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
.
4
,
A
u
g
u
s
t
20
25
,
p
p
.
3
9
9
6
~
4
0
0
3
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
4
.
pp
3
9
9
6
-
4
0
0
3
3996
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
M
ulti
-
cla
ss
pne
u
mo
nia
det
ect
io
n u
sing
f
ine
-
tuned
vis
io
n
trans
former mo
d
el
K
hu
s
h
bo
o
T
riv
edi
,
Chin
t
a
n
B.
T
ha
ck
er
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
e
p
a
r
t
me
n
t
,
P
a
r
u
l
U
n
i
v
e
r
si
t
y
,
V
a
d
o
d
a
r
a
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
1
2
,
2
0
2
4
R
ev
is
ed
Ma
r
5
,
2
0
2
5
Acc
ep
ted
Ma
r
2
0
,
2
0
2
5
Distin
g
u
ish
i
n
g
b
e
twe
e
n
th
e
v
a
ri
o
u
s
f
o
rm
s
o
f
p
n
e
u
m
o
n
ia
(b
a
c
teria
l,
v
iral,
fu
n
g
a
l,
a
n
d
n
o
rm
a
l
)
u
sin
g
c
h
e
st
X
-
ra
y
s
is
a
m
a
jo
r
p
ro
b
lem
in
g
l
o
b
a
l
h
e
a
lt
h
.
Co
n
v
e
n
ti
o
n
a
l
a
p
p
r
o
a
c
h
e
s
to
p
n
e
u
m
o
n
ia
i
d
e
n
ti
fica
ti
o
n
fre
q
u
e
n
tl
y
d
e
p
e
n
d
o
n
lab
o
ri
o
u
s
a
n
d
e
rro
r
-
p
r
o
n
e
m
a
n
u
a
l
in
ter
p
re
tatio
n
.
C
u
rre
n
t
m
a
c
h
i
n
e
lea
rn
in
g
(
ML
)
m
o
d
e
ls,
li
k
e
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
two
rk
s
(CN
N
s)
,
h
a
v
e
d
e
m
o
n
stra
ted
so
m
e
su
c
c
e
ss
,
b
u
t
t
h
e
y
fre
q
u
e
n
tl
y
fa
il
o
n
j
o
b
s
re
q
u
ir
in
g
m
u
lt
i
-
c
las
s
c
las
sific
a
ti
o
n
o
r
g
e
n
e
ra
li
z
a
ti
o
n
.
T
h
e
p
o
ten
ti
a
l
o
f
v
isio
n
tra
n
sfo
rm
e
r
(ViT)
m
o
d
e
ls,
fi
n
e
-
tu
n
e
d
t
o
a
d
d
re
ss
th
e
se
li
m
it
a
ti
o
n
s,
is
e
x
p
l
o
re
d
.
T
h
e
a
p
p
ro
a
c
h
e
n
h
a
n
c
e
s
th
e
a
c
c
u
ra
c
y
o
f
p
n
e
u
m
o
n
ia
c
las
sifica
ti
o
n
in
to
f
o
u
r
d
isti
n
c
t
c
las
se
s
b
y
le
v
e
ra
g
in
g
th
e
a
tt
e
n
ti
o
n
m
e
c
h
a
n
ism
in
v
isio
n
tra
n
sfo
rm
e
rs
(ViTs)
.
F
i
n
e
-
tu
n
in
g
wit
h
a
tag
g
e
d
c
h
e
st
X
-
ra
y
d
a
tas
e
t
imp
ro
v
e
s
t
h
e
a
lg
o
rit
h
m
'
s
a
b
il
it
y
to
d
e
tec
t
s
u
b
tl
e
v
a
riati
o
n
s
in
p
n
e
u
m
o
n
ia
t
y
p
e
s.
T
h
e
fin
d
i
n
g
s
d
e
m
o
n
stra
te
th
e
m
o
d
e
l'
s
e
ffe
c
ti
v
e
n
e
ss
in
m
u
lt
i
-
c
las
s
p
n
e
u
m
o
n
ia
d
iag
n
o
sis,
a
c
h
iev
i
n
g
a
sig
n
ifi
c
a
n
t
p
e
rfo
rm
a
n
c
e
imp
ro
v
e
m
e
n
t
with
9
8
%
a
c
c
u
ra
c
y
a
c
ro
ss
th
e
fo
u
r
c
las
se
s.
Th
is
wo
r
k
h
i
g
h
li
g
h
ts
th
e
p
ro
m
ise
o
f
v
isi
o
n
tran
sfo
rm
e
rs
in
m
e
d
ica
l
ima
g
in
g
,
e
n
a
b
li
n
g
th
e
d
e
v
e
lo
p
m
e
n
t
o
f
imp
r
o
v
e
d
a
n
d
sc
a
lab
le p
n
e
u
m
o
n
ia cla
ss
ifi
c
a
ti
o
n
m
e
th
o
d
s.
K
ey
w
o
r
d
s
:
C
h
est X
-
R
ay
clas
s
if
icatio
n
Fin
e
-
tu
n
in
g
Me
d
ical
im
ag
in
g
Mu
lti
-
class
p
n
eu
m
o
n
ia
Vis
io
n
tr
an
s
f
o
r
m
er
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
:
Kh
u
s
h
b
o
o
T
r
iv
ed
i
C
o
m
p
u
ter
Scien
ce
an
d
E
n
g
i
n
e
er
in
g
Dep
ar
tm
e
n
t,
Par
u
l U
n
iv
er
s
ity
Vad
o
d
ar
a,
G
u
jar
at,
I
n
d
ia
E
m
ail: k
h
u
s
h
b
o
o
.
tr
iv
e
d
i2
1
3
0
5
@
p
ar
u
lu
n
iv
er
s
ity
.
ac
.
in
1.
I
NT
RO
D
UCT
I
O
N
Pn
eu
m
o
n
ia
r
em
ain
s
a
s
ig
n
if
ic
an
t
g
lo
b
al
h
ea
lth
ch
allen
g
e
,
in
f
ec
tin
g
m
illi
o
n
s
an
n
u
ally
an
d
ca
u
s
in
g
a
s
u
b
s
tan
tial
n
u
m
b
er
o
f
d
ea
th
s
.
E
ar
ly
a
n
d
ac
c
u
r
ate
d
iag
n
o
s
i
s
is
cr
itical
f
o
r
im
p
r
o
v
in
g
p
a
tien
t
o
u
tco
m
es
a
n
d
r
ed
u
cin
g
co
m
p
licatio
n
s
[
1
]
,
[
2
]
.
C
h
est
X
-
r
ay
s
ar
e
wid
ely
u
s
ed
f
o
r
d
iag
n
o
s
in
g
p
n
eu
m
o
n
ia,
b
u
t
in
ter
p
r
etin
g
th
ese
im
ag
es
is
a
co
m
p
lex
task
,
esp
ec
ially
wh
en
d
is
t
i
n
g
u
is
h
in
g
b
etwe
en
b
ac
te
r
ial,
v
ir
al,
f
u
n
g
al,
a
n
d
m
y
co
p
lasma
p
n
eu
m
o
n
ia.
Va
r
iab
ilit
y
in
h
o
w
p
n
eu
m
o
n
ia
m
an
if
ests
ac
r
o
s
s
p
atien
ts
f
u
r
th
er
c
o
m
p
licates
d
iag
n
o
s
is
,
m
ak
in
g
m
an
u
al
in
te
r
p
r
etatio
n
b
y
r
a
d
io
lo
g
is
ts
b
o
th
tim
e
-
in
ten
s
iv
e
an
d
p
r
o
n
e
to
er
r
o
r
s
[
3
]
–
[
5
]
.
R
ec
en
t
ad
v
an
ce
m
en
ts
in
d
ee
p
lear
n
in
g
h
a
v
e
led
to
p
r
o
m
is
in
g
d
ev
el
o
p
m
en
ts
in
a
u
to
m
ati
n
g
m
ed
ical
im
ag
e
an
aly
s
is
.
C
o
n
v
o
lu
tio
n
a
l
n
eu
r
al
n
etw
o
r
k
s
(
C
NNs)
h
av
e
b
ee
n
p
ar
ticu
lar
l
y
s
u
cc
ess
f
u
l
in
im
ag
e
-
b
ased
d
is
ea
s
e
d
iag
n
o
s
is
,
in
clu
d
in
g
p
n
eu
m
o
n
ia
class
if
icatio
n
[
6
]
–
[
8
]
.
Ho
wev
er
,
C
NNs
o
f
ten
s
t
r
u
g
g
le
with
m
u
lti
-
class
clas
s
if
icatio
n
task
s
th
at
r
eq
u
ir
e
r
ec
o
g
n
izin
g
s
u
b
tle
v
ar
iatio
n
s
b
etwe
en
ca
teg
o
r
ies.
Ad
d
itio
n
ally
,
th
eir
p
er
f
o
r
m
an
ce
ca
n
d
e
g
r
ad
e
wh
e
n
ap
p
lied
to
u
n
s
ee
n
o
r
d
iv
e
r
s
e
d
atasets
,
h
ig
h
lig
h
tin
g
a
n
ee
d
f
o
r
m
o
r
e
a
d
ap
tab
le
an
d
r
o
b
u
s
t so
lu
tio
n
s
[
9
]
,
[
1
0
]
.
Vis
io
n
tr
an
s
f
o
r
m
e
r
s
(
ViT
s
)
o
f
f
er
a
co
m
p
ellin
g
alter
n
ativ
e
to
C
NNs
b
y
lev
er
ag
i
n
g
s
elf
-
atten
tio
n
m
ec
h
an
is
m
s
to
ca
p
tu
r
e
lo
n
g
-
r
an
g
e
d
ep
e
n
d
en
cies
with
in
im
ag
es.
T
h
is
ca
p
ab
ilit
y
m
ak
es
th
em
well
-
s
u
ited
f
o
r
co
m
p
lex
class
if
icatio
n
p
r
o
b
le
m
s
.
T
h
e
g
o
al
o
f
th
is
r
esear
ch
is
to
ex
p
lo
r
e
th
e
ef
f
ec
tiv
en
ess
o
f
f
in
e
-
tu
n
e
d
ViT
s
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
Mu
lti
-
cla
s
s
p
n
eu
mo
n
ia
d
etec
t
io
n
u
s
in
g
fin
e
-
tu
n
ed
visi
o
n
tr
a
n
s
fo
r
mer m
o
d
el
(
K
h
u
s
h
b
o
o
Tr
ived
i
)
3997
in
th
e
m
u
lti
-
class
cla
s
s
if
icat
io
n
o
f
p
n
eu
m
o
n
ia,
aim
in
g
to
o
v
er
co
m
e
th
e
lim
itatio
n
s
o
f
ex
is
tin
g
m
eth
o
d
s
an
d
ac
h
iev
e
h
ig
h
ac
cu
r
ac
y
ac
r
o
s
s
d
if
f
er
en
t
p
n
e
u
m
o
n
ia
ty
p
es.
T
h
is
s
tu
d
y
asp
ir
es
to
co
n
tr
ib
u
te
t
o
th
e
d
ev
el
o
p
m
en
t
o
f
s
ca
lab
le,
r
eliab
le,
a
n
d
ef
f
icien
t d
iag
n
o
s
tic
to
o
ls
f
o
r
p
n
eu
m
o
n
ia
d
etec
tio
n
.
2.
L
I
T
E
R
AT
U
RE
S
T
UDY
T
h
e
u
s
e
o
f
ar
tific
ial
in
tellig
en
ce
(
AI
)
an
d
d
ee
p
lea
r
n
in
g
h
as
r
ev
o
lu
tio
n
ized
m
ed
ica
l
im
ag
in
g
,
p
ar
ticu
lar
ly
in
p
n
e
u
m
o
n
ia
d
ia
g
n
o
s
is
.
ViT
s
h
av
e
im
p
r
o
v
e
d
e
f
f
icien
cy
an
d
ac
cu
r
ac
y
i
n
ch
es
t
X
-
r
ay
an
al
y
s
is
f
o
r
p
n
eu
m
o
n
ia
[
1
]
.
