I
n
t
e
r
n
at
ion
al
Jou
r
n
a
l
of
I
n
f
o
r
m
at
ics
an
d
Com
m
u
n
icat
ion
T
e
c
h
n
ol
ogy
(
I
J
-
I
CT
)
Vo
l
.
15
,
N
o
.
1
,
M
a
r
c
h
20
26
,
pp.
40
5
~
41
3
I
S
S
N:
2252
-
8776
,
DO
I
:
10
.
11591/i
ji
c
t
.
v
15
i
1
.
pp
40
5
-
41
3
405
Jou
r
n
al
h
o
m
e
page
:
ht
tp:
//
ij
ict
.
iaes
c
or
e
.
c
om
D
e
t
e
c
t
io
n
m
od
e
l
f
or
p
u
l
m
o
n
a
r
y
t
u
b
e
r
c
u
lo
si
s an
d
p
e
r
f
or
m
a
n
c
e
e
v
al
u
at
io
n
on
h
is
t
ogr
a
m
e
n
h
a
n
c
e
d
au
g
m
e
n
t
e
d
X
-
r
ay
s
Abd
u
l
K
ar
im
S
id
d
iq
u
i
1
,
Vij
ay
K
u
m
ar
Gar
g
2
1
S
c
h
oo
l
of
C
o
mput
e
r
S
c
i
e
n
c
e
a
nd
A
ppl
i
c
a
ti
o
n,
L
ove
l
y
P
r
of
e
s
s
io
na
l
U
ni
ve
r
s
it
y
, P
ha
gw
a
r
a
, I
ndi
a
2
S
c
h
oo
l
of
C
o
mput
e
r
S
c
i
e
n
c
e
a
nd
E
ng
in
e
e
r
in
g,
L
ove
l
y
P
r
of
e
s
s
i
o
na
l
U
ni
ve
r
s
it
y
, P
ha
gw
a
r
a
, I
ndi
a
Ar
t
ic
l
e
I
n
f
o
AB
S
T
RA
CT
A
r
ti
c
le
h
is
tor
y
:
R
e
c
e
i
ve
d
Oc
t
23,
2024
R
e
vi
s
e
d
S
e
p
28,
2025
A
c
c
e
pt
e
d
N
o
v
5,
2025
T
u
b
e
rcu
l
o
s
i
s
(T
B)
h
as
r
em
a
i
n
ed
a
b
i
g
co
n
ce
r
n
fo
r
d
ec
a
d
e
s
.
B
ei
n
g
c
o
n
t
ag
i
o
u
s
mi
l
l
i
o
n
s
o
f
l
i
v
e
s
h
av
e
b
een
faci
n
g
l
i
f
e
t
h
r
e
at
s
,
e
s
p
eci
al
l
y
i
n
u
n
d
e
r
d
ev
e
l
o
p
i
n
g
c
o
u
n
t
ri
e
s
w
h
o
h
a
v
e
l
e
s
s
re
s
o
u
r
ce
s
t
o
n
eu
t
ral
i
z
e
i
t
.
T
h
e
d
e
p
ri
v
e
d
s
o
ci
e
t
y
y
i
e
l
d
s
T
B
i
n
f
ec
t
i
o
n
d
u
e
t
o
i
n
c
o
m
p
l
e
t
e
t
re
at
me
n
t
s
an
d
t
h
e
l
e
s
s
o
r
n
o
p
re
v
e
n
t
i
v
e
me
as
u
r
e
s
.
T
h
e
c
u
rr
e
n
t
t
i
me
d
em
an
d
s
an
e
ff
ec
t
i
v
e
e
ffo
rt
t
o
e
rad
i
c
at
e
p
u
l
m
o
n
ar
y
T
B
d
i
s
e
as
e
.
T
B
affec
t
s
l
u
n
g
s
i
n
mo
s
t
c
as
e
s
w
i
t
h
s
o
me
o
t
h
e
r
s
o
ft
o
rg
a
n
s
w
h
e
n
n
o
t
t
r
e
at
ed
p
ro
p
e
rl
y
.
D
ee
p
l
e
ar
n
i
n
g
(
DL
)
h
as
p
o
t
e
n
t
i
al
t
o
p
red
i
c
t
a
n
d
d
i
a
g
n
o
s
e
t
h
e
s
ev
e
ri
t
y
o
f
p
u
l
mo
n
ar
y
an
d
e
x
t
ra
p
u
l
m
o
n
ar
y
c
as
e
s
.
I
t
i
s
a
s
u
b
s
e
t
o
f
m
a
c
h
i
n
e
l
e
arn
i
n
g
(
ML
)
t
h
at
c
l
as
s
i
fi
e
s
i
n
c
u
rab
l
e
an
d
fat
al
p
ro
b
l
em
s
w
i
t
h
mu
l
t
i
-
n
e
u
ra
l
ar
c
h
i
t
ec
t
u
re
s
.
I
t
h
e
l
p
s
me
d
i
c
a
l
p
rac
t
i
t
i
o
n
e
rs
t
o
i
d
e
n
t
i
f
y
b
a
c
t
e
r
i
al
i
n
f
ec
t
i
o
n
s
i
n
t
h
e
e
ar
l
y
s
t
ag
e
.
I
t
h
as
al
s
o
e
n
ab
l
ed
p
ro
p
e
r
d
i
ag
n
o
s
i
s
a
n
d
t
r
e
at
men
t
fo
r
p
u
l
mo
n
ary
TB
.
T
h
i
s
p
ap
e
r
i
n
t
ro
d
u
ce
s
a
n
i
m
p
ro
v
ed
me
t
h
o
d
fo
r
d
e
t
ec
t
i
n
g
an
d
d
i
s
t
i
n
g
u
i
s
h
i
n
g
b
e
t
w
ee
n
p
u
l
m
o
n
ar
y
T
B
an
d
n
o
r
m
al
c
as
e
s
u
s
i
n
g
cl
i
n
i
c
a
l
X
-
r
ay
i
m
a
g
e
s
.
I
t
u
s
e
s
e
n
h
an
ced
rad
i
o
g
rap
h
s
,
p
ro
ce
s
s
ed
t
h
ro
u
g
h
h
i
s
t
o
g
ra
m
e
q
u
al
i
zat
i
o
n
,
an
d
ap
p
l
i
e
s
t
h
em
t
o
co
mm
o
n
l
y
u
s
e
d
cl
as
s
i
fi
e
rs
.
T
w
o
b
e
s
t
p
e
rfo
r
m
i
n
g
b
as
e
c
l
as
s
i
fi
e
rs
w
e
r
e
p
as
s
e
d
i
n
t
o
s
t
ac
k
ed
e
n
s
em
b
l
e
c
l
as
s
i
fi
e
r
.
B
y
co
m
b
i
n
i
n
g
mu
l
t
i
p
l
e
m
o
d
e
l
s
,
X
G
Bo
o
s
t
c
o
u
l
d
r
e
d
u
ce
v
ari
a
n
ce
i
n
p
re
d
i
c
t
i
o
n
s
,
l
e
a
d
i
n
g
t
o
h
i
g
h
e
r
a
ccu
ra
cy
.
T
h
e
e
n
s
em
b
l
e
cl
as
s
i
fi
e
r
s
h
o
w
ed
t
h
e
b
e
s
t
acc
u
ra
cy
9
9
.
6
%
o
n
p
re
p
ro
ce
s
s
ed
ch
e
s
t
X
-
ra
y
s
.
K
e
y
w
o
r
d
s
:
De
e
p
l
e
a
r
ni
ng
I
n
t
e
l
l
i
g
e
n
t
m
o
de
l
P
u
l
m
o
n
a
r
y
T
B
T
B
de
t
e
c
t
i
o
n
T
ub
e
r
c
u
l
o
s
i
s
Th
i
s
i
s
a
n
o
p
en
a
c
ces
s
a
r
t
i
c
l
e
u
n
d
e
r
t
h
e
CC
B
Y
-
SA
l
i
cen
s
e.
C
or
r
e
s
pon
din
g
A
u
th
or
:
Ab
du
l
K
a
r
i
m
S
i
dd
i
qu
i
S
c
h
o
o
l
o
f
C
o
m
put
e
r
S
c
i
e
n
c
e
a
n
d
A
pp
li
c
a
t
i
o
n
,
L
o
v
e
l
y
P
r
o
f
e
s
s
i
o
n
a
l
U
ni
ve
r
s
i
t
y
P
h
a
gwa
r
a
,
I
n
d
i
a
E
m
a
i
l
:
a
b
du
l
.
m
o
m
e
n
t
u
m
@h
o
t
m
a
il
.
c
o
m
1.
I
NT
RODU
C
T
I
ON
T
ub
e
r
c
u
l
o
s
i
s
(
TB
)
i
s
t
e
r
m
e
d
a
s
o
n
e
o
f
t
h
e
s
e
v
e
r
e
c
o
n
t
a
gi
o
us
i
s
s
ue
s
wo
r
l
dw
i
de
.
A
pe
r
s
o
n
s
u
f
f
e
r
i
n
g
f
r
o
m
T
B
m
a
y
c
o
n
t
a
i
n
my
c
o
b
a
c
t
e
r
i
u
m
T
B
b
a
c
t
e
r
i
a
a
n
d
m
a
y
t
r
a
n
s
mi
t
t
h
e
i
n
f
e
c
t
i
o
n
dur
i
n
g
c
o
ughi
ng
o
r
whi
l
e
t
a
l
k
i
ng
to
a
pe
r
s
o
n
n
e
a
r
t
h
e
m
.
T
h
e
dr
o
pl
e
t
s
t
h
a
t
e
xi
s
t
i
n
t
h
e
a
i
r
m
e
d
i
u
m
c
a
n
b
e
pa
s
s
e
d
e
v
e
n
by
s
n
e
e
z
i
n
g.
I
t
m
u
l
t
i
p
l
i
e
s
whe
n
a
h
e
a
l
t
hy
pe
r
s
o
n
c
o
m
e
s
i
n
c
l
o
s
e
phy
s
i
c
a
l
c
o
n
t
a
c
t
wi
t
h
a
T
B
-
i
nf
e
c
t
e
d
pe
r
s
o
n
.
I
t
h
ur
t
s
o
n
e
's
l
u
n
gs
a
n
d
i
s
c
a
ll
e
d
pu
l
m
o
n
a
r
y
T
B
.
I
t
h
a
s
r
e
m
a
in
e
d
a
g
l
o
b
a
l
c
h
a
ll
e
n
g
e
f
o
r
de
c
a
de
s
.
De
v
e
l
o
p
i
ng
c
o
un
t
r
i
e
s
a
pp
l
y
t
h
e
t
r
a
di
t
i
o
n
a
l
T
B
d
i
a
g
n
o
s
t
i
c
pr
a
c
t
i
c
e
s
to
e
r
a
d
i
c
a
t
e
i
t
f
r
o
m
s
o
c
i
e
t
y
.
A
s
pe
r
W
HO
da
t
a
,
T
B
i
s
o
n
e
o
f
t
h
e
f
a
t
a
l
l
i
f
e
-
t
h
r
e
a
t
e
ni
ng
c
h
a
ll
e
n
ge
s
.
M
o
s
t
l
y
,
t
h
e
S
o
u
t
h
As
i
a
n
c
o
un
t
r
i
e
s
ha
v
e
hi
g
h
f
a
t
a
l
i
t
y
r
a
t
e
s
.
M
i
ll
i
o
n
s
o
f
t
h
e
y
o
u
n
g
ge
n
e
r
a
t
i
o
n
a
r
e
a
t
r
i
s
k.
R
e
ga
r
d
i
n
g
I
n
d
i
a
n
s
u
bc
o
n
t
i
n
e
n
t
,
t
h
e
r
ur
a
l
I
n
d
i
a
ns
n
e
e
d
pr
o
pe
r
a
tt
e
n
t
i
o
n
a
n
d
c
a
r
e
,
wh
e
r
e
e
f
f
e
c
t
i
ve
h
e
a
l
t
h
c
a
r
e
s
e
t
ups
m
a
n
da
t
e
s
n
e
ut
r
a
l
i
z
a
t
i
o
n
o
f
T
B
.
B
u
i
l
d
i
ng
o
n
pr
e
vi
o
us
wo
r
k
[
1]
a
da
p
ted
a
T
B
de
t
e
c
t
i
o
n
m
o
du
l
e
to
f
o
c
us
o
n
l
u
n
g
f
i
e
l
d
s
e
g
m
e
n
t
a
t
i
o
n
a
n
d
a
tt
e
m
pt
e
d
95.
6%
a
c
c
ur
a
c
y
.
M
L
c
a
n
a
c
qui
r
e
f
r
o
m
un
s
up
e
r
vi
s
e
d
da
t
a
.
E
v
e
n
w
he
n
i
n
put
i
s
u
n
s
t
r
uc
t
u
r
e
d
o
r
l
a
c
k
s
pr
o
pe
r
l
a
b
e
li
ng,
i
t
pr
e
d
i
c
t
s
m
o
r
e
s
o
phi
s
t
i
c
a
l
ly
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
15
,
N
o.
1
,
M
a
r
c
h
20
26
:
40
5
-
41
3
406
M
u
l
t
i
-
l
a
y
e
r
n
e
ur
a
l
n
e
t
wo
r
k
c
o
n
s
i
s
t
s
o
f
s
e
v
e
r
a
l
l
a
y
e
r
s
o
f
n
e
ur
o
ns
,
s
e
r
vi
n
g
a
s
a
uni
qu
e
m
o
de
l
t
o
a
dd
r
e
s
s
v
a
r
i
o
us
r
e
a
l
-
wo
r
l
d
s
c
e
n
a
r
i
o
s
.
