I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
11
,
No
.
6
,
Dec
em
b
er
2
0
2
1
,
p
p
.
4
9
9
9
~
5
0
0
8
I
SS
N:
2
0
8
8
-
8708
,
DOI
:
1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
1
1
i
6
.
pp
4
9
9
9
-
5
0
0
8
4999
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Tra
nsfer
dee
p lea
rning
appro
a
ch f
o
r det
ec
ting co
ro
na
v
irus
disea
se
in
X
-
ra
y
i
m
a
g
es
M
o
ha
m
m
e
d Al
-
S
m
a
di,
M
a
h
m
o
u
d H
a
mm
a
d,
Q
a
nita
B
a
ni B
a
k
er
,
Sa
j
a
K
ha
l
ed
T
a
w
a
l
beh,
Sa
’
a
d A.
Al
-
Z
bo
o
n
Co
ll
e
g
e
o
f
Co
m
p
u
ter an
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
,
Jo
rd
a
n
Un
iv
e
rsity
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
Irb
id
,
Jo
r
d
a
n
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
9
,
2
0
2
0
R
ev
i
s
ed
J
u
n
6
,
2
0
2
1
A
cc
ep
ted
Ju
n
16
,
2
0
2
1
Cu
rre
n
tl
y
,
th
e
w
h
o
le
w
o
rld
is
f
ig
h
ti
n
g
a
v
e
r
y
d
a
n
g
e
ro
u
s
a
n
d
in
f
e
c
ti
o
u
s
d
ise
a
se
c
a
u
se
d
b
y
th
e
n
o
v
e
l
c
o
ro
n
a
v
iru
s,
c
a
ll
e
d
COV
ID
-
1
9
.
T
h
e
COV
ID
-
1
9
is
ra
p
id
ly
sp
re
a
d
in
g
a
ro
u
n
d
th
e
w
o
rld
d
u
e
to
it
s
h
ig
h
in
f
e
c
ti
o
n
ra
te.
T
h
e
re
f
o
re
,
e
a
rl
y
d
isc
o
v
e
r
y
o
f
CO
V
ID
-
1
9
is
c
ru
c
ial
t
o
b
e
tt
e
r
trea
t
t
h
e
in
f
e
c
ted
p
e
rso
n
a
s
w
e
ll
a
s
to
slo
w
d
o
w
n
th
e
sp
re
a
d
o
f
t
h
is
v
iru
s.
Ho
w
e
v
e
r,
t
h
e
c
u
rre
n
t
so
lu
ti
o
n
f
o
r
d
e
tec
ti
n
g
CO
V
ID
-
1
9
c
a
se
s
in
c
lu
d
i
n
g
th
e
P
CR
tes
t,
C
T
i
m
a
g
e
s,
e
p
id
e
m
io
lo
g
ica
ll
y
h
isto
ry
,
a
n
d
c
li
n
ica
l
s
y
m
p
to
m
s
su
ffe
r
f
ro
m
h
ig
h
f
a
lse
p
o
siti
v
e
.
T
o
o
v
e
rc
o
m
e
th
is p
ro
b
le
m
,
we
h
a
v
e
d
e
v
e
lo
p
e
d
a
n
o
v
e
l
tra
n
sf
e
r
d
e
e
p
lea
rn
in
g
a
p
p
r
o
a
c
h
f
o
r
d
e
tec
ti
n
g
COV
ID
-
1
9
b
a
se
d
o
n
x
-
ra
y
i
m
a
g
e
s.
Ou
r
a
p
p
ro
a
c
h
h
e
l
p
s
m
e
d
ica
l
sta
ff
in
d
e
term
in
in
g
i
f
a
p
a
ti
e
n
t
is
n
o
rm
a
l,
h
a
s
COV
ID
-
1
9
,
o
r
o
t
h
e
r
p
n
e
u
m
o
n
ia.
Ou
r
a
p
p
r
o
a
c
h
re
li
e
s
o
n
p
re
-
trai
n
e
d
m
o
d
e
ls
in
c
lu
d
i
n
g
In
c
e
p
ti
o
n
-
V3
,
X
c
e
p
ti
o
n
,
a
n
d
M
o
b
il
e
Ne
t
to
p
e
rf
o
rm
t
w
o
tas
k
s:
i
)
b
in
a
ry
c
las
si
f
ic
a
ti
o
n
to
d
e
term
in
e
if
a
p
e
rso
n
in
f
e
c
ted
w
it
h
COV
ID
-
1
9
o
r
n
o
t
a
n
d
ii
)
a
m
u
lti
-
tas
k
c
las
s
if
ica
ti
o
n
p
ro
b
lem
to
d
isti
n
g
u
is
h
n
o
rm
a
l,
COV
ID
-
1
9
,
a
n
d
p
n
e
u
m
o
n
ia
c
a
se
s.
Ou
r
e
x
p
e
ri
m
e
n
tal
re
su
lt
s
o
n
a
larg
e
d
a
tas
e
t
sh
o
w
th
a
t
th
e
F
1
-
sc
o
re
i
s
1
0
0
%
in
t
h
e
f
irst
tas
k
a
n
d
9
7
.
6
6
in
t
h
e
se
c
o
n
d
tas
k
.
K
ey
w
o
r
d
s
:
C
NN
C
OVI
D
-
1
9
tr
an
s
f
er
lear
n
i
n
g
ep
id
em
ic
Dee
p
lear
n
in
g
d
etec
tin
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
:
Mo
h
a
m
m
ed
A
l
-
S
m
ad
i
C
o
lleg
e
o
f
C
o
m
p
u
ter
an
d
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
J
o
r
d
an
Un
iv
er
s
it
y
o
f
Scie
n
ce
a
n
d
T
ec
h
n
o
lo
g
y
I
r
b
id
,
2
2
1
1
0
,
J
o
r
d
an
E
m
ail:
m
as
m
ad
i
@
j
u
s
t.e
d
u
.
j
o
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
w
h
o
le
w
o
r
ld
c
u
r
r
en
tl
y
is
f
i
g
h
ti
n
g
t
h
e
r
ec
en
tl
y
d
i
s
co
v
er
ed
in
f
ec
tio
u
s
d
is
ea
s
e
k
n
o
w
n
a
s
C
OVI
D
-
1
9
.
T
h
e
W
o
r
ld
Hea
l
th
Or
g
an
iza
tio
n
(
W
HO)
[
1
]
an
n
o
u
n
ce
d
t
h
e
C
OVI
D
-
1
9
o
u
tb
r
ea
k
a
s
a
g
lo
b
al
p
an
d
e
m
ic
o
n
Feb
r
u
ar
y
o
f
2
0
2
0
.
C
OVI
D
-
1
9
ca
u
s
e
s
a
v
ar
iet
y
o
f
in
f
ec
tio
n
s
r
elate
d
to
t
h
e
r
e
s
p
i
r
a
t
o
r
y
s
y
s
t
e
m
w
i
t
h
n
o
v
a
c
c
i
n
e
a
g
a
i
n
s
t
t
h
i
s
v
i
r
u
s
s
o
f
a
r
.
T
h
e
f
i
r
s
t
d
e
a
t
h
c
a
u
s
e
d
b
y
t
h
i
s
v
i
r
u
s
r
e
p
o
r
t
e
d
o
n
J
a
n
u
a
r
y
1
1
o
f
2
0
2
0
.
A
s
m
e
n
t
i
o
n
e
d
i
n
[
2
]
,
th
e
i
n
f
ec
tio
n
r
ate
o
f
C
O
VI
D
-
1
9
is
3
.
7
7
,
i.e
.
,
a
s
ick
p
er
s
o
n
ca
n
i
n
f
ec
t
ab
o
u
t
4
o
th
er
p
er
s
o
n
s
.
Du
e
to
t
h
e
f
ast
s
p
r
ea
d
o
f
C
O
VI
D
-
1
9
,
as
o
f
Dec
e
m
b
er
9
o
f
2
0
2
0
,
m
o
r
e
th
a
n
6
8
.
3
m
illi
o
n
p
eo
p
le
h
a
v
e
b
ee
n
in
f
ec
ted
w
it
h
C
OVI
D
-
1
9
an
d
m
o
r
e
th
a
n
1
.
5
m
illi
o
n
p
er
s
o
n
s
lo
s
t
t
h
eir
li
v
e
s
d
u
e
to
t
h
is
v
ir
u
s
in
2
2
0
d
if
f
er
e
n
t
co
u
n
tr
ies
a
n
d
ter
r
ito
r
ies
ar
o
u
n
d
th
e
w
o
r
ld
.
T
h
is
v
ir
u
s
ca
u
s
ed
all
g
o
v
er
n
m
e
n
ts
ar
o
u
n
d
t
h
e
wo
r
ld
to
tak
e
s
ev
er
e
ac
tio
n
s
to
p
r
ev
en
t
t
h
e
s
p
r
ea
d
in
g
o
f
th
is
v
ir
u
s
in
cl
u
d
i
n
g
q
u
ar
a
n
ti
n
e,
p
ar
tial
a
n
d
co
m
p
lete
lo
ck
-
d
o
w
n
to
v
ar
io
u
s
cities o
r
ev
e
n
t
h
e
w
h
o
le
co
u
n
t
r
y
,
m
o
v
in
g
t
h
e
ed
u
ca
tio
n
to
d
i
s
tan
ce
ed
u
ca
tio
n
,
m
o
v
in
g
p
h
y
s
ical
w
o
r
k
p
lace
s
to
v
ir
tu
a
l
w
o
r
k
e
n
v
ir
o
n
m
e
n
t
s
w
h
en
e
v
er
p
o
s
s
ib
le,
an
d
u
r
g
i
n
g
p
eo
p
le
to
d
o
s
o
cial
d
is
tan
ci
n
g
o
r
b
etter
s
tay
at
h
o
m
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
6
,
Dec
em
b
er
202
1
:
4
9
9
9
-
5
0
0
8
5000
Sev
er
al
w
a
y
s
h
av
e
b
ee
n
f
o
llo
w
ed
to
d
iag
n
o
s
e
th
e
C
O
VI
D
-
1
9
ca
s
es.
Fo
r
ex
a
m
p
le,
C
OVI
D
-
1
9
test
i
n
g
k
it,
p
o
s
iti
v
e
C
T
i
m
a
g
es,
ep
id
e
m
io
lo
g
ical
h
is
to
r
y
,
an
d
cl
in
i
ca
l
s
y
m
p
to
m
s
(
i.e
.
,
f
e
v
er
,
co
u
g
h
,
d
y
s
p
n
ea
,
an
d
p
n
eu
m
o
n
ia)
[
3
]
,
[
4
]
.
Ho
w
e
v
e
r
,
r
ely
i
n
g
o
n
t
h
e
cli
n
ical
s
y
m
p
to
m
s
ca
n
n
o
t
b
e
g
e
n
er
alize
d
s
in
ce
an
in
f
ec
ted
p
er
s
o
n
ca
n
ca
r
r
y
th
e
v
ir
u
s
f
o
r
f
e
w
d
a
y
s
b
e
f
o
r
e
th
e
s
y
m
p
to
m
s
ap
p
ea
r
s
.
Mo
r
eo
v
er
,
d
if
f
er
en
t
p
er
s
o
n
s
r
esp
o
n
d
d
if
f
er
e
n
tl
y
to
th
e
v
ir
u
s
b
ased
o
n
th
eir
h
ea
lt
h
co
n
d
itio
n
an
d
th
eir
i
m
m
u
n
e
s
y
s
te
m
.
Ho
w
e
v
er
,
s
ev
er
al
f
ac
to
r
s
af
f
ec
ted
th
e
ac
cu
r
ac
y
o
f
t
h
e
r
esu
lt
s
o
b
tain
ed
f
r
o
m
t
h
e
tes
ti
n
g
k
i
ts
s
u
c
h
a
s
t
h
e
q
u
alit
y
a
n
d
th
e
a
v
ailab
ilit
y
o
f
th
e
test
i
n
g
k
it
s
as
w
ell
as
t
h
e
n
ee
d
f
o
r
r
etak
in
g
th
e
tes
t
s
e
v
er
al
ti
m
e
s
,
in
s
o
m
e
ca
s
es,
to
m
ak
e
s
u
r
e
th
at
t
h
e
p
er
s
o
n
is
test
ed
n
eg
ati
v
e
ag
ai
n
s
t
C
OVI
D
-
1
9
.
T
h
er
ef
o
r
e,
ca
r
ef
u
ll
y
a
n
al
y
z
in
g
x
-
r
a
y
i
m
ag
e
s
an
d
C
T
s
ca
n
s
g
i
v
e
m
ed
ical
s
ta
f
f
b
etter
u
n
d
er
s
ta
n
d
in
g
o
f
th
e
h
ea
lt
h
s
tat
u
s
o
f
th
e
p
atien
t
in
cl
u
d
i
n
g
i
f
h
e
i
s
b
ein
g
i
n
f
ec
ted
b
y
C
OVI
D
-
1
9
,
s
u
f
f
er
f
r
o
m
o
th
er
p
n
eu
m
o
n
ia,
o
r
n
o
r
m
al
[
5
]
.
M
o
r
eo
v
er
,
ca
r
ef
u
ll
y
a
n
al
y
zi
n
g
x
-
r
a
y
s
an
d
C
T
s
ca
n
s
allo
w
m
ed
ical
s
taf
f
to
u
n
d
er
s
t
an
d
th
e
i
n
f
ec
ted
ar
ea
an
d
t
h
e
s
ev
er
it
y
o
f
t
h
e
d
is
ea
s
e.
Un
f
o
r
tu
n
atel
y
,
d
eter
m
i
n
i
n
g
C
OVI
D
-
1
9
f
r
o
m
o
th
er
t
y
p
e
s
o
f
p
n
e
u
m
o
n
ia
o
r
e
v
en
n
o
r
m
a
l
u
s
in
g
x
-
r
a
y
i
m
a
g
es
is
n
o
t
a
tr
iv
ial
p
r
o
ce
s
s
a
n
d
er
r
o
r
-
p
r
o
n
e
f
o
r
m
a
n
y
r
ad
io
l
o
g
is
ts
a
n
d
m
ed
ical
s
ta
f
f
.
T
o
th
at
en
d
,
th
is
r
esear
c
h
tr
ies
to
h
el
p
m
ed
ical
s
taf
f
i
n
ac
cu
r
atel
y
d
etec
ti
n
g
C
OVI
D
-
1
9
in
x
-
r
a
y
i
m
ag
e
s
u
s
i
n
g
d
ee
p
n
eu
r
al
n
et
w
o
r
k
s
tec
h
n
iq
u
es.
I
n
r
esp
o
n
s
e
to
t
h
is
g
lo
b
al
p
an
d
e
m
ic,
m
a
n
y
r
esear
c
h
er
s
d
ev
elo
p
ed
s
ev
er
al
d
iag
n
o
s
in
g
s
y
s
te
m
s
d
ep
en
d
in
g
o
n
d
ee
p
lear
n
in
g
a
n
d
m
ac
h
i
n
e
lear
n
i
n
g
tec
h
n
iq
u
es.
Dee
p
lear
n
in
g
tec
h
n
iq
u
e
s
a
r
e
p
er
f
ec
t
ca
n
d
id
ate
f
o
r
m
ed
ical
i
m
ag
i
n
g
d
ataset
s
in
ce
t
h
e
y
ca
n
ex
tr
ac
t
i
m
p
o
r
tan
t
f
ea
tu
r
es
f
r
o
m
t
h
e
m
ed
ica
l
i
m
a
g
es
i
n
clu
d
i
n
g
s
h
ap
e
a
n
d
s
p
atial
r
elatio
n
f
e
atu
r
es.
I
n
p
ar
ticu
lar
,
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
et
w
o
r
k
s
(
C
NN
s
)
p
r
o
v
id
e
th
e
b
est
p
er
f
o
r
m
a
n
ce
r
eg
ar
d
i
n
g
f
ea
t
u
r
e
ex
tr
ac
tio
n
as
w
el
l
as
th
e
ir
ab
ili
t
y
to
i
m
p
r
o
v
e
lear
n
in
g
f
r
o
m
lo
w
li
g
h
t
i
m
a
g
e
s
ex
tr
ac
ted
f
r
o
m
v
id
eo
s
[
6
]
.
