I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
2
,
A
p
r
il
20
25
,
p
p
.
1
8
2
6
~
1
8
3
3
I
SS
N:
2088
-
8
7
0
8
,
DOI
:
1
0
.
1
1
5
9
1
/ijece.
v
15
i
2
.
pp
1
8
2
6
-
1
8
3
3
1826
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
O
CNe
t
-
2
3
:
a
fine
-
tuned
trans
fer
lea
rning
appro
a
ch f
o
r ora
l
ca
ncer
de
tect
io
n
f
ro
m histo
pa
tholo
g
ica
l ima
g
es
Am
a
t
ul B
us
hra
Ak
hi
1
,
Abd
u
lla
h Al
No
m
a
n
1
,
So
njo
y
P
r
o
s
a
d Sha
ha
1
,
F
a
rz
a
na
Akt
er
2
,
M
un
ira
Ak
t
er
L
a
t
a
3
,
Rubel
Sh
eik
h
3
1
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
,
D
a
f
f
o
d
i
l
I
n
t
e
r
n
a
t
i
o
n
a
l
U
n
i
v
e
r
si
t
y
,
D
h
a
k
a
,
B
a
n
g
l
a
d
e
s
h
2
D
e
p
a
r
t
me
n
t
o
f
I
o
T
a
n
d
R
o
b
o
t
i
c
s E
n
g
i
n
e
e
r
i
n
g
,
B
a
n
g
a
b
a
n
d
h
u
S
h
e
i
k
h
M
u
j
i
b
u
r
R
a
h
ma
n
D
i
g
i
t
a
l
U
n
i
v
e
r
si
t
y
,
D
h
a
k
a
,
B
a
n
g
l
a
d
e
sh
3
D
e
p
a
r
t
me
n
t
o
f
E
d
u
c
a
t
i
o
n
a
l
Te
c
h
n
o
l
o
g
y
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
B
a
n
g
a
b
a
n
d
h
u
S
h
e
i
k
h
M
u
j
i
b
u
r
R
a
h
ma
n
D
i
g
i
t
a
l
U
n
i
v
e
r
s
i
t
y
,
D
h
a
k
a
,
B
a
n
g
l
a
d
e
s
h
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
r
2
0
,
2
0
2
4
R
ev
is
ed
Sep
2
4
,
2
0
2
4
Acc
ep
ted
Oct
1
,
2
0
2
4
Ora
l
sq
u
a
m
o
u
s
c
e
ll
c
a
rc
in
o
m
a
(
OSCC)
is
e
m
e
rg
i
n
g
a
s
a
si
g
n
ifi
c
a
n
t
g
lo
b
a
l
h
e
a
lt
h
c
o
n
c
e
rn
,
u
n
d
e
rsc
o
rin
g
t
h
e
n
e
e
d
fo
r
p
ro
m
p
t
d
e
tec
ti
o
n
a
n
d
trea
tme
n
t.
Ou
r
stu
d
y
in
tr
o
d
u
c
e
s
a
n
i
n
n
o
v
a
ti
v
e
d
iag
n
o
st
ic
m
e
th
o
d
fo
r
OSCC,
lev
e
ra
g
in
g
th
e
c
a
p
a
b
il
it
ies
o
f
a
rti
f
icia
l
i
n
tel
li
g
e
n
c
e
(AI)
a
n
d
h
isto
p
a
th
o
lo
g
ic
a
l
ima
g
e
s
(HIs
).
Ou
r
p
rima
ry
o
b
jec
ti
v
e
is
to
e
x
p
e
d
it
e
t
h
e
i
d
e
n
ti
f
ica
ti
o
n
p
ro
c
e
ss
fo
r
m
e
d
ica
l
p
ro
fe
ss
io
n
a
ls.
To
a
c
h
ie
v
e
th
is,
we
e
m
p
lo
y
tran
sfe
r
lea
rn
in
g
a
n
d
in
c
o
rp
o
ra
te
re
n
o
w
n
e
d
m
o
d
e
ls
s
u
c
h
a
s
VG
G
1
6
,
VG
G
1
9
,
M
o
b
i
leN
e
t_
v
1
,
M
o
b
i
leN
e
t_
v
2
,
De
n
se
Ne
t,
a
n
d
In
c
e
p
ti
o
n
V
3
.
A
k
e
y
fe
a
tu
re
o
f
o
u
r
a
p
p
ro
a
c
h
is
th
e
m
e
ti
c
u
lo
u
s
o
p
ti
m
iza
ti
o
n
o
f
t
h
e
VG
G
1
9
a
rc
h
it
e
c
tu
re
,
p
a
ired
wit
h
a
d
v
a
n
c
e
d
ima
g
e
p
re
p
r
o
c
e
ss
in
g
tec
h
n
iq
u
e
s
su
c
h
a
s
c
o
n
tras
t
li
m
it
e
d
a
d
a
p
ti
v
e
h
isto
g
ra
m
e
q
u
a
li
z
a
ti
o
n
(
CLAH
E
)
a
n
d
m
e
d
ian
b
l
u
r
.
We
c
o
n
d
u
c
ted
a
n
a
b
latio
n
stu
d
y
with
o
p
ti
m
ize
d
h
y
p
e
r
p
a
ra
m
e
ters
,
c
u
lmin
a
ti
n
g
i
n
a
n
imp
re
ss
iv
e
9
5
.
3
2
%
a
c
c
u
ra
c
y
.
Th
i
s
g
ro
u
n
d
b
re
a
k
in
g
re
se
a
rc
h
e
n
su
re
s
a
c
c
u
ra
te
a
n
d
ti
m
e
ly
d
ia
g
n
o
se
s,
lea
d
in
g
t
o
imp
ro
v
e
d
p
a
ti
e
n
t
o
u
tco
m
e
s,
a
n
d
re
p
re
se
n
ts
a
sig
n
ifi
c
a
n
t
a
d
v
a
n
c
e
m
e
n
t
in
th
e
a
p
p
li
c
a
ti
o
n
o
f
AI
fo
r
o
ra
l
c
a
n
c
e
r
d
iag
n
o
stics
.
Util
izi
n
g
a
su
b
sta
n
ti
a
l
d
a
tas
e
t
o
f
5
,
1
9
2
m
e
ti
c
u
l
o
u
sl
y
c
a
teg
o
rize
d
ima
g
e
s
in
to
OSCC
a
n
d
n
o
rm
a
l
c
a
teg
o
ries
,
o
u
r
wo
r
k
p
io
n
e
e
rs
th
e
field
o
f
OSCC
d
e
tec
ti
o
n
.
B
y
p
ro
v
id
in
g
m
e
d
ica
l
p
ro
fe
ss
io
n
a
ls
with
a
ro
b
u
st
t
o
o
l
to
e
n
h
a
n
c
e
th
e
ir
d
ia
g
n
o
stic
c
a
p
a
b
il
it
ies
,
o
u
r
m
e
th
o
d
h
a
s
th
e
p
o
ten
ti
a
l
t
o
re
v
o
lu
ti
o
n
ize
t
h
e
se
c
to
r
a
n
d
u
s
h
e
r
i
n
a
n
e
w
e
ra
o
f
m
o
re
e
ffe
c
ti
v
e
a
n
d
e
fficie
n
t
o
ra
l
c
a
n
c
e
r
trea
tme
n
t.
K
ey
w
o
r
d
s
:
Dee
p
lear
n
in
g
I
m
ag
e
p
r
o
ce
s
s
in
g
Or
al
ca
n
ce
r
d
etec
tio
n
Or
al
s
q
u
am
o
u
s
ce
ll c
ar
cin
o
m
a
T
r
an
s
f
er
lear
n
i
n
g
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
:
Am
atu
l Bu
s
h
r
a
Ak
h
i
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
,
Daf
f
o
d
il
I
n
ter
n
atio
n
al
Un
iv
er
s
ity
Dh
ak
a,
B
an
g
lad
esh
E
m
ail: a
k
h
i.c
s
e@
d
iu
.
ed
u
.
b
d
1.
I
NT
RO
D
UCT
I
O
N
Or
al
ca
n
ce
r
is
a
p
r
e
v
alen
t
f
o
r
m
o
f
ca
n
ce
r
with
a
wid
esp
r
ea
d
p
r
esen
ce
th
r
o
u
g
h
o
u
t
th
e
wo
r
ld
.
I
n
r
ec
en
t
d
ec
ad
es,
b
o
th
th
e
in
ci
d
en
ce
an
d
f
atality
r
ates
h
av
e
s
ee
n
co
n
ce
r
n
i
n
g
in
cr
ea
s
es
[
1
]
.
Or
al
ca
n
ce
r
r
em
ain
s
a
g
r
im
p
r
o
g
n
o
s
is
,
with
lo
w
s
u
r
v
iv
al
r
ates
d
esp
ite
a
d
v
an
ce
m
en
ts
in
s
u
r
g
ical
a
n
d
r
ad
io
th
er
ap
eu
tic
tech
n
iq
u
e
s
[
2
]
.
I
n
m
o
s
t
ca
s
es,
th
e
d
is
ea
s
e
s
tar
ts
with
d
y
s
p
lasi
a,
wh
ic
h
is
f
o
llo
wed
b
y
ca
r
cin
o
m
a
i
n
s
itu
,
wh
er
e
ce
lls
p
r
o
life
r
ate
u
n
co
n
t
r
o
llab
ly
b
u
t
r
em
ain
lo
ca
lized
,
o
f
f
e
r
in
g
a
c
h
an
ce
o
f
r
ec
o
v
er
y
[
3
]
.
I
n
t
h
e
f
in
al
s
tag
e,
ca
n
ce
r
is
in
v
asiv
e
an
d
m
ay
s
p
r
ea
d
to
o
t
h
er
o
r
g
an
s
.
T
h
er
e
is
a
c
r
u
cial
n
ee
d
f
o
r
ea
r
l
y
d
etec
tio
n
o
f
ab
n
o
r
m
al
o
r
al
tis
s
u
e
g
r
o
wth
,
as
th
is
f
ac
ilit
ates
m
o
r
e
ef
f
icien
t
tr
ea
tm
en
t
p
lan
n
i
n
g
an
d
in
cr
ea
s
es
th
e
lik
elih
o
o
d
o
f
a
s
u
cc
ess
f
u
l
o
u
tco
m
e
[
4
]
.
W
ith
3
5
4
,
8
6
4
n
ew
ca
s
es
an
d
1
7
7
,
3
8
4
d
ea
th
s
in
2
0
1
8
,
o
r
al
ca
n
ce
r
p
o
s
ed
a
s
ig
n
if
ican
t
g
lo
b
a
l
h
ea
lth
ch
allen
g
e
[
5
]
.
I
t
is
esti
m
ated
th
at
9
0
%
o
f
all
ca
s
es
o
f
o
r
al
ca
v
ity
ca
n
ce
r
ar
e
s
q
u
am
o
u
s
ce
ll
ca
r
cin
o
m
as
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
OC
N
et
-
2
3
:
a
fin
e
-
tu
n
e
d
tr
a
n
s
fer lea
r
n
in
g
a
p
p
r
o
a
ch
fo
r
o
r
a
l
ca
n
ce
r
d
ec
tectio
n
…
(
A
ma
tu
l
B
u
s
h
r
a
A
kh
i
)
1827
(
SC
C
s
)
[
6
]
.
A
r
ap
id
,
n
o
n
-
in
v
a
s
iv
e,
ef
f
icien
t,
an
d
u
s
er
-
f
r
ie
n
d
ly
d
ee
p
lear
n
in
g
s
y
s
tem
is
d
ev
elo
p
ed
h
e
r
e
f
o
r
th
e
id
en
tific
atio
n
o
f
o
r
al
s
q
u
a
m
o
u
s
ce
ll c
ar
cin
o
m
as (
OSC
C
s
)
u
s
in
g
h
is
to
p
ath
o
lo
g
ical
im
ag
es.
B
etel
q
u
id
co
n
s
u
m
p
tio
n
c
o
n
tr
ib
u
tes
to
th
e
late
d
etec
tio
n
o
f
o
r
al
lesi
o
n
s
,
with
o
v
er
two
-
th
ir
d
s
d
etec
ted
in
ad
v
an
ce
d
s
tag
es,
r
esu
ltin
g
in
lo
wer
s
u
r
v
iv
al
r
ates.
