I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l
E
ng
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
6
,
No
.
3
,
Dec
em
b
er
20
24
,
p
p
.
1
8
9
5
~
1
903
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
6
.
i
3
.
pp
1
8
9
5
-
1
9
0
3
1895
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
DeepCerv
i
x
:
enh
a
ncing
cervica
l ca
ncer de
tec
tion th
r
o
ug
h
trans
fer
l
ea
rning
with
VG
G
-
16
a
rc
hitectu
re
Va
is
ha
li M
.
J
o
s
hi
1
,
P
ra
j
k
t
a
P
.
Da
nd
a
v
a
t
e
2
,
R.
Ra
s
hm
i
3
,
G
it
a
nja
li R.
Sh
ind
e
4
,
Nee
t
a
N.
T
hu
ne
5
,
Ridd
h
i Mi
ra
j
k
a
r
4
1
D
e
p
a
r
t
me
n
t
o
f
E
l
e
c
t
r
o
n
i
c
s a
n
d
T
e
l
e
c
o
mm
u
n
i
c
a
t
i
o
n
E
n
g
i
n
e
e
r
i
n
g
,
K
JEI
’
s T
r
i
n
i
t
y
A
c
a
d
e
my
o
f
En
g
i
n
e
e
r
i
n
g
,
P
u
n
e
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
V
i
sh
w
a
k
a
r
ma
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
P
u
n
e
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
T
e
l
e
c
o
mm
u
n
i
c
a
t
i
o
n
E
n
g
i
n
e
e
r
i
n
g
,
P
a
d
m
a
b
h
o
o
s
h
a
n
V
a
sa
n
t
d
a
d
a
P
a
t
i
l
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
P
u
n
e
,
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
En
g
i
n
e
e
r
i
n
g
,
V
i
sh
w
a
k
a
r
ma
I
n
st
i
t
u
t
e
o
f
I
n
f
o
r
ma
t
i
o
n
Te
c
h
n
o
l
o
g
y
,
P
u
n
e
,
I
n
d
i
a
5
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
T
e
l
e
c
o
mm
u
n
i
c
a
t
i
o
n
E
n
g
i
n
e
e
r
i
n
g
,
M
a
r
a
t
h
w
a
d
a
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
P
u
n
e
,
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
Ap
r
1
3
,
2
0
2
4
R
ev
is
ed
Au
g
1
9
,
2
0
2
4
Acc
ep
ted
Au
g
3
1
,
2
0
2
4
Ce
rv
ica
l
c
a
n
c
e
r
re
m
a
in
s
a
sig
n
ifi
c
a
n
t
g
lo
b
a
l
h
e
a
lt
h
c
o
n
c
e
rn
,
e
m
p
h
a
siz
in
g
th
e
u
rg
e
n
t
n
e
e
d
f
o
r
imp
r
o
v
e
d
d
e
tec
ti
o
n
m
e
th
o
d
s
to
e
n
s
u
re
ti
m
e
ly
t
re
a
tme
n
t.
Th
is
re
se
a
rc
h
in
tro
d
u
c
e
s
a
so
p
h
isti
c
a
ted
m
e
th
o
d
o
l
o
g
y
lev
e
ra
g
i
n
g
re
c
e
n
t
a
d
v
a
n
c
e
s
in
m
e
d
ica
l
ima
g
i
n
g
a
n
d
d
e
e
p
lea
rn
in
g
a
lg
o
rit
h
m
s
t
o
e
n
h
a
n
c
e
th
e
a
c
c
u
ra
c
y
a
n
d
e
fficie
n
c
y
o
f
c
e
rv
ic
a
l
c
a
n
c
e
r
d
e
tec
ti
o
n
.
Th
e
p
r
o
p
o
se
d
a
p
p
ro
a
c
h
c
o
m
p
rise
s
m
e
ti
c
u
lo
u
s
d
a
ta
p
re
p
ro
c
e
ss
in
g
to
e
n
s
u
re
th
e
in
teg
ri
t
y
o
f
in
p
u
t
ima
g
e
s,
fo
ll
o
we
d
b
y
t
h
e
trai
n
in
g
o
f
d
e
e
p
lea
rn
i
n
g
m
o
d
e
ls
i
n
c
lu
d
in
g
Re
sN
et
-
5
0
,
Ale
x
Ne
t,
a
n
d
VG
G
-
1
6
,
re
n
o
wn
e
d
fo
r
th
e
ir
p
e
rfo
rm
a
n
c
e
i
n
c
o
m
p
u
ter
v
isio
n
tas
k
s.
E
v
a
lu
a
ti
o
n
m
e
tri
c
s
su
c
h
a
s
a
c
c
u
ra
c
y
,
p
re
c
isio
n
,
r
e
c
a
ll
,
a
n
d
F1
-
sc
o
re
d
e
m
o
n
stra
te
th
e
e
ffica
c
y
o
f
th
e
m
e
th
o
d
o
lo
g
y
,
with
a
n
o
u
tstan
d
i
n
g
a
c
c
u
ra
c
y
ra
te
o
f
9
8
%
a
c
h
ie
v
e
d
.
Th
e
m
o
d
e
l
’
s
p
ro
ficie
n
c
y
in
a
c
c
u
ra
tely
d
isti
n
g
u
is
h
in
g
h
e
a
lt
h
y
c
e
rv
ica
l
ti
ss
u
e
fro
m
c
a
n
c
e
ro
u
s
ti
ss
u
e
is
u
n
d
e
rsc
o
re
d
b
y
p
re
c
isio
n
,
re
c
a
ll
,
a
n
d
F
1
-
sc
o
r
e
v
a
lu
e
s.
Th
e
p
rima
ry
stre
n
g
th
o
f
th
is
d
e
e
p
lea
rn
in
g
-
b
a
se
d
a
p
p
r
o
a
c
h
li
e
s
in
i
ts
p
o
ten
ti
a
l
fo
r
e
a
rly
d
e
tec
ti
o
n
,
p
ro
m
isin
g
sig
n
ifi
c
a
n
t
imp
a
c
t
o
n
c
e
rv
ica
l
c
a
n
c
e
r
d
iag
n
o
sis
a
n
d
trea
tme
n
t
o
u
tco
m
e
s.
Th
is
m
e
th
o
d
o
lo
g
y
c
o
n
tri
b
u
tes
to
a
d
v
a
n
c
e
m
e
n
ts
in
m
e
d
ica
l
ima
g
in
g
tec
h
n
iq
u
e
s,
fa
c
il
it
a
ti
n
g
imp
r
o
v
e
d
o
u
tco
m
e
s
in
c
e
rv
ica
l
c
a
n
c
e
r
d
e
t
e
c
ti
o
n
a
n
d
trea
tme
n
t.
K
ey
w
o
r
d
s
:
Alex
Net
C
er
v
ical
ca
n
ce
r
D
ee
p
lear
n
in
g
R
esNet
-
50
V
GG
-
16
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
:
Vaish
ali
M.
J
o
s
h
i
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics an
d
T
elec
o
m
m
u
n
icatio
n
E
n
g
in
ee
r
in
g
,
KJEI
’
s
,
T
r
in
ity
Aca
d
em
y
o
f
E
n
g
i
n
ee
r
in
g
Pu
n
e
4
1
1
0
4
8
,
Ma
h
ar
ash
tr
a,
I
n
d
ia
E
m
ail:
jo
s
h
iv
aish
ali7
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
C
er
v
ical
ca
n
ce
r
r
an
k
s
as
th
e
f
o
u
r
t
h
m
o
s
t
p
r
e
v
alen
t
ca
n
ce
r
in
wo
m
en
wo
r
ld
wid
e
a
n
d
r
em
ain
s
a
lead
in
g
ca
u
s
e
o
f
ca
n
ce
r
-
r
elate
d
m
o
r
tality
,
with
p
r
o
jectio
n
s
e
s
tim
atin
g
6
0
4
,
0
0
0
n
ew
ca
s
es
an
d
3
4
2
,
0
0
0
d
ea
th
s
g
lo
b
ally
in
2
0
2
0
[
1
]
.
T
h
e
h
ig
h
m
o
r
tality
r
ate
p
r
i
m
ar
ily
s
te
m
s
f
r
o
m
late
d
iag
n
o
s
es,
em
p
h
asizin
g
th
e
cr
itical
im
p
o
r
tan
ce
o
f
ea
r
ly
d
etec
tio
n
an
d
s
cr
ee
n
in
g
i
n
itiativ
es.
W
h
ile
tr
ad
itio
n
al
s
cr
ee
n
in
g
m
eth
o
d
s
lik
e
Pap
s
m
ea
r
test
s
h
av
e
d
em
o
n
s
tr
ated
ef
f
ica
cy
in
r
ed
u
cin
g
ce
r
v
ical
ca
n
ce
r
r
is
k
,
th
ey
ar
e
in
h
er
en
tly
r
elian
t
o
n
th
e
e
x
p
er
tis
e
o
f
h
ea
lth
ca
r
e
p
r
o
f
ess
io
n
als
an
d
ca
n
b
e
s
u
b
ject
t
o
s
u
b
jectiv
e
in
ter
p
r
etatio
n
,
lead
in
g
to
p
o
ten
tial
f
alse
n
eg
ativ
es
o
r
p
o
s
itiv
es
[
2
]
–
[
4
]
.
I
n
r
ec
en
t
y
ea
r
s
,
d
ee
p
lear
n
in
g
(
DL
)
alg
o
r
ith
m
s
h
av
e
g
a
r
n
er
e
d
in
cr
e
asin
g
atten
tio
n
f
o
r
th
eir
p
o
ten
tial
r
o
le
in
au
to
m
a
tin
g
th
e
id
en
tific
atio
n
an
d
d
ia
g
n
o
s
is
o
f
ce
r
v
ical
ca
n
ce
r
[
5
]
,
[
6
]
.
DL
lev
er
ag
es
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
to
an
aly
ze
d
ata
an
d
g
e
n
er
ate
p
r
ed
ictio
n
s
,
ex
h
ib
itin
g
n
o
tab
le
s
u
c
ce
s
s
ac
r
o
s
s
v
ar
io
u
s
d
o
m
ain
s
,
p
ar
ticu
lar
ly
i
n
m
e
d
ical
im
ag
in
g
.
DL
alg
o
r
ith
m
s
ex
ce
l
in
r
ec
o
g
n
izin
g
s
u
b
tle
p
atter
n
s
an
d
d
etails
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
6
,
No
.
3
,
Dec
em
b
er
20
24
:
1
8
9
5
-
1
9
0
3
1896
with
in
im
ag
es,
s
u
r
p
ass
in
g
h
u
m
an
p
er
ce
p
t
u
al
ca
p
ab
ilit
ies
an
d
en
h
an
ci
n
g
th
e
p
r
ec
is
io
n
an
d
r
eliab
ilit
y
o
f
ca
n
ce
r
d
iag
n
o
s
is
[
7
]
–
[
9
]
.
L
itjen
s
et
a
l.
[
1
0
]
s
u
r
v
ey
ed
th
e
u
s
e
o
f
d
ee
p
lear
n
in
g
in
im
a
g
e
an
aly
s
is
,
u
n
d
er
lin
in
g
th
e
p
r
o
s
p
ec
t
o
f
th
is
tech
n
iq
u
e
f
o
r
e
n
h
an
cin
g
d
iag
n
o
s
tic
ac
cu
r
ac
y
an
d
tr
ea
tm
en
t
in
a
v
ar
iety
o
f
m
e
d
ical
s
p
ec
ialties
.
Xu
e
et
a
l.
[
1
1
]
o
f
f
er
e
d
an
ex
ten
s
iv
e
r
ev
i
ew
o
f
th
e
u
tili
za
tio
n
o
f
DL
m
eth
o
d
s
in
th
e
d
etec
tio
n
o
f
ce
r
v
ical
ca
n
ce
r
.
T
h
e
y
d
is
cu
s
s
ed
th
e
ad
v
an
tag
es
a
n
d
ch
allen
g
es
ass
o
ciate
d
with
t
h
e
s
e
ap
p
r
o
ac
h
es,
in
clu
d
in
g
th
e
r
eq
u
ir
em
en
t
f
o
r
a
lo
t
o
f
g
o
o
d
d
ata,
th
e
p
o
ten
tial
f
o
r
b
ias
an
d
o
v
er
f
itti
n
g
,
an
d
th
e
i
m
p
o
r
tan
ce
o
f
in
ter
p
r
etab
ilit
y
an
d
tr
a
n
s
p
ar
en
cy
in
m
ed
ical
d
ec
is
io
n
-
m
ak
i
n
g
u
s
in
g
m
u
lti
-
p
ar
a
m
etr
ic
m
ag
n
etic
r
eso
n
an
ce
im
ag
i
n
g
(
MRI)
d
at
a.
