d
s
ev
er
al
q
u
ality
ch
a
r
ac
ter
is
tics
in
th
i
s
ar
ticle.
L
ak
s
h
m
an
ar
a
o
et
a
l.
[
1
2
]
s
u
g
g
ested
an
ML
-
b
ased
f
u
s
io
n
class
if
ier
m
o
d
el.
Fo
llo
win
g
b
ase
-
lev
el
m
o
d
el
tr
ain
in
g
,
r
an
k
in
g
-
b
ased
alg
o
r
ith
m
s
p
r
ed
icted
ac
cu
r
ac
y
.
T
h
e
s
u
g
g
ested
a
p
p
r
o
ac
h
was
ev
a
lu
ated
o
n
UC
I
a
nd
Kag
g
le
ca
n
ce
r
d
atasets
.
T
h
e
s
u
g
g
ested
ap
p
r
o
ac
h
w
o
r
k
e
d
o
n
th
ese
d
atasets
.
M
L
was
u
s
ed
to
cr
ea
te
ef
f
ec
tiv
e
lu
n
g
ca
n
ce
r
r
is
k
ass
ess
m
en
t
m
o
d
els
in
[
1
3
]
.
T
h
e
r
o
tatio
n
f
o
r
est
tech
n
iq
u
e
p
er
f
o
r
m
ed
well
i
n
p
r
ec
is
io
n
,
r
ec
all,
f
-
m
ea
s
u
r
e
,
ac
cu
r
ac
y
,
an
d
AUC.
T
h
e
m
o
d
el
p
er
f
o
r
m
e
d
well
in
ex
p
er
im
en
ts
,
with
an
A
UC
o
f
9
9
.
3
%
an
d
ac
cu
r
ac
y
o
f
9
7
.
1
%.
Pan
d
ian
et
a
l.
[
1
4
]
p
r
esen
ted
a
tech
n
iq
u
e
to
id
en
tify
ab
er
r
a
n
t
lu
n
g
tis
s
u
e
d
ev
elo
p
m
e
n
t
b
u
t
s
tr
ess
ed
th
e
r
eq
u
ir
em
en
t
f
o
r
h
ig
h
ac
cu
r
ac
y
to
r
e
d
u
ce
m
is
d
iag
n
o
s
is
.
An
aly
zin
g
h
ea
lth
y
a
n
d
m
alig
n
a
n
t
lu
n
g
p
ictu
r
es,
d
atab
ases
f
o
r
d
if
f
er
e
n
t
C
T
s
ca
n
n
in
g
s
y
s
tem
p
er
s
p
ec
tiv
es
wer
e
cr
ea
ted
.
A
n
e
u
r
a
l
n
etwo
r
k
class
if
ied
n
o
r
m
al
an
d
ca
n
ce
r
o
u
s
p
ictu
r
es
u
s
in
g
im
a
g
e
te
x
tu
r
al
p
r
o
p
er
ties
.
L
alith
a
[
1
5
]
in
t
r
o
d
u
ce
d
a
ML
-
b
ased
au
to
m
ated
lu
n
g
ca
n
ce
r
d
etec
t
io
n
s
y
s
tem
th
at
ca
n
d
is
tin
g
u
is
h
b
en
ig
n
,
ag
g
r
ess
iv
e,
an
d
n
o
r
m
al
lu
n
g
ca
n
ce
r
s
.
T
h
e
s
u
g
g
ested
l
u
n
g
ca
n
ce
r
d
e
tectio
n
tech
n
iq
u
e
o
u
tp
er
f
o
r
m
e
d
th
e
o
t
h
er
s
with
o
v
er
9
5
%
a
cc
u
r
ac
y
.
T
h
e
s
tu
d
y
aim
ed
to
d
etec
t
ea
r
ly
-
s
tag
e
l
u
n
g
ca
n
ce
r
u
s
in
g
m
ac
h
i
n
e
le
ar
n
in
g
m
eth
o
d
s
.
I
t
s
o
u
g
h
t
to
ass
ess
m
o
r
e
ca
s
es
ef
f
icien
tly
,
ac
h
ie
v
in
g
r
esu
lts
co
m
p
ar
ab
le
to
o
r
f
aster
th
an
h
u
m
a
n
ex
p
er
ts
.
Nin
e
d
if
f
er
e
n
t
alg
o
r
ith
m
s
wer
e
u
tili
ze
d
in
th
e
d
ev
elo
p
e
d
m
o
d
el
(
n
aiv
e
b
ay
es
(
NB
)
,
L
R
,
d
ec
is
io
n
tr
ee
s
(
DT
)
,
R
F,
g
r
ad
ien
t
b
o
o
s
t
(
GB
)
,
an
d
SVM)
,
an
d
th
eir
s
u
cc
ess
was
ev
alu
ated
b
ased
o
n
ac
cu
r
ac
y
,
s
en
s
itiv
ity
,
an
d
p
r
ec
is
io
n
m
etr
ics.
T
h
e
r
e
s
u
lts
d
em
o
n
s
tr
ated
a
m
ax
im
u
m
ac
c
u
r
ac
y
o
f
9
1
% in
ca
n
ce
r
d
etec
tio
n
.
Dir
ik
[
1
6
]
aim
ed
to
d
e
v
elo
p
an
au
to
m
ated
m
o
d
el
f
o
r
ea
r
ly
-
s
tag
e
lu
n
g
ca
n
ce
r
d
etec
tio
n
u
s
in
g
n
in
e
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
(
NB
,
L
R
,
DT
,
R
F,
GB
,
an
d
SVM)
.
T
h
e
m
o
d
el
’
s
s
u
cc
ess
was
ev
alu
ated
with
ac
cu
r
ac
y
,
s
en
s
itiv
ity
,
a
n
d
p
r
ec
is
io
n
m
etr
ics
f
r
o
m
th
e
co
n
f
u
s
i
o
n
m
atr
ix
.
T
h
e
r
esu
lts
s
h
o
wed
th
at
th
e
p
r
o
p
o
s
ed
m
o
d
el
d
etec
ted
ca
n
ce
r
with
a
m
ax
im
u
m
ac
cu
r
ac
y
o
f
9
1
%.
Naz
ir
et
a
l.
[
1
7
]
,
DL
an
d
ML
ac
ce
ler
ated
ca
n
ce
r
d
iag
n
o
s
is
an
d
s
tag
e
ca
teg
o
r
iz
atio
n
.
T
h
is
wo
r
k
v
alid
ate
d
with
PC
A
an
d
d
is
cr
ete
wav
elet
tr
an
s
f
o
r
m
f
o
r
im
ag
e
f
u
s
io
n
u
s
in
g
m
u
ltire
s
o
lu
tio
n
r
i
g
id
r
eg
is
tr
atio
n
an
d
im
a
g
e
s
eg
m
en
tatio
n
.
Mish
r
a
an
d
Gan
g
war
[
1
8
]
,
SVM,
LR
,
ANN,
an
d
NB
wer
e
u
tili
ze
d
t
o
s
tu
d
y
an
d
p
r
o
g
n
o
s
e
l
u
n
g
ca
n
ce
r
.
T
h
is
ar
ticle
u
s
ed
s
u
r
v
e
y
d
ata
a
n
d
m
ac
h
in
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
:
4
1
6
-
4
2
4
418
lear
n
in
g
alg
o
r
ith
m
s
lik
e
SV
M
,
NB
,
KNN
etc.
to
p
r
ed
ict
lu
n
g
ca
n
ce
r
.
Ab
d
u
llah
et
a
l.
[
1
9
]
e
v
alu
ated
t
h
r
ee
class
if
ier
s
SVM,
KNN,
an
d
ANN
b
y
d
etec
tin
g
ea
r
ly
-
s
tag
e
lu
n
g
ca
n
ce
r
.
Usi
n
g
UC
I
d
atasets
,
th
e
s
tu
d
y
ex
am
in
ed
class
if
icatio
n
alg
o
r
ith
m
s
’
ac
cu
r
ac
y
u
s
in
g
W
E
KA.
SVM
h
as
th
e
h
ig
h
est
ac
cu
r
ac
y
(
9
5
.
5
6
%),
f
o
llo
wed
b
y
C
NN
(
9
2
%)
a
n
d
KNN
(
8
8
%).
h
y
b
r
i
d
m
eth
o
d
s
wer
e
u
s
ed
to
d
iag
n
o
s
e
lu
n
g
an
d
b
r
ea
s
t
ca
n
ce
r
b
ased
o
n
ce
ll
s
ize
an
d
s
h
ap
e
[
20]
.
T
h
e
y
i
n
tr
o
d
u
ce
d
b
r
ea
s
t
an
d
lu
n
g
ca
n
ce
r
b
lo
ck
d
iag
r
am
s
an
d
d
is
cu
s
s
ed
ca
n
ce
r
d
etec
tio
n
an
d
d
iag
n
o
s
tic
is
s
u
es a
n
d
p
r
o
s
p
ec
tiv
e
u
s
es.
Mo
h
am
ed
et
a
l.
[2
1
]
p
r
esen
te
d
a
C
NN
-
m
etah
eu
r
is
tic
h
y
b
r
i
d
.
A
C
NN
ar
ch
itectu
r
e
was
c
o
n
s
tr
u
cted
an
d
th
e
m
o
d
el
’
s
s
o
lu
tio
n
v
e
cto
r
ca
lcu
lated
.
T
h
is
s
o
lu
tio
n
v
ec
to
r
was
s
e
n
t
to
eb
o
la
o
p
tim
izatio
n
s
ea
r
ch
alg
o
r
ith
m
(
E
OSA
)
m
o
d
el
to
ch
o
o
s
e
th
e
o
p
tim
al
weig
h
ts
an
d
b
ias
f
o
r
C
NN
m
o
d
el
class
if
icatio
n
tr
ain
in
g
.