I
t
d
o
e
s
pr
e
di
c
t
i
o
ns
s
o
m
e
h
o
w
a
s
h
u
m
a
n
be
i
ngs
.
B
y
up
s
c
a
li
ng
t
h
e
s
e
l
f
-
l
e
a
r
ni
ng
f
e
a
t
ur
e
,
DL
p
r
o
c
e
s
s
e
s
da
t
a
to
b
r
i
n
g
m
e
a
ni
ng
f
u
l
r
e
s
u
l
t
s
.
T
h
e
c
o
n
n
e
c
t
e
d
n
o
de
s
a
r
e
r
e
f
e
r
r
e
d
to
a
s
n
e
ur
o
n
s
.
F
i
l
t
e
r
i
ng
a
n
d
ga
m
m
a
c
o
r
r
e
c
t
i
o
n
we
r
e
s
up
p
l
i
e
d
by
[
2]
i
n
t
h
e
T
B
m
o
de
l
.
A
bb
a
s
e
t
al.
[
3]
w
o
r
ke
d
o
n
De
T
r
a
C
us
i
ng
t
r
a
n
s
f
e
r
l
e
a
r
ni
ng.
He
us
e
d
i
m
ba
l
a
n
c
e
d
da
t
a
s
e
t
s
.
B
y
i
n
t
r
o
duc
i
n
g
pa
r
a
m
e
t
r
i
c
va
r
i
a
t
i
o
ns
i
n
C
NN
a
r
c
hi
t
e
c
t
ur
e
,
h
e
b
r
o
ugh
t
de
t
e
c
t
i
o
n
o
f
P
T
B
-
p
o
s
i
t
i
v
e
c
a
s
e
s
.
H
oo
da
e
t
al.
[
4
]
us
e
d
a
DL
to
e
x
a
m
i
ne
T
B
i
n
bi
na
r
y
c
l
a
s
s
i
f
i
c
a
t
i
o
n
s
a
n
d
s
e
c
ur
e
d
82%
a
c
c
ur
a
c
y
.
S
c
hl
o
a
r
[
5]
p
r
e
s
e
n
t
e
d
a
C
A
D
s
y
s
t
e
m
f
o
r
l
u
n
g
i
m
a
ge
pa
tt
e
r
n
r
e
c
o
gni
t
i
o
n
o
n
C
NN
s
.
He
g
ot
a
n
a
c
c
ur
a
c
y
o
f
88%
.
M
e
r
a
j
e
t
al.
[
6]
c
o
m
pa
r
e
d
t
h
e
v
a
r
i
o
us
c
l
a
s
s
i
f
i
e
r
s
,
vi
z
.
VG
Gs
,
Go
ogL
e
N
e
t
,
a
n
d
R
e
s
i
dua
l
Ne
t
50.
Ya
da
v
e
t
al.
[
7]
s
ke
tch
e
d
T
B
d
i
a
g
n
o
s
t
i
c
s
o
n
a
s
i
mi
l
a
r
C
NN
-
b
a
s
e
d
t
r
a
n
s
f
e
r
l
e
a
r
ni
ng,
ge
tt
i
n
g
94%
a
c
c
ur
a
c
y
.
R
a
hm
a
n
e
t
al.
[
8]
e
x
a
mi
ne
d
ni
ne
C
NN
c
l
a
s
s
i
f
i
e
r
s
f
o
r
t
h
e
s
e
g
m
e
n
t
a
t
i
o
n
pr
o
c
e
s
s
a
n
d
f
o
r
t
h
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
.
He
s
e
c
ur
e
d
96%
a
c
c
ur
a
c
y
i
n
hi
s
wo
r
k
.
Da
s
a
n
a
y
a
ka
a
n
d
D
i
s
s
a
n
a
y
a
ke
[
9]
,
h
e
u
s
e
d
a
n
e
ns
e
m
b
l
e
m
o
de
l
o
n
t
wo
b
a
s
e
c
l
a
s
s
if
i
e
r
s
u
s
i
n
g
T
B
r
a
d
i
o
gr
a
ph
s
.
He
m
e
n
t
i
o
ne
d
a
n
a
c
c
ur
a
c
y
o
f
0.
971.
T
h
e
i
nve
s
t
i
ga
t
o
r
s
[
10
]
us
e
d
i
m
a
g
e
e
nh
a
n
c
e
m
e
n
t
t
e
c
hni
que
s
a
n
d
f
e
d
t
h
e
r
a
di
o
gr
a
phs
i
n
t
o
t
h
e
R
e
s
Ne
t
,
a
n
d
a
f
e
w
ot
h
e
r
DL
m
o
de
l
s
t
o
ge
t
hi
g
h
e
r
a
c
c
ur
a
c
y
t
h
a
t
e
xi
s
t
e
d
89%
.
T
h
e
i
nv
e
s
t
i
ga
t
o
r
s
[
11]
pr
o
p
o
s
e
s
C
NN
s
to
c
l
a
s
s
if
y
o
b
t
a
i
n
e
d
c
l
i
n
i
c
a
l
i
m
a
ge
s
’
a
bn
o
r
m
a
li
t
i
e
s
i
n
a
n
e
ns
e
m
b
l
e
e
nvi
r
o
nm
e
n
t
.
T
h
a
t
s
t
udy
[
12]
us
e
d
a
ge
n
e
r
a
li
z
e
d
pr
e
-
t
r
a
i
n
e
d
s
y
s
t
e
m
.
T
h
e
y
go
t
a
c
c
ur
a
c
i
e
s
o
f
81.
25%
wi
t
h
im
a
ge
a
ug
m
e
n
t
a
t
i
o
n
a
n
d
80%
w
i
t
h
o
u
t
i
t
s
i
m
u
l
t
a
n
e
o
us
ly
.
T
he
i
r
s
t
udy
i
nc
o
r
po
r
a
t
e
d
l
e
a
d
i
ng
s
t
a
t
e
-
of
-
t
h
e
-
a
r
t
pr
e
-
t
r
a
i
n
e
d
de
e
p
C
NN
s
f
o
r
c
h
e
s
t
r
a
d
i
o
gr
a
ph
s
f
o
r
t
h
e
c
l
a
s
s
if
i
c
a
t
i
o
n
.
I
t
di
s
t
i
n
gu
i
s
h
e
d
b
e
t
we
e
n
n
o
r
m
a
l
a
n
d
P
T
B
-
i
n
f
e
c
t
e
d
c
a
s
e
s
.
L
o
pe
s
a
n
d
Va
li
a
t
i
[
13]
us
e
d
publ
ic
X
-
r
a
y
l
a
b
e
l
e
d
da
t
a
s
e
t
s
.
P
r
e
-
t
r
a
i
n
e
d
C
NN
s
we
r
e
us
e
d
a
s
c
l
a
s
s
if
i
e
r
s
a
n
d
c
l
a
im
e
d
a
n
a
c
c
ur
a
c
y
o
f
up
to
96.
1
%
.
M
i
z
a
n
e
t
al.
[
14]
,
DC
NN
s
a
r
e
h
i
g
hly
e
f
f
e
c
t
i
ve
f
o
r
TB
de
t
e
c
t
i
o
n
f
r
o
m
c
h
e
s
t
X
-
r
a
y
i
m
a
ge
s
,
w
i
t
h
R
e
s
Ne
t
50
e
m
e
r
g
i
ng
a
s
t
h
e
m
o
s
t
e
f
f
i
c
i
e
n
t
m
o
de
l
a
m
o
n
g
t
h
o
s
e
t
e
s
t
e
d.
C
a
o
e
t
a
l.
[
15]
e
m
p
ha
s
i
z
e
d
C
NN
s
a
s
hi
g
hly
e
f
f
e
c
t
i
v
e
f
o
r
c
l
a
s
s
i
f
yi
ng
T
B
wh
e
n
c
o
m
bi
ne
d
w
i
t
h
his
to
gr
a
m
m
a
t
c
hi
ng
t
e
c
h
ni
qu
e
s
,
b
ut
t
h
e
i
r
s
t
udy
l
a
c
ks
s
e
g
m
e
n
t
a
t
i
o
n
.
T
h
e
r
e
s
e
a
r
c
h
e
r
s
[
16]
a
i
m
e
d
to
c
o
m
pa
r
e
a
c
us
to
m
C
NN
t
r
a
i
n
e
d
f
r
o
m
s
c
r
a
t
c
h
w
i
t
h
s
e
ve
r
a
l
pr
e
-
t
r
a
i
ne
d
C
NN
m
o
de
l
s
u
s
i
n
g
t
r
a
ns
f
e
r
l
e
a
r
ni
ng,
w
i
t
h
a
c
l
a
im
e
d
a
c
c
ur
a
c
y
o
f
87%
.
E
T
DH
DN
e
t
,
p
r
o
p
o
s
e
d
by
[
17]
,
i
s
a
De
ns
e
Ne
t
-
b
a
s
e
d
m
o
de
l
t
o
i
n
t
e
gr
a
t
e
e
x
t
e
n
de
d
t
e
x
t
u
r
e
de
s
c
r
i
pt
o
r
s
.
T
h
e
wor
k
a
c
hi
e
v
e
d
A
U
C
s
c
o
r
e
s
o
f
m
o
r
e
t
h
a
n
99
%
a
s
c
l
a
i
m
e
d.
T
h
e
i
n
t
r
o
duc
t
i
o
n
de
s
c
r
i
be
s
t
h
e
s
e
v
e
r
i
t
y
o
f
t
h
e
pr
o
bl
e
m
a
n
d
wo
r
l
dw
i
de
e
f
f
o
r
t
s
to
e
r
a
di
c
a
t
e
pul
m
o
n
a
r
y
TB
.
R
e
l
a
t
e
d
w
o
r
ks
i
n
t
hi
s
d
i
r
e
c
t
i
o
n
us
i
n
g
i
n
t
e
ll
i
ge
n
t
m
o
de
l
s
a
r
e
de
s
c
r
i
b
e
d.
S
e
c
t
i
o
n
2
pr
e
s
e
n
t
s
t
h
e
m
e
t
h
o
do
l
o
g
y
f
o
r
t
h
e
de
t
e
c
t
i
o
n
s
y
s
t
e
m
,
hi
g
hli
g
h
t
i
n
g
pr
e
pr
o
c
e
s
s
i
ng,
da
t
a
s
e
t
s
de
s
c
r
i
pt
i
o
n
,
t
h
e
pr
o
p
o
s
e
d
s
y
s
t
e
m
,
a
n
d
e
x
pe
r
i
m
e
n
t
s
.
S
e
c
t
i
o
n
3
e
x
p
l
a
i
n
s
t
h
e
r
e
s
u
l
t
s
a
n
d
d
i
s
c
u
s
s
i
o
ns
o
n
v
a
r
i
o
us
C
N
N
m
o
de
l
s
o
n
T
B
de
t
e
c
t
i
o
n
w
i
t
h
a
n
d
w
i
t
h
o
ut
hi
s
t
o
g
r
a
m
e
qu
a
l
i
z
a
t
i
o
n
,
a
n
d
a
t
r
ue
pi
c
t
ur
e
o
f
e
n
s
e
m
bli
ng
b
a
s
e
c
l
a
s
s
if
i
e
r
s
i
n
t
o
a
s
t
a
c
ke
d
c
l
a
s
s
i
f
i
e
r
.
T
h
e
c
o
n
c
l
u
s
i
o
n
i
s
i
n
s
e
c
t
i
o
n
4
wi
t
h
f
ut
ur
e
w
o
r
k
a
n
d
s
t
udy
t
o
i
n
c
o
r
por
a
t
e
.
2.
RE
S
E
AR
CH
M
E
T
HO
D
T
h
e
o
v
e
r
a
l
l
pr
o
po
s
e
d
m
e
t
h
o
do
l
o
g
y
t
o
de
t
e
c
t
a
n
d
c
l
a
s
s
if
y
P
T
B
c
a
s
e
s
u
s
i
n
g
o
nli
ne
a
n
d
o
f
f
li
ne
C
h
e
s
t
X
-
r
a
y
i
m
a
ge
s
i
s
de
s
c
r
i
be
d
i
n
t
h
e
m
e
t
h
o
do
l
o
g
y
s
e
c
t
i
o
n
.
I
t
us
e
s
pr
e
pr
o
c
e
s
s
i
n
g
a
n
d
a
ug
m
e
n
t
a
t
i
o
n
o
f
t
h
e
da
t
a
s
e
t
,
I
n
put
e
n
ha
n
c
e
d
by
hi
s
t
o
gr
a
m
e
qu
a
l
i
z
a
t
i
o
n
.
T
h
e
e
ns
e
m
bl
e
s
t
a
c
ke
d
m
o
de
l
s
h
o
ws
t
h
e
b
e
s
t
o
f
t
h
e
f
us
e
d
a
tt
r
i
b
ut
e
s
o
f
t
w
o
di
f
f
e
r
e
n
t
c
l
a
s
s
i
f
i
e
r
s
.
S
to
r
i
n
g
t
h
e
da
t
a
s
e
t
i
s
c
r
uc
i
a
l
a
n
d
i
s
t
h
e
i
ni
t
i
a
l
s
t
e
p
i
n
pr
e
d
i
c
t
i
o
n
m
o
de
l
de
s
i
g
n
.