T
h
e
co
s
t
o
f
m
an
ag
in
g
lesi
o
n
s
,
esp
ec
ially
th
o
s
e
in
ad
v
a
n
ce
d
s
tag
es,
is
s
u
b
s
tan
tial
[
6
]
.
Pre
m
alig
n
a
n
t
o
r
al
l
esio
n
s
s
u
ch
as
leu
k
o
p
lak
ia,
e
r
y
th
r
o
p
lak
ia,
lich
e
n
p
lan
u
s
,
an
d
s
u
b
m
u
c
o
u
s
f
ib
r
o
s
is
ar
e
co
m
m
o
n
in
h
i
g
h
-
r
is
k
g
r
o
u
p
s
.
A
clea
r
d
is
tin
ctio
n
b
et
wee
n
th
ese
lesi
o
n
s
an
d
th
eir
m
alig
n
an
t c
o
u
n
ter
p
a
r
ts
is
cr
itical
[
7
]
.
A
s
u
b
s
et
o
f
m
ac
h
in
e
lear
n
in
g
en
titl
ed
d
ee
p
lear
n
in
g
h
as
b
ec
o
m
e
th
e
d
o
m
in
an
t
f
o
r
ce
i
n
th
e
d
ata
an
aly
tics
an
d
ar
tific
ial
in
tellig
en
ce
d
o
m
ai
n
s
.
T
h
is
s
o
p
h
is
ticated
m
eth
o
d
,
wh
ich
is
s
im
ilar
t
o
n
eu
r
al
n
etwo
r
k
s
f
o
u
n
d
in
th
e
h
u
m
a
n
b
r
ain
,
h
as
th
e
am
az
in
g
ca
p
ac
ity
to
lear
n
an
d
ex
tr
ac
t
co
m
p
lex
p
atter
n
s
an
d
r
ep
r
esen
tatio
n
s
f
r
o
m
lar
g
e
d
atasets
o
n
its
o
wn
.
At
th
e
lead
in
g
ed
g
e
o
f
m
o
d
er
n
tec
h
n
o
lo
g
ical
p
r
o
g
r
e
s
s
,
d
ee
p
lear
n
in
g
is
esp
ec
ially
p
r
o
f
icien
t
at
im
ag
e
id
en
tific
atio
n
,
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
,
an
d
s
elf
-
d
ir
ec
te
d
d
ec
is
io
n
-
m
ak
in
g
.
I
ts
tr
an
s
f
o
r
m
atio
n
al
p
o
ten
tial
ex
ten
d
s
ac
r
o
s
s
a
wid
e
r
an
g
e
o
f
in
d
u
s
tr
ies,
in
clu
d
in
g
r
o
b
o
tics
,
h
ea
lth
ca
r
e,
b
an
k
in
g
,
an
d
au
to
n
o
m
o
u
s
d
r
iv
in
g
[
8
]
.
I
n
th
is
r
ese
ar
ch
,
A
I
-
b
ase
d
t
ec
h
n
o
lo
g
y
is
b
ei
n
g
u
s
e
d
t
o
r
e
v
o
lu
t
io
n
i
ze
ea
r
l
y
d
ia
g
n
o
s
is
o
f
O
SC
C
.
T
h
e
f
o
c
u
s
is
s
p
ec
if
i
ca
ll
y
o
n
u
ti
lizi
n
g
h
is
t
o
p
a
th
o
l
o
g
i
ca
l
i
m
a
g
es
(
HI
s
)
t
o
p
r
o
v
id
e
h
ea
lt
h
ca
r
e
p
r
a
cti
t
io
n
e
r
s
wit
h
a
r
a
p
i
d
an
d
d
e
p
en
d
ab
le
d
i
a
g
n
o
s
t
ic
to
o
l.
B
y
em
p
l
o
y
i
n
g
t
r
a
n
s
f
e
r
l
ea
r
n
in
g
m
o
d
els
li
k
e
VGG
1
6
,
VGG
1
9
,
M
o
b
ileN
et
_
v
1
,
Mo
b
il
eNe
t_
v
2
,
De
n
s
e
Net
,
an
d
I
n
ce
p
ti
o
n
V
3
[
9
]
–
[
1
8
]
,
[
1
9
]
,
al
o
n
g
s
i
d
e
a
f
in
e
-
t
u
n
ed
m
o
d
el
OC
Ne
t
-
2
3
,
o
u
r
r
es
ea
r
c
h
ai
m
s
t
o
e
n
h
a
n
c
e
th
e
ac
c
u
r
a
cy
o
f
OSC
C
id
e
n
ti
f
ic
ati
o
n
f
r
o
m
h
is
to
p
at
h
o
lo
g
i
ca
l
i
m
a
g
es
.
B
y
le
v
e
r
a
g
i
n
g
AI
-
d
r
i
v
e
n
i
m
a
g
e
a
n
al
y
s
is
,
w
e
ca
n
n
o
t
o
n
ly
e
x
p
e
d
i
te
d
ia
g
n
o
s
is
b
u
t
als
o
p
r
o
v
i
d
e
e
ar
l
y
i
n
t
er
v
e
n
ti
o
n
,
im
p
r
o
v
i
n
g
p
at
ie
n
t
o
u
t
c
o
m
es
s
i
g
n
i
f
ic
a
n
tl
y
.
I
n
a
d
d
it
i
o
n
,
we
e
x
p
lo
r
e
ad
v
an
ce
d
im
ag
e
p
r
e
p
r
o
ce
s
s
i
n
g
te
ch
n
i
q
u
es
,
s
u
c
h
as
s
p
e
ck
le
n
o
is
e
r
e
m
o
v
al
,
m
o
r
p
h
o
lo
g
i
ca
l
o
p
er
ati
o
n
,
a
n
d
c
o
n
tr
ast
li
m
it
ed
a
d
a
p
ti
v
e
h
is
t
o
g
r
am
e
q
u
al
iza
ti
o
n
(
C
L
AH
E
)
,
t
o
e
n
h
an
ce
i
m
a
g
e
q
u
al
it
y
,
w
h
i
ch
is
a
c
r
u
ci
al
c
o
m
p
o
n
e
n
t
o
f
r
eli
ab
le
a
n
al
y
s
is
.
Ou
r
u
ltima
te
g
o
als
ar
e
to
im
p
r
o
v
e
h
ea
lth
ca
r
e
s
tan
d
ar
d
s
an
d
p
r
ev
en
t
d
ea
th
s
.
W
e
an
ticip
at
e
th
at
th
is
r
esear
ch
will
b
r
id
g
e
th
e
g
a
p
b
etwe
en
tech
n
o
lo
g
ical
in
n
o
v
atio
n
an
d
h
ea
lth
ca
r
e
d
el
iv
er
y
,
s
ig
n
if
ican
tly
ad
v
an
cin
g
th
e
f
ield
o
f
o
r
al
ca
n
ce
r
d
iag
n
o
s
tics
.
T
h
e
k
ey
c
o
n
tr
ib
u
tio
n
s
o
f
t
h
is
s
tu
d
y
ar
e
s
u
m
m
ar
ized
b
elo
w:
−
T
h
e
q
u
ality
o
f
o
r
al
ca
n
ce
r
h
i
s
to
p
ath
o
lo
g
ical
im
ag
es
is
s
y
s
tem
atica
lly
im
p
r
o
v
ed
b
y
u
s
in
g
a
v
ar
iety
o
f
im
ag
e
p
r
ep
a
r
atio
n
m
et
h
o
d
s
,
s
u
ch
as m
ed
ian
f
ilter
,
C
L
AHE
,
a
n
d
im
ag
e
r
esizin
g
.
−
A
r
ig
o
r
o
u
s
ev
alu
atio
n
p
r
o
ce
d
u
r
e
is
u
s
ed
t
o
d
eter
m
in
e
th
e
b
est
tr
an
s
f
er
lear
n
in
g
m
o
d
el
am
o
n
g
s
ev
er
al
d
if
f
er
en
t
m
eth
o
d
s
o
f
tr
a
n
s
f
er
lear
n
in
g
th
at
h
a
v
e
b
ee
n
a
p
p
lied
to
t
h
e
d
ataset.
T
o
im
p
r
o
v
e
th
e
m
o
d
el's
p
er
f
o
r
m
an
ce
an
d
r
esil
ien
ce
,
ad
d
itio
n
al
d
ev
elo
p
m
en
t
p
r
o
ce
s
s
es a
r
e
ap
p
lied
.
−
T
o
im
p
r
o
v
e
r
esil
ien
ce
,
a
ca
r
ef
u
lly
d
esig
n
ed
Fin
e
-
tu
n
ed
tr
a
n
s
f
er
lear
n
in
g
m
o
d
el
n
am
e
d
OC
Net
-
2
3
is
b
u
il
t
th
r
o
u
g
h
a
h
y
p
er
p
ar
am
eter
a
b
la
tio
n
s
tu
d
y
.
−
Af
ter
d
ev
elo
p
m
en
t
o
f
OC
Net
-
2
3
,
it
is
p
u
t
th
r
o
u
g
h
a
r
i
g
o
r
o
u
s
test
in
g
p
r
o
ce
s
s
with
k
ey
p
er
f
o
r
m
a
n
ce
m
etr
ics.
I
n
th
ese
test
s
,
th
e
ac
cu
r
ac
y
an
d
r
eliab
ilit
y
o
f
th
e
m
o
d
el
h
av
e
b
ee
n
d
eter
m
in
ed
.
2.
M
E
T
H
O
D
T
h
e
ad
v
a
n
ce
m
en
t
o
f
d
ee
p
l
ea
r
n
in
g
tec
h
n
iq
u
es
h
as
g
ar
n
er
ed
s
u
b
s
tan
tial
atten
tio
n
d
u
e
to
th
eir
p
o
ten
tial
to
en
h
an
ce
th
e
p
r
ec
is
io
n
an
d
ef
f
icac
y
o
f
m
ed
ical
im
ag
e
an
aly
s
is
.
Am
o
n
g
th
ese
ap
p
licatio
n
s
,
th
e
class
if
icatio
n
o
f
o
r
al
ca
n
ce
r
f
o
r
d
iag
n
o
s
tic
p
u
r
p
o
s
es
s
tan
d
s
o
u
t
as
p
ar
ticu
lar
ly
cr
u
cial,
w
ith
th
e
p
r
o
m
is
e
o
f
s
ig
n
if
ican
tly
im
p
r
o
v
in
g
t
h
e
ac
cu
r
ac
y
o
f
o
r
al
h
ea
lth
ass
ess
m
en
ts
.
T
h
is
p
a
p
er
i
n
tr
o
d
u
ce
s
a
s
tate
-
of
-
th
e
-
ar
t
d
ee
p
lear
n
in
g
m
eth
o
d
f
o
r
ca
teg
o
r
iz
in
g
h
is
to
p
ath
o
lo
g
ical
im
ag
es
o
f
o
r
al
ca
n
ce
r
[
2
0
]
–
[
2
4
]
,
u
tili
zin
g
th
e
OC
Net
-
2
3
m
o
d
el.
T
h
e
p
r
o
ject
aim
s
n
o
t
o
n
ly
to
im
p
r
o
v
e
d
ia
g
n
o
s
tic
a
cc
u
r
ac
y
f
o
r
o
r
al
ca
n
ce
r
b
u
t
a
ls
o
to
allev
iate
th
e
wo
r
k
lo
ad
o
n
h
ea
lth
c
ar
e
p
r
o
f
ess
io
n
als.
I
n
th
e
r
ea
lm
o
f
o
r
al
o
n
c
o
lo
g
y
,
t
h
is
in
n
o
v
ativ
e
ap
p
r
o
ac
h
h
as
t
h
e
p
o
ten
tial
to
r
e
v
o
lu
tio
n
ize
d
ia
g
n
o
s
tic
p
r
o
ce
s
s
es
an
d
u
ltima
tely
elev
ate
p
atien
t
ca
r
e.
Fig
u
r
e
1
d
ep
icts
o
u
r
co
m
p
r
eh
e
n
s
iv
e
s
tu
d
y
wo
r
k
f
lo
w,
en
co
m
p
ass
in
g
d
ata
p
r
e
p
r
o
c
ess
in
g
,
th
e
d
ev
elo
p
m
en
t
o
f
t
h
e
OC
Net
-
2
3
m
o
d
el,
an
d
s
u
b
s
eq
u
e
n
t statis
tical
an
al
y
s
is
.