Fu
r
th
er
m
o
r
e,
C
NN
ap
p
r
o
ac
h
es
h
a
v
e
b
ee
n
s
u
cc
e
s
s
f
u
ll
y
u
t
ilized
t
o
r
ec
o
g
n
ize
s
e
v
er
al
d
is
ea
s
es,
f
o
r
in
s
tan
ce
,
cla
s
s
i
f
y
in
g
p
o
l
y
p
s
d
u
r
in
g
co
lo
n
o
s
c
o
p
ic
v
id
eo
s
as
w
ell
a
s
u
s
i
n
g
x
-
r
a
y
i
m
a
g
es
f
o
r
d
iag
n
o
s
i
s
o
f
p
ed
iatr
ic
p
n
e
u
m
o
n
ia
[
7
]
,
[
8
]
.
Sev
er
al
f
ea
t
u
r
es a
r
e
ac
cr
ed
ited
to
id
en
tify
th
e
v
ir
al
p
ath
o
g
e
n
s
b
ased
o
n
s
ca
n
s
p
atter
n
s
(
i.e
.
C
T
o
r
x
-
r
a
y
)
[
9
]
.
T
h
e
ch
ar
ac
ter
is
tic
th
at
d
is
ti
n
g
u
is
h
es
C
OVI
D
-
1
9
f
r
o
m
o
th
er
s
ar
e
t
h
e
b
ilater
al
d
is
tr
ib
u
tio
n
o
f
p
atc
h
y
s
h
ad
o
w
s
a
n
d
g
r
o
u
n
d
-
g
la
s
s
o
p
ac
ity
in
th
e
ea
r
l
y
s
ta
g
es.
Mo
r
eo
v
er
,
m
u
lt
ip
le
g
r
o
u
n
d
g
las
s
a
n
d
in
f
iltra
t
e
s
i
n
lu
n
g
s
w
ill
ap
p
ea
r
in
late
s
tag
es
[
3
]
.
C
NN
ap
p
r
o
ac
h
es
m
a
y
h
elp
to
id
en
ti
f
y
t
h
e
u
n
iq
u
e
f
ea
t
u
r
es
o
f
C
OVI
D
-
1
9
p
n
eu
m
o
n
ia
r
eg
ar
d
in
g
th
e
d
if
f
icu
lt
y
o
f
v
is
u
al
r
ec
o
g
n
itio
n
.
I
n
th
i
s
r
esear
ch
,
w
e
p
r
o
p
o
s
ed
a
d
iag
n
o
s
tic
s
y
s
te
m
u
s
i
n
g
d
ee
p
le
ar
n
i
n
g
tech
n
iq
u
e
b
ased
o
n
co
n
v
o
lu
tio
n
al
n
eu
r
a
l
n
et
w
o
r
k
s
(
C
NNs
)
to
d
etec
t COVI
D
-
1
9
ca
s
es.
T
h
e
m
ain
co
n
tr
ib
u
tio
n
o
f
t
h
is
r
es
ea
r
ch
ca
n
b
e
s
u
m
m
ar
ized
as:
No
v
el
tr
an
s
f
er
lear
n
i
n
g
m
o
d
el
s
;
t
o
d
ev
elo
p
o
u
r
C
OVI
D
-
1
9
p
r
ed
ictio
n
s
y
s
te
m
,
w
e
h
av
e
d
e
v
elo
p
ed
a
n
o
v
e
l
tr
an
s
f
er
d
ee
p
lear
n
in
g
ap
p
r
o
a
ch
.
Ou
r
tr
an
s
f
er
lear
n
i
n
g
r
elie
s
o
n
3
s
tate
-
of
-
th
e
-
ar
t
C
NN
m
o
d
el
s
th
a
t
h
a
v
e
b
ee
n
p
r
e
-
tr
ai
n
ed
o
n
I
m
ag
e
N
et
d
ataset
f
o
llo
w
ed
b
y
g
lo
b
al
av
er
a
g
e
p
o
o
lin
g
to
e
x
tr
ac
t
d
is
cr
i
m
in
at
iv
e
f
ea
t
u
r
es,
th
e
n
b
atch
n
o
r
m
aliza
tio
n
an
d
d
r
o
p
o
u
t to
p
r
ev
en
t th
e
o
v
er
f
itti
n
g
.
D
ataset
;
w
e
h
a
v
e
co
llected
a
d
ataset
co
n
s
is
t
in
g
o
f
7
,
8
0
0
x
-
r
a
y
i
m
a
g
es
f
r
o
m
d
if
f
er
en
t
s
o
u
r
ce
s
.
T
h
ese
i
m
a
g
es
co
n
tai
n
s
x
-
r
a
y
f
o
r
p
atien
t
s
w
i
th
C
OVI
D
-
1
9
,
n
o
r
m
al,
an
d
p
atien
ts
w
it
h
o
th
er
p
n
eu
m
o
n
ia.
T
o
en
lar
g
e
o
u
r
d
ataset,
w
e
h
a
v
e
a
p
p
lied
v
ar
io
u
s
d
ata
au
g
m
e
n
tat
io
n
tech
n
iq
u
e
s
an
d
g
en
er
ated
4
9
9
,
2
0
0
lab
ele
d
x
-
r
a
y
i
m
ag
e
s
.
W
e
m
ak
e
t
h
i
s
d
ataset
av
ai
lab
le
to
o
th
er
r
esear
ch
er
s
an
d
p
r
ac
titi
o
n
er
s
o
n
d
e
m
an
d
.
C
o
m
p
r
eh
e
n
s
i
v
e
s
tu
d
y
;
w
e
p
r
o
v
id
e
a
co
m
p
r
eh
en
s
i
v
e
s
t
u
d
y
ab
o
u
t
th
e
av
a
ilab
le
d
atasets
f
o
r
C
OVI
D
-
1
9
r
esear
ch
as
w
ell
as t
h
e
r
elate
d
w
o
r
k
e
f
f
o
r
t in
d
etec
tin
g
C
OVI
D
-
1
9
u
s
i
n
g
m
ac
h
i
n
e
lear
n
i
n
g
t
ec
h
n
iq
u
es.
T
o
d
ev
elo
p
an
d
ev
alu
a
te
o
u
r
ap
p
r
o
ac
h
,
w
e
h
a
v
e
u
s
ed
7
,
8
0
0
X
-
r
a
y
i
m
a
g
es
an
d
f
o
cu
s
ed
o
n
t
w
o
m
ai
n
task
s
.
T
h
e
f
ir
s
t
ta
s
k
is
to
d
ev
e
lo
p
a
b
in
ar
y
cla
s
s
i
f
ier
t
h
at
ca
n
d
is
tin
g
u
is
h
b
et
w
ee
n
C
OVI
D
-
1
9
o
r
n
o
n
C
OVI
D
x
-
r
a
y
i
m
ag
e.
T
h
e
s
ec
o
n
d
tas
k
is
to
b
u
ild
a
m
u
lti
-
clas
s
class
if
ier
th
at
ca
n
d
eter
m
i
n
e
i
f
an
x
-
r
ay
i
m
a
g
e
co
n
tai
n
s
C
OVI
D
-
1
9
,
o
th
er
p
n
eu
m
o
n
ia,
o
r
n
o
r
m
al
i
m
a
g
e.
Ou
r
tr
an
s
f
er
d
ee
p
lear
n
in
g
m
o
d
el
u
tili
z
ed
3
s
tat
-
of
-
t
h
e
-
ar
t
m
o
d
el
s
,
I
n
ce
p
tio
n
-
V3
,
Xce
p
tio
n
,
an
d
Mo
b
ileNet.
U
s
i
n
g
o
u
t
d
ataset
a
f
ter
d
ata
a
u
g
m
e
n
tat
io
n
,
o
u
r
ap
p
r
o
ac
h
ac
h
iev
ed
1
0
0
%
ac
c
u
r
ac
y
a
n
d
1
0
0
%
F
-
s
co
r
e
o
n
th
e
f
ir
s
t
t
ask
.
R
eg
ar
d
i
n
g
th
e
s
ec
o
n
d
ta
s
k
,
o
u
r
b
e
s
t
m
o
d
el
ac
h
iev
ed
ac
c
u
r
ac
y
o
f
9
7
.
3
7
% a
n
d
an
F
-
s
co
r
e
o
f
9
7
.
6
6
%.
T
h
e
r
est
o
f
th
is
p
ap
er
is
o
r
g
a
n
ized
as
f
o
llo
w
s
;
s
ec
tio
n
2
d
is
cu
s
s
t
h
e
r
elate
d
r
esear
ch
ef
f
o
r
t
to
o
u
r
r
esear
ch
an
d
p
r
o
v
id
e
a
d
etaile
d
d
is
cu
s
s
io
n
ab
o
u
t
th
e
a
v
ailab
le
d
atasets
o
f
C
OVI
D
-
1
9
.
Sect
io
n
3
d
escr
ib
es
o
u
r
m
et
h
o
d
in
m
o
d
e
d
etails
a
n
d
s
e
ctio
n
4
s
h
o
w
s
th
e
e
x
p
er
i
m
e
n
ta
l
r
esu
lt
s
o
f
o
u
r
ap
p
r
o
ac
h
.
Sect
io
n
5
d
is
cu
s
s
es
t
h
e
r
esu
lt
s
.
Fin
a
ll
y
,
o
u
r
p
ap
er
co
n
clu
d
es
w
it
h
av
e
n
u
e
o
f
f
u
t
u
r
e
d
ir
ec
tio
n
s
i
n
s
ec
tio
n
6
.
2.
R
E
L
AT
E
D
WO
RK
Du
e
to
t
h
e
g
lo
b
al
p
an
d
e
m
ic
c
au
s
ed
b
y
th
e
n
o
v
el
co
r
o
n
av
ir
u
s
,
C
OVI
D
-
1
9
,
m
a
n
y
r
esear
ch
er
s
i
n
al
l
f
ield
s
w
o
r
k
ed
v
er
y
h
ar
d
to
s
tu
d
y
an
d
in
v
est
ig
ate
t
h
is
v
ir
u
s
an
d
its
ef
f
ec
t
o
f
t
h
e
h
u
m
a
n
it
y
.
I
n
th
e
m
ac
h
i
n
e
lear
n
in
g
f
iled
,
s
o
m
e
r
esear
c
h
e
r
s
tr
ied
to
co
llect
d
atas
ets,
tex
t
u
al
an
d
i
m
a
g
es,
to
m
a
k
e
t
h
e
m
av
ailab
le
to
o
th
er
s
.
W
h
ile
o
th
er
s
tr
ied
to
d
ev
elo
p
n
e
w
tech
n
iq
u
e
s
to
d
etec
t
th
e
C
OVI
D
-
1
9
ac
cu
r
atel
y
.
T
h
is
s
ec
tio
n
(
1
)
d
is
cu
s
s
e
s
th
e
r
elate
d
r
esear
ch
ef
f
o
r
ts
i
n
th
e
m
ac
h
i
n
e
lear
n
i
n
g
f
ie
ld
,
s
ec
tio
n
2
.
1
as
w
ell
as
(
2
)
d
is
c
u
s
s
in
g
t
h
e
av
ailab
le
C
OVI
D
-
1
9
d
atasets
in
s
ec
tio
n
2
.
2
.
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:
2
0
8
8
-
8708
Tr
a
n
s
fer d
ee
p
lea
r
n
in
g
a
p
p
r
o
a
ch
fo
r
d
etec
tin
g
c
o
r
o
n
a
viru
s
d
is
ea
s
e
(
C
OV
I
D
-
19)
…
(
Mo
h
a
mme
d
A
l
-
S
ma
d
i
)
5001
2
.
1
.
M
a
chine le
a
rning
ba
s
ed
t
ec
h
niq
ue
s
A
lt
h
o
u
g
h
t
h
e
w
o
r
k
o
n
th
e
m
ed
ical
i
m
a
g
es
is
r
elate
d
to
o
u
r
w
o
r
k
[
1
0
]
-
[
1
2
]
,
d
u
e
to
th
e
s
p
ac
e
li
m
ita
tio
n
,
i
n
th
is
s
ec
tio
n
w
e
w
il
l
d
is
c
u
s
s
t
h
e
r
elate
d
r
esear
ch
e
f
f
o
r
ts
i
n
d
etec
ti
n
g
C
OVI
D
-
1
9
u
s
i
n
g
m
ac
h
i
n
e
lear
n
in
g
tec
h
n
iq
u
e
s
.
Yan
et
a
l
.
[
1
3
]
in
tr
o
d
u
ce
d
an
XGB
o
o
s
t
class
i
f
ier
to
p
r
ed
ict
th
e
p
r
o
g
n
o
s
tic
s
tate
’
s
s
e
v
er
e
o
f
C
OVI
D
-
1
9
in
f
ec
tio
n
u
s
i
n
g
clin
ical
d
ata
i
n
W
u
h
a
n
,
C
h
in
a
.
I
n
ad
d
itio
n
,
P
al
et
a
l.
[
1
4
]
in
tr
o
d
u
ce
d
an
L
ST
M
m
o
d
el
to
p
r
ed
ict
th
e
lo
n
g
d
u
r
atio
n
o
u
tb
r
ea
k
ca
u
s
ed
b
y
C
O
VI
D
-
1
9
an
d
h
o
w
t
h
e
r
is
k
a
f
f
e
cts
th
e
co
u
n
tr
ies
s
o
th
e
y
ca
n
ta
k
e
p
r
ev
e
n
ti
v
e
s
tep
s
ea
r
lie
r
.
On
th
e
o
th
er
h
a
n
d
,
Ma
tteo
et
a
l.
[
1
5
]
co
llected
lar
g
e
d
ataset
o
b
tai
n
ed
f
r
o
m
t
h
e
s
o
cial
m
ed
ia
p
latf
o
r
m
s
(
e.
g
.
,
T
w
itter
,
Yo
u
T
u
b
e,
Face
b
o
o
k
)
r
elate
d
to
th
e
C
OVI
D
-
1
9
an
d
an
al
y
ze
d
th
e
m
.
W
an
g
et
a
l.
[
1
6
]
in
tr
o
d
u
ce
d
a
d
ia
g
n
o
s
t
ic
e
v
alu
a
tio
n
u
s
i
n
g
a
tr
a
n
s
f
er
lear
n
i
n
g
b
ase
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
(
I
n
c
e
p
t
i
o
n
n
e
t
w
o
r
k
)
u
s
i
n
g
C
T
i
m
a
g
e
s
t
o
d
e
t
e
c
t
t
h
e
C
O
V
I
D
-
1
9
.
S
i
m
i
l
a
r
i
t
y
,
S
e
t
h
y
e
t
a
l.
[
1
7
]
p
r
o
p
o
s
e
d
s
e
v
e
r
a
l
d
e
e
p
n
e
u
r
a
l
n
e
tw
o
r
k
s
b
a
s
e
d
o
n
S
V
M
u
s
i
n
g
d
e
e
p
f
e
a
t
u
r
e
s
t
o
d
e
t
e
c
t
C
O
V
I
D
-
1
9
i
n
x
-
r
a
y
i
m
a
g
e
s
.
S
h
a
n
et
a
l.
[
1
8
]
in
tr
o
d
u
ce
d
an
au
to
m
atic
s
eg
m
en
tatio
n
b
a
s
ed
o
n
d
ee
p
lear
n
in
g
to
s
p
ec
if
y
th
e
i
n
f
ec
tio
n
r
eg
io
n
s
o
f
t
h
e
C
OVI
D
-
1
9
b
ased
o
n
th
eir
s
h
a
p
es,
v
o
lu
m
es,
a
n
d
p
er
ce
n
tag
e
o
f
in
f
ec
tio
n
(
P
OI
)
r
ely
in
g
o
n
c
h
est
C
T
s
ca
n
s
.
Ma
g
h
d
id
et
a
l.