I
t
de
c
i
de
s
t
h
e
pa
t
t
e
r
n
w
i
t
hi
n
s
upe
r
vi
s
e
d
l
e
a
r
ni
ng.
I
t
a
l
s
o
e
x
t
r
a
c
t
s
i
m
po
r
t
a
n
t
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
dur
i
n
g
t
h
e
DL
pr
o
c
e
s
s
.
T
h
us
,
i
t
i
s
o
f
ut
m
o
s
t
i
m
po
r
t
a
n
c
e
to
c
o
n
v
e
r
t
i
m
a
g
e
da
t
a
i
n
t
o
a
s
t
r
uc
t
ur
e
d
a
n
d
s
t
a
n
da
r
d
i
z
e
d
f
o
r
m
a
t
.
2.
1.
D
at
as
e
t
s
d
e
s
c
r
ip
t
ion
T
h
e
M
.
C
o
un
t
y
C
X
R
s
e
t
i
s
d
i
s
t
i
n
gu
i
s
he
d
by
i
t
s
i
n
c
l
u
s
i
o
n
o
f
m
a
n
ua
ll
y
s
e
g
m
e
n
t
e
d
l
u
n
g
m
a
s
ks
f
o
r
a
s
ubs
e
t
o
f
i
t
s
138
DI
C
OM
-
f
o
r
m
a
t
.
T
h
e
s
e
i
m
a
g
e
s
,
c
o
m
pr
i
s
i
ng
80
n
or
m
a
l
a
n
d
58
pot
e
n
t
i
a
l
ly
T
B
-
po
s
i
t
i
v
e
c
a
s
e
s
,
a
r
e
a
c
c
o
m
pa
ni
e
d
by
de
t
a
i
l
e
d
r
a
d
i
o
l
o
g
y
r
e
a
d
i
ngs
in
t
e
x
t
f
i
l
e
s
.
I
n
c
o
n
t
r
a
s
t
,
t
h
e
S
.
H
o
s
p
i
t
a
l
C
X
R
S
e
t
,
a
c
qu
i
r
e
d
f
r
o
m
S
h
e
n
z
h
e
n
,
C
hi
na
,
o
f
f
e
r
s
a
l
a
r
ge
r
c
o
l
l
e
c
t
i
o
n
o
f
662
J
P
E
G
-
f
o
r
m
a
t
i
m
a
ge
s
—
326
n
o
r
m
a
l
a
n
d
336
a
bn
o
r
m
a
l
—
s
pa
nni
ng
b
o
t
h
a
du
l
t
a
n
d
pe
d
i
a
t
r
i
c
c
a
s
e
s
.
T
h
e
NI
A
I
D
T
B
P
o
r
t
a
l
s
P
r
o
gr
a
m
s
t
a
n
d
s
o
u
t
a
s
a
c
o
m
pr
e
h
e
ns
i
ve
i
n
t
e
r
n
a
t
i
o
n
a
l
r
e
po
s
i
t
o
r
y
,
i
n
t
e
gr
a
t
i
n
g
o
v
e
r
4,
200
r
a
d
i
o
gr
a
ph
s
(
3,
500
n
o
r
m
a
l
a
n
d
700
T
B
-
po
s
i
t
i
v
e
)
w
i
t
h
m
u
l
t
i
-
do
m
a
i
n
da
t
a
l
i
nke
d
t
o
i
n
d
i
v
i
d
ua
l
pa
t
i
e
n
t
s
.
T
h
i
s
i
nc
l
ud
e
s
r
a
d
i
o
l
o
g
i
c
a
l
im
a
ge
s
,
c
l
ini
c
a
l
a
n
d
l
a
b
o
r
a
tor
y
r
e
po
r
t
s
,
ge
n
o
m
i
c
da
t
a
,
a
n
d
s
o
c
i
o
e
c
o
n
o
m
i
c
a
n
d
ge
o
gr
a
phi
c
c
o
n
t
e
x
t
.
D
a
t
a
f
r
o
m
T
B
s
us
pe
c
t
s
,
i
nc
l
ud
i
ng
o
u
t
pa
t
i
e
n
t
pr
e
s
c
r
i
pt
i
o
n
s
a
n
d
im
a
g
i
ng
r
e
c
o
r
ds
f
r
o
m
H
A
HC
H
i
n
Ne
w
De
l
h
i
,
we
r
e
c
o
l
l
e
c
t
e
d
b
e
t
we
e
n
J
u
l
y
2021
a
n
d
J
u
n
e
2024,
o
f
f
e
r
i
n
g
a
r
i
c
h
r
e
s
o
ur
c
e
f
o
r
h
o
l
i
s
t
i
c
T
B
r
e
s
e
a
r
c
h
a
n
d
pr
e
d
i
c
t
i
v
e
m
o
de
l
i
ng.
2.
2.
Ches
t
X
-
r
ay
an
d
f
e
at
u
r
e
e
x
t
r
ac
t
ion
T
h
e
ga
i
ne
d
c
h
e
s
t
X
-
r
a
y
im
a
ge
s
e
xhi
bi
t
v
a
r
i
a
t
i
o
n
s
i
n
s
i
z
e
a
n
d
m
a
y
b
e
e
i
t
h
e
r
c
o
l
o
r
-
gr
a
y
s
c
a
l
e
o
r
R
GB
due
to
a
v
a
i
l
a
bil
i
t
y
f
r
o
m
t
h
e
d
i
ve
r
s
e
s
o
ur
c
e
s
.
T
o
gu
a
r
a
n
t
e
e
unif
o
r
m
i
t
y
,
a
l
l
a
c
qu
i
r
e
d
r
a
w
da
t
a
we
r
e
c
o
nv
e
r
t
e
d
to
gr
a
y
s
c
a
l
e
.
T
h
e
c
o
nn
e
c
t
e
d
l
a
y
e
r
s
t
h
a
t
c
o
m
po
s
e
C
NN
a
r
c
hi
t
e
c
t
ur
e
i
n
s
e
r
t
c
o
n
s
i
s
t
e
n
t
i
m
a
ge
d
im
e
ns
i
o
ns
.
P
r
e
pr
o
c
e
s
s
i
n
g
o
f
a
ll
c
li
n
i
c
a
l
im
a
g
e
s
s
e
r
v
e
s
t
h
e
pur
po
s
e
o
f
e
nh
a
n
c
i
ng
da
t
a
qua
l
i
t
y
by
m
o
d
if
yi
ng
un
de
s
i
r
e
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
De
tec
ti
on
mode
l
f
or
pulmonar
y
tuber
c
ulos
is
and
p
e
r
f
or
manc
e
e
v
aluat
ion
on
…
(
A
bdul
K
ar
im
Siddi
q
ui
)
407
d
i
s
t
o
r
t
i
o
n
s
a
n
d
a
c
c
e
n
t
i
n
g
r
e
l
e
v
a
n
t
f
e
a
t
ur
e
s
f
o
r
s
u
b
s
e
que
n
t
pr
o
c
e
s
s
i
n
g
a
n
d
a
n
a
ly
s
i
s
.
T
h
e
R
OI
,
de
n
ot
i
n
g
t
h
e
a
r
e
a
o
f
i
n
t
e
r
e
s
t
,
i
n
pr
o
p
o
s
e
d
c
a
s
e
-
t
h
e
c
a
vi
t
i
e
s
o
n
t
h
e
l
u
n
g
s
ur
f
a
c
e
,
i
s
we
l
l
r
e
c
o
gni
z
e
d
by
t
h
e
s
e
g
m
e
n
t
a
t
i
o
n
.
T
hi
s
i
s
i
m
po
r
t
a
n
t
s
t
e
p
to
a
dm
i
t
s
ubs
e
que
n
t
f
e
a
t
ur
e
e
x
t
r
a
c
t
i
o
n
f
o
c
us
e
s
o
n
r
e
l
e
v
a
n
t
r
e
g
i
o
n
s
o
f
i
n
t
e
r
e
s
t
.
T
h
e
s
e
f
e
a
t
ur
e
s
i
n
c
l
ude
s
h
a
pe
,
i
n
t
e
ns
i
t
y
,
t
e
x
t
ur
e
,
a
n
d
s
t
a
t
i
s
t
i
c
a
l
m
e
a
s
ur
e
s
.
2.
3.
I
m
age
p
r
e
p
r
oc
e
s
s
in
g
P
r
e
pr
o
c
e
s
s
i
n
g
i
s
t
h
e
i
ni
t
i
a
l
s
t
e
p
to
wa
r
ds
da
t
a
p
r
e
pa
r
a
t
i
o
n
[
18]
.
B
e
f
o
r
e
t
h
e
i
ns
e
r
t
i
o
n
o
f
t
h
e
i
nput
im
a
ge
i
n
t
o
t
h
e
pr
o
p
o
s
e
d
A
I
m
o
de
l
,
da
t
a
s
e
t
s
a
r
e
c
l
e
a
ne
d
t
h
r
o
ugh
v
a
r
i
o
us
pr
e
pr
o
c
e
s
s
i
n
g
t
e
c
hni
que
s
.
I
n
t
h
e
pr
o
p
o
s
e
d
w
o
r
k
,
b
ot
h
o
nl
i
ne
a
n
d
o
f
f
li
ne
X
-
r
a
y
im
a
g
e
s
h
a
d
d
if
f
e
r
e
n
t
i
m
pur
i
t
y
i
s
s
u
e
s
.
T
h
e
o
nl
i
ne
im
a
ge
da
t
a
s
e
t
s
h
a
d
s
i
z
e
v
a
r
i
a
bil
i
t
y
w
i
t
h
d
i
f
f
e
r
i
n
g
im
a
ge
t
y
p
e
s
a
nd
c
o
l
o
ur
i
s
s
ue
s
.
S
i
mi
l
a
r
l
y
,
t
h
e
o
f
f
-
li
ne
c
h
e
s
t
X
-
r
a
y
i
m
a
g
e
s
h
a
d
pr
o
bl
e
m
s
li
ke
i
m
a
ge
i
nve
r
s
i
o
n
,
r
ot
a
t
i
o
n
,
gr
a
y
s
c
a
l
e
a
n
d
c
o
l
o
ur
e
d
i
m
a
ge
s
,
f
li
pp
i
ng
i
s
s
ue
,
unc
r
o
ppe
d
im
a
ge
s
,
e
t
c
.
Al
l
t
h
e
s
e
t
y
p
e
s
o
f
o
dd
p
o
i
n
t
s
we
r
e
r
e
m
o
v
e
d
us
i
ng
t
h
e
pr
o
c
e
s
s
o
f
c
r
o
ppi
n
g,
f
li
pp
i
ng,
r
e
s
i
z
i
ng,
gr
a
y
s
c
a
l
i
ng,
r
ot
a
t
i
o
n
,
a
n
d
t
y
p
e
c
o
n
v
e
r
s
i
o
n
.
Al
t
h
o
ugh
t
h
e
m
a
j
o
r
X
-
r
a
y
s
c
o
n
t
a
i
ne
d
o
n
e
c
o
l
o
ur
c
h
a
nne
l
,
s
o
m
e
o
f
t
h
e
m
ha
d
t
h
r
e
e
c
o
l
o
ur
c
h
a
nn
e
l
s
.
T
o
hi
de
t
h
e
e
f
f
e
c
t
o
f
bl
ue
c
o
l
o
ur
,
s
uc
h
i
m
a
ge
s
we
r
e
c
o
n
v
e
r
t
e
d
f
r
o
m
R
GB
to
gr
a
y
s
c
a
l
e
.
T
h
e
P
NG
f
o
r
m
a
t
wa
s
a
pp
li
e
d
t
o
di
m
e
ns
i
o
ns
o
f
250
X
250
X
3
r
e
s
o
l
ut
i
o
n
.
F
i
gur
e
1
c
o
n
t
a
i
ns
T
B
i
n
f
e
c
t
e
d
a
r
e
a
s
o
v
e
r
l
u
n
g
s
.
F
i
gur
e
1(
a
)
i
s
s
h
o
w
i
n
g
i
nf
e
c
t
i
o
n
o
n
t
h
e
r
i
g
h
t
uppe
r
l
o
b
e
,
F
i
gur
e
1(
b
)
on
lym
p
h
n
o
de
,
F
i
gur
e
1(
c
)
o
n
l
e
f
t
uppe
r
l
o
b
e
a
n
d
F
i
gur
e
1(
d)
a
s
a
i
r
s
pa
c
e
o
pa
c
i
t
i
e
s
.
(
a
)
(
b
)
(
c
)
(
d)
F
i
gur
e
1.
I
n
f
e
c
t
e
d
a
r
e
a
o
f
T
B
o
n
l
u
n
gs
:
(
a
)
c
o
a
l
e
s
c
in
g
a
i
r
s
pa
c
e
o
pa
c
i
t
y
o
n
t
h
e
r
i
g
h
t
uppe
r
l
o
b
e
,
(
b
)
e
nlar
ge
d
hil
a
r
a
n
d
m
e
d
i
a
s
t
i
n
a
l
lym
p
h
n
o
de
s
,
(
c
)
T
hi
c
k
-
wa
ll
e
d
c
a
vi
t
a
r
y
l
e
s
i
o
n
i
n
t
h
e
l
e
f
t
uppe
r
l
o
b
e
,
a
n
d
(
d)
bi
l
a
t
e
r
a
l
a
p
i
c
a
l
t
hi
c
k
-
wa
ll
e
d
c
a
vi
t
i
e
s
m
u
l
t
if
o
c
a
l
s
a
t
e
l
li
t
e
a
i
r
s
pa
c
e
o
pa
c
i
t
i
e
s
2.