Sev
er
al
m
o
d
els
wer
e
test
ed
u
t
ilizin
g
ch
est
X
-
r
ay
s
o
r
C
T
s
c
an
s
to
d
iag
n
o
s
e
a
d
is
ea
s
e
[
2
2
]
.
T
h
e
s
tu
d
y
s
o
u
g
h
t
th
e
b
est
DL
lu
n
g
d
is
ea
s
e
p
r
ed
ictio
n
m
eth
o
d
s
.
T
h
e
ap
p
r
o
ac
h
was
ass
ess
ed
u
s
in
g
v
ar
io
u
s
m
etr
ices
.
His
to
p
ath
o
lo
g
ical
lu
n
g
ca
n
ce
r
tis
s
u
e
p
ictu
r
es
wer
e
u
tili
ze
d
to
tr
ain
d
ee
p
n
e
u
r
al
n
etwo
r
k
s
to
id
en
tify
lu
n
g
ca
n
ce
r
in
[
2
3
]
.
I
n
ce
p
tio
n
V
3
,
r
an
d
o
m
f
o
r
est
,
an
d
C
NN
wer
e
test
ed
f
o
r
a
u
to
m
ated
lu
n
g
ca
n
ce
r
ce
ll
id
en
tific
atio
n
.
T
r
ain
in
g
th
e
C
NN
to
ex
tr
ac
t
k
ey
ch
ar
ac
ter
is
t
ics
im
p
r
o
v
ed
lu
n
g
ca
n
ce
r
d
etec
tio
n
ef
f
icien
cy
an
d
ac
cu
r
ac
y
.
Na
d
k
ar
n
i
an
d
B
o
r
k
ar
[
2
4
]
d
e
m
o
n
s
tr
ated
au
to
m
at
ic
lu
n
g
ca
n
ce
r
d
etec
tio
n
with
C
T
s
ca
n
s
.
Me
d
ian
f
ilter
in
g
f
o
r
im
ag
e
p
r
ep
r
o
ce
s
s
in
g
an
d
m
ath
em
atica
l
m
o
r
p
h
o
l
o
g
ical
s
eg
m
en
tatio
n
o
f
th
e
lu
n
g
r
eg
io
n
o
f
in
ter
est
wer
e
u
s
ed
to
id
en
tify
lu
n
g
ca
n
ce
r
.
Kh
o
s
r
av
an
a
n
d
B
ag
ci
[
2
5
]
p
r
o
p
o
s
ed
a
3
D
d
ee
p
m
u
lti
-
task
C
NN
ac
h
iev
ed
9
1
% seg
m
en
tatio
n
ac
c
u
r
ac
y
a
n
d
9
2
% FP r
ed
u
ctio
n
o
n
th
e
L
UNA1
6
d
ataset.
2.
M
E
T
H
O
D
T
h
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
f
o
r
ca
n
ce
r
d
etec
tio
n
is
s
h
o
wn
in
Fig
u
r
e
1
.
A
h
y
b
r
id
lu
n
g
ca
n
ce
r
d
etec
tio
n
m
o
d
el
was
cr
ea
ted
u
s
in
g
tr
a
d
itio
n
al
ML
tech
n
iq
u
es
a
n
d
au
to
en
co
d
er
s
f
o
r
f
ea
tu
r
e
ex
t
r
ac
tio
n
.
T
h
e
d
ataset
in
clu
d
es Ka
g
g
le
C
T
s
ca
n
p
ictu
r
es c
lass
ed
as b
en
ig
n
,
m
alig
n
a
n
t,
an
d
n
o
r
m
al,
d
ep
ictin
g
lu
n
g
ca
n
ce
r
s
tag
es.
Fig
u
r
e
1
.
Pro
p
o
s
ed
ar
c
h
itectu
r
e
f
o
r
lu
n
g
ca
n
ce
r
d
etec
tio
n
I
n
itially
,
a
r
an
g
e
o
f
co
n
v
en
ti
o
n
al
ML
alg
o
r
ith
m
s
,
in
clu
d
i
n
g
SVM,
R
F,
DT
,
LR
,
NB
,
an
d
KNN
class
if
ier
s
,
wa
s
ap
p
lied
to
th
e
d
ataset.
T
h
e
r
esu
lts
o
b
tain
ed
f
r
o
m
th
ese
alg
o
r
ith
m
s
s
er
v
ed
as
a
b
aselin
e
f
o
r
co
m
p
ar
is
o
n
a
n
d
wer
e
m
eticu
lo
u
s
ly
r
ec
o
r
d
ed
f
o
r
s
u
b
s
eq
u
en
t
an
aly
s
is
.
Fo
llo
win
g
th
e
ev
al
u
atio
n
o
f
t
h
e
co
n
v
en
tio
n
al
al
g
o
r
ith
m
s
,
a
u
to
en
co
d
er
s
wer
e
in
tr
o
d
u
ce
d
f
o
r
f
ea
t
u
r
e
ex
tr
ac
tio
n
f
r
o
m
t
h
e
C
T
s
ca
n
im
ag
es.
Au
to
en
co
d
er
s
wer
e
e
m
p
lo
y
ed
to
ca
p
tu
r
e
laten
t
r
ep
r
esen
tatio
n
s
o
f
th
e
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
Lu
n
g
ca
n
ce
r
d
etec
tio
n
u
s
in
g
h
yb
r
id
in
teg
r
a
tio
n
o
f
a
u
to
e
n
co
d
er
…
(
A
n
n
emn
ee
d
i La
ksh
ma
n
a
r
a
o
)
419
in
p
u
t
d
ata,
g
en
e
r
atin
g
a
n
ew
f
ea
tu
r
e
v
ec
t
o
r
th
at
e
n
ca
p
s
u
lat
ed
th
e
s
alien
t
ch
ar
ac
te
r
is
tics
o
f
th
e
lu
n
g
ca
n
ce
r
im
ag
es.
Su
b
s
eq
u
e
n
tly
,
t
h
e
e
x
tr
ac
ted
f
ea
t
u
r
es
f
r
o
m
th
e
a
u
to
e
n
co
d
er
s
we
r
e
in
teg
r
ated
with
t
h
e
af
o
r
em
en
tio
n
ed
co
n
v
en
tio
n
al
m
ac
h
i
n
e
lear
n
i
n
g
class
if
ier
s
.
T
h
is
h
y
b
r
id
m
o
d
el
ar
c
h
itectu
r
e
was
d
esig
n
ed
to
h
ar
n
ess
th
e
s
tr
en
g
th
s
o
f
b
o
th
f
ea
t
u
r
e
ex
tr
ac
tio
n
th
r
o
u
g
h
au
to
e
n
co
d
e
r
s
an
d
th
e
p
r
ed
ictiv
e
ca
p
ab
ilit
ies
o
f
d
iv
er
s
e
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
.
T
h
e
h
y
b
r
id
m
o
d
el
was
th
en
tr
ain
ed
u
s
in
g
th
e
ex
tr
ac
te
d
f
e
atu
r
es
o
b
tain
ed
f
r
o
m
th
e
au
t
o
en
co
d
e
r
s
.
Fo
llo
win
g
tr
ain
in
g
,
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
h
y
b
r
id
m
o
d
el
w
as
ev
alu
ated
u
s
in
g
ap
p
r
o
p
r
iate
ev
alu
atio
n
m
etr
ics.
T
h
r
o
u
g
h
e
x
ten
s
iv
e
ex
p
er
im
en
tatio
n
an
d
v
alid
atio
n
o
n
i
n
d
e
p
en
d
en
t
test
s
ets,
th
e
ef
f
icac
y
o
f
t
h
e
in
teg
r
ated
f
r
am
ewo
r
k
was
d
em
o
n
s
tr
ated
.
T
h
e
p
er
f
o
r
m
an
ce
m
etr
ics
o
f
th
e
h
y
b
r
i
d
m
o
d
el
wer
e
c
o
m
p
ar
ed
with
th
o
s
e
o
b
tain
ed
f
r
o
m
i
n
d
iv
id
u
al
class
if
ier
s
,
s
h
o
wc
asin
g
its
s
u
p
er
io
r
ity
in
ac
h
iev
in
g
h
ig
h
ac
cu
r
ac
y
an
d
r
o
b
u
s
tn
ess
in
lu
n
g
ca
n
ce
r
d
etec
tio
n
.
T
h
is
h
y
b
r
id
ap
p
r
o
ac
h
r
e
p
r
esen
ted
a
s
ig
n
if
ican
t
ad
v
an
ce
m
en
t
in
e
ar
ly
d
iag
n
o
s
is
an
d
p
er
s
o
n
alize
d
tr
ea
tm
e
n
t
s
tr
ateg
ies
f
o
r
lu
n
g
ca
n
ce
r
,
o
f
f
er
in
g
a
v
er
s
atile
an
d
ef
f
ec
tiv
e
s
o
lu
tio
n
f
o
r
clin
ical
s
ettin
g
s
.
2
.
1
.
Da
t
a
s
et
A
Kag
g
le
d
ataset
[
26
]
was
co
llected
f
o
r
ex
p
e
r
im
en
tatio
n
.
I
t
co
n
tain
s
th
r
ee
class
es
o
f
im
ag
es
n
am
ely
b
en
ig
n
,
m
alig
n
a
n
t,
an
d
n
o
r
m
al
with
1
2
0
,
5
6
1
a
n
d
4
1
6
im
ag
es
Her
e,
“
b
e
n
ig
n
”
r
ef
er
s
to
n
o
n
-
ca
n
ce
r
o
u
s
ab
n
o
r
m
alities
o
r
g
r
o
wth
s
,
“
m
a
lig
n
an
t
”
in
d
icate
s
ca
n
ce
r
o
u
s
lesi
o
n
s
o
r
tu
m
o
r
s
,
an
d
“
n
o
r
m
al
”
r
ep
r
esen
ts
im
ag
es
s
h
o
win
g
h
ea
lth
y
lu
n
g
tis
s
u
e
with
o
u
t
an
y
ab
n
o
r
m
alities
.