T
r
an
s
f
er
lear
n
in
g
alg
o
r
ith
m
s
,
s
u
c
h
as
th
o
s
e
ap
p
lied
to
d
etec
t
C
OVI
D
-
1
9
p
n
e
u
m
o
n
ia,
h
a
v
e
b
ee
n
k
e
y
in
e
n
h
an
ci
n
g
d
ia
g
n
o
s
is
[
2
]
,
[
3
]
.
Gen
etic
alg
o
r
it
h
m
s
r
ef
in
in
g
m
o
d
els
lik
e
DC
GAN
s
with
C
NN
ar
ch
itectu
r
es
(
e.
g
.
,
VGG
-
1
6
)
h
av
e
f
u
r
th
e
r
im
p
r
o
v
e
d
p
n
eu
m
o
n
ia
ca
teg
o
r
izatio
n
[
4
]
.
Den
s
eNe
t
-
1
2
1
h
as
b
ee
n
ef
f
ec
tiv
e
in
p
ed
iatr
ic
p
n
eu
m
o
n
ia
class
if
icatio
n
,
ev
en
with
i
m
b
alan
ce
d
d
atasets
[
5
]
,
[
6
]
.
Sy
s
tem
atic
r
ev
iews
h
av
e
s
u
p
p
o
r
ted
p
n
eu
m
o
n
ia
d
i
ag
n
o
s
is
in
r
e
g
io
n
s
with
h
ig
h
c
o
m
o
r
b
i
d
ities
,
lik
e
I
n
d
ia
[
7
]
,
w
h
ile
m
o
d
els
lik
e
th
e
L
AC
E
in
d
ex
p
r
e
d
ict
3
0
-
d
ay
h
o
s
p
ital r
ea
d
m
is
s
io
n
s
f
o
r
p
n
eu
m
o
n
ia
[
8
]
,
[
9
]
.
T
h
e
co
r
o
n
a
v
ir
u
s
d
is
ea
s
e
2
0
1
9
(
C
OVI
D
-
19
)
p
a
n
d
em
ic
h
as
a
m
p
lifie
d
th
e
im
p
o
r
tan
ce
o
f
d
e
ep
lear
n
in
g
in
p
n
eu
m
o
n
ia
d
etec
tio
n
.
E
m
er
g
in
g
tec
h
n
iq
u
es,
in
clu
d
in
g
ex
p
lain
ab
le
m
o
d
els
an
d
f
u
zz
y
-
en
h
a
n
ce
d
d
ee
p
lear
n
in
g
,
h
a
v
e
s
h
o
wn
p
r
o
m
is
e
in
ea
r
ly
p
n
eu
m
o
n
ia
p
r
e
d
ictio
n
,
esp
ec
ially
in
C
OVI
D
-
1
9
ca
s
es
[
1
0
]
,
[
1
1
]
.
Gr
ap
h
-
b
ased
d
ee
p
lear
n
in
g
w
ith
d
if
f
u
s
io
n
p
s
eu
d
o
-
lab
elin
g
h
as
en
h
an
ce
d
ex
p
lain
a
b
ilit
y
in
d
iag
n
o
s
es
[
1
2
]
,
[
1
3
]
,
an
d
ViT
-
b
ased
m
o
d
el
s
f
o
r
C
OVI
D
-
1
9
s
cr
ee
n
i
n
g
p
r
o
v
i
d
e
s
tr
o
n
g
d
iag
n
o
s
tic
ju
s
tific
atio
n
s
[
1
4
]
.
I
n
ter
p
r
etab
le
p
n
eu
m
o
n
ia
alg
o
r
ith
m
s
th
at
in
teg
r
ate
m
u
lti
s
o
u
r
ce
d
ata
h
a
v
e
b
ee
n
d
ev
elo
p
ed
[
1
5
]
.
Oth
e
r
d
iag
n
o
s
tic
ap
p
r
o
ac
h
es,
s
u
c
h
as
an
tig
en
an
d
n
u
cleic
ac
i
d
am
p
lific
atio
n
test
s
,
h
av
e
also
co
n
tr
ib
u
ted
to
p
n
eu
m
o
n
ia
r
esear
c
h
[
1
6
]
,
[
1
7
]
.
C
NNs
with
L
I
ME
h
a
v
e
im
p
r
o
v
ed
th
e
in
ter
p
r
etab
ilit
y
o
f
p
n
eu
m
o
n
ia
d
iag
n
o
s
es
[
1
8
]
,
an
d
s
elf
-
s
u
p
e
r
v
is
ed
lear
n
in
g
h
as
en
h
an
ce
d
g
en
e
r
aliza
b
ilit
y
[
1
9
]
.
Ps
eu
d
o
-
lab
elin
g
h
as
f
u
r
th
er
r
ef
i
n
e
d
C
OVI
D
-
1
9
d
iag
n
o
s
is
ac
cu
r
a
cy
[
2
0
]
.
T
h
e
W
o
r
l
d
Hea
lth
Or
g
an
izatio
n
h
as
s
tr
ess
ed
th
e
n
ee
d
to
im
p
r
o
v
e
d
etec
tio
n
p
r
o
to
co
ls
d
u
r
in
g
th
e
p
an
d
em
ic
[
2
1
]
.
Dee
p
r
esid
u
a
l
n
etwo
r
k
s
co
m
b
i
n
ed
with
tr
a
n
s
f
er
lear
n
in
g
h
av
e
o
p
tim
ized
p
e
d
iatr
ic
p
n
e
u
m
o
n
i
a
d
iag
n
o
s
is
[
2
2
]
.
GANs
ar
e
in
cr
ea
s
in
g
ly
u
s
ed
in
m
ed
ical
im
ag
e
an
aly
s
is
,
in
clu
d
in
g
b
o
n
e
s
u
r
f
ac
e
s
eg
m
en
tatio
n
an
d
b
r
ea
s
t
u
ltra
s
o
u
n
d
im
ag
i
n
g
[
2
3
]
,
[
2
4
]
.
GAN
-
b
ased
a
u
g
m
e
n
tatio
n
h
as
h
elp
ed
o
v
e
r
co
m
e
d
ata
s
h
o
r
tag
es
in
p
n
eu
m
o
n
ia
d
iag
n
o
s
is
[
2
5
]
,
[
2
6
]
an
d
h
as
in
cr
ea
s
ed
m
o
d
el
g
en
er
aliza
b
ilit
y
in
o
th
er
a
r
ea
s
,
s
u
ch
as
h
ip
f
r
ac
tu
r
e
d
etec
tio
n
an
d
p
r
o
s
tate
ca
n
ce
r
g
r
ad
i
n
g
[
2
7
]
,
[
2
8
]
.
Dee
p
lear
n
in
g
m
o
d
els
lik
e
C
h
eXN
eXt
h
av
e
d
e
m
o
n
s
tr
ated
ef
f
ec
tiv
en
ess
in
d
iag
n
o
s
in
g
ch
est
illn
ess
es,
in
clu
d
in
g
p
n
eu
m
o
n
ia,
co
m
p
ar
ed
to
r
ad
io
lo
g
is
ts
[
2
9
]
.
T
h
e
av
ailab
ilit
y
o
f
o
p
en
c
h
est
X
-
r
ay
d
atasets
h
as
ac
ce
ler
ated
r
esear
ch
b
y
p
r
o
v
id
in
g
cr
itical
tr
ain
in
g
d
ata
f
o
r
m
o
d
els
[
3
0
]
.
C
NNs
an
d
GANs
ar
e
p
ar
ticu
lar
ly
u
s
ef
u
l
f
o
r
p
n
eu
m
o
n
ia
d
ia
g
n
o
s
is
,
esp
ec
ially
in
d
ata
-
lim
ite
d
s
ce
n
ar
io
s
[
3
1
]
,
[
3
2
]
.
Fin
e
-
t
u
n
i
n
g
p
r
e
-
t
r
ain
ed
C
NN
m
o
d
els
h
as
en
ab
led
ac
cu
r
ate
lo
ca
lizatio
n
an
d
class
if
icatio
n
o
f
lu
n
g
illn
ess
es
in
ch
est
X
-
r
a
y
s
[
3
3
]
.
AI
-
b
ased
s
cr
ee
n
in
g
s
y
s
tem
s
h
av
e
p
la
y
ed
a
cr
u
cial
r
o
le
in
im
p
r
o
v
i
n
g
th
e
ac
cu
r
ac
y
an
d
s
p
ee
d
o
f
p
n
eu
m
o
n
ia
d
iag
n
o
s
is
d
u
r
in
g
th
e
C
OVI
D
-
1
9
p
an
d
em
ic
[
3
4
]
.
T
h
e
r
o
le
o
f
AI
ex
ten
d
s
b
ey
o
n
d
p
n
e
u
m
o
n
ia,
in
f
lu
e
n
ci
n
g
d
iag
n
o
s
tics
in
o
th
er
d
is
ea
s
es,
s
u
ch
as
ea
r
ly
lu
n
g
ca
n
ce
r
d
etec
tio
n
[
3
5
]
,
[
3
6
]
.
Pn
eu
m
o
n
ia
d
ia
g
n
o
s
is
s
y
s
tem
s
b
ased
o
n
C
NNs
h
av
e
s
u
cc
ess
f
u
lly
p
r
o
ce
s
s
ed
lar
g
e
X
-
r
a
y
d
atasets
[
3
7
]
,
[
3
8
]
.
Ad
v
an
ce
s
in
co
m
p
u
tatio
n
al
al
g
o
r
ith
m
s
co
n
tin
u
e
to
d
r
iv
e
th
e
ev
o
lu
tio
n
o
f
AI
-
d
r
iv
en
m
e
d
ic
al
im
ag
e
d
iag
n
o
s
is
[
3
9
]
,
[
4
0
]
,
an
d
co
m
p
ar
is
o
n
s
b
etwe
en
C
T
s
ca
n
s
an
d
PC
R
test
s
h
av
e
h
ig
h
li
g
h
ted
th
e
im
p
o
r
tan
ce
o
f
p
r
o
m
p
t
C
OVI
D
-
1
9
p
n
eu
m
o
n
ia
d
ia
g
n
o
s
is
[
4
1
]
.
3.
M
E
T
H
O
D
T
h
e
m
e
t
h
o
d
s
e
ct
i
o
n
b
e
g
i
n
s
w
ith
a
n
o
v
e
r
v
i
e
w
o
f
t
h
e
d
at
a
s
e
t
s
u
s
e
d
f
o
r
p
n
e
u
m
o
n
i
a
d
e
t
e
c
ti
o
n
,
a
s
d
e
t
ai
l
e
d
i
n
T
a
b
l
e
1
.
T
h
es
e
p
u
b
l
i
cl
y
av
a
i
l
a
b
l
e
d
at
a
s
et
s
i
n
c
l
u
d
e
a
v
ar
i
e
t
y
o
f
c
h
e
s
t
X
-
r
a
y
i
m
a
g
e
s
la
b
e
l
l
e
d
t
o
i
d
e
n
t
i
f
y
p
n
e
u
m
o
n
i
a
,
w
i
t
h
d
e
t
ai
ls
a
b
o
u
t
t
h
e
i
r
s
i
z
e
,
s
o
u
r
c
e
,
a
n
d
s
p
ec
i
f
i
c
u
s
e
c
as
e
s
p
r
o
v
i
d
e
d
i
n
t
h
e
t
a
b
l
e
.
T
h
e
p
r
e
p
r
o
c
e
s
s
i
n
g
t
e
c
h
n
i
q
u
e
s
,
o
u
t
l
i
n
e
d
i
n
T
a
b
l
e
2
,
d
e
s
c
r
i
b
e
s
t
e
p
s
t
a
k
e
n
t
o
p
r
e
p
a
r
e
t
h
e
m
e
d
i
c
a
l
i
m
a
g
e
s
f
o
r
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
,
s
u
c
h
as
r
es
i
zi
n
g
t
o
a
c
o
n
s
i
s
te
n
t
i
m
a
g
e
s
i
z
e
,
n
o
r
m
a
li
z
i
n
g
p
i
x
el
v
a
l
u
es
,
a
n
d
a
u
g
m
e
n
t
i
n
g
t
h
e
d
a
t
a
s
et
t
o
i
m
p
r
o
v
e
m
o
d
e
l
g
e
n
e
r
a
l
i
za
t
i
o
n
.