4.
Au
gm
e
n
t
at
ion
an
d
d
at
s
e
t
s
p
ar
t
ion
I
m
a
ge
a
ug
m
e
n
t
a
t
i
o
n
i
s
r
e
s
o
l
ut
e
s
t
e
p
i
n
c
o
m
put
e
r
vi
s
i
o
n
a
n
d
i
n
DL
-
b
a
s
e
d
c
l
a
s
s
if
i
c
a
t
i
o
n
s
.
I
t
e
n
r
i
c
he
s
i
ns
o
ur
c
e
d
c
l
i
n
i
c
a
l
im
a
ge
s
by
f
i
r
s
t
r
e
m
o
vi
ng
u
nn
e
c
e
s
s
a
r
y
de
t
a
i
l
s
[
19]
.
I
t
s
h
o
ul
d
b
e
a
pp
li
e
d
dur
i
ng
t
r
a
i
n
i
ng
o
nl
y
,
n
o
t
dur
i
n
g
i
nf
e
r
e
n
c
e
a
s
s
h
o
wn
i
n
F
i
gur
e
2.
T
r
a
i
ni
ng
da
t
a
s
e
t
s
a
r
e
c
h
a
n
ge
d
i
n
t
o
n
o
r
m
a
li
z
e
d
s
i
z
e
s
to
a
v
o
i
d
o
v
e
r
-
f
i
t
t
i
n
g.
F
i
gur
e
2.
Un
c
l
e
a
n
s
e
d
X
-
r
a
y
im
a
ge
s
A
ug
m
e
n
t
a
t
i
o
n
i
s
us
e
d
a
l
o
n
g
s
i
d
e
da
t
a
s
e
t
pa
r
t
i
t
i
o
ni
n
g
w
i
t
h
t
h
e
tot
a
l
i
m
a
g
e
c
o
l
l
e
c
t
i
o
n
d
i
v
i
de
d
i
n
t
o
70%
f
o
r
tr
a
i
ni
ng,
15%
f
o
r
v
a
l
i
da
t
i
o
n
,
a
n
d
15%
f
o
r
t
e
s
t
i
n
g.
A
tot
a
l
o
f
6221
c
h
e
s
t
X
-
r
a
y
i
m
a
ge
s
c
o
n
t
a
i
ni
ng
b
o
t
h
n
o
r
m
a
l
a
n
d
pu
lm
o
n
a
r
y
T
B
c
a
s
e
s
we
r
e
c
o
l
l
e
c
t
e
d,
w
i
t
h
4355
a
l
l
o
c
a
t
e
d
f
o
r
t
r
a
i
ni
ng,
933
f
o
r
v
a
l
i
d
a
t
i
o
n
,
a
n
d
t
e
s
t
i
n
g,
r
e
s
pe
c
t
i
v
e
ly
a
s
s
h
o
wn
i
n
T
a
bl
e
1.
Hi
s
t
o
gr
a
m
E
qua
l
i
z
a
t
i
o
n
i
s
ba
s
i
c
a
ll
y
a
r
e
d
i
s
t
r
i
b
ut
i
o
n
o
f
p
i
x
e
l
i
n
t
e
n
s
i
t
i
e
s
s
o
t
h
a
t
t
h
e
y
b
e
c
o
m
e
m
o
r
e
unif
o
r
m
ly
d
i
s
t
r
i
b
ut
e
d
a
c
r
o
s
s
t
h
e
e
n
t
i
r
e
a
v
a
il
a
bl
e
i
n
t
e
ns
i
t
y
r
a
nge
.
T
hi
s
t
r
a
n
s
f
o
r
m
a
t
i
o
n
e
ns
ur
e
s
t
h
a
t
t
h
e
o
u
t
pu
t
hi
s
t
o
gr
a
m
i
s
a
ppr
o
xi
m
a
t
e
l
y
u
ni
f
o
r
m
[
20]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
15
,
N
o.
1
,
M
a
r
c
h
20
26
:
40
5
-
41
3
408
T
a
bl
e
1.
I
m
a
ge
da
t
a
s
e
t
s
i
n
t
h
e
pr
o
p
o
s
e
d
w
o
r
k
D
a
ta
s
e
ts
N
O
R
M
L
P
T
B
T
r
a
in
V
a
li
da
ti
o
n
T
e
s
t
T
ot
a
l
T
r
a
in
V
a
li
da
ti
o
n
T
e
s
t
T
ot
a
l
M.
C
o
unt
y
56
12
12
80
41
8
9
58
S.
H
o
s
pi
ta
l
227
49
49
325
235
51
50
336
N
I
A
D
1674
358
358
2390
490
105
105
700
B
e
la
r
us
0
0
0
700
150
150
1000
H
A
H
C
H
o
s
pi
ta
l
222
48
48
318
710
152
152
1014
T
O
T
A
L
2179
467
467
3113
2176
466
466
3108
2.
5.
P
r
op
os
e
d
m
e
t
h
od
T
e
n
d
i
f
f
e
r
e
n
t
DC
NN
s
a
r
e
s
t
ud
i
e
d
s
o
t
h
a
t
t
h
e
o
u
t
c
o
m
e
s
w
i
ll
h
a
ve
a
t
r
i
b
ut
e
d
X
-
r
a
y
s
’
a
bn
o
r
m
a
li
t
y
de
t
e
c
t
i
o
ns
a
n
d
t
h
us
t
h
e
i
ni
t
i
a
l
TB
s
c
r
e
e
ni
n
g
a
n
d
r
e
l
a
t
e
d
pr
e
di
c
t
i
o
n
c
a
n
b
e
a
c
hi
e
v
e
d.
On
t
h
e
b
a
s
i
s
o
f
c
o
l
l
e
c
t
e
d
C
he
s
t
r
a
di
o
gr
a
ph
s
,
a
l
l
s
t
a
t
e
-
of
-
t
h
e
-
a
r
t
c
l
a
s
s
i
f
i
e
r
s
w
e
r
e
t
r
a
i
n
e
d
o
n
t
h
e
gi
v
e
n
T
r
a
i
ni
ng
da
t
a
s
e
t
s
(
70%
o
f
t
h
e
tot
a
l
o
nl
i
ne
a
n
d
r
e
a
l
i
m
a
g
e
da
t
a
s
e
t
s
)
.
On
f
i
ne
-
t
uni
ng
of
hy
pe
r
-
pa
r
a
m
e
t
e
r
s
,
15%
v
a
l
i
da
t
i
o
n
da
t
a
s
e
t
s
we
r
e
f
e
d
i
n
t
o
t
h
e
pr
e
-
t
r
a
i
n
e
d
m
o
de
l
.
T
h
e
r
e
m
a
i
ni
ng
15%
o
f
t
h
e
un
t
o
uc
h
e
d
da
t
a
s
e
t
s
we
r
e
t
e
s
t
e
d
o
n
a
pr
e
-
tr
a
i
ne
d
m
o
de
l
us
i
n
g
t
r
a
n
s
f
e
r
l
e
a
r
ni
ng.
On
c
o
m
pa
r
i
n
g
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
a
l
l
t
h
e
c
l
a
s
s
if
i
e
r
s
,
t
h
e
t
w
o
b
e
s
t
-
pe
r
f
o
r
m
i
ng
ba
s
e
c
l
a
s
s
if
i
e
r
s
(
R
e
s
Ne
t
50
a
n
d
De
n
s
e
N
e
t
169)
we
r
e
pa
s
s
e
d
i
n
t
o
a
s
t
a
c
ke
d
e
n
s
e
m
b
l
e
c
l
a
s
s
i
f
i
e
r
.
F
e
a
t
ur
e
s
a
r
e
e
x
t
r
a
c
t
e
d
f
r
o
m
t
h
e
s
e
m
o
de
l
s
'
i
n
t
e
r
m
e
d
i
a
t
e
l
a
y
e
r
s
.
T
h
e
s
e
e
x
t
r
a
c
t
e
d
f
e
a
t
ur
e
s
a
r
e
t
h
e
n
c
o
n
c
a
t
e
n
a
t
e
d
i
n
t
o
a
s
i
n
g
l
e
f
e
a
t
ur
e
v
e
c
to
r
,
whi
c
h
s
e
r
v
e
s
a
s
t
h
e
i
n
put
f
o
r
t
h
e
m
e
t
a
-
l
e
a
r
n
e
r
.
T
h
e
XG
B
oo
s
t
m
o
de
l
i
s
t
r
a
i
ne
d
to
m
a
ke
t
h
e
f
i
na
l
bi
na
r
y
c
l
a
s
s
i
f
i
c
a
t
i
o
n
pr
e
d
i
c
t
i
o
n
(
P
T
B
-
p
o
s
i
t
i
ve
o
r
P
T
B
-
n
e
ga
t
i
ve
)
.
A
s
s
h
o
wn
i
n
F
i
gur
e
3.
T
h
i
s
m
e
t
h
o
d
b
r
i
ngs
t
h
e
p
o
we
r
f
u
l
f
e
a
t
ur
e
e
x
tr
a
c
t
i
o
n
a
bil
i
t
i
e
s
of
t
h
e
C
NN
s
whil
e
us
i
n
g
XG
B
o
o
s
t
to
l
e
a
r
n
h
o
w
to
b
e
s
t
c
o
m
bi
ne
t
h
e
i
r
(
p
re
-
tr
a
i
n
e
d
b
a
s
e
c
l
a
s
s
i
f
i
e
r
s
)
pr
e
di
c
t
i
o
n
s
[
21]
.
F
i
gur
e
3.
M
e
t
h
o
d
o
l
o
gy
f
o
r
t
h
e
pr
o
p
o
s
e
d
s
y
s
t
e
m
2.
6
.
E
x
p
e
r
im
e
n
t
s
T
r
a
n
s
f
e
r
l
e
a
r
ni
ng
s
uppo
r
t
s
m
o
de
l
s
to
p
o
we
r
pr
e
vi
o
us
l
y
a
c
qu
i
r
e
d
l
e
a
r
ni
ng
s
f
r
o
m
o
n
e
t
a
s
k
a
n
d
a
pp
ly
t
h
e
m
to
a
s
i
mi
l
a
r
t
a
s
k.
T
hi
s
a
ppr
o
a
c
h
c
o
n
s
t
i
t
ut
e
s
a
pr
e
-
t
r
a
i
n
e
d
m
o
de
l
,
w
hi
c
h
h
a
s
a
l
r
e
a
d
y
b
e
e
n
t
r
a
i
n
e
d
o
n
a
l
a
r
ge
da
t
a
s
e
t
c
o
m
pr
i
s
i
n
g
4355
i
m
a
ge
s
o
f
b
o
t
h
n
o
r
m
a
l
a
n
d
P
T
B
c
a
s
e
s
i
n
t
h
e
pr
o
p
o
s
e
d
w
o
r
k
.
B
y
do
i
n
g
s
o
,
i
t
c
o
n
s
i
de
r
a
bl
y
r
e
duc
e
s
t
r
a
i
ni
ng
t
i
m
e
a
n
d
c
o
m
put
a
t
i
o
n
a
l
r
e
qu
i
r
e
m
e
n
t
s
f
o
r
n
e
w
m
o
de
l
r
unni
ng
w
hi
l
e
e
nh
a
n
c
i
n
g
m
o
de
l
a
c
c
ur
a
c
y
a
n
d
m
i
t
i
ga
t
i
n
g
t
h
e
po
s
s
i
bl
e
i
s
s
ue
o
f
o
v
e
r
f
i
t
t
i
n
g.
I
n
C
NN
-
ba
s
e
d
a
r
c
hi
t
e
c
t
ur
e
,
T
L
pr
o
v
e
s
h
e
l
p
f
u
l
w
h
e
n
de
a
li
ng
w
i
t
h
s
m
a
ll
im
a
ge
d
a
t
a
s
e
t
s
,
e
l
im
i
na
t
i
n
g
t
h
e
n
e
c
e
s
s
i
t
y
f
o
r
e
x
t
e
n
s
i
ve
da
t
a
c
o
l
l
e
c
t
i
o
n
a
n
d
mi
n
im
i
z
i
ng
t
h
e
t
r
a
i
ni
ng
t
i
m
e
.
I
n
t
h
e
s
h
a
r
e
d
a
r
c
hit
e
c
t
ur
e
,
i
n
t
e
r
m
e
d
i
a
t
e
we
i
g
h
t
s
r
e
m
a
i
n
n
o
n
-
t
r
a
i
n
a
ble,
whi
l
e
f
i
na
l
l
a
y
e
r
we
i
g
h
t
s
un
de
r
go
tr
a
i
ni
ng,
w
i
t
h
t
h
e
S
i
g
m
o
i
d
a
c
t
i
va
t
i
o
n
f
u
n
c
t
i
o
n
i
n
t
h
e
f
i
na
l
l
a
y
e
r
.
HE
-
e
nh
a
nc
e
d
im
a
ge
s
we
r
e
pa
r
t
i
t
i
o
n
e
d
i
n
t
o
t
r
a
i
ni
ng,
v
a
l
i
da
t
i
o
n
,
a
n
d
t
e
s
t
i
n
g
s
e
t
s
.
F
o
r
t
r
a
i
ni
ng,
70%
o
f
t
h
e
tot
a
l
i
mage
s
,
a
n
d
30%
f
o
r
v
a
l
i
da
t
i
o
n
a
n
d
t
e
s
t
i
n
g
we
r
e
ke
pt
r
e
s
pe
c
t
i
v
e
ly
.