J
ian
g
et
a
l.
[
1
2
]
d
ev
elo
p
e
d
DL
-
b
ased
r
ad
io
m
ic
alg
o
r
ith
m
s
to
d
is
tin
g
u
is
h
b
etwe
en
v
ess
el
in
v
asio
n
an
d
n
o
n
-
v
ess
el
in
v
asio
n
i
n
ce
r
v
ical
ca
n
ce
r
.
No
v
itas
ar
i
et
a
l.
[
1
3
]
p
r
o
p
o
s
ed
a
ce
r
v
ical
ca
n
ce
r
d
ia
g
n
o
s
is
s
y
s
tem
th
at
u
s
es
g
r
ay
lev
el
co
-
o
cc
u
r
r
e
n
ce
m
atr
ix
tech
n
iq
u
es
.
T
h
e
s
y
s
tem
ac
h
iev
ed
an
ac
cu
r
ac
y
o
f
9
5
%
u
s
in
g
a
g
au
s
s
ian
k
er
n
el
in
d
etec
tin
g
ab
n
o
r
m
al
ce
lls
,
d
em
o
n
s
tr
atin
g
its
p
o
ten
tial
as
a
u
s
ef
u
l
to
o
l
f
o
r
ce
r
v
ical
ca
n
ce
r
s
cr
ee
n
i
n
g
.
Pau
l
e
t
a
l.
[
1
4
]
em
p
lo
y
ed
a
n
ad
ap
ti
v
e
m
ed
ia
n
f
ilter
to
ef
f
ec
tiv
ely
elim
i
n
a
te
im
p
u
ls
e
n
o
is
es
p
r
esen
t
in
Pap
s
m
ea
r
im
ag
es.
Su
b
s
eq
u
en
tly
,
th
ey
u
tili
ze
d
a
b
i
-
g
r
o
u
p
en
h
an
ce
r
to
d
i
f
f
er
e
n
tiate
b
etwe
en
n
u
cleu
s
p
ix
el
s
an
d
o
t
h
er
o
b
ject
p
ix
els.
Fo
llo
win
g
th
is
,
a
s
eg
m
en
tatio
n
m
eth
o
d
o
lo
g
y
was
ap
p
lied
to
is
o
late
th
e
n
u
cleu
s
r
eg
io
n
s
with
in
th
e
c
e
r
v
i
c
a
l
s
m
e
a
r
i
m
a
g
e
s
.
T
h
e
m
et
h
o
d
o
l
o
g
y
d
e
m
o
n
s
t
r
a
t
e
d
a
n
i
m
p
r
e
s
s
i
v
e
a
cc
u
r
a
c
y
r
a
t
e
o
f
9
8
.
3
7
%
.
C
h
a
n
k
o
n
g
e
t
a
l
.
[
1
5
]
in
tr
o
d
u
ce
d
a
m
eth
o
d
f
o
r
au
to
m
atic
s
eg
m
en
tatio
n
a
n
d
c
lass
if
icatio
n
o
f
ce
r
v
ical
ca
n
ce
r
ce
lls
,
em
p
l
o
y
in
g
th
e
f
u
zz
y
C
-
m
ea
n
s
(
FC
M)
clu
s
ter
in
g
tech
n
iq
u
e.
T
h
e
y
v
alid
ated
th
eir
ap
p
r
o
ac
h
u
s
in
g
ar
tific
ial
n
eu
r
al
n
etwo
r
ks
(
ANNs)
,
ac
h
ie
v
in
g
ac
cu
r
ac
ies
o
f
9
3
.
7
8
%
f
o
r
th
e
7
-
class
p
r
o
b
lem
a
n
d
9
9
.
2
7
%
f
o
r
th
e
2
-
class
p
r
o
b
lem
.
W
h
ile
p
r
ev
io
u
s
s
tu
d
ies
h
av
e
h
ig
h
lig
h
ted
th
e
p
o
ten
tial
o
f
D
L
tech
n
iq
u
es
in
e
n
h
an
cin
g
th
e
p
r
ec
is
io
n
an
d
ef
f
ec
tiv
en
ess
o
f
ce
r
v
ical
ca
n
ce
r
s
cr
ee
n
in
g
,
d
iag
n
o
s
is
,
an
d
class
if
icatio
n
[
1
6
]
,
[
1
7
]
,
t
h
er
e
ar
e
s
till
s
ev
er
al
g
ap
s
in
th
e
liter
atu
r
e
th
at
n
ee
d
to
b
e
ad
d
r
ess
ed
.
On
e
m
ajo
r
g
ap
is
th
e
lack
o
f
ex
ten
s
iv
e
r
esear
ch
s
p
ec
if
ically
f
o
cu
s
in
g
o
n
th
e
u
tili
za
tio
n
o
f
DL
f
o
r
ce
r
v
ical
ca
n
ce
r
id
e
n
tific
atio
n
,
p
ar
ticu
lar
ly
in
ter
m
s
o
f
its
p
r
ac
tical
im
p
lem
en
tatio
n
a
n
d
co
m
p
a
r
ativ
e
an
aly
s
is
with
tr
ad
itio
n
al
s
cr
ee
n
in
g
m
eth
o
d
s
.
Ad
d
itio
n
al
ly
,
th
er
e
is
a
n
ee
d
f
o
r
m
o
r
e
s
tu
d
ies
th
at
in
v
esti
g
ate
th
e
s
ca
lab
ilit
y
an
d
f
ea
s
ib
ilit
y
o
f
in
teg
r
atin
g
DL
al
g
o
r
ith
m
s
in
to
ex
is
tin
g
s
cr
ee
n
in
g
p
r
o
ce
s
s
es,
esp
ec
iall
y
in
r
eg
i
o
n
s
with
lim
ited
ac
ce
s
s
to
h
ea
lth
ca
r
e
r
eso
u
r
ce
s
.
Ou
r
s
tu
d
y
ad
d
r
ess
es
th
ese
r
es
ea
r
ch
g
ap
s
b
y
p
r
o
p
o
s
in
g
a
m
eth
o
d
o
lo
g
y
f
o
r
u
tili
zin
g
DL
s
p
ec
if
ically
f
o
r
ce
r
v
ical
ca
n
ce
r
id
e
n
tific
atio
n
.
W
e
co
n
tr
ib
u
te
b
y
d
ev
elo
p
in
g
a
co
m
p
r
eh
e
n
s
iv
e
ap
p
r
o
ac
h
th
at
in
clu
d
es
d
ata
p
r
e
-
p
r
o
ce
s
s
in
g
,
m
o
d
el
tr
ain
in
g
,
an
d
m
o
d
el
ev
alu
atio
n
u
s
i
n
g
v
ar
io
u
s
m
etr
ics.
B
y
em
p
l
o
y
in
g
well
-
k
n
o
wn
co
n
v
o
l
u
tio
n
al
n
e
u
r
al
n
etwo
r
k
ar
ch
itectu
r
es
lik
e
R
esNet
-
5
0
,
Alex
Net,
an
d
v
is
u
al
g
e
o
m
etr
y
g
r
o
u
p
(
VGG
)
-
1
6
,
we
p
r
o
v
id
e
i
n
s
ig
h
ts
in
to
t
h
e
co
m
p
ar
ativ
e
ef
f
ec
tiv
e
n
ess
o
f
th
ese
m
o
d
els
f
o
r
ce
r
v
ical
ca
n
ce
r
id
e
n
tific
atio
n
.
Ad
d
itio
n
ally
,
we
h
ig
h
lig
h
t
th
e
p
o
ten
tial
b
en
ef
its
o
f
in
te
g
r
atin
g
DL
alg
o
r
ith
m
s
in
to
ex
is
tin
g
s
cr
ee
n
in
g
p
r
o
ce
s
s
es,
s
u
ch
as
i
n
cr
ea
s
e
d
s
cr
ee
n
in
g
e
f
f
icien
cy
,
o
b
jectiv
ity
in
a
n
aly
s
is
,
an
d
th
e
ab
ilit
y
to
id
e
n
tify
p
r
ec
an
ce
r
o
u
s
lesi
o
n
s
at
ea
r
lier
s
tag
es.
Ou
r
r
esear
ch
co
n
tr
ib
u
tes
to
ad
v
an
cin
g
th
e
u
n
d
er
s
ta
n
d
in
g
o
f
DL
’
s
r
o
le
in
ce
r
v
ical
ca
n
ce
r
s
cr
ee
n
in
g
a
n
d
p
r
o
v
id
es
p
r
ac
tical
im
p
licat
io
n
s
f
o
r
im
p
r
o
v
in
g
p
atien
t
o
u
t
co
m
es,
p
ar
ticu
lar
l
y
in
r
eso
u
r
ce
-
c
o
n
s
tr
ain
ed
s
ettin
g
s
.
2.
M
E
T
H
O
DS A
ND
M
A
T
E
R
I
AL
T
h
e
p
r
im
ar
y
o
b
jectiv
e
o
f
th
is
s
tu
d
y
is
to
e
n
h
an
ce
th
e
ac
cu
r
ac
y
a
n
d
au
to
m
atio
n
o
f
ce
r
v
i
ca
l
ca
n
ce
r
d
etec
tio
n
an
d
d
ia
g
n
o
s
is
th
r
o
u
g
h
th
e
u
tili
za
tio
n
o
f
DL
a
p
p
r
o
ac
h
es.
B
y
h
a
r
n
ess
in
g
th
e
ca
p
ab
ilit
ies
o
f
th
ese
ad
v
an
ce
d
m
eth
o
d
s
,
o
u
r
aim
is
to
s
tr
ea
m
lin
e
t
h
e
p
r
o
ce
s
s
o
f
ea
r
ly
d
etec
tio
n
an
d
tr
ea
tm
en
t
o
f
ce
r
v
ical
ca
n
ce
r
,
u
ltima
tely
co
n
tr
ib
u
tin
g
t
o
a
r
e
d
u
ctio
n
i
n
its
m
o
r
tality
r
ate.
F
ig
u
r
e
1
illu
s
tr
ates
th
e
wo
r
k
f
lo
w
o
f
o
u
r
p
r
o
p
o
s
ed
wo
r
k
,
s
h
o
wca
s
in
g
th
e
v
a
r
io
u
s
s
tag
es
in
v
o
lv
ed
in
o
u
r
ap
p
r
o
a
ch
to
lev
er
ag
in
g
DL
f
o
r
ce
r
v
ic
al
ca
n
ce
r
d
etec
tio
n
an
d
d
iag
n
o
s
is
.
T
h
r
o
u
g
h
t
h
is
co
m
p
r
eh
e
n
s
iv
e
wo
r
k
f
lo
w,
we
s
ee
k
to
estab
lis
h
a
r
o
b
u
s
t
f
r
am
ewo
r
k
th
at
en
a
b
les
ef
f
icien
t
an
d
ac
c
u
r
ate
i
d
en
tifi
ca
tio
n
o
f
ce
r
v
ical
ca
n
ce
r
,
t
h
e
r
eb
y
im
p
r
o
v
in
g
p
atien
t
o
u
tc
o
m
es
an
d
ad
v
a
n
cin
g
th
e
f
ield
o
f
ca
n
ce
r
d
etec
tio
n
a
n
d
tr
ea
tm
en
t.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
c
o
m
p
r
is
es
k
ey
s
tep
s
,
in
clu
d
in
g
d
atab
ase
co
llectio
n
,
p
r
o
ce
s
s
in
g
,
f
ea
tu
r
e
ex
tr
ac
tio
n
,
an
d
class
if
icatio
n
,
with
a
f
o
cu
s
o
n
u
tili
zin
g
th
e
Har
lev
b
en
ch
m
ar
k
d
atab
ase
f
o
r
ce
r
v
ical
ca
n
ce
r
d
etec
tio
n
.
R
ig
o
r
o
u
s
p
r
e
-
p
r
o
ce
s
s
in
g
was c
o
n
d
u
cted
to
elim
in
ate
p
o
ten
tial n
o
is
e
an
d
a
r
tifa
cts,
en
s
u
r
in
g
ac
cu
r
ate
im
ag
e
an
aly
s
is
.
I
n
th
e
s
u
b
s
eq
u
en
t
p
h
ase,
R
esNet
-
5
0
,
Alex
Net,
an
d
VGG
-
16
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN
)
ar
ch
itectu
r
es
wer
e
em
p
lo
y
ed
t
o
tr
ain
t
h
e
DL
m
o
d
el.
B
in
ar
y
cr
o
s
s
-
en
tr
o
p
y
lo
s
s
f
u
n
ctio
n
an
d
th
e
Ad
am
o
p
tim
izer
wer
e
u
tili
ze
d
f
o
r
b
i
n
ar
y
class
if
icatio
n
p
r
o
b
lem
s
,
allo
win
g
th
e
m
o
d
el
to
id
e
n
tif
y
o
p
tim
al
weig
h
ts
an
d
b
iases
to
m
in
im
ize
clas
s
i
f
icatio
n
er
r
o
r
s
.