[
1
9
]
p
r
esen
ted
th
e
id
ea
o
f
p
r
o
p
o
s
in
g
A
I
to
o
ls
f
o
r
C
OVI
D
-
1
9
d
iag
n
o
s
is
as
w
e
ll
a
s
p
er
f
o
r
m
in
g
d
ee
p
lear
n
in
g
s
y
s
t
e
m
u
s
in
g
C
T
an
d
x
-
r
a
y
i
m
a
g
e
s
.
Si
m
i
l
ar
l
y
,
Xu
et
a
l.
[
2
0
]
s
tu
d
ied
th
e
p
o
s
s
ib
ilit
y
o
f
p
r
o
p
o
s
in
g
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
es
to
b
e
u
s
ed
a
s
a
d
iag
n
o
s
tic
s
y
s
te
m
to
p
r
ed
ict
C
OVI
D
-
1
9
o
r
o
th
e
r
p
n
eu
m
o
n
ia
u
s
in
g
C
T
s
ca
n
s
.
G
o
ze
s
et
a
l.
[
2
1
]
p
r
o
p
o
s
ed
au
to
m
ated
C
T
i
m
a
g
e
an
a
l
y
s
is
to
o
l
ai
m
s
to
d
etec
t
an
d
tr
ac
k
i
f
t
h
e
p
atie
n
t
i
n
f
ec
ted
o
f
C
OVI
D
-
1
9
d
is
ea
s
e
o
r
n
o
t.
L
i
et
a
l.
[
2
2
]
p
r
o
p
o
s
ed
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
ca
lled
C
OVNe
t
(
C
O
VI
D
-
1
9
d
etec
tio
n
n
e
u
r
al
n
et
w
o
r
k
)
t
h
at
is
b
e
ab
le
to
o
b
tain
v
is
u
a
l
f
ea
tu
r
e
s
f
r
o
m
t
h
e
v
o
lu
m
etr
ic
C
T
s
ca
n
s
an
d
d
is
ti
n
g
u
i
s
h
b
et
w
ee
n
C
O
VI
D
-
19
an
d
o
th
er
p
n
eu
m
o
n
ia.
B
u
k
h
ar
i
et
a
l.
[
2
3
]
p
r
o
p
o
s
ed
tr
an
s
f
er
lear
n
i
n
g
u
s
i
n
g
p
r
e
-
tr
a
in
ed
I
m
a
g
eNe
t
ai
m
s
to
av
o
id
lack
o
f
d
ataset
i
s
s
u
e
to
d
etec
t
o
n
e
o
f
th
e
t
h
r
ee
class
es
C
OVI
D
-
1
9
,
p
n
e
u
m
o
n
i
a,
o
r
n
o
r
m
a
l.
Si
m
ilar
l
y
,
A
p
o
s
to
lo
p
o
u
lo
s
et
a
l.
[
2
4
]
p
r
o
p
o
s
e
d
tr
an
s
f
er
lear
n
in
g
ad
ap
tio
n
th
at
p
er
f
o
r
m
s
C
NN
f
r
o
m
s
cr
atch
ca
lled
Mo
b
ile
Ne
t
to
d
ete
ct
ty
p
e
s
o
f
p
n
e
u
m
o
n
i
a.
Nar
in
et
a
l.
[
2
5
]
p
r
o
p
o
s
ed
3
d
ee
p
C
NN
m
o
d
el
s
to
class
if
y
a
b
alan
ce
d
d
atas
et
o
f
x
-
r
a
y
i
m
a
g
es
to
C
O
VI
D
-
1
9
o
r
n
o
n
C
OVI
D.
J
ais
w
al
et
a
l.
[
2
6
]
p
r
o
p
o
s
ed
d
ee
p
lear
n
i
n
g
m
o
d
el
to
id
en
t
i
f
y
in
g
p
n
e
u
m
o
n
ia
t
y
p
e
s
.
A
r
o
r
a
et
a
l.
[
2
7
]
p
r
esen
ted
an
a
n
al
y
s
i
s
s
t
u
d
y
u
s
i
n
g
d
ee
p
lear
n
in
g
r
e
g
ar
d
in
g
C
OVI
D
-
1
9
.
Far
o
o
q
an
d
Ha
f
ee
z
[
2
8
]
in
tr
o
d
u
ce
d
an
en
h
a
n
ce
m
en
t
o
f
t
h
e
p
r
ev
io
u
s
m
o
d
els
to
d
etec
t
p
n
e
u
m
o
n
i
a
ca
s
es
u
s
i
n
g
f
in
e
-
t
u
n
in
g
R
e
s
Net5
0
.
H
o
w
e
v
e
r
,
A
l
q
u
d
a
h
et
a
l
.
[
2
9
]
p
r
o
p
o
s
e
d
h
y
b
r
i
d
a
p
p
r
o
a
c
h
b
a
s
e
d
o
n
C
N
N
m
o
d
e
l
s
t
o
d
e
t
e
c
t
C
O
V
I
D
-
1
9
i
n
e
a
r
l
i
e
r
s
t
a
g
e
s
.
A
l
o
m
et
a
l
.
[
3
0
]
i
n
t
r
o
d
u
c
e
d
e
n
d
-
to
-
e
n
d
s
y
s
t
e
m
t
o
d
e
t
e
c
t
C
O
V
I
D
-
1
9
a
n
d
s
e
l
e
c
t
t
h
e
i
n
f
e
c
t
e
d
a
r
e
a
.
S
i
m
i
l
a
r
l
y
,
H
a
m
m
o
u
d
i
et
a
l.
[
3
1
]
p
r
o
p
o
s
ed
an
au
to
m
a
ti
c
C
NN
ap
p
r
o
ac
h
th
at
ai
m
s
to
d
etec
t
th
e
esti
m
atio
n
o
f
i
n
f
ec
t
io
n
r
ate
u
s
i
n
g
x
-
r
a
y
i
m
a
g
es.
R
ah
m
at
izad
eh
et
a
l.
[
3
2
]
p
r
o
p
o
s
ed
an
A
I
-
b
ased
d
ec
is
io
n
-
m
ak
i
n
g
s
y
s
te
m
ai
m
s
to
h
elp
an
d
m
an
a
g
e
t
h
e
C
OVI
D
-
19
I
C
U
p
atien
t
s
.
Mo
r
eo
v
er
,
Sh
i
et
a
l.
[
3
3
]
an
d
Ng
u
y
e
n
[
3
4
]
in
tr
o
d
u
ce
d
co
m
p
r
eh
en
s
i
v
e
r
ev
ie
w
s
o
f
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
es
t
h
at
u
s
ed
to
d
etec
t
an
d
s
p
ec
if
y
t
h
e
in
f
ec
ted
ar
ea
as
w
ell
a
s
h
o
w
th
e
A
I
ca
n
h
elp
to
r
ed
u
c
e
th
e
C
O
VI
D
-
1
9
in
f
ec
tio
n
,
s
p
r
ea
d
,
an
d
d
etec
tio
n
.
A
ll
o
f
th
e
af
o
r
e
m
en
tio
n
ed
r
esear
ch
ef
f
o
r
ts
s
u
p
p
o
r
ts
th
at
d
e
ep
lear
n
in
g
i
s
a
u
s
e
f
u
l
to
o
l
f
o
r
d
etec
tin
g
C
OVI
D
-
1
9
f
r
o
m
v
ar
io
u
s
s
o
u
r
ce
s
in
o
r
d
er
to
h
elp
m
ed
ical
s
t
af
f
i
n
d
iag
n
o
s
i
n
g
p
atien
ts
a
s
w
ell
a
s
r
ed
u
cin
g
t
h
e
s
p
r
ea
d
o
f
th
i
s
v
ir
u
s
.
Ou
r
r
esea
r
ch
is
s
i
m
ilar
to
t
h
ese
r
esear
c
h
ef
f
o
r
t
b
u
t
s
ig
n
i
f
ica
n
tl
y
d
if
f
er
e
n
t.
W
e
h
a
v
e
le
v
er
-
ag
ed
tr
an
s
f
er
lear
n
i
n
g
tech
n
iq
u
e
to
m
a
k
e
o
u
r
ap
p
r
o
ac
h
f
ast
er
an
d
r
eq
u
ir
es
less
co
m
p
u
tati
o
n
al
s
p
ec
if
icatio
n
s
.
W
e
h
av
e
co
llected
x
-
r
a
y
i
m
ag
e
s
s
y
s
te
m
at
icall
y
f
r
o
m
d
i
f
f
er
e
n
t
d
ata
s
o
u
r
ce
s
a
n
d
ap
p
lied
v
a
r
io
u
s
s
o
p
h
is
ticate
d
d
ata
au
g
m
en
tatio
n
tec
h
n
iq
u
es
to
in
cr
ea
s
e
th
e
p
er
f
o
r
m
an
ce
o
f
o
u
r
ap
p
r
o
a
ch
.
2
.
2
.
CO
VID
-
1
9
a
v
a
ila
ble da
t
a
s
et
s
T
h
is
s
ec
tio
n
li
s
ts
th
e
m
ai
n
C
OVI
D
-
1
9
d
atasets
to
h
e
l
p
o
t
h
e
r
r
e
s
e
a
r
c
h
e
r
s
a
n
d
p
r
a
c
t
i
t
i
o
n
e
r
s
.
M
a
n
y
d
a
t
a
s
e
t
s
p
r
e
s
e
n
t
t
e
x
t
u
a
l
i
n
f
o
r
m
a
t
i
o
n
a
b
o
u
t
t
h
e
C
O
V
I
D
-
1
9
o
b
t
a
i
n
e
d
f
r
o
m
t
h
e
T
w
i
t
t
e
r
p
lat
f
o
r
m
i
n
clu
d
i
n
g
[
3
5
]
,
w
it
h
o
v
er
1
1
0
M
t
w
ee
ts
[
3
6
]
,
w
ith
o
v
er
4
0
M
tw
ee
t
s
[
3
7
]
,
w
it
h
o
v
er
1
5
0
M
tw
ee
t
s
[
3
8
]
,
an
d
w
i
th
o
v
er
7
5
M
t
w
ee
ts
[
3
9
]
.
M
o
r
eo
v
er
,
p
r
o
v
id
e
d
atas
et
an
d
k
er
n
el
s
to
an
al
y
ze
C
O
V
I
D
-
1
9
r
elate
d
t
w
ee
ts
[
4
0
]
-
[
4
2
]
.
Fo
r
r
ea
l
ti
m
e
r
e
s
e
a
r
c
h
,
t
h
i
s
h
u
m
a
n
i
t
a
r
i
a
n
d
a
t
a
e
x
c
h
a
n
g
e
[
4
3
]
b
r
o
a
d
c
a
s
t
s
a
l
i
v
e
m
a
p
f
o
r
t
h
e
C
OVI
D
-
19.
I
n
ter
ac
tiv
e
v
is
u
aliza
tio
n
s
p
r
es
en
ted
b
y
Ne
x
ts
tr
ai
n
[
4
4
]
.
Mo
r
eo
v
er
,
Kag
g
le
[
4
5
]
p
r
o
v
id
ed
ch
est
x
-
r
a
y
i
m
a
g
e
s
u
s
ed
f
o
r
P
n
eu
m
o
n
ia
d
etec
tio
n
w
it
h
5
,
8
6
3
im
a
g
es.
Si
m
ilar
l
y
,
C
o
h
en
et
al
.
[
4
6
]
p
r
esen
ted
ch
est
x
-
r
a
y
an
d
C
T
i
m
a
g
es
to
d
etec
t
C
OVI
D
-
19
,
ME
R
S,
S
AR
S,
a
n
d
A
R
DS.
Y
an
g
et
a
l.
[
4
7
]
b
u
ilt
a
C
T
i
m
a
g
es
d
atase
t
to
d
etec
t
C
OVI
D
-
1
9
.
Me
d
Seq
[
4
8
]
p
r
o
v
id
ed
a
C
OVI
D
-
1
9
C
T
s
eg
m
en
tatio
n
d
ata
s
et.
R
ad
io
p
ae
d
ia
[
4
9
]
aim
s
to
cr
ea
te
th
e
b
est
r
ad
io
lo
g
y
r
ef
er
e
n
ce
f
o
r
th
e
w
o
r
ld
f
o
r
C
OVI
D
-
1
9
p
o
s
itiv
e
ca
s
e
s
.
Se
v
er
al
r
eso
u
r
ce
s
ar
e
r
ich
w
it
h
in
f
o
r
m
atio
n
ab
o
u
t
t
h
e
C
OVI
D
-
1
9
an
d
it
is
u
p
d
ated
f
r
eq
u
en
tl
y
s
u
c
h
as
[
5
0
]
an
d
[
5
1
]
.
Fin
ally
,
th
is
w
eb
s
i
te
[
5
2
]
p
r
o
v
id
es a
C
OVI
D
-
1
9
ep
id
e
m
io
lo
g
ical
d
ataset.
3.
RE
S
E
ARCH
M
E
T
H
O
D
3
.
1
.
Da
t
a
s
et
prepa
ra
t
io
n
T
o
co
llect
x
-
r
a
y
i
m
ag
e
s
f
o
r
p
a
tien
t
s
w
it
h
p
o
s
itiv
e
C
OVI
D
-
1
9
,
w
e
h
a
v
e
co
llected
x
-
r
a
y
s
i
m
ag
e
s
f
r
o
m
th
e
d
a
tasets
m
en
t
io
n
ed
in
s
ec
t
io
n
2
.
2
.
W
e
also
c
o
llected
x
-
r
a
y
i
m
a
g
es
f
o
r
p
atien
ts
w
it
h
C
OVI
D
-
1
9
d
iag
n
o
s
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
6
,
Dec
em
b
er
202
1
:
4
9
9
9
-
5
0
0
8
5002
clin
icall
y
,
u
s
i
n
g
s
y
m
p
to
m
s
s
u
ch
as
co
u
g
h
,
s
p
u
t
u
m
,
f
ev
er
,
d
y
s
p
n
ea
,
o
r
p
leu
r
it
ic
c
h
est
p
a
in
,
f
r
o
m
[
5
3
]
-
[
5
7
]
.
R
eg
ar
d
in
g
t
h
e
n
o
n
C
OVI
D
-
1
9
im
a
g
es,
w
e
o
b
tain
ed
x
-
r
a
y
s
i
m
ag
e
s
f
r
o
m
Ka
g
g
le
co
m
p
et
itio
n
s
t
h
at
co
n
tai
n
x
-
r
a
y
i
m
a
g
es
f
o
r
n
o
r
m
al
a
n
d
p
n
eu
m
o
n
ia
ch
e
s
t
i
m
a
g
es.
T
h
e
ag
es
o
f
t
h
e
p
atie
n
t
s
i
n
o
u
r
d
at
aset
ar
e
b
et
w
ee
n
2
5
an
d
8
5
.
So
m
e
i
m
ag
e
s
r
ep
r
esen
t th
e
x
-
r
a
y
f
o
r
th
e
s
a
m
e
p
atie
n
t
t
ak
en
o
n
d
i
f
f
er
en
t d
ates.
Fig
u
r
e
1
d
ep
icts
ex
a
m
p
les
o
f
t
h
e
x
-
r
a
y
i
m
ag
e
s
f
o
r
p
atien
ts
with
C
OVI
D
-
1
9
,
th
e
i
m
a
g
es
i
n
th
e
ab
o
v
e
r
o
w
,
an
d
n
o
r
m
al
p
atien
t
s
,
th
e
i
m
a
g
es
in
t
h
e
b
elo
w
r
o
w
,
in
o
u
r
d
ataset.
Si
m
ilar
l
y
,
Fig
u
r
e
2
s
h
o
w
s
ex
a
m
p
les
o
f
th
e
i
m
ag
e
s
in
o
u
r
d
atase
t
u
s
ed
f
o
r
th
e
s
ec
o
n
d
tas
k
,
th
e
m
u
l
ti
-
clas
s
class
if
icatio
n
tas
k
.
