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.
16
,
No
.
1
,
Feb
r
u
ar
y
20
26
,
p
p
.
414
~
422
I
SS
N:
2
0
8
8
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
16
i
1
.
p
p
4
1
4
-
4
2
2
414
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Deep learni
ng
arc
hitectu
re
for de
te
ction o
f
fet
a
l h
ea
rt
a
no
ma
lies
Nus
ra
t
J
a
wed
I
qb
a
l A
n
s
a
ri
1,
2
,
M
a
niro
j
a
M
.
E
din
bu
rg
h
1
,
Nik
it
a
3
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
T
e
l
e
c
o
mm
u
n
i
c
a
t
i
o
n
E
n
g
i
n
e
e
r
i
n
g
,
T
h
a
d
o
ma
l
S
h
a
h
a
n
i
En
g
i
n
e
e
r
i
n
g
C
o
l
l
e
g
e
,
M
u
m
b
a
i
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
V
i
v
e
k
a
n
a
n
d
Ed
u
c
a
t
i
o
n
S
o
c
i
e
t
y
’
s I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
M
u
m
b
a
i
,
I
n
d
i
a
3
C
e
r
t
i
f
i
e
d
G
y
n
e
c
o
l
o
g
i
st
a
n
d
F
e
t
a
l
M
e
d
i
c
i
n
e
S
p
e
c
i
a
l
i
st
,
P
.
G
.
M
e
d
i
c
a
l
Tr
u
s
t
H
o
sp
i
t
a
l
,
K
e
r
a
l
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
Ma
r
4
,
2
0
2
5
R
ev
is
ed
Oct
4
,
2
0
2
5
Acc
ep
ted
No
v
2
3
,
2
0
2
5
Re
se
a
rc
h
h
a
s
d
e
m
o
n
stra
ted
th
a
t
a
rti
ficia
l
in
telli
g
e
n
c
e
(AI)
tec
h
n
i
q
u
e
s
h
a
v
e
sh
o
wn
trem
e
n
d
o
u
s
p
o
ten
ti
a
l
o
v
e
r
th
e
p
a
st d
e
c
a
d
e
fo
r
a
n
a
ly
z
i
n
g
a
n
d
d
e
tec
ti
n
g
a
n
o
m
a
li
e
s
in
th
e
fe
tal
h
e
a
rt
d
u
ri
n
g
u
lt
ra
so
u
n
d
tes
ts.
De
sp
it
e
t
h
e
ir
p
o
ten
ti
a
l
,
th
e
a
d
o
p
ti
o
n
o
f
t
h
e
se
a
lg
o
ri
th
m
s
re
m
a
in
s
li
m
it
e
d
d
u
e
to
c
o
n
c
e
rn
s
o
v
e
r
p
a
ti
e
n
t
p
riv
a
c
y
,
t
h
e
sc
a
rc
it
y
o
f
larg
e
we
ll
-
a
n
n
o
tate
d
d
a
tas
e
ts
a
n
d
c
h
a
ll
e
n
g
e
s
in
a
c
h
ie
v
in
g
h
i
g
h
a
c
c
u
ra
c
y
.
Th
is
r
e
se
a
rc
h
a
ims
to
o
v
e
rc
o
m
e
t
h
e
se
li
m
it
a
ti
o
n
s
b
y
p
r
o
p
o
sin
g
a
n
o
p
t
ima
l
so
l
u
ti
o
n
.
Two
m
e
th
o
d
s
s
u
c
h
a
s
d
e
term
in
is
ti
c
i
m
a
g
e
a
u
g
m
e
n
tatio
n
tec
h
n
i
q
u
e
s
a
n
d
W
a
ss
e
rste
in
g
e
n
e
ra
ti
v
e
a
d
v
e
rsa
rial
n
e
two
rk
with
g
ra
d
ien
t
p
e
n
a
lt
y
(W
G
AN
-
G
P
)
sh
o
wc
a
se
th
e
fra
m
e
wo
rk
'
s
c
a
p
a
c
it
y
to
se
a
m
les
sly
a
n
d
e
ffe
c
ti
v
e
ly
e
x
p
a
n
d
o
ri
g
in
a
l
d
a
tas
e
ts
to
1
4
ti
m
e
s
a
n
d
1
7
t
ime
s
re
sp
e
c
ti
v
e
ly
,
th
e
re
b
y
e
ffe
c
ti
v
e
ly
t
a
c
k
li
n
g
t
h
e
p
ro
b
lem
o
f
d
a
ta sc
a
rc
it
y
.
It
u
se
s
a
n
a
n
n
o
tatio
n
to
o
l
to
p
re
c
ise
ly
c
a
teg
o
rize
a
n
o
m
a
li
e
s
id
e
n
ti
f
i
e
d
in
th
e
e
c
h
o
c
a
rd
io
g
ra
m
d
a
tas
e
t.
S
e
g
m
e
n
tatio
n
o
f
th
e
a
n
n
o
tate
d
d
a
ta
i
s
d
o
n
e
t
o
h
ig
h
li
g
h
t
re
g
io
n
o
f
in
tere
st.
Ni
n
e
d
isti
n
c
t
fe
tal
h
e
a
rt
a
n
o
m
a
li
e
s
a
r
e
id
e
n
ti
fie
d
with
re
sp
e
c
t
to
th
e
fe
we
r
c
o
v
e
re
d
in
e
x
isti
n
g
re
se
a
rc
h
.
Th
is
s
tu
d
y
a
lso
in
v
e
stig
a
tes
t
h
e
sta
te
-
of
-
t
h
e
-
a
rt
a
rc
h
it
e
c
tu
re
s
a
n
d
o
p
ti
m
iza
ti
o
n
t
e
c
h
n
iq
u
e
s
u
se
d
i
n
d
e
e
p
lea
rn
in
g
m
o
d
e
ls.
T
h
e
re
su
lt
s
c
lea
rly
in
d
ica
te
th
a
t
th
e
Re
sN
e
t
-
1
0
1
m
o
d
e
l
d
e
m
o
n
stra
ted
s
u
p
e
ri
o
r
p
re
c
isio
n
a
c
c
u
ra
c
y
o
f
9
9
.
1
5
%
.
To
e
n
su
re
th
e
re
li
a
b
il
it
y
o
f
th
e
p
ro
p
o
se
d
m
o
d
e
l,
i
ts
p
e
rfo
rm
a
n
c
e
u
n
d
e
rwe
n
t
th
o
r
o
u
g
h
e
v
a
lu
a
ti
o
n
a
n
d
v
a
li
d
a
ti
o
n
b
y
c
e
rti
fied
g
y
n
e
c
o
l
o
g
ists
a
n
d
fe
tal
m
e
d
icin
e
sp
e
c
ialists.
K
ey
w
o
r
d
s
:
Au
g
m
en
tatio
n
Dee
p
lear
n
in
g
E
ch
o
ca
r
d
i
o
g
r
ap
h
y
Gen
er
ativ
e
ad
v
e
r
s
ar
ial
n
etwo
r
k
s
Pre
n
atal
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
:
Nu
s
r
at
J
awe
d
I
q
b
al
An
s
ar
i
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics an
d
T
elec
o
m
m
u
n
icatio
n
E
n
g
in
ee
r
in
g
,
T
h
a
d
o
m
al
Sh
ah
a
n
i E
n
g
in
ee
r
in
g
C
o
lleg
e
Mu
m
b
ai,
I
n
d
ia
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
E
n
g
i
n
ee
r
in
g
,
Viv
e
k
an
an
d
E
d
u
ca
tio
n
So
ciety
’
s
I
n
s
titu
te
o
f
T
ec
h
n
o
lo
g
y
Mu
m
b
ai,
I
n
d
ia
E
m
ail:
n
u
s
r
at.
an
s
ar
i@
v
es.a
c.
in
1.
I
NT
RO
D
UCT
I
O
N
Fetal
h
ea
r
t
an
o
m
alies
en
co
m
p
ass
a
wid
e
s
p
ec
tr
u
m
o
f
s
tr
u
ctu
r
al
an
d
f
u
n
ctio
n
al
d
is
o
r
d
er
,
f
r
o
m
r
elativ
ely
s
im
p
le
d
ef
ec
ts
s
u
ch
as
s
ep
tal
ab
n
o
r
m
alities
to
co
m
p
lex
co
n
g
en
ital
m
alf
o
r
m
ati
o
n
s
lik
e
h
y
p
o
p
last
ic
lef
t
h
ea
r
t
f
r
o
m
th
e
lef
t
s
y
n
d
r
o
m
e
an
d
tr
an
s
p
o
s
itio
n
o
f
th
e
g
r
ea
t
ar
ter
ies.
E
ar
ly
an
d
p
r
e
cise
id
en
tific
atio
n
th
r
o
u
g
h
p
r
e
n
atal
u
ltra
s
o
u
n
d
i
s
ess
en
tia
l,
en
s
u
r
in
g
d
iag
n
o
s
es
alig
n
with
s
tan
d
ar
d
ized
p
r
o
to
co
ls
.
Gu
id
elin
es
estab
lis
h
ed
b
y
th
e
I
n
ter
n
atio
n
al
So
ciety
o
f
Ultr
aso
u
n
d
i
n
Ob
s
tetr
ics
an
d
Gy
n
ec
o
lo
g
y
(
I
SUOG)
o
f
f
er
a
s
tr
u
ctu
r
ed
a
p
p
r
o
ac
h
to
f
etal
ca
r
d
iac
ass
ess
m
en
t,
p
r
o
m
o
tin
g
c
o
n
s
is
ten
cy
in
clin
ical
p
r
ac
tice
[
1
]
.
T
h
e
Am
e
r
ica
n
I
n
s
titu
te
o
f
Ultr
aso
u
n
d
i
n
Me
d
icin
e
(
AI
UM
)
h
ig
h
lig
h
ts
th
at
f
etal
ec
h
o
ca
r
d
io
g
r
ap
h
y
f
o
cu
s
es
o
n
th
e
ev
alu
atio
n
o
f
th
e
f
etal
h
ea
r
t
u
s
in
g
u
ltra
s
o
u
n
d
im
ag
in
g
,
wh
ic
h
is
r
ec
o
g
n
ized
as
r
eliab
le,
s
ec
u
r
e
an
d
n
o
n
-
in
v
asiv
e
[
2
]
.
Ho
wev
er
,
h
ea
lth
ca
r
e
p
r
o
f
ess
io
n
als en
co
u
n
ter
o
b
s
tacle
s
r
elate
d
to
f
etal
h
ea
r
t a
b
n
o
r
m
alities
,
s
u
ch
as c
o
n
s
tr
ain
ts
in
u
ltra
s
o
u
n
d
r
eso
lu
tio
n
,
v
ar
iab
ilit
y
in
f
etal
p
o
s
itio
n
in
g
,
g
estatio
n
al
ag
e
-
d
ep
en
d
en
t
v
i
s
ib
ilit
y
o
f
ca
r
d
iac
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
Dee
p
lea
r
n
in
g
a
r
ch
itectu
r
e
fo
r
d
etec
tio
n
o
f fe
ta
l h
e
a
r
t a
n
o
m
a
lies
(
N
u
s
r
a
t J
a
w
ed
I
q
b
a
l A
n
s
a
r
i
)
415
s
tr
u
ctu
r
es
an
d
lim
ited
d
iag
n
o
s
tic
ca
p
ab
ilit
ies
in
ce
r
tain
r
eg
io
n
s
[
3
]
.
Dee
p
lear
n
in
g
(
DL
)
p
la
y
s
a
cr
u
cial
r
o
le
in
m
ed
ical
im
ag
in
g
b
y
en
ab
lin
g
au
to
m
ated
im
a
g
e
s
eg
m
e
n
t
atio
n
,
h
el
p
in
g
to
id
en
tify
an
d
is
o
late
f
etal
h
ea
r
t
s
tr
u
ctu
r
es
f
o
r
p
r
ec
is
e
an
aly
s
i
s
.
I
t
en
h
an
ce
s
class
if
icatio
n
,
im
p
r
o
v
es
im
ag
e
r
ec
o
n
s
tr
u
ctio
n
.
T
h
r
o
u
g
h
im
a
g
e
s
y
n
th
esis
,
it
g
en
er
ates
h
ig
h
-
q
u
ality
s
y
n
th
etic
f
etal
h
ea
r
t
im
ag
es
f
o
r
tr
ain
in
g
an
d
r
esear
ch
[
4
]
,
[
5
]
.