T
h
e
ad
ap
ti
v
e
lear
n
in
g
r
ate
o
p
tim
izatio
n
f
ea
tu
r
e
o
f
th
e
Ad
am
o
p
tim
izer
co
n
tr
i
b
u
ted
to
en
h
a
n
ce
d
m
o
d
el
p
er
f
o
r
m
an
ce
.
T
h
e
th
ir
d
p
h
ase
in
v
o
lv
ed
a
th
o
r
o
u
g
h
ev
alu
atio
n
o
f
th
e
tr
ain
ed
m
o
d
el
’
s
p
er
f
o
r
m
an
ce
u
s
in
g
k
e
y
m
etr
ics
s
u
ch
as
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e.
R
ec
eiv
er
o
p
er
atin
g
ch
ar
ac
te
r
is
tic
(
R
OC
)
an
d
ar
ea
u
n
d
er
th
e
c
u
r
v
e
(
A
UC
)
cu
r
v
es
wer
e
g
en
e
r
ated
t
o
ass
ess
th
e
m
o
d
el
’
s
ab
ilit
y
to
d
if
f
er
en
tiate
b
etwe
en
ce
r
v
ical
ca
n
ce
r
an
d
n
o
r
m
al
ce
r
v
ical
tis
s
u
e,
p
r
o
v
id
in
g
a
v
is
u
al
r
ep
r
esen
tatio
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
Dee
p
C
ervix:
en
h
a
n
cin
g
ce
r
vic
a
l c
a
n
ce
r
d
etec
tio
n
t
h
r
o
u
g
h
…
(
V
a
is
h
a
li M.
Jo
s
h
i
)
1897
o
f
its
p
er
f
o
r
m
a
n
ce
in
d
if
f
e
r
e
n
tiatin
g
tr
u
e
p
o
s
itiv
e
a
n
d
f
alse
p
o
s
itiv
e
r
ates.
T
h
is
m
et
h
o
d
o
lo
g
y
h
as
b
ee
n
m
eticu
lo
u
s
ly
d
esig
n
ed
to
ad
d
r
ess
ch
allen
g
es
r
elate
d
to
d
ata
v
ar
iab
ilit
y
,
m
o
d
el
co
m
p
lex
ity
,
an
d
in
ter
p
r
etab
ilit
y
,
ess
en
tial
f
o
r
d
ev
elo
p
in
g
a
clin
ically
r
ele
v
an
t
an
d
d
ep
en
d
ab
le
ce
r
v
ical
ca
n
c
er
d
etec
tio
n
m
o
d
el.
Vis
u
al
r
ep
r
esen
tatio
n
s
o
f
ca
n
ce
r
o
u
s
an
d
n
o
n
-
ca
n
ce
r
o
u
s
im
ag
es
in
Fig
u
r
es
2
an
d
3
f
u
r
th
er
illu
s
tr
ate
th
e
o
u
tco
m
es
o
f
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
.
I
n
s
u
m
m
ar
y
,
th
e
m
et
h
o
d
o
lo
g
y
aim
s
to
ad
v
a
n
ce
m
ed
i
ca
l
im
ag
e
an
aly
s
is
an
d
d
iag
n
o
s
is
,
o
f
f
er
i
n
g
a
c
o
m
p
r
eh
en
s
iv
e
f
r
am
ewo
r
k
f
o
r
au
t
o
m
ated
ce
r
v
ical
ca
n
ce
r
d
etec
ti
o
n
.
Fig
u
r
e
1
.
W
o
r
k
f
lo
w
o
f
p
r
o
p
o
s
ed
wo
r
k
Fig
u
r
e
2
.
C
an
ce
r
o
u
s
i
m
ag
es
Fig
u
r
e
3
.
No
n
-
ca
n
ce
r
o
u
s
im
ag
es
2
.1
.
Da
t
a
ba
s
e:
H
er
lev
d
a
t
a
s
et
T
h
e
Her
lev
d
ataset,
d
e
v
elo
p
e
d
b
y
Her
lev
Un
iv
er
s
ity
H
o
s
p
ital,
is
a
s
ig
n
if
ican
t
r
eso
u
r
ce
f
o
r
r
esear
c
h
in
ce
r
v
ical
ca
n
ce
r
d
etec
tio
n
a
n
d
d
iag
n
o
s
tics
[
1
8
]
.
T
h
is
d
ata
s
et
is
r
ea
d
ily
ac
ce
s
s
ib
le
f
o
r
r
e
s
ea
r
ch
p
u
r
p
o
s
es
an
d
o
f
f
er
s
a
r
o
b
u
s
t
f
o
u
n
d
atio
n
f
o
r
d
ev
elo
p
in
g
an
d
test
in
g
a
u
to
m
ated
d
etec
tio
n
s
y
s
tem
s
.
T
h
e
Her
lev
Pap
s
m
ea
r
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
6
,
No
.
3
,
Dec
em
b
er
20
24
:
1
8
9
5
-
1
9
0
3
1898
d
ataset
co
m
p
r
is
es
9
1
7
s
in
g
le
-
ce
ll
ce
r
v
ical
im
ag
es,
ca
p
t
u
r
ed
at
a
h
ig
h
r
eso
lu
tio
n
o
f
0
.
2
0
1
µm
p
er
p
ix
el
u
s
in
g
ad
v
an
ce
d
m
icr
o
s
co
p
es a
n
d
d
ig
ital c
am
er
as.
T
h
e
im
ag
es a
r
e
o
b
tain
ed
th
r
o
u
g
h
co
n
v
en
tio
n
al
Pap
s
m
ea
r
s
tain
in
g
an
d
p
r
o
ce
s
s
in
g
m
eth
o
d
s
,
en
s
u
r
in
g
co
n
s
is
ten
cy
an
d
r
eliab
ilit
y
in
th
e
d
ata.
T
h
e
d
ataset
in
clu
d
es
s
ev
en
d
is
tin
ct
s
tag
e
class
if
icatio
n
s
to
f
ac
ilit
a
te
ac
cu
r
ate
d
iag
n
o
s
is
:
i)
Su
p
er
f
icial
Sq
u
am
o
u
s
7
4
:
n
o
r
m
al
ce
lls
.
ii)
I
n
ter
m
ed
iate
Sq
u
a
m
o
u
s
7
0
:
n
o
r
m
al
ce
lls
.
iii)
C
o
lu
m
n
ar
Sq
u
am
o
u
s
9
8
:
n
o
r
m
al
ce
lls
.
i
v
)
Mild
d
y
s
p
lasi
a
1
8
2
:
a
b
n
o
r
m
al.
v)
Mo
d
er
ate
d
y
s
p
lasi
a
1
4
6
:
a
b
n
o
r
m
al.
v
i
)
Sev
er
e
d
y
s
p
lasi
a
1
9
7
:
a
b
n
o
r
m
al.
v
i
i
)
C
ar
cin
o
m
a
in
s
itu
1
5
0
:
a
b
n
o
r
m
al.
T
h
ese
class
if
icatio
n
s
ar
e
f
u
r
th
er
g
r
o
u
p
e
d
in
to
two
m
ain
ca
teg
o
r
ies:
b
en
ig
n
(
class
es
1
-
3
)
an
d
m
alig
n
an
t
(
class
es
4
-
7
)
.
T
h
is
ca
teg
o
r
izatio
n
s
u
p
p
o
r
ts
th
e
d
e
v
elo
p
m
en
t
o
f
m
o
d
els
th
at
ca
n
d
is
tin
g
u
is
h
b
etwe
e
n
h
ea
lth
y
an
d
p
o
ten
tially
ca
n
ce
r
o
u
s
ce
lls
.
On
e
o
f
th
e
k
ey
f
e
atu
r
es
u
s
ed
f
o
r
class
if
icatio
n
with
in
th
e
Her
lev
d
ataset
is
th
e
s
ig
n
if
ican
t
s
ize
d
if
f
er
en
ce
in
th
e
n
u
clei
o
f
a
b
n
o
r
m
al
o
r
m
alig
n
an
t
ce
lls
co
m
p
ar
ed
to
n
o
r
m
al
ce
lls
.
Ma
lig
n
an
t c
ells
o
f
ten
ex
h
ib
it lar
g
er
n
u
clei
with
ir
r
eg
u
lar
s
h
ap
es a
n
d
in
cr
ea
s
ed
ch
r
o
m
atin
co
n
ten
t,
wh
ich
ar
e
cr
itical
in
d
icato
r
s
f
o
r
au
to
m
ated
d
etec
tio
n
s
y
s
tem
s
.
2
.
2
.
Seg
m
ent
a
t
i
o
n
I
n
Pap
s
m
ea
r
ce
ll
im
ag
es,
b
o
t
h
th
e
n
u
cle
u
s
an
d
cy
to
p
lasm
a
r
e
p
r
esen
t,
an
d
th
e
ch
a
r
ac
ter
is
tics
o
f
th
e
n
u
cleu
s
,
s
u
ch
as
s
ize
an
d
s
h
a
p
e,
p
lay
a
cr
u
cial
r
o
le
i
n
d
ete
r
m
in
in
g
w
h
eth
er
a
ce
ll
is
p
ath
o
lo
g
ical
o
r
n
o
r
m
al.
T
o
an
aly
ze
th
e
p
r
o
p
er
ties
o
f
th
e
n
u
cleu
s
,
a
s
p
ec
if
ic
p
o
r
tio
n
o
f
th
e
im
a
g
e
n
ee
d
s
to
b
e
ex
t
r
ac
ted
,
a
n
d
s
eg
m
en
tatio
n
is
em
p
lo
y
e
d
t
o
id
en
tify
t
h
e
r
eg
io
n
o
f
in
t
er
est
[
1
9
]
,
[
2
0
]
.
T
h
e
e
x
tr
ac
t
io
n
o
f
b
ac
k
g
r
o
u
n
d
,
cy
to
p
lasm,
an
d
n
u
cleu
s
f
r
o
m
s
in
g
le
-
ce
ll
Pap
s
m
ea
r
im
a
g
es
in
v
o
lv
es
a
s
eg
m
en
tatio
n
p
r
o
c
ess
.
T
h
e
s
m
ea
r
ce
ll
im
ag
e
ty
p
ically
co
n
s
is
ts
o
f
th
r
ee
r
eg
io
n
s
:
cy
to
p
lasm,
n
u
cleu
s
,
an
d
b
ac
k
g
r
o
u
n
d
.
Fo
r
a
m
o
r
e
d
etailed
an
aly
s
is
,
it
is
im
p
er
ativ
e
to
s
eg
m
en
t
th
e
cy
to
p
lasm
an
d
n
u
cle
u
s
r
eg
io
n
s
.
T
h
e
n
u
cleu
s
ar
ea
s
ar
e
s
eg
m
en
ted
u
s
in
g
th
e
k
-
m
ea
n
s
clu
s
ter
in
g
tech
n
iq
u
e,
f
o
llo
wed
b
y
m
o
r
p
h
o
lo
g
ical
p
r
o
c
ed
u
r
es.
T
h
e
k
-
m
ea
n
s
clu
s
ter
in
g
tech
n
iq
u
e
u
tili
ze
s
th
e
E
u
clid
ea
n
d
is
tan
ce
m
etr
ic
to
p
ar
titi
o
n
item
s
in
to
two
g
r
o
u
p
s
.
I
n
itially
,
K
cl
u
s
ter
ce
n
ter
s
ar
e
ch
o
s
en
,
an
d
d
ata
p
o
in
ts
ar
e
d
iv
i
d
ed
in
t
o
K
clu
s
ter
s
b
ased
o
n
th
eir
p
r
o
x
im
ity
to
th
ese
ce
n
ter
s
.
T
h
e
E
u
clid
ea
n
d
is
tan
ce
m
etr
ic
is
em
p
lo
y
ed
to
d
eter
m
in
e
p
r
o
x
im
ity
.
T
h
e
p
r
o
ce
s
s
is
iter
ated
u
n
til th
er
e
a
r
e
n
o
f
u
r
t
h
er
ch
an
g
es to
th
e
clu
s
ter
ce
n
te
r
s
.
T
h
e
s
tag
es o
f
th
e
k
-
m
ea
n
s
alg
o
r
ith
m
in
clu
d
e:
1)
C
r
ea
te
a
h
is
to
g
r
am
o
f
i
n
ten
s
ity
lev
els.
2)
Set K
clu
s
ter
ce
n
ter
s
’
r
an
d
o
m
in
ten
s
ities
to
K
f
o
r
ea
ch
clu
s
te
r
.
3)
R
ep
ea
t step
s
1
-
3
u
n
til th
e
clu
s
ter
ce
n
ter
s
r
em
ain
th
e
s
am
e.