T
h
e
co
m
p
lete
s
tu
d
y
p
r
o
ce
d
u
r
e
is
s
u
m
m
ar
ized
as f
o
llo
ws:
−
Data
s
et:
T
h
e
s
tu
d
y
u
tili
ze
s
5
,
1
9
2
h
is
to
p
ath
o
l
o
g
ical
im
ag
es
o
f
o
r
al
ca
n
ce
r
,
class
if
ied
in
to
two
ca
teg
o
r
ies:
“
n
o
r
m
al
”
an
d
“
OSC
C
”
(
o
r
al
s
q
u
am
o
u
s
ce
ll c
ar
cin
o
m
a
).
−
I
m
ag
e
en
h
an
ce
m
e
n
t:
v
ar
io
u
s
p
r
ep
r
o
ce
s
s
in
g
tech
n
i
q
u
es,
i
n
clu
d
in
g
m
ed
ian
f
ilter
in
g
,
c
o
n
tr
ast
lim
ited
ad
ap
tiv
e
h
is
to
g
r
am
eq
u
aliza
tio
n
,
an
d
im
ag
e
r
esizin
g
,
a
r
e
ap
p
lied
to
im
p
r
o
v
e
th
e
q
u
ality
o
f
th
e
h
is
to
p
ath
o
lo
g
ical
im
a
g
es.
−
Ass
es
s
m
en
t o
f
tr
an
s
f
er
lear
n
i
n
g
m
o
d
els:
s
ev
er
al
tr
an
s
f
er
lea
r
n
in
g
m
o
d
els ar
e
in
itially
test
ed
o
n
th
e
d
ataset.
An
ev
alu
atio
n
p
r
o
ce
s
s
id
en
tifie
s
th
e
o
p
tim
al
m
o
d
el,
wh
i
ch
is
th
en
f
u
r
th
er
d
ev
elo
p
ed
to
en
h
an
ce
its
p
er
f
o
r
m
an
ce
an
d
r
o
b
u
s
tn
ess
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
1
8
2
6
-
1
8
3
3
1828
−
C
u
s
to
m
ized
OC
Net
-
2
3
Mo
d
e
l:
A
v
ar
iety
tr
a
n
s
f
er
lear
n
in
g
m
o
d
el,
OC
Net
-
2
3
,
is
m
eticu
lo
u
s
ly
d
esig
n
ed
b
ased
o
n
tr
a
d
itio
n
al
tr
an
s
f
er
lear
n
in
g
ar
c
h
itectu
r
e.
T
h
is
m
o
d
el'
s
p
er
f
o
r
m
an
ce
e
x
ce
ed
s
t
h
at
o
f
th
e
b
ase
m
o
d
el
an
d
o
th
er
co
m
p
a
r
ab
le
m
o
d
els,
as e
v
id
en
ce
d
b
y
a
co
m
p
r
eh
en
s
iv
e
a
b
latio
n
s
tu
d
y
.
−
E
v
alu
atio
n
: T
h
e
r
ef
in
e
d
OC
Net
-
2
3
m
o
d
el
is
ex
ten
s
iv
ely
test
ed
u
s
in
g
v
ar
io
u
s
ev
alu
atio
n
m
etr
ics,
in
clu
d
in
g
m
ea
n
s
q
u
ar
e
er
r
o
r
(
MSE
)
,
p
ea
k
s
ig
n
al
-
to
-
n
o
is
e
r
atio
(
PS
NR
)
,
s
tr
u
ctu
r
al
s
im
ilar
ity
in
d
ex
(
SS
I
M)
,
an
d
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
.
T
h
e
r
esu
lts
co
n
f
ir
m
th
e
m
o
d
el'
s
r
o
b
u
s
tn
ess
an
d
p
r
ec
is
io
n
in
class
if
y
in
g
o
r
al
ca
n
ce
r
ca
s
es.
Fig
u
r
e
1
.
W
o
r
k
f
lo
w
o
f
th
e
en
ti
r
e
class
if
icatio
n
2
.
1
.
Da
t
a
s
et
des
cr
iptio
n
A
to
tal
o
f
5
,
1
9
2
h
is
to
p
ath
o
lo
g
ical
im
ag
es
h
as
b
ee
n
ca
r
ef
u
lly
co
llected
f
r
o
m
Kag
g
le,
a
cr
ed
ib
le
s
o
u
r
ce
o
f
d
ata
.
T
wo
ca
teg
o
r
ies
h
av
e
b
ee
n
m
eticu
lo
u
s
ly
d
is
tin
g
u
is
h
ed
“
OSC
C
”
wh
ich
s
tan
d
s
f
o
r
ca
s
es
o
f
o
r
al
s
q
u
am
o
u
s
ce
ll
ca
r
cin
o
m
a
an
d
“
n
o
r
m
al
”
wh
ic
h
r
ef
er
s
to
non
-
ca
n
ce
r
o
u
s
co
n
d
itio
n
s
.
T
h
e
class
o
f
OSC
C
co
n
tain
s
2
4
9
4
im
ag
es a
n
d
n
o
r
m
al
co
n
tain
s
2
6
9
8
im
ag
es.
2
.
2
.
I
m
a
g
e
prepro
ce
s
s
ing
t
ec
hn
iq
ues
I
n
th
is
s
ec
tio
n
,
s
ev
er
al
im
a
g
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es,
s
u
ch
as
m
e
d
ian
f
ilter
in
g
,
m
o
r
p
h
o
lo
g
ical
o
p
en
in
g
,
C
L
AHE
,
an
d
im
ag
e
r
esizin
g
,
wer
e
u
tili
ze
d
.
T
h
ese
m
eth
o
d
s
aim
ed
to
en
h
a
n
ce
im
ag
e
q
u
ality
b
y
r
em
o
v
in
g
n
o
is
e,
in
cr
ea
s
in
g
c
o
n
tr
ast,
an
d
r
ef
i
n
in
g
d
etails.
T
h
e
im
p
r
o
v
ed
clar
ity
o
f
h
is
to
p
ath
o
lo
g
ical
i
m
ag
es
f
ac
ilit
ated
p
r
ec
is
e
f
ea
tu
r
e
ex
tr
ac
tio
n
,
wh
ich
is
ess
en
tial f
o
r
a
cc
u
r
ate
an
d
e
f
f
icien
t im
ag
e
an
aly
s
is
[
2
5
]
.
2
.
2
.
1
.
I
m
a
g
e
re
s
izing
T
h
e
p
r
ep
r
o
ce
s
s
in
g
s
tag
e
s
tar
ts
with
im
ag
e
r
esizin
g
[
2
6
]
,
a
f
u
n
d
am
en
tal
s
tep
in
im
ag
e
p
r
o
ce
s
s
in
g
th
at
ad
ju
s
ts
im
ag
e
d
im
en
s
io
n
s
wh
ile
m
ain
tain
in
g
th
e
asp
ec
t
r
atio
.
I
n
th
is
s
tu
d
y
,
o
r
al
ca
n
c
er
h
is
to
p
ath
o
lo
g
ical
im
ag
es
wer
e
r
esized
to
2
2
4
×
2
2
4
p
ix
els
to
m
atch
t
h
e
in
p
u
t
s
p
ec
if
icatio
n
s
o
f
th
e
an
aly
s
is
p
ip
elin
e.
T
h
is
s
tep
en
s
u
r
es
u
n
if
o
r
m
ity
i
n
d
ata
p
r
ep
ar
atio
n
,
wh
ich
is
ess
en
tial
f
o
r
ac
h
iev
in
g
r
eliab
le
a
n
d
c
o
n
s
is
ten
t
r
esu
lts
in
s
u
b
s
eq
u
en
t a
n
aly
s
es.
2
.
2
.
2
.
M
edia
n
f
ilte
r
T
h
is
tech
n
iq
u
e
ef
f
icien
tly
r
em
o
v
ed
n
o
is
e
wh
ile
p
r
eser
v
in
g
cr
u
cial
im
ag
e
d
etails,
lead
in
g
to
en
h
an
ce
d
clar
ity
.
T
h
e
p
r
eser
v
atio
n
o
f
th
ese
d
etails
en
s
u
r
ed
th
at
cr
itica
l
f
ea
tu
r
es
r
em
ain
ed
in
tact
f
o
r
f
u
r
th
er
p
r
o
ce
s
s
in
g
.
B
y
ap
p
ly
in
g
t
h
is
m
eth
o
d
,
we
e
n
h
an
ce
d
th
e
ac
cu
r
ac
y
an
d
r
eli
ab
ilit
y
o
f
o
u
r
d
ia
g
n
o
s
tic
an
aly
s
is
[
2
7
]
.
(
,
)
=
(
,
)
∗
(
,
)
+
(
,
)
2
.
2
.
3
.
CL
AH
E
I
n
h
is
to
p
ath
o
lo
g
ical
im
a
g
e
p
r
o
ce
s
s
in
g
,
C
L
AHE
is
a
p
o
ten
t
im
ag
e
en
h
a
n
ce
m
en
t
m
eth
o
d
.
I
t
wo
r
k
s
b
y
f
ir
s
t
d
iv
id
in
g
th
e
im
ag
e
i
n
to
s
m
aller
s
ec
tio
n
s
,
th
en
s
ep
ar
ately
eq
u
alizin
g
ea
ch
r
eg
io
n
'
s
h
is
to
g
r
am
[
2
8
]
.
I
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
OC
N
et
-
2
3
:
a
fin
e
-
tu
n
e
d
tr
a
n
s
fer lea
r
n
in
g
a
p
p
r
o
a
ch
fo
r
o
r
a
l
ca
n
ce
r
d
ec
tectio
n
…
(
A
ma
tu
l
B
u
s
h
r
a
A
kh
i
)
1829
d
o
in
g
s
o
,
C
L
AHE
s
u
cc
ess
f
u
ll
y
im
p
r
o
v
es
th
e
im
ag
e'
s
v
is
ib
ilit
y
o
f
im
p
o
r
tan
t
elem
e
n
ts
,
lead
in
g
to
m
o
r
e
p
r
ec
is
e
m
ed
ical
d
iag
n
o
s
is
.
T
h
e
C
L
AHE
f
o
r
m
u
la
is
:
(
,
)
=
(
(
,
)
)
=
(
−
1
)
∑
T
h
e
o
v
e
r
all
p
r
ep
r
o
ce
s
s
in
g
ap
p
r
o
ac
h
is
d
em
o
n
s
tr
ated
in
Fig
u
r
e
2
.
Fig
u
r
e
2
.
I
m
ag
e
p
r
e
-
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
2
.
3
.
P
ro
po
s
ed
O
CNe
t
-
23
OC
Net
-
2
3
was
p
ain
s
tak
in
g
ly
co
n
s
tr
u
cted
u
s
in
g
h
y
p
e
r
-
p
ar
a
m
eter
ab
latio
n
r
esear
ch
,
with
th
e
VGG1
9
m
o
d
el
s
er
v
in
g
as
its
co
r
e
ar
ch
itectu
r
e.
T
h
e
s
elec
tio
n
o
f
VGG1
9
h
ig
h
lig
h
ts
a
d
ed
icatio
n
to
ac
cu
r
ac
y
b
ec
au
s
e
it
h
as
b
ee
n
s
h
o
wn
to
b
e
m
o
r
e
ac
cu
r
ate
th
an
o
th
er
tr
an
s
f
er
lear
n
in
g
m
o
d
els.
Af
ter
th
at,
th
o
r
o
u
g
h
ab
latio
n
r
esear
ch
was
ca
r
r
ied
o
u
t
to
f
u
r
th
er
en
h
an
ce
th
e
m
o
d
el'
s
r
esil
i
en
ce
u
s
in
g
f
in
e
-
t
u
n
in
g
ap
p
r
o
a
ch
es,
g
u
ar
an
teein
g
th
e
b
est p
er
f
o
r
m
an
ce
i
n
task
s
in
v
o
lv
in
g
th
e
ca
teg
o
r
izatio
n
o
f
o
r
al
ca
n
ce
r
[
2
9
]
–
[
3
2
]
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
Resul
t
s
o
f
t
ra
ns
f
er
lea
rning
m
o
dels
T
ab
le
1
p
r
esen
ts
th
e
r
esu
lts
o
f
s
ix
d
if
f
er
en
t
tr
an
s
f
er
lear
n
in
g
m
o
d
els
f
o
r
a
g
iv
en
task
.
