I
nte
rna
t
io
na
l J
o
urna
l o
f
I
nfo
rm
a
t
ics a
nd
Co
m
m
un
ica
t
io
n T
ec
hn
o
lo
g
y
(
I
J
-
I
CT
)
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
,
p
p
.
1
2
2
6
~
1
2
3
7
I
SS
N:
2252
-
8
7
7
6
,
DOI
:
1
0
.
1
1
5
9
1
/iji
ct
.
v
1
5
i
3
.
pp
1
2
2
6
-
1
2
3
7
1226
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ict.
ia
esco
r
e.
co
m
Neura
l ne
twork
-
b
a
sed dia
g
no
sis
of
type 2
dia
bet
es
using
a
n
irido
lo
g
y
appro
a
ch
Ala
a
Abdu
lk
a
re
em
Ahm
ed
1
,
M
o
ha
m
m
a
d T
a
riq Y
a
s
ee
n
1
,2
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
s
i
t
y
o
f
M
o
su
l
,
M
o
su
l
,
I
r
a
q
2
D
e
p
a
r
t
me
n
t
o
f
C
o
mm
u
n
i
c
a
t
i
o
n
s
a
n
d
I
n
t
e
l
l
i
g
e
n
t
D
i
g
i
t
a
l
S
y
s
t
e
ms
En
g
i
n
e
e
r
i
n
g
,
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
y
o
f
M
o
s
u
l
,
M
o
s
u
l
,
I
r
a
q
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
r
8
,
2
0
2
5
R
ev
is
ed
Feb
1
4
,
2
0
2
6
Acc
ep
ted
Ma
y
2
1
,
2
0
2
6
Th
e
g
r
o
win
g
g
l
o
b
a
l
o
c
c
u
rre
n
c
e
o
f
ty
p
e
2
d
iab
e
tes
re
q
u
ires
t
h
e
d
e
v
e
lo
p
m
e
n
t
o
f
n
o
n
-
in
v
a
siv
e
a
n
d
e
ffe
c
ti
v
e
d
iag
n
o
stic
m
e
th
o
d
s.
Th
is
wo
r
k
p
ro
p
o
se
s
a
n
o
v
e
l
a
p
p
r
o
a
c
h
to
d
e
tec
ti
n
g
ty
p
e
2
d
iab
e
tes
u
si
n
g
ir
id
o
lo
g
y
a
n
d
m
a
c
h
in
e
lea
rn
in
g
(
M
L)
tec
h
n
iq
u
e
s.
By
a
n
a
ly
z
in
g
th
e
ir
is
o
f
t
h
e
rig
h
t
e
y
e
,
a
sin
g
le
re
g
io
n
o
f
in
tere
st
(ROI)
c
o
rre
sp
o
n
d
i
n
g
t
o
th
e
h
e
a
d
o
f
t
h
e
p
a
n
c
re
a
s
is
re
c
o
g
n
ize
d
fo
r
fe
a
tu
re
e
x
trac
ti
o
n
.
A
to
tal
o
f
1
1
2
sta
ti
stica
l
a
n
d
tex
tu
re
fe
a
tu
re
s
a
re
e
x
trac
ted
u
sin
g
g
ra
y
-
lev
e
l
c
o
-
o
c
c
u
rre
n
c
e
m
a
tri
x
(G
LCM
)
a
n
d
d
isc
re
te
wa
v
e
let
tran
sfo
rm
(DWT
)
a
lg
o
rit
h
m
s.
F
iv
e
n
e
u
ra
l
n
e
two
rk
(NN
)
m
o
d
e
ls
-
n
a
rr
o
w,
m
e
d
i
u
m
,
wid
e
,
b
i
-
lay
e
re
d
,
a
n
d
tr
i
-
lay
e
re
d
a
re
d
e
p
lo
y
e
d
to
c
las
sify
h
e
a
lt
h
y
a
n
d
d
ia
b
e
ti
c
p
e
o
p
le.