4)
Fo
r
ea
ch
p
ix
el,
d
eter
m
in
e
th
e
d
is
tan
ce
b
etwe
en
ea
ch
clu
s
ter
’
s
ce
n
ter
an
d
th
e
s
ig
n
al
in
ten
s
ity
,
ass
ig
n
in
g
th
e
s
ig
n
al
to
th
e
clo
s
est clu
s
ter
.
5)
Dete
r
m
in
e
th
e
n
ew
clu
s
ter
ce
n
ter
s
b
y
av
er
a
g
in
g
all
clu
s
ter
m
em
b
er
s
.
T
h
e
o
u
tco
m
e
o
f
th
e
k
-
m
ea
n
s
m
eth
o
d
is
th
e
s
eg
m
en
tatio
n
o
f
th
e
n
u
cleu
s
r
eg
io
n
f
r
o
m
th
e
c
er
v
ical
ce
ll
im
ag
e.
T
h
is
r
esu
lt
u
n
d
er
g
o
es
m
o
r
p
h
o
lo
g
ical
p
r
o
ce
s
s
es,
s
p
ec
if
ically
er
o
s
io
n
a
n
d
m
o
r
p
h
o
lo
g
ical
r
ec
o
n
s
tr
u
ctio
n
,
to
ac
cu
r
ately
s
eg
m
en
t
th
e
n
u
cle
u
s
r
eg
io
n
.
T
h
ese
p
r
o
ce
s
s
es
co
n
tr
ib
u
te
to
a
r
ef
in
ed
an
aly
s
is
o
f
th
e
ce
llu
lar
co
m
p
o
n
e
n
ts
,
aid
in
g
in
th
e
d
iag
n
o
s
is
an
d
s
tu
d
y
o
f
p
ath
o
lo
g
ical
co
n
d
itio
n
s
.
2
.
3
.
Net
w
o
rk
a
rc
hite
ct
ures
2
.
3
.1
.
VG
G
-
16
T
h
e
VGG
-
1
6
n
etwo
r
k
a
r
ch
i
tectu
r
e
g
ain
ed
p
r
o
m
in
en
ce
wh
en
it
was
in
tr
o
d
u
ce
d
b
y
th
e
v
is
u
al
g
eo
m
etr
y
g
r
o
u
p
at
Ox
f
o
r
d
Un
iv
er
s
ity
f
o
r
th
e
I
m
ag
eNe
t
I
L
S
VR
C
-
2
0
1
4
co
m
p
etitio
n
.
No
ta
b
ly
,
VGG
-
1
6
s
to
o
d
o
u
t
am
o
n
g
its
co
n
tem
p
o
r
ar
ie
s
d
u
e
to
its
r
em
ar
k
a
b
le
d
e
p
t
h
,
a
c
h
ar
ac
ter
is
tic
th
at
r
esu
lt
ed
in
a
s
u
b
s
tan
tial
in
cr
ea
s
e
in
th
e
n
u
m
b
er
o
f
p
ar
am
eter
s
.
T
o
m
an
a
g
e
th
is
p
ar
am
eter
in
c
r
ea
s
e,
VGG
-
1
6
ad
o
p
ted
a
s
tr
ateg
ic
ap
p
r
o
ac
h
b
y
u
s
in
g
s
m
all
3
×
3
co
n
v
o
l
u
tio
n
al
f
ilter
s
with
a
s
tr
id
e
o
f
1
a
n
d
p
ad
d
in
g
o
f
1
f
o
r
all
its
co
n
v
o
lu
tio
n
al
l
a
y
e
r
s
.
T
h
is
d
e
s
i
g
n
c
h
o
i
c
e
e
n
s
u
r
e
d
t
h
a
t
t
h
e
s
p
at
i
al
d
i
m
e
n
s
i
o
n
s
o
f
t
h
e
i
n
p
u
t
w
e
r
e
n
o
t
s
i
g
n
i
f
i
c
a
n
t
l
y
r
e
d
u
c
e
d
[
2
1
]
.
I
n
th
e
VGG
-
1
6
ar
ch
itectu
r
e,
t
h
e
co
n
v
o
l
u
tio
n
al
lay
er
s
wer
e
s
tr
u
ctu
r
ed
in
to
clu
s
ter
s
co
m
p
r
is
in
g
two
o
r
th
r
ee
lay
er
s
.
Af
ter
ea
c
h
clu
s
ter
,
m
ax
p
o
o
lin
g
was
ap
p
lie
d
to
d
o
wn
s
am
p
le
th
e
in
p
u
t,
co
n
tr
ib
u
tin
g
to
th
e
n
etwo
r
k
’
s
ab
ilit
y
to
ca
p
tu
r
e
a
n
d
lear
n
h
ie
r
ar
ch
ical
f
ea
tu
r
es
ef
f
ec
tiv
ely
.
T
o
war
d
s
th
e
latter
p
ar
t
o
f
th
e
VGG
-
1
6
n
etwo
r
k
,
th
r
ee
f
u
lly
co
n
n
ec
te
d
(
FC
)
lay
e
r
s
wer
e
in
co
r
p
o
r
at
ed
,
f
o
llo
wed
b
y
a
So
f
tMa
x
la
y
er
.
T
h
ese
FC
lay
er
s
p
lay
ed
a
cr
u
cial
r
o
le
in
lear
n
in
g
h
ig
h
-
lev
el
f
ea
tu
r
es
a
n
d
m
ak
in
g
p
r
ed
ictio
n
s
b
ased
o
n
th
e
lear
n
ed
r
ep
r
esen
tatio
n
s
.
T
h
e
So
f
tMa
x
lay
er
p
r
o
d
u
ce
d
th
e
f
in
al
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
ac
r
o
s
s
d
if
f
er
en
t
class
es
in
th
e
class
if
icatio
n
task
.
Ov
er
all,
V
GG
-
1
6
g
ain
e
d
wid
esp
r
ea
d
r
e
co
g
n
itio
n
f
o
r
its
d
ep
th
an
d
p
a
r
am
eter
ef
f
icien
cy
,
ac
h
iev
ed
th
r
o
u
g
h
th
e
u
tili
za
tio
n
o
f
s
m
all
f
ilter
s
,
th
e
p
r
eser
v
atio
n
o
f
in
p
u
t
d
im
en
s
io
n
s
,
a
n
d
th
e
in
c
o
r
p
o
r
atio
n
o
f
clu
s
ter
ed
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
,
as d
ep
icted
in
Fig
u
r
e
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
Dee
p
C
ervix:
en
h
a
n
cin
g
ce
r
vic
a
l c
a
n
ce
r
d
etec
tio
n
t
h
r
o
u
g
h
…
(
V
a
is
h
a
li M.
Jo
s
h
i
)
1899
Fig
u
r
e
4.
VGG
-
1
6
ar
ch
itectu
r
e
2
.
3
.2
.
Alex
Net
Alex
Net,
a
d
ee
p
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(D
C
NN
)
ar
ch
itectu
r
e
d
ep
icted
in
Fig
u
r
e
5
,
was
in
itially
in
tr
o
d
u
ce
d
i
n
th
e
I
m
ag
eNe
t
I
L
SVR
C
-
2
0
1
2
c
o
m
p
e
titi
o
n
.
I
t
r
ev
o
lu
tio
n
ized
d
ee
p
lear
n
in
g
f
o
r
im
ag
e
ca
teg
o
r
izatio
n
p
r
o
b
lem
s
with
its
in
n
o
v
ativ
e
d
esig
n
.
T
h
e
ar
ch
itectu
r
e
o
f
Alex
Net
co
m
p
r
is
es
th
r
ee
f
u
lly
co
n
n
ec
ted
lay
er
s
,
r
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
U
)
ac
tiv
atio
n
,
m
ax
p
o
o
lin
g
,
l
o
ca
l
r
esp
o
n
s
e
n
o
r
m
aliza
tio
n
(
L
R
N
)
,
th
r
ee
co
n
v
o
lu
tio
n
al
lay
er
s
w
ith
v
ar
y
in
g
f
ilter
s
izes,
d
r
o
p
o
u
t
f
o
r
r
e
g
u
lar
izatio
n
,
an
d
a
s
o
f
tm
ax
lay
er
f
o
r
class
if
icatio
n
[
2
2
]
.
T
h
e
s
eq
u
e
n
ce
o
f
lay
e
r
s
in
Ale
x
Net
p
er
f
o
r
m
s
f
ea
t
u
r
e
e
x
tr
ac
ti
o
n
a
n
d
class
if
icatio
n
,
p
av
in
g
t
h
e
way
f
o
r
ad
v
an
ce
m
e
n
ts
in
d
ee
p
lear
n
in
g
f
o
r
im
ag
e
an
aly
s
is
.
I
ts
d
ee
p
co
n
v
o
lu
tio
n
al
ar
ch
itectu
r
e,
u
tili
za
tio
n
o
f
R
eL
U
ac
tiv
atio
n
,
in
co
r
p
o
r
atio
n
o
f
m
ax
p
o
o
lin
g
,
L
R
N,
an
d
d
r
o
p
o
u
t
tech
n
iq
u
es h
a
v
e
s
ig
n
if
ican
tly
in
f
lu
en
ce
d
t
h
e
f
ield
o
f
C
NNs.
Alex
Net
’
s
g
r
o
u
n
d
b
r
ea
k
in
g
d
esig
n
f
u
n
d
am
en
t
ally
ch
an
g
ed
th
e
la
n
d
s
ca
p
e
o
f
d
ee
p
lear
n
i
n
g
,
co
n
tr
ib
u
tin
g
to
its
s
u
cc
ess
in
ad
d
r
ess
in
g
im
ag
e
class
if
icatio
n
ch
allen
g
es.
T
h
e
in
tr
o
d
u
ctio
n
o
f
Alex
Net
m
ar
k
ed
a
s
ig
n
if
ican
t
m
iles
to
n
e
in
t
h
e
ev
o
lu
tio
n
o
f
d
ee
p
lear
n
in
g
,
s
ettin
g
th
e
s
tag
e
f
o
r
s
u
b
s
eq
u
en
t
d
ev
elo
p
m
en
ts
an
d
in
n
o
v
atio
n
s
in
C
NN
ar
ch
itectu
r
es.
I
ts
im
p
ac
t
co
n
tin
u
es
to
r
eso
n
ate
in
th
e
f
ield
,
s
h
ap
in
g
th
e
tr
ajec
to
r
y
o
f
r
esear
ch
an
d
a
p
p
licatio
n
s
in
i
m
ag
e
an
aly
s
is
an
d
class
if
icatio
n
task
s
.
Fig
u
r
e
5.
Alex
Net
ar
c
h
itectu
r
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
6
,
No
.
3
,
Dec
em
b
er
20
24
:
1
8
9
5
-
1
9
0
3
1900
2
.
3
.
3
.
ResNet
-
50
R
esNet
-
5
0
,
a
DC
NN
ar
ch
it
ec
tu
r
e
u
n
v
eiled
b
y
Mic
r
o
s
o
f
t
R
esear
ch
,
is
d
ep
icted
in
Fig
u
r
e
6
.
I
t
in
tr
o
d
u
ce
s
a
g
r
o
u
n
d
b
r
e
ak
in
g
co
n
ce
p
t
k
n
o
wn
as
r
esid
u
al
co
n
n
ec
tio
n
s
,
wh
ich
e
n
ab
le
th
e
n
etwo
r
k
to
lear
n
r
esid
u
al
f
u
n
ctio
n
s
,
th
e
r
eb
y
ad
d
r
ess
in
g
th
e
ch
allen
g
e
o
f
tr
ain
in
g
d
ee
p
n
etwo
r
k
s
e
f
f
ec
tiv
ely
.
W
ith
a
to
tal
o
f
5
0
co
n
v
o
l
u
tio
n
al
lay
er
s
,
R
esNet
-
5
0
is
co
m
p
o
s
ed
o
f
m
u
ltip
l
e
co
n
v
o
lu
ti
o
n
al
lay
er
s
o
r
g
a
n
ized
in
to
p
h
ases
.
T
o
en
h
a
n
ce
co
m
p
u
tatio
n
al
ef
f
i
cien
cy
,
th
e
ar
c
h
itectu
r
e
in
c
o
r
p
o
r
ates b
o
ttlen
ec
k
a
n
d
r
esid
u
al
b
lo
ck
s
[
2
3
]
,
[
2
4
]
.
Fo
r
class
if
icatio
n
p
u
r
p
o
s
es,
a
f
u
lly
c
o
n
n
e
cted
lay
e
r
is
u
tili
ze
d
,
an
d
g
lo
b
al
av
er
a
g
e
p
o
o
lin
g
is
em
p
lo
y
ed
to
r
ed
u
ce
s
p
atial
d
i
m
en
s
io
n
s
.