Six
m
etr
ics
—
test
ac
cu
r
ac
y
,
v
alid
atio
n
ac
cu
r
ac
y
,
tr
ain
ac
c
u
r
ac
y
,
tr
ain
lo
s
s
,
test
lo
s
s
,
an
d
v
alid
atio
n
lo
s
s
—
ar
e
s
h
o
wn
in
th
e
tab
le
f
o
r
ea
ch
m
o
d
el.
T
h
e
tab
le
d
is
p
lay
s
s
ix
m
o
d
els
o
f
tr
an
s
f
er
lear
n
i
n
g
[
3
3
]
–
[
3
9
]
:
I
n
ce
p
tio
n
V3
,
Mo
b
ileNetV1
,
Mo
b
ileNetV2
,
VGG1
6
,
VGG1
9
,
Den
s
eNe
t2
0
1
,
an
d
Mo
b
ileNetV2
.
T
h
e
ta
b
le
s
h
o
ws
th
at,
o
u
t
o
f
th
e
s
ix
m
o
d
els,
VGG
-
1
9
p
er
f
o
r
m
s
th
e
b
est,
with
th
e
h
ig
h
est
tr
ain
ac
cu
r
ac
y
(
9
6
.
8
4
%),
test
ac
cu
r
ac
y
(
9
0
.
7
5
%),
a
n
d
Val
ac
cu
r
ac
y
(
9
2
.
2
4
%).
Ho
we
v
er
,
VGG
-
1
6
p
er
f
o
r
m
s
th
e
wo
r
s
t
o
u
t
o
f
th
e
s
ix
m
o
d
els,
as
ev
id
en
ce
d
b
y
its
lo
west tr
ain
a
cc
u
r
ac
y
o
f
9
5
.
8
4
%,
test
ac
cu
r
a
cy
o
f
8
4
.
7
5
%,
an
d
Val
ac
c
u
r
a
cy
o
f
8
2
.
2
4
%.
T
ab
le
1
.
R
esu
lts
o
f
s
ix
tr
an
s
f
er
lear
n
in
g
m
o
d
el
M
o
d
e
l
Tr
a
i
n
a
c
c
u
r
a
c
y
Te
st
a
c
c
u
r
a
c
y
V
a
l
a
c
c
u
r
a
c
y
Tr
a
i
n
l
o
ss
Te
st
l
o
ss
V
a
l
l
o
ss
M
o
b
i
l
e
N
e
t
V
1
9
7
.
8
0
8
8
.
2
2
8
1
.
8
5
0
.
1
7
0
.
2
8
0
.
1
8
M
o
b
i
l
e
N
e
t
V
2
9
7
.
0
0
8
5
.
7
1
8
3
.
7
8
0
.
3
1
0
.
3
2
0
.
3
2
V
G
G
1
6
9
5
.
8
4
8
4
.
7
5
8
2
.
2
4
0
.
2
1
0
.
1
6
0
.
2
9
V
G
G
1
9
9
6
.
8
4
9
0
.
7
5
9
2
.
2
4
0
.
2
1
0
.
1
4
0
.
2
0
D
e
n
seN
e
t
2
0
1
9
6
.
5
9
8
8
.
4
2
8
5
.
7
1
0
.
3
1
0
.
3
2
0
.
3
2
I
n
c
e
p
t
i
o
n
V
3
9
5
.
3
2
8
6
.
4
9
8
4
.
1
7
0
.
3
2
0
.
3
6
0
.
3
7
3
.
2
.
Resul
t
o
f
a
bla
t
io
n study
T
h
is
cr
u
cial
s
ec
tio
n
in
v
o
lv
es
a
ca
r
ef
u
l
ex
am
in
atio
n
o
f
th
e
r
esu
lts
o
b
tain
e
d
f
r
o
m
o
u
r
ex
ten
s
iv
e
ab
latio
n
r
esear
ch
,
wh
ich
f
in
el
y
tu
n
es
th
e
s
tab
le
an
d
o
p
tim
al
OC
Net
-
2
3
m
o
d
el
b
ased
o
n
th
e
r
en
o
wn
e
d
VGG1
9
ar
ch
itectu
r
e.
C
r
itical
h
y
p
er
p
a
r
am
eter
s
s
u
ch
as
b
atch
s
ize,
f
la
tten
lay
er
,
o
p
tim
izer
,
lear
n
in
g
r
ate,
an
d
ac
tiv
atio
n
f
u
n
ctio
n
wer
e
ex
am
in
e
d
a
n
d
f
in
e
-
tu
n
e
d
.
T
h
ese
p
a
r
am
eter
s
co
llectiv
ely
ac
co
u
n
ted
f
o
r
a
l
ar
g
e
p
o
r
tio
n
o
f
t
h
e
m
o
d
el'
s
r
em
ar
k
ab
le
p
er
f
o
r
m
a
n
ce
an
d
d
u
r
ab
ilit
y
.
3
.
2
.
1
.
Ca
s
e
s
t
ud
y
1
:
cha
ng
ing
ba
t
ch
s
ize
T
h
e
f
in
d
in
g
s
o
f
a
ca
s
e
s
tu
d
y
o
n
h
o
w
b
atch
s
ize
af
f
ec
ts
a
m
a
ch
in
e
lear
n
in
g
m
o
d
el'
s
test
ac
cu
r
ac
y
ar
e
d
is
p
lay
ed
in
T
a
b
le
2
.
T
h
r
ee
s
etu
p
s
with
v
ar
y
i
n
g
b
atch
s
ize
s
,
ep
o
ch
s
,
tr
ain
i
n
g
tim
es,
an
d
test
ac
cu
r
ac
ies
ar
e
s
h
o
wn
in
t
h
e
tab
le.
C
o
n
f
ig
u
r
atio
n
n
u
m
b
er
two
,
wh
e
r
e
th
e
b
atch
s
ize
is
3
2
a
n
d
t
h
e
m
o
d
el
is
tr
ain
ed
f
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
1
8
2
6
-
1
8
3
3
1830
4
3
ep
o
c
h
s
with
a
tr
ain
in
g
d
u
r
atio
n
o
f
4
s
ec
o
n
d
s
,
y
ield
s
th
e
h
ig
h
est
ac
cu
r
ac
y
o
f
9
2
.
7
4
%.
Acc
o
r
d
in
g
to
t
h
e
tab
le,
s
elec
tin
g
th
e
id
ea
l b
atch
s
ize
is
es
s
en
tial to
g
ettin
g
th
e
b
est ac
cu
r
ac
y
.
T
ab
le
2
.
C
h
an
g
in
g
b
atch
s
ize
C
o
n
f
i
g
u
r
a
t
i
o
n
n
o
B
a
t
c
h
si
z
e
Ep
o
c
h
s
×
t
r
a
i
n
i
n
g
t
i
me
Te
st
a
c
c
u
r
a
c
y
F
i
n
d
i
n
g
1
64
82
×
5
s
9
1
.
7
3
%
A
c
c
u
r
a
c
y
d
e
c
r
e
a
se
d
2
32
43
×
4
s
9
2
.
7
4
%
H
i
g
h
e
s
t
a
c
c
u
r
a
c
y
3
16
97
×
5
s
9
0
.
7
5
%
A
c
c
u
r
a
c
y
i
n
c
r
e
a
s
e
3
.
2
.
2
.
Ca
s
e
s
t
ud
y
2
:
cha
ng
ing
f
la
t
t
en
la
y
er
T
ab
le
3
s
h
o
ws
th
at
th
e
b
est
ac
cu
r
ac
y
is
o
b
tain
e
d
wh
en
th
e
f
l
atten
ed
lay
er
is
u
s
ed
.
M
o
r
eo
v
er
,
p
o
o
lin
g
tech
n
iq
u
es
s
u
ch
as
g
lo
b
al
m
a
x
p
o
o
lin
g
d
o
n
o
t
p
r
o
v
id
e
h
ig
h
er
p
er
f
o
r
m
an
ce
.
C
o
n
s
eq
u
en
tl
y
,
th
e
lay
er
ca
n
b
e
f
latten
ed
to
p
r
o
d
u
ce
9
6
.
1
3
% a
cc
u
r
ac
y
.
T
ab
le
3
.
C
h
an
g
in
g
f
latten
la
y
e
r
C
o
n
f
i
g
u
r
a
t
i
o
n
n
o
F
l
a
t
t
e
n
l
a
y
e
r
t
y
p
e
s
Ep
o
c
h
s
×
t
r
a
i
n
i
n
g
t
i
me
Te
st
a
c
c
u
r
a
c
y
F
i
n
d
i
n
g
1
F
l
a
t
t
e
n
97
×
5
s
9
2
.
7
9
%
H
i
g
h
e
s
t
a
c
c
u
r
a
c
y
2
G
l
o
b
a
l
M
a
x
P
o
o
l
i
n
g
60
×
4
s
9
0
.
6
5
%
A
c
c
u
r
a
c
y
d
e
c
r
e
a
se
d
3
.
2
.
3
.
Ca
s
e
s
t
ud
y
3
:
cha
ng
ing
o
ptim
izer
T
h
e
ef
f
ec
ts
o
f
u
s
in
g
v
ar
i
o
u
s
o
p
tim
izer
s
o
n
th
e
VGG
-
1
6
m
o
d
el'
s
te
s
t
ac
cu
r
ac
y
ar
e
s
h
o
wn
i
n
T
ab
le
4
.
I
n
co
n
f
ig
u
r
atio
n
n
o
.
1
,
wh
e
n
t
h
e
m
o
d
el
is
tr
ain
ed
f
o
r
9
7
e
p
o
ch
s
with
a
tr
ain
in
g
tim
e
o
f
5
s
ec
o
n
d
s
,
th
e
Ad
am
o
p
tim
izer
h
it
th
e
h
ig
h
est
ac
cu
r
ac
y
o
f
9
2
.
8
2
%.
Her
e,
ac
cu
r
ac
y
d
r
o
p
s
wer
e
th
e
o
u
tco
m
e
o
f
th
e
Ad
am
o
p
tim
izer
'
s
s
u
p
er
io
r
p
er
f
o
r
m
a
n
ce
o
v
er
th
e
o
th
e
r
o
p
tim
izer
s
,
in
clu
d
in
g
Na
d
am
.
T
ab
le
4
.
C
h
an
g
in
g
o
p
tim
izer
C
o
n
f
i
g
u
r
a
t
i
o
n
n
o
O
p
t
i
mi
z
e
r
s
Ep
o
c
h
s
×
t
r
a
i
n
i
n
g
t
i
me
Te
st
a
c
c
u
r
a
c
y
F
i
n
d
i
n
g
1
A
d
a
m
97
×
5
s
9
2
.
8
2
%
H
i
g
h
e
s
t
a
c
c
u
r
a
c
y
2
N
a
d
a
m
44
×
5
s
9
0
.
9
9
%
P
r
e
v
i
o
u
s a
c
c
u
r
a
c
y
3
.
2
.
4
.
Ca
s
e
s
t
ud
y
4
:
cha
ng
ing
lea
rning
ra
t
e
T
ab
le
5
p
r
esen
ts
th
e
o
u
tco
m
e
s
o
f
v
ar
y
in
g
lear
n
i
n
g
r
ates
in
ter
m
s
o
f
im
p
r
o
v
in
g
th
e
ac
cu
r
ac
y
o
f
th
e
m
o
d
el.
s
etu
p
n
o
.
1
y
ield
s
th
e
m
ax
im
u
m
ac
cu
r
ac
y
o
f
9
4
.
8
8
%.
I
n
th
is
s
etu
p
,
th
e
m
o
d
el
is
tr
ain
ed
f
o
r
5
5
s
ec
o
n
d
s
ac
r
o
s
s
9
7
ep
o
c
h
s
at
a
lear
n
in
g
r
ate
o
f
0
.
0
0
1
.
T
h
e
b
est
ac
cu
r
ac
y
in
th
is
in
s
tan
ce
was
o
b
tain
ed
with
a
lear
n
in
g
r
ate
o
f
0
.