S
k
l
e
a
r
n
.
m
o
de
l
_
s
e
l
e
c
t
i
o
n
i
m
po
r
t
t
r
a
i
n
_t
e
s
t
_s
p
l
i
t
wa
s
s
e
t
wi
t
h
a
r
a
n
do
m
s
t
a
t
e
o
f
22
f
o
r
r
e
pr
o
duc
i
bil
i
t
y
.
T
h
e
s
y
s
t
e
m
a
l
s
o
i
n
c
o
r
por
a
t
e
s
t
h
e
A
da
m
o
pt
i
m
i
z
e
r
a
l
o
n
gs
i
d
e
B
i
n
a
r
y
C
r
o
s
s
-
E
n
t
r
o
py
a
s
t
h
e
l
o
s
s
f
u
n
c
t
i
o
n
.
T
h
e
pr
o
c
e
s
s
wa
s
e
x
e
c
ut
e
d
o
n
t
h
e
G
oo
gl
e
C
o
l
a
b
us
i
ng
T
e
n
s
o
r
F
l
o
w
us
i
n
g
P
y
t
h
o
n
3.
7.
10.
T
h
e
tr
a
i
ni
ng
pr
o
c
e
dur
e
wa
s
f
i
ne
-
t
un
e
d
ke
e
p
i
ng
b
a
t
c
h
s
i
z
e
o
f
64
a
n
d
a
de
f
a
u
l
t
t
h
r
e
s
h
o
l
d
o
f
0.
5.
T
o
p
r
e
v
e
n
t
o
v
e
r
f
i
t
t
i
n
g,
e
po
c
h
s
we
r
e
r
e
duc
e
d
f
r
o
m
15
to
5
,
e
n
s
ur
i
n
g
o
p
t
i
m
a
l
ge
n
e
r
a
li
z
a
t
i
o
n
a
n
d
a
l
i
g
nm
e
n
t
b
e
t
we
e
n
t
r
a
i
ni
ng,
v
a
li
da
t
i
o
n
,
a
n
d
t
e
s
t
i
n
g
pe
r
f
o
r
m
a
n
c
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
De
tec
ti
on
mode
l
f
or
pulmonar
y
tuber
c
ulos
is
and
p
e
r
f
or
manc
e
e
v
aluat
ion
on
…
(
A
bdul
K
ar
im
Siddi
q
ui
)
409
3.
RE
S
UL
T
S
AN
D
DI
S
CU
S
S
I
ON
A
I
b
a
s
e
d
d
e
t
e
c
t
i
o
n
m
o
de
l
ne
e
ds
t
o
b
e
v
e
r
i
f
i
e
d
o
n
d
i
f
f
e
r
e
n
t
a
s
s
e
s
s
m
e
n
t
pa
r
a
m
e
t
e
r
s
,
e
s
pe
c
i
a
ll
y
m
e
d
i
c
a
l
d
i
a
g
n
o
s
t
i
c
s
y
s
t
e
m
s
a
r
e
v
a
li
da
t
e
d
o
n
t
h
e
f
o
l
l
o
w
i
ng
e
va
l
u
a
t
i
o
n
m
e
t
r
i
c
s
:
1.
S
e
n
s
i
t
i
vi
t
y
2.
P
r
e
c
i
s
i
o
n
3.
S
pe
c
i
f
i
c
i
t
y
4.
A
c
c
ur
a
c
y
5.
F
1
s
c
o
r
e
a
n
d
6.
R
OC
.
3.
1.
P
e
r
f
o
r
m
an
c
e
of
CN
Ns
on
X
-
r
ay
d
at
as
e
t
wit
h
ou
t
HE
T
a
bl
e
2
i
s
s
h
o
wn
t
o
c
o
m
pa
r
e
t
h
e
pe
r
f
o
r
m
a
n
c
e
of
s
t
a
t
e
-
of
-
t
h
e
-
a
r
t
C
NN
s
f
o
r
bi
n
a
r
y
c
l
a
s
s
if
i
c
a
t
i
o
n
w
i
t
h
o
ut
us
i
n
g
hi
s
t
o
gr
a
m
e
qua
l
i
z
a
t
i
o
n
.
T
h
i
s
c
o
m
pa
r
i
s
o
n
i
s
m
a
d
e
o
n
p
r
e
pr
o
c
e
s
s
e
d
i
m
a
ge
i
n
put
s
c
o
l
l
e
c
t
e
d
f
r
o
m
f
i
ve
r
e
po
s
i
t
o
r
i
e
s
,
vi
z
.
M
.
C
o
un
t
y
,
S
.
H
o
s
p
i
t
a
l
[
2
2]
,
NI
A
D
[
23]
,
B
e
l
a
r
us
da
t
a
s
e
t
[
24]
a
n
d
i
m
a
ge
s
c
o
l
l
e
c
t
e
d
dur
i
n
g
36
m
o
n
t
hs
f
r
o
m
t
h
e
H
A
HC
h
o
s
p
i
t
a
l
.
T
a
bl
e
2.
P
e
r
f
o
r
m
a
nc
e
m
a
t
r
i
x
o
f
c
l
a
s
s
i
f
i
e
r
s
–
W
i
t
h
o
ut
HE
M
o
de
l
R
e
s
ne
t5
0
R
e
s
ne
t
101
R
e
s
ne
t
152
I
nc
e
pt
i
o
n
V3
V
G
G
16
V
G
G
19
D
e
ns
e
n
e
t
121
D
e
ns
e
N
e
t
169
D
e
ns
e
n
e
t
201
M
o
bi
l
e
ne
t
A
c
c
u
r
a
c
y
99.1
98.4
98.8
94.7
97.8
98
98
98
98.6
98
S
e
ns
it
i
v
it
y
99.1
98.5
98.9
93.3
97.9
96.9
98.2
96.6
98.4
98.3
S
pe
c
ifi
c
it
y
99.1
98.3
98.8
97
97.7
99
97.2
99.2
98.3
97.5
P
r
e
c
is
i
o
n
99.1
98.2
98.9
97.3
97.5
98.9
97.3
98.8
98.2
97.4
F1
-
s
c
o
r
e
99.1
98.5
98.8
96
97.7
97.9
98
97
98.4
98
T
h
e
pe
r
f
o
r
m
a
n
c
e
i
s
m
e
a
s
ur
e
d
o
n
s
i
x
pa
r
a
m
e
t
e
r
s
,
b
a
s
i
c
c
r
i
t
e
r
i
a
to
c
h
e
c
k
t
h
e
qua
l
i
t
y
o
f
a
ny
m
e
d
i
c
a
l
d
i
a
g
n
o
s
t
i
c
s
y
s
t
e
m
.
I
t
i
s
f
o
un
d
t
h
a
t
b
ot
h
R
e
s
Ne
t
50
a
n
d
R
e
s
N
e
t
152
o
u
t
pe
r
f
o
r
m
t
h
e
r
e
s
t
o
f
t
h
e
C
NN
s
w
i
t
h
o
u
t
t
h
e
us
e
o
f
t
h
e
hi
s
t
o
gr
a
m
a
l
go
r
i
t
hm
.
R
e
s
Ne
t
50
a
l
l
o
ws
gr
a
d
i
e
n
t
s
to
f
l
o
w
t
h
r
o
ugh
t
h
e
n
e
t
w
o
r
k
m
o
r
e
e
a
s
i
ly
,
wh
e
r
e
a
s
De
n
s
e
Ne
t
201
i
s
i
n
t
e
n
s
i
ve
due
to
c
o
m
put
a
t
i
o
n
a
ll
y
d
e
n
s
e
r
c
o
nn
e
c
t
i
o
n
s
.
Al
s
o
,
R
e
s
Ne
t
50
e
x
e
m
p
li
f
i
e
s
t
h
e
t
r
a
n
s
f
e
r
l
e
a
r
ni
ng
h
e
r
e
.
Ot
h
e
r
c
l
a
s
s
if
i
e
r
s
h
a
ve
s
h
o
wn
i
m
pr
e
s
s
i
o
n
s
s
uc
h
a
s
R
e
s
Ne
t
101,
De
n
s
e
Ne
t
201,
De
ns
e
Ne
t
169,
a
n
d
De
n
s
e
Ne
t
121.
F
i
gur
e
4,
wh
e
n
e
v
a
l
ua
t
i
n
g
t
h
e
pr
o
c
e
s
s
e
d
c
h
e
s
t
X
-
r
a
y
s
i
n
n
e
ur
a
l
ne
t
w
o
r
ks
w
i
t
h
o
ut
h
i
s
t
o
g
r
a
m
e
qua
l
i
z
a
t
i
o
n
,
R
e
s
Ne
t
50
a
n
d
R
e
s
Ne
t
152
h
a
v
e
o
v
e
r
l
a
pp
i
ng
R
OC
c
ur
v
e
s
,
a
n
d
b
o
t
h
h
a
v
e
o
u
t
s
t
a
n
d
i
n
g
R
OC
,
f
o
l
l
o
we
d
by
R
e
s
Ne
t
101.
De
n
s
e
Ne
t
a
l
s
o
h
a
s
a
b
e
t
t
e
r
R
OC
t
h
a
n
ot
h
e
r
c
l
a
s
s
if
i
e
r
s
.
He
r
e
,
de
e
pe
r
n
e
t
wo
r
ks
n
e
e
d
n
o
t
pe
r
f
o
r
m
b
e
t
t
e
r
r
e
s
u
l
t
s
;
i
ns
t
e
a
d,
R
e
s
n
e
t
50
s
h
o
ws
a
n
e
f
f
e
c
t
i
ve
e
xa
m
p
l
e
f
o
r
tr
a
n
s
f
e
r
l
e
a
r
ni
ng.
A
c
o
nf
u
s
i
o
n
m
a
t
r
i
x
i
s
im
po
r
t
a
n
t
f
o
r
s
um
m
a
r
i
z
a
t
i
o
n
o
f
t
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
a
pr
o
p
o
s
e
d
s
y
s
t
e
m
o
n
467
n
o
r
m
a
l
a
n
d
466
P
T
B
t
e
s
t
r
a
di
o
gr
a
ph
s
i
n
F
i
gur
e
5.
F
i
gur
e
5(
a
)
s
h
o
ws
c
o
nf
us
i
o
n
m
a
r
i
x
f
o
r
R
e
s
Ne
t
50
a
n
d
F
i
gur
e
5(
b
)
f
o
r
R
e
s
Ne
t
152
w
i
t
h
o
ut
hi
s
t
o
gr
a
m
e
qua
li
z
a
t
i
o
n
.
F
i
gur
e
4.
R
OC
–
Va
r
i
o
us
c
l
a
s
s
i
f
i
e
r
s
w
i
t
h
o
ut
HE
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
15
,
N
o.
1
,
M
a
r
c
h
20
26
:
40
5
-
41
3
410
(
a
)
(
b
)
F
i
gur
e
5.
C
o
nf
u
s
i
o
n
m
a
t
r
i
x
-
w
i
t
h
o
ut
H
E
(
a
)
R
e
s
n
e
t
50
a
n
d
(
b
)
R
e
s
n
e
t
152
3.
2.
P
e
r
f
o
r
m
an
c
e
of
c
l
a
s
s
i
f
ie
r
s
wit
h
HE
T
a
bl
e
3
i
s
s
h
o
wn
to
c
o
m
pa
r
e
t
h
e
s
a
m
e
s
e
t
s
o
f
da
ta
i
n
put
e
x
p
l
a
i
ne
d
i
n
s
e
c
t
i
o
n
3.
1.
T
h
e
pe
r
f
o
r
m
a
nc
e
o
f
a
ll
10
bi
na
r
y
c
l
a
s
s
i
f
i
e
r
s
i
s
e
v
a
l
ua
t
e
d
o
n
f
i
ve
e
v
a
l
ua
t
i
o
n
m
a
t
r
i
c
e
s
a
n
d
R
OC
c
ur
v
e
s
o
n
a
pp
lyi
ng
HE
.
I
t
i
s
f
o
u
n
d
t
h
a
t
b
ot
h
R
e
s
Ne
t
50
a
n
d
De
n
s
e
Ne
t
169
h
a
ve
o
u
t
m
a
t
c
h
e
d
t
h
e
r
e
s
t
o
f
t
h
e
C
NN
s
by
e
nh
a
n
c
i
ng
im
a
ge
s
w
i
t
h
c
o
n
t
r
a
s
t
e
n
h
a
nc
e
m
e
n
t
.
R
e
s
Ne
t
50
a
l
l
o
ws
gr
a
d
i
e
n
t
s
to
f
l
o
w
t
h
r
o
ugh
t
h
e
n
e
t
wo
r
k
m
o
r
e
e
a
s
i
ly
,
wh
e
r
e
a
s
De
ns
e
Ne
t
169
i
s
i
n
t
e
n
s
i
ve
due
to
c
o
m
put
a
t
i
o
n
a
ll
y
de
n
s
e
r
c
o
nn
e
c
t
i
o
n
s
.
E
f
f
e
c
t
i
v
e
s
e
n
s
i
t
i
v
i
t
y
i
n
De
ns
e
Ne
t
169
c
o
m
pa
r
e
d
t
o
R
e
s
Ne
t
50
s
h
o
ws
i
m
pr
o
v
e
d
qua
l
i
t
y
o
f
i
de
n
t
i
f
yi
ng
t
r
ue
po
s
i
t
i
v
e
s
.