L
ater
,
th
is
d
ataset
is
d
iv
id
ed
in
to
tr
ain
in
g
an
d
test
in
g
s
ets with
8
5
% a
n
d
1
5
% r
atio
.
2
.
2
.
M
L
cla
s
s
if
ica
t
io
n a
lg
o
ri
t
hm
s
I
n
th
is
wo
r
k
,
s
ix
ML
alg
o
r
ith
m
s
wer
e
u
tili
ze
d
to
an
al
y
ze
l
u
n
g
ca
n
ce
r
d
atasets
an
d
ai
d
i
n
ac
cu
r
ate
id
en
tific
atio
n
an
d
class
if
icatio
n
o
f
lu
n
g
ca
n
ce
r
ca
s
es.
T
h
ese
alg
o
r
ith
m
s
in
cl
u
d
e
SVM,
RF
,
DT
,
LR
,
N
B
,
an
d
KNN.
E
ac
h
alg
o
r
ith
m
was e
m
p
lo
y
ed
to
an
aly
ze
f
ea
tu
r
es e
x
tr
ac
ted
f
r
o
m
th
e
d
atasets
,
s
u
ch
as C
T
s
ca
n
im
ag
es,
an
d
to
r
ec
o
g
n
ize
p
atter
n
s
a
n
d
r
elatio
n
s
h
ip
s
with
in
th
e
d
ata,
co
n
tr
ib
u
tin
g
to
t
h
e
o
v
e
r
all
o
b
j
ec
tiv
e
o
f
im
p
r
o
v
i
n
g
ca
n
ce
r
d
iag
n
o
s
is
.
SVM
f
in
d
s
th
e
ap
p
r
o
p
r
iate
h
y
p
er
p
lan
e
to
d
i
v
id
e
f
ea
tu
r
e
clas
s
es.
r
an
d
o
m
f
o
r
est
tr
ain
s
s
ev
er
al
DT
an
d
p
r
o
d
u
ce
s
class
m
o
d
e
f
o
r
ca
teg
o
r
izatio
n
.
Dec
is
io
n
T
r
ee
class
if
ies
b
y
r
ec
u
r
s
iv
ely
p
ar
titi
o
n
in
g
f
ea
tu
r
e
s
p
ac
e
b
y
v
alu
e.
L
R
u
s
es
p
r
ed
icto
r
v
a
r
iab
les
to
m
o
d
el
b
in
ar
y
o
u
tc
o
m
es.
NB
class
if
ies
f
ea
tu
r
es
u
s
in
g
b
ay
es
’
th
eo
r
e
m
an
d
s
tr
o
n
g
in
d
ep
en
d
en
ce
ass
u
m
p
tio
n
s
.
KNN
class
if
ie
s
an
u
n
s
ee
n
in
s
tan
ce
b
ased
o
n
th
e
m
ajo
r
ity
class
o
f
its
clo
s
est n
eig
h
b
o
r
s
in
f
ea
t
u
r
e
s
p
ac
e.
2.
3
.
F
e
a
t
ure
ex
t
r
a
ct
io
n wit
h
a
uto
enco
der
I
n
th
is
wo
r
k
,
a
n
au
to
e
n
co
d
e
r
n
eu
r
al
n
etwo
r
k
is
d
ef
in
e
d
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
.
T
h
e
au
to
e
n
co
d
er
is
tr
ain
ed
to
r
ec
o
n
s
tr
u
ct
in
p
u
t
i
m
ag
es
wh
ile
m
in
im
izin
g
r
ec
o
n
s
tr
u
ctio
n
er
r
o
r
.
Hid
d
e
n
lay
er
s
o
f
th
e
au
to
e
n
co
d
er
ex
tr
ac
t
s
alien
t
f
ea
tu
r
es
f
r
o
m
th
e
im
ag
es,
cr
ea
tin
g
a
co
m
p
r
ess
ed
r
ep
r
esen
tatio
n
.
T
h
ese
f
ea
tu
r
es
ar
e
th
en
co
n
ca
ten
ated
t
o
f
o
r
m
a
n
ew
f
ea
tu
r
e
v
ec
to
r
f
o
r
ea
ch
i
m
ag
e.
T
h
e
f
ea
tu
r
e
v
ec
to
r
s
ar
e
in
teg
r
ated
with
m
ac
h
i
n
e
lear
n
in
g
class
if
ier
s
lik
e
SV
M,
r
an
d
o
m
f
o
r
est,
an
d
LR
f
o
r
lu
n
g
ca
n
ce
r
d
etec
tio
n
.
T
h
is
p
r
o
ce
s
s
en
h
an
ce
s
class
if
icatio
n
ac
cu
r
ac
y
b
y
ca
p
tu
r
in
g
ess
en
tial
ch
ar
ac
ter
is
tics
o
f
th
e
im
ag
es,
im
p
r
o
v
i
n
g
o
v
e
r
all
p
er
f
o
r
m
an
ce
in
id
en
tify
in
g
l
u
n
g
ca
n
ce
r
ca
s
es f
r
o
m
m
ed
ical
im
a
g
in
g
d
ata.
2.
4
.
H
y
brid inte
g
ra
t
io
n wit
h m
a
chine le
a
rning
m
o
dels
I
n
th
is
s
tep
,
f
ea
tu
r
e
v
ec
to
r
s
ex
tr
ac
ted
b
y
th
e
au
to
e
n
co
d
er
ar
e
in
teg
r
ated
with
ML
m
o
d
els,
cr
ea
tin
g
a
h
y
b
r
id
f
r
am
ew
o
r
k
f
o
r
lu
n
g
ca
n
ce
r
d
etec
tio
n
.
T
h
ese
v
ec
to
r
s
en
ca
p
s
u
late
ess
en
tial
C
T
s
ca
n
im
ag
e
ch
ar
ac
ter
is
tics
,
en
h
an
cin
g
ML
alg
o
r
ith
m
s
’
p
er
f
o
r
m
a
n
ce
.
T
h
e
h
y
b
r
id
a
p
p
r
o
ac
h
co
m
b
in
es
au
to
en
co
d
er
f
ea
tu
r
e
ex
tr
ac
tio
n
with
ML
class
if
ier
s
.
E
ac
h
m
o
d
el
e
f
f
icien
tly
u
tili
ze
s
th
ese
v
ec
to
r
s
to
class
if
y
i
m
ag
es
in
to
b
en
ig
n
,
m
alig
n
an
t,
o
r
n
o
r
m
al
ty
p
es
.
T
h
is
in
teg
r
atio
n
y
ield
s
s
u
p
er
io
r
p
r
ec
is
io
n
,
r
ec
all,
an
d
ac
cu
r
ac
y
,
b
o
ls
ter
in
g
ea
r
ly
lu
n
g
ca
n
ce
r
d
etec
tio
n
an
d
d
iag
n
o
s
is
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
Appl
y
ing
M
L
cla
s
s
if
ica
t
io
n a
lg
o
rit
hm
s
wit
h o
rig
ina
l
da
t
a
s
et
I
n
th
e
in
itial
p
h
ase
,
we
aim
ed
at
ev
alu
at
e
th
e
p
er
f
o
r
m
an
ce
o
f
v
ar
io
u
s
ML
class
if
ier
s
in
l
u
n
g
ca
n
ce
r
d
etec
tio
n
u
s
in
g
f
iv
e
class
if
ier
s
n
am
ely
SVM,
RF
,
DT
,
LR
,
NB
,
an
d
KN
N.
A
s
a
p
r
ep
r
o
ce
s
s
in
g
s
tep
,
th
e
im
ag
es
ar
e
r
esized
to
a
co
n
s
is
ten
t
d
im
en
s
io
n
o
f
1
2
8
x
1
2
8
p
ix
els.
T
h
is
r
esizin
g
en
s
u
r
es
u
n
if
o
r
m
ity
in
th
e
in
p
u
t
d
ata
.
E
ac
h
p
ix
el
in
th
e
im
ag
es,
r
ep
r
esen
ted
b
y
n
u
m
er
ic
v
alu
es
co
r
r
esp
o
n
d
in
g
to
its
in
ten
s
i
ty
,
is
f
latten
ed
in
to
a
one
-
d
im
en
s
io
n
al
ar
r
ay
to
c
o
n
v
er
t
t
h
e
im
ag
es
in
to
n
u
m
er
ic
d
ata,
k
n
o
wn
as
f
ea
t
u
r
e
v
ec
to
r
s
.
T
h
e
f
latten
i
n
g
p
r
o
ce
s
s
en
ab
les
th
e
g
r
ay
s
ca
le
im
ag
es
to
b
e
r
ep
r
esen
ted
as
n
u
m
er
ic
ar
r
ay
s
s
u
itab
le
f
o
r
p
r
o
ce
s
s
in
g
b
y
ML
alg
o
r
ith
m
s
.
T
h
is
co
n
v
er
s
io
n
is
ess
en
tial
f
o
r
s
u
b
s
eq
u
en
t
an
al
y
s
is
task
s
an
d
en
ab
les
ef
f
icien
t
p
r
o
ce
s
s
in
g
b
y
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
:
4
1
6
-
4
2
4
420
ML
class
if
ier
s
.
Gr
ay
s
ca
le
im
ag
es
ar
e
p
r
ef
er
r
e
d
f
o
r
th
eir
co
m
p
u
tatio
n
al
ef
f
icien
cy
an
d
r
elev
an
ce
to
lu
n
g
ca
n
ce
r
d
etec
tio
n
task
s
.
T
h
e
d
ataset
is
th
en
s
p
lit
in
to
tr
ai
n
in
g
a
n
d
test
in
g
s
ets.