Th
e
m
o
d
e
ls
a
re
train
e
d
a
n
d
a
ss
e
ss
e
d
u
sin
g
a
ra
n
g
e
o
f
k
-
fo
l
d
v
a
l
u
e
s (2
t
o
2
0
)
t
o
o
p
ti
m
ize
p
e
rfo
rm
a
n
c
e
.
T
h
e
h
i
g
h
e
s
t
c
las
sifica
ti
o
n
a
c
c
u
ra
c
y
o
f
8
3
.
2
%
wa
s
re
a
c
h
e
d
u
sin
g
t
h
e
n
a
rr
o
w
n
e
u
ra
l
n
e
two
rk
(NN
N)
m
o
d
e
l
a
t
7
-
fo
l
d
c
ro
ss
-
v
a
li
d
a
ti
o
n
.
T
h
is
wo
r
k
e
x
h
i
b
it
s
th
e
p
o
ten
ti
a
l
o
f
iri
d
o
lo
g
y
-
b
a
se
d
M
L
a
p
p
ro
a
c
h
e
s
fo
r
n
o
n
-
in
v
a
siv
e
d
iab
e
tes
d
iag
n
o
sis,
p
ro
v
id
i
n
g
a
p
r
o
m
isin
g
su
b
stit
u
te t
o
trad
it
i
o
n
a
l
b
l
o
o
d
tes
t
s.
K
ey
w
o
r
d
s
:
B
io
m
ed
ical
im
ag
in
g
Dis
ea
s
e
p
r
ed
ictio
n
I
r
id
o
lo
g
y
I
r
is
class
if
icatio
n
Ma
ch
in
e
lear
n
in
g
Neu
r
al
n
etwo
r
k
No
n
-
in
v
asiv
e
d
ia
g
n
o
s
is
T
y
p
e
2
d
iab
etes
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Mo
h
am
m
ad
T
ar
iq
Yaseen
Dep
ar
tm
en
t o
f
C
o
m
m
u
n
icatio
n
s
an
d
I
n
tellig
e
n
t D
ig
ital Sy
s
tem
s
E
n
g
in
ee
r
in
g
,
C
o
lleg
e
o
f
E
n
g
in
ee
r
in
g
Un
iv
er
s
ity
o
f
Mo
s
u
l
Mo
s
u
l,
I
r
aq
E
m
ail:
m
ty
aseen
@
u
o
m
o
s
u
l.e
d
u
.
iq
1.
I
NT
RO
D
UCT
I
O
N
D
iab
etes
is
a
d
is
ea
s
e
th
at
is
p
r
ev
alen
t
wo
r
ld
wid
e
a
n
d
it
s
p
r
ev
alen
ce
c
o
n
tin
u
es
to
r
i
s
e
d
u
e
to
u
n
h
ea
lth
y
life
s
ty
le
ch
a
n
g
es
o
f
u
n
h
ea
lth
y
d
iet
an
d
lac
k
o
f
e
x
er
cise
[
1
]
,
wh
ich
c
o
n
s
titu
tes
a
s
ig
n
if
ican
t
b
u
r
d
en
o
n
h
ea
lth
ca
r
e
s
y
s
tem
s
an
d
p
u
b
lic
h
ea
lth
.
I
ts
co
m
p
licatio
n
s
p
o
s
e
a
r
is
k
to
h
u
m
an
h
ea
lt
h
as
it
m
ay
ca
u
s
e
k
id
n
ey
f
ailu
r
e,
h
ea
r
t
attac
k
s
,
a
m
p
u
tatio
n
o
f
th
e
lo
wer
lim
b
s
,
r
etin
o
p
ath
y
a
n
d
s
tr
o
k
e
[
2
]
Di
ab
etes
is
a
ch
r
o
n
ic
m
etab
o
lic
d
is
ea
s
e
th
at
o
cc
u
r
s
as
a
r
esu
lt
o
f
d
ec
r
ea
s
ed
in
s
u
li
n
ef
f
ec
tiv
en
ess
o
r
t
h
e
in
ab
ilit
y
o
f
th
e
p
a
n
cr
ea
s
to
s
ec
r
ete
in
s
u
lin
p
r
o
p
er
ly
,
wh
ic
h
p
o
s
es
a
r
is
k
to
th
e
b
o
d
y
'
s
o
r
g
an
s
[
1
]
.