F
i
n
a
ll
y
,
T
a
b
l
e
3
p
r
es
e
n
ts
t
h
e
d
e
e
p
le
a
r
n
i
n
g
a
r
c
h
i
t
e
ct
u
r
e
s
e
m
p
l
o
y
e
d
t
o
c
l
as
s
i
f
y
p
n
e
u
m
o
n
i
a
f
r
o
m
c
h
e
s
t
X
-
r
a
y
s
,
i
n
c
l
u
d
i
n
g
ad
v
a
n
c
e
d
m
o
d
e
l
s
l
i
k
e
V
i
T
,
V
GG
-
1
6
,
a
n
d
R
e
s
N
e
t
-
5
0
,
e
a
c
h
c
h
o
s
e
n
f
o
r
t
h
e
i
r
p
r
o
v
e
n
p
e
r
f
o
r
m
a
n
c
e
i
n
i
m
a
g
e
c
l
as
s
i
f
ic
a
t
i
o
n
t
as
k
s
.
T
h
e
s
e
m
o
d
e
ls
ar
e
t
r
a
i
n
e
d
u
s
i
n
g
t
h
e
p
r
o
c
e
s
s
ed
d
a
t
a
s
et
s
a
n
d
a
r
e
e
v
a
l
u
a
t
e
d
b
a
s
e
d
o
n
t
h
e
i
r
a
c
c
u
r
ac
y
a
n
d
a
b
i
l
i
t
y
t
o
d
e
te
c
t
p
n
e
u
m
o
n
i
a
f
r
o
m
t
h
e
X
-
r
a
y
i
m
a
g
es
.
T
ab
le
1
.
L
is
t o
f
d
atasets
D
a
t
a
s
e
t
N
u
mb
e
r
o
f
I
mag
e
s
/
P
a
t
i
e
n
t
s
C
a
t
e
g
o
r
i
e
s
N
I
H
d
a
t
a
se
t
[
3
8
]
1
0
8
,
9
4
8
c
h
e
s
t
r
a
d
i
o
g
r
a
p
h
s
f
r
o
m
3
2
,
7
1
7
p
a
t
i
e
n
t
s
8
C
H
E
d
a
t
a
se
t
[
3
9
]
2
2
4
,
3
1
6
c
h
e
s
t
X
-
r
a
y
s fr
o
m
6
5
,
2
4
0
p
a
t
i
e
n
t
s
14
K
A
G
d
a
t
a
se
t
[
4
0
]
5
,
8
6
3
c
h
e
st
X
-
r
a
y
i
m
a
g
e
s (p
e
d
i
a
t
r
i
c
p
a
t
i
e
n
t
s
o
n
l
y
)
2
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
.
4
,
Au
g
u
s
t
20
25
:
3
9
9
6
-
4003
3998
T
ab
le
2
.
L
is
t o
f
p
r
e
-
p
r
o
ce
s
s
m
eth
o
d
s
M
e
t
h
o
d
M
e
t
h
o
d
s/
D
e
t
a
i
l
s
R
e
si
z
e
[
2
]
,
[
3
]
,
[
1
3
]
,
[
1
4
]
,
[
1
6
]
,
[
1
7
]
,
[
1
9
]
,
[
2
1
]
,
[
2
4
]
-
N
e
a
r
e
s
t
-
n
e
i
g
h
b
o
r
i
n
t
e
r
p
o
l
a
t
i
o
n
:
U
s
e
s
t
h
e
c
l
o
s
e
st
p
i
x
e
l
t
o
t
h
e
n
e
w
p
i
x
e
l
l
o
c
a
t
i
o
n
(
f
a
st
b
u
t
may
a
p
p
e
a
r
b
l
o
c
k
y
)
.
-
B
i
l
i
n
e
a
r
i
n
t
e
r
p
o
l
a
t
i
o
n
:
A
v
e
r
a
g
e
s
t
h
e
f
o
u
r
c
l
o
ses
t
p
i
x
e
l
s f
o
r
a
smo
o
t
h
e
r
r
e
s
u
l
t
.
-
B
i
c
u
b
i
c
i
n
t
e
r
p
o
l
a
t
i
o
n
:
U
ses
c
u
b
i
c
p
o
l
y
n
o
m
i
a
l
s
f
o
r
s
mo
o
t
h
e
r
i
ma
g
e
s
b
u
t
i
s
c
o
m
p
u
t
a
t
i
o
n
a
l
l
y
e
x
p
e
n
si
v
e
.
-
A
sp
e
c
t
r
a
t
i
o
:
P
r
e
s
e
r
v
e
s
a
s
p
e
c
t
r
a
t
i
o
d
u
r
i
n
g
r
e
si
z
i
n
g
t
o
a
v
o
i
d
d
i
s
t
o
r
t
i
o
n
.
-
P
a
d
d
i
n
g
:
A
d
d
s
b
o
r
d
e
r
s
t
o
ma
i
n
t
a
i
n
a
sp
e
c
t
r
a
t
i
o
d
u
r
i
n
g
r
e
si
z
i
n
g
.
N
o
r
mal
i
z
a
t
i
o
n
[
1
]
,
[
2
]
,
[
4
]
,
[
6
]
,
[
1
8
]
,
[
2
2
]
-
M
i
n
-
m
a
x
n
o
r
ma
l
i
z
a
t
i
o
n
:
S
c
a
l
e
s
p
i
x
e
l
v
a
l
u
e
s
t
o
a
sp
e
c
i
f
i
e
d
r
a
n
g
e
,
u
s
u
a
l
l
y
[
0
,
1
]
u
si
n
g
t
h
e
f
o
r
mu
l
a
:
n
o
rm
a
l
i
ze
d
_
v
a
l
u
e
=
(
p
i
x
e
l
_
v
a
l
u
e
-
m
i
n
_
v
a
l
u
e
)
/
(
m
a
x
_
v
a
l
u
e
-
m
i
n
_
v
a
l
u
e
)
.
-
Z
-
sco
r
e
n
o
r
m
a
l
i
z
a
t
i
o
n
:
A
d
j
u
st
s
p
i
x
e
l
v
a
l
u
e
s
t
o
h
a
v
e
a
m
e
a
n
o
f
0
a
n
d
s
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
o
f
1
u
si
n
g
:
n
o
rm
a
l
i
ze
d
_
v
a
l
u
e
=
(
p
i
x
e
l
_
v
a
l
u
e
-
m
e
a
n
)
/
(
st
a
n
d
a
r
d
_
d
e
v
i
a
t
i
o
n
)
.
-
S
t
a
n
d
a
r
d
i
z
a
t
i
o
n
:
A
s
u
b
s
e
t
o
f
n
o
r
ma
l
i
z
a
t
i
o
n
,
i
t
r
e
sc
a
l
e
s
p
i
x
e
l
v
a
l
u
e
s
t
o
h
a
v
e
a
me
a
n
o
f
0
a
n
d
v
a
r
i
a
n
c
e
o
f
1
u
s
i
n
g
:
st
a
n
d
a
r
d
i
z
e
d
_
v
a
l
u
e
=
(
p
i
x
e
l
_
v
a
l
u
e
-
m
e
a
n
)
/
(
st
a
n
d
a
r
d
_
d
e
v
i
a
t
i
o
n
)
.
T
ab
le
3
.
L
is
t o
f
m
o
d
el
M
e
t
h
o
d
D
e
scri
p
t
i
o
n
V
i
si
o
n
t
r
a
n
sf
o
r
m
e
r
(
V
i
T)
[
1
]
A
t
r
a
n
sf
o
r
m
e
r
-
b
a
s
e
d
a
r
c
h
i
t
e
c
t
u
r
e
f
o
r
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
t
h
a
t
u
ses
se
l
f
-
a
t
t
e
n
t
i
o
n
me
c
h
a
n
i
sms
i
n
s
t
e
a
d
o
f
C
N
N
s.
D
i
v
i
d
e
s i
ma
g
e
s
i
n
t
o
f
i
x
e
d
-
si
z
e
p
a
t
c
h
e
s,
p
r
o
c
e
sses
t
h
e
m
a
s
t
o
k
e
n
s
,
a
n
d
c
a
p
t
u
r
e
s g
l
o
b
a
l
d
e
p
e
n
d
e
n
c
i
e
s.
VGG
-
16
[
4
]
A
d
e
e
p
C
N
N
a
r
c
h
i
t
e
c
t
u
r
e
w
i
t
h
1
6
w
e
i
g
h
t
l
a
y
e
r
s
:
1
3
c
o
n
v
o
l
u
t
i
o
n
a
l
a
n
d
3
f
u
l
l
y
c
o
n
n
e
c
t
e
d
l
a
y
e
r
s.
I
t
u
s
e
s
sm
a
l
l
3
x
3
f
i
l
t
e
r
s t
o
e
x
t
r
a
c
t
f
i
n
e
d
e
t
a
i
l
s,
w
i
t
h
ma
x
-
p
o
o
l
i
n
g
l
a
y
e
r
s
f
o
r
s
p
a
t
i
a
l
d
o
w
n
s
a
m
p
l
i
n
g
.
D
e
n
seN
e
t
-
1
2
1
[
6
]
A
C
N
N
w
h
e
r
e
e
a
c
h
l
a
y
e
r
i
s
c
o
n
n
e
c
t
e
d
t
o
a
l
l
p
r
e
v
i
o
u
s
l
a
y
e
r
s.
R
e
d
u
c
e
s
f
e
a
t
u
r
e
r
e
d
u
n
d
a
n
c
y
a
n
d
e
n
h
a
n
c
e
s
f
e
a
t
u
r
e
r
e
u
se
.
I
n
c
l
u
d
e
s f
o
u
r
d
e
n
se
b
l
o
c
k
s
a
n
d
t
r
a
n
s
i
t
i
o
n
l
a
y
e
r
s
f
o
r
d
o
w
n
s
a
mp
l
i
n
g
.
R
e
sN
e
t
-
5
0
[
2
2
]
A
5
0
-
l
a
y
e
r
a
r
c
h
i
t
e
c
t
u
r
e
u
si
n
g
r
e
s
i
d
u
a
l
c
o
n
n
e
c
t
i
o
n
s
(
sk
i
p
c
o
n
n
e
c
t
i
o
n
s)
t
o
c
o
mb
a
t
v
a
n
i
sh
i
n
g
g
r
a
d
i
e
n
t
s
.
T
h
e
n
e
t
w
o
r
k
l
e
a
r
n
s res
i
d
u
a
l
m
a
p
p
i
n
g
s
i
n
st
e
a
d
o
f
d
i
r
e
c
t
t
r
a
n
sf
o
r
ma
t
i
o
n
s.
I
n
c
e
p
t
i
o
n
N
e
t
V
3
[
3
8
]
A
n
a
d
v
a
n
c
e
d
v
e
r
s
i
o
n
o
f
t
h
e
I
n
c
e
p
t
i
o
n
a
r
c
h
i
t
e
c
t
u
r
e
w
i
t
h
m
u
l
t
i
p
l
e
f
i
l
t
e
r
si
z
e
s
i
n
a
si
n
g
l
e
l
a
y
e
r
.
U
ses
i
n
c
e
p
t
i
o
n
mo
d
u
l
e
s
t
o
c
a
p
t
u
r
e
f
e
a
t
u
r
e
s
a
t
d
i
f
f
e
r
e
n
t
sca
l
e
s
a
n
d
f
a
c
t
o
r
i
z
e
d
c
o
n
v
o
l
u
t
i
o
n
s
t
o
r
e
d
u
c
e
c
o
m
p
u
t
a
t
i
o
n
a
l
c
o
mp
l
e
x
i
t
y
.