T
h
e
d
is
tin
g
u
is
h
in
g
f
ea
tu
r
e
o
f
R
esNet
-
5
0
,
th
e
in
clu
s
io
n
o
f
r
esid
u
al
co
n
n
ec
tio
n
s
,
h
as
p
r
o
p
elled
i
ts
p
o
p
u
lar
ity
ac
r
o
s
s
v
ar
io
u
s
co
m
p
u
ter
v
is
io
n
ap
p
licatio
n
s
.
T
h
ese
r
esid
u
al
co
n
n
ec
tio
n
s
en
a
b
le
th
e
tr
ain
in
g
o
f
d
ee
p
er
an
d
m
o
r
e
ac
c
u
r
ate
n
etwo
r
k
s
,
co
n
tr
i
b
u
tin
g
to
im
p
r
o
v
ed
p
er
f
o
r
m
an
ce
an
d
r
o
b
u
s
tn
ess
in
co
m
p
lex
task
s
.
Ov
er
all,
R
esNet
-
5
0
s
t
an
d
s
o
u
t
as
a
s
ig
n
if
ican
t
ad
v
an
ce
m
en
t
in
DL
ar
ch
itectu
r
es,
o
f
f
er
i
n
g
en
h
a
n
ce
d
ca
p
ab
ilit
ies
f
o
r
tr
ain
in
g
d
ee
p
n
eu
r
al
n
etwo
r
k
s
an
d
ac
h
iev
in
g
s
u
p
er
i
o
r
p
er
f
o
r
m
an
ce
in
co
m
p
u
ter
v
is
io
n
ap
p
licatio
n
s
[
2
5
]
.
I
ts
in
n
o
v
ativ
e
d
esig
n
an
d
u
tili
za
tio
n
o
f
r
esid
u
al
co
n
n
ec
tio
n
s
h
av
e
s
o
lid
if
ied
its
p
o
s
itio
n
as
a
p
r
e
f
er
r
e
d
ch
o
ice
f
o
r
a
wid
e
r
an
g
e
o
f
tas
k
s
in
th
e
f
ield
o
f
co
m
p
u
ter
v
is
io
n
.
Fig
u
r
e
6.
R
esNet
-
5
0
ar
c
h
itectu
r
e
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
r
esu
lts
o
f
o
u
r
s
tu
d
y
d
em
o
n
s
tr
ate
th
e
ef
f
ec
tiv
en
ess
o
f
o
u
r
p
r
o
p
o
s
ed
DL
m
o
d
el
in
th
e
co
n
tex
t
o
f
ce
r
v
ical
ca
n
ce
r
d
etec
tio
n
s
h
o
wn
in
T
a
b
le
1
.
Ou
r
m
o
d
el,
tr
ain
ed
o
n
a
d
ed
icate
d
d
ataset
o
f
ce
r
v
ical
im
ag
es,
ac
h
iev
ed
a
r
e
m
ar
k
ab
le
ac
cu
r
a
cy
r
ate
o
f
ap
p
r
o
x
im
ately
9
8
%.
T
h
e
h
ig
h
er
AUC
v
alu
es
f
u
r
t
h
er
u
n
d
er
s
co
r
e
th
e
s
u
p
er
io
r
p
e
r
f
o
r
m
an
ce
o
f
o
u
r
a
p
p
r
o
ac
h
.
T
h
e
s
u
cc
ess
o
f
o
u
r
DL
m
o
d
el
in
ac
cu
r
ately
id
en
tify
i
n
g
ca
s
es
o
f
ce
r
v
ical
ca
n
ce
r
is
a
k
ey
h
ig
h
lig
h
t.
W
ith
an
ac
cu
r
ac
y
o
f
9
8
%,
o
u
r
m
o
d
el
s
h
o
wca
s
es
its
r
o
b
u
s
tn
e
s
s
in
d
is
tin
g
u
is
h
in
g
b
etwe
en
c
an
ce
r
o
u
s
a
n
d
n
o
n
-
ca
n
ce
r
o
u
s
in
s
tan
ce
s
in
Pap
s
m
ea
r
im
ag
es.
T
h
e
ev
alu
atio
n
m
etr
ics,
in
clu
d
in
g
F1
-
s
co
r
e
,
a
cc
u
r
ac
y
,
an
d
r
ec
all,
f
u
r
th
er
v
alid
ate
th
e
m
o
d
el
’
s
p
r
o
f
icien
cy
,
with
v
alu
es
o
f
9
8
%,
9
9
%,
an
d
9
8
%,
r
esp
ec
tiv
ely
.
I
n
th
e
co
n
tex
t
o
f
th
e
ac
cu
r
ac
y
v
er
s
u
s
v
alid
atio
n
ac
cu
r
ac
y
cu
r
v
e
as
s
h
o
wn
in
Fig
u
r
e
7
an
d
th
e
lo
s
s
v
er
s
u
s
v
alid
atio
n
lo
s
s
cu
r
v
e
as
s
h
o
wn
in
Fig
u
r
e
8
,
o
u
r
m
o
d
el
ex
h
ib
its
co
n
s
is
ten
t
an
d
f
a
v
o
r
ab
le
p
e
r
f
o
r
m
an
ce
.
T
h
ese
v
is
u
al
r
ep
r
esen
tatio
n
s
p
r
o
v
id
e
i
n
s
ig
h
ts
in
to
th
e
m
o
d
el
’
s
lear
n
in
g
p
r
o
ce
s
s
,
h
ig
h
lig
h
tin
g
its
ab
ilit
y
to
g
en
er
alize
well
an
d
m
in
im
ize
lo
s
s
d
u
r
in
g
v
alid
atio
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
Dee
p
C
ervix:
en
h
a
n
cin
g
ce
r
vic
a
l c
a
n
ce
r
d
etec
tio
n
t
h
r
o
u
g
h
…
(
V
a
is
h
a
li M.
Jo
s
h
i
)
1901
T
ab
le
1
.
C
o
m
p
a
r
ativ
e
an
aly
s
is
N
e
t
w
o
r
k
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F
sco
r
e
VGG
-
16
9
8
%
9
7
%
9
9
%
9
8
%
R
e
sN
e
t
-
50
8
3
%
8
5
%
8
1
%
8
3
%
A
l
e
x
N
e
t
8
0
%
7
8
%
8
2
%
8
0
%
Fig
u
r
e
7
.
Acc
u
r
ac
y
v
s
v
alid
atio
n
ac
cu
r
ac
y
Fig
u
r
e
8
.
L
o
s
s
v
s
v
alid
atio
n
lo
s
s
T
h
e
d
is
cu
s
s
io
n
o
f
th
ese
r
esu
lt
s
em
p
h
asizes
th
e
p
o
ten
tial
an
d
s
ig
n
if
ican
ce
o
f
DL
tech
n
i
q
u
es
in
ea
r
ly
ce
r
v
ical
ca
n
ce
r
d
etec
tio
n
.
Ac
h
iev
in
g
a
h
ig
h
lev
el
o
f
ac
cu
r
ac
y
,
o
u
r
DL
m
o
d
el
ad
d
r
ess
es
a
cr
itical
asp
ec
t
o
f
h
ea
lth
ca
r
e
b
y
o
f
f
er
in
g
a
r
eliab
le
an
d
au
to
m
ated
s
cr
ee
n
in
g
m
eth
o
d
.
T
h
is
n
o
t o
n
l
y
s
h
o
wca
s
es th
e
ca
p
ab
ilit
ies o
f
DL
in
m
ed
ical
im
ag
e
an
aly
s
is
b
u
t
also
u
n
d
er
s
co
r
es
th
e
im
p
o
r
tan
ce
o
f
lev
er
a
g
in
g
ad
v
an
ce
d
tech
n
o
lo
g
ies
f
o
r
th
e
tim
ely
d
iag
n
o
s
is
an
d
m
an
a
g
em
en
t o
f
d
is
ea
s
es.
Fu
r
th
er
m
o
r
e
,
o
u
r
s
tu
d
y
e
n
h
a
n
ce
s
th
e
b
r
o
ad
e
r
lan
d
s
ca
p
e
o
f
ce
r
v
ical
ca
n
ce
r
d
etec
tio
n
r
e
s
ea
r
ch
b
y
o
f
f
er
in
g
a
d
etailed
co
m
p
ar
is
o
n
o
f
th
e
latest
ad
v
a
n
ce
m
en
ts
in
ex
is
tin
g
liter
atu
r
e,
as
s
u
m
m
ar
ized
in
T
ab
le
2
.
T
h
is
p
r
o
v
id
es
co
n
te
x
t
f
o
r
o
u
r
f
in
d
i
n
g
s
,
h
i
g
h
lig
h
tin
g
th
e
n
o
v
elty
a
n
d
ef
f
ec
tiv
e
n
ess
o
f
o
u
r
p
r
o
p
o
s
ed
DL
m
eth
o
d
o
l
o
g
y
.
R
esu
lts
an
d
d
is
cu
s
s
io
n
co
llectiv
ely
af
f
ir
m
th
e
s
u
cc
ess
o
f
o
u
r
DL
m
o
d
el
in
au
to
m
ated
ce
r
v
ica
l
ca
n
ce
r
d
etec
tio
n
.
T
h
e
h
ig
h
ac
cu
r
ac
y
r
ates,
alo
n
g
with
r
o
b
u
s
t
ev
alu
atio
n
m
etr
ics
an
d
v
is
u
al
r
ep
r
esen
tatio
n
s
,
v
alid
ate
th
e
m
o
d
el
’
s
ef
f
icac
y
a
n
d
u
n
d
er
s
co
r
e
its
p
o
te
n
tial f
o
r
r
ea
l
-
wo
r
ld
clin
ical
ap
p
licatio
n
s
.
T
ab
le
2
.
C
o
m
p
a
r
is
o
n
with
th
e
s
tate
o
f
th
e
ar
t
A
u
t
h
o
r
M
e
t
h
o
d
o
l
o
g
y
A
c
c
u
r
a
c
y
H
u
ssa
i
n
e
t
a
l
.
[
2
1
]
A
l
e
x
N
e
t
,
V
G
G
-
1
6
,
a
n
d
1
9
,
R
e
sN
e
t
-
5
0
a
n
d
1
0
1
,
G
o
o
g
l
e
Le
N
e
t
9
0
%
S
o
mp
a
w
o
n
g
e
t
a
l
.
[
2
6
]
M
a
s
k
r
e
g
i
o
n
a
l
C
N
N
9
1
.
7
0
%
W
u
e
t
a
l
.
[
2
7
]
D
C
N
N
9
3
.
3
3
%
P
r
o
p
o
se
d
m
o
d
e
l
V
G
G
N
e
t
-
16
9
8
%
4.
CO
NCLU
SI
O
N
I
n
th
is
r
esear
ch
,
we
in
tr
o
d
u
c
ed
a
DL
ap
p
r
o
ac
h
f
o
r
th
e
ea
r
ly
d
etec
tio
n
o
f
ce
r
v
ical
ca
n
ce
r
u
tili
zin
g
ce
r
v
ical
im
ag
es.
Ou
r
m
eth
o
d
o
lo
g
y
,
wh
ich
i
n
clu
d
es
d
ata
p
r
e
-
p
r
o
ce
s
s
in
g
,
f
ea
tu
r
e
ex
tr
ac
tio
n
,
an
d
class
if
icatio
n
s
tag
es,
d
em
o
n
s
tr
ated
a
h
ig
h
ac
cu
r
ac
y
r
ate
o
f
9
8
%
in
ex
p
er
i
m
en
ts
co
n
d
u
cted
o
n
a
d
ataset
o
f
ce
r
v
ical
im
ag
es.
C
en
tr
al
to
o
u
r
ap
p
r
o
ac
h
is
th
e
u
tili
za
tio
n
o
f
C
NNs,
s
p
ec
if
ically
th
e
VGGN
et
-
1
6
ar
ch
itectu
r
e.
T
h
is
ch
o
ice
p
r
o
v
id
es
a
f
ast
an
d
ac
cu
r
ate
m
eth
o
d
f
o
r
d
etec
tin
g
ce
r
v
ic
al
ca
n
ce
r
in
its
ea
r
ly
s
tag
es,
h
o
ld
in
g
s
ig
n
if
ican
t
im
p
licatio
n
s
f
o
r
ca
n
c
er
s
cr
ee
n
in
g
an
d
d
iag
n
o
s
is
.
Ou
r
s
tu
d
y
b
u
ild
s
u
p
o
n
p
r
e
v
i
o
u
s
r
esear
ch
i
n
th
e
f
ield
o
f
m
ed
ical
im
ag
in
g
an
d
ca
n
ce
r
d
etec
tio
n
.