T
h
e
f
i
g
u
r
e
s
h
o
w
s
x
-
r
a
y
i
m
a
g
es
f
o
r
n
o
r
m
al
p
atien
t
s
(
t
h
e
lo
w
er
r
o
w
)
,
p
atie
n
ts
w
it
h
C
OVI
D
-
1
9
(
th
e
m
id
d
le
r
o
w
)
,
an
d
p
atie
n
ts
w
it
h
o
th
er
t
y
p
es
o
f
p
n
eu
m
o
n
ia
(
th
e
u
p
p
er
r
o
w
)
.
T
a
b
le
1
s
u
m
m
ar
izes
o
u
r
d
ataset
in
clu
d
i
n
g
t
h
e
n
u
m
b
er
o
f
x
-
r
a
y
i
m
a
g
es
f
o
r
tr
ain
in
g
a
n
d
test
i
n
g
.
Fig
u
r
e
1
.
Sa
m
p
le
x
-
r
a
y
i
m
a
g
e
s
f
r
o
m
o
u
r
d
ataset
u
s
ed
f
o
r
th
e
f
ir
s
t ta
s
k
Fig
u
r
e
2
.
Sa
m
p
le
x
-
r
a
y
i
m
a
g
e
s
f
r
o
m
o
u
r
d
ataset
u
s
ed
f
o
r
th
e
s
ec
o
n
d
task
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:
2
0
8
8
-
8708
Tr
a
n
s
fer d
ee
p
lea
r
n
in
g
a
p
p
r
o
a
ch
fo
r
d
etec
tin
g
c
o
r
o
n
a
viru
s
d
is
ea
s
e
(
C
OV
I
D
-
19)
…
(
Mo
h
a
mme
d
A
l
-
S
ma
d
i
)
5003
T
ab
le
1
.
Su
m
m
ar
y
o
f
t
h
e
d
atas
et
u
s
ed
f
o
r
tr
ain
i
n
g
an
d
ev
a
lu
a
tin
g
o
u
r
tr
an
s
f
er
d
ee
p
lear
n
in
g
m
o
d
el
F
i
l
e
s
C
O
V
I
D
-
19
N
on
C
O
V
I
D
-
19
P
n
e
u
mo
n
i
a
T
o
t
a
l
T
r
a
i
n
8
6
5
1
,
9
5
7
3
,
4
1
8
6
,
2
4
0
T
e
st
2
1
6
4
8
9
8
5
5
1
,
5
6
0
T
o
t
a
l
1
,
0
8
1
2
,
4
4
6
4
,
2
7
3
7
,
8
0
0
3
.
2
.
Da
t
a
a
ug
m
e
nta
t
io
n
T
h
e
d
ata
au
g
m
e
n
tatio
n
p
r
o
ce
s
s
i
n
cr
ea
s
es
t
h
e
n
u
m
b
er
a
n
d
th
e
d
iv
er
s
it
y
o
f
t
h
e
d
ataset
an
d
h
en
c
e
r
ed
u
ce
s
t
h
e
o
v
er
f
itti
n
g
a
n
d
t
h
e
m
e
m
o
r
izatio
n
p
r
o
b
lem
s
o
f
m
ac
h
in
e
lear
n
i
n
g
m
o
d
els.
M
o
r
eo
v
er
,
s
in
ce
d
ee
p
lear
n
in
g
m
o
d
els
r
eq
u
ir
e
lar
g
e
d
ataset,
th
i
s
tech
n
iq
u
e
is
cr
u
cial
f
o
r
b
u
ild
in
g
s
tab
le
a
n
d
g
en
er
aliza
b
le
d
ee
p
lear
n
in
g
m
o
d
el
s
.
T
o
th
at
en
d
,
w
e
h
av
e
ap
p
lied
v
ar
io
u
s
d
ata
au
g
m
e
n
tatio
n
tech
n
iq
u
e
s
,
as
p
r
esen
ted
in
T
ab
le
2
,
to
en
lar
g
e
o
u
r
d
ataset.
T
h
e
to
tal
n
u
m
b
er
o
f
i
m
ag
e
s
af
ter
t
h
e
d
ata
au
g
m
en
tatio
n
i
s
4
9
9
,
2
0
0
lab
eled
im
a
g
e
s
.
T
ab
le
2
.
A
d
v
an
ce
d
au
g
m
en
tati
o
n
t
y
p
es t
h
at
h
a
v
e
u
s
ed
an
d
th
eir
p
ar
am
eter
s
A
u
g
me
n
t
a
t
i
o
n
T
y
p
e
D
e
scri
p
t
i
o
n
a
n
d
P
a
r
a
me
t
e
r
s
F
l
i
p
H
o
r
i
z
o
n
t
a
l
l
y
a
n
d
v
e
r
t
i
c
a
l
l
y
f
l
i
p
p
i
n
g
t
h
e
i
mag
e
.
H
o
r
i
z
o
n
t
a
l
l
y
f
l
i
p
5
0
%
o
f
a
l
l
i
m
a
g
e
s,
v
e
r
t
i
c
a
l
l
y
f
l
i
p
2
0
%
o
f
a
l
l
i
mag
e
s
S
c
a
l
e
Re
-
sca
l
e
t
h
e
i
m
a
g
e
s o
u
t
w
a
r
d
o
r
i
n
w
a
r
d
.
R
o
t
a
t
i
o
n
R
o
t
a
t
e
e
a
c
h
i
m
a
g
e
b
y
(
-
1
0
,
1
0
)
d
e
g
r
e
e
s
S
h
e
a
r
i
n
g
o
r
S
h
e
a
r
M
a
p
p
i
n
g
D
i
sp
l
a
c
e
d
e
a
c
h
p
i
x
e
l
i
n
t
h
e
v
e
r
t
i
c
a
l
d
i
r
e
c
t
i
o
n
b
y
-
1
6
p
r
o
p
o
r
t
i
o
n
a
l
t
o
+
1
6
d
e
g
r
e
e
s.
El
a
st
i
c
a
n
d
P
e
r
sp
e
c
t
i
v
e
T
r
a
n
sf
o
r
mat
i
o
n
El
a
st
i
c
:
u
se
t
h
e
r
a
n
d
o
m
st
r
e
n
g
t
h
s
t
o
mo
v
e
p
i
x
e
l
s
l
o
c
a
l
l
y
a
r
o
u
n
d
.
P
e
r
sp
e
c
t
i
v
e
:
c
r
e
a
t
e
s
a
d
i
f
f
e
r
e
n
t
i
m
a
g
e
c
a
p
t
u
r
e
d
f
r
o
m d
i
f
f
e
r
e
n
t
c
a
me
r
a
v
i
e
w
p
o
i
n
t
s
a
l
p
h
a
=
(
0
.
5
,
3
.
5
)
,
si
g
ma
=
0
.
2
5
O
r
d
e
r
i
n
g
U
t
i
l
i
z
e
s
t
h
e
n
e
a
r
e
st
n
e
i
g
h
b
o
r
o
r
b
i
l
i
n
e
a
r
i
n
t
e
r
p
o
l
a
t
i
o
n
(
f
a
s
t
)
.
[
0
,
1
]
,
u
se
n
e
a
r
e
st
n
e
i
g
h
b
o
r
o
r
b
i
l
i
n
e
a
r
i
n
t
e
r
p
o
l
a
t
i
o
n
(
f
a
s
t
)
G
a
u
ssi
a
n
B
l
u
r
P
r
o
d
u
c
e
s
a
b
l
u
r
r
y
i
mag
e
,
t
h
e
e
d
g
e
s
b
e
c
o
me
sh
a
r
p
e
r
u
s
i
n
g
h
i
g
h
c
o
n
t
r
a
s
t
f
i
l
t
e
r
.
B
l
u
r
i
mag
e
s w
i
t
h
a
s
i
g
ma
b
e
t
w
e
e
n
(
0
,
3
.
0
)
A
v
e
r
a
g
e
B
l
u
r
C
o
mp
u
t
i
n
g
a
s
i
m
p
l
e
me
d
i
a
n
o
v
e
r
n
e
i
g
h
b
o
r
h
o
o
d
s.
B
l
u
r
i
mag
e
u
si
n
g
l
o
c
a
l
me
a
n
s
w
i
t
h
k
e
r
n
e
l
si
z
e
s b
e
t
w
e
e
n
(
3
,
5
)
M
e
d
i
a
n
B
l
u
r
G
e
t
s
r
i
d
o
f
t
h
e
smal
l
n
o
i
se
i
n
t
h
e
i
ma
g
e
s
w
h
i
c
h
c
a
u
se
d
b
y
c
o
mp
u
t
i
n
g
t
h
e
me
d
i
a
n
v
a
l
u
e
s
o
v
e
r
n
e
i
g
h
b
o
r
h
o
o
d
s.
b
l
u
r
i
mag
e
u
s
i
n
g
l
o
c
a
l
me
d
i
a
n
s w
i
t
h
k
e
r
n
e
l
si
z
e
s b
e
t
w
e
e
n
(
3
,
5
)
S
h
a
r
p
i
n
g
P
r
o
d
u
c
e
s
i
mag
e
s
i
n
f
o
c
u
s
t
h
a
t
e
n
c
a
p
s
u
l
a
t
e
s
t
h
e
i
mp
o
r
t
a
n
t
d
e
t
a
i
l
s
a
b
o
u
t
o
b
j
e
c
t
s
o
f
i
n
t
e
r
e
st
.
a
l
p
h
a
=
(
0
,
1
.
0
)
,
l
i
g
h
t
n
e
ss=(
0
.
9
,
1
.
1
)
Emb
o
ss
O
v
e
r
l
a
y
s
t
h
e
i
mag
e
w
i
t
h
t
h
e
o
r
i
g
i
n
a
l
i
mag
e
s
b
y
t
u
n
i
n
g
a
l
p
h
a
b
e
t
w
e
e
n
0
.
0
a
n
d
1
.
0
.
a
l
p
h
a
=
(
0
,
1
.
0
)
,
s
t
r
e
n
g
t
h
=
(
0
,
2
.
0
)
Ad
d
i
t
i
v
e
G
a
u
ssi
a
n
N
o
i
se
I
t
mi
t
i
g
a
t
e
s
o
v
e
r
f
i
t
t
i
n
g
a
n
d
a
d
i
s
h
o
n
e
s
t
p
r
o
c
e
d
u
r
e
f
o
r
r
e
a
l
v
a
l
u
e
d
i
n
p
u
t
s
b
y
a
d
d
i
n
g
n
o
i
se
samp
l
e
d
t
o
t
h
e
i
m
a
g
e
s.
l
o
c
=
0
,
sca
l
e
=
(
0
.
0
,
0
.
0
1
*
2
5
5
)
,
p
e
r
c
h
a
n
n
e
l
=
0
.
5
3
.
3
.
T
ra
ns
f
er
lea
rning
a
pp
ro
a
ch
T
h
is
s
ec
tio
n
d
escr
ib
es
o
u
r
tr
an
s
f
er
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
o
f
d
etec
tin
g
C
OVI
D
-
1
9
i
m
ag
e
s
u
s
i
n
g
o
u
r
tr
an
s
f
er
lear
n
in
g
m
o
d
el
f
o
r
th
e
s
ak
e
o
f
h
elp
in
g
m
ed
ical
s
taf
f
ac
cu
r
atel
y
a
n
d
co
n
f
id
e
n
tl
y
d
iag
n
o
s
is
C
O
VI
D
-
1
9
in
m
ed
ical
i
m
a
g
es
a
n
d
h
en
ce
b
etter
tr
ea
tin
g
t
h
e
p
atien
ts
a
s
ea
r
l
y
as
p
o
s
s
ib
le.
T
r
an
s
f
e
r
lea
r
n
in
g
tec
h
n
iq
u
e
h
a
s
i
m
p
r
o
v
ed
th
e
p
er
f
o
r
m
a
n
ce
o
f
i
m
a
g
e
clas
s
i
f
icatio
n
an
d
co
m
p
u
ter
v
is
io
n
r
esear
ch
a
s
n
o
ted
i
n
L
itj
en
s
et
a
l.
[
5
8
]
w
o
r
k
.
T
h
e
m
ain
id
e
a
o
f
tr
an
s
f
er
lear
n
in
g
i
s
to
r
e
-
u
s
e
a
p
r
ev
i
o
u
s
l
y
tr
ain
ed
m
o
d
el
o
n
s
i
m
i
la
r
d
o
m
ai
n
i
n
s
tead
o
f
re
-
tr
ain
i
n
g
a
n
e
w
m
o
d
el
f
r
o
m
s
cr
atch
.
He
n
ce
b
o
o
s
tin
g
th
e
p
er
f
o
r
m
an
ce
(
i
n
ter
m
s
o
f
ti
m
e
a
n
d
a
c
c
u
r
a
c
y
)
o
f
t
h
e
t
r
a
n
s
f
e
r
l
e
a
r
n
i
n
g
m
o
d
e
l
.
M
o
r
e
o
v
e
r
,
t
r
a
n
s
f
e
r
l
e
a
r
n
i
n
g
a
l
l
o
w
s
u
s
t
o
u
s
e
a
p
r
e
v
i
o
u
s
l
y
t
r
a
i
n
e
d
m
o
d
e
l
t
h
a
t
m
i
g
h
t
b
e
t
r
a
i
n
e
d
o
n
a
h
i
g
h
s
p
e
c
i
f
i
c
a
t
i
o
n
s
c
o
m
p
u
t
i
n
g
d
e
v
i
c
e
t
h
a
t
w
e
m
i
g
h
t
n
o
t
h
a
v
e
o
r
a
b
o
v
e
o
u
r
b
u
d
g
e
t
.
Fo
r
e
x
a
m
p
le,
th
e
I
m
ag
eNe
t
d
ataset,
in
tr
o
d
u
ce
d
b
y
R
u
s
s
a
k
o
v
s
k
y
et
a
l
.
[
5
9
]
,
co
n
tain
s
t
h
o
u
s
an
d
s
o
f
i
m
a
g
es.
Ma
n
y
n
eu
r
al
n
et
w
o
r
k
m
o
d
el
s
h
a
v
e
b
ee
n
tr
ai
n
ed
o
n
th
e
I
m
ag
eNe
t d
ataset
i
n
clu
d
i
n
g
VGG,
I
n
ce
p
tio
n
,
Xc
ep
tio
n
,
a
n
d
R
esNet.
T
o
a
d
d
r
ess
o
u
r
p
r
o
b
lem
,
w
e
h
av
e
d
ev
elo
p
ed
a
C
NN
ap
p
r
o
ac
h
b
ased
o
n
tr
an
s
f
er
lear
n
i
n
g
t
o
s
o
lv
e
t
h
e
t
w
o
i
m
ag
e
cla
s
s
i
f
icatio
n
tas
k
s
o
f
o
u
r
C
OVI
D
-
1
9
d
etec
tio
n
p
r
o
b
lem
.
I
n
o
u
r
ap
p
r
o
ac
h
,
w
e
h
av
e
u
tili
ze
d
t
w
o
s
tate
-
of
-
th
e
-
ar
t
C
NN
m
o
d
el
s
:
th
e
I
n
ce
p
tio
n
m
o
d
el
i
n
tr
o
d
u
ce
d
b
y
Sze
g
ed
y
et
a
l.
[
6
0
]
an
d
th
e
Xce
p
tio
n
m
o
d
el
p
r
o
p
o
s
ed
b
y
C
h
o
llet
[
6
1
]
.
Fig
u
r
e
3
d
ep
icts
t
h
e
ar
ch
itect
u
r
e
o
f
o
u
r
ap
p
r
o
ac
h
w
h
ich
s
t
ar
ts
b
y
lev
er
a
g
i
n
g
v
ar
io
u
s
d
ata
a
u
g
m
e
n
tatio
n
te
ch
n
iq
u
es
(
r
ec
all
s
ec
tio
n
3
.
2
.
)
th
e
n
th
e
r
es
u
lted
i
m
a
g
es
f
e
d
to
th
e
p
r
e
-
tr
ai
n
ed
m
o
d
el.
Af
ter
t
h
at,
a
g
lo
b
al
av
er
ag
e
p
o
o
lin
g
2
D
i
s
p
er
f
o
r
m
e
d
to
ex
tr
ac
t
th
e
d
is
cr
i
m
in
at
iv
e
f
ea
t
u
r
es
f
r
o
m
t
h
e
i
m
a
g
es
to
u
s
e
t
h
e
m
in
th
e
n
e
x
t
la
y
er
s
.