F
i
n
e
-
Tu
n
i
n
g
[
1
]
,
[
4
]
,
[
6
]
,
[
2
2
]
,
[
3
8
]
I
n
v
o
l
v
e
s
a
p
p
l
y
i
n
g
a
p
r
e
-
t
r
a
i
n
e
d
m
o
d
e
l
t
o
a
n
e
w
t
a
s
k
b
y
c
o
n
t
i
n
u
i
n
g
t
r
a
i
n
i
n
g
o
n
a
d
i
f
f
e
r
e
n
t
d
a
t
a
se
t
,
t
y
p
i
c
a
l
l
y
w
i
t
h
a
smal
l
e
r
l
e
a
r
n
i
n
g
r
a
t
e
.
H
e
l
p
s
a
d
a
p
t
t
h
e
mo
d
e
l
t
o
n
e
w
t
a
s
k
s w
i
t
h
o
u
t
r
e
t
r
a
i
n
i
n
g
f
r
o
m s
c
r
a
t
c
h
.
4.
P
RO
P
O
SE
D
SYS
T
E
M
Fig
u
r
e
1
d
em
o
n
s
tr
ates
a
p
r
o
p
o
s
ed
th
r
ee
-
s
tag
e
p
r
o
ce
d
u
r
e
f
o
r
tr
ain
in
g
,
test
in
g
,
an
d
ass
ess
in
g
a
m
o
d
el
.
T
h
is
m
o
d
el
is
lik
ely
to
b
e
u
s
ed
f
o
r
a
m
ed
ical
im
ag
in
g
i
m
ag
e
class
if
icatio
n
p
r
o
b
lem
with
th
e
f
o
llo
win
g
class
es
:
n
o
r
m
al,
v
ir
al,
b
ac
ter
i
a,
an
d
f
u
n
g
al
.
T
h
e
f
o
llo
win
g
i
s
an
ex
h
au
s
tiv
e
d
escr
ip
tio
n
o
f
th
e
s
tep
s
an
d
th
eir
co
n
s
titu
en
t p
ar
ts
:
Fig
u
r
e
1
.
Pro
p
o
s
ed
s
y
s
tem
f
lo
w
d
iag
r
am
Stag
e
1
d
ata
in
itializatio
n
an
d
p
r
e
-
p
r
o
ce
s
s
in
g
:
T
h
is
s
tag
e
in
v
o
lv
es
co
m
b
in
in
g
im
ag
es
f
r
o
m
v
ar
io
u
s
s
o
u
r
ce
s
in
to
a
s
in
g
le
d
ataset,
s
o
r
ted
in
to
ca
te
g
o
r
ies
lik
e
n
o
r
m
al,
v
i
r
al,
b
ac
te
r
ial,
an
d
f
u
n
g
al.
T
h
e
d
ata
u
n
d
er
g
o
es
p
r
e
-
p
r
o
ce
s
s
in
g
,
in
c
lu
d
in
g
r
esizin
g
im
ag
es
to
f
it
t
h
e
ViT
m
o
d
el
an
d
n
o
r
m
alizin
g
p
ix
el
v
al
u
es
to
a
s
tan
d
ar
d
r
an
g
e.
Fin
ally
,
th
e
d
ataset
is
s
p
lit
in
to
tr
ain
in
g
(
8
0
%)
an
d
test
in
g
(
2
0
%)
s
ets
f
o
r
m
o
d
el
tr
ain
in
g
a
n
d
ev
alu
atio
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
Mu
lti
-
cla
s
s
p
n
eu
mo
n
ia
d
etec
t
io
n
u
s
in
g
fin
e
-
tu
n
ed
visi
o
n
tr
a
n
s
fo
r
mer m
o
d
el
(
K
h
u
s
h
b
o
o
Tr
ived
i
)
3999
Stag
e
2
m
o
d
el
t
u
n
in
g
an
d
tr
a
in
in
g
:
I
n
th
is
s
tag
e,
th
e
ViT
m
o
d
el
is
f
i
n
e
-
tu
n
e
d
u
s
in
g
a
p
r
e
-
tr
ain
ed
m
o
d
el
an
d
m
e
d
ical
im
ag
e
d
a
ta.
T
h
e
m
o
d
el
p
r
o
ce
s
s
es
im
a
g
es
b
y
d
iv
id
in
g
th
em
in
to
3
2
×
3
2
p
atch
es.
T
h
e
lear
n
in
g
r
ate
is
s
et
to
1
e
-
3
,
a
n
d
th
e
Ad
am
o
p
tim
izer
a
d
ju
s
ts
weig
h
ts
d
u
r
i
n
g
tr
ain
in
g
.
T
h
e
ca
teg
o
r
ical
cr
o
s
s
-
en
tr
o
p
y
lo
s
s
f
u
n
ctio
n
is
u
s
ed
,
an
d
ea
r
ly
s
to
p
p
in
g
p
r
ev
e
n
t
s
o
v
er
f
itti
n
g
b
y
h
altin
g
tr
ai
n
in
g
if
p
e
r
f
o
r
m
an
ce
p
latea
u
s
b
ef
o
r
e
5
0
e
p
o
ch
s
.
Stag
e
3
m
o
d
el
test
in
g
an
d
ev
a
lu
atio
n
:
T
h
e
tr
ain
ed
m
o
d
el
is
ev
alu
ated
u
s
in
g
th
e
2
0
%
test
s
et,
wh
er
e
its
ab
ilit
y
to
g
en
er
alize
to
u
n
s
ee
n
d
ata
is
as
s
es
s
ed
.
T
h
e
m
o
d
el
class
if
ies
im
ag
es
as
n
o
r
m
al,
v
ir
al,
b
ac
ter
ial,
o
r
f
u
n
g
al.
Per
f
o
r
m
an
ce
is
ev
alu
a
ted
u
s
in
g
m
etr
ics
s
u
ch
as
ac
c
u
r
ac
y
(
AC
C
)
,
p
r
ec
is
io
n
(
P),
r
ec
all
(
R
)
,
an
d
F1
-
s
co
r
e
to
d
eter
m
in
e
class
if
icati
o
n
ac
cu
r
ac
y
an
d
m
o
d
el
ef
f
ec
ti
v
en
ess
.
5.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
h
i
g
h
lig
h
t
th
e
p
e
r
f
o
r
m
a
n
ce
o
f
t
h
e
p
r
o
p
o
s
ed
ViT
m
o
d
el,
f
in
e
-
tu
n
ed
f
o
r
p
n
eu
m
o
n
ia
class
if
icatio
n
.
A
c
o
n
cise
co
m
p
a
r
is
o
n
with
c
u
r
r
e
n
t
tr
an
s
f
er
lea
r
n
in
g
m
o
d
els,
s
u
p
p
o
r
ted
b
y
d
etailed
tab
les
an
d
f
ig
u
r
es,
d
e
m
o
n
s
tr
at
es
th
e
m
o
d
el'
s
ef
f
ec
tiv
en
ess
a
cr
o
s
s
f
o
u
r
p
n
eu
m
o
n
ia
ca
teg
o
r
ies.
T
h
e
r
esu
lts
ar
e
d
is
cu
s
s
ed
in
th
e
co
n
tex
t
o
f
th
e
s
tu
d
y
'
s
o
b
jectiv
es,
ex
is
t
in
g
h
y
p
o
th
eses
,
an
d
r
elate
d
r
esear
ch
wh
ile
ad
d
r
ess
in
g
p
o
ten
tial
in
ter
p
r
etatio
n
s
an
d
lim
itatio
n
s
.
Fig
u
r
e
2
s
u
m
m
ar
iz
es
th
e
d
ataset
d
is
tr
ib
u
tio
n
ac
r
o
s
s
th
e
f
o
u
r
class
es:
1
4
8
im
ag
es
f
o
r
v
ir
a
l
p
n
eu
m
o
n
ia,
2
4
2
f
o
r
b
ac
ter
ial,
2
3
f
o
r
f
u
n
g
al,
an
d
2
3
2
f
o
r
n
o
r
m
al
ca
s
es.
T
h
is
im
b
alan
ce
h
ig
h
lig
h
ts
th
e
ch
allen
g
es
in
a
ch
iev
in
g
r
o
b
u
s
t
p
er
f
o
r
m
an
ce
ac
r
o
s
s
all
ca
teg
o
r
ies,
p
ar
ticu
la
r
ly
f
o
r
t
h
e
m
in
o
r
ity
class
(
f
u
n
g
al)
.
Fig
u
r
e
3
p
r
o
v
id
es
an
o
v
er
v
iew
o
f
th
e
f
in
e
-
tu
n
ed
ViT
a
r
ch
itectu
r
e.
T
h
e
m
o
d
el
c
o
m
p
r
is
e
s
o
v
er
8
5
m
illi
o
n
p
ar
am
ete
r
s
,
with
o
n
ly
th
e
f
i
n
al
lin
ea
r
lay
er
(
3
,
0
7
6
tr
ain
ab
le
p
a
r
am
eter
s
)
o
p
tim
iz
ed
d
u
r
in
g
tr
ain
in
g
.
T
h
is
d
esig
n
lev
er
ag
es
th
e
p
r
e
-
tr
ain
ed
weig
h
ts
o
f
th
e
f
r
o
ze
n
l
ay
er
s
wh
ile
f
in
e
-
tu
n
i
n
g
th
e
o
u
tp
u
t
lay
er
to
ad
a
p
t
to
th
e
p
n
e
u
m
o
n
ia
class
if
icatio
n
task
.
Fig
u
r
e
2
.
Data
s
et
r
ea
d
in
g
Fig
u
r
e
3
.
Fin
e
-
tu
n
e
ViT
ar
c
h
itectu
r
e
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
.
4
,
Au
g
u
s
t
20
25
:
3
9
9
6
-
4003
4000
Fig
u
r
e
4
d
ep
icts
th
e
ac
cu
r
ac
y
an
d
lo
s
s
cu
r
v
es
o
v
e
r
5
0
tr
ain
in
g
iter
atio
n
s
.
B
o
th
tr
ai
n
in
g
a
n
d
test
in
g
ac
cu
r
ac
ies
co
n
v
er
g
e
at
ap
p
r
o
x
im
ately
0
.
9
8
,
with
s
tead
ily
d
ec
r
ea
s
in
g
lo
s
s
v
alu
es
an
d
clo
s
ely
alig
n
ed
cu
r
v
es
f
o
r
tr
ain
in
g
an
d
test
in
g
.
T
h
ese
r
esu
lts
in
d
icate
s
tr
o
n
g
m
o
d
el
p
er
f
o
r
m
a
n
ce
with
o
u
t
o
v
er
f
itti
n
g
.
Fig
u
r
e
4
.
Fin
e
-
tu
n
e
ViT
ac
cu
r
ac
y
/lo
s
s
p
lo
ts
Fig
u
r
e
5
p
r
esen
ts
th
e
co
n
f
u
s
io
n
m
atr
ix
an
d
class
if
icatio
n
r
ep
o
r
t,
s
h
o
wca
s
in
g
th
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
ac
r
o
s
s
th
e
f
o
u
r
p
n
e
u
m
o
n
ia
class
es.
Hig
h
d
i
ag
o
n
al
v
alu
es
in
th
e
c
o
n
f
u
s
io
n
m
atr
i
x
in
d
icate
ac
cu
r
ate
p
r
e
d
ictio
n
s
f
o
r
all
ca
t
eg
o
r
ies.
T
h
e
class
if
icatio
n
r
ep
o
r
t
f
u
r
th
er
co
n
f
i
r
m
s
th
ese
r
e
s
u
lts
,
with
an
o
v
er
all
ac
cu
r
ac
y
o
f
0
.
9
8
an
d
h
ig
h
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
es
f
o
r
all
class
es.
No
tab
ly
,
f
u
n
g
al
p
n
eu
m
o
n
ia
p
r
ed
ictio
n
s
ac
h
iev
e
f
lawless
s
co
r
es,
u
n
d
er
s
co
r
in
g
th
e
m
o
d
el'
s
ab
ilit
y
to
h
an
d
le
im
b
alan
ce
d
d
atasets
ef
f
ec
tiv
ely
.
T
ab
le
4
co
m
p
ar
es
t
h
e
p
r
o
p
o
s
ed
m
o
d
el'
s
p
er
f
o
r
m
an
ce
wi
th
o
th
e
r
d
ee
p
-
lear
n
i
n
g
ap
p
r
o
ac
h
es
f
o
r
p
n
eu
m
o
n
ia
d
etec
tio
n
.