W
h
ile
ea
r
lier
s
tu
d
ies
h
av
e
ex
p
lo
r
ed
v
ar
io
u
s
m
ac
h
in
e
lear
n
in
g
an
d
im
ag
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es,
o
u
r
wo
r
k
d
is
tin
g
u
is
h
es
its
elf
b
y
lev
e
r
ag
in
g
th
e
a
d
v
an
ce
d
ca
p
a
b
i
liti
es
o
f
C
NNs,
p
ar
ticu
lar
ly
th
e
VGGN
et
-
1
6
ar
ch
itectu
r
e,
to
ac
h
iev
e
s
u
p
e
r
io
r
ac
cu
r
ac
y
.
T
h
is
ad
v
an
ce
m
en
t
alig
n
s
with
th
e
g
r
o
win
g
t
r
en
d
o
f
em
p
l
o
y
in
g
d
ee
p
lear
n
in
g
in
m
e
d
ical
d
iag
n
o
s
tics
to
en
h
an
ce
ea
r
l
y
d
etec
t
io
n
an
d
tr
ea
tm
en
t o
u
tco
m
es.
L
o
o
k
in
g
ah
ea
d
,
p
o
ten
tial
f
u
tu
r
e
r
esear
ch
d
ir
ec
tio
n
s
in
clu
d
e
ex
p
an
d
in
g
th
e
d
ataset
an
d
t
esti
n
g
th
e
m
o
d
el
o
n
d
if
f
er
e
n
t
im
a
g
in
g
m
o
d
alities
to
f
u
r
th
er
v
alid
ate
its
p
er
f
o
r
m
an
ce
an
d
r
o
b
u
s
tn
ess
.
Ad
d
itio
n
ally
,
ex
p
lo
r
in
g
o
th
er
C
NN
ar
ch
itectu
r
es
an
d
in
teg
r
atin
g
m
u
lti
-
m
o
d
al
d
ata
co
u
ld
p
r
o
v
id
e
d
ee
p
er
in
s
ig
h
ts
an
d
im
p
r
o
v
e
th
e
m
o
d
el
’
s
g
en
er
ali
za
b
ilit
y
.
B
y
co
n
tin
u
o
u
s
ly
r
ef
i
n
in
g
an
d
im
p
r
o
v
i
n
g
o
u
r
DL
ap
p
r
o
ac
h
,
we
aim
to
en
h
an
ce
its
ap
p
licab
ilit
y
a
n
d
e
f
f
ec
tiv
en
ess
in
r
ea
l
-
wo
r
ld
clin
ical
s
ettin
g
s
.
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
6
,
No
.
3
,
Dec
em
b
er
20
24
:
1
8
9
5
-
1
9
0
3
1902
I
n
s
u
m
m
ar
y
,
o
u
r
d
ee
p
lear
n
i
n
g
ap
p
r
o
ac
h
f
o
r
d
etec
tin
g
ce
r
v
ical
ca
n
ce
r
u
s
in
g
ce
r
v
ical
i
m
ag
es
h
as
ex
h
ib
ited
a
h
ig
h
lev
el
o
f
a
cc
u
r
ac
y
,
h
o
ld
in
g
p
r
o
m
is
e
f
o
r
ap
p
licatio
n
in
o
t
h
er
ca
n
ce
r
d
etec
tio
n
task
s
.
T
h
is
m
eth
o
d
o
lo
g
y
h
as
th
e
p
o
t
en
tial
to
s
ig
n
if
ican
tly
im
p
ac
t
c
an
ce
r
s
cr
ee
n
in
g
a
n
d
d
ia
g
n
o
s
is
p
r
ac
tices.
T
h
r
o
u
g
h
co
n
tin
u
ed
r
esear
ch
an
d
d
ev
e
lo
p
m
en
t,
we
asp
ir
e
to
co
n
tr
ib
u
te
to
th
e
ad
v
a
n
ce
m
en
t
o
f
m
ed
ical
im
ag
in
g
tech
n
o
lo
g
ies an
d
im
p
r
o
v
e
o
u
t
co
m
es in
ca
n
ce
r
d
etec
tio
n
an
d
tr
ea
tm
en
t.
RE
F
E
R
E
NC
E
S
[
1
]
K
.
E.
D
i
b
i
s
a
,
M
.
T.
D
i
n
k
a
,
L.
M
.
M
o
t
i
,
a
n
d
G
.
F
e
t
e
n
sa
,
“
P
r
e
c
a
n
c
e
r
o
u
s
Le
s
i
o
n
o
f
t
h
e
c
e
r
v
i
x
a
n
d
a
ss
o
c
i
a
t
e
d
f
a
c
t
o
r
s
a
mo
n
g
w
o
m
e
n
o
f
W
e
s
t
W
o
l
l
e
g
a
,
W
e
st
Et
h
i
o
p
i
a
,
2
0
2
2
,
”
C
a
n
c
e
r
C
o
n
t
ro
l
,
v
o
l
.
2
9
,
p
.
1
0
7
3
2
7
4
8
2
2
1
1
1
7
9
0
0
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
7
7
/
1
0
7
3
2
7
4
8
2
2
1
1
1
7
9
0
0
.
[
2
]
M
.
T.
R
e
z
e
n
d
e
,
A
.
G
.
C
.
B
i
a
n
c
h
i
,
a
n
d
C
.
M
.
C
a
r
n
e
i
r
o
,
“
C
e
r
v
i
c
a
l
c
a
n
c
e
r
:
a
u
t
o
ma
t
i
o
n
o
f
P
a
p
t
e
s
t
s
c
r
e
e
n
i
n
g
,
”
D
i
a
g
n
o
s
t
i
c
C
y
t
o
p
a
t
h
o
l
o
g
y
,
v
o
l
.
4
9
,
n
o
.
4
,
p
p
.
5
5
9
–
5
7
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
2
/
d
c
.
2
4
7
0
8
.
[
3
]
P
.
B
.
S
h
a
n
t
h
i
,
K
.
S
.
H
a
r
e
e
sh
a
,
a
n
d
R
.
K
u
d
v
a
,
“
A
u
t
o
ma
t
e
d
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
c
e
r
v
i
c
a
l
c
a
n
c
e
r
u
si
n
g
p
a
p
sme
a
r
mi
c
r
o
sc
o
p
i
c
i
ma
g
e
s
:
a
c
o
m
p
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
a
n
d
f
u
t
u
r
e
p
e
r
s
p
e
c
t
i
v
e
s
,
”
E
n
g
i
n
e
e
r
e
d
S
c
i
e
n
c
e
,
v
o
l
.
1
9
,
p
p
.
2
0
–
4
1
,
2
0
2
2
,
d
o
i
:
1
0
.
3
0
9
1
9
/
e
s8
d
6
3
3
.
[
4
]
V
.
S
.
P
a
l
a
n
i
sa
my
,
R
.
K
.
A
t
h
i
a
p
p
a
n
,
a
n
d
T
.
N
a
g
a
l
i
n
g
a
m
,
“
P
a
p
s
mea
r
b
a
se
d
c
e
r
v
i
c
a
l
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
u
si
n
g
r
e
si
d
u
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
d
e
e
p
l
e
a
r
n
i
n
g
a
r
c
h
i
t
e
c
t
u
r
e
,
”
C
o
n
c
u
rre
n
c
y
a
n
d
C
o
m
p
u
t
a
t
i
o
n
:
Pra
c
t
i
c
e
a
n
d
E
x
p
e
ri
e
n
c
e
,
v
o
l
.
3
4
,
n
o
.
4
,
p
.
e
6
6
0
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
2
/
c
p
e
.
6
6
0
8
.
[
5
]
N
.
Y
o
u
n
e
sza
d
e
,
M
.
M
a
r
j
a
n
i
,
a
n
d
C
.
P
.
P
e
i
,
“
D
e
e
p
l
e
a
r
n
i
n
g
i
n
c
e
r
v
i
c
a
l
c
a
n
c
e
r
d
i
a
g
n
o
s
i
s:
a
r
c
h
i
t
e
c
t
u
r
e
,
o
p
p
o
r
t
u
n
i
t
i
e
s,
a
n
d
o
p
e
n
r
e
sea
r
c
h
c
h
a
l
l
e
n
g
e
s,
”
I
EE
E
A
c
c
e
s
s
,
v
o
l
.
1
1
,
p
p
.
6
1
3
3
–
6
1
4
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
3
5
8
3
3
.
[
6
]
M
.
M
.
K
a
l
b
h
o
r
a
n
d
S
.
V
.
S
h
i
n
d
e
,
“
C
e
r
v
i
c
a
l
c
a
n
c
e
r
d
i
a
g
n
o
s
i
s
u
s
i
n
g
c
o
n
v
o
l
u
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
:
f
e
a
t
u
r
e
l
e
a
r
n
i
n
g
a
n
d
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s,
”
S
o
f
t
C
o
m
p
u
t
i
n
g
,
p
p
.
1
–
1
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s0
0
5
0
0
-
0
2
3
-
0
8
9
6
9
-
1.
[
7
]
W
.
W
i
l
l
i
a
m,
A
.
W
a
r
e
,
A
.
H
.
B
a
saz
a
-
Ej
i
r
i
,
a
n
d
J.
O
b
u
n
g
o
l
o
c
h
,
“
A
r
e
v
i
e
w
o
f
i
ma
g
e
a
n
a
l
y
s
i
s
a
n
d
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
f
o
r
a
u
t
o
m
a
t
e
d
c
e
r
v
i
c
a
l
c
a
n
c
e
r
scr
e
e
n
i
n
g
f
r
o
m
p
a
p
-
sm
e
a
r
i
ma
g
e
s
,
”
C
o
m
p
u
t
e
r
Me
t
h
o
d
s
a
n
d
Pr
o
g
ra
m
s
i
n
Bi
o
m
e
d
i
c
i
n
e
,
v
o
l
.
1
6
4
,
p
p
.
1
5
–
2
2
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
m
p
b
.
2
0
1
8
.
0
5
.
0
3
4
.
[
8
]
I
.
P
a
c
a
l
a
n
d
S
.
K
ı
l
ı
c
a
r
sl
a
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
a
p
p
r
o
a
c
h
e
s
f
o
r
r
o
b
u
s
t
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
c
e
r
v
i
c
a
l
c
a
n
c
e
r
,
”
N
e
u
r
a
l
C
o
m
p
u
t
i
n
g
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
5
,
n
o
.
2
5
,
p
p
.
1
8
8
1
3
–
1
8
8
2
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
0
2
3
-
0
8
7
5
7
-
w.
[
9
]
W
.
A
.
M
u
s
t
a
f
a
,
A
.
H
a
l
i
m
,
M
.
A
.
J
a
ml
o
s,
a
n
d
S
.
Z.
S
.
I
d
r
u
s
,
“
A
r
e
v
i
e
w
:
p
a
p
smea
r
a
n
a
l
y
si
s b
a
s
e
d
o
n
i
ma
g
e
p
r
o
c
e
ssi
n
g
a
p
p
r
o
a
c
h
,
”
i
n
J
o
u
r
n
a
l
o
f
P
h
y
s
i
c
s:
C
o
n
f
e
r
e
n
c
e
S
e
r
i
e
s
,
2
0
2
0
,
v
o
l
.
1
5
2
9
,
n
o
.
2
,
p
.
2
2
0
8
0
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
1
5
2
9
/
2
/
0
2
2
0
8
0
.
[
1
0
]
G
.
Li
t
j
e
n
s
e
t
a
l
.
,
“
A
su
r
v
e
y
o
n
d
e
e
p
l
e
a
r
n
i
n
g
i
n
me
d
i
c
a
l
i
m
a
g
e
a
n
a
l
y
si
s
,
”
M
e
d
i
c
a
l
i
m
a
g
e
a
n
a
l
y
si
s
,
v
o
l
.
4
2
,
p
p
.
6
0
–
8
8
,
2
0
1
7
.
[
1
1
]
P
.
X
u
e
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
i
n
i
m
a
g
e
-
b
a
s
e
d
b
r
e
a
s
t
a
n
d
c
e
r
v
i
c
a
l
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
:
a
s
y
s
t
e
m
a
t
i
c
r
e
v
i
e
w
a
n
d
met
a
-
a
n
a
l
y
s
i
s,
”
N
PJ
D
i
g
i
t
a
l
M
e
d
i
c
i
n
e
,
v
o
l
.
5
,
n
o
.
1
,
p
.
1
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
7
4
6
-
0
2
2
-
0
0
5
5
9
-
z.
[
1
2
]
X
.
Ji
a
n
g
e
t
a
l
.
,
“
M
R
I
b
a
s
e
d
r
a
d
i
o
m
i
c
s
a
p
p
r
o
a
c
h
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
p
r
e
d
i
c
t
i
o
n
o
f
v
e
ssel
i
n
v
a
si
o
n
i
n
e
a
r
l
y
-
st
a
g
e
c
e
r
v
i
c
a
l
c
a
n
c
e
r
,
”
I
EEE
/
A
C
M
T
r
a
n
s
a
c
t
i
o
n
s
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
B
i
o
l
o
g
y
a
n
d
Bi
o
i
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
8
,
n
o
.