T
h
e
r
e
s
u
lts
with
all
th
ese
class
if
ier
s
ar
e
tab
u
lated
.
T
ab
le
1
an
d
Fig
u
r
e
2
s
h
o
ws r
esu
lts
with
ML
m
o
d
els.
T
ab
le
1
.
Ou
tp
u
t w
ith
ac
tu
al
im
ag
e
d
ataset
an
d
ML
m
o
d
els
M
o
d
e
l
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
A
c
c
u
r
a
c
y
S
V
M
0
.
9
6
0
.
9
7
0
.
9
6
0
.
9
7
RF
0
.
9
6
0
.
8
8
0
.
9
1
0
.
9
5
DT
0
.
8
5
0
.
8
9
0
.
8
7
0
.
9
LR
0
.
9
7
0
.
9
5
0
.
9
2
0
.
9
5
NB
0
.
6
3
0
.
7
0
0
.
6
4
0
.
6
8
K
N
N
0
.
9
0
0
.
9
1
0
.
8
8
0
.
8
9
Fig
u
r
e
2
.
Ou
t
p
u
t w
ith
ML
class
if
ier
s
I
n
ev
alu
atin
g
m
ac
h
in
e
lear
n
in
g
m
o
d
els
f
o
r
lu
n
g
ca
n
ce
r
d
etec
tio
n
,
s
ev
er
al
k
ey
p
er
f
o
r
m
a
n
ce
m
etr
ics
wer
e
ass
ess
ed
.
SVM
an
d
L
R
d
em
o
n
s
tr
ated
th
e
h
ig
h
est
p
r
ec
is
io
n
(
SVM:
0
.
9
6
,
LR
:
0
.
9
7
)
,
r
ec
all
(
SVM:
0
.
9
7
,
LR
:
0
.
9
5
)
,
an
d
ac
cu
r
ac
y
(
SVM:
0
.
9
7
,
LR
:
0
.
9
5
)
,
m
ak
in
g
th
em
p
r
o
m
is
in
g
ch
o
ices
f
o
r
ac
cu
r
ate
lu
n
g
ca
n
ce
r
id
en
tific
atio
n
.
r
a
n
d
o
m
f
o
r
est
an
d
d
ec
is
io
n
tr
ee
m
o
d
els
s
h
o
wed
s
lig
h
tly
lo
wer
p
er
f
o
r
m
an
ce
,
with
h
ig
h
e
r
r
ates
o
f
f
alse
p
o
s
itiv
es
(
r
an
d
o
m
f
o
r
est
p
r
ec
is
io
n
:
0
.
9
6
,
r
ec
all:
0
.
8
8
,
F1
-
s
co
r
e:
0
.
9
1
,
ac
cu
r
ac
y
:
0
.
9
5
;
d
ec
is
io
n
tr
ee
p
r
ec
is
io
n
:
0
.
8
,
r
ec
all:
0
.
8
,
F
1
-
s
co
r
e:
0
.
8
7
,
ac
cu
r
ac
y
:
0
.
9
)
.
NB
ex
h
ib
ited
th
e
lo
west
o
v
er
all
p
er
f
o
r
m
an
ce
(
p
r
ec
is
io
n
:
0
.
6
3
,
r
ec
all:
0
.
7
0
,
F1
-
s
co
r
e:
0
.
6
4
,
ac
cu
r
ac
y
:
0
.
6
8
)
,
wh
ile
KNN
s
h
o
wed
b
ala
n
ce
d
p
r
ec
is
io
n
an
d
r
ec
all
(
p
r
ec
is
io
n
: 0
.
9
0
,
r
ec
all: 0
.
9
1
,
F1
-
s
co
r
e:
0
.
8
8
,
ac
c
u
r
ac
y
: 0
.
8
9
)
.
3
.
2
.
Appl
y
Aut
o
enco
der
f
o
r
f
ea
t
ure
ex
t
r
a
ct
io
n
An
au
to
en
c
o
d
er
a
r
ch
itectu
r
e
i
s
d
ef
in
ed
f
o
r
f
ea
t
u
r
e
ex
t
r
ac
tio
n
f
r
o
m
C
T
s
ca
n
im
ag
es.
T
h
e
a
r
ch
itectu
r
e
co
n
s
is
ts
o
f
an
e
n
co
d
e
r
an
d
a
d
ec
o
d
er
co
m
p
o
n
e
n
t.
I
n
th
e
e
n
co
d
er
s
ec
tio
n
,
c
o
n
v
o
lu
tio
n
al
lay
er
s
with
R
eL
U
ac
tiv
atio
n
f
u
n
ctio
n
s
ar
e
ap
p
lied
to
ca
p
tu
r
e
ess
en
tial
f
ea
tu
r
es
o
f
th
e
in
p
u
t
im
ag
es.
Ma
x
p
o
o
l
in
g
lay
er
s
ar
e
u
tili
ze
d
to
d
o
wn
s
am
p
le
th
e
f
ea
tu
r
e
m
ap
s
,
r
ed
u
cin
g
d
im
e
n
s
io
n
ality
wh
ile
r
etain
in
g
r
el
ev
an
t
in
f
o
r
m
atio
n
.
E
n
co
d
er
co
m
p
r
is
es
o
f
co
n
v
o
l
u
tio
n
al
lay
er
s
f
o
llo
wed
b
y
m
ax
-
p
o
o
lin
g
lay
e
r
s
.
I
t
s
tar
ts
with
a
co
n
v
o
lu
tio
n
al
lay
er
with
1
6
f
ilter
s
an
d
a
k
er
n
el
s
ize
o
f
(
3
,
3
)
,
ap
p
ly
i
n
g
R
eL
U
ac
t
iv
atio
n
f
u
n
ctio
n
s
to
ca
p
tu
r
e
lo
w
-
lev
el
f
ea
tu
r
es
f
r
o
m
t
h
e
in
p
u
t
C
T
s
ca
n
im
ag
es.
Su
b
s
eq
u
en
tly
,
a
m
ax
-
p
o
o
lin
g
lay
er
d
o
wn
s
am
p
l
es
th
e
f
ea
tu
r
e
m
ap
s
b
y
a
f
ac
to
r
o
f
2
,
r
ed
u
cin
g
th
eir
s
p
atial
d
im
en
s
io
n
s
wh
ile
p
r
eser
v
in
g
ess
en
tia
l
in
f
o
r
m
atio
n
.
An
o
th
er
co
n
v
o
l
u
tio
n
al
lay
e
r
with
8
f
ilt
er
s
an
d
t
h
e
s
am
e
k
er
n
el
s
ize
is
ap
p
lied
,
f
u
r
th
e
r
ex
t
r
ac
tin
g
h
i
g
h
er
-
lev
el
f
ea
tu
r
es,
f
o
llo
wed
b
y
an
o
t
h
er
m
ax
-
p
o
o
l
in
g
lay
e
r
f
o
r
d
o
wn
s
am
p
lin
g
.
T
h
is
s
eq
u
en
ce
o
f
co
n
v
o
lu
tio
n
al
an
d
m
ax
-
p
o
o
lin
g
lay
er
s
f
o
r
m
s
th
e
en
co
d
er
s
ec
tio
n
,
p
r
o
g
r
ess
iv
ely
r
ed
u
cin
g
t
h
e
s
p
atial
d
im
en
s
io
n
s
o
f
th
e
in
p
u
t
im
ag
es
an
d
ex
tr
ac
tin
g
in
c
r
ea
s
in
g
ly
a
b
s
tr
ac
t
f
ea
tu
r
es,
u
ltima
tely
lead
in
g
to
a
c
o
m
p
r
ess
ed
r
ep
r
esen
tati
o
n
o
f
th
e
in
p
u
t
d
ata
at
th
e
b
o
ttlen
ec
k
la
y
er
.
T
h
e
d
ec
o
d
er
a
r
ch
itectu
r
e
m
ir
r
o
r
s
th
e
e
n
co
d
e
r
’
s
s
tr
u
c
tu
r
e
b
u
t
in
r
e
v
er
s
e
o
r
d
er
,
aim
ed
at
r
ec
o
n
s
tr
u
ctin
g
th
e
in
p
u
t
im
a
g
es
o
b
tain
ed
at
th
e
b
o
ttlen
ec
k
lay
er
.
I
t
b
e
g
in
s
with
a
c
o
n
v
o
lu
tio
n
al
lay
e
r
th
at
em
p
lo
y
s
8
f
ilter
s
an
d
th
e
s
am
e
k
er
n
el
s
ize
(
3
,
3
)
as
th
e
en
co
d
er
’
s
last
co
n
v
o
lu
tio
n
al
lay
e
r
.
T
h
is
lay
er
in
itiates
th
e
r
ec
o
n
s
tr
u
cti
o
n
p
r
o
ce
s
s
b
y
ex
tr
ac
tin
g
f
ea
tu
r
es
f
r
o
m
th
e
co
m
p
r
ess
ed
r
e
p
r
esen
tatio
n
.
S
u
b
s
eq
u
en
tly
,
an
u
p
-
s
am
p
lin
g
lay
er
in
cr
ea
s
es
th
e
s
p
atial
d
im
en
s
io
n
s
o
f
th
e
f
ea
tu
r
e
m
ap
s
to
m
atch
th
o
s
e
o
f
th
e
o
r
ig
in
al
in
p
u
t
im
ag
es.
An
o
th
er
co
n
v
o
l
u
tio
n
al
lay
er
with
1
6
f
ilter
s
an
d
t
h
e
s
am
e
k
er
n
el
s
ize
co
n
tin
u
es
th
e
r
ec
o
n
s
tr
u
ctio
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
Lu
n
g
ca
n
ce
r
d
etec
tio
n
u
s
in
g
h
yb
r
id
in
teg
r
a
tio
n
o
f
a
u
to
e
n
co
d
er
…
(
A
n
n
emn
ee
d
i La
ksh
ma
n
a
r
a
o
)
421
p
r
o
ce
s
s
b
y
f
u
r
th
er
r
ef
in
in
g
th
e
f
ea
tu
r
es e
x
tr
ac
ted
f
r
o
m
th
e
b
o
ttlen
ec
k
lay
er
.