W
h
ile
m
o
s
t
p
r
io
r
s
tu
d
ies
ad
d
r
ess
o
n
l
y
two
-
o
r
th
r
ee
-
class
p
r
o
b
lem
s
,
th
e
f
in
e
-
tu
n
ed
ViT
ac
h
iev
es
9
8
%
ac
c
u
r
ac
y
ac
r
o
s
s
f
o
u
r
class
es,
m
atch
in
g
o
r
ex
c
ee
d
in
g
th
e
p
er
f
o
r
m
an
ce
o
f
e
x
is
tin
g
m
eth
o
d
s
.
T
h
is
d
em
o
n
s
tr
ates th
e
ViT
'
s
ca
p
ab
ilit
y
to
g
en
er
alize
a
n
d
class
if
y
p
n
eu
m
o
n
ia
m
o
r
e
co
m
p
r
eh
e
n
s
iv
ely
.
Fig
u
r
e
5
.
C
o
n
f
u
s
io
n
m
atr
i
x
an
d
class
if
icatio
n
r
ep
o
r
t
T
ab
le
4
.
Ass
ess
m
en
t o
f
d
ee
p
l
ea
r
n
in
g
s
tr
ateg
ies
M
o
d
e
l
A
C
C
(
%)
P
(
%)
R
(
%)
F
1
(
%)
S
i
n
g
h
e
t
a
l
.
[
1
]
[2
-
c
l
a
ss]
0
.
9
7
0
.
9
6
0
.
9
7
0
.
9
7
A
l
i
e
t
a
l
.
[
2
]
[3
-
c
l
a
ss]
0
.
9
5
0
.
9
4
0
.
9
5
0
.
9
5
G
u
a
n
d
L
e
e
[
3
]
[2
-
c
l
a
ss]
0
.
9
8
0
.
9
7
0
.
9
8
0
.
9
8
P
u
t
r
i
a
n
d
A
l
M
a
k
i
[
4
]
[3
-
c
l
a
ss]
0
.
9
6
0
.
9
5
0
.
9
6
0
.
9
6
A
sn
a
k
e
e
t
a
l
.
[
5
]
[2
-
c
l
a
ss]
0
.
9
4
0
.
9
3
0
.
9
4
0
.
9
4
P
r
o
p
o
se
d
f
i
n
e
-
t
u
n
e
V
i
T
[4
-
c
l
a
ss]
0
.
9
8
0
.
9
8
0
.
9
8
0
.
9
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:
2088
-
8
7
0
8
Mu
lti
-
cla
s
s
p
n
eu
mo
n
ia
d
etec
t
io
n
u
s
in
g
fin
e
-
tu
n
ed
visi
o
n
tr
a
n
s
fo
r
mer m
o
d
el
(
K
h
u
s
h
b
o
o
Tr
ived
i
)
4001
6.
CO
NCLU
SI
O
N
T
h
is
r
esear
ch
d
em
o
n
s
tr
ated
t
h
at
th
e
f
in
e
-
t
u
n
ed
ViT
m
o
d
el
ac
h
iev
ed
a
n
im
p
r
ess
iv
e
9
8
%
ac
cu
r
ac
y
,
alo
n
g
s
id
e
9
8
%
p
r
ec
is
io
n
,
r
ec
a
ll,
an
d
F1
-
s
co
r
es,
ac
r
o
s
s
th
e
f
o
u
r
p
n
eu
m
o
n
ia
class
es
—
n
o
r
m
al,
f
u
n
g
al,
b
ac
ter
ial,
an
d
v
ir
al.
T
h
e
ViT
m
o
d
el’
s
a
b
ilit
y
to
ef
f
ec
tiv
ely
d
if
f
er
e
n
tiate
b
etwe
en
v
a
r
io
u
s
f
o
r
m
s
o
f
p
n
eu
m
o
n
ia
h
ig
h
lig
h
ts
its
im
p
r
o
v
ed
ca
p
ac
ity
to
ca
p
tu
r
e
co
m
p
lex
p
atter
n
s
in
ch
est
X
-
r
ay
im
a
g
es,
m
ad
e
p
o
s
s
ib
le
b
y
its
s
elf
-
atten
tio
n
m
ec
h
an
is
m
.
T
h
ese
f
in
d
in
g
s
s
u
g
g
est
th
at
th
e
f
in
e
-
tu
n
ed
ViT
m
o
d
el
is
a
p
r
o
m
is
in
g
to
o
l
f
o
r
cl
in
ical
ap
p
licatio
n
,
p
o
ten
tially
ac
ce
ler
atin
g
d
iag
n
o
s
is
an
d
s
ig
n
if
ican
tly
im
p
r
o
v
in
g
ac
cu
r
ac
y
,
u
ltima
tely
lead
i
n
g
to
b
etter
p
atien
t
o
u
tco
m
es.
I
n
s
u
m
m
ar
y
,
th
e
f
i
n
d
in
g
s
o
f
th
is
r
esear
ch
h
a
v
e
s
ig
n
if
ican
t
im
p
licatio
n
s
f
o
r
b
o
t
h
th
e
r
esear
ch
f
ield
an
d
th
e
h
ea
lth
ca
r
e
c
o
m
m
u
n
ity
,
p
r
o
v
id
in
g
a
r
o
b
u
s
t
f
r
a
m
ewo
r
k
f
o
r
th
e
d
ev
elo
p
m
en
t
o
f
ad
v
a
n
ce
d
,
s
ca
lab
le,
a
n
d
r
eliab
le
d
iag
n
o
s
tic
to
o
ls
in
m
e
d
ical
im
ag
in
g
.
Fu
tu
r
e
r
esear
ch
s
h
o
u
ld
f
o
c
u
s
o
n
f
u
r
th
er
en
h
a
n
cin
g
th
e
g
en
e
r
aliza
b
ilit
y
o
f
t
h
e
ViT
m
o
d
el
b
y
u
tili
zin
g
lar
g
er
an
d
m
o
r
e
d
iv
e
r
s
e
d
atasets
th
at
in
co
r
p
o
r
ate
v
ar
iatio
n
s
i
n
d
em
o
g
r
ap
h
ics,
im
ag
in
g
co
n
d
itio
n
s
,
an
d
d
is
ea
s
e
s
tag
es.
T
o
im
p
r
o
v
e
p
e
r
f
o
r
m
an
ce
,
h
y
b
r
i
d
m
o
d
els
co
m
b
in
in
g
th
e
s
tr
en
g
th
s
o
f
ViT
s
a
n
d
C
NNs
co
u
ld
b
e
ex
p
lo
r
ed
,
with
a
p
ar
ticu
lar
f
o
cu
s
o
n
b
etter
ca
p
tu
r
in
g
b
o
th
lo
ca
l
an
d
g
l
o
b
al
in
f
o
r
m
atio
n
.
Ad
d
itio
n
ally
,
in
co
r
p
o
r
atin
g
e
x
p
lain
ab
ilit
y
te
ch
n
iq
u
es
in
to
th
e
m
o
d
el’
s
d
ec
is
io
n
-
m
ak
in
g
p
r
o
ce
s
s
co
u
ld
in
cr
ea
s
e
p
h
y
s
ician
s
'
tr
u
s
t
an
d
f
ac
ilit
ate
wid
er
ad
o
p
t
io
n
in
h
ea
lth
ca
r
e.
Fin
ally
,
e
x
p
an
d
in
g
th
e
u
s
e
o
f
f
in
e
-
t
u
n
ed
V
iT
m
o
d
els
to
o
th
er
me
d
ical
im
ag
in
g
m
o
d
alities
,
s
u
ch
as
C
T
an
d
MRI,
co
u
l
d
o
p
en
u
p
n
ew
av
e
n
u
es
f
o
r
d
iag
n
o
s
in
g
a
b
r
o
ad
er
r
an
g
e
o
f
p
u
l
m
o
n
ar
y
an
d
o
th
e
r
d
is
ea
s
es.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Kh
u
s
h
b
o
o
T
r
iv
ed
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
h
in
tan
B
.
T
h
ac
k
er
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
I
NF
O
RM
E
D
CO
NS
E
N
T
W
e
h
av
e
o
b
tain
ed
in
f
o
r
m
ed
c
o
n
s
en
t f
r
o
m
all
in
d
iv
id
u
als in
c
lu
d
ed
in
t
h
is
s
tu
d
y
.
E
T
H
I
CAL AP
P
RO
V
AL
T
h
is
r
esear
ch
d
id
n
o
t
in
v
o
lv
e
th
e
u
s
e
o
f
h
u
m
an
p
ar
ticip
a
n
ts
o
r
an
im
als.
T
h
er
ef
o
r
e,
eth
ica
l
ap
p
r
o
v
al
was n
o
t r
eq
u
ir
e
d
.
DATA AV
AI
L
AB
I
L
I
T
Y
D
a
t
a
a
v
a
il
a
b
i
li
t
y
is
n
o
t
a
p
p
l
i
ca
b
l
e
t
o
t
h
is
p
a
p
e
r
a
s
n
o
n
e
w
d
at
a
w
e
r
e
c
r
e
a
t
e
d
o
r
a
n
al
y
z
e
d
i
n
t
h
is
s
t
u
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
S
.
S
i
n
g
h
,
M
.
K
u
m
a
r
,
A
.
K
u
mar,
B
.
K
.
V
e
r
ma,
K
.
A
b
h
i
s
h
e
k
,
a
n
d
S
.
S
e
l
v
a
r
a
j
a
n
,
“
Ef
f
i
c
i
e
n
t
p
n
e
u
m
o
n
i
a
d
e
t
e
c
t
i
o
n
u
si
n
g
v
i
s
i
o
n
t
r
a
n
sf
o
r
mers
o
n
c
h
e
st
X
-
r
a
y
s,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
1
4
,
n
o
.
1
,
Ja
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
024
-
5
2
7
0
3
-
2.
[
2
]
A
.
M
.
A
l
i
,
K
.
G
h
a
f
o
o
r
,
A
.
M
u
l
a
h
u
w
a
i
sh
,
a
n
d
H
.
M
a
g
h
d
i
d
,
“
C
O
V
I
D
-
1
9
p
n
e
u
m
o
n
i
a
l
e
v
e
l
d
e
t
e
c
t
i
o
n
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
a
n
d
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
,
”
Ev
o
l
u
t
i
o
n
a
ry
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
7
,
n
o
.
2
,
p
p
.
1
0
3
5
–
1
0
4
6
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
0
6
5
-
0
2
2
-
0
0
7
7
7
-
0.
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
.
4
,
Au
g
u
s
t
20
25
:
3
9
9
6
-
4003
4002
[
3
]
C
.
G
u
a
n
d
M
.
L
e
e
,
“
D
e
e
p
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
u
s
i
n
g
r
e
a
l
-
w
o
r
l
d
i
m
a
g
e
f
e
a
t
u
r
e
s
f
o
r
m
e
d
i
c
a
l
i
m
a
g
e
c
l
a
ssi
f
i
c
a
t
i
o
n
,
w
i
t
h
a
c
a
se
st
u
d
y
o
n
p
n
e
u
mo
n
i
a
X
-
r
a
y
i
ma
g
e
s,
”
B
i
o
e
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
1
,
n
o
.
4
,
p
.
4
0
6
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
b
i
o
e
n
g
i
n
e
e
r
i
n
g
1
1
0
4
0
4
0
6
.
[
4
]
K
.
A
.
P
u
t
r
i
a
n
d
W
.
F
a
w
w
a
z
A
l
M
a
k
i
,
“
En
h
a
n
c
i
n
g
p
n
e
u
mo
n
i
a
d
i
se
a
se
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
-
t
u
n
e
d
D
C
G
A
N
s
a
n
d
VGG
-
1
6
i
n
t
e
g
r
a
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
E
l
e
c
t
ro
n
i
c
s,
E
l
e
c
t
r
o
m
e
d
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
,
a
n
d
M
e
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
6
,
n
o
.
1
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
3
5
8
8
2
/
j
e
e
e
m
i
.
v
6
i
1
.