I
n
m
e
d
ical
im
ag
in
g
,
d
ee
p
lear
n
in
g
m
o
d
e
ls
o
f
ten
f
ac
e
ch
allen
g
es
d
u
e
to
th
e
lim
ited
av
ailab
ilit
y
o
f
an
n
o
tated
d
atasets
.
T
h
is
s
ca
r
city
ca
n
lead
to
o
v
e
r
f
itti
n
g
[
6
]
wh
er
e
m
o
d
els
f
ail
to
g
en
er
alize
to
n
ew
u
n
s
ee
n
d
at
a
[
7
]
.
Ad
d
itio
n
ally
,
s
m
all
d
atasets
m
ay
n
o
t
ca
p
tu
r
e
th
e
f
u
ll
v
a
r
iab
ilit
y
o
f
m
e
d
ical
co
n
d
itio
n
s
,
lim
itin
g
t
h
e
m
o
d
el'
s
r
o
b
u
s
tn
ess
an
d
d
iag
n
o
s
tic
ac
cu
r
ac
y
.
Fo
r
s
en
s
itiv
e
h
ea
lth
ca
r
e
d
o
m
ain
,
s
y
n
t
h
etic
d
ata
ca
n
b
e
u
s
ed
to
ar
tific
ially
in
cr
ea
s
e
th
e
s
ize
o
f
tr
ain
in
g
d
atasets
an
d
it
ca
n
h
elp
d
ee
p
lear
n
in
g
m
o
d
e
ls
b
ec
o
m
e
m
o
r
e
ad
ap
tab
le,
r
el
iab
le,
an
d
r
esil
ien
t
to
v
ar
iatio
n
s
[
8
]
.
Mu
lti
-
task
d
ee
p
lear
n
in
g
ap
p
licatio
n
s
h
av
e
ac
h
iev
ed
s
ig
n
if
ica
n
t
s
u
cc
ess
in
f
etal
h
ea
r
t
ass
es
s
m
en
ts
,
aid
in
g
i
n
th
e
d
e
tectio
n
o
f
n
e
o
n
atal
c
o
n
d
itio
n
s
f
r
o
m
u
ltra
s
o
u
n
d
s
ca
n
s
[
9
]
–
[
1
2
]
.
T
h
e
ex
is
tin
g
r
esear
ch
[
1
3
]
in
t
r
o
d
u
ce
s
a
d
o
m
ain
-
s
p
ec
if
ic
d
ata
au
g
m
e
n
tatio
n
s
tr
ateg
y
f
o
r
m
ed
ical
im
ag
in
g
task
s
.
I
t
d
em
o
n
s
tr
ates
h
o
w
c
o
n
tex
t
-
p
r
eser
v
in
g
au
g
m
en
tatio
n
ca
n
e
n
h
an
ce
m
o
d
el
p
er
f
o
r
m
an
ce
i
n
f
etal
u
ltra
s
o
u
n
d
class
if
icatio
n
.
Misk
ee
n
et
a
l.
[
1
4
]
h
ig
h
lig
h
ts
ex
ten
s
iv
e
in
v
esti
g
atio
n
o
f
s
ev
e
r
al
m
eth
o
d
s
f
o
r
id
en
tify
in
g
p
r
en
atal
h
ea
r
t
d
is
ea
s
e.
No
wak
et
a
l.
[
1
5
]
p
r
o
v
id
es
a
s
y
s
tem
a
tic
s
tr
ateg
y
to
u
ltra
s
o
u
n
d
d
ata
au
g
m
en
tatio
n
with
th
e
g
o
al
o
f
im
p
r
o
v
i
n
g
class
if
icatio
n
p
er
f
o
r
m
a
n
ce
f
o
r
f
et
al
s
tan
d
ar
d
p
la
n
e
d
etec
tio
n
.
I
t
em
p
h
asizes
th
e
im
p
o
r
tan
ce
o
f
o
p
tim
al
au
g
m
e
n
tatio
n
p
r
o
ce
d
u
r
es
in
m
ed
ical
im
ag
es.
B
alah
a
et
a
l.
[
1
6
]
in
v
esti
g
ates
s
ev
er
al
d
ata
au
g
m
e
n
tatio
n
a
n
d
p
r
ep
r
o
ce
s
s
in
g
s
tr
ateg
ies
f
o
r
im
p
r
o
v
i
n
g
d
ee
p
lear
n
in
g
m
o
d
els
f
o
r
m
ed
ical
ap
p
licatio
n
s
.
T
h
e
f
in
d
in
g
s
s
h
o
w
th
at
r
o
tatio
n
is
th
e
m
o
s
t
s
u
cc
ess
f
u
l a
u
g
m
en
tatio
n
ap
p
r
o
ac
h
,
in
cr
ea
s
in
g
in
-
d
o
m
ain
ac
c
u
r
ac
y
b
y
1
0
.
1
%.
T
iag
o
et
a
l.
[
1
7
]
f
o
cu
s
es
o
n
im
p
r
o
v
in
g
X
-
r
ay
c
ateg
o
r
izatio
n
f
o
r
n
e
cr
o
tizin
g
en
ter
o
co
liti
s
(
NE
C
)
,
an
u
n
co
m
m
o
n
b
u
t
d
an
g
e
r
o
u
s
in
f
an
t
illn
ess
.
Du
e
to
s
ca
r
cit
y
o
f
im
ag
es,
th
e
au
th
o
r
s
ex
a
m
in
ed
h
o
w
v
ar
i
o
u
s
im
ag
e
ad
ju
s
tm
en
ts
an
d
p
r
e
p
a
r
atio
n
tech
n
iq
u
es
ca
n
o
v
e
r
co
m
e
d
ata
s
ca
r
city
a
n
d
ar
tific
ial
in
tellig
en
ce
(
AI
)
m
o
d
els'
ab
ilit
y
f
o
r
b
etter
d
etec
tio
n
[
1
8
]
,
[
1
9
]
.
T
h
i
s
r
e
s
ea
r
ch
ad
d
r
es
s
e
s
th
e
ch
al
le
n
g
e
o
f
d
ata
s
ca
r
ci
ty
in
th
e
s
tu
d
y
o
f
f
e
ta
l
h
ea
r
t
ab
n
o
r
m
al
i
ti
es
.
Al
th
o
u
g
h
th
i
s
a
r
ea
h
a
s
b
ee
n
e
x
ten
s
iv
e
ly
e
x
p
lo
r
ed
,
i
t
wa
s
f
o
u
n
d
th
at
r
e
la
tiv
ely
l
i
tt
le
wo
r
k
h
ad
b
e
en
d
ed
i
ca
ted
to
en
h
an
cin
g
m
o
d
e
l
tr
a
in
in
g
t
h
r
o
u
g
h
d
at
a
au
g
m
en
t
at
io
n
t
ec
h
n
iq
u
e
s
,
p
ar
t
icu
la
r
ly
th
o
s
e
b
a
s
ed
o
n
W
a
s
s
e
r
s
te
in
g
en
er
at
iv
e
ad
v
er
s
ar
ia
l
n
e
two
r
k
s
w
ith
g
r
ad
i
en
t
p
en
a
lty
(
W
G
AN
-
G
P)
an
d
d
e
te
r
m
in
i
s
t
ic
im
ag
e
au
g
m
en
t
at
io
n
.
Us
in
g
d
e
te
r
m
in
i
s
t
ic
im
ag
e
a
u
g
m
en
t
at
io
n
,
two
a
u
g
m
en
ta
ti
o
n
l
ev
e
l
s
we
r
e
ap
p
li
ed
,
ex
p
a
n
d
in
g
th
e
o
r
ig
in
a
l
d
ata
s
et
s
ar
o
u
n
d
1
4
t
im
e
s
an
d
ar
o
u
n
d
1
7
t
im
es
u
s
in
g
W
GA
N
-
GP
.
W
i
th
th
is
en
lar
g
e
d
d
at
a
s
e
t,
th
e
d
ee
p
lea
r
n
in
g
m
o
d
el
ac
h
i
ev
ed
h
ig
h
er
a
cc
u
r
ac
y
an
d
ab
le
to
d
e
tec
t
f
iv
e
c
o
m
p
l
ex
co
n
g
e
n
i
ta
l
h
ea
r
t
an
o
m
al
ie
s
:
h
y
p
o
p
la
s
ti
c
h
ea
r
t
s
y
n
d
r
o
m
e
(
HL
HS)
,
tr
a
n
s
p
o
s
i
tio
n
o
f
th
e
g
r
ea
t
ar
t
er
i
e
s
(
T
G
A)
,
ab
er
r
an
t
r
ig
h
t
s
u
b
cl
av
i
an
ar
t
er
y
(
A
R
S
A)
,
ec
h
o
g
en
i
c
in
t
r
ac
a
r
d
i
ac
f
o
cu
s
(
E
C
I
F)
,
an
d
d
il
at
ed
ca
r
d
i
ac
s
in
u
s
(
D
C
S)
wi
th
in
a
s
in
g
le
s
tu
d
y
.
T
h
i
s
a
d
v
an
c
em
en
t
en
h
an
ce
s
th
e
m
o
d
e
l
's
u
ti
l
ity
f
o
r
m
e
d
ica
l
p
r
o
f
e
s
s
io
n
a
ls
in
f
e
ta
l
ca
r
d
iac
a
s
s
e
s
s
m
e
n
t.
R
esNet
-
1
0
1
was
s
elec
ted
f
o
r
i
ts
ab
ilit
y
to
a
d
d
r
ess
th
e
g
r
a
d
ie
n
t
lo
s
s
is
s
u
e
an
d
d
eliv
e
r
o
p
tim
al
r
esu
lts
.
Prio
r
to
u
tili
zin
g
R
esNet
-
1
0
1
,
ec
h
o
c
ar
d
io
g
r
a
p
h
y
im
ag
es
wer
e
e
x
am
in
ed
u
s
in
g
s
ev
er
al
o
th
e
r
m
o
d
els,
in
clu
d
in
g
R
esNet
-
5
0
,
Den
s
eNe
t1
6
9
,
VGG1
6
,
an
d
E
f
f
icien
tNetB
0
.
Ho
wev
er
,
th
e
r
esu
lts
wer
e
u
n
s
atis
f
ac
to
r
y
.
T
h
er
e
f
o
r
e,
th
e
tr
an
s
itio
n
to
R
esNet
-
1
0
1
,
co
u
p
led
with
d
eter
m
in
is
tic
an
d
W
GAN
-
GP
au
g
m
en
tatio
n
,
y
ield
ed
s
ig
n
if
ican
tly
im
p
r
o
v
e
d
o
u
tc
o
m
es.
Als
o
,
s
ix
o
u
t o
f
n
in
e
class
es a
ch
iev
ed
f
u
ll p
er
f
o
r
m
a
n
ce
ac
cu
r
ac
y
u
s
in
g
R
esNet
-
101.
T
h
e
s
tr
u
ctu
r
e
o
f
t
h
is
p
ap
er
is
as
f
o
llo
ws:
Sectio
n
2
elab
o
r
ates
o
n
p
r
o
p
o
s
ed
m
o
d
el
a
d
o
p
ted
f
o
r
ar
tifa
cts d
ev
elo
p
m
en
t.
Sectio
n
3
d
is
cu
s
s
th
e
r
esu
lt th
at
co
m
p
ar
e
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
'
s
o
u
tco
m
es to
ea
r
lier
s
tu
d
ies,
h
ig
h
lig
h
tin
g
t
h
e
ef
f
ec
tiv
en
ess
o
f
th
e
ch
o
s
en
tec
h
n
iq
u
es
in
ac
h
iev
in
g
ac
cu
r
ate
d
is
e
ase
d
iag
n
o
s
is
with
m
in
im
u
m
d
ata.
Sectio
n
4
c
o
n
c
lu
d
es th
e
p
ap
e
r
an
d
f
u
tu
r
e
s
co
p
e
o
f
th
is
wo
r
k
.
2.
M
E
T
H
O
D
2
.
1
.
Co
ncept
ua
l
dia
g
ra
m
T
h
e
co
m
p
r
eh
e
n
s
iv
e
wo
r
k
f
lo
w
f
o
r
t
h
e
p
r
o
p
o
s
ed
s
y
s
tem
i
s
s
h
o
wn
in
Fig
u
r
e
1
.
I
t
co
n
s
is
t
s
o
f
th
e
f
o
llo
win
g
s
tep
s
:
a.