Ne
x
t,
th
e
b
atc
h
n
o
r
m
aliza
tio
n
la
y
er
is
p
er
f
o
r
m
ed
to
s
tan
d
ar
d
ize
th
e
in
p
u
t
s
f
o
r
ea
ch
m
in
i
b
atc
h
a
n
d
to
s
tab
ilize
th
e
lear
n
in
g
p
r
o
ce
s
s
.
T
h
e
f
latte
n
la
y
er
is
ap
p
l
ied
to
co
n
v
er
t
th
e
in
p
u
t
d
ata
to
a
1
D
ar
r
a
y
an
d
f
ed
it
to
th
e
d
en
s
e
la
y
er
w
i
t
h
1
2
8
n
eu
r
o
n
s
,
t
h
e
n
to
th
e
d
r
o
p
o
u
t
la
y
er
w
ith
a
d
r
o
p
o
u
t
r
ate
o
f
0
.
5
.
Fin
all
y
,
th
e
p
r
ed
ictio
n
la
y
er
co
n
s
i
s
ts
o
f
d
e
n
s
e
o
f
1
f
o
r
th
e
C
OVI
D
-
1
9
b
in
ar
y
i
m
a
g
e
class
i
f
icatio
n
tas
k
a
n
d
d
en
s
e
o
f
3
f
o
r
t
h
e
s
ec
o
n
d
m
u
lti
-
ta
s
k
cla
s
s
i
f
icat
io
n
ta
s
k
w
it
h
a
s
o
f
t
m
ax
ac
ti
v
atio
n
f
u
n
ctio
n
f
o
r
in
p
u
t c
las
s
i
f
icatio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
6
,
Dec
em
b
er
202
1
:
4
9
9
9
-
5
0
0
8
5004
Fig
u
r
e
3
.
T
h
e
ar
ch
itectu
r
e
o
f
o
u
r
tr
an
s
f
er
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
4.
E
XP
E
R
I
M
E
NT
A
L
E
VA
L
U
AT
I
O
N
4
.
1
.
P
er
f
o
r
m
a
nce
m
et
rics
Sev
er
al
s
ta
n
d
ar
d
m
ea
s
u
r
es h
a
v
e
b
ee
n
u
s
ed
to
ev
alu
a
te
th
e
p
er
f
o
r
m
an
ce
o
f
o
u
r
m
o
d
els.
=
+
+
+
+
(
1
)
1
=
2
∗
∗
+
(
2
)
W
h
er
e
P
r
ec
is
io
n
:
r
ep
r
esen
ts
th
e
n
u
m
b
er
o
f
ca
s
es
t
h
at
t
h
e
m
o
d
el
p
r
ed
icted
co
r
r
ec
tly
o
u
t
o
f
t
h
e
o
v
er
all
p
r
ed
icted
ca
s
es.
T
h
e
p
r
ec
is
io
n
m
ea
s
u
r
e
ca
n
b
e
co
m
p
u
ted
u
s
i
n
g
(
3
)
:
=
+
(
3
)
R
ec
all: r
ep
r
esen
t
s
th
e
n
u
m
b
er
o
f
ca
s
es t
h
at
t
h
e
m
o
d
el
p
r
ed
icted
co
r
r
ec
tly
o
u
t o
f
t
h
e
o
v
er
all
ca
s
es in
th
e
d
ataset.
T
h
e
r
ec
all
m
ea
s
u
r
e
ca
n
b
e
co
m
p
u
ted
u
s
in
g
(
4
)
:
=
+
(
4
)
T
r
u
e
P
o
s
itiv
es
(
T
P
)
:
ca
n
b
e
d
ef
i
n
ed
as
t
h
e
ca
s
es
in
w
h
ich
t
h
e
p
r
ed
icted
ca
s
e
d
iag
n
o
s
ed
a
s
C
OVI
D
-
19
an
d
th
e
ac
t
u
al
d
iag
n
o
s
e
is
C
O
VI
D
-
19.
T
r
u
e
Neg
ativ
e
s
(
T
N)
:
ca
n
b
e
d
ef
i
n
ed
as
t
h
e
ca
s
es
in
wh
ich
t
h
e
p
r
ed
icted
ca
s
e
d
iag
n
o
s
ed
as
n
o
n
-
C
OVI
D
-
19
an
d
th
e
ac
tu
a
l c
ase
d
iag
n
o
s
ed
as
n
o
n
C
OVI
D.
Fals
e
P
o
s
iti
v
es
(
FP
)
:
ca
n
b
e
d
ef
i
n
ed
as
th
e
ca
s
e
s
i
n
w
h
ic
h
t
h
e
p
r
ed
icted
ca
s
e
d
ia
g
n
o
s
ed
a
s
C
OVI
D
-
19
w
h
er
ea
s
t
h
e
ac
tu
al
ca
s
e
d
iag
n
o
s
ed
as n
o
n
C
OVI
D.
Fals
e
Neg
ati
v
e
s
(
FN)
:
ca
n
b
e
d
ef
i
n
ed
as
th
e
ca
s
e
s
i
n
wh
ich
t
h
e
p
r
ed
icted
ca
s
e
d
ia
g
n
o
s
ed
as
n
o
n
-
C
OVI
D
-
19
w
h
er
e
as th
e
ac
t
u
a
l c
ase
d
iag
n
o
s
ed
as
C
OVI
D
-
1
9
.
4
.
2
.
E
x
peri
m
e
nta
l r
esu
lt
s
I
n
o
r
d
er
to
ev
alu
ate
th
e
d
e
v
el
o
p
ed
tr
an
s
f
er
lear
n
in
g
ap
p
r
o
ac
h
,
w
e
co
llected
C
OVI
D
-
1
9
d
ataset
f
r
o
m
d
if
f
er
e
n
t
r
eso
u
r
ce
s
t
h
at
ai
m
s
t
o
s
o
lv
e
b
o
th
p
r
o
b
le
m
s
.
Se
v
er
al
s
i
m
p
le
an
d
ad
v
an
ce
d
a
u
g
m
en
tatio
n
tech
n
iq
u
e
s
ar
e
u
s
ed
to
in
cr
ea
s
e
th
e
n
u
m
b
er
o
f
t
h
e
tr
ain
i
n
g
d
ataset
(
r
ec
all
s
ec
tio
n
3
.
2
.
)
.
T
a
b
le
3
s
u
m
m
ar
izes
th
e
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:
2
0
8
8
-
8708
Tr
a
n
s
fer d
ee
p
lea
r
n
in
g
a
p
p
r
o
a
ch
fo
r
d
etec
tin
g
c
o
r
o
n
a
viru
s
d
is
ea
s
e
(
C
OV
I
D
-
19)
…
(
Mo
h
a
mme
d
A
l
-
S
ma
d
i
)
5005
ev
alu
a
tio
n
r
es
u
lts
o
f
o
u
r
tr
an
s
f
er
d
ee
p
lear
n
in
g
m
o
d
els
u
s
i
n
g
3
d
if
f
er
en
t
p
r
etr
ain
ed
m
o
d
el
s
,
th
e
I
n
ce
p
tio
n
-
V3
,
th
e
Xce
p
tio
n
,
a
n
d
th
e
Mo
b
il
eNe
t
m
o
d
els.
R
e
g
ar
d
in
g
t
h
e
f
ir
s
t
ta
s
k
,
t
h
e
b
i
n
ar
y
cla
s
s
i
f
ic
atio
n
tas
k
,
T
ab
le
3
s
h
o
w
s
t
h
at
o
u
r
m
o
d
el
w
it
h
3
d
if
f
er
en
t p
r
e
-
tr
ai
n
ed
m
o
d
els ac
h
iev
ed
t
h
e
p
er
f
ec
t sco
r
e
in
th
e
ac
cu
r
ac
y
as
w
e
ll a
s
in
th
e
F1
-
Sco
r
e,
i.e
.
,
1
0
0
%.
O
n
th
e
o
th
er
h
a
n
d
,
r
eg
ar
d
in
g
th
e
m
u
lti
cla
s
s
i
f
icatio
n
task
,
T
ab
le
3
s
h
o
w
s
th
at
o
u
r
m
o
d
el
ac
h
ie
v
ed
t
h
e
b
est
r
es
u
lt
s
u
s
i
n
g
th
e
Xce
p
tio
n
p
r
e
-
tr
ai
n
ed
m
o
d
el
w
it
h
9
7
.
3
7
%
ac
cu
r
ac
y
a
n
d
9
7
.
6
6
%
F1
-
Sco
r
e.
T
h
ese
h
ig
h
ac
cu
r
ate
r
esu
lt
s
o
f
o
u
r
m
o
d
els
m
a
k
e
u
s
co
n
f
id
e
n
t
th
at
o
u
r
d
ev
elo
p
ed
m
o
d
el
s
ca
n
b
e
u
s
ed
b
y
m
ed
ical
s
ta
f
f
to
h
elp
t
h
e
m
i
n
d
iag
n
o
s
i
n
g
C
OVI
D
-
1
9
ca
s
es
ac
cu
r
atel
y
a
n
d
ef
f
icie
n
tl
y
.
T
ab
le
3
.
E
v
alu
atio
n
r
es
u
lts
o
f
o
u
r
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
u
s
in
g
3
d
if
f
er
en
t p
r
e
-
tr
ain
ed
m
o
d
els
u
s
i
n
g
x
-
r
a
y
i
m
a
g
es
d
ataset
f
o
r
b
o
th
task
s
,
th
e
b
i
n
a
r
y
a
n
d
th
e
m
u
lti
-
clas
s
c
las
s
i
f
ic
atio
n
s
B
i
n
a
r
y
C
l
a
ssi
f
i
c
a
t
i
o
n
M
u
l
t
i
-
C
l
a
ss
C
l
a
ssi
f
i
c
a
t
i
o
n
M
o
d
e
l
A
c
c
u
r
a
c
y
F1
-
S
c
o
r
e
A
c
c
u
r
a
c
y
F1
-
S
c
o
r
e
I
n
c
e
p
t
i
o
n
-
V3
1
0
0
%
1
0
0
%
9
7
.
1
2
%
9
7
.
4
7
%
X
c
e
p
t
i
o
n
1
0
0
%
1
0
0
%
9
7
.
3
7
%
9
7
.
6
6
%
M
o
b
i
l
e
N
e
t
1
0
0
%
1
0
0
%
9
6
.
0
6
%
9
6
.
4
7
%
5.
DIS
CU
SS
I
O
N
Sev
er
al
tec
h
n
iq
u
e
s
w
er
e
ap
p
li
ed
to
av
o
id
t
h
e
p
r
o
b
le
m
o
f
o
v
er
f
itti
n
g
i
n
t
h
e
m
o
d
el
tr
ai
n
i
n
g
as
f
o
llo
w
s
:
i
)
d
ata
au
g
m
e
n
tatio
n
w
a
s
ap
p
lied
to
th
e
d
ataset
an
d
th
e
r
esu
lted
d
ata
w
er
e
u
s
ed
to
tr
ain
th
e
m
o
d
el
;
ii
)
th
e
ca
ll
-
b
ac
k
f
u
n
ctio
n
o
f
Ker
as
“
E
ar
l
y
Sto
p
p
in
g
”
[
6
2
]
is
u
s
ed
to
s
to
p
th
e
m
o
d
el
tr
ai
n
i
n
g
w
h
en
th
e
c
o
m
p
u
ted
v
alid
atio
n
lo
s
s
v
al
u
e
i
s
n
o
t
i
m
p
r
o
v
in
g
d
u
r
in
g
tr
ai
n
i
n
g
ep
o
ch
s
;
an
d
iii
)
r
eg
u
latio
n
tec
h
n
iq
u
es
s
u
c
h
as
B
atc
h
No
r
m
a
lizatio
n
[
6
3
]
an
d
Dr
o
p
o
u
t
[
6
4
]
w
er
e
u
s
ed
to
r
ed
u
ce
th
e
m
o
d
el
o
v
er
f
itti
n
g
a
n
d
en
h
a
n
ce
t
h
e
m
o
d
el
lear
n
in
g
ca
p
ab
ilit
ies.
As
d
ep
icted
in
Fig
u
r
e
4
,
th
e
m
o
d
el
w
a
s
tr
ain
ed
w
it
h
o
u
t
o
v
er
f
itti
n
g
.
B
ec
au
s
e
o
f
th
e
tec
h
n
iq
u
es
u
s
ed
to
r
ed
u
ce
o
v
er
f
itti
n
g
,
b
o
th
lo
s
s
v
a
lu
e
s
o
f
tr
ain
lo
s
s
an
d
t
h
e
v
alid
atio
n
lo
s
s
d
ec
lin
ed
to
g
eth
er
d
u
r
in
g
m
o
d
el
tr
ain
i
n
g
w
it
h
o
u
t
h
a
v
i
n
g
lar
g
e
g
ap
s
b
et
w
ee
n
t
h
eir
co
m
p
u
ted
v
alu
e
s
o
v
er
tr
ai
n
in
g
ep
o
ch
s
.
I
n
o
r
d
er
to
v
al
id
ate
th
e
p
r
o
p
o
s
ed
m
o
d
el
ac
h
ie
v
ed
r
esu
lt
s
,
an
ab
latio
n
a
n
al
y
s
is
was c
o
n
d
u
c
ted
o
n
t
h
e
r
es
u
lt
s
o
f
th
e
b
est
p
er
f
o
r
m
i
n
g
m
o
d
el
(
Xce
p
tio
n
+d
at
a
a
u
g
m
en
tatio
n
+T
r
an
s
f
er
L
ea
r
n
i
n
g
)
.
A
s
p
r
ese
n
ted
in
T
ab
le
4
,
tr
ain
i
n
g
t
h
e
m
o
d
el
w
it
h
o
u
t
au
g
m
e
n
ted
lear
n
i
n
g
d
ec
r
ea
s
ed
th
e
r
esu
lts
f
o
r
b
in
ar
y
cla
s
s
i
f
icatio
n
in
T
ask
1
w
it
h
4
.
9
2
%
f
o
r
th
e
F1
-
s
co
r
e,
an
d
f
o
r
th
e
m
u
lti
-
class
clas
s
i
f
icatio
n
in
T
ask
2
w
it
h
4
.
7
8
%.
A
b
l
ati
n
g
th
e
tr
an
s
f
er
lear
n
i
n
g
an
d
tr
ain
i
n
g
th
e
Xce
p
tio
n
m
o
d
el
alo
n
e
o
n
th
e
a
u
g
m
en
ted
d
ata
s
et
h
as
a
h
i
g
h
er
in
f
l
u
e
n
ce
o
n
th
e
r
e
s
u
l
ts
w
i
th
a
d
ec
r
ea
s
e
o
f
6
.
1
3
% f
o
r
b
in
ar
y
class
i
f
icatio
n
i
n
T
ask
1
an
d
a
d
ec
r
ea
s
e
o
f
9
.
2
1
% f
o
r
t
h
e
m
u
l
ti
-
clas
s
cla
s
s
i
f
icatio
n
in
T
ask
2
.
I
t
al
s
o
ca
n
b
e
n
o
ti
ce
d
th
at
t
h
e
ab
lat
io
n
o
f
b
o
th
d
ata
au
g
m
e
n
tatio
n
a
n
d
tr
an
s
f
er
lear
n
in
g
h
a
s
t
h
e
h
ig
h
e
s
t
d
ec
r
ea
s
e
o
n
th
e
ta
s
k
s
r
esu
lt
s
w
it
h
1
1
.
1
2
%
f
o
r
b
in
ar
y
class
i
f
icatio
n
in
T
ask
1
an
d
a
d
ec
r
ea
s
e
o
f
1
6
.
5
4
%
f
o
r
th
e
m
u
lti
-
cla
s
s
c
lass
if
icat
io
n
i
n
T
ask
2
.