3
4
9
.
[
5
]
N
.
W
.
A
sn
a
k
e
,
A
.
O
.
S
a
l
a
u
,
a
n
d
A
.
M
.
A
y
a
l
e
w
,
“
X
-
r
a
y
i
m
a
g
e
-
b
a
se
d
p
n
e
u
m
o
n
i
a
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
Mu
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
3
,
n
o
.
2
1
,
p
p
.
6
0
7
8
9
–
6
0
8
0
7
,
Ja
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
0
4
2
-
0
2
3
-
1
7
9
6
5
-
4.
[
6
]
T.
S
.
A
r
u
l
a
n
a
n
t
h
,
S
.
W
.
P
r
a
k
a
s
h
,
R
.
K
.
A
y
y
a
sam
y
,
V
.
P
.
K
a
v
i
t
h
a
,
P
.
G
.
K
u
p
p
u
sam
y
,
a
n
d
P
.
C
h
i
n
n
a
sam
y
,
“
C
l
a
s
si
f
i
c
a
t
i
o
n
o
f
p
a
e
d
i
a
t
r
i
c
p
n
e
u
m
o
n
i
a
u
si
n
g
m
o
d
i
f
i
e
d
D
e
n
seNe
t
-
1
2
1
d
e
e
p
-
l
e
a
r
n
i
n
g
m
o
d
e
l
,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
3
5
7
1
6
–
3
5
7
2
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
a
c
c
e
s
s.
2
0
2
4
.
3
3
7
1
1
5
1
.
[
7
]
C
.
J.
G
h
i
a
a
n
d
G
.
S
.
R
a
mb
h
a
d
,
“
S
y
st
e
ma
t
i
c
r
e
v
i
e
w
a
n
d
me
t
a
-
a
n
a
l
y
s
i
s
o
f
c
o
m
o
r
b
i
d
i
t
i
e
s
a
n
d
a
sso
c
i
a
t
e
d
r
i
sk
f
a
c
t
o
r
s
i
n
I
n
d
i
a
n
p
a
t
i
e
n
t
s
o
f
c
o
mm
u
n
i
t
y
-
a
c
q
u
i
r
e
d
p
n
e
u
mo
n
i
a
,
”
S
AG
E
O
p
e
n
M
e
d
i
c
i
n
e
,
v
o
l
.
1
0
,
J
a
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
7
7
/
2
0
5
0
3
1
2
1
2
2
1
0
9
5
4
8
5
.
[
8
]
V
.
R
a
j
a
g
u
r
u
,
T
.
H
.
K
i
m,
J.
S
h
i
n
,
S
.
G
.
Le
e
,
a
n
d
W
.
H
a
n
,
“
A
b
i
l
i
t
y
o
f
t
h
e
LA
C
E
i
n
d
e
x
t
o
p
r
e
d
i
c
t
3
0
-
d
a
y
r
e
a
d
m
i
ssi
o
n
s
i
n
p
a
t
i
e
n
t
s
w
i
t
h
a
c
u
t
e
my
o
c
a
r
d
i
a
l
i
n
f
a
r
c
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
Pe
r
so
n
a
l
i
ze
d
Me
d
i
c
i
n
e
,
v
o
l
.
1
2
,
n
o
.
7
,
p
.
1
0
8
5
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
j
p
m
1
2
0
7
1
0
8
5
.
[
9
]
M
.
O
.
Le
w
i
s,
P
.
T.
Tr
a
n
,
Y
.
H
u
a
n
g
,
R
.
A
.
D
e
sa
i
,
Y
.
S
h
e
n
,
a
n
d
J.
D
.
B
r
o
w
n
,
“
D
i
sea
s
e
se
v
e
r
i
t
y
a
n
d
r
i
s
k
f
a
c
t
o
r
s
o
f
3
0
-
d
a
y
h
o
s
p
i
t
a
l
r
e
a
d
m
i
ssi
o
n
i
n
p
e
d
i
a
t
r
i
c
h
o
sp
i
t
a
l
i
z
a
t
i
o
n
s
f
o
r
p
n
e
u
mo
n
i
a
,
”
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
.
1
1
,
n
o
.
5
,
p
.
1
1
8
5
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
j
c
m1
1
0
5
1
1
8
5
.
[
1
0
]
C
.
I
e
r
a
c
i
t
a
n
o
e
t
a
l
.
,
“
A
f
u
z
z
y
-
e
n
h
a
n
c
e
d
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
e
a
r
l
y
d
e
t
e
c
t
i
o
n
o
f
C
o
v
i
d
-
1
9
p
n
e
u
mo
n
i
a
f
r
o
m
p
o
r
t
a
b
l
e
c
h
e
st
X
-
r
a
y
i
ma
g
e
s
,
”
N
e
u
r
o
c
o
m
p
u
t
i
n
g
,
v
o
l
.
4
8
1
,
p
p
.
2
0
2
–
2
1
5
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m.
2
0
2
2
.
0
1
.
0
5
5
.
[
1
1
]
M
.
R
o
st
a
m
i
a
n
d
M
.
O
u
ssa
l
a
h
,
“
A
n
o
v
e
l
e
x
p
l
a
i
n
a
b
l
e
C
O
V
I
D
-
1
9
d
i
a
g
n
o
si
s
met
h
o
d
b
y
i
n
t
e
g
r
a
t
i
o
n
o
f
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
w
i
t
h
r
a
n
d
o
m
f
o
r
e
st
,
”
I
n
f
o
rm
a
t
i
c
s
i
n
M
e
d
i
c
i
n
e
U
n
l
o
c
k
e
d
,
v
o
l
.
3
0
,
p
.
1
0
0
9
4
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
mu
.
2
0
2
2
.
1
0
0
9
4
1
.
[
1
2
]
A
.
I
.
A
v
i
l
e
s
-
R
i
v
e
r
o
,
P
.
S
e
l
l
a
r
s,
C
.
-
B
.
S
c
h
ö
n
l
i
e
b
,
a
n
d
N
.
P
a
p
a
d
a
k
i
s
,
“
G
r
a
p
h
X
C
O
V
I
D
:
Ex
p
l
a
i
n
a
b
l
e
d
e
e
p
g
r
a
p
h
d
i
f
f
u
s
i
o
n
p
se
u
d
o
-
La
b
e
l
l
i
n
g
f
o
r
i
d
e
n
t
i
f
y
i
n
g
C
O
V
I
D
-
1
9
o
n
c
h
e
s
t
X
-
r
a
y
s,”
Pa
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
,
v
o
l
.
1
2
2
,
p
.
1
0
8
2
7
4
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
c
o
g
.
2
0
2
1
.
1
0
8
2
7
4
.
[
1
3
]
A
.
M
a
l
h
o
t
r
a
e
t
a
l
.
,
“
M
u
l
ti
-
t
a
s
k
d
r
i
v
e
n
e
x
p
l
a
i
n
a
b
l
e
d
i
a
g
n
o
si
s
o
f
C
O
V
I
D
-
1
9
u
s
i
n
g
c
h
e
st
X
-
r
a
y
i
m
a
g
e
s,”
Pa
t
t
e
rn
Re
c
o
g
n
i
t
i
o
n
,
v
o
l
.
1
2
2
,
p
.
1
0
8
2
4
3
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
c
o
g
.
2
0
2
1
.
1
0
8
2
4
3
.
[
1
4
]
A
.
K
.
M
o
n
d
a
l
,
A
.
B
h
a
t
t
a
c
h
a
r
j
e
e
,
P
.
S
i
n
g
l
a
,
a
n
d
A
.
P
.
P
r
a
t
h
o
sh
,
“
x
V
i
TC
O
S
:
e
x
p
l
a
i
n
a
b
l
e
v
i
si
o
n
t
r
a
n
sf
o
r
mer
b
a
s
e
d
C
O
V
I
D
-
1
9
scree
n
i
n
g
u
si
n
g
r
a
d
i
o
g
r
a
p
h
y
,
”
I
EE
E
J
o
u
rn
a
l
o
f
T
ra
n
sl
a
t
i
o
n
a
l
E
n
g
i
n
e
e
ri
n
g
i
n
H
e
a
l
t
h
a
n
d
Me
d
i
c
i
n
e
,
v
o
l
.
1
0
,
p
p
.
1
–
1
0
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
j
t
e
h
m.
2
0
2
1
.
3
1
3
4
0
9
6
.
[
1
5
]
H
.
R
e
n
e
t
a
l
.
,
“
I
n
t
e
r
p
r
e
t
a
b
l
e
p
n
e
u
m
o
n
i
a
d
e
t
e
c
t
i
o
n
b
y
c
o
m
b
i
n
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
e
x
p
l
a
i
n
a
b
l
e
mo
d
e
l
s
w
i
t
h
mu
l
t
i
s
o
u
r
c
e
d
a
t
a
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
9
,
p
p
.
9
5
8
7
2
–
9
5
8
8
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
a
c
c
e
ss.
2
0
2
1
.
3
0
9
0
2
1
5
.
[
1
6
]
F
.
C
o
l
a
v
i
t
a
e
t
a
l
.
,
“
C
O
V
I
D
-
1
9
r
a
p
i
d
a
n
t
i
g
e
n
t
e
s
t
a
s
s
c
r
e
e
n
i
n
g
st
r
a
t
e
g
y
a
t
p
o
i
n
t
s
o
f
e
n
t
r
y
:
e
x
p
e
r
i
e
n
c
e
i
n
l
a
z
i
o
r
e
g
i
o
n
,
C
e
n
t
r
a
l
I
t
a
l
y
,
A
u
g
u
st
–
O
c
t
o
b
e
r
2
0
2
0
,
”
Bi
o
m
o
l
e
c
u
l
e
s
,
v
o
l
.
1
1
,
n
o
.
3
,
p
.
4
2
5
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
b
i
o
m1
1
0
3
0
4
2
5
.
[
1
7
]
M
.
M
u
st
a
f
a
H
e
l
l
o
u
e
t
a
l
.
,
“
N
u
c
l
e
i
c
a
c
i
d
a
m
p
l
i
f
i
c
a
t
i
o
n
t
e
st
s
o
n
r
e
s
p
i
r
a
t
o
r
y
samp
l
e
s
f
o
r
t
h
e
d
i
a
g
n
o
s
i
s
o
f
c
o
r
o
n
a
v
i
r
u
s
i
n
f
e
c
t
i
o
n
s:
a
sy
s
t
e
ma
t
i
c
r
e
v
i
e
w
a
n
d
m
e
t
a
-
a
n
a
l
y
s
i
s,”
C
l
i
n
i
c
a
l
Mi
c
r
o
b
i
o
l
o
g
y
a
n
d
I
n
f
e
c
t
i
o
n
,
v
o
l
.
2
7
,
n
o
.
3
,
p
p
.
3
4
1
–
3
5
1
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
m
i
.
2
0
2
0
.
1
1
.
0
0
2
.
[
1
8
]
M
.
T
o
ğ
a
ç
a
r
,
N
.
M
u
z
o
ğ
l
u
,
B
.
Er
g
e
n
,
B
.
S
.
B
.
Y
a
r
ma
n
,
a
n
d
A
.
M
.
H
a
l
e
f
o
ğ
l
u
,
“
D
e
t
e
c
t
i
o
n
o
f
C
O
V
I
D
-
1
9
f
i
n
d
i
n
g
s
b
y
t
h
e
l
o
c
a
l
i
n
t
e
r
p
r
e
t
a
b
l
e
mo
d
e
l
-
a
g
n
o
s
t
i
c
e
x
p
l
a
n
a
t
i
o
n
s
m
e
t
h
o
d
o
f
t
y
p
e
s
-
b
a
se
d
a
c
t
i
v
a
t
i
o
n
s
e
x
t
r
a
c
t
e
d
f
r
o
m
C
N
N
s,
”
B
i
o
m
e
d
i
c
a
l
S
i
g
n
a
l
Pro
c
e
ssi
n
g
a
n
d
C
o
n
t
ro
l
,
v
o
l
.
7
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
sp
c
.
2
0
2
1
.
1
0
3
1
2
8
.
[
1
9
]
D
.