Data
p
r
ep
ar
atio
n
:
T
h
e
m
o
s
t
s
ig
h
ted
d
ata
was
s
elec
ted
,
f
o
llo
wed
b
y
d
ata
clea
n
in
g
an
d
p
r
ep
r
o
ce
s
s
in
g
o
n
th
e
ch
o
s
en
im
ag
es
b.
Def
ec
t
id
en
tific
atio
n
:
Un
d
er
t
h
e
s
u
p
er
v
is
io
n
o
f
ex
p
er
ts
,
ea
c
h
d
ef
ec
t
was
g
iv
en
a
n
am
e
a
n
d
lab
elled
u
s
in
g
La
b
elMe
in
An
ac
o
n
d
a
.
c.
T
h
e
s
eg
m
en
tatio
n
tech
n
iq
u
e
in
v
o
lv
es
p
ar
titi
o
n
in
g
an
im
ag
e
in
to
d
is
tin
ct
r
eg
io
n
s
to
ef
f
ec
tiv
ely
id
en
tify
th
e
r
eg
io
n
o
f
in
ter
est (
R
OI
)
,
wh
ic
h
is
cr
u
cial
f
o
r
p
r
ec
is
e
an
aly
s
i
s
an
d
in
ter
p
r
etatio
n
.
d.
T
h
e
im
p
lem
en
tatio
n
an
d
ass
es
s
m
en
t o
f
d
ee
p
lear
n
in
g
alg
o
r
ith
m
s
f
o
r
d
ata
an
aly
s
is
2
.
2
.
Da
t
a
s
et
I
n
th
is
r
esear
ch
,
o
p
en
ly
ac
ce
s
s
ib
le
d
ataset
f
etal
ec
h
o
ca
r
d
io
g
r
ap
h
y
(
FECG)
was
u
s
ed
[
2
0
]
.
T
h
ir
teen
s
tr
u
ctu
r
es
h
av
e
b
ee
n
i
d
en
tifi
ed
n
am
ely
lef
t
v
e
n
tr
icu
lar
o
u
tf
lo
w
tr
ac
t
(
L
VOT
)
,
r
ig
h
t
v
en
tr
icle
(
R
V)
,
lef
t
v
en
tr
icle
(
L
V)
,
a
o
r
ta
(
Ao
)
,
r
ig
h
t
atr
iu
m
(
R
A)
,
lef
t
atr
iu
m
(
L
A)
,
r
ig
h
t
v
e
n
tr
icle
(
R
V)
,
lef
t
v
en
tr
icle
(
L
V)
,
r
ig
h
t
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.
16
,
No
.
1
,
Feb
r
u
ar
y
20
26
:
4
1
4
-
422
416
h
y
p
o
p
last
ic
h
ea
r
t
s
y
n
d
r
o
m
e
(
HL
HS)
,
atr
ial
s
ep
tal
d
ef
ec
t
(
ASD)
,
v
en
tr
icu
lar
s
ep
tal
d
ef
ec
t
(
VSD)
,
tr
an
s
p
o
s
itio
n
o
f
th
e
g
r
ea
t
ar
te
r
ies
(
T
GA)
,
n
o
r
m
al
h
ea
r
t
(
N
H)
,
Dilated
C
ar
d
iac
Sin
u
s
(
D
C
S)
an
d
ec
h
o
g
en
ic
in
tr
ac
ar
d
iac
f
o
c
u
s
(
E
C
I
F).
Su
b
s
eq
u
en
tly
,
C
er
tifie
d
Gy
n
ec
o
lo
g
is
t
an
d
Fetal
Me
d
icin
e
Sp
ec
ialis
t
ex
am
in
ed
ea
ch
in
d
iv
id
u
al
im
ag
e
th
at
w
as
tak
en
f
r
o
m
th
e
FECG
r
ec
o
r
d
in
g
s
an
d
r
ec
o
m
m
en
d
e
d
th
at
th
e
h
ig
h
er
s
ig
h
ted
im
ag
es
to
b
e
tak
en
in
to
co
n
s
id
er
atio
n
.
T
h
e
r
aw,
u
n
s
tr
u
ctu
r
e
d
d
ata
was
o
r
g
an
ized
an
d
n
o
r
m
alize
d
to
im
p
r
o
v
e
q
u
ality
,
co
n
s
is
ten
cy
,
an
d
r
e
d
u
ce
r
ed
u
n
d
an
cy
.
No
r
m
aliza
tio
n
in
clu
d
e
d
r
em
o
v
i
n
g
d
u
p
licates,
s
tan
d
ar
d
izin
g
f
o
r
m
ats,
h
an
d
lin
g
m
is
s
in
g
v
al
u
es,
an
d
s
ca
lin
g
n
u
m
e
r
ical
f
ea
tu
r
es.
T
h
ese
p
r
ep
r
o
ce
s
s
in
g
task
s
en
s
u
r
ed
th
e
d
ata
was c
lean
,
co
n
s
is
ten
t,
an
d
r
ea
d
y
f
o
r
an
aly
s
is
T
h
e
p
i
x
els ar
e
n
o
r
m
alize
d
as p
e
r
g
iv
e
n
eq
u
ati
o
n
.
`
=
.
`
=
.
ℎ
(
1
)
wh
er
e
(
,
)
ar
e
o
r
ig
in
al
c
o
o
r
d
i
n
ates,
(
`
,
`
)
ar
e
n
ew
co
o
r
d
in
ate
d
af
ter
r
esizin
g
an
d
(
,
ℎ
)
ar
e
t
h
e
o
r
ig
in
al
wid
th
an
d
h
eig
h
t o
f
th
e
im
ag
e
an
d
,
ar
e
n
ew
wid
th
an
d
h
eig
h
t
o
f
th
e
im
a
g
e.
:
(
,
)
=
(
,
)
255
(
2
)
Fo
r
R
GB
im
ag
es,
ea
ch
ch
an
n
e
l is n
o
r
m
alize
d
as:
(
,
,
)
=
(
,
,
)
−
(
3
)
wh
er
e
(
,
,
)
is
th
e
p
i
x
el
in
ten
s
ity
a
t
ch
an
n
el
c
a
n
d
an
d
ar
e
t
h
e
s
tan
d
ar
d
d
ev
iatio
n
an
d
m
ea
n
o
f
th
e
ch
an
n
el
.
Fig
u
r
e
1
.
Fu
n
ctio
n
al
ar
c
h
itectu
r
e
an
d
in
ter
r
elatio
n
s
with
in
t
h
e
s
y
s
tem
T
h
e
d
is
tr
ib
u
tio
n
o
f
ec
h
o
ca
r
d
io
g
r
am
d
ata
f
o
r
p
er
f
o
r
m
an
c
e
ev
alu
atio
n
is
s
ee
n
in
T
ab
le
1
.
T
h
e
p
r
o
ce
d
u
r
e
f
o
r
s
eg
m
e
n
tin
g
r
elies
o
n
th
e
an
at
o
m
ical
s
tr
u
ct
u
r
es
o
f
th
e
h
ea
r
t.
Usi
n
g
th
e
d
ata
lab
elin
g
to
o
l
L
ab
elM
e,
ex
ac
t
b
o
u
n
d
ar
ies
ar
e
d
r
awn
ar
o
u
n
d
th
e
h
ea
r
t
im
ag
es
wh
ich
will
s
p
o
t
th
e
p
r
ec
is
e
p
o
s
itio
n
o
f
an
o
m
alies.
T
ab
le
2
g
iv
es a
n
ill
u
s
tr
atio
n
o
f
a
f
ea
tu
r
e
m
a
p
d
e
r
iv
ed
f
r
o
m
L
ab
elM
e
a
n
d
s
eg
m
e
n
tatio
n
.
T
ab
le
1
.
Or
ig
i
n
al
d
ataset
s
u
m
m
ar
y
with
o
u
t a
u
g
m
e
n
tatio
n
C
l
a
s
s
Tr
a
i
n
i
n
g
Te
st
i
n
g
V
a
l
i
d
a
t
i
o
n
To
t
3
V
T
41
12
6
59
A
R
S
A
3
1
1
5
D
C
S
1
1
0
2
LV
O
T
30
9
4
43
H
LH
S
9
3
1
13
TG
A
8
2
1
11
V
S
D
4
2
1
7
A
V
S
D
4
2
1
7
EC
I
F
15
4
3
22
NH
55
16
8
79
T
o
t
a
l
1
7
0
52
26
2
4
8
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Dee
p
lea
r
n
in
g
a
r
ch
itectu
r
e
fo
r
d
etec
tio
n
o
f fe
ta
l h
e
a
r
t a
n
o
m
a
lies
(
N
u
s
r
a
t J
a
w
ed
I
q
b
a
l A
n
s
a
r
i
)
417
2
.
3
.
Da
t
a
a
ug
m
ent
a
t
io
n
Data
au
g
m
en
tatio
n
is
ap
p
lied
to
in
cr
ea
s
e
d
ataset
s
ize
[
2
1
]
.
T
h
e
ch
o
ice
o
f
th
e
b
est
im
ag
e
au
g
m
en
tatio
n
tech
n
iq
u
e
r
elie
s
o
n
th
e
p
ar
ticu
lar
task
b
ein
g
p
er
f
o
r
m
e
d
,
d
ataset
an
d
m
o
d
el
b
ein
g
u
s
ed
.
T
h
e
tech
n
iq
u
es
s
u
ch
as
f
lip
p
in
g
(
h
o
r
izo
n
tal/v
er
tical)
:
’
(
,
)
=
(
−
−
1
,
)
,
r
o
ta
tio
n
:
’
=
(
)
−
(
)
an
d
’
=
(
)
+
(
)
an
d
cr
o
p
p
in
g
ar
e
u
s
ed
in
d
ee
p
lea
r
n
in
g
f
o
r
im
ag
e
au
g
m
en
tatio
n
.
Af
ter
ex
h
au
s
tiv
e
r
esear
ch
an
d
in
-
d
e
p
th
an
aly
s
is
,
d
eter
m
i
n
is
tic
im
ag
e
au
g
m
en
tatio
n
a
n
d
W
GAN
-
GP
ar
e
u
s
ed
in
th
is
r
esear
ch
wo
r
k
.
2
.
3
.
1
.
Det
er
m
ini
s
t
ic
im
a
g
e
a
ug
m
ent
a
t
io
n
Dete
r
m
i
n
is
ti
c
i
m
a
g
e
a
u
g
m
e
n
t
ati
o
n
a
p
p
li
es
f
i
x
e
d
,
p
r
ed
ef
in
e
d
t
r
a
n
s
f
o
r
m
a
ti
o
n
s
t
o
i
m
a
g
es
,
e
n
s
u
r
i
n
g
co
n
s
is
t
e
n
t
a
n
d
r
e
p
r
o
d
u
ci
b
l
e
r
e
s
u
lts
as
s
h
o
wn
i
n
T
a
b
l
e
2
.
I
n
t
h
e
i
m
a
g
e
p
r
ep
r
o
c
ess
i
n
g
p
i
p
el
i
n
e
,
a
c
o
m
p
r
e
h
e
n
s
i
v
e
d
at
a
a
u
g
m
en
tat
io
n
s
t
r
a
te
g
y
was
im
p
l
em
e
n
te
d
t
h
a
t
e
v
o
lv
ed
i
n
tw
o
d
is
t
in
ct
p
h
ases
t
o
o
p
t
im
i
ze
m
o
d
el
p
e
r
f
o
r
m
a
n
c
e.
T
h
e
af
f
i
n
e
t
r
a
n
s
f
o
r
m
at
io
n
s
we
r
e
ca
r
e
f
u
ll
y
ca
li
b
r
at
ed
to
p
r
ese
r
v
e
t
h
e
ess
e
n
t
i
al
c
h
a
r
ac
t
er
is
ti
cs
o
f
th
e
i
m
a
g
es
.
W
h
i
le
i
n
t
r
o
d
u
c
in
g
m
ea
n
i
n
g
f
u
l
v
a
r
ia
ti
o
n
s
r
o
tat
io
n
s
we
r
e
c
o
n
s
t
r
ai
n
ed
wi
th
in
-
3
0
°
t
o
3
0
°
to
m
ai
n
t
ai
n
f
e
at
u
r
e
o
r
ie
n
t
ati
o
n
.
Sc
ali
n
g
o
p
er
ati
o
n
s
w
er
e
ap
p
lie
d
wit
h
f
a
cto
r
s
b
etw
ee
n
0
.
8
a
n
d
1
.