An
o
th
er
u
p
-
s
a
m
p
lin
g
lay
er
is
th
e
n
ap
p
lied
to
r
esto
r
e
th
e
s
p
atial
d
im
en
s
io
n
s
f
u
r
t
h
er
.
Fin
ally
,
t
h
e
o
u
t
p
u
t
lay
er
co
n
s
is
ts
o
f
a
co
n
v
o
l
u
tio
n
al
lay
er
with
3
f
ilter
s
an
d
a
So
f
tMa
x
ac
tiv
atio
n
f
u
n
ctio
n
.
T
h
is
lay
er
r
ec
o
n
s
tr
u
cts
th
e
in
p
u
t
im
ag
es
b
y
m
ap
p
in
g
th
e
ex
tr
ac
ted
f
ea
tu
r
es
b
ac
k
to
p
ix
el
in
ten
s
ities
,
co
m
p
letin
g
th
e
d
ec
o
d
in
g
p
r
o
ce
s
s
.
Ov
er
all,
th
e
d
ec
o
d
e
r
ar
ch
itectu
r
e
aim
s
to
r
ev
er
s
e
th
e
en
co
d
in
g
p
r
o
ce
s
s
,
g
r
ad
u
ally
r
ec
o
n
s
tr
u
ctin
g
th
e
o
r
ig
in
al
in
p
u
t
im
ag
es
f
r
o
m
th
e
co
m
p
r
ess
ed
r
ep
r
esen
tatio
n
o
b
tain
ed
at
th
e
b
o
ttlen
ec
k
lay
e
r
.
T
h
e
au
to
e
n
co
d
e
r
is
co
m
p
iled
with
th
e
Ad
am
o
p
tim
izer
.
Su
b
s
eq
u
en
tly
,
th
e
m
o
d
el
is
tr
ai
n
ed
o
n
th
e
p
r
o
v
id
e
d
im
ag
es
u
s
in
g
a
s
p
ec
if
ied
n
u
m
b
er
o
f
ep
o
ch
s
an
d
s
t
ep
s
p
er
ep
o
ch
,
with
v
alid
atio
n
p
er
f
o
r
m
ed
o
n
t
h
e
s
am
e
d
ataset
g
en
er
ato
r
.
T
h
e
tr
ain
in
g
d
o
n
e
with
2
5
ep
o
c
h
s
.
Fig
u
r
e
3
s
h
o
ws
th
e
ep
o
ch
wis
e
lo
s
s
in
tr
ain
in
g
an
d
v
alid
atio
n
p
h
ases
.
Fro
m
F
ig
u
r
e
3
,
it
is
o
b
s
er
v
ed
t
h
at
th
e
lo
s
s
v
alu
e
is
d
ec
r
ea
s
in
g
in
b
o
th
t
r
ain
in
g
a
n
d
test
in
g
p
h
ases
,
in
d
icatin
g
th
at
it c
an
a
b
le
to
ex
tr
ac
t u
s
ef
u
l f
ea
tu
r
es.
Fig
u
r
e
3
.
E
p
o
ch
wis
e
tr
ain
in
g
an
d
v
alid
atio
n
lo
s
s
with
au
to
e
n
co
d
er
3
.
3
.
I
ma
g
e
re
c
o
ns
t
ruct
io
n wit
h t
ra
ined a
uto
enco
der
T
h
e
r
ec
o
n
s
tr
u
cte
d
im
ag
es
ar
e
g
en
er
ated
u
s
in
g
th
e
tr
ain
e
d
au
to
en
co
d
er
m
o
d
el.
Fig
u
r
e
4
s
h
o
ws
th
e
o
r
ig
in
al
an
d
r
ec
o
n
s
tr
u
cted
im
ag
es
o
f
f
ir
s
t
8
s
am
p
les.
T
h
is
v
is
u
aliza
tio
n
en
ab
les
a
q
u
alitativ
e
ass
e
s
s
m
en
t
o
f
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
au
to
en
co
d
er
in
r
ec
o
n
s
tr
u
ctin
g
th
e
in
p
u
t im
ag
es.
B
y
co
m
p
ar
in
g
th
e
o
r
ig
in
al
an
d
r
ec
o
n
s
tr
u
cted
im
ag
es,
we
ca
n
g
au
g
e
h
o
w
ac
cu
r
ately
th
e
a
u
to
en
co
d
er
ca
p
tu
r
es
th
e
ess
en
tial
f
ea
tu
r
es
o
f
th
e
in
p
u
t
d
ata
d
u
r
in
g
th
e
tr
ain
in
g
p
r
o
ce
s
s
.
T
h
e
r
ec
o
n
s
tr
u
cted
im
ag
es
m
a
y
ap
p
ea
r
s
lig
h
tly
b
l
u
r
r
ed
.
T
h
is
is
a
co
m
m
o
n
c
h
ar
ac
ter
is
tic
o
f
au
to
e
n
co
d
e
r
-
b
ased
r
ec
o
n
s
tr
u
ctio
n
s
,
e
s
p
ec
ially
wh
en
th
e
m
o
d
el
is
tr
ain
ed
wit
h
a
lim
ited
am
o
u
n
t o
f
d
ata
wit
h
s
p
ec
if
ic
co
n
s
tr
ain
ts
.
Fig
u
r
e
4
.
R
ec
o
n
s
tr
u
cte
d
im
ag
e
s
g
en
er
ated
b
y
th
e
tr
ain
e
d
au
to
en
co
d
er
m
o
d
el
3.
4
. C
re
a
t
ing
new
f
ea
t
ure
v
e
ct
o
r
wit
h o
utput
o
f
a
ut
o
enco
der
T
o
f
u
r
th
er
lev
er
a
g
e
th
e
tr
ain
ed
au
to
e
n
co
d
e
r
f
o
r
f
ea
tu
r
e
e
x
tr
ac
tio
n
,
a
s
ep
ar
ate
en
co
d
er
m
o
d
el
is
co
n
s
tr
u
cted
.
T
h
is
m
o
d
el
is
d
esig
n
ed
to
ex
tr
ac
t
f
ea
tu
r
es
f
r
o
m
th
e
en
co
d
er
s
ec
tio
n
o
f
th
e
au
to
e
n
co
d
er
ar
ch
itectu
r
e.
T
h
e
f
ea
tu
r
e
ex
tr
a
ctio
n
p
r
o
ce
s
s
f
r
o
m
th
e
en
co
d
e
r
s
ec
tio
n
o
f
th
e
au
t
o
en
co
d
er
y
ield
s
8
1
0
0
f
ea
tu
r
es
f
o
r
ea
ch
in
p
u
t
im
ag
e.
T
h
ese
f
ea
tu
r
es
r
ep
r
esen
t
a
co
n
d
en
s
ed
r
ep
r
esen
tatio
n
o
f
th
e
o
r
i
g
in
al
in
p
u
t
im
ag
es,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
:
4
1
6
-
4
2
4
422
ca
p
tu
r
in
g
th
eir
ess
en
tial
ch
ar
ac
ter
is
tics
in
a
lo
wer
-
d
im
e
n
s
i
o
n
al
f
ea
tu
r
e
s
p
ac
e.
T
h
ese
ex
t
r
ac
ted
f
ea
tu
r
es
ar
e
th
en
u
tili
ze
d
in
s
u
b
s
eq
u
en
t
s
tep
s
,
s
u
ch
as
i
n
teg
r
atio
n
with
ML
class
if
ier
s
,
f
o
r
lu
n
g
ca
n
ce
r
d
etec
tio
n
a
n
d
class
if
icatio
n
.
3.
5
.
Appl
y
ing
M
L
cla
s
s
if
ica
t
io
n a
lg
o
rit
hm
s
wit
h
new
f
ea
t
ure
da
t
a
s
et
I
n
th
is
p
h
ase,
ML
class
if
i
er
s
ap
p
lied
with
n
ew
f
ea
t
u
r
e
v
ec
to
r
g
en
er
ated
b
y
a
u
to
en
co
d
er
.
T
h
e
alg
o
r
ith
m
s
n
am
ely
SVM,
R
F,
DT
C
,
LR
,
NB
an
d
K
NN
ar
e
ap
p
lied
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
all
m
o
d
els
in
cr
ea
s
es
in
ter
m
s
o
f
all
m
atr
ices.
T
ab
le
2
an
d
F
ig
u
r
e
5
s
h
o
ws
th
e
r
esu
lts
o
f
ML
m
o
d
els
ap
p
lied
with
au
to
en
co
d
er
ex
tr
ac
te
d
f
ea
tu
r
e
v
ec
to
r
.
T
ab
le
2
.
Ou
tp
u
t w
ith
n
ew
f
ea
t
u
r
e
v
ec
to
r
an
d
ML
m
o
d
els
M
o
d
e
l
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
A
c
c
u
r
a
c
y
S
V
M
0
.
9
6
0
.
9
7
0
.
9
6
0
.
9
7
RF
0
.
9
6
0
.
8
8
0
.
9
1
0
.
9
5
DT
0
.
8
5
0
.
8
9
0
.
8
7
0
.
9
LR
0
.
9
7
0
.
9
5
0
.
9
2
0
.
9
5
NB
0
.
6
3
0
.
7
0
0
.
6
4
0
.
6
8
K
N
N
0
.
9
0
0
.
9
1
0
.
8
8
0
.
8
9
Fig
u
r
e
5
.