0
0
1
,
b
u
t
lo
wer
o
r
h
ig
h
er
lear
n
in
g
r
ates le
d
to
d
ec
r
e
ases
in
ac
cu
r
ac
y
.
T
ab
le
5
.
C
h
an
g
in
g
lear
n
in
g
r
ate
C
o
n
f
i
g
u
r
a
t
i
o
n
n
o
Le
a
r
n
i
n
g
r
a
t
e
Ep
o
c
h
s
×
t
r
a
i
n
i
n
g
t
i
me
Te
st
a
c
c
u
r
a
c
y
F
i
n
d
i
n
g
1
0
.
0
0
1
94
×
55
s
9
4
.
8
8
%
H
i
g
h
e
s
t
a
c
c
u
r
a
c
y
2
0
.
0
0
8
97
×
5
s
9
1
.
8
8
%
A
c
c
u
r
a
c
y
d
e
c
r
e
a
se
d
3
0
.
0
0
0
1
68
×
57
s
9
2
.
2
8
%
A
c
c
u
r
a
c
y
d
e
c
r
e
a
se
d
3
.
2
.
5
.
Ca
s
e
s
t
ud
y
5
:
cha
ng
ing
a
ct
iv
a
t
io
n f
un
ct
io
n
T
h
e
ef
f
e
cts
o
f
u
s
in
g
v
ar
io
u
s
o
p
tim
i
ze
r
s
o
n
th
e
VGG
-
1
6
m
o
d
e
l'
s
test
a
cc
u
r
ac
y
a
r
e
s
h
o
w
n
i
n
T
a
b
le
6
.
I
n
co
n
f
i
g
u
r
a
ti
o
n
n
o
.
2
,
wh
e
n
t
h
e
m
o
d
el
is
tr
ai
n
e
d
f
o
r
9
7
ep
o
c
h
s
wit
h
a
tr
ai
n
i
n
g
ti
m
e
o
f
5
s
,
t
h
e
So
f
tMa
x
ac
ti
v
at
io
n
f
u
n
cti
o
n
att
ai
n
e
d
th
e
m
a
x
i
m
u
m
ac
c
u
r
a
cy
o
f
9
5
.
3
2
%.
H
er
e,
ac
c
u
r
a
cy
l
o
s
s
es
w
er
e
t
h
e
o
u
tc
o
m
e
o
f
t
h
e
So
f
t
Ma
x
'
s
s
u
p
e
r
i
o
r
p
e
r
f
o
r
m
a
n
ce
o
v
e
r
t
h
e
o
t
h
e
r
ac
ti
v
at
io
n
f
u
n
ct
io
n
,
wh
ic
h
in
cl
u
d
e
d
PR
eL
U
a
n
d
L
e
a
k
y
R
eL
U
.
T
ab
le
6
.
C
h
an
g
in
g
ac
tiv
atio
n
f
u
n
ctio
n
C
o
n
f
i
g
u
r
a
t
i
o
n
n
o
A
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
Ep
o
c
h
s
×
t
r
a
i
n
i
n
g
t
i
me
Te
st
a
c
c
u
r
a
c
y
F
i
n
d
i
n
g
1
P
R
e
LU
9
×
5s
9
9
.
8
8
%
P
r
e
v
i
o
u
s a
c
c
u
r
a
c
y
2
S
o
f
t
M
a
x
97
×
5s
9
5
.
3
2
%
H
i
g
h
e
s
t
a
c
c
u
r
a
c
y
3
Le
a
k
y
R
e
L
U
88
×
5s
9
0
.
6
5
%
A
c
c
u
r
a
c
y
d
e
c
r
e
a
se
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
OC
N
et
-
2
3
:
a
fin
e
-
tu
n
e
d
tr
a
n
s
fer lea
r
n
in
g
a
p
p
r
o
a
ch
fo
r
o
r
a
l
ca
n
ce
r
d
ec
tectio
n
…
(
A
ma
tu
l
B
u
s
h
r
a
A
kh
i
)
1831
3
.
3
.
P
er
f
o
rma
nce
co
m
pa
riso
n be
t
wee
n t
ra
ns
f
er
lea
rning
m
o
d
els wit
h pro
po
s
ed
m
o
del
T
h
is
s
ec
tio
n
p
r
esen
ts
a
th
o
r
o
u
g
h
co
m
p
ar
is
o
n
s
tu
d
y
th
at
co
m
p
ar
es
th
e
p
r
o
p
o
s
ed
m
o
d
el
t
o
th
e
m
o
s
t
ad
v
an
ce
d
tr
an
s
f
er
lear
n
in
g
m
o
d
els.
T
h
e
r
esu
lts
s
h
o
w
h
o
w
well
th
e
s
u
g
g
ested
m
o
d
el
p
er
f
o
r
m
ed
—
b
etter
t
h
an
an
y
o
th
er
m
o
d
el
tak
en
in
to
c
o
n
s
id
er
atio
n
in
t
h
e
s
tu
d
y
—
in
class
if
y
in
g
B
-
All
in
to
d
is
cr
ete
ca
teg
o
r
ies.
T
h
is
s
tr
o
n
g
p
r
o
o
f
o
f
co
n
ce
p
t
p
lace
s
th
e
p
r
o
p
o
s
ed
m
o
d
el
at
th
e
to
p
o
f
th
e
lis
t
f
o
r
p
r
ec
is
e
an
d
ef
f
e
ctiv
e
class
if
icatio
n
task
s
,
u
n
d
er
s
co
r
in
g
its
ef
f
ec
tiv
en
ess
in
th
e
f
ield
o
f
tr
an
s
f
er
le
ar
n
in
g
.
T
h
e
d
etailed
f
in
d
in
g
s
s
h
o
wn
in
T
ab
le
7
clea
r
ly
d
e
m
o
n
s
tr
ate
th
e
s
u
p
er
io
r
ity
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el.
T
h
ese
r
esu
lts
,
wh
ich
s
u
r
p
ass
th
e
p
er
f
o
r
m
an
ce
o
f
all
o
th
er
m
o
d
els
co
n
s
id
er
ed
,
h
ig
h
lig
h
t
th
e
ex
tr
ao
r
d
i
n
ar
y
ef
f
ec
tiv
en
ess
an
d
ex
p
er
tis
e
in
g
r
ain
ed
in
th
e
d
esig
n
o
f
th
e
r
ec
o
m
m
en
d
ed
m
o
d
el.
O
u
r
m
o
d
el'
s
s
tr
o
n
g
p
er
f
o
r
m
an
ce
d
em
o
n
s
tr
ates
its
s
o
p
h
is
ticated
n
atu
r
e
a
n
d
m
a
k
es
it
a
u
n
iq
u
e
o
p
tio
n
f
o
r
ap
p
licatio
n
s
th
at
n
ee
d
m
o
r
e
p
r
ec
is
io
n
an
d
e
f
f
icien
cy
th
an
th
o
s
e
o
f
its
co
m
p
etito
r
s
.
T
ab
le
7
.
A
th
r
o
u
g
h
co
m
p
ar
is
o
n
o
f
th
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
s
u
g
g
ested
m
o
d
el
with
t
r
an
s
f
er
le
ar
n
in
g
m
o
d
els
M
o
d
e
l
Tr
a
i
n
a
c
c
u
r
a
c
y
Te
st
a
c
c
u
r
a
c
y
V
a
l
a
c
c
u
r
a
c
y
Tr
a
i
n
l
o
ss
Te
st
l
o
ss
V
a
l
l
o
ss
M
o
b
i
l
e
N
e
t
V
1
9
7
.
8
0
8
8
.
2
2
8
1
.
8
5
0
.
1
7
0
.
2
8
0
.
1
8
M
o
b
i
l
e
N
e
t
V
2
9
7
.
0
0
8
5
.
7
1
8
3
.
7
8
0
.
3
1
0
.
3
2
0
.
3
2
V
G
G
1
6
9
5
.
8
4
8
4
.
7
5
8
2
.
2
4
0
.
2
1
0
.
1
6
0
.
2
9
V
G
G
1
9
9
6
.
8
4
9
0
.
7
5
9
2
.
2
4
0
.
2
1
0
.
1
4
0
.
2
0
D
e
n
seN
e
t
2
0
1
9
6
.
5
9
8
8
.
4
2
8
5
.
7
1
0
.
3
1
0
.
3
2
0
.
3
2
I
n
c
e
p
t
i
o
n
V
3
9
5
.
3
2
8
6
.
4
9
8
4
.
1
7
0
.
3
2
0
.
3
6
0
.
3
7
O
C
N
e
t
-
23
9
8
.
8
4
9
5
.
3
2
9
5
.
2
3
0
.
1
5
0
.
1
6
0
.
0
3
4.
CO
NCLU
SI
O
N
T
h
e
s
tu
d
y
p
r
esen
ts
OC
Net
-
2
3
,
a
cu
ttin
g
-
ed
g
e
C
AD
s
y
s
tem
b
ased
o
n
VGG1
9
,
aim
ed
at
ac
cu
r
ately
id
en
tify
in
g
a
n
d
class
if
y
in
g
m
icr
o
s
co
p
ic
im
ag
es
o
f
o
r
al
ca
n
ce
r
.
E
x
te
n
s
iv
e
ev
alu
atio
n
s
a
n
d
r
ig
o
r
o
u
s
test
in
g
d
em
o
n
s
tr
ate
its
r
eliab
ilit
y
an
d
o
p
tim
al
p
er
f
o
r
m
an
ce
.
Fu
tu
r
e
v
alid
atio
n
with
lar
g
er
d
atasets
an
d
r
ea
l
-
tim
e
d
ata
is
p
lan
n
ed
.
OC
Net
-
2
3
s
h
o
ws
p
r
o
m
is
e
as
a
to
o
l
f
o
r
ea
r
ly
d
etec
tio
n
an
d
d
ia
g
n
o
s
is
,
p
o
t
en
tially
im
p
r
o
v
in
g
p
atien
t c
ar
e
b
y
r
ed
u
cin
g
u
n
n
ec
ess
ar
y
tr
ea
tm
en
ts
an
d
en
h
a
n
ci
n
g
class
if
icatio
n
ac
cu
r
ac
y
.
RE
F
E
R
E
NC
E
S
[
1
]
E.
P
.
Tr
a
n
b
y
e
t
a
l
.
,
“
O
r
a
l
c
a
n
c
e
r
p
r
e
v
a
l
e
n
c
e
,
m
o
r
t
a
l
i
t
y
,
a
n
d
c
o
st
s
i
n
M
e
d
i
c
a
i
d
a
n
d
c
o
mm
e
r
c
i
a
l
i
n
s
u
r
a
n
c
e
c
l
a
i
m
s
d
a
t
a
,
”
C
a
n
c
e
r
Ep
i
d
e
m
i
o
l
o
g
y
B
i
o
m
a
rk
e
rs
a
n
d
Pre
v
e
n
t
i
o
n
,
v
o
l
.
3
1
,
n
o
.
9
,
p
p
.
1
8
4
9
–
1
8
5
7
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
8
/
1
0
5
5
-
9
9
6
5
.
EPI
-
22
-
0
1
1
4
.
[
2
]
S
.
B
.
Th
a
v
a
r
o
o
l
e
t
a
l
.
,
“
I
m
p
r
o
v
e
d
su
r
v
i
v
a
l
a
mo
n
g
o
r
a
l
c
a
n
c
e
r
p
a
t
i
e
n
t
s
:
F
i
n
d
i
n
g
s
f
r
o
m
a
r
e
t
r
o
sp
e
c
t
i
v
e
s
t
u
d
y
a
t
a
t
e
r
t
i
a
r
y
c
a
r
e
c
a
n
c
e
r
c
e
n
t
r
e
i
n
r
u
r
a
l
K
e
r
a
l
a
,
I
n
d
i
a
,
”
W
o
r
l
d
J
o
u
r
n
a
l
o
f
S
u
rg
i
c
a
l
O
n
c
o
l
o
g
y
,
v
o
l
.
1
7
,
n
o
.
1
,
J
a
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
8
6
/
s1
2
9
5
7
-
018
-
1
5
5
0
-
z.
[
3
]
K
.
J.
H
a
r
r
i
n
g
t
o
n
a
n
d
P
.