2
t
o
en
s
u
r
e
r
ea
l
is
ti
c
s
i
ze
v
a
r
i
ati
o
n
s
a
n
d
h
o
r
iz
o
n
t
al/
v
e
r
t
ical
f
l
ip
s
we
r
e
i
m
p
le
m
en
te
d
wit
h
a
5
0
%
p
r
o
b
a
b
ili
ty
t
o
d
o
u
b
le
t
h
e
e
f
f
ec
t
iv
e
d
at
ase
t
s
i
ze
.
E
las
tic
t
r
a
n
s
f
o
r
m
at
io
n
s
we
r
e
p
a
r
ti
cu
la
r
l
y
v
a
l
u
a
b
l
e
as
t
h
e
y
s
i
m
u
lat
ed
n
at
u
r
al
d
e
f
o
r
m
at
io
n
s
b
y
ap
p
l
y
i
n
g
r
a
n
d
o
m
d
is
p
l
ac
em
e
n
t
f
iel
d
s
,
c
r
ea
t
in
g
r
ea
lis
tic
v
a
r
ia
tio
n
s
th
at
c
o
u
ld
o
cc
u
r
in
r
ea
l
-
wo
r
l
d
s
c
e
n
a
r
i
o
s
.
T
o
f
u
r
t
h
er
e
n
h
a
n
c
e
t
h
e
m
o
d
e
l'
s
r
el
ia
b
il
it
y
a
n
d
r
e
d
u
c
e
th
e
r
is
k
o
f
o
v
e
r
f
itti
n
g
,
t
h
e
a
u
g
m
en
t
ati
o
n
p
i
p
el
in
e
w
as
ex
p
a
n
d
e
d
w
it
h
a
d
d
iti
o
n
al
s
o
p
h
is
t
ica
te
d
t
ec
h
n
iq
u
es.
C
o
n
tr
o
ll
ed
n
o
is
e
was
i
n
t
r
o
d
u
ce
d
t
h
r
o
u
g
h
s
alt
a
n
d
p
ep
p
er
in
j
ec
t
io
n
,
w
h
ic
h
h
el
p
e
d
t
h
e
m
o
d
el
b
e
c
o
m
e
m
o
r
e
r
esis
t
a
n
t
t
o
i
m
a
g
e
a
r
t
if
ac
ts
an
d
s
e
n
s
o
r
n
o
is
e.
T
h
e
f
i
n
a
l
la
y
e
r
o
f
au
g
m
e
n
ta
ti
o
n
i
n
cl
u
d
e
d
r
a
n
d
o
m
c
r
o
p
p
i
n
g
an
d
p
ad
d
i
n
g
o
p
e
r
at
io
n
s
wit
h
i
n
±
1
0
%
o
f
th
e
o
r
i
g
i
n
al
d
im
en
s
io
n
s
,
ef
f
e
cti
v
e
ly
te
ac
h
i
n
g
t
h
e
m
o
d
el
t
o
h
an
d
l
e
v
a
r
y
i
n
g
o
b
jec
t
s
ca
l
es
a
n
d
p
o
s
iti
o
n
s
.
T
wo
le
v
els
o
f
d
et
er
m
i
n
is
t
ic
au
g
m
e
n
ta
ti
o
n
w
er
e
ca
r
r
ie
d
o
u
t
.
W
it
h
s
i
n
g
le
l
ev
el
a
u
g
m
e
n
t
ati
o
n
d
a
tase
t
s
i
ze
w
as
i
n
cr
ea
s
ed
f
r
o
m
2
4
8
to
5
5
2
a
n
d
wit
h
s
e
c
o
n
d
le
v
el
a
u
g
m
e
n
t
ati
o
n
it
h
as
i
n
c
r
ea
s
e
d
t
o
3
5
1
8
.
T
h
is
a
p
p
r
o
a
c
h
s
i
g
n
if
ica
n
t
ly
i
n
c
r
e
ase
d
t
h
e
s
iz
e
o
f
tr
a
in
in
g
d
at
a
w
h
i
le
m
ai
n
ta
in
in
g
th
e
s
em
a
n
tic
i
n
t
e
g
r
i
ty
o
f
t
h
e
im
a
g
es
.
T
ab
le
2
.
Data
s
et
s
u
m
m
ar
y
f
o
r
d
eter
m
in
is
tic
im
ag
e
au
g
m
e
n
ta
tio
n
S
i
n
g
l
e
-
l
e
v
e
l
A
u
g
m
e
n
t
a
t
i
o
n
Bi
-
l
e
v
e
l
A
u
g
me
n
t
a
t
i
o
n
C
l
a
s
s
Tr
a
i
n
i
n
g
Te
st
i
n
g
V
a
l
i
d
a
t
i
o
n
To
t
C
l
a
s
s
Tr
a
i
n
i
n
g
Te
st
i
n
g
V
a
l
i
d
a
t
i
o
n
To
t
3
V
T
41
12
6
59
3
V
T
2
4
7
72
35
3
5
4
A
R
S
A
38
12
5
55
A
R
S
A
2
4
8
72
35
3
5
5
D
C
S
36
11
5
52
D
C
S
2
1
1
61
30
3
0
2
LV
O
T
30
9
4
43
LV
O
T
2
4
0
70
34
3
4
4
H
LH
S
36
11
5
52
H
LH
S
2
4
5
71
35
3
5
1
TG
A
32
10
6
48
TG
A
2
4
7
72
35
3
5
4
V
S
D
34
10
5
49
V
S
D
2
4
7
72
35
3
5
4
A
V
S
D
34
10
5
49
A
V
S
D
2
4
9
72
36
3
5
7
EC
I
F
46
14
6
66
EC
I
F
2
4
6
71
35
3
5
2
NH
55
16
8
79
NH
2
7
6
80
39
3
9
5
T
o
t
a
l
3
8
2
1
1
5
55
5
5
2
T
o
t
a
l
2
4
5
6
7
1
3
3
4
9
3
5
1
8
2
.
3
.
2
.
Wa
s
s
er
s
t
ein G
AN
wit
h
g
ra
dient
pena
lt
y
W
as
s
er
s
tein
GAN
with
Gr
ad
ien
t
Pen
alty
(
W
GAN
-
GP)
was
u
s
ed
[
2
2
]
–
[
2
4
]
to
g
e
n
er
at
e
im
ag
es
co
n
d
itio
n
e
d
o
n
class
lab
els.
Gen
er
ato
r
u
s
es
r
an
d
o
m
n
o
is
e
an
d
class
lab
els
to
p
r
o
d
u
ce
class
-
s
p
ec
if
ic
im
ag
es.
T
h
e
d
is
cr
im
in
ato
r
(
cr
itic)
co
m
p
ar
es
ac
tu
al
an
d
g
en
er
ated
im
ag
es,
u
s
in
g
th
e
W
as
s
er
s
tei
n
lo
s
s
with
g
r
ad
ien
t
p
en
alty
to
ass
u
r
e
L
ip
s
ch
itz
co
n
tin
u
ity
.
Du
r
in
g
tr
ain
in
g
,
th
e
m
o
d
el
u
p
d
ates
th
e
d
is
cr
im
in
at
o
r
an
d
th
e
g
e
n
er
ato
r
alter
n
ately
.
T
h
e
g
r
a
d
ien
t
p
en
a
lty
s
tab
ilizes
tr
ain
in
g
b
y
p
en
a
lizin
g
g
r
ad
ien
ts
.
T
h
e
g
e
n
er
ato
r
lear
n
s
to
p
r
o
d
u
ce
h
ig
h
-
q
u
ality
,
d
i
v
er
s
if
ied
im
ag
es,
wh
ile
th
e
d
is
cr
im
in
ato
r
d
ev
elo
p
s
its
ab
ilit
y
to
tell
th
e
d
if
f
er
en
ce
b
etwe
en
r
ea
l
an
d
f
a
k
e.
B
o
th
u
s
e
a
W
ass
er
s
tein
lo
s
s
to
o
p
tim
ize
th
e
g
en
er
ativ
e
p
r
o
ce
s
s
.
Fin
ally
,
class
co
n
d
itio
n
in
g
en
ab
les
th
e
cr
ea
tio
n
o
f
im
ag
es
th
at
b
elo
n
g
to
s
p
ec
if
ied
class
es
an
d
ex
p
an
d
ed
th
e
d
ataset
to
4
2
6
4
as
s
h
o
wn
in
T
ab
le
3.
T
ab
le
3
.
Data
s
et
af
ter
W
GAN
g
en
er
atin
g
C
l
a
s
ses
Tr
a
i
n
Te
st
V
a
l
i
d
a
t
i
o
n
To
t
a
l
N
o
r
mal
H
e
a
r
t
5
4
5
1
5
4
76
7
7
5
A
b
n
o
r
ma
l
H
e
a
r
t
2
4
4
2
6
9
8
3
4
9
3
4
8
9
To
t
a
l
2
9
8
7
8
5
2
4
2
5
4
2
6
4
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.
16
,
No
.
1
,
Feb
r
u
ar
y
20
26
:
4
1
4
-
422
418
2
.
4
.
T
he
pro
po
s
e
d hea
lt
hca
re
a
rc
hite
ct
ura
l f
ra
m
ewo
r
k
I
n
ea
ch
im
p
lem
en
ted
m
o
d
el,
r
aw
FECG
im
ag
es
ar
e
an
n
o
tate
d
u
s
in
g
a
n
an
n
o
tatio
n
to
o
l
(
L
a
b
elM
e)
to
h
ig
h
lig
h
t
ar
ea
s
o
f
in
ter
est.
T
h
ese
lab
eled
im
ag
es
u
n
d
er
g
o
d
ata
au
g
m
en
tatio
n
to
e
n
h
an
ce
th
e
d
ataset.
T
h
e
im
ag
es a
r
e
s
eg
m
en
ted
to
is
o
late
k
ey
r
e
g
io
n
s
u
s
in
g
d
ee
p
lear
n
in
g
m
o
d
els.
2
.
4
.
1
.
ResNet
-
1
0
1
a
rc
hite
ct
u
re
T
h
e
R
esNet
-
1
0
1
m
o
d
el
in
Fig
u
r
e
2
,
a
d
ee
p
er
v
ar
ian
t o
f
R
esNet
[
2
5
]
,
[
2
6
]
,
is
p
r
e
tr
ain
ed
o
n
I
m
ag
eNe
t
an
d
f
in
e
-
tu
n
ed
o
n
th
e
s
eg
m
en
t
ed
u
ltra
s
o
u
n
d
d
ataset.
T
h
e
p
ip
elin
e
co
n
s
is
ts
o
f
f
o
u
r
m
ain
s
tag
es
with
a
to
tal
o
f
1
0
1
lay
er
s
,
in
clu
d
i
n
g
in
itial
an
d
f
in
al
lay
er
s
.
Stag
e
2
h
as
3
r
esid
u
al
b
lo
ck
s
,
co
n
tr
ib
u
tin
g
to
9
lay
er
s
,
wh
ile
s
tag
e
3
in
clu
d
es
4
r
esid
u
al
b
lo
ck
s
,
m
ak
in
g
u
p
1
2
lay
e
r
s
.
Stag
e
4
is
th
e
d
ee
p
est
with
2
3
r
esid
u
al
b
lo
ck
s
,
to
talin
g
6
9
la
y
er
s
,
an
d
s
tag
e
5
co
n
tain
s
3
r
esid
u
al
b
lo
ck
s
wi
th
9
lay
er
s
.
Fin
al
l
ay
er
s
in
clu
d
e
av
e
r
ag
e
p
o
o
lin
g
lay
er
,
f
latten
in
g
,
an
d
a
f
u
lly
c
o
n
n
ec
ted
la
y
er
(
FC
)
f
o
r
class
if
icatio
n
.
Fig
u
r
e
2
.
Pro
p
o
s
ed
m
o
d
el
wit
h
R
esNet
-
1
0
1
ar
ch
itectu
r
e
2
.
4
.
2
.
WG
AN
-
G
P
a
rc
hite
ct
u
re
W
GAN
-
G
P
is
a
s
tab
il
ized
GA
N
v
er
s
io
n
th
at
en
h
an
ce
s
tr
ain
in
g
b
y
in
tr
o
d
u
cin
g
a
g
r
ad
ien
t
p
en
alty
f
o
r
m
o
r
e
c
o
n
s
is
ten
t
an
d
a
u
th
en
tic
g
en
er
atio
n
[
2
7
]
,
[
2
8
]
.
T
h
e
g
en
er
ato
r
a
n
d
cr
itic
co
m
p
ete
i
n
a
m
i
n
im
ax
g
am
e.