Ou
t
p
u
t w
ith
ML
m
o
d
els ap
p
lied
with
au
to
e
n
co
d
e
r
ex
tr
ac
ted
d
ataset
4.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
p
r
esen
ted
th
e
c
r
itical
is
s
u
e
o
f
lu
n
g
ca
n
ce
r
d
etec
tio
n
,
r
ec
o
g
n
izin
g
its
g
lo
b
al
s
ig
n
if
ican
ce
an
d
th
e
u
r
g
en
t
n
ee
d
f
o
r
in
n
o
v
ativ
e
d
iag
n
o
s
tic
ap
p
r
o
ac
h
es.
Utilizin
g
C
T
s
ca
n
im
ag
es
ca
te
g
o
r
ized
in
t
o
b
en
i
g
n
,
m
alig
n
an
t,
a
n
d
n
o
r
m
al
class
es
,
th
e
r
esear
c
h
in
itially
em
p
lo
y
ed
co
n
v
en
tio
n
al
ML
alg
o
r
ith
m
s
,
in
clu
d
in
g
SVM,
r
an
d
o
m
f
o
r
ests
,
DT
,
LR
,
NB
,
an
d
KNN,
to
d
etec
t
lu
n
g
ca
n
ce
r
.
Su
b
s
eq
u
en
tly
,
a
n
o
v
el
h
y
b
r
id
m
o
d
el
was
in
tr
o
d
u
ce
d
,
in
teg
r
atin
g
d
iv
e
r
s
e
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
with
au
to
en
co
d
e
r
-
b
ased
f
ea
tu
r
e
ex
tr
ac
tio
n
.
T
h
e
au
to
en
co
d
er
tech
n
iq
u
e
was
em
p
lo
y
ed
to
ex
tr
ac
t
ess
en
tial
f
ea
tu
r
es
f
r
o
m
th
e
im
ag
es,
cr
ea
tin
g
a
n
ew
f
ea
tu
r
e
v
ec
to
r
.
T
h
e
s
am
e
co
n
v
en
tio
n
al
ML
class
if
ier
s
wer
e
th
en
ap
p
lied
to
th
is
n
ew
d
ataset,
r
esu
ltin
g
in
s
ig
n
if
ican
tly
en
h
a
n
ce
d
p
e
r
f
o
r
m
an
ce
.
No
tab
ly
,
th
e
h
y
b
r
i
d
m
o
d
el
ac
h
iev
e
d
r
em
ar
k
ab
le
r
es
u
lts
,
with
all
m
etr
ics
ex
ce
ed
in
g
0
.
9
0
ac
r
o
s
s
m
u
ltip
l
e
class
if
ier
s
.
SVM,
LR
,
an
d
K
NN
clas
s
if
ier
s
d
em
o
n
s
tr
ated
p
r
ec
is
io
n
an
d
r
ec
all
v
alu
es
o
f
0
.
9
7
an
d
0
.
9
5
,
r
esp
e
ctiv
ely
,
h
ig
h
lig
h
tin
g
th
e
e
f
f
ec
t
iv
en
ess
o
f
th
e
in
teg
r
ate
d
f
r
a
m
ewo
r
k
in
ac
cu
r
ately
d
etec
tin
g
lu
n
g
ca
n
ce
r
ca
s
es.
T
h
ese
f
in
d
in
g
s
u
n
d
e
r
s
co
r
e
a
s
u
b
s
tan
tial
ad
v
an
ce
m
en
t
in
lu
n
g
ca
n
ce
r
d
etec
tio
n
,
s
h
o
wca
s
in
g
th
e
ef
f
icac
y
o
f
th
e
in
teg
r
ated
f
r
am
ewo
r
k
in
ac
h
iev
in
g
h
ig
h
ac
cu
r
ac
y
a
n
d
en
ab
lin
g
ea
r
ly
d
iag
n
o
s
is
.
RE
F
E
R
E
NC
E
S
[
1
]
G
.
R
a
j
a
e
t
a
l
.
,
“
S
y
n
e
r
g
i
st
i
c
a
n
a
l
y
si
s
o
f
l
u
n
g
c
a
n
c
e
r
’
s
i
m
p
a
c
t
o
n
c
a
r
d
i
o
v
a
sc
u
l
a
r
d
i
sea
se
u
s
i
n
g
M
L
-
b
a
se
d
t
e
c
h
n
i
q
u
e
s,
”
I
EEE
J
o
u
rn
a
l
o
f
Bi
o
m
e
d
i
c
a
l
a
n
d
H
e
a
l
t
h
I
n
f
o
rm
a
t
i
c
s
,
p
p
.
1
–
8
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
J
B
H
I
.
2
0
2
4
.
3
3
6
5
1
7
6
.
[
2
]
A
.
R
.
W
.
S
a
i
t
,
“
L
u
n
g
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
mo
d
e
l
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
(
S
w
i
t
zerl
a
n
d
)
,
v
o
l
.
1
3
,
n
o
.
2
2
,
p
.
1
2
5
1
0
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
2
2
1
2
5
1
0
.
[
3
]
H
.
A
l
q
a
h
t
a
n
i
,
E
.
A
l
a
b
d
u
l
k
r
e
e
m,
F
.
A
.
A
l
o
t
a
i
b
i
,
M
.
M
.
A
l
n
f
i
a
i
,
C
.
S
i
n
g
l
a
,
a
n
d
A
.
S
.
S
a
l
a
m
a
,
“
I
mp
r
o
v
e
d
w
a
t
e
r
st
r
i
d
e
r
a
l
g
o
r
i
t
h
m
w
i
t
h
c
o
n
v
o
l
u
t
i
o
n
a
l
a
u
t
o
e
n
c
o
d
e
r
f
o
r
l
u
n
g
a
n
d
c
o
l
o
n
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
o
n
h
i
s
t
o
p
a
t
h
o
l
o
g
i
c
a
l
i
m
a
g
e
s,
”
I
EEE
Ac
c
e
s
s
,
v
o
l
.
1
2
,
p
p
.
9
4
9
–
9
5
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
3
4
6
8
9
4
.
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
Lu
n
g
ca
n
ce
r
d
etec
tio
n
u
s
in
g
h
yb
r
id
in
teg
r
a
tio
n
o
f
a
u
to
e
n
co
d
er
…
(
A
n
n
emn
ee
d
i La
ksh
ma
n
a
r
a
o
)
423
[
4
]
Q
.
G
a
o
,
L.
Y
a
n
g
,
M
.
Lu
,
R
.
Ji
n
,
H
.
Y
e
,
a
n
d
T.
M
a
,
“
T
h
e
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
i
n
l
u
n
g
c
a
n
c
e
r
i
mm
u
n
o
t
h
e
r
a
p
y
,
”
J
o
u
r
n
a
l
o
f
H
e
m
a
t
o
l
o
g
y
a
n
d
O
n
c
o
l
o
g
y
,
v
o
l
.
1
6
,
n
o
.
1
,
p
.
5
5
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
3
0
4
5
-
023
-
0
1
4
5
6
-
y.
[
5
]
A
.
Jawai
d
,
J.
H
a
f
e
e
z
,
S
.
K
h
a
n
,
a
n
d
A
.
U
r
R
e
h
ma
n
,
“
Lu
n
g
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
u
s
i
n
g
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
o
n
a
n
d
r
o
i
d
,
”
i
n
2
0
2
3
G
l
o
b
a
l
C
o
n
f
e
re
n
c
e
o
n
Wi
rel
e
ss
a
n
d
O
p
t
i
c
a
l
T
e
c
h
n
o
l
o
g
i
e
s
(
G
C
WOT
)
,
I
EEE,
Jan
.
2
0
2
3
,
p
p
.
1
–
8
.
d
o
i
:
1
0
.
1
1
0
9
/
G
C
W
O
T
5
7
8
0
3
.
2
0
2
3
.
1
0
0
6
4
6
5
8
.
[
6
]
B
.
D
.
R
a
o
a
n
d
M
.
A
r
sh
a
d
,
“
E
a
r
l
y
d
e
t
e
c
t
i
o
n
o
f
l
u
n
g
c
a
n
c
e
r
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
,
”
i
n
2
0
2
3
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
I
n
f
o
rm
a
t
i
c
s (I
C
C
C
I
)
,
I
EEE,
Ja
n
.
2
0
2
3
,
p
p
.
1
–
5
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
C
I
5
6
7
4
5
.
2
0
2
3
.
1
0
1
2
8
3
8
9
.
[
7
]
D
.
G
u
p
t
a
a
n
d
S
.
D
a
w
n
,
“
D
e
t
e
c
t
i
o
n
a
n
d
st
a
g
i
n
g
o
f
l
u
n
g
c
a
n
c
e
r
f
r
o
m
C
T
s
c
a
n
i
ma
g
e
s
b
y
d
e
e
p
l
e
a
r
n
i
n
g
,
”
i
n
2
0
2
3
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
i
sr
u
p
t
i
v
e
T
e
c
h
n
o
l
o
g
i
e
s,
I
C
D
T
2
0
2
3
,
I
EEE,
M
a
y
2
0
2
3
,
p
p
.
2
7
4
–
2
7
8
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
D
T5
7
9
2
9
.
2
0
2
3
.
1
0
1
5
1
1
9
4
.
[
8
]
R
.
M
a
h
u
m
a
n
d
A
.
S
.
A
l
-
S
a
l
ma
n
,
“
L
u
n
g
-
R
e
t
i
n
a
N
e
t
:
l
u
n
g
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
u
si
n
g
a
R
e
t
i
n
a
N
e
t
w
i
t
h
m
u
l
t
i
-
sc
a
l
e
f
e
a
t
u
r
e
f
u
s
i
o
n
a
n
d
c
o
n
t
e
x
t
m
o
d
u
l
e
,
”
I
E
EE
A
c
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
5
3
8
5
0
–
5
3
8
6
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
8
1
2
5
9
.
[
9
]
S
.
B
h
a
r
a
t
h
y
,
R
.