T
h
e
h
o
r
m
o
n
e
in
s
u
li
n
is
r
esp
o
n
s
ib
le
f
o
r
f
ac
ilit
atin
g
th
e
ab
s
o
r
p
tio
n
o
f
g
lu
co
s
e
in
to
th
e
b
o
d
y
'
s
ce
ll
s
,
w
h
ich
in
tu
r
n
is
r
esp
o
n
s
ib
le
f
o
r
g
en
er
atin
g
e
n
er
g
y
.
T
h
e
d
e
f
icien
cy
i
n
in
s
u
lin
s
ec
r
etio
n
in
th
e
b
o
d
y
lead
s
t
o
an
i
n
cr
ea
s
e
in
t
h
e
lev
el
o
f
g
lu
c
o
s
e
in
th
e
b
lo
o
d
as
a
r
esu
lt
o
f
th
ese
ce
lls
n
o
t
ab
s
o
r
b
in
g
g
lu
co
s
e.
T
h
is
m
ak
es
th
e
h
u
m
an
b
o
d
y
f
ac
e
ch
allen
g
es
in
p
r
o
d
u
cin
g
o
r
u
s
in
g
in
s
u
lin
,
wh
ich
lead
s
to
d
if
f
icu
l
ty
co
n
tr
o
llin
g
g
lu
c
o
s
e
[
2
]
.
T
h
e
k
n
o
wn
ty
p
es
o
f
d
iab
etes
ar
e
ty
p
e
1
d
iab
etes,
t
y
p
e
2
d
i
ab
etes,
an
d
g
estatio
n
al
d
iab
et
es.
T
y
p
e
2
d
iab
etes
k
n
o
w
n
as
n
o
n
-
in
s
u
lin
-
d
ep
en
d
en
t
d
iab
etes
[
3
]
,
is
t
h
e
m
o
s
t
co
m
m
o
n
in
th
e
w
o
r
ld
.
I
t
o
cc
u
r
s
as
a
r
esu
lt
o
f
wea
k
in
s
u
lin
p
r
o
d
u
ctio
n
a
n
d
s
ec
r
etio
n
f
r
o
m
t
h
e
b
eta
ce
ll
s
o
f
t
h
e
p
an
cr
ea
s
i
n
a
d
d
itio
n
t
o
in
s
u
lin
r
esis
tan
ce
in
th
e
p
er
ip
h
e
r
al
tis
s
u
es.
T
h
e
o
cc
u
r
r
e
n
ce
o
f
ty
p
e
2
is
lin
k
ed
to
a
ch
an
g
e
in
life
s
ty
le
f
r
o
m
an
u
n
h
ea
lth
y
d
iet.
T
h
e
in
cr
e
ased
r
is
k
o
f
d
e
v
elo
p
in
g
th
is
t
y
p
e
i
n
cr
ea
s
es
as
a
r
e
s
u
lt
o
f
i
n
cr
ea
s
ed
i
n
tak
e
o
f
h
i
g
h
-
ca
lo
r
ie
f
o
o
d
s
in
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
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
N
eu
r
a
l n
etw
o
r
k
-
b
a
s
ed
d
ia
g
n
o
s
is
o
f
typ
e
2
d
ia
b
etes
u
s
in
g
an
ir
id
o
lo
g
y
a
p
p
r
o
a
ch
(
A
la
a
A
b
d
u
lka
r
ee
m
A
h
med
)
1227
lar
g
e
q
u
an
titi
es,
lack
o
f
e
x
e
r
cise,
o
b
esit
y
,
h
ig
h
b
lo
o
d
p
r
ess
u
r
e,
h
y
p
e
r
lip
id
em
ia,
h
ea
r
t
d
is
ea
s
e,
ag
in
g
,
in
ad
d
itio
n
to
a
f
am
ily
h
is
to
r
y
o
f
p
r
ed
is
p
o
s
itio
n
to
d
ia
b
etes
as
well
as
r
ac
e
(
s
u
ch
as
Asi
an
,
Af
r
ican
,
etc.