N
e
n
c
l
a
r
e
s,
“
T
h
e
b
i
o
l
o
g
y
o
f
c
a
n
c
e
r
,
”
Me
d
i
c
i
n
e
,
v
o
l
.
5
1
,
n
o
.
1
,
p
p
.
1
–
6
,
Jan
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
mp
me
d
.
2
0
2
2
.
1
0
.
0
0
1
.
[
4
]
M
.
Á
.
G
o
n
z
á
l
e
z
-
M
o
l
e
s,
M
.
A
g
u
i
l
a
r
-
R
u
i
z
,
a
n
d
P
.
R
a
m
o
s
-
G
a
r
c
í
a
,
“
C
h
a
l
l
e
n
g
e
s
i
n
t
h
e
e
a
r
l
y
d
i
a
g
n
o
si
s
o
f
o
r
a
l
c
a
n
c
e
r
,
e
v
i
d
e
n
c
e
g
a
p
s
a
n
d
s
t
r
a
t
e
g
i
e
s
f
o
r
i
m
p
r
o
v
e
me
n
t
:
a
sco
p
i
n
g
r
e
v
i
e
w
o
f
s
y
st
e
ma
t
i
c
r
e
v
i
e
w
s,”
C
a
n
c
e
rs
,
v
o
l
.
1
4
,
n
o
.
1
9
,
p
.
4
9
6
7
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
c
a
n
c
e
r
s1
4
1
9
4
9
6
7
.
[
5
]
S
.
Z.
Z
h
a
n
g
,
L.
X
i
e
,
a
n
d
Z
.
J
.
S
h
a
n
g
,
“
B
u
r
d
e
n
o
f
o
r
a
l
c
a
n
c
e
r
o
n
t
h
e
1
0
m
o
st
p
o
p
u
l
o
u
s
c
o
u
n
t
r
i
e
s
f
r
o
m
1
9
9
0
t
o
2
0
1
9
:
Est
i
ma
t
e
s
f
r
o
m
t
h
e
G
l
o
b
a
l
B
u
r
d
e
n
o
f
D
i
se
a
se
S
t
u
d
y
2
0
1
9
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
n
v
i
ro
n
m
e
n
t
a
l
R
e
se
a
rc
h
a
n
d
P
u
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
1
9
,
n
o
.
2
,
p
.
8
7
5
,
J
a
n
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
e
r
p
h
1
9
0
2
0
8
7
5
.
[
6
]
Y
.
Ta
n
e
t
a
l
.
,
“
O
r
a
l
s
q
u
a
m
o
u
s
c
e
l
l
c
a
r
c
i
n
o
m
a
s:
st
a
t
e
o
f
t
h
e
f
i
e
l
d
a
n
d
e
m
e
r
g
i
n
g
d
i
r
e
c
t
i
o
n
s
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
O
ra
l
S
c
i
e
n
c
e
,
v
o
l
.
1
5
,
n
o
.
1
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
3
6
8
-
023
-
0
0
2
4
9
-
w.
[
7
]
U
.
N
a
i
r
,
H
.
B
a
r
t
s
c
h
,
a
n
d
J
.
N
a
i
r
,
“
A
l
e
r
t
f
o
r
a
n
e
p
i
d
e
m
i
c
o
f
o
r
a
l
c
a
n
c
e
r
d
u
e
t
o
u
s
e
o
f
t
h
e
b
e
t
e
l
q
u
i
d
s
u
b
st
i
t
u
t
e
s
g
u
t
k
h
a
a
n
d
p
a
n
masa
l
a
:
A
r
e
v
i
e
w
o
f
a
g
e
n
t
s
a
n
d
c
a
u
sat
i
v
e
me
c
h
a
n
i
sms
,
”
M
u
t
a
g
e
n
e
s
i
s
,
v
o
l
.
1
9
,
n
o
.
4
,
p
p
.
2
5
1
–
2
6
2
,
Ju
l
.
2
0
0
4
,
d
o
i
:
1
0
.
1
0
9
3
/
m
u
t
a
g
e
/
g
e
h
0
3
6
.
[
8
]
L.
A
l
z
u
b
a
i
d
i
e
t
a
l
.
,
“
R
e
v
i
e
w
o
f
d
e
e
p
l
e
a
r
n
i
n
g
:
c
o
n
c
e
p
t
s,
C
N
N
a
r
c
h
i
t
e
c
t
u
r
e
s
,
c
h
a
l
l
e
n
g
e
s,
a
p
p
l
i
c
a
t
i
o
n
s
,
f
u
t
u
r
e
d
i
r
e
c
t
i
o
n
s,
”
J
o
u
rn
a
l
o
f
Bi
g
D
a
t
a
,
v
o
l
.
8
,
n
o
.
1
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
5
3
7
-
0
2
1
-
0
0
4
4
4
-
8.
[
9
]
M
.
A
w
a
i
s
e
t
a
l
.
,
“
H
e
a
l
t
h
c
a
r
e
p
r
o
f
e
s
si
o
n
a
l
i
n
t
h
e
l
o
o
p
(
H
P
I
L)
:
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
s
t
a
n
d
a
r
d
a
n
d
o
r
a
l
c
a
n
c
e
r
-
c
a
u
si
n
g
a
n
o
ma
l
o
u
s
r
e
g
i
o
n
s
o
f
o
r
a
l
c
a
v
i
t
y
u
s
i
n
g
t
e
x
t
u
r
a
l
a
n
a
l
y
si
s
t
e
c
h
n
i
q
u
e
i
n
a
u
t
o
f
l
u
o
r
e
s
c
e
n
c
e
i
ma
g
i
n
g
,
”
S
e
n
so
r
s
,
v
o
l
.
2
0
,
n
o
.
2
0
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
0
2
0
5
7
8
0
.
[
1
0
]
R
.
A
.
W
e
l
i
k
a
l
a
e
t
a
l
.
,
“
A
u
t
o
ma
t
e
d
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
o
r
a
l
l
e
si
o
n
s
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
e
a
r
l
y
d
e
t
e
c
t
i
o
n
o
f
o
r
a
l
c
a
n
c
e
r
,
”
I
E
EE
A
c
c
e
ss
,
v
o
l
.
8
,
p
p
.
1
3
2
6
7
7
–
1
3
2
6
9
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
1
0
1
8
0
.
[
1
1
]
P
.
R
.
Je
y
a
r
a
j
a
n
d
E.
R
.
S
a
mu
e
l
N
a
d
a
r
,
“
C
o
m
p
u
t
e
r
-
a
ssi
s
t
e
d
me
d
i
c
a
l
i
m
a
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
f
o
r
e
a
r
l
y
d
i
a
g
n
o
si
s
o
f
o
r
a
l
c
a
n
c
e
r
e
mp
l
o
y
i
n
g
d
e
e
p
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
C
a
n
c
e
r
R
e
se
a
rc
h
a
n
d
C
l
i
n
i
c
a
l
O
n
c
o
l
o
g
y
,
v
o
l
.
1
4
5
,
n
o
.
4
,
p
p
.
8
2
9
–
8
3
7
,
J
a
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
4
3
2
-
018
-
0
2
8
3
4
-
7.
[
1
2
]
X
.
A
.
L
ó
p
e
z
-
C
o
r
t
é
s,
F
.
M
a
t
a
m
a
l
a
,
B
.
V
e
n
e
g
a
s,
a
n
d
C
.
R
i
v
e
r
a
,
“
M
a
c
h
i
n
e
-
l
e
a
r
n
i
n
g
a
p
p
l
i
c
a
t
i
o
n
s
i
n
o
r
a
l
c
a
n
c
e
r
:
A
s
y
st
e
ma
t
i
c
r
e
v
i
e
w
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
2
,
n
o
.
1
1
,
Ju
n
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
2
1
1
5
7
1
5
.
[
1
3
]
A
.
U
.
R
a
h
m
a
n
e
t
a
l
.
,
“
H
i
st
o
p
a
t
h
o
l
o
g
i
c
o
r
a
l
c
a
n
c
e
r
p
r
e
d
i
c
t
i
o
n
u
si
n
g
o
r
a
l
s
q
u
a
mo
u
s c
e
l
l
c
a
r
c
i
n
o
ma
b
i
o
p
s
y
e
m
p
o
w
e
r
e
d
w
i
t
h
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
2
,
n
o
.
1
0
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
2
1
0
3
8
3
3
.
[
1
4
]
N
.
D
a
s,
E
.
H
u
ss
a
i
n
,
a
n
d
L
.
B
.
M
a
h
a
n
t
a
,
“
A
u
t
o
mat
e
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
c
e
l
l
s
i
n
t
o
m
u
l
t
i
p
l
e
c
l
a
ss
e
s
i
n
e
p
i
t
h
e
l
i
a
l
t
i
ss
u
e
o
f
o
r
a
l
sq
u
a
m
o
u
s
c
e
l
l
c
a
r
c
i
n
o
ma
u
si
n
g
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
a
n
d
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
,
”
N
e
u
r
a
l
N
e
t
w
o
rks
,
v
o
l
.
1
2
8
,
p
p
.
4
7
–
6
0
,
A
u
g
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
n
e
t
.
2
0
2
0
.
0
5
.
0
0
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
1
8
2
6
-
1
8
3
3
1832
[
1
5
]
K
.
B
a
n
s
a
l
,
R
.
K
.
B
a
t
h
l
a
,
a
n
d
Y
.
K
u
m
a
r
,
“
D
e
e
p
t
r
a
n
s
f
e
r
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
w
i
t
h
h
y
b
r
i
d
o
p
t
i
m
i
z
a
t
i
o
n
i
n
e
a
r
l
y
p
r
e
d
i
c
t
i
o
n
a
n
d
d
i
a
g
n
o
s
i
s
o
f
d
i
f
f
e
r
e
n
t
t
y
p
e
s
o
f
o
r
a
l
c
a
n
c
e
r
,
”
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
6
,
n
o
.
2
1
,
p
p
.
1
1
1
5
3
–
1
1
1
8
4
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
0
0
-
022
-
0
7
2
4
6
-
x.
[
1
6
]
A
.
R
.
A
b
d
u
l
R
a
u
f
,
W
.
H
.
M
o
h
d
I
sa,
I
.
M
.
K
h
a
i
r
u
d
d
i
n
,
M
.
A
.
M
o
h
d
R
a
z
man
,
M
.
H
.
A
r
z
m
i
,
a
n
d
A
.
P
.
P
.
A
b
d
u
l
M
a
j
e
e
d
,
“
T
h
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
o
r
a
l
sq
u
a
mo
u
s c
e
l
l
c
a
r
c
i
n
o
m
a
(
O
S
C
C
)
b
y
me
a
n
s o
f
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
,
”
i
n
L
e
c
t
u
re
N
o
t
e
s
i
n
N
e
t
w
o
rks
a
n
d
S
y
st
e
m
s
,
v
o
l
.
4
2
9
,
S
p
r
i
n
g
e
r
I
n
t
e
r
n
a
t
i
o
n
a
l
P
u
b
l
i
s
h
i
n
g
,
2
0
2
2
,
p
p
.
3
8
6
–
3
9
1
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
030
-
9
7
6
7
2
-
9
_
3
4
.
[
1
7
]
Y
.
B
.
B
a
k
a
r
e
a
n
d
K
.
M
,
“
H
i
st
o
p
a
t
h
o
l
o
g
i
c
a
l
i
ma
g
e
a
n
a
l
y
s
i
s fo
r
o
r
a
l
c
a
n
c
e
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
b
y
s
u
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
s
i
n
S
i
g
n
a
l
a
n
d
I
m
a
g
e
S
c
i
e
n
c
e
s
,
v
o
l
.
7
,
n
o
.
2
,
p
p
.
1
–
1
0
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
2
9
2
8
4
/
i
j
a
s
i
s.
7
.
2
.
2
0
2
1
.
1
-
1
0
.
[
1
8
]
M
.
J.
Je
n
g
e
t
a
l
.
,
“
R
a
ma
n
sp
e
c
t
r
o
s
c
o
p
y
a
n
a
l
y
s
i
s
f
o
r
o
p
t
i
c
a
l
d
i
a
g
n
o
s
i
s
o
f
o
r
a
l
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
C
l
i
n
i
c
a
l
M
e
d
i
c
i
n
e
,
v
o
l
.