3
,
p
p
.
9
9
5
–
1
0
0
2
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
TC
B
B
.
2
0
1
9
.
2
9
6
3
8
6
7
.
[
1
3
]
D
.
C
.
R
.
N
o
v
i
t
a
s
a
r
i
,
A
.
H
.
A
s
y
h
a
r
,
M
.
Th
o
h
i
r
,
A
.
Z
.
A
r
i
f
i
n
,
H
.
M
u
’
j
i
z
a
h
,
a
n
d
A
.
Z
.
F
o
e
a
d
y
,
“
C
e
r
v
i
c
a
l
c
a
n
c
e
r
i
d
e
n
t
i
f
i
c
a
t
i
o
n
b
a
se
d
t
e
x
t
u
r
e
a
n
a
l
y
si
s
u
si
n
g
G
LC
M
-
K
EL
M
o
n
c
o
l
p
o
sc
o
p
y
d
a
t
a
,
”
i
n
2
0
2
0
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
I
n
f
o
rm
a
t
i
o
n
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
,
I
C
A
I
I
C
2
0
2
0
,
2
0
2
0
,
p
p
.
4
0
9
–
4
1
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
I
I
C
4
8
5
1
3
.
2
0
2
0
.
9
0
6
5
2
5
2
.
[
1
4
]
P
.
R
.
P
a
u
l
,
M
.
K
.
B
h
o
w
mi
k
,
a
n
d
D
.
B
h
a
t
t
a
c
h
a
r
j
e
e
,
“
A
u
t
o
ma
t
e
d
c
e
r
v
i
c
a
l
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
u
s
i
n
g
p
a
p
sm
e
a
r
i
ma
g
e
s,
”
i
n
A
d
v
a
n
c
e
s
i
n
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
a
n
d
C
o
m
p
u
t
i
n
g
,
2
0
1
5
,
v
o
l
.
3
3
5
,
p
p
.
2
6
7
–
2
7
8
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
81
-
322
-
2
2
1
7
-
0
_
2
3
.
[
1
5
]
T.
C
h
a
n
k
o
n
g
,
N
.
T
h
e
e
r
a
-
U
mp
o
n
,
a
n
d
S
.
A
u
e
p
h
a
n
w
i
r
i
y
a
k
u
l
,
“
A
u
t
o
m
a
t
i
c
c
e
r
v
i
c
a
l
c
e
l
l
se
g
me
n
t
a
t
i
o
n
a
n
d
c
l
a
s
si
f
i
c
a
t
i
o
n
i
n
P
a
p
smea
r
s,
”
C
o
m
p
u
t
e
r
Me
t
h
o
d
s
a
n
d
Pr
o
g
ra
m
s
i
n
B
i
o
m
e
d
i
c
i
n
e
,
v
o
l
.
1
1
3
,
n
o
.
2
,
p
p
.
5
3
9
–
5
5
6
,
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
m
p
b
.
2
0
1
3
.
1
2
.
0
1
2
.
[
1
6
]
B
.
C
h
i
t
r
a
,
S
.
S
.
K
u
m
a
r
,
a
n
d
D
.
S
u
b
b
u
l
e
k
s
h
m
i
,
“
P
r
e
d
i
c
t
i
o
n
m
o
d
e
l
s
a
p
p
l
y
i
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
b
a
se
d
d
e
e
p
l
e
a
r
n
i
n
g
t
o
c
e
r
v
i
c
a
l
c
a
n
c
e
r
o
u
t
c
o
mes
,
”
I
ET
E
J
o
u
r
n
a
l
o
f
Re
s
e
a
r
c
h
,
p
p
.
1
–
1
2
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
8
0
/
0
3
7
7
2
0
6
3
.
2
0
2
4
.
2
3
0
5
8
3
1
.
[
1
7
]
H
.
K
a
u
r
,
R
.
S
h
a
r
m
a
,
a
n
d
J
.
K
a
u
r
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
c
e
r
v
i
c
a
l
c
a
n
c
e
r
f
r
o
m
p
a
p
sme
a
r
i
ma
g
e
s
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
:
a
c
o
m
p
a
r
i
s
o
n
o
f
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
mo
d
e
l
s,
”
R
e
se
a
rc
h
S
q
u
a
re
Pr
e
p
r
i
n
t
,
2
0
2
4
,
d
o
i
:
1
0
.
2
1
2
0
3
/
r
s.3
.
r
s
-
3
9
7
7
1
2
3
/
v
1
.
[
1
8
]
Y
.
M
a
r
i
n
a
k
i
s
,
G
.
D
o
u
n
i
a
s,
a
n
d
J
.
Ja
n
t
z
e
n
,
“
P
a
p
sm
e
a
r
d
i
a
g
n
o
s
i
s
u
si
n
g
a
h
y
b
r
i
d
i
n
t
e
l
l
i
g
e
n
t
s
c
h
e
me
f
o
c
u
si
n
g
o
n
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
b
a
s
e
d
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
a
n
d
n
e
a
r
e
s
t
n
e
i
g
h
b
o
r
c
l
a
s
si
f
i
c
a
t
i
o
n
,
”
C
o
m
p
u
t
e
rs
i
n
Bi
o
l
o
g
y
a
n
d
M
e
d
i
c
i
n
e
,
v
o
l
.
3
9
,
n
o
.
1
,
p
p
.
6
9
–
7
8
,
2
0
0
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
b
i
o
me
d
.
2
0
0
8
.
1
1
.
0
0
6
.
[
1
9
]
P
.
M
a
h
a
j
a
n
a
n
d
P
.
K
a
u
r
,
“
I
mp
r
o
v
i
n
g
c
e
r
v
i
c
a
l
c
a
n
c
e
r
c
l
a
s
si
f
i
c
a
t
i
o
n
i
n
P
A
P
sme
a
r
i
ma
g
e
s
w
i
t
h
e
n
h
a
n
c
e
d
se
g
m
e
n
t
a
t
i
o
n
a
n
d
d
e
e
p
p
r
o
g
r
e
ss
i
v
e
l
e
a
r
n
i
n
g
-
b
a
s
e
d
t
e
c
h
n
i
q
u
e
s
,
”
D
i
a
g
n
o
s
t
i
c
C
y
t
o
p
a
t
h
o
l
o
g
y
,
v
o
l
.
5
2
,
n
o
.
6
,
p
p
.
3
1
3
–
3
2
4
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
2
/
d
c
.
2
5
2
9
5
.
[
2
0
]
A
.
S
a
r
w
a
r
,
A
.
A
.
S
h
e
i
k
h
,
J.
M
a
n
h
a
s,
a
n
d
V
.
S
h
a
r
ma
,
“
S
e
g
me
n
t
a
t
i
o
n
o
f
c
e
r
v
i
c
a
l
c
e
l
l
s
f
o
r
a
u
t
o
ma
t
e
d
s
c
r
e
e
n
i
n
g
o
f
c
e
r
v
i
c
a
l
c
a
n
c
e
r
:
a
r
e
v
i
e
w
,
”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
R
e
v
i
e
w
,
v
o
l
.
5
3
,
n
o
.
4
,
p
p
.
2
3
4
1
–
2
3
7
9
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
4
6
2
-
0
1
9
-
0
9
7
3
5
-
2.
[
2
1
]
E.
H
u
ss
a
i
n
,
L
.
B
.
M
a
h
a
n
t
a
,
C
.
R
.
D
a
s
,
a
n
d
R
.
K
.
T
a
l
u
k
d
a
r
,
“
A
c
o
m
p
r
e
h
e
n
s
i
v
e
st
u
d
y
o
n
t
h
e
m
u
l
t
i
-
c
l
a
ss
c
e
r
v
i
c
a
l
c
a
n
c
e
r
d
i
a
g
n
o
s
t
i
c
p
r
e
d
i
c
t
i
o
n
o
n
p
a
p
sme
a
r
i
ma
g
e
s
u
s
i
n
g
a
f
u
si
o
n
-
b
a
s
e
d
d
e
c
i
s
i
o
n
f
r
o
m
e
n
se
mb
l
e
d
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
T
i
ss
u
e
a
n
d
C
e
l
l
,
v
o
l
.
6
5
,
p
.
1
0
1
3
4
7
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
i
c
e
.
2
0
2
0
.
1
0
1
3
4
7
.
[
2
2
]
M
.
M
.
R
a
h
a
ma
n
e
t
a
l
.
,
“
D
e
e
p
C
e
r
v
i
x
:
a
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
f
r
a
mew
o
r
k
f
o
r
t
h
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
c
e
r
v
i
c
a
l
c
e
l
l
s
u
si
n
g
h
y
b
r
i
d
d
e
e
p
f
e
a
t
u
r
e
f
u
s
i
o
n
t
e
c
h
n
i
q
u
e
s,
”
C
o
m
p
u
t
e
rs
i
n
Bi
o
l
o
g
y
a
n
d
Me
d
i
c
i
n
e
,
v
o
l
.
1
3
6
,
p
.
1
0
4
6
4
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
b
i
o
me
d
.
2
0
2
1
.
1
0
4
6
4
9
.
[
2
3
]
Z.
K
.
Ş
e
n
t
ü
r
k
a
n
d
S
.
U
z
u
n
,
“
A
n
i
mp
r
o
v
e
d
d
e
e
p
l
e
a
r
n
i
n
g
b
a
se
d
c
e
r
v
i
c
a
l
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
u
si
n
g
a
me
d
i
a
n
f
i
l
t
e
r
b
a
se
d
p
r
e
p
r
o
c
e
ssi
n
g
,
”
E
u
ro
p
e
a
n
J
o
u
r
n
a
l
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
n
o
.
3
2
,
p
p
.
5
0
–
5
8
,
2
0
2
2
,
d
o
i
:
1
0
.
3
1
5
9
0
/
e
j
o
s
a
t
.
1
0
4
5
5
3
8
.
[
2
4
]
W
.
M
o
u
sser
a
n
d
S
.
O
u
a
d
f
e
l
,
“
D
e
e
p
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
f
o
r
p
a
p
-
sme
a
r
i
ma
g
e
c
l
a
ssi
f
i
c
a
t
i
o
n
:
a
c
o
m
p
a
r
a
t
i
v
e
st
u
d
y
,
”
i
n
A
C
M
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
Pro
c
e
e
d
i
n
g
S
e
r
i
e
s
,
2
0
1
9
,
v
o
l
.
P
a
r
t
F
1
4
8
2
6
2
,
p
p
.
6
–
1
0
,
d
o
i
:
1
0
.
1
1
4
5
/
3
3
2
3
9
3
3
.
3
3
2
4
0
6
0
.
[
2
5
]
S
.
D
h
a
w
a
n
,
K
.
S
i
n
g
h
,
a
n
d
M
.
A
r
o
r
a
,
“
C
e
r
v
i
x
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
f
o
r
p
r
o
g
n
o
s
i
s o
f
c
e
r
v
i
c
a
l
c
a
n
c
e
r
u
s
i
n
g
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
w
i
t
h
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
,
”
EAI
E
n
d
o
rs
e
d
T
ra
n
s
a
c
t
i
o
n
s
o
n
P
e
rv
a
si
v
e
H
e
a
l
t
h
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
7
,
n
o
.
2
7
,
2
0
2
1
,
d
o
i
:
1
0
.
4
1
0
8
/
e
a
i
.
1
2
-
4
-
2
0
2
1
.
1
6
9
1
8
3
.
[
26
]
N
.
S
o
m
p
a
w
o
n
g
e
t
a
l
.
,
“
A
u
t
o
mat
e
d
P
a
p
S
m
e
a
r
c
e
r
v
i
c
a
l
c
a
n
c
e
r
scre
e
n
i
n
g
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
i
n
2
0
1
9
4
1
s
t
A
n
n
u
a
l
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
f
t
h
e
I
EE
E
E
n
g
i
n
e
e
ri
n
g
i
n
M
e
d
i
c
i
n
e
a
n
d
Bi
o
l
o
g
y
S
o
c
i
e
t
y
(
EM
BC
)
,
J
u
l
.
2
0
1
9
,
p
p
.
7
0
4
4
–
7
0
4
8
,
d
o
i
:
1
0
.
1
1
0
9
/
EM
B
C
.
2
0
1
9
.
8
8
5
6
3
6
9
.
[
27
]
M
.
W
u
,
C
.
Y
a
n
,
H
.
Li
u
,
Q
.
L
i
u
,
a
n
d
Y
.