Al
s
o
,
R
e
s
Ne
t
50
e
x
e
m
p
li
f
i
e
s
t
h
e
t
r
a
n
s
f
e
r
l
e
a
r
ni
ng
h
e
r
e
.
Ot
h
e
r
c
l
a
s
s
if
i
e
r
s
h
a
v
e
s
ho
wn
a
n
i
m
pr
e
s
s
i
o
n
,
s
uc
h
a
s
R
e
s
Ne
t
152,
R
e
s
Ne
t101,
a
n
d
De
ns
e
Ne
t
121.
R
e
s
Ne
50
h
a
s
a
s
i
g
nif
i
c
a
n
t
R
OC
,
a
s
i
n
t
h
e
a
b
o
v
e
c
a
s
e
o
f
s
e
ns
i
t
i
vi
t
y
o
f
t
h
e
m
o
de
l
w
i
t
ho
u
t
HE
,
R
e
s
Ne
t
152
a
n
d
101
a
l
s
o
h
a
v
e
f
e
w
e
r
f
a
l
s
e
n
e
ga
t
i
ve
s
,
m
a
k
i
ng
t
h
e
m
a
m
o
r
e
r
e
l
i
a
bl
e
m
o
de
l
f
o
r
de
t
e
c
t
i
o
n
.
VG
G16
a
n
d
De
n
s
e
Ne
t
201
o
v
e
r
l
a
p
i
n
t
h
e
R
OC
C
ur
v
e
pr
e
s
e
n
t
e
d
i
n
F
i
gur
e
6.
T
a
bl
e
3.
P
e
r
f
o
r
m
a
nc
e
m
a
t
r
i
x
o
f
c
l
a
s
s
i
f
i
e
r
s
–
w
i
t
h
HE
M
o
de
l
R
e
s
ne
t5
0
R
e
s
ne
t
101
R
e
s
ne
t
152
I
nc
e
pt
i
o
n
V3
VGG
16
V
G
G
19
D
e
ns
e
n
e
t
121
D
e
ns
e
N
e
t
169
D
e
ns
e
n
e
t
201
M
o
bi
l
e
ne
t
A
c
c
u
r
a
c
y
99.36
99
99.1
95
98.3
98
99
99.25
98.6
96.5
S
e
ns
it
i
v
it
y
99.36
99.1
99.14
95.6
98.4
98.96
98.6
99.36
98.4
96.2
S
pe
c
ifi
c
it
y
99.36
99
98.8
94.8
98.23
97.1
99.6
99.14
98.7
97.1
P
r
e
c
is
i
o
n
99.36
98.6
98.7
94.51
98.1
96.95
99
99.14
98.61
96.6
F1
-
s
c
o
r
e
99.36
99
98.9
94.83
98.2
97.5
99.13
99.2
98.5
96.5
F
i
gur
e
6.
R
OC
–
Va
r
i
o
us
c
l
a
s
s
i
f
i
e
r
s
w
i
t
h
HE
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
De
tec
ti
on
mode
l
f
or
pulmonar
y
tuber
c
ulos
is
and
p
e
r
f
or
manc
e
e
v
aluat
ion
on
…
(
A
bdul
K
ar
im
Siddi
q
ui
)
411
F
i
gur
e
6
pr
e
s
e
n
t
s
R
OC
o
n
di
f
f
e
r
e
n
t
c
l
a
s
s
i
f
i
e
r
s
us
i
n
g
HE
e
n
h
a
nc
e
d
X
r
a
y
s
.
F
i
gur
e
7
de
p
i
c
t
s
c
o
nf
us
i
o
n
m
a
t
r
i
x
o
n
t
wo
b
e
s
t
pe
r
f
o
r
m
i
ng
c
l
a
s
s
if
i
e
r
s
.
B
i
n
a
r
y
c
l
a
s
s
if
i
e
r
R
e
s
N
e
t
50
r
e
t
ur
n
e
d
3
o
u
t
o
f
466
T
B
t
e
s
t
r
a
d
i
o
gr
a
ph
s
m
i
s
c
l
a
s
s
if
i
e
d
a
s
n
o
r
m
a
l
a
s
i
n
F
i
gur
e
7(
a
)
.
3
o
u
t
o
f
467
n
o
r
m
a
l
c
h
e
s
t
t
e
s
t
r
a
di
o
gr
a
ph
s
we
r
e
mi
s
c
l
a
s
s
if
i
e
d
a
s
T
B
X
-
r
a
y
.
I
n
t
h
e
e
v
a
l
ua
t
i
o
n
o
f
De
ns
e
Ne
t
169,
o
nl
y
3
o
ut
o
f
466
T
B
t
e
s
t
gr
a
p
h
s
w
e
r
e
mi
s
c
l
a
s
s
if
i
e
d
a
s
n
o
r
m
a
l
a
s
i
n
F
i
gur
e
7(
b
)
.
4
o
u
t
o
f
467
n
o
r
m
a
l
C
XR
t
e
s
t
gr
a
ph
s
we
r
e
mi
s
c
o
un
t
e
d
a
s
T
B
im
a
ge
s
[
25]
.
(
a
)
(
b
)
F
i
gur
e
7.
C
o
nf
u
s
i
o
n
m
a
t
r
i
x
-
w
i
t
h
HE
(
a
)
De
n
s
e
Ne
t
169
a
n
d
(
b
)
R
e
s
n
e
t
50
3.
3.
P
e
r
f
o
r
m
an
c
e
m
at
r
ics
of
e
n
s
e
m
b
l
e
s
t
ac
k
e
d
c
l
as
s
if
ie
r
T
h
e
XG
B
o
o
s
t
m
o
de
l
l
e
a
r
n
t
t
h
e
o
p
t
i
m
a
l
w
a
y
t
o
c
o
m
bi
ne
t
h
e
f
e
a
t
ur
e
s
f
r
o
m
b
o
t
h
R
e
s
Ne
t
50
a
n
d
De
ns
e
Ne
t
169
to
ge
t
t
h
e
b
e
s
t
pe
r
f
o
r
m
a
nc
e
by
e
a
c
h
R
e
s
Ne
t
50
a
n
d
De
ns
e
Ne
t
169
s
e
pa
r
a
t
e
l
y
o
n
t
h
e
gi
ve
n
t
e
s
t
da
t
a
s
e
t
s
.
C
a
l
c
u
l
a
t
i
n
g
t
h
e
f
i
na
l
m
o
d
e
l
's
pe
r
f
o
r
m
a
n
c
e
us
i
n
g
bi
na
r
y
c
l
a
s
s
i
f
i
c
a
t
i
o
n
,
s
uc
h
a
s
a
c
c
ur
a
c
y
,
pr
e
c
i
s
i
o
n
,
r
e
c
a
l
l
,
F
1
-
s
c
o
r
e
,
a
n
d
A
U
C
-
R
OC
o
n
t
h
e
s
a
m
e
t
e
s
t
da
t
a
s
e
t
s
,
vi
z
.
467
n
o
r
m
a
l
a
n
d
466
P
T
B
p
o
s
i
t
i
v
e
i
mage
s
,
t
h
e
f
o
l
l
o
w
i
n
g
f
i
gur
e
s
c
a
m
e
o
u
t
.
F
i
gur
e
8
pr
e
s
e
n
t
s
to
vi
e
w
t
h
e
c
o
n
f
u
s
i
o
n
m
a
t
r
i
x
f
o
r
T
P
,
T
N,
F
P
,
a
n
d
F
N.
I
t
s
h
o
ws
t
h
e
o
u
t
pe
r
f
o
r
m
i
ng
c
l
a
s
s
if
i
e
r
s
,
vi
z
.
De
n
s
e
Ne
t
169
a
n
d
R
e
s
Ne
t
50.
T
h
e
c
o
m
bi
ne
d
f
e
a
t
ur
e
s
r
e
v
e
a
l
e
d
f
r
o
m
t
h
e
t
w
o
b
a
s
e
c
l
a
s
s
if
i
e
r
s
,
t
h
e
t
e
s
t
da
t
a
s
e
t
s
b
r
o
ugh
t
t
h
e
be
s
t
pe
r
f
o
r
m
i
ng
bi
na
r
y
c
l
a
s
s
i
f
i
e
r
f
r
o
m
t
h
e
XG
B
o
o
s
t
s
t
a
c
ke
d
c
l
a
s
s
if
i
e
r
,
a
s
2
o
u
t
o
f
466
T
B
t
e
s
t
r
a
di
o
gr
a
ph
s
mi
s
c
l
a
s
s
if
i
e
d
a
s
n
o
r
m
a
l
,
2
o
u
t
o
f
467
n
o
r
m
a
l
c
h
e
s
t
t
e
s
t
r
a
d
i
o
gr
a
ph
s
we
r
e
m
i
s
c
l
a
s
s
if
i
e
d
a
s
T
B
X
-
r
a
y
.
I
t
g
ot
t
h
e
b
e
s
t
e
v
e
r
a
c
c
ur
a
c
y
o
f
99.
57%
.
B
y
e
va
l
ua
t
i
n
g
c
l
a
s
s
if
i
c
a
t
i
o
n
pe
r
f
o
r
m
a
n
c
e
us
i
n
g
hi
s
t
o
gr
a
m
m
a
t
c
hin
g
a
c
r
o
s
s
10
de
e
p
C
NN
m
o
de
l
s
,
o
ur
a
ppr
o
a
c
h
r
e
s
ul
t
e
d
i
n
a
m
o
r
e
r
e
l
i
a
bl
e
a
n
d
e
f
f
i
c
i
e
n
t
s
y
s
t
e
m
,
a
c
hi
e
vi
ng
a
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
c
c
ur
a
c
y
o
f
99.
57
pe
r
c
e
n
t
a
s
s
h
o
wn
i
n
T
a
bl
e
4.
F
i
gur
e
8.
C
o
nf
u
s
i
o
n
m
a
t
r
i
x
-
e
n
s
e
m
b
l
e
c
l
a
s
s
if
i
e
r
T
a
bl
e
4.
P
e
r
f
o
r
m
a
nc
e
m
a
t
r
i
x
o
f
ba
s
e
c
l
a
s
s
i
f
i
e
r
s
a
nd
s
t
a
c
ke
d
c
l
a
s
s
if
i
e
r
C
la
s
s
if
ie
r
B
a
s
e
c
la
s
s
if
i
e
r
-
1
B
a
s
e
c
la
s
s
if
i
e
r
-
2
B
a
s
e
c
la
s
s
if
i
e
r
-
1
B
a
s
e
c
la
s
s
if
i
e
r
-
2
E
ns
e
mbl
e
c
la
s
s
if
i
e
r
mo
d
e
l
R
e
s
ne
t5
0
(
w
it
ho
u
t
H
E
)
R
e
s
ne
t
152
(
w
it
ho
u
t
H
E
)
R
e
s
ne
t
50
(
w
it
h H
E
)
D
e
ns
e
N
e
t
169
(
w
it
h H
E
)
X
G
B
oo
s
t
(
w
it
h H
E
)
A
c
c
ur
ac
y
99.1
98.8
99.36
99.25
99.57
Se
ns
it
iv
it
y
99.1
98.9
99.36
99.36
99.57
Spe
c
ifi
c
it
y
99.1
98.8
99.36
99.14
99.57
P
r
e
c
is
io
n
99.1
98.9
99.36
99.14
99.57
F1
-
s
c
or
e
99.1
98.8
99.36
99.2
99.57
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
15
,
N
o.
1
,
M
a
r
c
h
20
26
:
40
5
-
41
3
412
4.
CONC
L
USI
ON
T
h
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
r
e
s
u
l
t
s
f
o
r
t
h
e
pul
m
o
na
r
y
TB
pr
e
d
i
c
t
i
o
n
m
o
de
l
r
e
v
e
a
l
a
n
e
x
c
e
pt
i
o
n
a
ll
y
hi
g
h
l
e
v
e
l
o
f
d
i
a
g
n
o
s
t
i
c
a
c
c
ur
a
c
y
.
Out
o
f
a
ll
c
a
s
e
s
e
v
a
l
ua
t
e
d,
464
we
r
e
c
o
r
r
e
c
t
l
y
i
de
n
t
i
f
i
e
d
a
s
TB
(
T
r
ue
P
o
s
i
t
i
ve
s
)
,
whi
l
e
o
nl
y
2
c
a
s
e
s
we
r
e
mi
s
s
e
d
(
F
a
l
s
e
Ne
ga
t
i
v
e
s
)
,
i
n
d
i
c
a
t
i
n
g
a
v
e
r
y
l
o
w
r
a
t
e
o
f
u
n
de
r
d
i
a
g
n
o
s
i
s
.
S
i
mi
l
a
r
ly,
a
m
o
n
g
t
h
e
n
o
r
m
a
l
c
a
s
e
s
,
465
we
r
e
a
c
c
ur
a
t
e
l
y
c
l
a
s
s
if
ied
a
s
n
o
n
-
T
B
(
T
r
ue
Ne
ga
t
i
v
e
s
)
,
w
i
t
h
j
u
s
t
2
i
n
s
t
a
n
c
e
s
mi
s
c
l
a
s
s
if
i
e
d
a
s
T
B
(
F
a
l
s
e
P
o
s
i
t
i
v
e
s
)
.
T
hi
s
ne
a
r
-
pe
r
f
e
c
t
b
a
l
a
n
c
e
b
e
t
we
e
n
s
e
ns
i
t
i
vi
t
y
a
n
d
s
p
e
c
i
f
i
c
i
t
y
un
de
r
s
c
o
r
e
s
t
h
e
m
o
de
l
’
s
r
o
b
us
t
n
e
s
s
a
n
d
r
e
l
i
a
bil
i
t
y
.