8
,
n
o
.
9
,
A
u
g
.
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
j
c
m
8
0
9
1
3
1
3
.
[
1
9
]
A
.
F
.
K
e
b
e
d
e
,
“
H
i
st
o
p
a
t
h
o
l
o
g
i
c
o
r
a
l
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
u
si
n
g
C
N
N
s,
”
K
a
g
g
l
e
,
2
0
2
1
.
[
2
0
]
P
.
J.
F
o
r
d
a
n
d
C
.
S
.
F
a
r
a
h
,
“
Ea
r
l
y
d
e
t
e
c
t
i
o
n
a
n
d
d
i
a
g
n
o
s
i
s
o
f
o
r
a
l
c
a
n
c
e
r
:
s
t
r
a
t
e
g
i
e
s
f
o
r
i
m
p
r
o
v
e
m
e
n
t
,
”
J
o
u
r
n
a
l
o
f
C
a
n
c
e
r
P
o
l
i
c
y
,
v
o
l
.
1
,
n
o
.
1
–
2
,
p
p
.
2
–
7
,
M
a
r
.
2
0
1
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
c
p
o
.
2
0
1
3
.
0
4
.
0
0
2
.
[
2
1
]
A
.
K
.
M
a
r
k
o
p
o
u
l
o
s
,
E.
Z.
M
i
c
h
a
i
l
i
d
o
u
,
a
n
d
G
.
Tz
i
ma
g
i
o
r
g
i
s,
“
S
a
l
i
v
a
r
y
m
a
r
k
e
r
s
f
o
r
o
r
a
l
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
,
”
T
h
e
O
p
e
n
D
e
n
t
i
st
r
y
J
o
u
rn
a
l
,
v
o
l
.
4
,
n
o
.
1
,
p
p
.
1
7
2
–
1
7
8
,
A
u
g
.
2
0
1
0
,
d
o
i
:
1
0
.
2
1
7
4
/
1
8
7
4
2
1
0
6
0
1
0
0
4
0
1
0
1
7
2
.
[
2
2
]
R
.
M
e
h
r
o
t
r
a
a
n
d
D
.
K
.
G
u
p
t
a
,
“
E
x
c
i
t
i
n
g
n
e
w
a
d
v
a
n
c
e
s
i
n
o
r
a
l
c
a
n
c
e
r
d
i
a
g
n
o
s
i
s:
a
v
e
n
u
e
s
t
o
e
a
r
l
y
d
e
t
e
c
t
i
o
n
,
”
H
e
a
d
a
n
d
N
e
c
k
O
n
c
o
l
o
g
y
,
v
o
l
.
3
,
n
o
.
1
,
Ju
l
.
2
0
1
1
,
d
o
i
:
1
0
.
1
1
8
6
/
1
7
5
8
-
3
2
8
4
-
3
-
3
3
.
[
2
3
]
W
.
Ju
n
g
e
t
a
l
.
,
“
A
d
v
a
n
c
e
s
i
n
o
r
a
l
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
u
s
i
n
g
o
p
t
i
c
a
l
c
o
h
e
r
e
n
c
e
t
o
m
o
g
r
a
p
h
y
,
”
I
EE
E
J
o
u
rn
a
l
o
n
S
e
l
e
c
t
e
d
T
o
p
i
c
s
i
n
Q
u
a
n
t
u
m
E
l
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
1
,
n
o
.
4
,
p
p
.
8
1
1
–
8
1
6
,
Ju
l
.
2
0
0
5
,
d
o
i
:
1
0
.
1
1
0
9
/
J
S
TQ
E.
2
0
0
5
.
8
5
7
6
7
8
.
[
2
4
]
F
.
J
u
b
a
i
r
,
O
.
A
l
-
k
a
r
a
d
s
h
e
h
,
D
.
M
a
l
a
mo
s,
S
.
A
l
M
a
h
d
i
,
Y
.
S
a
a
d
,
a
n
d
Y
.
H
a
sso
n
a
,
“
A
n
o
v
e
l
l
i
g
h
t
w
e
i
g
h
t
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
f
o
r
e
a
r
l
y
d
e
t
e
c
t
i
o
n
o
f
o
r
a
l
c
a
n
c
e
r
,
”
O
ra
l
D
i
se
a
ses
,
v
o
l
.
2
8
,
n
o
.
4
.
W
i
l
e
y
,
p
p
.
1
1
2
3
–
1
1
3
0
,
Jan
.
2
0
2
2
.
d
o
i
:
1
0
.
1
1
1
1
/
o
d
i
.
1
3
8
2
5
.
[
2
5
]
M
.
M
.
R
.
K
r
i
sh
n
a
n
e
t
a
l
.
,
“
A
u
t
o
ma
t
e
d
o
r
a
l
c
a
n
c
e
r
i
d
e
n
t
i
f
i
c
a
t
i
o
n
u
s
i
n
g
h
i
st
o
p
a
t
h
o
l
o
g
i
c
a
l
i
ma
g
e
s
:
A
h
y
b
r
i
d
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
p
a
r
a
d
i
g
m
,
”
Mi
c
ro
n
,
v
o
l
.
4
3
,
n
o
.
2
–
3
,
p
p
.
3
5
2
–
3
6
4
,
F
e
b
.
2
0
1
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
mi
c
r
o
n
.
2
0
1
1
.
0
9
.
0
1
6
.
[
2
6
]
X
.
Li
n
,
Y
.
l
a
n
M
a
,
L
.
z
h
u
a
n
g
M
a
,
a
n
d
R
.
l
i
n
g
Z
h
a
n
g
,
“
A
s
u
r
v
e
y
f
o
r
i
ma
g
e
r
e
si
z
i
n
g
,
”
J
o
u
r
n
a
l
o
f
Z
h
e
j
i
a
n
g
U
n
i
v
e
rsi
t
y
:
S
c
i
e
n
c
e
C
,
v
o
l
.
1
5
,
n
o
.
9
,
p
p
.
6
9
7
–
7
1
6
,
S
e
p
.
2
0
1
4
,
d
o
i
:
1
0
.
1
6
3
1
/
j
z
u
s.
C
1
4
0
0
1
0
2
.
[
2
7
]
K
.
S
u
g
a
n
y
a
,
S
.
S
u
m
a
t
h
i
,
K
.
K
a
r
t
h
i
k
e
s
h
,
S
.
B
h
a
r
g
a
v
i
,
a
n
d
T.
S
e
t
h
u
ma
d
h
a
v
a
n
,
“
P
e
r
f
o
r
ma
n
c
e
a
n
a
l
y
si
s
o
f
v
a
r
i
o
u
s
f
i
l
t
e
r
s
f
o
r
d
e
n
o
i
si
n
g
b
r
e
a
s
t
c
a
n
c
e
r
h
i
s
t
o
p
a
t
h
o
l
o
g
y
i
ma
g
e
s,”
I
n
d
i
a
n
J
o
u
r
n
a
l
o
f
G
y
n
e
c
o
l
o
g
i
c
O
n
c
o
l
o
g
y
,
v
o
l
.
2
1
,
n
o
.
4
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
0
9
4
4
-
0
2
3
-
0
0
7
6
1
-
1.
[
2
8
]
K
.
R
a
o
,
M
.
B
a
n
s
a
l
,
a
n
d
G
.
K
a
u
r
,
“
R
e
t
i
n
e
x
-
c
e
n
t
e
r
e
d
c
o
n
t
r
a
st
e
n
h
a
n
c
e
m
e
n
t
met
h
o
d
f
o
r
h
i
st
o
p
a
t
h
o
l
o
g
y
i
ma
g
e
s
w
i
t
h
w
e
i
g
h
t
e
d
C
LA
H
E,
”
Ar
a
b
i
a
n
J
o
u
rn
a
l
f
o
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
4
7
,
n
o
.
1
1
,
p
p
.
1
3
7
8
1
–
1
3
7
9
8
,
J
a
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
3
3
6
9
-
0
2
1
-
0
6
4
2
1
-
w.
[
2
9
]
K
.
W
a
r
i
n
,
W
.
Li
m
p
r
a
s
e
r
t
,
S
.
S
u
e
b
n
u
k
a
r
n
,
S
.
Ji
n
a
p
o
r
n
t
h
a
m,
a
n
d
P
.
J
a
n
t
a
n
a
,
“
A
u
t
o
m
a
t
i
c
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
n
d
d
e
t
e
c
t
i
o
n
o
f
o
r
a
l
c
a
n
c
e
r
i
n
p
h
o
t
o
g
r
a
p
h
i
c
i
ma
g
e
s
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
s,”
J
o
u
r
n
a
l
o
f
O
r
a
l
Pa
t
h
o
l
o
g
y
a
n
d
M
e
d
i
c
i
n
e
,
v
o
l
.
5
0
,
n
o
.
9
,
p
p
.
9
1
1
–
9
1
8
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
1
1
/
j
o
p
.
1
3
2
2
7
.
[
3
0
]
B
.
L.
Z
i
o
b
e
r
,
M
.
G
.
M
a
u
k
,
E
.
M
.
F
a
l
l
s
,
Z.
C
h
e
n
,
A
.
F
.
Zi
o
b
e
r
,
a
n
d
H
.
H
.
B
a
u
,
“
La
b
-
on
-
a
-
c
h
i
p
f
o
r
o
r
a
l
c
a
n
c
e
r
s
c
r
e
e
n
i
n
g
a
n
d
d
i
a
g
n
o
si
s,
”
H
e
a
d
a
n
d
N
e
c
k
,
v
o
l
.
3
0
,
n
o
.
1
,
p
p
.
1
1
1
–
1
2
1
,
S
e
p
.
2
0
0
8
,
d
o
i
:
1
0
.
1
0
0
2
/
h
e
d
.
2
0
6
8
0
.
[
3
1
]
S
.
U
y
u
n
a
n
d
L.
C
h
o
r
i
d
a
h
,
“
F
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
m
a
mm
o
g
r
a
m
b
a
se
d
o
n
b
r
e
a
s
t
c
a
n
c
e
r
m
i
n
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r E
n
g
i
n
e
e
ri
n
g
(
I
J
E
C
E)
,
v
o
l
.
8
,
n
o
.
1
,
p
p
.
60
–
6
9
,
F
e
b
.
2
0
1
8
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
8
i
1
.
p
p
6
0
-
6
9
.
[
3
2
]
S
.
W
a
r
n
a
k
u
l
a
s
u
r
i
y
a
a
n
d
A
.
R
.
K
e
r
r
,
“
O
r
a
l
c
a
n
c
e
r
scr
e
e
n
i
n
g
:
p
a
st
,
p
r
e
se
n
t
,
a
n
d
f
u
t
u
r
e
,
”
J
o
u
r
n
a
l
o
f
D
e
n
t
a
l
Re
s
e
a
r
c
h
,
v
o
l
.
1
0
0
,
n
o
.
1
2
,
p
p
.
1
3
1
3
–
1
3
2
0
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
1
1
7
7
/
0
0
2
2
0
3
4
5
2
1
1
0
1
4
7
9
5
.
[
3
3
]
M
.
H
.
A
r
z
m
i
e
t
a
l
.
,
“
A
V
G
G
1
6
f
e
a
t
u
r
e
-
b
a
s
e
d
t
r
a
n
s
f
e
r
l
e
a
r
n
i
n
g
e
v
a
l
u
a
t
i
o
n
f
o
r
t
h
e
d
i
a
g
n
o
s
i
s
o
f
o
r
a
l
s
q
u
a
m
o
u
s
c
e
l
l
c
a
r
c
i
n
o
m
a
(
O
S
C
C
)
,
”
i
n
D
e
e
p
L
e
a
r
n
i
n
g
i
n
C
a
n
c
e
r
D
i
a
g
n
o
s
t
i
c
s
,
S
p
r
i
n
g
e
r
N
a
t
u
r
e
S
i
n
g
a
p
o
r
e
,
2
0
2
3
,
p
p
.
9
–
1
3
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
19
-
8
9
3
7
-
7
_
2
.
[
3
4
]
D
.
K
.
R
e
d
i
e
,
S
.
B
i
l
g
a
i
y
a
n
,
a
n
d
S
.