M
a
h
a
p
a
t
r
a
,
Z.
G
e
,
a
n
d
M
.
R
e
y
e
s,
“
S
e
l
f
-
s
u
p
e
r
v
i
se
d
g
e
n
e
r
a
l
i
z
e
d
z
e
r
o
s
h
o
t
l
e
a
r
n
i
n
g
f
o
r
me
d
i
c
a
l
i
ma
g
e
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
n
o
v
e
l
i
n
t
e
r
p
r
e
t
a
b
l
e
s
a
l
i
e
n
c
y
m
a
p
s
,
”
I
E
EE
T
ra
n
sa
c
t
i
o
n
s
o
n
M
e
d
i
c
a
l
I
m
a
g
i
n
g
,
v
o
l
.
4
1
,
n
o
.
9
,
p
p
.
2
4
4
3
–
2
4
5
6
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
t
m
i
.
2
0
2
2
.
3
1
6
3
2
3
2
.
[
2
0
]
M
.
Li
e
t
a
l
.
,
“
E
x
p
l
a
i
n
a
b
l
e
C
O
V
I
D
-
19
i
n
f
e
c
t
i
o
n
s i
d
e
n
t
i
f
i
c
a
t
i
o
n
a
n
d
d
e
l
i
n
e
a
t
i
o
n
u
s
i
n
g
c
a
l
i
b
r
a
t
e
d
p
s
e
u
d
o
l
a
b
e
l
s,”
I
E
EE
T
ra
n
s
a
c
t
i
o
n
s
o
n
Em
e
r
g
i
n
g
T
o
p
i
c
s
i
n
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
7
,
n
o
.
1
,
p
p
.
2
6
–
3
5
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
t
e
t
c
i
.
2
0
2
2
.
3
1
8
9
0
5
4
.
[
2
1
]
“
W
H
O
d
i
r
e
c
t
o
r
-
g
e
n
e
r
a
l
’
s
o
p
e
n
i
n
g
r
e
mar
k
s
a
t
t
h
e
me
d
i
a
b
r
i
e
f
i
n
g
o
n
C
O
V
I
D
-
1
9
,
”
W
o
rl
d
h
e
a
l
t
h
O
rg
a
n
i
s
a
t
i
o
n
.
A
c
c
e
ss
e
d
:
M
a
r
.
1
1
,
2
0
2
0
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
w
h
o
.
i
n
t
/
d
i
r
e
c
t
o
r
-
g
e
n
e
r
a
l
/
sp
e
e
c
h
e
s/
d
e
t
a
i
l
.
[
2
2
]
G
.
L
i
a
n
g
a
n
d
L.
Z
h
e
n
g
,
“
A
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
me
t
h
o
d
w
i
t
h
d
e
e
p
r
e
s
i
d
u
a
l
n
e
t
w
o
r
k
f
o
r
p
e
d
i
a
t
r
i
c
p
n
e
u
mo
n
i
a
d
i
a
g
n
o
s
i
s,
”
C
o
m
p
u
t
e
r
Me
t
h
o
d
s
a
n
d
Pr
o
g
ra
m
s
i
n
B
i
o
m
e
d
i
c
i
n
e
,
v
o
l
.
1
8
7
,
A
p
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
mp
b
.
2
0
1
9
.
0
6
.
0
2
3
.
[
2
3
]
T.
F
u
j
i
o
k
a
e
t
a
l
.
,
“
Ef
f
i
c
i
e
n
t
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
w
i
t
h
g
e
n
e
r
a
t
i
v
e
a
d
v
e
r
sar
i
a
l
n
e
t
w
o
r
k
f
o
r
b
r
e
a
s
t
u
l
t
r
a
s
o
u
n
d
i
m
a
g
i
n
g
,
”
D
i
a
g
n
o
st
i
c
s
,
v
o
l
.
1
0
,
n
o
.
7
,
p
.
4
5
6
,
Ju
l
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
d
i
a
g
n
o
st
i
c
s
1
0
0
7
0
4
5
6
.
[
2
4
]
A
.
Za
ma
n
,
S
.
H
.
P
a
r
k
,
H
.
B
a
n
g
,
C
.
P
a
r
k
,
I
.
P
a
r
k
,
a
n
d
S
.
J
o
u
n
g
,
“
G
e
n
e
r
a
t
i
v
e
a
p
p
r
o
a
c
h
f
o
r
d
a
t
a
a
u
g
m
e
n
t
a
t
i
o
n
f
o
r
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
b
o
n
e
s
u
r
f
a
c
e
se
g
me
n
t
a
t
i
o
n
f
r
o
m
u
l
t
r
a
so
u
n
d
i
ma
g
e
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r
Assi
s
t
e
d
R
a
d
i
o
l
o
g
y
a
n
d
S
u
rg
e
ry
,
v
o
l
.
1
5
,
n
o
.
6
,
p
p
.
9
3
1
–
9
4
1
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
5
4
8
-
0
2
0
-
0
2
1
9
2
-
1.
[
2
5
]
P
.
D
i
m
i
t
r
a
k
o
p
o
u
l
o
s,
G
.
S
f
i
k
a
s
,
a
n
d
C
.
N
i
k
o
u
,
“
I
S
I
N
G
-
G
A
N
:
a
n
n
o
t
a
t
e
d
d
a
t
a
a
u
g
me
n
t
a
t
i
o
n
w
i
t
h
a
s
p
a
t
i
a
l
l
y
c
o
n
s
t
r
a
i
n
e
d
g
e
n
e
r
a
t
i
v
e
a
d
v
e
r
sar
i
a
l
n
e
t
w
o
r
k
,
”
i
n
2
0
2
0
I
E
EE
1
7
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
si
u
m
o
n
B
i
o
m
e
d
i
c
a
l
I
m
a
g
i
n
g
(
I
S
BI
)
,
A
p
r
.
2
0
2
0
,
p
p
.
1
6
0
0
–
1
6
0
3
,
d
o
i
:
1
0
.
1
1
0
9
/
i
s
b
i
4
5
7
4
9
.
2
0
2
0
.
9
0
9
8
6
1
8
.
[
2
6
]
I
.
A
r
v
i
d
ss
o
n
,
N
.
C
.
O
v
e
r
g
a
a
r
d
,
K
.
A
st
r
o
m,
a
n
d
A
.
H
e
y
d
e
n
,
“
C
o
m
p
a
r
i
s
o
n
o
f
d
i
f
f
e
r
e
n
t
a
u
g
m
e
n
t
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
f
o
r
i
mp
r
o
v
e
d
g
e
n
e
r
a
l
i
z
a
t
i
o
n
p
e
r
f
o
r
ma
n
c
e
f
o
r
g
l
e
a
s
o
n
g
r
a
d
i
n
g
,
”
i
n
2
0
1
9
I
E
EE
1
6
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
S
y
m
p
o
si
u
m
o
n
Bi
o
m
e
d
i
c
a
l
I
m
a
g
i
n
g
(
I
S
BI
2
0
1
9
)
,
A
p
r
.
2
0
1
9
,
p
p
.
9
2
3
–
9
2
7
,
d
o
i
:
1
0
.
1
1
0
9
/
i
sb
i
.
2
0
1
9
.
8
7
5
9
2
6
4
.
[
2
7
]
Y.
-
J.
L
i
n
a
n
d
I
.
-
F
.
C
h
u
n
g
,
“
M
e
d
i
c
a
l
d
a
t
a
a
u
g
me
n
t
a
t
i
o
n
u
si
n
g
g
e
n
e
r
a
t
i
v
e
a
d
v
e
r
sar
i
a
l
n
e
t
w
o
r
k
s:
X
-
r
a
y
i
ma
g
e
g
e
n
e
r
a
t
i
o
n
f
o
r
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
o
f
h
i
p
f
r
a
c
t
u
r
e
d
e
t
e
c
t
i
o
n
,
”
i
n
2
0
1
9
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
T
e
c
h
n
o
l
o
g
i
e
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
o
f
Art
i
fi
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
(
T
AAI)
,
N
o
v
.
2
0
1
9
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
t
a
a
i
4
8
2
0
0
.
2
0
1
9
.
8
9
5
9
9
0
8
.
[
2
8
]
V
.
B
h
a
g
a
t
a
n
d
S
.
B
h
a
u
mi
k
,
“
D
a
t
a
a
u
g
m
e
n
t
a
t
i
o
n
u
si
n
g
g
e
n
e
r
a
t
i
v
e
a
d
v
e
r
s
a
r
i
a
l
n
e
t
w
o
r
k
s
f
o
r
p
n
e
u
m
o
n
i
a
c
l
a
ss
i
f
i
c
a
t
i
o
n
i
n
c
h
e
s
t
X
r
a
y
s,
”
i
n
2
0
1
9
Fi
f
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
m
a
g
e
I
n
f
o
rm
a
t
i
o
n
Pro
c
e
ssi
n
g
(
I
C
I
I
P)
,
N
o
v
.
2
0
1
9
,
p
p
.
5
7
4
–
5
7
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
I
P
4
7
2
0
7
.
2
0
1
9
.
8
9
8
5
8
9
2
.
[
2
9
]
P
.
R
a
j
p
u
r
k
a
r
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
c
h
e
s
t
r
a
d
i
o
g
r
a
p
h
d
i
a
g
n
o
s
i
s:
a
r
e
t
r
o
sp
e
c
t
i
v
e
c
o
m
p
a
r
i
s
o
n
o
f
t
h
e
C
h
e
X
N
e
X
t
a
l
g
o
r
i
t
h
m
t
o
p
r
a
c
t
i
c
i
n
g
r
a
d
i
o
l
o
g
i
s
t
s,”
PLO
S
M
e
d
i
c
i
n
e
,
v
o
l
.
1
5
,
n
o
.
1
1
,
N
o
v
.
2
0
1
8
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
me
d
.
1
0
0
2
6
8
6
.
[
3
0
]
H
.
Q
.
N
g
u
y
e
n
e
t
a
l
.
,
“
V
i
n
D
r
-
C
X
R
:
a
n
o
p
e
n
d
a
t
a
se
t
o
f
c
h
e
s
t
X
-
r
a
y
s
w
i
t
h
r
a
d
i
o
l
o
g
i
st
’
s
a
n
n
o
t
a
t
i
o
n
s,
”
S
c
i
e
n
t
i
f
i
c
D
a
t
a
,
v
o
l
.
9
,
n
o
.
1
,
p
.
4
2
9
,
J
u
l
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
7
-
0
2
2
-
0
1
4
9
8
-
w.
[
3
1
]
S
.
I
sl
a
m
e
t
a
l
.
,
“
G
e
n
e
r
a
t
i
v
e
a
d
v
e
r
sari
a
l
n
e
t
w
o
r
k
s
(
G
A
N
s)
i
n
m
e
d
i
c
a
l
i
ma
g
i
n
g
:
a
d
v
a
n
c
e
me
n
t
s
,
a
p
p
l
i
c
a
t
i
o
n
s,
a
n
d
c
h
a
l
l
e
n
g
e
s,”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
3
5
7
2
8
–
3
5
7
5
3
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
3
7
0
8
4
8
.
[
3
2
]
J
.
G
u
i
,
Z
.
S
u
n
,
Y
.
W
e
n
,
D
.
T
a
o
,
a
n
d
J
.
Y
e
,
“
A
r
e
v
i
e
w
o
n
g
e
n
e
r
a
t
i
v
e
a
d
v
e
r
s
a
r
i
a
l
n
e
t
w
o
r
k
s
:
a
l
g
o
r
i
t
h
m
s
,
t
h
e
o
r
y
,
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s
,
”
I
E
E
E
T
r
a
n
s
a
c
t
i
o
n
s
o
n
K
n
o
w
l
e
d
g
e
a
n
d
D
a
t
a
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
3
5
,
n
o
.
4
,
p
p
.
3
3
1
3
–
3
3
3
2
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
T
K
D
E
.
2
0
2
1
.
3
1
3
0
1
9
1
.