Ab
latio
n
r
e
s
u
l
t
s
s
h
o
w
t
h
e
i
n
f
lu
e
n
ce
o
f
t
h
e
d
ata
au
g
m
e
n
tatio
n
tech
n
iq
u
es
u
s
ed
o
n
e
n
h
a
n
ci
n
g
th
e
r
es
u
lts
as
w
ell
as
th
e
s
tr
e
n
g
t
h
o
f
th
e
tr
an
s
f
er
lear
n
in
g
m
o
d
el
w
e
ap
p
lied
t
o
ac
h
iev
e
t
h
e
ta
s
k
s
r
eq
u
ir
e
m
e
n
t
s
.
Fig
u
r
e
4
.
L
o
s
s
v
al
u
es
f
o
r
th
e
t
r
ain
in
g
a
n
d
v
alid
at
io
n
d
u
r
in
g
ea
ch
tr
ain
i
n
g
ep
o
ch
f
o
r
th
e
b
e
s
t a
ch
ie
v
i
n
g
m
o
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
6
,
Dec
em
b
er
202
1
:
4
9
9
9
-
5
0
0
8
5006
T
ab
le
4
.
R
esu
lts
f
o
r
th
e
ab
lati
o
n
an
al
y
s
i
s
f
o
r
th
e
Xce
p
tio
n
+
tr
an
s
f
er
lear
n
i
n
g
m
o
d
el
B
i
n
a
r
y
C
l
a
ssi
f
i
c
a
t
i
o
n
M
u
l
t
i
-
C
l
a
ss
C
l
a
ssi
f
i
c
a
t
i
o
n
A
b
l
a
t
e
d
F
e
a
t
u
r
e
s
F1
-
S
c
o
r
e
D
i
f
f
e
r
e
n
c
e
F1
-
S
c
o
r
e
D
i
f
f
e
r
e
n
c
e
w
i
t
h
o
u
t
d
a
t
a
a
u
g
me
n
t
a
t
i
o
n
9
5
.
0
8
%
4
.
9
2
%
9
2
.
8
8
%
4
.
7
8
%
w
i
t
h
o
u
t
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
9
3
.
8
7
%
6
.
1
3
%
8
8
.
4
5
%
9
.
2
1
%
w
i
t
h
o
u
t
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
+
d
a
t
a
a
u
g
m
e
n
t
a
t
i
o
n
8
8
.
8
8
%
1
1
.
1
2
%
8
1
.
1
2
%
1
6
.
5
4
%
X
c
e
p
t
i
o
n
+
d
a
t
a
a
u
g
me
n
t
a
t
i
o
n
+
T
r
a
n
sf
e
r
L
e
a
r
n
i
n
g
1
0
0
%
-
9
7
.
6
6
%
-
6.
CO
NCLU
SI
O
N
I
n
th
i
s
r
esear
ch
,
w
e
h
a
v
e
d
ev
elo
p
ed
a
tr
an
s
f
er
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
to
d
etec
t
if
a
p
atien
t
h
as
a
C
OVI
D
-
1
9
o
r
n
o
t
u
s
in
g
x
-
r
a
y
s
i
m
a
g
es.
W
e
h
a
v
e
lev
er
a
g
ed
s
tate
-
of
-
th
e
-
ar
t
C
NN
m
o
d
els
(
I
n
ce
p
tio
n
-
V3
,
t
h
e
Xc
ep
tio
n
,
an
d
th
e
Mo
b
ileNet)
as
p
r
e
-
tr
ain
ed
m
o
d
els.
A
ll
o
f
th
ese
m
o
d
els
h
a
v
e
b
ee
n
tr
ain
e
d
o
n
th
e
I
m
ag
e
Net
d
ataset
an
d
t
h
e
y
ac
h
ie
v
ed
p
r
o
m
is
in
g
r
es
u
lt
s
.
Ou
r
tr
a
n
s
f
er
le
ar
n
in
g
ap
p
r
o
ac
h
en
h
an
ce
s
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
o
u
r
m
o
d
el
s
an
d
in
cr
ea
s
e
s
th
eir
ac
cu
r
ac
y
an
d
ef
f
icie
n
c
y
.
I
n
t
h
is
r
esear
ch
,
w
e
f
o
cu
s
ed
o
n
t
w
o
task
s
,
th
e
f
ir
s
t
task
i
s
a
b
in
ar
y
clas
s
i
f
icatio
n
ta
s
k
i
n
w
h
ic
h
th
e
m
o
d
el
n
ee
d
s
to
d
et
ec
t
if
a
g
i
v
e
n
x
-
r
a
y
i
m
a
g
e
s
h
o
w
s
th
at
t
h
e
p
atie
n
t
h
as
C
OVI
D
-
1
9
o
r
n
o
t.
I
n
th
e
s
ec
o
n
d
task
,
th
e
m
o
d
el
h
as
b
ee
n
tr
ain
ed
to
d
is
tin
g
u
i
s
h
b
et
w
ee
n
C
O
VI
D
-
1
9
,
n
o
r
m
al,
o
r
p
n
eu
m
o
n
ia
x
-
r
a
y
s
.
Ou
r
ex
p
er
i
m
en
tal
e
v
al
u
atio
n
s
s
h
o
w
t
h
at
o
u
r
m
o
d
els
ac
h
ie
v
e
d
h
ig
h
ac
cu
r
ac
y
in
b
o
th
task
s
,
1
0
0
%
in
th
e
f
ir
s
t
ta
s
k
a
n
d
9
7
.
6
6
%
o
n
th
e
s
ec
o
n
d
task
.
T
h
ese
h
i
g
h
ac
cu
r
ac
y
p
r
o
o
f
s
t
h
at
o
u
r
m
o
d
el
s
ca
n
b
e
u
s
ed
b
y
m
ed
ical
s
ta
f
f
t
o
d
iag
n
o
s
e
p
atien
ts
w
it
h
C
OV
I
D
-
1
9
u
s
in
g
th
eir
x
-
r
a
y
i
m
a
g
e
s
.
I
n
th
e
f
u
t
u
r
e,
w
e
w
il
l
d
ev
elo
p
a
tr
an
s
f
er
d
ee
p
lear
n
in
g
m
o
d
el
s
to
p
r
ed
ict
th
e
s
tag
e
a
n
d
th
e
s
e
v
er
it
y
o
f
t
h
e
C
OVI
D
-
1
9
f
r
o
m
x
-
r
a
y
i
m
ag
e
s
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
is
r
esear
ch
is
p
ar
tiall
y
f
u
n
d
ed
b
y
J
o
r
d
an
Un
i
v
er
s
it
y
o
f
S
cien
ce
an
d
T
ec
h
n
o
lo
g
y
,
R
ese
ar
ch
Gr
an
t
Nu
m
b
er
s
: 2
0
2
0
0
1
4
5
an
d
2
0
1
9
0
3
0
6
.
RE
F
E
R
E
NC
E
S
[1
]
W
HO
,
“
W
o
rld
h
e
a
lt
h
o
rg
a
n
iza
ti
o
n
(w
h
o
),
”
1
9
4
8
.
[
O
n
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s://
w
ww
.
w
h
o
.
in
t
.
[2
]
Y
.
Ya
n
g
e
t
a
l.
,
“
Ep
id
e
m
io
lo
g
ica
l
a
n
d
c
li
n
ica
l
f
e
a
tu
re
s
o
f
th
e
2
0
1
9
n
o
v
e
l
c
o
ro
n
a
v
iru
s
o
u
t
b
re
a
k
in
c
h
in
a
,
”
me
d
Rxiv
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
1
/
2
0
2
0
.
0
2
.
1
0
.
2
0
0
2
1
6
7
5
.
[3
]
D
.
W
a
n
g
e
t
a
l.
,
“
Cli
n
ica
l
C
h
a
r
a
c
ter
isti
c
s
o
f
1
3
8
H
o
sp
it
a
li
z
e
d
P
a
ti
e
n
ts
W
it
h
2
0
1
9
No
v
e
l
Co
r
o
n
a
v
iru
s
-
In
f
e
c
ted
P
n
e
u
m
o
n
ia i
n
W
u
h
a
n
,
Ch
i
n
a
,
”
J
A
M
A
,
v
o
l.
3
2
3
,
n
o
.
1
1
,
p
p
.
1
0
6
1
-
1
0
6
9
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
0
1
/j
a
m
a
.
2
0
2
0
.
1
5
8
5
.
[4
]
C
.
Hu
a
n
g
e
t
a
l.
,
“
Cli
n
ica
l
f
e
a
tu
re
s
o
f
p
a
ti
e
n
ts
in
f
e
c
ted
w
it
h
2
0
1
9
n
o
v
e
l
c
o
ro
n
a
v
iru
s
in
w
u
h
a
n
,
c
h
in
a
,
”
T
h
e
L
a
n
c
e
t,
v
o
l.
3
9
5
,
n
o
.
1
0
2
2
3
,
p
p
.
4
9
7
-
5
0
6
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
1
6
/
S
0
1
4
0
-
6
7
3
6
(2
0
)3
0
1
8
3
-
5
.
[5
]
D
.
K
.
W
.
Ch
u
e
t
a
l
.
,
“
M
o
lec
u
lar
Dia
g
n
o
sis
o
f
a
No
v
e
l
Co
ro
n
a
v
iru
s
(2
0
1
9
-
n
Co
V
)
C
a
u
sin
g
a
n
Ou
t
b
re
a
k
o
f
P
n
e
u
m
o
n
ia,”
Cli
n
ic
a
l
C
h
e
mistry
,
v
o
l.
6
6
,
n
o
.
4
,
p
p
.
5
4
9
-
5
5
5
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
9
3
/clin
c
h
e
m
/h
v
a
a
0
2
9
.
[6
]
P
.
G
o
´m
e
z
,
M
.
S
e
m
m
ler,
A
.
S
c
h
u
¨tze
n
b
e
rg
e
r,
C.
Bo
h
r,
a
n
d
M
.
Do
¨
ll
in
g
e
r,
“
L
o
w
-
li
g
h
t
ima
g
e
e
n
h
a
n
c
e
m
e
n
t
o
f
h
ig
h
-
sp
e
e
d
e
n
d
o
sc
o
p
ic
v
id
e
o
s
u
si
n
g
a
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
,
”
M
e
d
ica
l
and
b
i
o
l
o
g
ica
l
e
n
g
i
n
e
e
rin
g
and
c
o
mp
u
ti
n
g
,
v
o
l.
5
7
,
n
o
.
7
,
p
p
.
1
4
5
1
-
1
4
6
3
,
2
0
1
9
,
d
o
i:
1
0
.
1
0
0
7
/s
1
1
5
1
7
-
0
1
9
-
0
1
9
6
5
-
4
.
[7
]
J.
Ch
o
e
e
t
a
l.
,
“
De
e
p
lea
rn
in
g
-
b
a
se
d
i
m
a
g
e
c
o
n
v
e
rsio
n
o
f
CT
r
e
c
o
n
stru
c
ti
o
n
k
e
rn
e
ls
i
m
p
r
o
v
e
s
ra
d
io
m
i
c
s
re
p
ro
d
u
c
ib
il
it
y
f
o
r
p
u
lm
o
n
a
ry
n
o
d
u
l
e
s
o
r
m
a
ss
e
s
,”
Ra
d
i
o
lo
g
y
,
v
o
l.
2
9
2
,
n
o
.
2
,
p
p
.
3
6
5
-
3
7
3
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
4
8
/ra
d
io
l
.
2
0
1
9
1
8
1
9
6
0
.
[8
]
D
.
S
.
Ke
rm
a
n
y
e
t
a
l.
,
“
Id
e
n
ti
f
y
in
g
m
e
d
ica
l
d
iag
n
o
se
s
a
n
d
trea
tab
l
e
d
ise
a
se
s
b
y
i
m
a
g
e
-
b
a
se
d
d
e
e
p
lea
rn
in
g
,
”
Ce
ll
,
v
o
l.
1
7
2
,
n
o
.
5
,
p
p
.
1
1
2
2
-
1
1
3
1
,
2
0
1
8
,
d
o
i:
1
0
.
1
0
1
6
/
j.
c
e
ll
.
2
0
1
8
.
0
2
.
0
1
0
.
[9
]
H
.
J
.
Ko
o
,
S
.
L
im
,
J
.
Ch
o
e
,
S
.
-
H
.
Ch
o
i,
H
.
S
u
n
g
,
a
n
d
K.
-
H.
Do
,
“
Ra
d
io
g
ra
p
h
ic
a
n
d
c
t
f
e
a
tu
re
s
o
f
v
ir
a
l
p
n
e
u
m
o
n
ia,”
Ra
d
i
o
g
r
a
p
h
ics
,
v
o
l.
3
8
,
n
o
.
3
,
p
p
.
7
1
9
-
7
3
9
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
4
8
/rg
.
2
0
1
8
1
7
0
0
4
8
.
[1
0
]
P
.
G
u
o
,
A
.
Ev
a
n
s,
a
n
d
P
.
B
h
a
tt
a
c
h
a
ry
a
,
“
Nu
c
lei
se
g
m
e
n
tatio
n
f
o
r
q
u
a
n
ti
f
ica
ti
o
n
o
f
b
ra
in
t
u
m
o
rs i
n
d
i
g
it
a
l
p
a
th
o
l
o
g
y
im
a
g
e
s,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
S
o
ft
wa
re
S
c
ien
c
e
a
n
d
Co
mp
u
ta
ti
o
n
a
l
In
telli
g
e
n
c
e
(
IJ
S
S
CI),
v
o
l.
1
0
,
n
o
.
2
,
p
p
.
3
6
-
4
9
,
2
0
1
8
,
d
o
i:
1
0
.
4
0
1
8
/IJ
S
S
CI.
2
0
1
8
0
4
0
1
0
3
.
[1
1
]
O
.
Do
rg
h
a
m
e
t
a
l.
,
“
En
h
a
n
c
in
g
th
e
se
c
u
rit
y
o
f
e
x
c
h
a
n
g
in
g
a
n
d
sto
rin
g
d
i
c
o
m
m
e
d
ica
l
i
m
a
g
e
s
o
n
th
e
c
lo
u
d
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
f
Clo
u
d
Ap
p
li
c
a
ti
o
n
s
a
n
d
Co
mp
u
ti
n
g
(
IJ
CAC),
v
o
l.
8
,
n
o
.
1
,
p
p
.
1
5
4
-
1
7
2
,
2
0
1
8
,
d
o
i
:
1
0
.
4
0
1
8
/IJCA
C.
2
0
1
8
0
1
0
1
0
8
.
[1
2
]
A
.
G
h
o
n
e
im
,
G
.
M
u
h
a
m
m
a
d
,
S
.
U.
Am
in
,
a
n
d
B.
G
u
p
ta,
“
M
e
d
ica
l
im
a
g
e
f
o
rg
e
r
y
d
e
tec
ti
o
n
f
o
r
s
m
a
rt
h
e
a
lt
h
c
a
re
,
”
IEE
E
Co
mm
u
n
ica
t
io
n
s
M
a
g
a
zin
e
,
v
o
l.
5
6
,
n
o
.
4
,
p
p
.
3
3
-
3
7
,
2
0
1
8
,
d
o
i:
1
0
.
1
1
0
9
/
M
COM.
2
0
1
8
.
1
7
0
0
8
1
7
.
[1
3
]
L
.
Ya
n
e
t
a
l.
,
“
P
re
d
icti
o
n
o
f
c
rit
ica
li
ty
in
p
a
ti
e
n
ts
w
it
h
se
v
e
r
e
c
o
v
id
-
1
9
i
n
f
e
c
ti
o
n
u
sin
g
th
re
e
c
li
n
i
c
a
l
f
e
a
tu
re
s:
a
m
a
c
h
in
e
lea
rn
in
g
-
b
a
se
d
p
ro
g
n
o
stic
m
o
d
e
l
w
it
h
c
li
n
ica
l
d
a
ta
in
W
u
h
a
n
,”
me
d
Rxiv
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
1
/
2
0
2
0
.
0
2
.
2
7
.
2
0
0
2
8
0
2
7
.
[1
4
]
R
.
P
a
l,
A
.
A
.
S
e
k
h
,
S
.
Ka
r,
a
n
d
D.
K.