)
[
1
]
.
T
h
e
s
ev
er
ity
o
f
s
y
m
p
to
m
s
o
f
ty
p
e
2
d
iab
etes
v
ar
ies
d
ep
en
d
i
n
g
o
n
th
e
co
n
d
itio
n
an
d
d
u
r
at
io
n
o
f
in
f
ec
tio
n
,
as
p
eo
p
le
with
ea
r
ly
d
iab
etes
m
ay
n
o
t
s
h
o
w
o
b
v
io
u
s
s
y
m
p
to
m
s
[
3
]
.
So
m
etim
es,
d
iab
etics
av
o
id
u
s
in
g
n
ee
d
les
to
ch
ec
k
th
eir
b
lo
o
d
s
u
g
ar
lev
els
,
wh
ich
ca
n
lead
to
m
o
r
e
co
m
p
lex
h
ea
lth
p
r
o
b
lem
s
.
B
etwe
en
3
.
5
%
an
d
1
0
%
o
f
th
e
p
o
p
u
latio
n
s
u
f
f
er
s
f
r
o
m
a
n
x
iety
ab
o
u
t
n
ee
d
les,
k
n
o
wn
as
n
ee
d
le
p
h
o
b
ia.
T
h
e
r
ef
o
r
e
,
ir
id
o
lo
g
y
is
th
e
m
o
s
t
s
u
itab
le
ch
o
ice
f
o
r
th
ese
p
eo
p
le
[
4
]
.
I
r
id
o
l
o
g
y
k
n
o
w
n
as
i
r
i
d
o
d
ia
g
n
o
s
is
o
r
i
r
i
d
ia
g
n
o
s
is
[
5
]
.
I
r
i
d
o
l
o
g
y
is
a
s
ci
e
n
ce
t
h
at
h
as
g
ain
e
d
wi
d
e
atte
n
t
io
n
r
e
ce
n
tl
y
b
ec
a
u
s
e
it
is
a
n
o
n
-
i
n
v
asi
v
e
m
e
t
h
o
d
o
f
d
i
a
g
n
o
s
i
n
g
d
is
e
ases
t
h
r
o
u
g
h
th
e
i
r
is
.
I
t
is
a
d
i
a
g
n
o
s
t
ic
ap
p
r
o
ac
h
t
o
d
is
e
ases
c
o
n
s
i
d
e
r
e
d
a
co
m
p
le
m
e
n
t
ar
y
an
d
a
lt
er
n
a
ti
v
e
m
e
d
ic
in
e
s
ci
e
n
ce
th
at
li
n
k
s
ir
is
tis
s
u
e
wea
k
n
ess
es
,
f
r
a
ct
u
r
es,
p
att
e
r
n
s
,
a
n
d
c
o
l
o
r
s
,
w
h
i
c
h
p
r
o
v
i
d
e
c
lu
es
t
o
th
e
h
e
alt
h
o
f
h
u
m
a
n
o
r
g
a
n
s
,
b
y
o
b
s
er
v
i
n
g
ch
an
g
es
i
n
th
e
te
x
t
u
r
e,
c
o
l
o
r
an
d
s
tr
u
c
tu
r
e
o
f
s
p
ec
if
ic
a
r
e
a
s
in
t
h
e
i
r
is
,
w
h
i
ch
r
e
p
r
ese
n
ts
a
r
e
f
l
ec
t
i
o
n
o
f
t
h
e
h
e
alt
h
s
t
at
u
s
o
f
an
o
r
g
a
n
i
n
t
h
e
b
o
d
y
,
as
s
i
g
n
s
a
p
p
e
ar
in
t
h
e
i
r
is
tis
s
u
es
l
o
n
g
b
ef
o
r
e
th
e
s
y
m
p
to
m
s
o
f
t
h
e
d
is
ea
s
e
ap
p
e
ar
i
n
t
h
e
b
o
d
y
,
w
h
ic
h
m
a
k
es i
r
is
d
ia
g
n
o
s
is
u
s
e
f
u
l
f
o
r
d
i
a
g
n
o
s
i
n
g
p
r
o
b
le
m
s
in
t
h
e
b
o
d
y
o
r
g
an
s
[
6
]
,
[
7
]
.