T
h
e
cr
itic
aim
s
to
m
ax
im
ize
th
e
W
ass
er
s
tein
d
is
tan
ce
b
etwe
en
r
ea
l
an
d
g
en
er
ated
im
a
g
es.
T
h
e
g
en
e
r
ato
r
tr
ies
to
m
in
im
ize
th
e
d
is
tan
ce
t
o
f
o
o
l
th
e
cr
itic.
Gr
ad
ie
n
t
Pen
alt
y
to
e
n
f
o
r
ce
th
e
L
ip
s
ch
itz
co
n
s
tr
ain
t
r
eq
u
ir
e
d
b
y
W
GAN.
A
g
r
ad
ien
t
p
en
alty
ter
m
is
co
m
p
u
ted
an
d
ad
d
ed
t
o
th
e
cr
itic's
lo
s
s
f
u
n
ctio
n
.
T
h
e
cr
itic
is
u
p
d
ated
m
u
ltip
le
tim
es p
er
g
en
e
r
ato
r
u
p
d
ate
to
en
s
u
r
e
s
tr
o
n
g
f
ee
d
b
ac
k
as sh
o
wn
in
Fig
u
r
e
3
.
T
h
e
g
en
er
ato
r
(
)
m
ap
s
a
r
an
d
o
m
n
o
is
e
v
ec
to
r
∼
(
)
to
th
e
d
ata
s
p
ac
e.
T
h
e
g
e
n
er
ato
r
'
s
g
o
al
is
to
m
ax
im
ize
th
e
cr
itic’
s
esti
m
atio
n
W
as
s
er
s
tein
d
is
tan
ce
|
∼
(
)
[
(
(
)
)
]
|
.
Fig
u
r
e
3
.
Pro
p
o
s
ed
W
GAN
-
GP w
ith
R
esNe
t
-
5
0
ar
ch
itectu
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Dee
p
lea
r
n
in
g
a
r
ch
itectu
r
e
fo
r
d
etec
tio
n
o
f fe
ta
l h
e
a
r
t a
n
o
m
a
lies
(
N
u
s
r
a
t J
a
w
ed
I
q
b
a
l A
n
s
a
r
i
)
419
2
.
4
.
3
.
Dis
cr
im
ina
t
o
r
(
cr
it
ic
)
o
bje
ct
iv
e
Un
lik
e
tr
ad
itio
n
al
GANs,
W
G
AN
-
GP
d
o
es
n
o
t
u
s
e
a
s
ig
m
o
id
ac
tiv
atio
n
f
o
r
th
e
d
is
cr
im
in
a
to
r
.
I
n
s
tead
,
it
lear
n
s
a
f
u
n
ctio
n
D(
x
)
th
at
esti
m
ates
th
e
W
as
s
er
s
tein
d
is
t
an
ce
b
etwe
en
r
ea
l
an
d
g
e
n
er
at
ed
d
is
tr
ib
u
tio
n
s
.
T
h
e
cr
itic's
o
b
jectiv
e
is
^
~
[
(
^
)
]
−
^
~
[
(
)
]
+
^
~
[
(
∥
~
(
~
)
∥
2
−
1
)
2
]
(
4
)
wh
er
e
(
)
is
th
e
r
ea
l
d
ata
d
is
tr
ib
u
tio
n
.
(
)
is
th
e
g
en
er
ated
d
ata
d
is
tr
ib
u
tio
n
.
~
is
a
lin
ea
r
in
ter
p
o
lat
io
n
b
etwe
en
r
ea
l
an
d
f
ak
e
s
am
p
le
s
is
th
e
p
en
alty
c
o
ef
f
icien
t.
T
h
e
g
r
a
d
ien
t
p
en
alty
ter
m
[
(
∥
~
(
~
)
∥
2
−
1
)
2
]
en
f
o
r
ce
s
th
e
L
ip
s
ch
itz
co
n
s
tr
a
in
t b
y
p
e
n
alizin
g
g
r
ad
ien
ts
to
en
s
u
r
e
s
tab
ilit
y
d
u
r
in
g
tr
ain
in
g
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
th
is
r
esear
ch
,
aim
was
to
u
n
d
er
s
tan
d
an
d
ex
am
i
n
e
f
etal
h
ea
r
t
d
ef
ec
ts
.
T
h
e
i
n
itial
s
tr
id
e
in
v
o
lv
ed
th
e
p
r
o
cu
r
em
e
n
t
o
f
a
co
m
p
r
eh
en
s
iv
e
d
ataset
co
m
p
r
is
in
g
f
etal
ec
h
o
ca
r
d
io
g
r
a
p
h
ic
i
m
ag
es
w
h
ich
was
cu
r
ated
t
o
en
ca
p
s
u
late
d
iv
er
s
e
ca
r
d
iac
c
o
n
d
itio
n
s
.
E
m
p
l
o
y
in
g
d
o
m
ain
ex
p
er
tis
e,
v
ar
io
u
s
an
o
m
alies
with
in
th
e
d
ataset
wer
e
ass
ig
n
ed
ap
p
r
o
p
r
iate
n
o
m
en
clatu
r
e.
Utilizin
g
m
o
d
er
n
an
n
o
tatio
n
tec
h
n
iq
u
es
lik
e
L
ab
elM
e,
a
r
ea
s
o
f
in
ter
est
in
th
e
im
ag
es
a
r
e
id
en
tifie
d
,
estab
lis
h
in
g
th
e
way
f
o
r
s
eg
m
en
tatio
n
.
T
o
im
p
r
o
v
e
d
iag
n
o
s
is
p
r
ec
is
io
n
,
th
e
d
eter
m
in
is
tic
im
ag
e
au
g
m
en
tatio
n
an
d
W
GAN
GP
d
ata
au
g
m
en
tatio
n
m
eth
o
d
wer
e
u
s
ed
.
T
h
r
o
u
g
h
s
eg
m
en
tatio
n
,
th
e
im
ag
es
wer
e
ca
teg
o
r
ized
in
to
d
is
tin
ct
an
ato
m
ical
ar
ea
s
,
ea
ch
o
f
wh
ich
is
cr
u
cial
f
o
r
id
en
tify
in
g
ir
r
eg
u
lar
ities
in
th
e
h
ea
r
t.
T
h
en
,
we
u
tili
ze
d
m
o
d
er
n
d
ee
p
lear
n
in
g
ar
ch
itectu
r
es.
tailo
r
ed
to
o
u
r
d
ataset,
en
s
u
r
in
g
o
p
tim
al
p
e
r
f
o
r
m
an
ce
.
Acc
o
r
d
in
g
to
th
e
f
in
d
in
g
s
,
wh
ic
h
ar
e
s
u
m
m
e
d
u
p
in
th
e
T
ab
le
4
d
ata
au
g
m
en
tatio
n
b
ec
o
m
es
cr
u
cial
f
o
r
en
h
a
n
cin
g
m
o
d
el.
W
e
ex
a
m
in
ed
th
e
v
ar
i
o
u
s
m
o
d
el'
s
p
er
f
o
r
m
an
ce
s
ac
r
o
s
s
a
r
an
g
e
o
f
d
ata
s
izes
an
d
au
g
m
en
tatio
n
m
eth
o
d
s
in
clu
d
in
g
d
eter
m
in
is
tic
an
d
W
GAN
f
o
r
d
ata
en
h
an
ce
m
e
n
t.
Acc
o
r
d
in
g
to
t
h
e
f
in
d
i
n
g
s
,
wh
i
ch
ar
e
s
u
m
m
ed
u
p
in
th
e
T
a
b
le
s
4
an
d
5
d
ata
au
g
m
en
tatio
n
b
ec
o
m
es c
r
u
cial
f
o
r
en
h
an
cin
g
m
o
d
el.
T
ab
le
4
.
C
o
m
p
a
r
is
o
n
o
f
th
e
m
o
d
els o
n
d
ete
r
m
in
is
tic
au
g
m
en
ted
d
ataset
S
i
n
g
l
e
-
l
e
v
e
l
A
u
g
m
e
n
t
a
t
i
o
n
Bi
-
l
e
v
e
l
A
u
g
me
n
t
a
t
i
o
n
M
o
d
e
l
s
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
S
p
e
c
i
f
i
c
i
t
y
M
o
d
e
l
s
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
S
p
e
c
i
f
i
c
i
t
y
R
e
sN
e
t
-
101
9
1
.
3
0
9
2
.
5
7
9
8
.
9
5
R
e
sN
e
t
-
101
9
9
.
1
5
9
9
.
1
6
9
9
.
9
1
R
e
sN
e
t
-
50
9
1
.
3
0
9
2
.
9
1
9
9
.
0
6
R
e
sN
e
t
-
50
9
6
.
4
9
9
6
.
7
5
9
9
.
6
0
D
e
n
seN
e
t
1
6
9
8
6
.
0
9
8
8
.
0
8
9
8
.
4
0
D
e
n
seN
e
t
1
6
9
9
2
.
9
9
9
3
.
5
5
9
9
.
1
9
V
G
G
1
6
7
9
.
1
3
8
1
.
5
8
9
7
.
5
5
V
G
G
1
6
8
2
.
4
7
8
3
.
3
0
9
8
.
0
2
Ef
f
i
c
i
e
n
t
N
e
t
B
0
6
4
.
3
5
6
9
.
3
7
9
5
.
3
7
Ef
f
i
c
i
e
n
t
N
e
t
B
0
7
1
.
5
3
7
2
.
8
5
9
6
.
8
4
3
.
1
.
E
rr
o
r
m
et
rics
R
o
o
t
m
ea
n
s
q
u
ar
e
e
r
r
o
r
(
R
MSE
)
is
th
e
m
etr
ic
u
s
ed
to
m
ea
s
u
r
e
th
e
d
if
f
er
e
n
ce
b
etwe
en
tr
u
e
v
alu
es
an
d
p
r
ed
icted
v
alu
es a
s
s
h
o
wn
in
Fig
u
r
e
4
,
f
ir
s
t
im
ag
e
o
r
ig
i
n
al
im
ag
e
s
ec
o
n
d
o
n
e
p
r
ed
icted
v
a
lu
e
o
f
im
ag
e
r
esu
ltin
g
f
r
o
m
d
ete
r
m
in
is
tic
au
g
m
en
tati
o
n
an
d
last
I
m
ag
e
r
esu
ltin
g
f
r
o
m
W
GAN
-
GP.
=
√
1
∑
(
−
=
1
y
^
)
(
5
)
wh
er
e
−
,
^
−
an
d
n
–
Nu
m
b
er
o
f
s
am
p
les
.
Fo
r
R
esNet
-
1
0
1
m
o
d
el,
th
e
R
MSE
was f
o
u
n
d
to
b
e
0
.
0
3
0
0
as sh
o
wn
in
T
a
b
le
5
.
Fig
u
r
e
4
.
T
h
e
d
if
f
er
en
ce
b
etwe
en
tr
u
e
v
al
u
es
an
d
th
e
p
r
ed
ict
ed
v
alu
es
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.
16
,
No
.
1
,
Feb
r
u
ar
y
20
26
:
4
1
4
-
422
420
T
ab
le
5
.
R
esNet
-
1
0
1
Mo
d
el
p
er
f
o
r
m
a
n
ce
Au
g
m
e
n
tatio
n
Ac
c
u
ra
c
y
RM
S
E
De
term
in
isti
c
9
9
.
1
5
0
.
0
3
0
0
WG
AN
-
GP
8
9
.
9
0
0
.
3
0
7
5
T
h
e
r
esu
lts
an
d
f
in
d
i
n
g
s
o
f
ea
r
lier
s
tu
d
ies
ar
e
co
m
p
ar
e
d
.
T
a
b
le
6
s
h
o
ws
th
at
alth
o
u
g
h
d
ee
p
lear
n
in
g
m
eth
o
d
s
ar
e
v
er
y
s
u
cc
ess
f
u
l
in
class
if
y
in
g
,
s
eg
m
e
n
tin
g
,
a
n
d
p
r
e
d
ictin
g
co
m
p
lex
m
ed
ical
im
ag
es,
th
e
u
s
e
o
f
s
u
itab
le
au
g
m
en
tatio
n
tech
n
iq
u
es f
u
r
th
er
i
m
p
r
o
v
es m
o
d
el
p
e
r
f
o
r
m
a
n
ce
an
d
g
r
ea
tly
e
n
h
an
c
es a
cc
u
r
ac
y
.
T
ab
le
6
.