T
h
e
m
i
n
im
a
l
m
i
s
c
l
a
s
s
if
i
c
a
t
i
o
n
s
ugge
s
t
s
t
h
a
t
t
h
e
s
y
s
t
e
m
is
hi
g
hly
e
f
f
e
c
t
i
ve
i
n
d
i
s
t
i
n
gu
i
s
h
i
ng
be
t
we
e
n
T
B
a
n
d
n
o
r
m
a
l
c
a
s
e
s
,
m
a
k
i
ng
i
t
s
u
i
t
a
bl
e
f
o
r
c
li
ni
c
a
l
de
p
l
o
ym
e
n
t
o
r
i
n
t
e
gr
a
t
i
o
n
i
n
t
o
a
u
to
m
a
t
e
d
s
c
r
e
e
ni
n
g
wo
r
k
f
l
o
ws
.
T
h
e
c
o
n
s
i
s
t
e
n
t
pe
r
f
o
r
m
a
nc
e
o
f
t
h
e
e
n
s
e
m
bl
e
M
e
t
a
l
e
a
r
n
e
r
a
c
r
o
s
s
l
a
r
ge
a
n
d
v
a
r
i
e
d
da
t
a
s
e
t
s
hi
g
hl
i
g
h
t
s
t
h
e
r
o
b
us
t
n
e
s
s
a
n
d
ge
n
e
r
a
li
z
a
bil
i
t
y
o
f
o
ur
pr
o
p
o
s
e
d
a
ppr
o
a
c
h
.
F
UN
DI
NG
I
N
F
ORM
AT
I
ON
A
ut
h
o
r
s
s
t
a
t
e
n
o
f
u
n
d
i
ng
i
nv
o
l
v
e
d.
AU
T
HO
R
CONT
RI
B
UT
I
ONS
S
T
AT
E
M
E
NT
T
hi
s
j
o
ur
n
a
l
u
s
e
s
t
h
e
C
o
n
t
r
i
b
ut
or
R
o
l
e
s
T
a
x
o
n
o
m
y
(
C
R
e
d
i
T
)
to
r
e
c
o
gni
z
e
i
n
d
i
v
i
dua
l
a
ut
h
o
r
c
o
n
t
r
i
b
ut
i
o
ns
,
r
e
duc
e
a
ut
h
or
s
hi
p
d
i
s
put
e
s
,
a
n
d
f
a
c
il
i
t
a
t
e
c
o
l
l
a
b
o
r
a
t
i
o
n
.
Nam
e
of
Aut
h
or
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Ab
du
l
K
a
r
i
m
S
i
dd
i
qu
i
V
i
j
a
y
K
u
m
a
r
Ga
r
g
C
:
C
o
n
c
e
pt
ua
li
z
a
ti
o
n
M
:
M
e
th
o
d
o
l
o
g
y
So
:
So
f
twa
r
e
Va
:
Va
li
da
ti
o
n
Fo
:
Fo
r
ma
l
a
na
l
y
s
is
I
:
I
nve
s
ti
ga
ti
o
n
R
:
R
e
s
o
u
r
c
e
s
D
:
D
a
ta
C
ur
a
ti
o
n
O
:
W
r
it
in
g
-
O
r
ig
in
a
l
D
r
a
f
t
E
:
W
r
it
in
g
-
R
e
v
i
e
w
&
E
di
ti
ng
Vi
:
Vi
s
ua
li
z
a
ti
o
n
Su
:
Su
pe
r
v
is
io
n
P
:
P
r
o
j
e
c
t
a
dmi
ni
s
tr
a
ti
o
n
Fu
:
Fu
ndi
ng a
c
qui
s
it
i
o
n
CONF
L
I
CT
OF
I
NT
E
RE
S
T
S
T
AT
E
M
E
NT
A
ut
h
o
r
s
s
t
a
t
e
n
o
c
o
nf
li
c
t
o
f
i
n
t
e
r
e
s
t
.
DA
T
A
AV
AI
L
AB
I
L
I
T
Y
T
h
e
da
t
a
t
h
a
t
s
uppor
t
t
h
e
f
i
nd
i
ngs
o
f
t
hi
s
s
t
ud
y
a
r
e
a
v
a
il
a
bl
e
o
n
r
e
que
s
t
f
r
o
m
t
h
e
c
o
r
r
e
s
po
n
d
i
n
g
a
ut
h
o
r
,
[
S
i
dd
i
qu
i
,
AK
]
.
T
h
e
da
t
a
,
whi
c
h
c
o
n
t
a
i
n
i
nf
o
r
m
a
t
i
o
n
t
h
a
t
c
o
ul
d
c
o
m
pr
o
m
i
s
e
t
h
e
pr
i
v
a
c
y
o
f
r
e
s
e
a
r
c
h
pa
r
t
i
c
i
pa
n
t
s
,
a
r
e
n
ot
publ
i
c
ly
a
v
a
il
a
bl
e
due
to
c
e
r
t
a
i
n
r
e
s
t
r
i
c
t
i
o
ns
.
RE
F
E
R
E
NC
E
S
[
1]
S
.
V
a
jd
a
e
t
al
.
,
“
F
e
a
tu
r
e
s
e
l
e
c
ti
o
n
f
or
a
ut
o
ma
ti
c
tu
be
r
c
ul
o
s
is
s
c
r
e
e
ni
ng
in
f
r
o
nt
a
l
c
h
e
s
t
r
a
di
o
g
r
a
phs
,”
J
our
nal
of
M
e
di
c
al
Sy
s
te
m
s
,
vo
l.
42, n
o
. 8, J
un. 2018, d
o
i:
10.1007/s
10916
-
018
-
0991
-
9.
[
2]
P
.
C
hhi
ka
r
a
,
P
.
S
in
gh,
P
.
G
upt
a
,
a
nd
T
.
B
ha
ti
a
,
“
D
e
e
p
c
onvo
lu
ti
o
na
l
ne
u
r
a
l
n
e
tw
o
r
k
w
it
h
tr
a
ns
f
e
r
le
a
r
ni
ng
f
o
r
d
e
te
c
t
in
g
pne
um
o
ni
a
o
n
c
he
s
t
x
-
r
a
y
s
,”
in
A
dv
anc
e
s
in
B
io
in
f
or
m
at
ic
s
,
M
ul
ti
m
e
di
a,
and
E
le
c
tr
oni
c
s
C
ir
c
ui
ts
and
Si
gnal
s
,
S
pr
in
ge
r
S
in
ga
po
r
e
, 2019, pp. 155
–
168.
[
3]
A
. A
bba
s
, M
.
M
. A
bde
ls
a
me
a
, a
nd M
. M
. G
a
be
r
, “
D
e
T
r
a
c
:
t
r
a
ns
f
e
r
l
e
a
r
ni
ng
of
c
la
s
s
de
c
o
mp
o
s
e
d m
e
di
c
a
l
im
a
ge
s
i
n
c
o
n
vo
lu
ti
o
na
l
ne
ur
a
l
n
e
tw
o
r
ks
,”
I
E
E
E
A
c
c
e
s
s
, vo
l.
8, pp. 74901
–
74913, 2020,
do
i:
10.1109/a
c
c
e
s
s
.2020.2989273.
[
4]
R
.
H
oo
da
,
S
.
S
of
a
t,
S
.
K
a
ur
,
A
.
M
it
ta
l,
a
nd
F
.
M
e
r
ia
ude
a
u,
“
D
e
e
p
-
l
e
a
r
ni
ng:
A
pot
e
nt
ia
l
me
th
o
d
f
or
tu
be
r
c
u
l
o
s
is
de
te
c
ti
o
n
us
in
g
c
h
e
s
t
r
a
di
o
g
r
a
ph
y
,”
in
2017
I
E
E
E
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
o
n
Si
gnal
and
I
m
age
P
r
oc
e
s
s
in
g
A
ppl
ic
at
io
ns
(
I
C
SI
P
A
)
,
S
e
p.
2
017,
pp. 497
–
502, do
i:
10.1109/i
c
s
ip
a
.2017.8120663.
[
5]
L
.
G
. C
.
E
v
a
lg
e
li
s
ta
a
nd E
.
B
.
G
ue
d
e
s
, “
C
o
mput
e
r
-
a
id
e
d t
ub
e
r
c
ul
o
s
is
d
e
te
c
ti
o
n
f
r
o
m
c
h
e
s
t
x
-
r
a
y
im
a
ge
s
w
it
h
c
o
n
vo
lu
ti
o
na
l
n
e
ur
a
l
ne
tw
o
r
ks
,”
O
c
t.
2018, d
o
i:
10.5753/
e
ni
a
c
.2018.4444.
[
6]
S
.
S
.
M
e
r
a
j,
R
.
Y
a
a
ko
b,
A
.
A
z
ma
n,
S
.
N
.
M
.
R
um,
A
.
S
.
A
.
N
a
z
r
i,
a
nd
N
.
F
.
Z
a
ka
r
ia
,
“
D
e
t
e
c
ti
o
n
of
pul
m
o
na
r
y
tu
b
e
r
c
ul
o
s
is
ma
ni
f
e
s
ta
ti
o
n i
n
c
h
e
s
t
X
-
R
a
y
s
us
in
g di
f
f
e
r
e
nt
c
o
n
vo
lu
ti
o
na
l
n
e
ur
a
l
ne
tw
o
r
k
(
C
N
N
)
m
o
d
e
ls
,”
I
nt
e
r
nat
io
nal
J
our
nal
of
E
ngi
ne
e
r
in
g
and A
dv
anc
e
d T
e
c
hnol
ogy
, v
o
l.
9, n
o
. 1, pp. 2270
–
2275, O
c
t.
2
019, do
i:
10.35940/i
je
a
t.
a
2632.109119.
[
7]
O
. Y
a
da
v
, K
.
P
a
s
s
i,
a
nd
C
. K
. J
a
in
, “
U
s
in
g de
e
p l
e
a
r
n
in
g t
o
c
la
s
s
if
y
x
-
r
a
y
i
ma
g
e
s
of
p
o
t
e
nt
ia
l
tu
b
e
r
c
ul
o
s
is
pa
ti
e
nt
s
,”
i
n
2018 I
E
E
E
I
nt
e
r
nat
io
nal
C
onf
e
r
e
n
c
e
on
B
io
in
f
o
r
m
at
ic
s
and
B
io
m
e
di
c
in
e
(
B
I
B
M
)
,
D
e
c
.
2018,
pp.
2368
–
2375,
do
i:
10.1109/bi
bm.2018.8621525.
[
8]
T
.
R
a
hma
n
e
t
al
.
,
“
R
e
li
a
bl
e
tu
b
e
r
c
ul
o
s
is
de
t
e
c
t
i
o
n
us
in
g
c
he
s
t
x
-
r
a
y
w
it
h
d
e
e
p
l
e
a
r
ni
ng,
s
e
g
me
nt
a
ti
o
n
a
nd
v
is
ua
li
z
a
ti
o
n,”
I
E
E
E
A
c
c
e
s
s
, v
o
l.
8, pp. 191586
–
191601, 2020, d
o
i:
10.1109/a
c
c
e
s
s
.2020.3031384.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
De
tec
ti
on
mode
l
f
or
pulmonar
y
tuber
c
ulos
is
and
p
e
r
f
or
manc
e
e
v
aluat
ion
on
…
(
A
bdul
K
ar
im
Siddi
q
ui
)
413
[
9]
C
.
D
a
s
a
na
y
a
ka
a
nd
M
.
B
.
D
is
s
a
na
y
a
ke
,
“
D
e
e
p
l
e
a
r
ni
ng
m
e
t
ho
ds
f
or
s
c
r
e
e
ni
ng
pul
m
o
na
r
y
tu
be
r
c
u
l
o
s
is
us
in
g
c
h
e
s
t
x
-
r
a
y
s
,”
C
om
put
e
r
M
e
th
ods
in
B
io
m
e
c
hani
c
s
and
B
io
m
e
di
c
al
E
ngi
ne
e
r
in
g:
I
m
agi
ng
&
am
p;
V
is
ual
iz
at
io
n
,
vo
l.
9,
n
o
.
1,
pp.
39
–
49,
A
ug.
2020, do
i:
10.1080/21681163.
2020.1808532.
[
10]
K
.
M
una
di
,
K
.
M
uc
h
ta
r
,
N
.
M
a
ul
in
a
,
a
nd
B
.
P
r
a
dha
n,
“
I
ma
g
e
e
nha
nc
e
m
e
nt
f
or
tu
b
e
r
c
ul
o
s
is
d
e
te
c
ti
o
n
us
in
g
d
e
e
p
le
a
r
ni
ng,”
I
E
E
E
A
c
c
e
s
s
, v
o
l.
8, pp. 217897
–
217907, 2020, d
o
i:
10.1109/a
c
c
e
s
s
.2020.3041867.
[
11]
M
.
T
.
I
s
la
m,
M
.
A
.
A
o
w
a
l,
A
.
T
.
M
in
ha
z
,
a
nd
K
.
A
s
hr
a
f
,
“
A
bno
r
ma
li
t
y
d
e
t
e
c
ti
o
n
a
nd
l
oc
a
li
z
a
t
io
n
in
c
h
e
s
t
x
-
r
a
y
s
us
in
g
de
e
p
c
o
n
vo
lu
ti
o
na
l
n
e
ur
a
l
n
e
tw
o
r
ks
,”
ar
X
iv
pr
e
pr
in
t
ar
X
iv
:
1705.098
50
, 2017.