P
ra
sa
d
,
“
Ne
u
ra
l
n
e
tw
o
rk
b
a
se
d
c
o
u
n
try
w
ise
risk
p
re
d
ictio
n
o
f
c
o
v
id
-
1
9
,
”
Ap
p
li
e
d
S
c
ie
n
c
e
s
,
v
o
l.
1
0
,
n
o
.
1
8
,
2
0
2
0
,
A
rt.
n
o
.
6
4
4
8
,
d
o
i:
1
0
.
3
3
9
0
/ap
p
1
0
1
8
6
4
4
8
.
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:
2
0
8
8
-
8708
Tr
a
n
s
fer d
ee
p
lea
r
n
in
g
a
p
p
r
o
a
ch
fo
r
d
etec
tin
g
c
o
r
o
n
a
viru
s
d
is
ea
s
e
(
C
OV
I
D
-
19)
…
(
Mo
h
a
mme
d
A
l
-
S
ma
d
i
)
5007
[1
5
]
M
.
Ci
n
e
ll
i
e
t
a
l.
,
“
T
h
e
c
o
v
id
-
1
9
so
c
ial
m
e
d
ia
in
f
o
d
e
m
ic,”
S
c
ien
ti
fi
c
Re
p
o
rts
,
v
o
l.
1
0
,
n
o
.
1
,
p
p
.
1
-
1
0
,
2
0
2
0
,
A
rt.
n
o
.
1
6
5
9
8
,
d
o
i:
1
0
.
1
0
3
8
/s4
1
5
9
8
-
0
2
0
-
7
3
5
1
0
-
5
.
[1
6
]
S
.
W
a
n
g
e
t
a
l
.
,
“
A
d
e
e
p
lea
rn
in
g
a
lg
o
rit
h
m
u
sin
g
c
t
i
m
a
g
e
s
to
sc
re
e
n
f
o
r
c
o
ro
n
a
v
iru
s d
ise
a
se
(c
o
v
id
-
1
9
),
”
me
d
Rxiv
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
1
/
2
0
2
0
.
0
2
.
1
4
.
2
0
0
2
3
0
2
8
.
[1
7
]
P
.
K
.
S
e
th
y
,
S
.
K.
Be
h
e
ra
,
P
.
K.
Ra
th
a
,
P
.
Bisw
a
s,
“
De
te
c
ti
o
n
o
f
c
o
ro
n
a
v
iru
s
d
ise
a
se
(c
o
v
id
-
1
9
)
b
a
se
d
o
n
d
e
e
p
f
e
a
tu
re
s
a
n
d
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
M
a
th
e
ma
ti
c
a
l,
E
n
g
in
e
e
rin
g
a
n
d
M
a
n
a
g
e
me
n
t
S
c
ien
c
e
s
,
v
o
l.
5
,
n
o
.
4
,
p
p
.
6
4
3
-
6
5
1
,
2
0
2
0
,
d
o
i:
1
0
.
3
3
8
8
9
/IJM
E
M
S
.
2
0
2
0
.
5
.
4
.
0
5
2
.
[1
8
]
F
.
S
h
a
n
e
t
a
l
.
,
“
L
u
n
g
i
n
f
e
c
ti
o
n
q
u
a
n
ti
f
ica
ti
o
n
o
f
c
o
v
id
-
1
9
in
c
t
im
a
g
e
s
w
it
h
d
e
e
p
lea
rn
in
g
,
”
ArXi
v
,
a
b
s/2
0
0
3
.
0
4
6
5
5
,
2
0
2
0
.
[1
9
]
H
.
S
.
M
a
g
h
d
i
d
,
A
.
T
.
A
s
a
a
d
,
K
.
Z
.
G
h
a
f
o
o
r,
A
.
S
.
S
a
d
iq
,
a
n
d
M
.
K.
Kh
a
n
,
“
Dia
g
n
o
sin
g
c
o
v
id
-
1
9
p
n
e
u
m
o
n
ia
f
ro
m
x
-
ra
y
a
n
d
c
t
i
m
a
g
e
s
u
sin
g
d
e
e
p
le
a
rn
in
g
a
n
d
tran
sf
e
r
lea
rn
in
g
a
l
g
o
rit
h
m
s,”
Pro
c
e
e
d
in
g
s
Vo
l
u
me
1
1
7
3
4
,
M
u
lt
im
o
d
a
l
Ima
g
e
Exp
l
o
it
a
ti
o
n
a
n
d
L
e
a
r
n
in
g
2
0
2
1
,
v
o
l.
1
1
7
3
4
,
2
0
2
1
,
A
rt.
n
o
.
1
1
7
3
4
0
E,
d
o
i:
1
0
.
1
1
1
7
/
1
2
.
2
5
8
8
6
7
2
.
[2
0
]
X
.
X
u
e
t
a
l.
,
“
A
De
e
p
lea
rn
in
g
s
y
ste
m
to
sc
re
e
n
c
o
r
o
n
a
v
iru
s
d
ise
a
se
2
0
1
9
p
n
e
u
m
o
n
ia,”
En
g
in
e
e
rin
g
,
v
o
l.
6
,
n
o
.
1
0
,
p
p
.
1
1
2
2
-
1
1
2
9
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
1
6
/j
.
e
n
g
.
2
0
2
0
.
0
4
.
0
1
0
.
[2
1
]
O
.
G
o
z
e
s
e
t
a
l.
,
“
Ra
p
id
a
i
d
e
v
e
lo
p
m
e
n
t
c
y
c
le
f
o
r
th
e
c
o
ro
n
a
v
iru
s
(c
o
v
id
-
1
9
)
p
a
n
d
e
m
ic:
In
it
ial
re
su
lt
s
f
o
r
a
u
to
m
a
ted
d
e
tec
ti
o
n
a
n
d
p
a
ti
e
n
t
m
o
n
it
o
ri
n
g
u
sin
g
d
e
e
p
lea
rn
in
g
c
t
im
a
g
e
a
n
a
l
y
sis,”
a
rXiv p
re
p
rin
t
a
rXiv:2
0
0
3
.
0
5
0
3
7
,
2
0
2
0
.
[2
2
]
L
.
Li
e
t
a
l.
,
“
A
rti
f
i
c
ial
in
telli
g
e
n
c
e
d
isti
n
g
u
ish
e
s
c
o
v
id
-
1
9
f
ro
m
c
o
m
m
u
n
it
y
a
c
q
u
ired
p
n
e
u
m
o
n
i
a
o
n
c
h
e
st
CT
,
”
Ra
d
i
o
lo
g
y
,
2
0
2
0
,
A
rt.
n
o
.
2
0
0
9
0
5
,
d
o
i:
1
0
.
1
1
4
8
/ra
d
io
l.
2
0
2
0
2
0
0
9
0
5
.
[2
3
]
S
.
U
.
K
.
Bu
k
h
a
ri,
S
.
S
.
K
.
B
u
k
h
a
ri,
A
.
Sy
ed
,
S
.
S
.
H.
S
h
a
h
,
“
T
h
e
d
iag
n
o
stic
e
v
a
lu
a
ti
o
n
o
f
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
(
c
n
n
)
f
o
r
th
e
a
ss
e
ss
m
e
n
t
o
f
c
h
e
st
x
-
ra
y
o
f
p
a
ti
e
n
ts
in
f
e
c
ted
w
it
h
c
o
v
id
-
1
9
,
”
me
d
R
x
iv,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
1
/
2
0
2
0
.
0
3
.
2
6
.
2
0
0
4
4
6
1
0
.
[2
4
]
I
.
A
p
o
sto
lo
p
o
u
lo
s,
S
.
A
z
n
a
o
u
ri
d
i
s,
a
n
d
M
.
T
z
a
n
i,
“
Ex
trac
ti
n
g
p
o
ss
ib
ly
re
p
re
se
n
tativ
e
c
o
v
id
-
1
9
b
i
o
m
a
rk
e
r
s
f
ro
m
x
-
ra
y
i
m
a
g
e
s
w
it
h
d
e
e
p
lea
rn
in
g
a
p
p
r
o
a
c
h
a
n
d
im
a
g
e
d
a
t
a
re
late
d
to
p
u
lm
o
n
a
ry
d
ise
a
s
e
s,”
J
o
u
rn
a
l
o
f
M
e
d
ica
l
a
n
d
Bi
o
lo
g
ica
l
En
g
i
n
e
e
rin
g
,
v
o
l.
4
0
,
p
p
.
4
6
2
-
4
6
9
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
0
7
/s4
0
8
4
6
-
0
2
0
-
0
0
5
2
9
-
4
.
[2
5
]
A
.
Na
rin
,
C
.
Ka
y
a
,
a
n
d
Z
.
P
a
m
u
k
,
“
A
u
to
m
a
ti
c
d
e
tec
ti
o
n
o
f
c
o
ro
n
a
v
iru
s
d
ise
a
se
(
c
o
v
id
-
1
9
)
u
si
n
g
x
-
ra
y
ima
g
e
s
a
n
d
d
e
e
p
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
s,”
Pa
tt
e
rn
A
n
a
lys
is
a
n
d
A
p
p
li
c
a
ti
o
n
s,
p
p
.
1
-
1
4
,
2
0
2
1
,
d
o
i:
1
0
.
1
0
0
7
/s1
0
0
4
4
-
0
2
1
-
0
0
9
8
4
-
y
.
[2
6
]
A
.
K
.
Ja
is
wa
l,
P
.
T
iw
a
ri,
S
.
Ku
m
a
r,
D
.
G
u
p
ta,
A
.
Kh
a
n
n
a
,
a
n
d
J.
J.
P
.
C.
Ro
d
rig
u
e
s,
“
Id
e
n
ti
f
y
in
g
p
n
e
u
m
o
n
ia
in
c
h
e
st
x
-
ra
y
s:
A
d
e
e
p
lea
r
n
in
g
a
p
p
r
o
a
c
h
,
”
M
e
a
su
re
me
n
t,
v
o
l.
1
4
5
,
p
p
.
5
1
1
-
5
1
8
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j.
m
e
a
su
re
m
e
n
t.
2
0
1
9
.
0
5
.
0
7
6
[2
7
]
K
.
A
ro
ra
,
A
.
S
.
Bist,
S
.
C
h
a
u
ra
sia
,
a
n
d
R
.
P
ra
k
a
sh
,
“
A
n
a
l
y
sis
o
f
d
e
e
p
lea
rn
in
g
te
c
h
n
iq
u
e
s
f
o
r
c
o
v
id
-
1
9
d
e
tec
ti
o
n
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
f
S
c
ien
ti
fi
c
Res
e
a
rc
h
In
En
g
in
e
e
rin
g
An
d
M
a
n
a
g
e
me
n
t
(
IJ
S
RE
M
)
,
v
o
l.
4
,
n
o
.
4
,
p
p
.
1
-
5
,
2
0
2
0
.
[2
8
]
M
.
F
a
ro
o
q
a
n
d
A
.
Ha
f
e
e
z
,
“
Co
v
i
d
-
re
sn
e
t:
A
d
e
e
p
lea
rn
in
g
f
ra
m
e
wo
rk
f
o
r
sc
re
e
n
in
g
o
f
c
o
v
id
1
9
f
ro
m
r
a
d
io
g
ra
p
h
s,”
2
0
2
0
,
a
rXiv
p
re
p
rin
t
a
rXiv:2
0
0
3
.
1
4
3
9
5
.
[2
9
]
A
.
M
.
A
lq
u
d
a
h
,
S
.
Qa
z
a
n
,
H
.
H
.
A
lq
u
ra
n
,
I
.
A
b
u
q
a
sm
ieh
,
a
n
d
A
.
A
lq
u
d
a
h
,
“
Co
v
id
-
1
9
d
e
tec
ti
o
n
u
si
n
g
x
-
ra
y
i
m
a
g
e
s
a
n
d
a
rti
f
ic
ial
in
telli
g
e
n
c
e
h
y
b
rid
s
y
ste
m
s,”
Bi
o
me
d
ica
l
S
i
g
n
a
l
a
n
d
Ima
g
e
A
n
a
lys
is
a
n
d
Pr
o
jec
t;
Bi
o
me
d
ica
l
S
ig
n
a
l
a
n
d
Ima
g
e
An
a
lys
is a
n
d
M
a
c
h
in
e
L
e
a
rn
in
g
L
a
b
:
Bo
c
a
R
a
to
n
,
F
L
,
USA
, 2
0
1
9
,
d
o
i:
1
0
.
5
4
5
5
/j
jee
.
2
0
4
-
1
5
8
5
3
1
2
2
4
.
[3
0
]
M
d
Z
.
A
lo
m
,
M
.
M
.
S
.
Ra
h
m
a
n
,
M
.
S
.
Na
srin
,
T
.
M
.
T
a
h
a
,
a
n
d
V
.
K.
A
sa
ri,
“
COV
ID
M
T
Ne
t:
COV
ID
-
19
De
tec
ti
o
n
w
it
h
M
u
lt
i
-
T
a
sk
De
e
p
L
e
a
rn
in
g
A
p
p
ro
a
c
h
e
s,”
a
rXiv e
-
p
rin
ts
,
2
0
2
0
.
[3
1
]
K
.
Ha
m
m
o
u
d
i
e
t
a
l.
,
“
De
e
p
lea
r
n
in
g
o
n
c
h
e
st
x
-
ra
y
i
m
a
g
e
s
to
d
e
tec
t
a
n
d
e
v
a
lu
a
te
p
n
e
u
m
o
n
ia
c
a
s
e
s
a
t
th
e
e
r
a
o
f
c
o
v
id
-
1
9
,
”
2
0
2
0
,
ArXi
v
p
re
p
rin
t
a
rXiv:2
0
0
4
.
0
3
3
9
9
.
[3
2
]
S
.
Ra
h
m
a
ti
z
a
d
e
h
,
S
.
V
.
-
Ha
g
h
i,
a
n
d
A
.
Da
b
b
a
g
h
,
“
T
h
e
ro
le o
f
a
rti
f
i
c
ial
in
telli
g
e
n
c
e
in
m
a
n
a
g
e
m
e
n
t
o
f
c
rit
ica
l
c
o
v
id
-
1
9
p
a
ti
e
n
ts,”
J
o
u
rn
a
l
o
f
Ce
l
lu
la
r
and
M
o
lec
u
la
r
An
e
sth
e
si
a
,
v
o
l.
5
,
n
o
.
1
,
p
p
.
1
6
-
2
2
,
2
0
2
0
.
[3
3
]
F
.
S
h
i
e
t
a
l.
,
“
Re
v
ie
w
o
f
a
rti
f
icia
l
in
telli
g
e
n
c
e
tec
h
n
iq
u
e
s
in
im
a
g
i
n
g
d
a
ta
a
c
q
u
isit
i
o
n
,
se
g
m
e
n
tatio
n
a
n
d
d
iag
n
o
si
s
f
o
r
c
o
v
id
-
19,
”
I
EE
E
Rev
ie
ws
in
Bi
o
me
d
ica
l
En
g
in
e
e
rin
g
,
v
o
l.
1
4
,
p
p
.
4
-
1
5
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
0
9
/RB
M
E.
2
0
2
0
.
2
9
8
7
9
7
5
.
[3
4
]
T
.
T
.
N
g
u
y
e
n
,
“
A
rti
f
i
c
ial
in
telli
g
e
n
c
e
in
th
e
b
a
tt
le
a
g
a
in
st
c
o
ro
n
a
v
iru
s
(c
o
v
id
-
1
9
):
a
su
rv
e
y
a
n
d
f
u
tu
re
re
se
a
rc
h
d
irec
ti
o
n
s,”
2
0
2
0
,
a
rX
iv p
re
p
ri
n
t
a
rXiv:2
0
0
8
.
0
7
3
4
3
.
[3
5
]
Tw
e
e
t
Bin
d
e
r,
“
Co
v
id
1
9
-
tw
it
ter
e
v
o
lu
ti
o
n
,
”
[
On
l
in
e
]
.
A
v
a
il
a
b
l
e
:
h
tt
p
s://
w
ww
.
t
w
e
e
tb
in
d
e
r.
c
o
m
/b
lo
g
/co
v
id
-
19
-
c
o
ro
n
a
v
iru
s
-
tw
it
ter/
[3
6
]
R
.