P
a
v
i
t
h
r
a
,
a
n
d
B
.
A
k
sh
a
y
a
,
“
L
u
n
g
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ap
p
l
i
e
d
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
C
o
m
p
u
t
i
n
g
,
I
C
AAIC
2
0
2
2
,
I
EEE,
M
a
y
2
0
2
2
,
p
p
.
5
3
9
–
5
4
3
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
A
I
C
5
3
9
2
9
.
2
0
2
2
.
9
7
9
3
0
6
1
.
[
1
0
]
G
.
K
u
m
a
r
i
,
U
.
V
.
R
a
mes
h
,
P
.
P
.
R
a
mamo
h
a
n
,
K
.
S
.
P
a
v
a
n
i
,
a
n
d
A
.
La
k
sh
ma
n
a
r
a
o
,
“
C
a
n
c
e
r
d
e
t
e
c
t
i
o
n
w
i
t
h
e
n
sem
b
l
e
l
e
a
r
n
i
n
g
mo
d
e
l
f
r
o
m
n
o
v
e
l
p
r
e
c
e
d
e
n
c
e
b
a
se
d
a
l
g
o
r
i
t
h
ms,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
n
t
e
m
p
o
r
a
ry
C
o
m
p
u
t
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s,
I
C
3
I
2
0
2
3
,
I
EEE,
S
e
p
.
2
0
2
3
,
p
p
.
2
1
8
7
–
2
1
9
0
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
3
I
5
9
1
1
7
.
2
0
2
3
.
1
0
3
9
7
6
2
9
.
[
1
1
]
S
.
K
.
B
h
a
t
t
a
n
d
S
.
S
r
i
n
i
v
a
sa
n
,
“
Lu
n
g
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
u
si
n
g
A
I
a
n
d
d
i
f
f
e
r
e
n
t
t
e
c
h
n
i
q
u
e
s
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
i
n
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
2
,
n
o
.
8
,
p
p
.
6
3
0
–
6
3
8
,
2
0
2
4
.
[
1
2
]
A
.
La
k
s
h
ma
n
a
r
a
o
,
A
.
S
r
i
sa
i
l
a
,
a
n
d
T
.
S
.
R
.
K
i
r
a
n
,
“
C
a
n
c
e
r
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
n
o
v
e
l
r
a
n
k
i
n
g
a
l
g
o
r
i
t
h
ms
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
C
o
m
m
u
n
i
c
a
t
i
o
n
s i
n
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
r
m
a
t
i
o
n
S
c
i
e
n
c
e
,
v
o
l
.
1
3
9
3
,
2
0
2
1
,
p
p
.
6
2
–
7
0
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
16
-
3
6
6
0
-
8
_
6
.
[
1
3
]
E.
D
r
i
t
s
a
s
a
n
d
M
.
Tr
i
g
k
a
,
“
L
u
n
g
c
a
n
c
e
r
r
i
sk
p
r
e
d
i
c
t
i
o
n
w
i
t
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
,
”
B
i
g
D
a
t
a
a
n
d
C
o
g
n
i
t
i
v
e
C
o
m
p
u
t
i
n
g
,
v
o
l
.
6
,
n
o
.
4
,
p
.
1
3
9
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
b
d
c
c
6
0
4
0
1
3
9
.
[
1
4
]
R
.
P
a
n
d
i
a
n
,
V
.
V
e
d
a
n
a
r
a
y
a
n
a
n
,
D
.
N
.
S
.
R
.
K
u
mar,
a
n
d
R
.
R
a
j
a
k
u
m
a
r
,
“
D
e
t
e
c
t
i
o
n
a
n
d
c
l
a
s
si
f
i
c
a
t
i
o
n
o
f
l
u
n
g
c
a
n
c
e
r
u
si
n
g
C
N
N
a
n
d
G
o
o
g
l
e
n
e
t
,
”
M
e
a
s
u
rem
e
n
t
:
S
e
n
s
o
rs
,
v
o
l
.
2
4
,
p
.
1
0
0
5
8
8
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
a
se
n
.
2
0
2
2
.
1
0
0
5
8
8
.
[
1
5
]
S
.
La
l
i
t
h
a
,
“
A
n
a
u
t
o
m
a
t
e
d
l
u
n
g
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
s
y
st
e
m
b
a
s
e
d
o
n
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m,
”
J
o
u
rn
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
&
Fu
z
zy
S
y
s
t
e
m
s
,
v
o
l
.
4
0
,
n
o
.
4
,
p
p
.
6
3
5
5
–
6
3
6
4
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
3
2
3
3
/
JI
F
S
-
1
8
9
4
7
6
.
[
1
6
]
M
.
D
i
r
i
k
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
se
d
l
u
n
g
c
a
n
c
e
r
d
i
a
g
n
o
s
i
s,
”
T
u
r
k
i
s
h
J
o
u
r
n
a
l
o
f
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
7
,
n
o
.
4
,
p
p
.
3
2
2
–
3
3
0
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
3
1
1
2
7
/
t
u
j
e
.
1
1
8
0
9
3
1
.
[
1
7
]
I
.
N
a
z
i
r
,
I
.
U
.
H
a
q
,
S
.
A
.
A
l
q
a
h
t
a
n
i
,
M
.
M
.
Ja
d
o
o
n
,
a
n
d
M
.
D
a
h
sh
a
n
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
se
d
l
u
n
g
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
u
s
i
n
g
mu
l
t
i
v
i
e
w
i
ma
g
e
r
e
g
i
st
r
a
t
i
o
n
a
n
d
f
u
s
i
o
n
,
”
J
o
u
r
n
a
l
o
f
S
e
n
so
rs
,
v
o
l
.
2
0
2
3
,
n
o
.
1
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
3
/
6
6
8
3
4
3
8
.
[
1
8
]
A
.
M
i
s
h
r
a
a
n
d
S
.
G
a
n
g
w
a
r
,
“
Lu
n
g
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
n
R
e
c
e
n
t
a
n
d
I
n
n
o
v
a
t
i
o
n
T
r
e
n
d
s
i
n
C
o
m
p
u
t
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
,
v
o
l
.
1
1
,
n
o
.
6
S
,
p
p
.
2
7
7
–
2
8
2
,
J
u
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
7
7
6
2
/
i
j
r
i
t
c
c
.
v
1
1
i
6
s.
6
9
2
0
.
[
1
9
]
D
.
M
.
A
b
d
u
l
l
a
h
,
A
.
M
.
A
b
d
u
l
a
z
e
e
z
,
a
n
d
A
.
B
.
S
a
l
l
o
w
,
“
L
u
n
g
c
a
n
c
e
r
p
r
e
d
i
c
t
i
o
n
a
n
d
c
l
a
s
si
f
i
c
a
t
i
o
n
b
a
se
d
o
n
c
o
r
r
e
l
a
t
i
o
n
sel
e
c
t
i
o
n
met
h
o
d
u
si
n
g
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
,
”
Q
u
b
a
h
a
n
Ac
a
d
e
m
i
c
J
o
u
r
n
a
l
,
v
o
l
.
1
,
n
o
.
2
,
p
p
.
1
4
1
–
1
4
9
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
4
8
1
6
1
/
q
a
j
.
v
1
n
2
a
5
8
.
[
2
0
]
D
.
N
.
R
a
o
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
r
e
se
a
r
c
h
o
n
b
r
e
a
s
t
a
n
d
l
u
n
g
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
n
o
v
a
t
i
o
n
i
n
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
3
,
n
o
.
1
,
p
p
.
4
8
–
5
4
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
5
9
6
1
5
/
i
j
i
e
.
3
.
1
.
4
8
.
[
2
1
]
T.
I
.
A
.
M
o
h
a
m
e
d
,
O
.
N
.
O
y
e
l
a
d
e
,
a
n
d
A
.
E.
E
z
u
g
w
u
,
“
A
u
t
o
m
a
t
i
c
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
l
u
n
g
c
a
n
c
e
r
C
T
sca
n
s
b
a
s
e
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
e
b
o
l
a
o
p
t
i
m
i
z
a
t
i
o
n
sea
r
c
h
a
l
g
o
r
i
t
h
m,
”
PL
o
S
O
N
E
,
v
o
l
.
1
8
,
n
o
.
8
A
U
G
U
S
T,
p
.
e
0
2
8
5
7
9
6
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
8
5
7
9
6
.
[
2
2
]
B
.
S
.
D
e
e
p
a
p
r
i
y
a
e
t
a
l
.
,
“
P
e
r
f
o
r
ma
n
c
e
e
v
a
l
u
a
t
i
o
n
o
f
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s fo
r
l
u
n
g
c
a
n
c
e
r
p
r
e
d
i
c
t
i
o
n
,
”
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
7
,
n
o
.
1
3
,
p
p
.
9
1
9
1
–
9
1
9
8
,
Ju
l
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
0
0
-
0
2
3
-
0
8
3
1
3
-
7.
[
2
3
]
A
.
A
.
A
b
d
A
l
-
A
me
e
r
,
G
.
A
.
H
u
ss
i
e
n
,
a
n
d
H
.
A
.
A
l
A
meri
,
“
L
u
n
g
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
u
s
i
n
g
i
m
a
g
e
p
r
o
c
e
ssi
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
El
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
8
,
n
o
.
2
,
p
p
.
9
8
7
–
9
9
3
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
2
8
.
i
2
.
p
p
9
8
7
-
9
9
3
.
[
2
4
]
N
.
S
.
N
a
d
k
a
r
n
i
a
n
d
S
.
B
o
r
k
a
r
,
“
D
e
t
e
c
t
i
o
n
o
f
l
u
n
g
c
a
n
c
e
r
i
n
C
T
i
ma
g
e
s
u
si
n
g
i
m
a
g
e
p
r
o
c
e
ssi
n
g
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
T
re
n
d
s
i
n
El
e
c
t
ro
n
i
c
s
a
n
d
I
n
f
o
rm
a
t
i
c
s
,
I
C
O
EI
2
0
1
9
,
I
EEE,
A
p
r
.