I
r
id
o
lo
g
is
ts
wo
r
k
to
m
atch
t
h
e
ir
is
ch
ar
t
with
th
eir
in
te
r
p
r
et
atio
n
s
o
f
d
is
ea
s
es.
T
h
e
ir
is
ch
ar
t
ac
co
r
d
in
g
to
B
er
n
ar
d
J
en
s
en
'
s
class
if
icat
io
n
is
a
d
iv
is
io
n
o
f
th
e
s
u
r
f
ac
e
o
f
th
e
ir
is
in
to
8
0
to
9
0
r
eg
io
n
s
,
ea
ch
r
ep
r
esen
tin
g
an
o
r
g
an
o
f
th
e
b
o
d
y
[
8
]
.
T
h
e
lo
ca
tio
n
s
o
f
th
ese
o
r
g
an
s
in
th
e
lef
t
an
d
r
ig
h
t
ir
is
co
r
r
esp
o
n
d
to
th
eir
lo
ca
tio
n
s
in
th
e
b
o
d
y
[
9
]
,
as
s
h
o
wn
in
Fig
u
r
e
1
[
8
]
.
Ac
co
r
d
in
g
to
th
e
m
o
d
er
n
i
r
is
ch
a
r
t,
d
iab
etes
ca
n
b
e
d
iag
n
o
s
ed
b
y
th
r
ee
r
e
g
io
n
s
o
f
in
ter
est
(
R
OI
s
)
in
th
e
r
ig
h
t
an
d
lef
t
ir
is
ac
co
r
d
in
g
to
th
e
an
ato
m
y
o
f
t
h
e
p
an
cr
ea
s
,
wh
ich
c
o
n
s
is
ts
o
f
th
e
h
ea
d
,
b
o
d
y
an
d
tail.
I
n
t
h
e
r
i
g
h
t
ir
is
,
th
er
e
is
o
n
e
R
OI
r
ep
r
e
s
en
tin
g
th
e
h
ea
d
o
f
th
e
p
an
cr
ea
s
i
n
th
e
r
eg
io
n
b
etwe
en
7
an
d
8
o
'
clo
ck
.
As
f
o
r
t
h
e
lef
t
ir
is
,
th
e
r
e
ar
e
two
R
OI
s
,
th
e
f
ir
s
t
r
ep
r
esen
tin
g
th
e
b
o
d
y
o
f
th
e
p
an
cr
ea
s
in
th
e
r
eg
io
n
b
etwe
en
7
an
d
8
o
'
clo
ck
,
an
d
th
e
s
ec
o
n
d
r
ep
r
esen
tin
g
th
e
tail o
f
th
e
p
an
c
r
ea
s
in
th
e
r
e
g
i
o
n
b
etwe
en
4
an
d
5
o
'
clo
ck
[
7
]
.
T
h
er
ef
o
r
e,
r
esear
ch
is
b
ein
g
co
n
d
u
cte
d
to
d
e
v
elo
p
a
n
o
n
-
in
v
asiv
e
a
n
d
im
m
e
d
iate
ir
is
-
b
ased
d
iag
n
o
s
tic
s
y
s
tem
f
o
r
t
y
p
e
2
d
iab
etes
th
at
d
o
es
n
o
t
p
o
s
e
a
r
i
s
k
o
f
co
n
tam
in
atio
n
o
f
th
e
e
x
am
in
atio
n
to
o
ls
an
d
s
av
es
tim
e
an
d
ef
f
o
r
t
in
v
is
itin
g
h
ea
lth
ce
n
ter
s
.