L
a
m
sa
l
,
“
C
o
v
id
-
1
9
tw
e
e
ts d
a
tas
e
t,
”
IEE
E
d
a
ta
Po
rt
,
2
0
2
0
,
d
o
i
:
1
0
.
2
1
2
2
7
/
7
8
1
w
-
e
f
4
2
.
[3
7
]
J
.
M
.
Ba
n
d
a
a
n
d
R
.
T
e
k
u
m
a
ll
a
,
“
A
Tw
it
ter
Da
tas
e
t
o
f
4
0
+
m
il
li
o
n
t
w
e
e
ts
r
e
late
d
to
COV
ID
-
19
,”
T
h
is
d
a
ta
se
t
wil
l
b
e
u
p
d
a
ted
b
i
-
we
e
k
ly
,
2
0
2
0
.
[3
8
]
J
.
M
.
Ba
n
d
a
e
t
a
l
.
,
“
A
Tw
it
ter
Da
tas
e
t
o
f
1
5
0
+
m
il
li
o
n
tw
e
e
ts
re
lat
e
d
to
CO
V
ID
-
1
9
,
M
a
rc
h
2
0
2
0
,
”
T
h
is
d
a
t
a
se
t
wil
l
b
e
u
p
d
a
ted
b
i
-
we
e
k
ly a
t
lea
st w
it
h
a
d
d
it
i
o
n
a
l
twee
ts,
l
o
o
k
a
t
t
h
e
g
i
th
u
b
re
p
o
f
o
r th
e
se
u
p
d
a
tes
,
2
0
2
0
.
[3
9
]
P
a
n
a
c
e
a
L
a
b
,
“
Co
v
id
-
1
9
tw
it
ter ch
a
tt
e
r
d
a
tas
e
t
,”
[
O
n
li
n
e
].
A
v
a
il
a
b
le:
h
tt
p
:/
/w
ww
.
p
a
n
a
c
e
a
lab
.
o
rg
/co
v
id
1
9
/
[4
0
]
Ka
g
g
l
e
,
“
Twe
e
ts u
sin
g
h
a
sh
tag
s w
it
h
COV
ID1
9
,
”
[
On
li
n
e
].
A
v
a
il
a
b
le:
h
tt
p
s://
w
ww
.
k
a
g
g
le.co
m
/d
is
c
u
ss
io
n
/
2
3
2
5
5
8
.
[4
1
]
Ka
g
g
l
e
,
“
Da
y
le
v
e
l
in
f
o
r
m
a
ti
o
n
o
n
c
o
v
id
-
1
9
a
ff
e
c
ted
c
a
se
s,”
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/www
.
k
a
g
g
l
e
.
c
o
m
/su
d
a
lair
a
jk
u
m
a
r/n
o
v
e
l
-
c
o
ro
n
a
-
v
iru
s
-
2
0
1
9
-
d
a
tas
e
t
[4
2
]
Ka
g
g
l
e
,
“
Co
v
id
-
1
9
o
p
e
n
re
se
a
rc
h
d
a
tas
e
t
c
h
a
ll
e
n
g
e
(
c
o
rd
-
1
9
)
,
”
[
O
n
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s://
w
ww
.
k
a
g
g
le.co
m
/allen
-
in
stit
u
te
-
f
o
r
-
a
i/
CORD
-
19
-
re
se
a
rc
h
-
c
h
a
ll
e
n
g
e
[4
3
]
H
u
m
a
n
it
a
rian
Da
ta
Ex
c
h
a
n
g
e
(HD
X
),
“
No
v
e
l
c
o
v
id
-
1
9
ti
m
e
s
e
ries
d
a
ta,”
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/d
a
ta.h
u
m
d
a
ta.o
rg
/d
a
tas
e
t/
n
o
v
e
l
-
c
o
ro
n
a
v
iru
s
-
2
0
1
9
-
n
c
o
v
-
c
a
se
s
[4
4
]
Ne
x
tstrain
,
“
Ge
n
o
m
ic ep
id
e
m
io
lo
g
y
o
f
n
o
v
e
l
c
o
ro
n
a
v
iru
s,”
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s://
n
e
x
tstrain
.
o
rg
/n
c
o
v
/g
lo
b
a
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
6
,
Dec
em
b
er
202
1
:
4
9
9
9
-
5
0
0
8
5008
[4
5
]
Ka
g
g
l
e
,
“
Ch
e
st
x
-
ra
y
i
m
a
g
e
s
(p
n
e
u
m
o
n
ia),”
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/www
.
k
a
g
g
l
e
.
c
o
m
/p
a
u
lt
imo
th
y
m
o
o
n
e
y
/ch
e
st
-
x
r
a
y
-
p
n
e
u
m
o
n
ia
.
[4
6
]
J
.
P
.
C
o
h
e
n
,
P
.
M
o
rr
iso
n
,
a
n
d
L
.
Da
o
,
“
Co
v
id
-
1
9
im
a
g
e
d
a
ta,”
a
rXiv 2
0
0
3
.
1
1
5
9
7
,
2
0
2
0
.
[4
7
]
X.
Ya
n
g
,
X
.
He
,
J
.
Z
h
a
o
,
Y
.
Z
h
a
n
g
,
S
.
Zh
a
n
g
,
a
n
d
P
.
X
ie,
“
Co
v
i
d
-
ct
d
a
tas
e
t:
a
c
t
im
a
g
e
d
a
tas
e
t
a
b
o
u
t
c
o
v
id
-
19
,”
a
rXiv p
re
p
ri
n
t
a
rX
iv:2
0
0
3
.
1
3
8
6
5
,
2
0
2
0
.
[4
8
]
M
e
d
ica
l
S
e
g
m
e
n
t
a
ti
o
n
,
“
Co
v
id
-
1
9
c
t
se
g
m
e
n
tatio
n
,
”
[
O
n
li
n
e
].
Av
a
il
a
b
le:
h
tt
p
s:/
/www
.
e
ib
ir
.
o
rg
/co
v
id
-
19
-
im
a
g
in
g
-
d
a
tas
e
ts/
[4
9
]
Ra
d
io
p
a
e
d
ia,
“
Ra
d
io
p
a
e
d
ia.o
rg
,
”
2
0
0
5
.
[
O
n
li
n
e
].
A
v
a
il
a
b
le:
h
tt
p
s://
ra
d
io
p
a
e
d
ia.
o
rg
/
[5
0
]
M
o
n
trea
l
“
A
I.
Co
v
id
-
19
-
re
so
u
rc
e
s,”
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
t
t
p
s://
m
il
a
.
q
u
e
b
e
c
/en
/co
v
i
d
-
1
9
/
[5
1
]
T
ra
in
i
n
g
Da
ta.i
o
,
“
Co
v
id
-
1
9
ra
d
i
o
lo
g
y
d
a
tas
e
t
(c
h
e
st
x
ra
y
&
c
t)
f
o
r
a
n
n
o
tatio
n
&
c
o
ll
a
b
o
ra
ti
o
n
,
”
[
On
li
n
e
].
Av
a
il
a
b
le:
h
tt
p
s://
t
o
w
a
rd
sd
a
tas
c
ien
c
e
.
c
o
m
/co
v
id
-
19
-
im
a
g
in
g
-
d
a
tas
e
t
-
c
h
e
st
-
x
ra
y
-
ct
-
f
o
r
-
a
n
n
o
ta
t
i
o
n
-
c
o
ll
a
b
o
ra
ti
o
n
-
5
f
6
e
0
7
6
f
5
f
22
[5
2
]
Da
ta
a
n
d
Re
so
u
rc
e
s
,
“
Co
v
id
-
1
9
e
p
id
e
m
io
lo
g
ica
l
d
a
ta,”
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/sit
e
s.g
o
o
g
le.
c
o
m
/v
i
e
w
/d
a
ta
-
sc
ien
c
e
-
c
o
v
id
-
19/
[5
3
]
L
.
T
.
P
h
a
n
e
t
a
l
.
,
“
Im
p
o
rtatio
n
a
n
d
h
u
m
a
n
-
to
-
h
u
m
a
n
tran
s
m
issio
n
o
f
a
n
o
v
e
l
c
o
ro
n
a
v
iru
s in
v
ietn
a
m
,
”
Ne
w
En
g
l
and
J
o
u
rn
a
l
o
f
M
e
d
icin
e
,
v
o
l
.
3
8
2
,
n
o
.
9
,
p
p
.
8
7
2
-
8
7
4
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
5
6
/NEJM
c
2
0
0
1
2
7
2
[5
4
]
S
.
S
a
leh
i,
A
.
A
b
e
d
i,
S
.
Ba
lak
ri
sh
n
a
n
,
a
n
d
G
.
A
li
,
“
Co
ro
n
a
v
iru
s
d
ise
a
se
2
0
1
9
(c
o
v
id
-
1
9
):
a
sy
ste
m
a
ti
c
re
v
ie
w
o
f
i
m
a
g
in
g
f
in
d
in
g
s
in
9
1
9
p
a
ti
e
n
ts,”
Ame
ric
a
n
J
o
u
rn
a
l
o
f
R
o
e
n
tg
e
n
o
lo
g
y
,
v
o
l.
2
1
5
,
n
o
.
1
,
p
p.
87
-
9
3
,
2
0
2
0
,
doi
:
1
0
.
2
2
1
4
/A
JR.2
0
.
2
3
0
3
4
.
[5
5
]
Z
.
Y
.
Zu
e
t
a
l.
,
“
Co
ro
n
a
v
iru
s
d
i
se
a
se
2
0
1
9
(c
o
v
i
d
-
1
9
):
A
p
e
rsp
e
c
ti
v
e
f
ro
m
c
h
in
a
,
”
Ra
d
i
o
l
o
g
y
,
v
o
l.
2
9
6
,
n
o
.
2
,
p
p
.
E1
5
-
E2
5
,
2
0
2
0
,
A
rt.
n
o
.
2
0
0
4
9
0
,
d
o
i:
1
0
.
1
1
4
8
/ra
d
io
l
.
2
0
2
0
2
0
0
4
9
0
.
[5
6
]
W
.
Ko
n
g
a
n
d
P
.
P
.
A
g
a
r
w
a
l,
“
Ch
e
st
ima
g
in
g
a
p
p
e
a
ra
n
c
e
o
f
c
o
v
id
-
1
9
i
n
f
e
c
ti
o
n
,
”
Ra
d
io
lo
g
y
:
Ca
rd
io
th
o
ra
c
ic
Im
a
g
in
g
,
v
o
l.
2
,
n
o
.
1
,
2
0
2
0
,
A
rt.
n
o
.
e
2
0
0
0
2
8
,
d
o
i:
1
0
.
1
1
4
8
/ry
c
t.
2
0
2
0
2
0
0
0
2
8
.
[5
7
]
H
.
Y
.
F
.
W
o
n
g
e
t
a
l.
,
“
F
re
q
u
e
n
c
y
a
n
d
d
istri
b
u
ti
o
n
o
f
c
h
e
st
ra
d
io
g
ra
p
h
ic
f
in
d
in
g
s
in
c
o
v
id
-
1
9
p
o
s
it
iv
e
p
a
ti
e
n
ts
,
”
Ra
d
i
o
lo
g
y
,
v
o
l
.
2
9
6
,
n
o
.
2
,
p
p
.
E7
2
-
E7
8
,
2
0
2
0
,
A
rt.
n
o
.
2
0
1
1
6
0
,
d
o
i
:
1
0
.
1
1
4
8
/rad
i
o
l.
2
0
2
0
2
0
1
1
6
0
.
[5
8
]
G
.
L
it
jen
s
e
t
a
l.
,
“
A
su
rv
e
y
o
n
d
e
e
p
lea
rn
in
g
in
m
e
d
ica
l
im
a
g
e
a
n
a
l
y
sis
,
”
M
e
d
ica
l
ima
g
e
a
n
a
lys
is,
v
o
l.
4
2
,
p
p
.
6
0
-
8
8
,
2
0
1
7
,
d
o
i:
1
0
.
1
0
1
6
/
j.
m
e
d
ia.2
0
1
7
.
0
7
.
0
0
5
.
[5
9
]
O
.
Ru
ss
a
k
o
v
s
k
y
e
t
a
l.
,
“
I
m
a
g
e
n
e
t
larg
e
sc
a
le
v
isu
a
l
re
c
o
g
n
it
io
n
c
h
a
ll
e
n
g
e
,
”
In
ter
n
a
ti
o
n
a
l
jo
u
rn
a
l
o
f
c
o
mp
u
ter
v
isio
n
,
v
o
l
.
1
1
5
,
n
o
.
3
,
p
p
.
2
1
1
-
2
5
2
,
2
0
1
5
,
d
o
i:
1
0
.
1
0
0
7
/s
1
1
2
6
3
-
0
1
5
-
0
8
1
6
-
y
.
[6
0
]
C
.
S
z
e
g
e
d
y
,
V
.
V
a
n
h
o
u
c
k
e
,
S
.
Io
ff
e
,
J
.
S
h
len
s,
a
n
d
Z
.
W
o
jn
a
,
“
Re
th
in
k
in
g
t
h
e
in
c
e
p
ti
o
n
a
rc
h
it
e
c
tu
r
e
f
o
r
c
o
m
p
u
ter
v
isio
n
,
”
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
IEE
E
c
o
n
fer
e
n
c
e
o
n
c
o
mp
u
ter
v
isio
n
a
n
d
p
a
tt
e
rn
re
c
o
g
n
it
io
n
,
2
0
1
6
,
p
p
.
2
8
1
8
-
2
8
2
6
[6
1
]
F
.
Ch
o
ll
e
t,
“
X
c
e
p
ti
o
n
:
De
e
p
lea
rn
in
g
w
it
h
d
e
p
th
w
ise
se
p
a
ra
b
le
c
o
n
v
o
lu
ti
o
n
s,”
2
0
1
7
IEE
E
Co
n
fer
e
n
c
e
o
n
Co
m
p
u
te
r
Vi
sio
n
a
n
d
P
a
tt
e
rn
Rec
o
g
n
it
i
o
n
(
CVP
R)
,
2
0
1
7
,
p
p
.
1
2
5
1
-
1
2
5
8
,
d
o
i
:
1
0
.
1
1
0
9
/C
VP
R.
2
0
1
7
.
1
9
5
.
[6
2
]
Ke
ra
s,
“
Ke
ra
s a
p
i,
”
[
O
n
li
n
e
]
.
A
v
a
il
a
b
le:
h
t
tp
s://
k
e
ra
s.io
/ca
ll
b
a
c
k
s/
[6
3
]
S
.
Io
f
f
e
a
n
d
C
.
S
z
e
g
e
d
y
,
“
Ba
tch
n
o
rm
a
li
z
a
ti
o
n
:
A
c
c
e
lera
ti
n
g
d
e
e
p
n
e
tw
o
rk
train
in
g
b
y
re
du
c
in
g
in
t
e
rn
a
l
c
o
v
a
riate
sh
if
t,
”
Pro
c
e
e
d
in
g
s
o
f
t
h
e
3
2
n
d
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
M
a
c
h
i
n
e
L
e
a
rn
i
n
g
,
v
o
l.
3
7
,
2
0
1
5
,
p
p
.
4
4
8
-
4
5
6
.
[6
4
]
N
.
S
riv
a
sta
v
a
,
G
.
Hin
to
n
,
A
.
Kri
z
h
e
v
sk
y
,
I
.
S
u
tsk
e
v
e
r,
a
n
d
R
.
S
a
lak
h
u
td
i
n
o
v
,
“
Dro
p
o
u
t:
a
sim
p
le
w
a
y
to
p
re
v
e
n
t
n
e
u
ra
l
n
e
tw
o
rk
s
f
ro
m
o
v
e
r
f
it
ti
n
g
,
”
T
h
e
jo
u
rn
a
l
o
f
ma
c
h
in
e
lea
r
n
in
g
re
se
a
rc
h
,
v
o
l.
1
5
,
n
o
.
56
,
p
p
.
1
9
2
9
-
1
9
5
8
,
2
0
1
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.