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
Mu
lti
-
cla
s
s
p
n
eu
mo
n
ia
d
etec
t
io
n
u
s
in
g
fin
e
-
tu
n
ed
visi
o
n
tr
a
n
s
fo
r
mer m
o
d
el
(
K
h
u
s
h
b
o
o
Tr
ived
i
)
4003
[
3
3
]
G
.
M
.
M
.
A
l
s
h
mr
a
n
i
,
Q
.
N
i
,
R
.
J
i
a
n
g
,
H
.
P
e
r
v
a
i
z
,
a
n
d
N
.
M
.
El
s
h
e
n
n
a
w
y
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
a
r
c
h
i
t
e
c
t
u
r
e
f
o
r
mu
l
t
i
-
c
l
a
ss
l
u
n
g
d
i
s
e
a
se
s
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
c
h
e
s
t
X
-
r
a
y
(
C
X
R
)
i
ma
g
e
s
,
”
A
l
e
x
a
n
d
ri
a
E
n
g
i
n
e
e
ri
n
g
J
o
u
r
n
a
l
,
v
o
l
.
6
4
,
p
p
.
9
2
3
–
9
3
5
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
j
.
2
0
2
2
.
1
0
.
0
5
3
.
[
3
4
]
R
.
A
r
o
r
a
e
t
a
l
.
,
“
A
I
-
b
a
se
d
d
i
a
g
n
o
si
s
o
f
C
O
V
I
D
-
1
9
p
a
t
i
e
n
t
s
u
s
i
n
g
X
-
r
a
y
s
c
a
n
s
w
i
t
h
st
o
c
h
a
s
t
i
c
e
n
s
e
mb
l
e
o
f
C
N
N
s,”
Ph
y
si
c
a
l
a
n
d
En
g
i
n
e
e
ri
n
g
S
c
i
e
n
c
e
s
i
n
Me
d
i
c
i
n
e
,
v
o
l
.
4
4
,
n
o
.
4
,
p
p
.
1
2
5
7
–
1
2
7
1
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
3
2
4
6
-
0
2
1
-
0
1
0
6
0
-
9.
[
3
5
]
Y
.
G
u
a
n
e
t
a
l
.
,
“
C
o
m
p
a
r
i
s
o
n
o
f
d
e
e
p
-
l
e
a
r
n
i
n
g
a
n
d
r
a
d
i
o
mi
c
s
-
b
a
se
d
m
a
c
h
i
n
e
-
l
e
a
r
n
i
n
g
m
e
t
h
o
d
s
f
o
r
t
h
e
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
c
h
r
o
n
i
c
o
b
s
t
r
u
c
t
i
v
e
p
u
l
m
o
n
a
r
y
d
i
sea
s
e
o
n
l
o
w
-
d
o
se
c
o
m
p
u
t
e
d
t
o
m
o
g
r
a
p
h
y
i
ma
g
e
s,”
Q
u
a
n
t
i
t
a
t
i
v
e
I
m
a
g
i
n
g
i
n
Me
d
i
c
i
n
e
a
n
d
S
u
r
g
e
ry
,
v
o
l
.
1
4
,
n
o
.
3
,
p
p
.
2
4
8
5
–
2
4
9
8
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
2
1
0
3
7
/
q
i
ms
-
23
-
1
3
0
7
.
[
3
6
]
Q
.
A
n
,
W
.
C
h
e
n
,
a
n
d
W
.
S
h
a
o
,
“
A
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
p
n
e
u
mo
n
i
a
d
e
t
e
c
t
i
o
n
i
n
X
-
r
a
y
i
ma
g
e
s
w
i
t
h
a
t
t
e
n
t
i
o
n
e
n
s
e
mb
l
e
,
”
D
i
a
g
n
o
s
t
i
c
s
,
v
o
l
.
1
4
,
n
o
.
4
,
p
.
3
9
0
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
d
i
a
g
n
o
s
t
i
c
s1
4
0
4
0
3
9
0
.
[
3
7
]
S
.
p
r
a
sa
d
K
o
y
y
a
d
a
a
n
d
T.
P
.
S
i
n
g
h
,
“
A
n
e
x
p
l
a
i
n
a
b
l
e
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
m
o
d
e
l
f
o
r
i
d
e
n
t
i
f
y
i
n
g
l
o
c
a
l
i
n
d
i
c
a
t
o
r
s
a
n
d
d
e
t
e
c
t
i
n
g
l
u
n
g
d
i
se
a
se
f
r
o
m
c
h
e
st
X
-
r
a
y
i
m
a
g
e
s,
”
H
e
a
l
t
h
c
a
r
e
A
n
a
l
y
t
i
c
s
,
v
o
l
.
4
,
p
.
1
0
0
2
0
6
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
a
l
t
h
.
2
0
2
3
.
1
0
0
2
0
6
.
[
3
8
]
X
.
W
a
n
g
,
Y
.
P
e
n
g
,
L
.
Lu
,
Z.
L
u
,
M
.
B
a
g
h
e
r
i
,
a
n
d
R
.
M
.
S
u
mm
e
r
s,
“
C
h
e
st
X
-
r
a
y
8
:
h
o
s
p
i
t
a
l
-
sca
l
e
c
h
e
s
t
X
-
r
a
y
d
a
t
a
b
a
se
a
n
d
b
e
n
c
h
mar
k
s
o
n
w
e
a
k
l
y
-
s
u
p
e
r
v
i
se
d
c
l
a
ssi
f
i
c
a
t
i
o
n
a
n
d
l
o
c
a
l
i
z
a
t
i
o
n
o
f
c
o
m
mo
n
t
h
o
r
a
x
d
i
se
a
ses
,
”
i
n
2
0
1
7
I
EE
E
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
s
i
o
n
a
n
d
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
(
C
VP
R)
,
J
u
l
.
2
0
1
7
,
p
p
.
3
4
6
2
–
3
4
7
1
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
1
7
.
3
6
9
.
[
3
9
]
P
.
M
o
o
n
e
y
,
“
C
h
e
st
X
-
r
a
y
i
ma
g
e
s
(
p
n
e
u
m
o
n
i
a
)
,
”
K
a
g
g
l
e
.
2
0
1
7
,
A
c
c
e
sse
d
:
D
e
c
.
1
0
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m
/
p
a
u
l
t
i
m
o
t
h
y
mo
o
n
e
y
/
c
h
e
s
t
-
x
r
a
y
-
p
n
e
u
m
o
n
i
a
/
v
e
r
si
o
n
/
2
.
[
4
0
]
J.
I
r
v
i
n
e
t
a
l
.
,
“
C
h
e
X
p
e
r
t
:
a
l
a
r
g
e
c
h
e
st
r
a
d
i
o
g
r
a
p
h
d
a
t
a
set
w
i
t
h
u
n
c
e
r
t
a
i
n
t
y
l
a
b
e
l
s
a
n
d
e
x
p
e
r
t
c
o
m
p
a
r
i
s
o
n
,
”
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
AAAI C
o
n
f
e
re
n
c
e
o
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
3
3
,
n
o
.
0
1
,
p
p
.
5
9
0
–
5
9
7
,
J
u
l
.
2
0
1
9
,
d
o
i
:
1
0
.
1
6
0
9
/
a
a
a
i
.
v
3
3
i
0
1
.
3
3
0
1
5
9
0
.
[
4
1
]
S
.
W
a
k
r
i
m,
“
D
i
a
g
n
o
s
t
i
c
p
e
r
f
o
r
m
a
n
c
e
o
f
c
h
e
s
t
C
T
f
i
n
d
i
n
g
s
o
f
C
O
V
I
D
-
1
9
w
i
t
h
R
T
-
P
C
R
n
e
g
a
t
i
v
e
,
”
A
f
ri
c
a
n
H
e
a
l
t
h
S
c
i
e
n
c
e
s
,
v
o
l
.
2
2
,
n
o
.
4
,
p
p
.
5
0
2
–
5
0
4
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
4
3
1
4
/
a
h
s
.
v
2
2
i
4
.
5
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
K
h
u
shb
o
o
Tr
i
v
e
d
i
h
o
ld
s
a
m
a
ste
r’s
d
e
g
re
e
i
n
c
o
m
p
u
t
e
r
sc
ien
c
e
a
n
d
e
n
g
in
e
e
rin
g
fr
o
m
P
a
r
u
l
Un
iv
e
rs
it
y
a
n
d
c
u
rre
n
tl
y
p
u
rsu
in
g
P
h
.
D
.
in
th
e
d
o
m
a
in
o
f
d
e
e
p
lea
rn
in
g
a
n
d
c
o
m
p
u
ter
v
isio
n
fr
o
m
P
a
ru
l
Un
i
v
e
rsity
,
Va
d
o
d
a
ra
,
Gu
jara
t.
S
h
e
h
a
s
1
2
+
y
e
a
rs
o
f
e
x
p
e
rien
c
e
i
n
a
c
a
d
e
m
ia.
He
r
re
se
a
rc
h
in
tere
sts
a
re
in
m
a
c
h
in
e
lea
rn
in
g
,
d
e
e
p
lea
rn
i
n
g
,
a
rti
ficia
l
in
telli
g
e
n
c
e
,
a
n
d
c
o
m
p
u
ter
v
isio
n
.
Cu
rre
n
tl
y
,
sh
e
se
rv
e
s
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
in
th
e
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
i
n
e
e
rin
g
De
p
a
rtme
n
t
a
t
P
a
ru
l
In
sti
tu
te
o
f
Tec
h
n
o
lo
g
y
,
P
a
r
u
l
Un
iv
e
rsity
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
h
u
s
h
b
o
o
.
tri
v
e
d
i2
1
3
0
5
@p
a
ru
lu
n
iv
e
rsit
y
.
a
c
.
in
.
Chi
n
ta
n
B
.
Th
a
c
k
e
r
re
c
e
iv
e
d
a
P
h
.
D
.
d
e
g
re
e
in
th
e
d
o
m
a
in
o
f
a
rti
f
icia
l
in
telli
g
e
n
c
e
a
n
d
c
o
m
p
u
ter
v
i
sio
n
fro
m
G
u
jara
t
Tec
h
n
ica
l
Un
iv
e
rsit
y
i
n
t
h
e
y
e
a
r
2
0
2
2
.
He
h
a
d
se
rv
e
d
a
s
H
e
a
d
o
f
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
De
p
a
rtme
n
t
a
t
HJ
D
In
stit
u
te
o
f
Tec
h
n
ica
l
Ed
u
c
a
ti
o
n
a
n
d
Re
se
a
rc
h
,
Ke
ra
,
In
d
ia.
He
h
a
s
1
+
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
in
d
u
stry
a
n
d
1
2
+
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
a
c
a
d
e
m
ia.
Cu
rre
n
tl
y
,
h
e
se
rv
e
s
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
i
n
t
h
e
Co
m
p
u
ter
S
c
i
e
n
c
e
a
n
d
En
g
in
e
e
ri
n
g
De
p
a
rtm
e
n
t
a
t
P
a
ru
l
I
n
stit
u
te
o
f
En
g
i
n
e
e
rin
g
Tec
h
n
o
l
o
g
y
,
P
a
ru
l
Un
iv
e
rsity
,
Va
d
o
d
a
ra
,
G
u
jara
t.
In
a
d
d
it
i
o
n
,
h
e
h
a
s
a
ls
o
g
u
i
d
e
d
se
v
e
ra
l
d
o
c
to
ra
te
st
u
d
e
n
ts an
d
h
a
s
b
e
e
n
a
c
ti
v
e
in
c
o
n
d
u
c
ti
n
g
se
v
e
ra
l
wo
rk
sh
o
p
s
in
th
e
d
o
m
a
in
o
f
c
o
m
p
u
ter
v
isio
n
.
H
is
re
se
a
rc
h
in
tere
sts
a
re
in
m
a
c
h
in
e
lea
rn
in
g
,
a
rti
ficia
l
in
telli
g
e
n
c
e
,
d
e
e
p
lea
rn
i
n
g
a
n
d
c
o
m
p
u
ter
v
isi
o
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
c
h
in
tan
.
th
a
c
k
e
r1
9
4
3
5
@
p
a
ru
l
u
n
i
v
e
rsity
.
a
c
.
in
.
Evaluation Warning : The document was created with Spire.PDF for Python.