[
12]
M
.
A
hs
a
n,
R
.
G
o
m
e
s
,
a
nd
A
.
D
e
nt
o
n,
“
A
ppl
i
c
a
ti
o
n
of
a
c
o
n
vo
lu
ti
o
na
l
n
e
u
r
a
l
ne
twor
k
us
in
g
tr
a
ns
f
e
r
le
a
r
n
in
g
f
o
r
tu
b
e
r
c
ul
o
s
is
de
t
e
c
t
i
o
n,”
in
2019
I
E
E
E
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on
E
le
c
tr
o
I
nf
o
r
m
at
io
n
T
e
c
hnol
ogy
(
E
I
T
)
,
M
a
y
2019,
pp.
427
–
433,
do
i:
10.1109/e
it
.2019.8833768.
[
13]
U
.
K
.
L
o
p
e
s
a
nd
J
.
F
.
V
a
li
a
ti
,
“
P
r
e
-
tr
a
in
e
d
c
o
n
vo
lu
t
i
o
na
l
ne
ur
a
l
n
e
tw
o
r
ks
a
s
f
e
a
tu
r
e
e
x
t
r
a
c
t
or
s
f
or
tu
be
r
c
ul
o
s
is
de
te
c
ti
o
n,”
C
om
put
e
r
s
i
n B
io
lo
gy
and M
e
di
c
in
e
, v
o
l.
89, pp. 135
–
143, O
c
t.
2017, do
i:
10.1016/j
.
c
o
mpbi
ome
d.2017.08.001.
[
14]
M
.
B
.
M
iz
a
n,
M
.
A
.
M
.
H
a
s
a
n, a
nd
S
.
R
.
H
a
s
s
a
n,
“
A
c
o
mpa
r
a
t
iv
e
s
tu
d
y
of
tu
be
r
c
u
l
o
s
is
de
te
c
ti
o
n
us
in
g
de
e
p
c
o
n
vo
lu
ti
o
na
l
n
e
ur
a
l
ne
tw
o
r
k,”
i
n
2020
2nd
I
nt
e
r
nat
io
nal
C
onf
e
r
e
n
c
e
on A
dv
anc
e
d I
nf
or
m
at
io
n and C
om
m
uni
c
at
io
n T
e
c
hnol
ogy
(
I
C
A
I
C
T
)
, N
ov
. 20
20,
pp. 157
–
161, do
i:
10.1109/i
c
a
i
c
t5
1780.2020.9333464.
[
15]
K
.
C
a
o
,
J
.
Z
ha
ng,
M
.
H
ua
ng,
a
nd
T
.
D
e
ng,
“
X
-
r
a
y
c
la
s
s
if
i
c
a
ti
on
of
tu
b
e
r
c
ul
o
s
is
ba
s
e
d
o
n
c
o
n
vol
ut
i
o
na
l
n
e
tw
o
r
ks
,”
in
2021
I
E
E
E
I
nt
e
r
nat
io
nal
C
on
f
e
r
e
nc
e
on
A
r
ti
f
ic
ia
l
I
nt
e
ll
ig
e
nc
e
and
I
ndus
tr
ia
l
D
e
s
ig
n
(
A
I
I
D
)
,
M
a
y
2021,
pp.
125
–
129,
do
i:
10.1109/a
ii
d51893.2021.9456476.
[
16]
E
.
S
h
o
w
ka
ti
a
n,
M
.
S
a
le
hi
,
H
.
G
ha
f
f
a
r
i,
R
.
R
e
ia
z
i,
a
nd
N
.
S
a
di
ghi
,
“
D
e
e
p
l
e
a
r
ni
n
g
-
ba
s
e
d
a
ut
o
ma
ti
c
d
e
t
e
c
ti
o
n
of
tu
b
e
r
c
ul
o
s
is
di
s
e
a
s
e
i
n c
h
e
s
t
X
-
r
a
y
i
ma
g
e
s
,”
P
ol
is
h J
our
nal
of
R
adi
ol
ogy
, v
o
l.
87, pp. 118
–
124, F
e
b. 2022, d
o
i:
10.5114/p
jr
.2022.113435.
[
17]
A
.
S
ha
ti
,
A
.
D
a
tt
a
,
A
.
M
a
ns
o
o
r
,
a
nd
G
.
M
.
H
a
s
s
a
n,
“
E
T
D
H
D
N
e
t:
A
n
a
dv
a
n
c
e
d
D
e
ns
e
N
e
t
-
b
a
s
e
d
e
x
t
e
nd
e
d
te
xt
ur
e
de
s
c
r
ip
t
o
r
f
or
e
f
f
ic
i
e
nt
tu
b
e
r
c
ul
o
s
is
pr
e
di
c
ti
o
n
in
C
X
R
im
a
ge
s
,”
I
nt
e
ll
ig
e
nc
e
-
B
as
e
d
M
e
di
c
in
e
,
v
o
l.
12,
p.
100269,
2025,
do
i:
10.1016/j
.i
bme
d.2025.100269.
[
18]
M
.
S
a
lv
i,
U
.
R
.
A
c
ha
r
y
a
,
F
.
M
ol
in
a
r
i,
K
.
M
.
M
e
ib
ur
g
e
r
,
“
T
he
im
pa
c
t
of
p
r
e
-
a
nd
p
o
s
t
-
im
a
ge
pr
oc
e
s
s
in
g
t
e
c
hn
iq
ue
s
o
n
de
e
p
le
a
r
ni
ng
f
r
a
m
e
w
o
r
ks
:
A
c
ompr
e
he
ns
i
ve
r
e
vi
e
w
f
o
r
di
gi
ta
l
pa
t
ho
l
o
g
y
im
a
ge
a
na
l
y
s
is
,
”
C
om
put
e
r
s
in
B
io
lo
gy
and
M
e
di
c
in
e
,
vo
l.
128, 2021,
do
i:
10.1016/j
.
c
o
mpbi
ome
d.2020.104129.
[
19]
S.
P
a
r
k,
J.
K
im
,
S.
W
a
ng,
a
nd
J
.
K
im
,
“
E
f
f
e
c
ti
v
e
n
e
s
s
of
i
ma
ge
a
ugme
nt
a
ti
o
n
t
e
c
hni
qu
e
s
o
n
n
o
n
-
p
r
o
te
c
ti
ve
p
e
r
s
o
na
l
e
qui
pm
e
nt
de
t
e
c
t
i
o
n us
i
ng Y
O
L
O
v
8
,
”
A
ppl
ie
d Sc
ie
nc
e
s
,
v
o
l.
15
, n
o
.
5
,
p.
2631
,
2025
,
do
i
:
10.3390/a
pp15052631
.
[
20
]
R.
M.
D
y
k
e
a
nd
K
.
H
o
r
ma
nn,
“
H
is
t
o
gr
a
m
e
qua
li
z
a
ti
o
n
us
in
g
a
s
e
le
c
ti
ve
f
il
t
e
r
,
”
V
is
ual
C
om
put
e
r
,
vo
l.
39,
pp.
6221
–
6235
.
20
23
,
do
i
:
10.1007/s
00371
-
022
-
02723
-
8
.
[
21]
W.
Su
e
t
al
.
,
“
A
n
X
G
B
oo
s
t
-
B
a
s
e
d
kn
o
w
l
e
dg
e
t
r
a
c
in
g
m
o
d
el
,
”
I
nt
e
r
nat
io
nal
J
our
nal
of
C
om
put
at
io
nal
I
nt
e
ll
ig
e
nc
e
Sy
s
te
m
s
,
vo
l.
16,
no
.
13
,
2023
,
d
o
i
:
10.1007/s
44196
-
023
-
00192
-
y
.
[
22]
I
nde
x
of
publ
i
c
/
T
ube
r
c
u
l
o
s
is
-
C
he
s
t
-
X
-
r
a
y
-
D
a
ta
s
e
ts
,
“
N
a
ti
o
na
l
li
b
r
a
r
y
of
m
e
d
ic
in
e
,
”
2024
-
08
-
28.
[
O
nl
in
e
]
.
A
v
a
il
a
bl
e
:h
tt
ps
:/
/d
a
ta
.l
hnc
b
c
.nl
m.ni
h.g
ov
/p
ub
li
c
/
T
ub
e
r
c
ul
o
s
is
-
C
he
s
t
-
X
-
r
a
y
-
D
a
ta
s
e
ts
/i
nd
e
x
.ht
ml
[2
3
]
N
I
A
I
D
T
B
P
or
ta
ls
P
r
o
gr
a
m,
“
N
a
ti
o
na
l
I
ns
ti
tu
te
of
a
ll
e
r
g
y
a
nd
in
f
e
c
ti
o
us
di
s
e
a
s
e
s
,
”
J
ul
y
,
2025.
[
O
nl
in
e
]
.
A
v
a
il
a
bl
e
:h
tt
ps
:/
/t
bp
o
r
ta
ls
.ni
a
id
.ni
h.g
ov
/
[2
4
]
T
ub
e
r
c
ul
o
s
is
(
T
B
)
C
he
s
t
X
-
r
a
y
D
a
ta
ba
s
e
,
ka
ggl
e
,
2020.
[
O
nl
in
e
]
.
A
v
a
il
a
bl
e
:
ht
tp
s
:/
/ww
w
.ka
ggl
e
.c
o
m/
da
ta
s
e
ts
/t
a
w
s
i
f
ur
r
a
hma
n
/t
ube
r
c
ul
o
s
is
-
tb
-
c
h
e
s
t
-
x
r
a
y
-
da
ta
s
e
t
[2
5
]
G
l
o
ba
l
T
ube
r
c
u
l
o
s
is
R
e
p
o
r
t
2025,
W
H
O
,
2025
-
11
-
12.[
O
nl
in
e
]
.
A
v
a
il
a
bl
e
:
ht
tp
s
:/
/ww
w
.w
ho
.i
nt
/p
ubl
i
c
a
ti
o
ns
/i
/i
t
e
m/
9789240116924
B
I
OG
RA
P
HI
E
S
OF
AU
T
HO
RS
A
bd
u
l
Ka
ri
m
Si
dd
i
q
u
i
rece
i
v
e
d
h
i
s
fi
rs
t
d
e
g
r
ee
f
ro
m
S
H
U
A
T
S
,
A
l
l
a
h
a
ba
d
-
In
d
i
a
,
i
n
C
o
m
p
u
t
e
r
A
p
p
l
i
c
at
i
o
n
,
i
n
2
0
0
7
an
d
t
h
e
Ma
s
t
e
rs
fro
m
A
K
T
U
,
L
u
ck
n
o
w
-
In
d
i
a
i
n
Co
m
p
u
t
e
r
A
p
p
l
i
c
at
i
o
n
,
i
n
2
0
1
1
.
H
e
i
s
e
n
r
o
l
l
e
d
as
r
eg
u
l
ar
Ph
.
D
.
p
ro
g
ra
m
fr
o
m
L
PU
-
Pu
n
j
ab
,
I
n
d
i
a
.
H
i
s
m
a
i
n
r
e
s
e
ar
ch
i
n
t
e
r
e
s
t
s
fo
cu
s
o
n
d
ee
p
l
e
ar
n
i
n
g
,
d
at
a
mi
n
i
n
g
,
p
ro
g
ra
mmi
n
g
an
d
i
m
ag
e
p
ro
ce
s
s
i
n
g
an
d
MP
L
.
H
e
m
a
y
b
e
co
n
t
a
c
t
ed
at
emai
l
:
ab
d
u
l
.
m
o
men
t
u
m
@
h
o
t
m
ai
l
.
co
m
.
D
r
V
i
ja
y
K
um
a
r
Ga
rg
k
ee
p
s
a
d
o
c
t
o
rat
e
d
e
g
r
ee
i
n
C
o
m
p
u
t
e
r
S
c
i
en
ce
.
H
e
i
s
p
ro
fe
s
s
o
r
i
n
S
ch
o
o
l
o
f
C
o
m
p
u
t
e
r
S
ci
e
n
ce
an
d
En
g
i
n
ee
r
i
n
g
–
L
PU
-
Pu
n
j
ab
,
In
d
i
a.
H
i
s
s
p
e
c
i
a
l
i
z
ed
ar
e
a
i
s
DL
,
ML
,
o
b
j
ec
t
-
o
r
i
en
t
ed
p
ro
g
ra
mmi
n
g
,
h
u
m
an
c
o
m
p
u
t
e
r
i
n
t
e
ra
c
t
i
o
n
a
n
d
i
m
ag
e
p
ro
ce
s
s
i
n
g
.
H
e
h
as
p
u
b
l
i
s
h
ed
m
o
r
e
t
h
a
n
4
0
re
s
e
a
rc
h
p
ap
e
rs
an
d
t
en
s
o
f
b
o
o
k
c
h
ap
t
e
rs
.
Cu
rren
t
l
y
,
h
e
i
s
p
ro
g
ram
C
o
o
r
d
i
n
at
o
r
i
n
t
h
e
d
e
p
art
me
n
t
o
f
Sci
e
n
ce
a
n
d
T
e
ch
n
o
l
o
g
y
i
n
L
P
U
-
Ph
ag
w
ara
.
H
e
c
an
b
e
co
n
t
ac
t
e
d
at
em
a
i
l
:
v
i
j
a
y
.
g
arg
@
l
p
u
.
co
.
i
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.