S
a
g
n
i
k
a
,
“
O
r
a
l
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
u
s
i
n
g
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
-
b
a
se
d
f
r
a
m
e
w
o
r
k
f
r
o
m
h
i
st
o
p
a
t
h
o
l
o
g
y
i
ma
g
e
s,
”
J
o
u
r
n
a
l
o
f
El
e
c
t
ro
n
i
c
I
m
a
g
i
n
g
,
v
o
l
.
3
2
,
n
o
.
5
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
1
7
/
1
.
j
e
i
.
3
2
.
5
.
0
5
3
0
0
4
.
[
3
5
]
M
.
M
.
M
i
j
w
i
l
,
R
.
D
o
s
h
i
,
K
.
K
.
H
i
r
a
n
,
O
.
J
.
U
n
o
g
w
u
,
a
n
d
I
.
B
a
l
a
,
“
M
o
b
i
l
e
N
e
t
V
1
-
b
a
se
d
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
f
o
r
a
c
c
u
r
a
t
e
b
r
a
i
n
t
u
m
o
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
Me
s
o
p
o
t
a
m
i
a
n
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
p
p
.
3
2
–
4
1
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
5
8
4
9
6
/
m
j
c
sc
/
2
0
2
3
/
0
0
5
.
[
3
6
]
C
.
B
u
i
u
,
V
.
R
.
D
ă
n
ă
i
l
ă
,
a
n
d
C
.
N
.
R
ă
d
u
ţ
ă
,
“
M
o
b
i
l
e
N
e
t
V
2
e
n
sem
b
l
e
f
o
r
c
e
r
v
i
c
a
l
p
r
e
c
a
n
c
e
r
o
u
s
l
e
s
i
o
n
s
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
Pr
o
c
e
sse
s
,
v
o
l
.
8
,
n
o
.
5
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
P
R
8
0
5
0
5
9
5
.
[
3
7
]
S
.
H
.
W
a
n
g
a
n
d
Y
.
D
.
Z
h
a
n
g
,
“
D
e
n
s
e
N
e
t
-
2
0
1
-
b
a
se
d
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
w
i
t
h
c
o
m
p
o
s
i
t
e
l
e
a
r
n
i
n
g
f
a
c
t
o
r
a
n
d
p
r
e
c
o
mp
u
t
a
t
i
o
n
f
o
r
mu
l
t
i
p
l
e
s
c
l
e
r
o
si
s
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
A
C
M
T
r
a
n
sa
c
t
i
o
n
s
o
n
Mu
l
t
i
m
e
d
i
a
C
o
m
p
u
t
i
n
g
,
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
6
,
n
o
.
2
s,
p
p
.
1
–
1
9
,
A
p
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
4
5
/
3
3
4
1
0
9
5
.
[
3
8
]
A
.
A
l
j
u
a
i
d
,
M
.
A
l
m
o
h
a
y
a
,
a
n
d
M
.
A
n
w
a
r
,
“
A
n
e
a
r
l
y
d
e
t
e
c
t
i
o
n
o
f
o
r
a
l
e
p
i
t
h
e
l
i
a
l
d
y
s
p
l
a
si
a
b
a
se
d
o
n
G
o
o
g
Le
N
e
t
I
n
c
e
p
t
i
o
n
-
v
3
,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
2
0
2
2
I
EEE
/
AC
M
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
n
n
e
c
t
e
d
H
e
a
l
t
h
:
A
p
p
l
i
c
a
t
i
o
n
s,
S
y
s
t
e
m
s
a
n
d
E
n
g
i
n
e
e
r
i
n
g
T
e
c
h
n
o
l
o
g
i
e
s
,
C
H
AS
E
2
0
2
2
,
2
0
2
2
,
p
p
.
1
7
2
–
1
7
3
.
d
o
i
:
1
0
.
1
1
4
5
/
3
5
5
1
4
5
5
.
3
5
6
4
7
1
0
.
[
3
9
]
L.
D
u
,
“
H
o
w
mu
c
h
d
e
e
p
l
e
a
r
n
i
n
g
d
o
e
s
n
e
u
r
a
l
st
y
l
e
t
r
a
n
sf
e
r
r
e
a
l
l
y
n
e
e
d
?
a
n
a
b
l
a
t
i
o
n
s
t
u
d
y
,
”
i
n
2
0
2
0
I
EEE
Wi
n
t
e
r
C
o
n
f
e
re
n
c
e
o
n
Ap
p
l
i
c
a
t
i
o
n
s
o
f
C
o
m
p
u
t
e
r
Vi
s
i
o
n
(
WA
C
V)
,
M
a
r
.
2
0
2
0
,
p
p
.
3
1
3
9
–
3
1
4
8
.
d
o
i
:
1
0
.
1
1
0
9
/
W
A
C
V
4
5
5
7
2
.
2
0
2
0
.
9
0
9
3
5
3
7
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Am
a
tu
l
Bu
shr
a
Akh
i
h
a
s
b
e
e
n
a
fa
c
u
lt
y
m
e
m
b
e
r
a
t
D
a
ff
o
d
il
I
n
tern
a
ti
o
n
a
l
Un
iv
e
rsity
'
s
De
p
a
rtme
n
t
o
f
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
sin
c
e
2
0
1
6
.
S
h
e
c
u
rre
n
tl
y
h
o
l
d
s
t
h
e
p
o
siti
o
n
o
f
a
ss
istan
t
p
ro
fe
ss
o
r.
S
h
e
re
c
e
iv
e
d
a
first
-
c
las
s
b
a
c
h
e
lo
r
a
n
d
m
a
ste
r
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
i
n
e
e
rin
g
fr
o
m
Ja
h
a
n
g
irn
a
g
a
r
Un
iv
e
rs
it
y
.
He
r
a
re
a
s
o
f
in
tere
st
in
stu
d
y
a
re
m
a
c
h
in
e
lea
rn
i
n
g
,
ima
g
e
p
ro
c
e
ss
in
g
,
a
n
d
b
lo
c
k
c
h
a
in
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
k
h
i.
c
se
@d
iu
.
e
d
u
.
b
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
OC
N
et
-
2
3
:
a
fin
e
-
tu
n
e
d
tr
a
n
s
fer lea
r
n
in
g
a
p
p
r
o
a
ch
fo
r
o
r
a
l
ca
n
ce
r
d
ec
tectio
n
…
(
A
ma
tu
l
B
u
s
h
r
a
A
kh
i
)
1833
Abd
u
ll
a
h
Al
No
m
a
n
h
a
s
b
e
e
n
g
ra
d
u
a
ted
f
ro
m
Da
ffo
d
i
l
In
ter
n
a
ti
o
n
a
l
Un
iv
e
rsity
'
s
De
p
a
rtme
n
t
o
f
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
.
He
re
c
e
iv
e
d
a
f
irst
-
c
las
s
b
a
c
h
e
lo
r’s
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
i
n
e
e
rin
g
fro
m
Da
ffo
d
il
In
tern
a
ti
o
n
a
l
Un
iv
e
rsity
.
His
a
re
a
s
o
f
in
tere
st
in
stu
d
y
a
re
m
a
c
h
in
e
lea
rn
in
g
a
n
d
ima
g
e
p
r
o
c
e
ss
in
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
b
d
u
l
lah
1
5
-
3
5
7
9
@d
i
u
.
e
d
u
.
b
d
.
S
o
n
j
o
y
Pr
o
sa
d
S
h
a
h
a
h
a
s
c
o
m
p
lete
d
h
is
b
a
c
h
e
lo
r
o
f
sc
ien
c
e
in
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
i
n
e
e
rin
g
a
t
Da
ffo
d
il
I
n
tern
a
ti
o
n
a
l
Un
iv
e
rsit
y
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
m
a
c
h
in
e
lea
rn
in
g
,
d
e
e
p
lea
rn
in
g
,
ima
g
e
p
r
o
c
e
ss
in
g
,
a
n
d
c
o
m
p
u
ter
v
isio
n
.
H
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
so
n
jo
y
1
5
-
3
1
8
7
@d
iu
.
e
d
u
.
b
d
.
Fa
r
z
a
n
a
A
k
te
r
se
rv
e
d
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
in
th
e
De
p
a
r
tme
n
t
o
f
Io
T
a
n
d
Ro
b
o
ti
c
s
En
g
in
e
e
ri
n
g
a
t
Ba
n
g
a
b
a
n
d
h
u
S
h
e
ik
h
M
u
ji
b
u
r
Ra
h
m
a
n
Dig
i
tal
Un
i
v
e
rsity
,
Ba
n
g
lad
e
sh
.
S
h
e
c
o
m
p
lete
d
h
e
r
B
.
Sc
.
a
n
d
M
.
S
.
d
e
g
re
e
s
in
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
in
e
e
ri
n
g
fro
m
Ja
h
a
n
g
ir
n
a
g
a
r
Un
iv
e
rsity
.
He
r
re
se
a
rc
h
fo
c
u
se
s
o
n
m
a
c
h
in
e
lea
rn
in
g
,
n
a
t
u
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
,
d
a
ta
a
n
a
ly
sis,
in
ter
n
e
t
o
f
th
i
n
g
s
,
a
n
d
b
lo
c
k
c
h
a
in
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
fa
rz
a
n
a
jo
ti
@g
m
a
il
.
c
o
m
o
r
fa
rz
a
n
a
0
0
0
1
@b
d
u
.
a
c
.
b
d
.
Mu
n
ira
A
k
te
r
La
ta
is
c
u
rre
n
tl
y
w
o
rk
i
n
g
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
a
t
th
e
De
p
a
rtme
n
t
o
f
E
d
u
c
a
ti
o
n
a
l
Tec
h
n
o
lo
g
y
a
n
d
En
g
in
e
e
rin
g
o
f
Ba
n
g
a
b
a
n
d
h
u
S
h
e
ik
h
M
u
ji
b
u
r
Ra
h
m
a
n
Dig
it
a
l
U
n
iv
e
rsit
y
,
Ba
n
g
lad
e
sh
.
S
h
e
re
c
e
iv
e
d
h
e
r
B.
S
c
.
(Ho
n
s)
a
n
d
M
.
S
c
.
d
e
g
re
e
in
in
fo
rm
a
ti
o
n
tec
h
n
o
l
o
g
y
fr
o
m
Ja
h
a
n
g
ir
n
a
g
a
r
Un
i
v
e
rsity
,
S
a
v
a
r,
Dh
a
k
a
,
Ba
n
g
lad
e
sh
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
ima
g
e
p
ro
c
e
ss
in
g
,
m
a
c
h
in
e
lea
rn
in
g
,
d
e
e
p
lea
rn
in
g
,
h
u
m
a
n
-
c
o
m
p
u
ter
i
n
tera
c
ti
o
n
,
n
a
tu
ra
l
lan
g
u
a
g
e
p
r
o
c
e
ss
in
g
,
d
a
ta
m
i
n
in
g
,
d
a
ta
a
n
a
l
y
sis,
c
o
m
p
u
ter
v
isio
n
,
h
e
a
lt
h
i
n
fo
rm
a
ti
c
s a
n
d
Io
T
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
u
n
ira0
0
0
1
@b
d
u
.
a
c
.
b
d
.
Rub
e
l
S
h
e
ik
h
se
rv
e
d
a
s
a
lec
t
u
re
r
in
th
e
De
p
a
rtme
n
t
o
f
Ed
u
c
a
ti
o
n
a
l
Tec
h
n
o
l
o
g
y
a
t
Ba
n
g
a
b
a
n
d
h
u
S
h
e
ik
h
M
u
ji
b
u
r
Ra
h
m
a
n
Dig
it
a
l
U
n
iv
e
rsit
y
,
Ba
n
g
lad
e
sh
.
He
c
o
m
p
lete
d
h
is
B
.
Sc
.
a
n
d
M
.
S
.
d
e
g
re
e
s
in
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
in
e
e
rin
g
fro
m
Ja
h
a
n
g
irn
a
g
a
r
Un
i
v
e
rsity
.
His
re
se
a
rc
h
fo
c
u
se
s
o
n
m
a
c
h
in
e
lea
rn
in
g
,
ima
g
e
p
ro
c
e
ss
in
g
,
c
o
m
p
u
ter
v
isio
n
,
d
a
ta
sc
ien
c
e
,
a
n
d
n
a
t
u
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
r
u
b
e
l0
0
0
3
@b
d
u
.
a
c
.
b
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.