Y
i
n
,
“
A
u
t
o
mat
i
c
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
c
e
r
v
i
c
a
l
c
a
n
c
e
r
f
r
o
m
c
y
t
o
l
o
g
i
c
a
l
i
mag
e
s
b
y
u
si
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
B
i
o
sci
e
n
c
e
R
e
p
o
r
t
s
,
v
o
l
.
3
8
,
n
o
.
6
,
D
e
c
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
4
2
/
B
S
R
2
0
1
8
1
7
6
9
.
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
Dee
p
C
ervix:
en
h
a
n
cin
g
ce
r
vic
a
l c
a
n
ce
r
d
etec
tio
n
t
h
r
o
u
g
h
…
(
V
a
is
h
a
li M.
Jo
s
h
i
)
1903
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Dr
.
Va
ish
a
li
M.
J
o
shi
is
a
ss
o
c
iate
p
ro
fe
ss
o
r
a
t
KJ
EI
’
s
T
rin
it
y
Ac
a
d
e
m
y
o
f
En
g
i
n
e
e
rin
g
,
P
u
n
e
,
I
n
d
ia.
S
h
e
h
o
ld
s
a
P
h
.
D
.
d
e
g
re
e
in
E
lec
tro
n
i
c
s
En
g
in
e
e
ri
n
g
.
He
r
re
se
a
rc
h
a
re
a
s
a
re
im
a
g
e
/sig
n
a
l
p
r
o
c
e
ss
in
g
,
VLS
I,
AI
-
M
L
a
n
d
p
a
tt
e
rn
re
c
o
g
n
it
io
n
.
S
h
e
h
a
s
fil
e
d
se
v
e
ra
l
p
a
ten
ts.
He
r
re
se
a
rc
h
in
tere
sts
i
n
c
lu
d
e
ima
g
e
/sig
n
a
l
p
ro
c
e
ss
in
g
,
b
i
o
m
e
tri
c
s,
m
e
d
ica
l
ima
g
e
a
n
d
a
n
a
ly
sis,
a
n
d
p
a
tt
e
r
n
re
c
o
g
n
it
io
n
.
S
h
e
h
a
s
p
u
b
li
sh
e
d
te
n
re
se
a
rc
h
a
rti
c
les
in
in
tern
a
ti
o
n
a
l
a
n
d
n
a
ti
o
n
a
l
jo
u
rn
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s.
S
h
e
p
u
b
l
ish
e
d
th
re
e
p
a
p
e
rs
in
S
CI
i
n
d
e
x
e
d
j
o
u
r
n
a
l
.
S
h
e
h
a
s
2
3
y
e
a
rs
o
f
tea
c
h
in
g
a
n
d
re
se
a
r
c
h
e
x
p
e
rien
c
e
in
th
e
field
o
f
VLS
I,
c
o
m
m
u
n
ica
ti
o
n
,
a
n
d
AI
-
M
L.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
jo
sh
i
v
a
ish
a
li
8
6
7
5
@g
m
a
il
.
c
o
m
.
Pra
jk
ta
P.
D
a
n
d
a
v
a
te
is
a
ss
istan
t
p
ro
fe
ss
o
r
a
t
Vish
wa
k
a
rm
a
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
P
u
n
e
.
He
r
re
se
a
rc
h
a
re
a
s
is
m
a
c
h
in
e
lea
rn
in
g
,
s
h
e
h
a
s
p
u
b
li
s
h
e
d
m
a
n
y
p
a
p
e
rs
in
n
a
ti
o
n
a
l
a
n
d
i
n
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls.
S
h
e
h
a
s
p
u
b
li
s
h
e
d
2
p
a
ten
t
s.
S
h
e
h
a
s
to
tal
1
3
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
tea
c
h
in
g
.
S
h
e
p
u
b
li
sh
e
d
p
a
p
e
rs
in
UG
C
a
n
d
S
c
o
p
u
s
j
o
u
r
n
a
ls
.
S
h
e
c
a
n
b
e
c
o
n
tac
te
d
a
t
e
m
a
il
:
p
ra
jk
ta.sa
m
b
a
re
@g
m
a
il
.
c
o
m
.
Dr
.
R.
Ra
sh
m
i
i
s
d
e
a
n
a
c
a
d
e
m
ics
/a
ss
o
c
iate
p
ro
fe
ss
o
r
a
t
P
VPIT
Ba
v
d
h
a
n
En
g
i
n
e
e
rin
g
C
o
ll
e
g
e
P
u
n
e
In
d
i
a
.
S
h
e
h
o
ld
s
a
P
h
.
D.
d
e
g
re
e
i
n
El
e
c
tri
c
a
l
a
n
d
E
lec
tro
n
ics
En
g
i
n
e
e
rin
g
.
He
r
re
se
a
rc
h
a
re
a
s
a
re
a
u
to
m
o
ti
v
e
e
lec
tro
n
ics
,
p
o
we
r
e
lec
tro
n
ics
,
a
n
d
v
e
h
icl
e
sa
fe
ty
.
S
h
e
h
a
s
fil
e
d
se
v
e
ra
l
p
a
te
n
ts.
S
h
e
h
a
s
p
u
b
li
s
h
e
d
e
i
g
h
t
re
se
a
rc
h
a
rti
c
les
in
i
n
tern
a
ti
o
n
a
l
a
n
d
n
a
ti
o
n
a
l
jo
u
rn
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s.
S
h
e
p
u
b
l
ish
e
d
p
a
p
e
rs
in
UG
C
a
n
d
S
c
o
p
u
s
jo
u
rn
a
ls.
S
h
e
h
a
s
1
7
y
e
a
rs
o
f
tea
c
h
in
g
a
n
d
re
se
a
rc
h
e
x
p
e
rien
c
e
i
n
th
e
fiel
d
o
f
a
u
t
o
m
o
ti
v
e
a
n
d
d
i
g
it
a
l
e
lec
tro
n
ic
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
e
a
n
a
c
a
d
e
m
i
c
s0
9
@g
m
a
il
.
c
o
m
.
Dr
.
G
ita
n
ja
li
R.
S
h
in
d
e
h
a
s
o
v
e
ra
ll
1
5
y
e
a
rs
o
f
e
x
p
e
rien
c
e
,
p
re
se
n
tl
y
wo
rk
in
g
a
s
h
e
a
d
a
n
d
a
ss
o
c
iate
p
ro
fe
ss
o
r
in
D
e
p
a
rtme
n
t
o
f
C
o
m
p
u
ter S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
(AI
a
n
d
M
L)
,
Vish
wa
k
a
rm
a
In
stit
u
te
o
f
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
,
P
u
n
e
,
I
n
d
ia.
S
h
e
h
a
s
d
o
n
e
P
h
.
D
.
i
n
Wi
re
les
s
Co
m
m
u
n
ica
ti
o
n
fro
m
CM
I
,
Aa
lb
o
rg
Un
iv
e
rsity
,
Co
p
e
n
h
a
g
e
n
,
De
n
m
a
rk
o
n
Re
se
a
rc
h
P
ro
b
lem
S
tate
m
e
n
t
“
Clu
ste
r
fra
m
e
wo
rk
fo
r
in
tern
e
t
o
f
p
e
o
p
le,
t
h
in
g
s
a
n
d
s
e
rv
ice
s
”
–
P
h
.
D
.
a
wa
rd
e
d
o
n
8
th
M
a
y
2
0
1
8
.
S
h
e
o
b
tain
e
d
M
.
E.
(Co
m
p
u
ter
En
g
in
e
e
rin
g
)
d
e
g
re
e
fro
m
t
h
e
Un
iv
e
rsity
o
f
P
u
n
e
,
P
u
n
e
in
2
0
1
2
a
n
d
B.
E.
(Co
m
p
u
t
e
r
En
g
in
e
e
rin
g
)
d
e
g
re
e
fr
o
m
t
h
e
Un
i
v
e
rsity
o
f
P
u
n
e
,
P
u
n
e
i
n
2
0
0
6
.
S
h
e
h
a
s
re
c
e
iv
e
d
re
se
a
rc
h
fu
n
d
in
g
fo
r
th
e
p
r
o
jec
t
“
Li
g
h
twe
ig
h
t
g
ro
u
p
a
u
t
h
e
n
ti
c
a
ti
o
n
fo
r
Io
T”
b
y
S
P
P
U,
P
u
n
e
.
S
h
e
h
a
s
p
r
e
se
n
ted
a
re
se
a
rc
h
a
rti
c
le
i
n
th
e
wo
rld
wire
les
s
re
se
a
rc
h
fo
ru
m
(W
WRF
)
m
e
e
ti
n
g
,
Be
ij
i
n
g
C
h
in
a
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
g
i
tan
jali.
sh
i
n
d
e
@v
ii
t.
a
c
.
in
.
Dr
.
Ne
e
ta
N.
Th
u
n
e
is
a
ss
o
c
i
a
te
p
ro
fe
ss
o
r
a
t
M
a
ra
th
wa
d
a
C
o
l
l
e
g
e
o
f
E
n
g
in
e
e
rin
g
P
u
n
e
,
s
h
e
is
P
h
.
D
.
in
E
lec
tro
n
ics
fro
m
RT
M
NU
Na
g
p
u
r
U
n
i
v
e
rsity
.
He
r
re
se
a
rc
h
a
re
a
s
VLS
I
,
AI/M
L,
R
o
b
o
ti
c
s
a
n
d
Au
t
o
m
a
ti
o
n
.
S
h
e
h
a
s
p
u
b
li
sh
e
d
v
a
ri
o
u
s
p
a
p
e
rs
in
re
m
a
rk
a
b
le
i
n
d
e
x
in
g
jo
u
r
n
a
ls
li
k
e
,
ES
CI,
W
o
S
,
S
c
o
p
u
s,
a
n
d
UG
C
c
a
re
.
S
h
e
p
u
b
l
ish
e
d
h
e
r
o
wn
b
o
o
k
b
a
se
d
o
n
h
e
r
re
se
a
rc
h
a
re
a
.
Ha
v
in
g
v
a
rio
u
s
p
a
t
e
n
ts
a
n
d
c
o
p
y
ri
g
h
ts.
M
a
j
o
rly
sh
e
is
wo
rk
i
n
g
o
n
in
d
u
str
y
-
b
a
se
d
p
ro
jec
ts
o
n
m
o
d
e
l
-
b
a
se
d
d
e
si
g
n
with
KPIT
,
P
u
n
e
a
n
d
a
s
a
d
a
ta
sc
ien
c
e
c
o
n
su
lt
a
n
t
wit
h
Wo
rk
o
o
p
o
l
is.
He
r
a
re
a
o
f
in
tere
st
is
AI/M
L
a
n
d
a
u
to
m
a
ti
o
n
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
e
e
ta.t
h
u
n
e
@g
m
a
il
.
c
o
m
.
Rid
d
h
i
Mi
r
a
jk
a
r
p
u
rsi
n
g
a
D
o
c
to
r
o
f
P
h
i
lo
so
p
h
y
d
e
g
re
e
in
Co
m
p
u
ter
En
g
in
e
e
rin
g
fro
m
S
a
v
it
ri
b
a
i
P
h
u
le
P
u
n
e
Un
iv
e
rsity
,
P
u
n
e
,
I
n
d
ia.
S
h
e
h
a
s
r
e
c
e
iv
e
d
h
e
r
m
a
ste
r’s
(M
.
E.
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
)
d
e
g
re
e
fro
m
S
a
v
it
rib
a
i
P
h
u
le
P
u
n
e
Un
iv
e
rsity
,
P
u
n
e
i
n
2
0
1
6
.
S
h
e
is
wo
rk
in
g
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
i
n
In
f
o
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
De
p
a
rtme
n
t
o
f
Vish
wa
k
a
rm
a
In
stit
u
te
o
f
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
,
K
o
n
d
h
wa
(b
k
),
P
u
n
e
.
S
h
e
is
h
a
v
i
n
g
1
0
y
e
a
rs
o
f
wo
r
k
in
g
e
x
p
e
rien
c
e
.
He
r
a
re
a
o
f
i
n
tere
st
is
a
rti
ficia
l
i
n
telli
g
e
n
c
e
a
n
d
c
o
m
p
u
ter
n
e
two
rk
s
.
S
h
e
h
a
s
p
u
b
l
i
s
h
e
d
o
v
e
r
2
0
p
a
p
e
r
s
i
n
n
a
t
i
o
n
a
l
a
n
d
i
n
t
e
r
n
a
t
i
o
n
a
l
c
o
n
f
e
r
e
n
c
e
s
a
n
d
j
o
u
r
n
a
l
s
.
S
h
e
i
s
a
l
i
f
e
t
i
m
e
m
e
m
b
e
r
o
f
I
S
T
E
.
S
h
e
c
a
n
b
e
c
o
n
t
a
c
t
e
d
a
t
e
m
a
i
l
:
r
i
d
d
h
i
.
m
i
r
a
jk
a
r
@
v
i
i
t
.
a
c
.
i
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.