C
o
m
p
a
r
is
o
n
r
elatio
n
t
o
d
ata
au
g
m
en
tatio
n
a
n
d
f
etal
-
s
af
e
im
ag
in
g
tech
n
iq
u
es
Ref
C
l
a
s
si
f
i
e
r
D
a
t
a
s
e
t
P
e
r
f
o
r
ma
n
c
e
ma
t
r
i
x
[
1
7
]
GAN
Th
e
sy
n
t
h
e
t
i
c
d
a
t
a
s
e
t
i
s f
i
v
e
t
i
m
e
s l
a
r
g
e
r
t
h
a
n
t
h
e
o
r
i
g
i
n
a
l
d
a
t
a
D
i
c
e
sc
o
r
e
a
c
h
i
e
v
e
d
i
s
0
.
8
1
,
w
i
t
h
a
st
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
o
f
a
p
p
r
o
x
i
ma
t
e
l
y
0
.
0
9
[
1
4
]
R
e
sN
e
t
-
50
Th
e
sy
n
t
h
e
t
i
c
d
a
t
a
s
e
t
i
n
c
r
e
a
se
d
b
y
1
3
t
i
m
e
s t
h
e
si
z
e
o
f
t
h
e
o
r
i
g
i
n
a
l
d
a
t
a
s
e
t
Tw
o
d
a
t
a
s
e
t
s
w
e
r
e
u
se
d
F
ETA
L
-
1
2
5
a
n
d
OB
-
1
2
5
A
c
c
u
r
a
c
y
-
9
4
.
4
%
a
n
d
9
1
.
5
%
r
e
sp
e
c
t
i
v
e
l
y
[
2
9
]
R
e
sN
e
t
-
50
Ec
h
o
c
a
r
d
i
o
g
r
a
p
h
y
A
r
o
u
n
d
7
5
%
a
c
c
u
r
a
c
y
[
1
8
]
GAN
-
g
e
n
e
r
a
t
e
d
v
i
a
I
A
G
A
N
Th
e
sy
n
t
h
e
t
i
c
d
a
t
a
s
e
t
i
n
c
r
e
a
se
d
b
y
9
t
i
mes
t
h
e
si
z
e
o
f
t
h
e
o
r
i
g
i
n
a
l
d
a
t
a
s
e
t
A
c
c
u
r
a
c
y
-
8
0
%
A
U
C
-
0
.
9
0
[
2
8
]
R
e
sN
e
t
-
50
a
n
d
X
c
e
p
t
i
o
n
Th
e
sy
n
t
h
e
t
i
c
d
a
t
a
s
e
t
i
n
c
r
e
a
se
d
b
y
3
t
i
mes
t
h
e
si
z
e
o
f
t
h
e
o
r
i
g
i
n
a
l
d
a
t
a
.
R
e
sN
e
t
-
5
0
,
A
c
c
u
r
a
c
y
-
8
4
.
7
8
%
X
c
e
p
t
i
o
n
A
c
c
u
r
a
c
y
-
8
6
.
9
8
%
P
r
o
p
o
se
d
w
o
r
k
R
e
sN
e
t
-
101
Th
e
t
w
o
m
e
t
h
o
d
s
:
i
)
D
e
t
e
r
mi
n
i
s
t
i
c
i
m
a
g
e
a
u
g
me
n
t
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
,
i
i
)
W
G
A
N
-
G
P
e
x
p
a
n
d
e
d
o
r
i
g
i
n
a
l
d
a
t
a
se
t
s
t
o
1
4
t
i
m
e
s
a
n
d
1
7
t
i
mes
r
e
sp
e
c
t
i
v
e
l
y
.
D
e
t
e
r
m
i
n
i
st
i
c
i
ma
g
e
a
u
g
me
n
t
a
t
i
o
n
A
c
c
u
r
a
c
y
-
9
9
.
1
5
W
G
A
N
-
GP
A
c
c
u
r
a
c
y
-
8
9
.
9
0
4.
CO
NCLU
SI
O
N
T
h
e
d
ata
a
u
g
m
e
n
tatio
n
tech
n
i
q
u
es
ca
n
h
elp
u
s
ad
d
r
ess
th
e
c
h
allen
g
e
o
f
d
ata
s
ca
r
city
an
d
en
s
u
r
e
th
at
o
u
r
s
y
s
tem
f
u
n
ctio
n
s
ef
f
ec
tiv
e
ly
ac
r
o
s
s
a
r
an
g
e
o
f
p
atien
t
d
e
m
o
g
r
ap
h
ics an
d
clin
ical
cir
cu
m
s
tan
ce
s
.
Six
o
u
t o
f
n
in
e
class
es
ac
h
iev
ed
f
u
ll
p
er
f
o
r
m
an
ce
ac
cu
r
ac
y
u
s
in
g
R
esNet
-
1
0
1
with
an
av
er
a
g
e
p
r
e
cisi
o
n
ac
cu
r
ac
y
o
f
9
9
.
1
5
%.
T
h
e
s
ig
n
if
ican
ce
o
f
t
h
is
f
in
d
in
g
lies
in
th
e
p
o
s
s
ib
ilit
y
o
f
a
ch
iev
in
g
h
ig
h
-
q
u
ality
o
u
tco
m
es
with
less
d
ata
u
s
in
g
two
m
eth
o
d
s
,
d
eter
m
in
is
tic
im
ag
e
au
g
m
e
n
tatio
n
t
ec
h
n
iq
u
es
an
d
W
GAN
-
GP.
T
h
e
r
esu
lts
o
b
tain
ed
h
av
e
d
em
o
n
s
tr
ated
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
co
m
p
ar
ed
t
o
e
x
is
tin
g
s
y
s
tem
s
.
T
h
e
im
p
r
o
v
em
en
ts
in
o
v
er
all
d
etec
tio
n
ac
cu
r
ac
y
f
o
r
f
etal
h
ea
r
t
ab
n
o
r
m
alities
h
av
e
b
ee
n
v
alid
ated
b
y
ce
r
tifie
d
g
y
n
ec
o
lo
g
is
t
an
d
f
etal
m
ed
icin
e
s
p
ec
ialis
t
co
n
f
ir
m
in
g
th
at
o
u
r
r
esear
ch
ap
p
r
o
ac
h
o
u
tp
er
f
o
r
m
s
tr
ad
itio
n
al
m
eth
o
d
s
.
Op
tim
izin
g
th
e
p
r
o
p
o
s
ed
s
y
s
tem
f
o
r
r
ea
l
-
ti
m
e
d
ep
lo
y
m
e
n
t
an
d
s
ea
m
less
in
teg
r
atio
n
in
to
ex
is
tin
g
clin
ical
wo
r
k
f
lo
ws
is
ess
en
tial
f
o
r
its
p
r
ac
tical
u
tili
t
y
.
C
o
llab
o
r
atio
n
with
h
ea
lth
c
ar
e
in
s
titu
tio
n
s
an
d
in
d
u
s
tr
y
s
tak
eh
o
ld
er
s
will
b
e
p
iv
o
tal
in
d
ev
elo
p
in
g
u
s
er
-
f
r
ie
n
d
ly
in
ter
f
ac
es a
n
d
in
ter
o
p
e
r
a
b
le
s
y
s
tem
s
.
T
h
e
lim
itatio
n
o
f
th
is
r
esear
ch
is
th
at
im
ag
es
n
ee
d
to
b
e
lab
eled
u
n
d
er
ex
p
er
t
g
u
id
a
n
ce
.
ACK
NO
WL
E
DG
M
E
N
T
S
Au
th
o
r
wan
ts
to
ex
p
r
ess
m
y
s
in
ce
r
e
g
r
atitu
d
e
to
au
th
o
r
’
s
co
lleg
e
an
d
g
u
id
e
f
o
r
p
r
o
v
id
in
g
th
e
r
eso
u
r
ce
s
an
d
s
u
p
p
o
r
t
n
ec
ess
ar
y
f
o
r
th
e
co
m
p
letio
n
o
f
th
is
r
e
s
ea
r
ch
.
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
Nu
sra
t
Ja
we
d
Iq
b
a
l
A
n
sa
ri
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
M
a
n
iro
ja
M
.
E
d
in
b
u
r
g
h
✓
✓
✓
✓
✓
Nik
ita
✓
✓
✓
✓
✓
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
Dee
p
lea
r
n
in
g
a
r
ch
itectu
r
e
fo
r
d
etec
tio
n
o
f fe
ta
l h
e
a
r
t a
n
o
m
a
lies
(
N
u
s
r
a
t J
a
w
ed
I
q
b
a
l A
n
s
a
r
i
)
421
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
T
h
e
au
th
o
r
s
r
ep
o
r
t
th
at
n
o
k
n
o
wn
co
m
p
etin
g
f
in
an
cial
in
te
r
est
o
r
p
er
s
o
n
al
r
elatio
n
s
h
ip
ap
p
ea
r
s
to
h
av
e
in
f
lu
e
n
ce
d
a
n
y
o
f
th
e
wo
r
k
d
escr
ib
ed
in
th
is
p
ap
e
r
.
I
NF
O
RM
E
D
CO
NS
E
N
T
I
n
f
o
r
m
ed
co
n
s
en
t w
as o
b
tain
e
d
f
r
o
m
all
p
ar
ticip
a
n
ts
in
v
o
lv
e
d
in
th
e
s
tu
d
y
.
T
h
e
y
wer
e
f
u
ll
y
in
f
o
r
m
e
d
ab
o
u
t th
e
s
tu
d
y
'
s
p
u
r
p
o
s
e,
p
r
o
ce
d
u
r
es,
an
d
an
y
p
o
ten
tial r
is
k
s
b
ef
o
r
e
ag
r
ee
in
g
t
o
p
ar
ticip
at
e.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t th
e
f
in
d
i
n
g
s
o
f
th
is
s
tu
d
y
a
r
e
o
p
en
ly
a
v
ailab
le
in
r
ef
er
e
n
ce
n
u
m
b
er
[
2
2
]
.
RE
F
E
R
E
NC
E
S
[
1
]
L.
J.
S
a
l
o
m
o
n
e
t
a
l
.
,
“
I
S
U
O
G
P
r
a
c
t
i
c
e
G
u
i
d
e
l
i
n
e
s
(
u
p
d
a
t
e
d
)
:
p
e
r
f
o
r
ma
n
c
e
o
f
t
h
e
r
o
u
t
i
n
e
m
i
d
‐
t
r
i
m
e
st
e
r
f
e
t
a
l
u
l
t
r
a
s
o
u
n
d
sc
a
n
,
”
U
l
t
r
a
so
u
n
d
i
n
O
b
st
e
t
ri
c
s &
G
y
n
e
c
o
l
o
g
y
,
v
o
l
.
5
9
,
n
o
.
6
,
p
p
.
8
4
0
–
8
5
6
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
2
/
u
o
g
.
2
4
8
8
8
.
[
2
]
A
.
J.
M
o
o
n
-
G
r
a
d
y
e
t
a
l
.
,
“
G
u
i
d
e
l
i
n
e
s
a
n
d
r
e
c
o
mm
e
n
d
a
t
i
o
n
s
f
o
r
p
e
r
f
o
r
ma
n
c
e
o
f
t
h
e
f
e
t
a
l
e
c
h
o
c
a
r
d
i
o
g
r
a
m:
a
n
u
p
d
a
t
e
f
r
o
m
t
h
e
A
meric
a
n
S
o
c
i
e
t
y
o
f
Ec
h
o
c
a
r
d
i
o
g
r
a
p
h
y
,
”
J
o
u
rn
a
l
o
f
t
h
e
Am
e
ri
c
a
n
S
o
c
i
e
t
y
o
f
E
c
h
o
c
a
r
d
i
o
g
ra
p
h
y
,
v
o
l
.
3
6
,
n
o
.
7
,
p
p
.
6
7
9
–
7
2
3
,
Ju
l
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
c
h
o
.
2
0
2
3
.
0
4
.
0
1
4
.
[
3
]
M
.
C
.
F
i
o
r
e
n
t
i
n
o
,
F
.
P
.
V
i
l
l
a
n
i
,
M
.
D
i
C
o
sm
o
,
E.
F
r
o
n
t
o
n
i
,
a
n
d
S
.
M
o
c
c
i
a
,
“
A
r
e
v
i
e
w
o
n
d
e
e
p
-
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
f
e
t
a
l
u
l
t
r
a
s
o
u
n
d
-
i
ma
g
e
a
n
a
l
y
s
i
s,
”
M
e
d
i
c
a
l
I
m
a
g
e
A
n
a
l
y
s
i
s
,
v
o
l
.