I
n
ad
d
itio
n
,
it
is
in
ex
p
en
s
iv
e
a
n
d
u
s
ef
u
l
f
o
r
ea
r
ly
d
etec
tio
n
o
f
ty
p
e
2
d
iab
etes,
wh
o
s
e
s
y
m
p
to
m
s
m
ay
ap
p
ea
r
late.
Usi
n
g
ar
tific
ial
in
tellig
en
ce
(
AI
)
alg
o
r
ith
m
s
co
m
m
o
n
l
y
u
s
ed
in
m
ed
ical
ap
p
licatio
n
s
,
i
n
clu
d
in
g
d
is
ea
s
es d
iag
n
o
s
is
.
T
h
er
e
ar
e
m
an
y
wo
r
k
s
th
at
d
i
ag
n
o
s
e
d
ia
b
etes
in
d
i
f
f
er
en
t
r
e
g
io
n
o
f
i
n
ter
est
(
R
OI
)
,
an
d
in
ad
d
itio
n
t
o
th
e
d
if
f
er
e
n
ce
in
t
h
e
n
u
m
b
er
a
n
d
ty
p
e
o
f
ex
tr
ac
ted
f
ea
tu
r
es,
as
well
as
th
e
d
i
f
f
er
en
ce
in
cla
s
s
if
icatio
n
m
eth
o
d
s
u
s
in
g
d
if
f
er
e
n
t
ty
p
es
o
f
AI
alg
o
r
ith
m
s
,
wh
eth
er
f
o
r
d
ee
p
lea
r
n
in
g
(
DL
)
o
r
m
ac
h
in
e
lear
n
in
g
(
ML
)
,
th
er
e
s
o
m
e
wo
r
k
s
th
at
d
ea
lt with
d
if
f
er
en
t
ty
p
es o
f
n
e
u
r
al
n
etwo
r
k
(
NN)
alg
o
r
ith
m
s
.
Hu
s
s
ein
et
a
l.
[
8
]
u
s
ed
ir
id
o
lo
g
y
an
d
A
I
tech
n
iq
u
e
to
d
iag
n
o
s
e
k
id
n
e
y
d
is
ea
s
e
u
s
in
g
ad
ap
tiv
e
n
eu
r
o
-
f
u
zz
y
i
n
f
er
en
c
e
s
y
s
tem
(
ANFI
S)
wh
ich
co
m
b
in
es
f
u
zz
y
s
y
s
tem
with
NN.
E
ig
h
t
f
ea
tu
r
es
wer
e
ex
tr
ac
ted
f
r
o
m
ea
c
h
R
OI
f
o
r
b
o
th
th
e
r
i
g
h
t
an
d
lef
t
e
y
es
an
d
th
ese
f
ea
tu
r
es
ar
e
e
n
er
g
y
an
d
en
tr
o
p
y
f
o
r
s
in
g
le
-
lev
el
wav
elet
ec
o
m
p
o
s
itio
n
a
n
aly
s
is
.
T
h
e
ev
alu
atio
n
was
c
o
n
d
u
cte
d
o
n
two
g
r
o
u
p
s
.
T
h
e
f
ir
s
t
g
r
o
u
p
was
1
7
2
p
eo
p
le
s
u
f
f
er
in
g
f
r
o
m
ch
r
o
n
ic
k
id
n
e
y
f
ailu
r
e
an
d
th
e
s
ec
o
n
d
g
r
o
u
p
was
1
6
8
p
eo
p
le
with
o
u
t
k
id
n
ey
d
is
ea
s
e.
T
h
e
d
ia
g
n
o
s
tic
ac
cu
r
ac
y
o
f
th
e
f
ir
s
t
g
r
o
u
p
s
u
f
f
e
r
in
g
f
r
o
m
k
id
n
ey
f
ailu
r
e
was
8
2
%,
w
h
ile
th
e
s
ec
o
n
d
g
r
o
u
p
with
o
u
t k
id
n
e
y
d
is
ea
s
e
was 9
3
%,
with
1
0
-
f
o
l
d
cr
o
s
s
v
alid
ati
o
n
.
Fig
u
r
e
1
.