2
0
1
9
,
p
p
.
8
6
3
–
8
6
6
.
d
o
i
:
1
0
.
1
1
0
9
/
i
c
o
e
i
.
2
0
1
9
.
8
8
6
2
5
7
7
.
[
2
5
]
N
.
K
h
o
sr
a
v
a
n
a
n
d
U
.
B
a
g
c
i
,
“
S
e
mi
-
su
p
e
r
v
i
se
d
mu
l
t
i
-
t
a
s
k
l
e
a
r
n
i
n
g
f
o
r
l
u
n
g
c
a
n
c
e
r
d
i
a
g
n
o
s
i
s,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
An
n
u
a
l
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
f
t
h
e
I
EE
E
En
g
i
n
e
e
r
i
n
g
i
n
M
e
d
i
c
i
n
e
a
n
d
B
i
o
l
o
g
y
S
o
c
i
e
t
y
,
EM
BS
,
I
EEE,
J
u
l
.
2
0
1
8
,
p
p
.
7
1
0
–
7
1
3
.
d
o
i
:
1
0
.
1
1
0
9
/
EM
B
C
.
2
0
1
8
.
8
5
1
2
2
9
4
.
[
2
6
]
H
a
md
a
l
l
a
F
.
A
l
-
Y
a
sr
i
y
,
“
Th
e
I
Q
-
O
TH
/
N
C
C
D
l
u
n
g
c
a
n
c
e
r
d
a
t
a
s
e
t
.
”
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m
/
d
a
t
a
se
t
s/
h
a
m
d
a
l
l
a
k
/
t
h
e
-
i
q
o
t
h
n
c
c
d
-
l
u
n
g
-
c
a
n
c
e
r
-
d
a
t
a
set
B
I
O
G
RAP
H
I
E
S
OF
AUTH
O
RS
Dr
.
Ann
e
m
n
e
e
d
i
La
k
sh
m
a
n
a
r
a
o
c
u
rre
n
tl
y
w
o
rk
i
n
g
a
s
a
ss
o
c
iate
p
ro
fe
ss
o
r
in
Ad
it
y
a
Un
iv
e
rsity
,
S
u
ra
m
p
a
lem
.
He
c
o
m
p
lete
d
h
is
B.
Tec
h
.
i
n
CS
I
T
a
n
d
M
.
Tec
h
i
n
S
o
ftwa
re
En
g
i
n
e
e
rin
g
.
He
Co
m
p
lete
d
P
h
.
D.
in
An
d
h
ra
Un
i
v
e
rsity
,
Vish
a
k
h
a
p
a
tn
a
m
.
His
a
re
a
s
o
f
in
tere
st
a
re
m
a
c
h
in
e
lea
rn
in
g
,
c
y
b
e
r
se
c
u
rit
y
,
d
e
e
p
lea
rn
in
g
.
He
is
a
li
fe
m
e
m
b
e
r
o
f
Co
m
p
u
ter
S
o
c
iety
o
f
I
n
d
ia (CS
I)
a
n
d
IS
TE
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
la
x
m
a
n
1
2
1
6
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
:
4
1
6
-
4
2
4
424
Nir
m
a
l
G
o
p
a
l
wh
o
g
ra
d
u
a
ted
with
a
b
a
c
h
e
lo
r
’
s
d
e
g
re
e
i
n
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
fro
m
C
h
e
n
n
a
i
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
.
He
h
a
s
c
o
n
tr
ib
u
ted
tw
o
c
o
n
fe
re
n
c
e
p
a
p
e
rs
p
re
se
n
ted
a
t
In
ter
n
a
ti
o
n
a
l
Co
n
fe
re
n
c
e
s
a
n
d
h
a
s
a
p
r
o
fo
u
n
d
in
tere
st
in
t
h
e
d
y
n
a
m
ic
re
a
lms
in
a
rti
ficia
l
in
telli
g
e
n
c
e
,
m
a
c
h
in
e
lea
rn
in
g
a
n
d
d
a
ta
sc
ien
c
e
.
He
is
c
u
rre
n
tl
y
wo
r
k
i
n
g
a
s
a
n
AW
S
d
e
v
e
lo
p
e
r.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
g
n
irma
l2
0
0
1
@g
m
a
il
.
c
o
m
.
Dr
.
Na
g
a
g
o
p
ira
j
u
Vu
ll
a
m
c
u
r
re
n
tl
y
wo
rk
in
g
a
s
p
ro
fe
ss
o
r
i
n
De
p
a
rtme
n
t
o
f
CS
E,
Ch
a
lap
a
th
i
I
n
stit
u
te
o
f
E
n
g
in
e
e
ri
n
g
a
n
d
Tec
h
n
o
l
o
g
y
,
G
u
n
t
u
r,
An
d
h
ra
P
ra
d
e
sh
,
G
u
n
tu
r
Dist
.
He
p
u
b
li
sh
e
d
p
a
p
e
rs
in
v
a
rio
u
s
c
o
n
fe
re
n
c
e
s
a
n
d
jo
u
rn
a
ls.
His
a
re
a
s
o
f
in
tere
st
a
re
m
a
c
h
in
e
lea
rn
in
g
,
d
a
ta
a
n
a
ly
ti
c
s
t
h
ro
u
g
h
R,
a
rti
ficia
l
in
telli
g
e
n
c
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
g
o
p
i.
ra
ju
5
2
4
@g
m
a
il
.
c
o
m
.
Dr
.
Ma
n
d
a
p
a
ti
S
r
id
h
a
r
Dr.
S
rid
h
a
r
M
a
n
d
a
p
a
ti
,
o
b
tain
e
d
h
is
m
a
ste
r‟
s
d
e
g
re
e
in
Co
m
p
u
ters
Ap
p
li
c
a
ti
o
n
s
fro
m
S
.
V
Un
iv
e
rsity
,
Ti
r
u
p
a
t
h
i.
He
re
c
e
iv
e
d
h
is
P
h
.
D.
i
n
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
a
t
Ac
h
a
ry
a
Na
g
a
rju
n
a
U
n
iv
e
rsit
y
,
G
u
n
t
u
r
.
He
is
c
u
rre
n
tl
y
w
o
rk
i
n
g
a
s
P
ro
fe
ss
o
r
i
n
th
e
De
p
a
rtme
n
t
o
f
C
o
m
p
u
ter
Ap
p
li
c
a
ti
o
n
s,
R.
V.R.
a
n
d
J.C
Co
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
,
G
u
n
tu
r
.
He
h
a
s
2
4
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rie
n
c
e
.
He
h
a
s
m
o
re
th
a
n
5
0
In
tern
a
ti
o
n
a
l
a
n
d
Na
ti
o
n
a
l
p
u
b
li
c
a
ti
o
n
s
t
o
h
is
c
re
d
i
t.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
d
a
ta
m
in
i
n
g
a
n
d
b
ig
d
a
ta
a
n
a
ly
t
ics
,
m
a
c
h
in
e
l
e
a
rn
in
g
a
n
d
c
l
o
u
d
c
o
m
p
u
ti
n
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
a
n
d
a
p
a
ti
1
2
@g
m
a
il
.
c
o
m
.
Mo
d
a
la
v
a
l
a
sa
K
r
ish
n
a
K
a
n
th
c
u
rre
n
tl
y
wo
r
k
i
n
g
a
s
a
s
sista
n
t
p
r
o
fe
ss
o
r
,
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
(Cy
b
e
r
S
e
c
u
rit
y
),
M
a
ll
a
Re
d
d
y
E
n
g
i
n
e
e
rin
g
c
o
ll
e
g
e
,
M
e
d
c
h
a
l
,
Tela
n
g
a
n
a
.
He
o
b
tai
n
e
d
h
is
M
.
Tec
h
.
in
C
o
m
p
u
t
e
r
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
fro
m
JN
TU
Ka
k
in
a
d
a
,
a
n
d
h
a
s
g
o
o
d
p
u
b
li
c
a
ti
o
n
s
i
n
h
is
re
se
a
rc
h
a
re
a
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
k
k
a
n
th
3
8
8
7
@m
re
c
.
a
c
.
in
.
Um
a
Ma
h
e
sw
a
r
i
Ra
y
u
d
u
i
s
c
u
rre
n
tl
y
wo
r
k
i
n
g
a
n
a
ss
istan
t
p
r
o
fe
ss
o
r
a
t
KL
Un
iv
e
rsity
,
Va
d
d
e
sw
a
ra
m
.
S
h
e
c
o
m
p
lete
d
h
e
r
M
.
S
c
.
i
n
Ap
p
li
c
a
ti
o
n
Orie
n
ted
M
a
th
e
m
a
ti
c
s
a
n
d
c
o
m
p
lete
d
M
.
Tec
h
i
n
Co
m
p
u
ter
sc
ien
c
e
a
n
d
En
g
in
e
e
ri
n
g
.
S
h
e
h
a
s
1
3
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
tea
c
h
in
g
.
S
h
e
h
a
s
e
x
ten
si
v
e
e
x
p
e
rien
c
e
in
tea
c
h
in
g
su
b
jec
ts
li
k
e
e
n
g
in
e
e
rin
g
m
a
th
e
m
a
ti
c
s,
p
ro
b
a
b
il
it
y
a
n
d
sta
ti
stics
,
d
a
ta
wa
re
h
o
u
si
n
g
,
m
in
in
g
,
m
a
c
h
in
e
lea
rn
in
g
,
b
u
si
n
e
ss
a
n
a
ly
ti
c
s,
a
n
d
b
ig
d
a
ta
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
u
m
a
m
a
h
e
sw
a
ri@k
lu
n
i
v
e
rsity
.
i
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.