8
3
,
p
.
1
0
2
6
2
9
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
d
i
a
.
2
0
2
2
.
1
0
2
6
2
9
.
[
4
]
M
.
K
o
mat
s
u
e
t
a
l
.
,
“
D
e
t
e
c
t
i
o
n
o
f
c
a
r
d
i
a
c
s
t
r
u
c
t
u
r
a
l
a
b
n
o
r
m
a
l
i
t
i
e
s
i
n
f
e
t
a
l
u
l
t
r
a
s
o
u
n
d
v
i
d
e
o
s
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
1
,
n
o
.
1
,
p
.
3
7
1
,
Ja
n
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
1
0
1
0
3
7
1
.
[
5
]
O
.
J.
B
e
n
a
v
i
d
e
z
,
K
.
G
a
u
v
r
e
a
u
,
a
n
d
T.
G
e
v
a
,
“
D
i
a
g
n
o
st
i
c
e
r
r
o
r
s
i
n
c
o
n
g
e
n
i
t
a
l
e
c
h
o
c
a
r
d
i
o
g
r
a
p
h
y
:
i
m
p
o
r
t
a
n
c
e
o
f
st
u
d
y
c
o
n
d
i
t
i
o
n
s
,
”
J
o
u
rn
a
l
o
f
t
h
e
Am
e
ri
c
a
n
S
o
c
i
e
t
y
o
f
Ec
h
o
c
a
r
d
i
o
g
r
a
p
h
y
,
v
o
l
.
2
7
,
n
o
.
6
,
p
p
.
6
1
6
–
6
2
3
,
J
u
n
.
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
c
h
o
.
2
0
1
4
.
0
3
.
0
0
1
.
[
6
]
S
.
G
e
m
a
n
,
E
.
B
i
e
n
e
n
s
t
o
c
k
,
a
n
d
R
.
D
o
u
r
sat
,
“
N
e
u
r
a
l
n
e
t
w
o
r
k
s
a
n
d
t
h
e
b
i
a
s/
v
a
r
i
a
n
c
e
d
i
l
e
mm
a
,
”
N
e
u
r
a
l
C
o
m
p
u
t
a
t
i
o
n
,
v
o
l
.
4
,
n
o
.
1
,
p
p
.
1
–
5
8
,
J
a
n
.
1
9
9
2
,
d
o
i
:
1
0
.
1
1
6
2
/
n
e
c
o
.
1
9
9
2
.
4
.
1
.
1
.
[
7
]
S
.
I
o
f
f
e
a
n
d
C
.
S
z
e
g
e
d
y
,
“
B
a
t
c
h
n
o
r
mal
i
z
a
t
i
o
n
:
a
c
c
e
l
e
r
a
t
i
n
g
d
e
e
p
n
e
t
w
o
r
k
t
r
a
i
n
i
n
g
b
y
r
e
d
u
c
i
n
g
i
n
t
e
r
n
a
l
c
o
v
a
r
i
a
t
e
sh
i
f
t
,
”
Pr
e
p
ri
n
t
a
rXi
v
:
1
5
0
2
.
0
3
1
6
7
,
M
a
r
.
2
0
1
5
.
[
8
]
H.
-
C
.
S
h
i
n
e
t
a
l
.
,
“
M
e
d
i
c
a
l
i
ma
g
e
s
y
n
t
h
e
s
i
s
f
o
r
d
a
t
a
a
u
g
m
e
n
t
a
t
i
o
n
a
n
d
a
n
o
n
y
m
i
z
a
t
i
o
n
u
s
i
n
g
g
e
n
e
r
a
t
i
v
e
a
d
v
e
r
sa
r
i
a
l
n
e
t
w
o
r
k
s
,
”
i
n
I
n
S
i
m
u
l
a
t
i
o
n
a
n
d
S
y
n
t
h
e
s
i
s
i
n
M
e
d
i
c
a
l
I
m
a
g
i
n
g
:
T
h
i
r
d
I
n
t
e
r
n
a
t
i
o
n
a
l
W
o
rks
h
o
p
,
S
AS
H
I
MI
2
0
1
8
,
2
0
1
8
,
p
p
.
1
–
11
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
0
0
5
3
6
-
8
_
1
.
[
9
]
S
.
N
u
r
mai
n
i
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
sed
c
o
m
p
u
t
e
r
-
a
i
d
e
d
f
e
t
a
l
e
c
h
o
c
a
r
d
i
o
g
r
a
p
h
y
:
a
p
p
l
i
c
a
t
i
o
n
t
o
h
e
a
r
t
st
a
n
d
a
r
d
v
i
e
w
seg
m
e
n
t
a
t
i
o
n
f
o
r
c
o
n
g
e
n
i
t
a
l
h
e
a
r
t
d
e
f
e
c
t
s
d
e
t
e
c
t
i
o
n
,
”
S
e
n
so
rs
,
v
o
l
.
2
1
,
n
o
.
2
3
,
p
.
8
0
0
7
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
1
2
3
8
0
0
7
.
[
1
0
]
S
.
N
u
r
ma
i
n
i
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
i
m
p
r
o
v
i
n
g
t
h
e
e
f
f
e
c
t
i
v
e
n
e
ss
o
f
r
o
u
t
i
n
e
p
r
e
n
a
t
a
l
scre
e
n
i
n
g
f
o
r
ma
j
o
r
c
o
n
g
e
n
i
t
a
l
h
e
a
r
t
d
i
s
e
a
se
s,”
J
o
u
r
n
a
l
o
f
C
l
i
n
i
c
a
l
Me
d
i
c
i
n
e
,
v
o
l
.
1
1
,
n
o
.
2
1
,
p
.
6
4
5
4
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
j
c
m
1
1
2
1
6
4
5
4
.
[
1
1
]
C
.
A
.
C
o
m
b
s
,
A
.
B
.
H
a
m
e
e
d
,
A
.
M
.
F
r
i
e
d
m
a
n
,
a
n
d
I
.
A
.
H
o
sk
i
n
s,
“
S
p
e
c
i
a
l
st
a
t
e
me
n
t
:
P
r
o
p
o
se
d
q
u
a
l
i
t
y
me
t
r
i
c
s
t
o
a
ss
e
ss
a
c
c
u
r
a
c
y
o
f
p
r
e
n
a
t
a
l
d
e
t
e
c
t
i
o
n
o
f
c
o
n
g
e
n
i
t
a
l
h
e
a
r
t
d
e
f
e
c
t
s
,
”
Am
e
ri
c
a
n
J
o
u
r
n
a
l
o
f
O
b
st
e
t
r
i
c
s
a
n
d
G
y
n
e
c
o
l
o
g
y
,
v
o
l
.
2
2
2
,
n
o
.
6
,
p
p
.
B
2
--
B
9
,
Ju
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
j
o
g
.
2
0
2
0
.
0
2
.
0
4
0
.
[
1
2
]
R
.
V
u
l
l
i
n
g
s
,
“
F
e
t
a
l
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
p
h
y
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
p
r
e
n
a
t
a
l
d
e
t
e
c
t
i
o
n
o
f
c
o
n
g
e
n
i
t
a
l
h
e
a
r
t
d
i
sea
s
e
,
”
i
n
2
0
1
9
C
o
m
p
u
t
i
n
g
i
n
C
a
rd
i
o
l
o
g
y
(
C
i
n
C
)
,
D
e
c
.
2
0
1
9
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
2
2
4
8
9
/
C
i
n
C
.
2
0
1
9
.
0
7
2
.
[
1
3
]
C
.
A
t
h
a
l
y
e
a
n
d
R
.
A
r
n
a
o
u
t
,
“
D
o
m
a
i
n
-
g
u
i
d
e
d
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
o
n
me
d
i
c
a
l
i
m
a
g
i
n
g
,
”
PLO
S
O
N
E
,
v
o
l
.
1
8
,
n
o
.
3
,
p
.
e
0
2
8
2
5
3
2
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
8
2
5
3
2
.
[
1
4
]
E.
M
i
s
k
e
e
n
e
t
a
l
.
,
“
P
r
o
s
p
e
c
t
i
v
e
a
p
p
l
i
c
a
t
i
o
n
s
o
f
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
i
n
f
e
t
a
l
m
e
d
i
c
i
n
e
:
a
sc
o
p
i
n
g
r
e
v
i
e
w
o
f
r
e
c
e
n
t
u
p
d
a
t
e
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
G
e
n
e
r
a
l
M
e
d
i
c
i
n
e
,
v
o
l
.
V
o
l
u
m
e
1
8
,
p
p
.
2
3
7
–
2
4
5
,
J
a
n
.
2
0
2
5
,
d
o
i
:
1
0
.
2
1
4
7
/
I
JG
M
.
S
4
9
0
2
6
1
.
[
1
5
]
F
.
N
o
w
a
k
e
t
a
l
.
,
“
A
n
i
n
v
e
st
i
g
a
t
i
o
n
i
n
t
o
a
u
g
me
n
t
a
t
i
o
n
a
n
d
p
r
e
p
r
o
c
e
ssi
n
g
f
o
r
o
p
t
i
mi
s
i
n
g
X
-
r
a
y
c
l
a
ss
i
f
i
c
a
t
i
o
n
i
n
l
i
mi
t
e
d
d
a
t
a
se
t
s:
a
c
a
se
st
u
d
y
o
n
n
e
c
r
o
t
i
si
n
g
e
n
t
e
r
o
c
o
l
i
t
i
s,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
Assi
s
t
e
d
Ra
d
i
o
l
o
g
y
a
n
d
S
u
r
g
e
r
y
,
v
o
l
.
1
9
,
n
o
.
6
,
p
p
.
1
2
2
3
–
1
2
3
1
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
5
4
8
-
0
2
4
-
0
3
1
0
7
-
0.
[
1
6
]
H
.
M
.
B
a
l
a
h
a
,
A
.
O
.
S
h
a
b
a
n
,
E
.
M
.
E
l
-
G
e
n
d
y
,
a
n
d
M
.
M
.
S
a
a
f
a
n
,
“
A
m
u
l
t
i
-
v
a
r
i
a
t
e
h
e
a
r
t
d
i
s
e
a
s
e
o
p
t
i
m
i
z
a
t
i
o
n
a
n
d
r
e
c
o
g
n
i
t
i
o
n
f
r
a
m
e
w
o
r
k
,
”
N
e
u
r
a
l
C
o
m
p
u
t
i
n
g
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
4
,
n
o
.
1
8
,
p
p
.
1
5
9
0
7
–
1
5
9
4
4
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
022
-
07241
-
1.
[
1
7
]
C
.
T
i
a
g
o
e
t
a
l
.
,
“
A
d
a
t
a
a
u
g
me
n
t
a
t
i
o
n
p
i
p
e
l
i
n
e
t
o
g
e
n
e
r
a
t
e
s
y
n
t
h
e
t
i
c
l
a
b
e
l
e
d
d
a
t
a
se
t
s
o
f
3
D
e
c
h
o
c
a
r
d
i
o
g
r
a
p
h
y
i
m
a
g
e
s
u
s
i
n
g
a
G
A
N
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
9
8
8
0
3
–
9
8
8
1
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
E
S
S
.
2
0
2
2
.
3
2
0
7
1
7
7
.
[
1
8
]
S
.
M
o
t
a
m
e
d
,
P
.
R
o
g
a
l
l
a
,
a
n
d
F
.
K
h
a
l
v
a
t
i
,
“
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
(
G
A
N
s)
f
o
r
G
A
N
-
b
a
se
d
d
e
t
e
c
t
i
o
n
o
f
P
n
e
u
m
o
n
i
a
a
n
d
C
O
V
I
D
-
1
9
i
n
c
h
e
st
X
-
r
a
y
i
ma
g
e
s
,
”
I
n
f
o
rm
a
t
i
c
s
i
n
Me
d
i
c
i
n
e
U
n
l
o
c
k
e
d
,
v
o
l
.
2
7
,
p
.
1
0
0
7
7
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
m
u
.
2
0
2
1
.
1
0
0
7
7
9
.
[
1
9
]
X
.
W
a
n
g
,
K
.
W
a
n
g
,
a
n
d
S
.
Li
a
n
,
“
A
su
r
v
e
y
o
n
f
a
c
e
d
a
t
a
a
u
g
m
e
n
t
a
t
i
o
n
f
o
r
t
h
e
t
r
a
i
n
i
n
g
o
f
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
N
e
u
r
a
l
C
o
m
p
u
t
i
n
g
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
2
,
n
o
.