I
r
is
ch
ar
t f
o
r
r
ig
h
t a
n
d
lef
t
ir
is
es
[
8
]
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
1
2
2
6
-
1
2
3
7
1228
B
an
z
i
a
n
d
X
u
e
[
1
0
]
u
s
e
d
i
r
i
d
o
lo
g
y
wit
h
c
o
m
p
u
t
er
v
is
i
o
n
to
d
ia
g
n
o
s
e
d
ia
b
e
tes
.
Usi
n
g
a
f
ee
d
-
f
o
r
wa
r
d
b
a
ck
p
r
o
p
ag
ati
o
n
n
e
u
r
al
n
etw
o
r
k
f
o
r
cl
ass
if
ic
ati
o
n
a
n
d
t
r
ai
n
i
n
g
L
ev
en
b
er
g
-
Ma
r
q
u
a
r
d
t
b
ac
k
p
r
o
p
a
g
at
io
n
th
at
u
p
d
ates
t
h
e
n
etw
o
r
k
w
ei
g
h
t
a
n
d
b
ias
.
Fea
tu
r
es
we
r
e
e
x
t
r
ac
t
e
d
u
s
in
g
p
r
in
ci
p
a
l
c
o
m
p
o
n
e
n
t
a
n
al
y
s
is
(
PC
A
)
f
r
o
m
th
e
R
O
I
in
t
h
e
r
i
g
h
t
ey
e
lo
ca
t
e
d
b
e
twe
e
n
0
1
:
4
5
t
o
0
2
:
1
5
o
'
cl
o
c
k
.
8
0
0
p
e
o
p
le
we
r
e
class
if
i
e
d
,
4
0
0
o
f
t
h
e
m
we
r
e
h
e
alt
h
y
a
n
d
4
0
0
w
e
r
e
d
ia
b
e
ti
c.
8
p
eo
p
l
e
we
r
e
t
este
d
a
n
d
wer
e
f
o
u
n
d
t
o
h
a
v
e
d
ia
b
etes
an
d
w
h
e
n
t
h
e
y
we
r
e
co
n
f
i
r
m
ed
a
f
t
er
i
n
s
u
li
n
test
in
g
,
t
h
e
y
we
r
e
c
o
n
f
ir
m
e
d
t
o
h
a
v
e
t
y
p
e
2
d
ia
b
e
tes
.
Sam
an
t
an
d
Ag
ar
wal
[
1
1
]
u
s
ed
ir
id
o
lo
g
y
with
AI
alg
o
r
ith
m
s
to
d
iag
n
o
s
e
d
iab
etes.
3
R
OI
wer
e
u
s
ed
f
o
r
p
an
cr
ea
tic
r
eg
i
o
n
s
in
th
e
r
ig
h
t
ir
is
b
etwe
en
3
6
'
-
3
9
'
an
d
i
n
th
e
lef
t
ir
is
b
etwe
en
3
8
'
-
4
1
'
an
d
2
1
'
-
2
4
'
with
6
0
d
eg
r
ee
s
’
ir
is
d
iv
id
in
g
.
6
3
f
e
atu
r
es
wer
e
ex
tr
ac
ted
f
r
o
m
e
ac
h
R
OI
,
7
f
e
atu
r
es
(
Me
an
I
n
ten
s
ity
,
Stan
d
ar
d
Dev
iatio
n
,
E
n
tr
o
p
y
,
C
o
n
tr
ast,
C
o
r
r
elatio
n
,
E
n
er
g
y
an
d
Ho
m
o
g
en
eity
)
d
ir
ec
tly
f
r
o
m
th
e
R
OI
an
d
f
r
o
m
ea
ch
o
f
th
e
eig
h
t
-
3
D
d
is
cr
ete
wav
ef
o
r
m
tr
an
s
f
o
r
m
s
.
C
lass
if
icat
io
n
was
d
o
n
e
o
n
2
0
0
in
d
iv
i
d
u
als,
1
0
0
o
f
t
h
em
wer
e
h
ea
lth
y
an
d
1
0
0
wer
e
d
iab
etic
.