1
9
,
p
p
.
1
5
5
0
3
–
1
5
5
3
1
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
020
-
0
4
7
4
8
-
3.
[
2
0
]
R
.
S
t
o
e
a
n
,
D
.
I
l
i
e
sc
u
,
C
.
S
t
o
e
a
n
,
C
.
P
a
t
r
u
,
a
n
d
R
.
N
a
g
y
,
“
S
e
c
o
n
d
t
r
i
mest
e
r
f
e
t
a
l
e
c
h
o
c
a
r
d
i
o
g
r
a
p
h
y
d
a
t
a
set
f
o
r
i
ma
g
e
seg
m
e
n
t
a
t
i
o
n
,
”
Fi
g
s
h
a
r
e
F
i
g
u
r
e
,
2
0
2
2
,
d
o
i
:
1
0
.
6
0
8
4
/
m
9
.
f
i
g
s
h
a
r
e
.
2
1
2
1
5
5
9
7
.
[
2
1
]
Q
.
N
i
n
g
a
n
d
Z
.
Q
i
,
“
W
G
A
N
-
G
P
_
G
l
u
:
A
se
mi
-
s
u
p
e
r
v
i
se
d
m
o
d
e
l
b
a
s
e
d
o
n
d
o
u
b
l
e
g
e
n
e
r
a
t
o
r
-
W
a
s
serst
e
i
n
G
A
N
w
i
t
h
g
r
a
d
i
e
n
t
p
e
n
a
l
t
y
a
l
g
o
r
i
t
h
m
f
o
r
g
l
u
t
a
r
y
l
a
t
i
o
n
s
i
t
e
i
d
e
n
t
i
f
i
c
a
t
i
o
n
,
”
C
o
m
p
u
t
e
rs
i
n
Bi
o
l
o
g
y
a
n
d
M
e
d
i
c
i
n
e
,
v
o
l
.
1
8
4
,
p
.
1
0
9
3
2
8
,
Ja
n
.
2
0
2
5
,
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.
16
,
No
.
1
,
Feb
r
u
ar
y
20
26
:
4
1
4
-
422
422
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
b
i
o
me
d
.
2
0
2
4
.
1
0
9
3
2
8
.
[
2
2
]
G.
-
C
.
L
e
e
,
J.
-
H
.
Li
,
a
n
d
Z.
-
Y
.
L
i
,
“
A
W
a
ssers
t
e
i
n
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
–
g
r
a
d
i
e
n
t
p
e
n
a
l
t
y
-
b
a
se
d
m
o
d
e
l
w
i
t
h
i
m
b
a
l
a
n
c
e
d
d
a
t
a
e
n
h
a
n
c
e
me
n
t
f
o
r
n
e
t
w
o
r
k
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
3
,
n
o
.
1
4
,
p
.
8
1
3
2
,
J
u
l
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
1
4
8
1
3
2
.
[
2
3
]
C
.
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
(
g
e
n
e
r
a
t
i
v
e
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
)
i
n
p
e
d
i
a
t
r
i
c
r
a
d
i
o
l
o
g
y
:
A
s
y
st
e
ma
t
i
c
r
e
v
i
e
w
,
”
C
h
i
l
d
r
e
n
,
v
o
l
.
1
0
,
n
o
.
8
,
p
.
1
3
7
2
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
c
h
i
l
d
r
e
n
1
0
0
8
1
3
7
2
.
[
2
4
]
K
.
H
e
,
X
.
Z
h
a
n
g
,
S
.
R
e
n
,
a
n
d
J
.
S
u
n
,
“
D
e
e
p
r
e
si
d
u
a
l
l
e
a
r
n
i
n
g
f
o
r
i
ma
g
e
r
e
c
o
g
n
i
t
i
o
n
,
”
i
n
2
0
1
6
I
EEE
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
si
o
n
a
n
d
Pa
t
t
e
rn
Re
c
o
g
n
i
t
i
o
n
(
C
V
P
R)
,
Ju
n
.
2
0
1
6
,
p
p
.
7
7
0
–
778
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
1
6
.
9
0
.
[
2
5
]
M
.
F
.
A
s
l
a
n
,
K
.
S
a
b
a
n
c
i
,
a
n
d
A
.
D
u
r
d
u
,
“
A
C
N
N
-
b
a
se
d
n
o
v
e
l
so
l
u
t
i
o
n
f
o
r
d
e
t
e
r
mi
n
i
n
g
t
h
e
su
r
v
i
v
a
l
s
t
a
t
u
s
o
f
h
e
a
r
t
f
a
i
l
u
r
e
p
a
t
i
e
n
t
s
w
i
t
h
c
l
i
n
i
c
a
l
r
e
c
o
r
d
d
a
t
a
:
n
u
meri
c
t
o
i
ma
g
e
,
”
Bi
o
m
e
d
i
c
a
l
S
i
g
n
a
l
Pr
o
c
e
s
si
n
g
a
n
d
C
o
n
t
ro
l
,
v
o
l
.
6
8
,
p
.
1
0
2
7
1
6
,
Ju
l
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
s
p
c
.
2
0
2
1
.
1
0
2
7
1
6
.
[
2
6
]
Y
.
F
u
,
M
.
G
o
n
g
,
G
.
Y
a
n
g
,
H
.
W
e
i
,
a
n
d
J.
Z
h
o
u
,
“
E
v
o
l
u
t
i
o
n
a
r
y
G
A
N
–
b
a
sed
d
a
t
a
a
u
g
me
n
t
a
t
i
o
n
f
o
r
c
a
r
d
i
a
c
m
a
g
n
e
t
i
c
r
e
so
n
a
n
c
e
i
ma
g
e
,
”
C
o
m
p
u
t
e
r
s,
Ma
t
e
r
i
a
l
s &
C
o
n
t
i
n
u
a
,
v
o
l
.
6
8
,
n
o
.
1
,
p
p
.
1
3
5
9
–
1
3
7
4
,
2
0
2
1
,
d
o
i
:
1
0
.
3
2
6
0
4
/
c
m
c
.
2
0
2
1
.
0
1
6
5
3
6
.
[
2
7
]
I
.
E.
Ti
b
e
r
mac
i
n
e
e
t
a
l
.
,
“
A
d
v
e
r
sar
i
a
l
d
e
n
o
i
s
i
n
g
o
f
EEG
si
g
n
a
l
s
:
a
c
o
mp
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
st
a
n
d
a
r
d
G
A
N
a
n
d
W
G
A
N
-
G
P
a
p
p
r
o
a
c
h
e
s,
”
F
ro
n
t
i
e
rs
i
n
H
u
m
a
n
N
e
u
ro
sc
i
e
n
c
e
,
v
o
l
.
1
9
,
M
a
y
2
0
2
5
,
d
o
i
:
1
0
.
3
3
8
9
/
f
n
h
u
m.
2
0
2
5
.
1
5
8
3
3
4
2
.
[
2
8
]
B
.
Z
h
a
n
g
,
H
.
Li
u
,
H
.
L
u
o
,
a
n
d
K
.
Li
,
“
A
u
t
o
ma
t
i
c
q
u
a
l
i
t
y
a
ssessm
e
n
t
f
o
r
2
D
f
e
t
a
l
s
o
n
o
g
r
a
p
h
i
c
s
t
a
n
d
a
r
d
p
l
a
n
e
b
a
se
d
o
n
mu
l
t
i
t
a
sk
l
e
a
r
n
i
n
g
,
”
M
e
d
i
c
i
n
e
,
v
o
l
.
1
0
0
,
n
o
.
4
,
p
.
e
2
4
4
2
7
,
J
a
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
9
7
/
M
D
.
0
0
0
0
0
0
0
0
0
0
0
2
4
4
2
7
.
[
2
9
]
Y
.
G
o
n
g
e
t
a
l
.
,
“
F
e
t
a
l
c
o
n
g
e
n
i
t
a
l
h
e
a
r
t
d
i
sea
s
e
e
c
h
o
c
a
r
d
i
o
g
r
a
m
scr
e
e
n
i
n
g
b
a
se
d
o
n
D
G
A
C
N
N
:
a
d
v
e
r
sari
a
l
o
n
e
-
c
l
a
ss
c
l
a
ssi
f
i
c
a
t
i
o
n
c
o
m
b
i
n
e
d
w
i
t
h
v
i
d
e
o
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
,
”
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
Me
d
i
c
a
l
I
m
a
g
i
n
g
,
v
o
l
.
3
9
,
n
o
.
4
,
p
p
.
1
2
0
6
–
1
2
2
2
,
A
p
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
T
M
I
.
2
0
1
9
.
2
9
4
6
0
5
9
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Nusr
a
t
J
a
we
d
Iq
b
a
l
Ansa
r
i
is
c
u
rre
n
tl
y
p
u
rsu
i
n
g
a
P
h
D
d
e
g
re
e
in
e
lec
tro
n
ics
a
n
d
tele
c
o
m
m
u
n
ica
ti
o
n
e
n
g
in
e
e
ri
n
g
fr
o
m
th
e
Un
i
v
e
rsity
o
f
M
u
m
b
a
i,
In
d
ia.
S
h
e
is
wo
r
k
i
n
g
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
in
th
e
De
p
a
rtme
n
t
o
f
C
o
m
p
u
ter
E
n
g
i
n
e
e
rin
g
a
t
Vi
v
e
k
a
n
a
n
d
Ed
u
c
a
ti
o
n
S
o
c
iety
’s
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
C
h
e
m
b
u
r,
In
d
ia.
He
r
re
se
a
r
c
h
in
tere
sts
in
c
lu
d
e
sig
n
a
l
p
ro
c
e
ss
in
g
,
a
rti
ficia
l
in
tel
li
g
e
n
c
e
,
ima
g
e
p
ro
c
e
ss
in
g
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
u
sra
t.
a
n
sa
ri
@v
e
s.a
c
.
in
.
Ma
n
iro
j
a
M.
Ed
in
b
u
r
g
h
h
o
l
d
s
a
P
h
.
D.
i
n
e
lec
tro
n
ic
s
fro
m
S
G
BAU
,
M
a
h
a
ra
sh
tra,
In
d
ia.
S
h
e
is t
h
e
He
a
d
o
f
t
h
e
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
i
c
s a
n
d
Tele
c
o
m
m
u
n
ica
ti
o
n
s
En
g
i
n
e
e
rin
g
a
t
TS
EC
,
M
u
m
b
a
i.
S
h
e
h
o
ld
s
3
1
y
e
a
rs
o
f
w
o
rk
e
x
p
e
rien
c
e
in
a
c
a
d
e
m
ics
a
n
d
is
a
re
c
o
g
n
ize
d
P
h
.
D
.
G
u
id
e
o
f
th
e
U
n
iv
e
rsit
y
o
f
M
u
m
b
a
i.
S
h
e
h
a
s
a
ro
u
n
d
3
0
n
a
ti
o
n
a
l/
in
ter
n
a
ti
o
n
a
l
j
o
u
r
n
a
l
p
u
b
li
c
a
ti
o
n
s,
a
r
o
u
n
d
2
4
n
a
ti
o
n
a
l/
i
n
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
a
n
d
re
c
e
iv
e
d
a
m
in
o
r
re
se
a
rc
h
g
ra
n
t
fro
m
th
e
Un
i
v
e
rsity
o
f
M
u
m
b
a
i
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
a
n
iro
ja@
th
a
d
o
m
a
l.
o
rg
.
Nik
ita
is
Ce
rti
fied
G
y
n
e
c
o
lo
g
ist
a
n
d
F
e
tal
M
e
d
icin
e
S
p
e
c
ialist,
G
y
n
e
c
o
lo
g
ica
l
Lap
a
ro
sc
o
p
ic
S
u
r
g
e
o
n
(M
UH
S
,
F
M
AS,
ICOG
)
a
ss
istan
t
p
r
o
fe
ss
o
r
,
De
p
a
rtme
n
t
o
f
Ob
ste
tri
c
s
a
n
d
G
y
n
e
c
o
lo
g
y
a
t
P
.
G
M
e
d
ica
l
Tru
st
Ho
sp
it
a
l.
P
u
b
li
s
h
e
d
e
x
ten
siv
e
l
y
in
n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls.
Au
t
h
o
r
o
f
“
Co
n
c
e
p
ti
o
n
t
o
Co
n
fi
n
e
m
e
n
t”
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
rn
i
k
it
a
1
9
6
2
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.