T
h
e
class
if
icatio
n
p
r
o
ce
s
s
was
d
o
n
e
u
s
in
g
6
t
y
p
es
o
f
ML
alg
o
r
ith
m
s
,
o
n
e
o
f
wh
ich
is
NN,
wh
ich
h
ad
class
if
icatio
n
ac
cu
r
ac
y
was
6
7
.
2
9
%
an
d
ar
ea
u
n
d
er
th
e
cu
r
v
e
(
AUC)
was
0
.
6
7
with
10
-
f
o
l
d
cr
o
s
s
-
v
alid
atio
n
.
Sam
an
t
an
d
Ag
ar
wal
[
7
]
u
s
ed
ir
id
o
lo
g
y
to
d
etec
t
ty
p
e
2
d
iab
etes
u
s
in
g
6
ty
p
es
o
f
ML
alg
o
r
ith
m
s
f
o
r
class
if
icatio
n
;
o
n
e
o
f
th
ese
c
lass
if
ier
s
is
NN
class
if
ier
.
Usi
n
g
im
ag
e
d
ata
o
f
3
3
8
p
eo
p
le,
1
5
8
im
ag
es
o
f
h
ea
lth
y
in
d
iv
id
u
als
,
a
n
d
1
8
0
i
m
ag
es
o
f
p
eo
p
le
with
d
iab
ete
s
.
T
h
r
ee
R
OI
wer
e
u
s
ed
,
tw
o
r
eg
io
n
s
o
f
th
e
lef
t
ey
e
b
etwe
en
7
-
8
o
'
clo
ck
an
d
4
-
5
o
'
clo
ck
an
d
o
n
e
r
e
g
io
n
o
f
th
e
r
ig
h
t e
y
e
b
etwe
en
7
-
8
o
'
clo
ck
,
an
d
1
8
0
f
ea
tu
r
es
wer
e
ex
tr
ac
ted
,
co
n
s
is
tin
g
o
f
4
f
ir
s
t
-
o
r
d
er
s
tatis
tics
f
ea
tu
r
es
an
d
4
tex
tu
r
e
f
ea
tu
r
es
f
r
o
m
th
e
g
r
ay
-
le
v
el
co
-
o
cc
u
r
r
en
ce
m
a
tr
ix
(
GL
C
M)
,
ex
tr
ac
ted
f
r
o
m
th
e
2
D
w
av
ef
o
r
m
s
o
f
th
e
f
o
u
r
d
ec
o
m
p
o
s
itio
n
s
,
an
d
f
o
r
all
p
o
s
s
ib
le
co
m
b
in
atio
n
s
o
f
th
ese
d
ec
o
m
p
o
s
itio
n
s
f
r
o
m
th
e
R
OI
.
T
h
e
h
ig
h
est
ac
cu
r
ac
y
o
b
tain
ed
b
y
NN
class
if
ier
ty
p
e
o
n
ly
was 6
7
.
2
9
% a
t 1
0
-
f
o
ld
f
o
r
5
0
f
ea
tu
r
es b
y
t
-
test
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
.
C
ar
r
er
a
an
d
Ma
y
a
[
1
2
]
u
s
ed
ir
id
o
lo
g
y
to
d
etec
t
g
astro
in
t
esti
n
al
d
is
ea
s
es
u
s
in
g
4
ty
p
e
s
o
f
ML
alg
o
r
ith
m
s
to
class
if
y
1
0
0
e
y
e
im
ag
es.
On
e
o
f
th
e
class
if
ier
s
u
s
ed
is
NN
class
if
ier
wh
ich
s
h
o
wed
8
3
%
ac
cu
r
ac
y
b
y
ex
tr
ac
tin
g
6
f
ea
tu
r
es
f
r
o
m
th
e
R
OI
.
R
ac
h
m
a
n
a
n
d
B
asar
i
[
1
3
]
t
h
ey
u
s
ed
ir
id
o
lo
g
y
to
d
etec
t
h
ig
h
ch
o
lest
er
o
l
lev
els
u
s
in
g
th
e
b
a
ck
-
p
r
o
p
ag
atio
n
n
eu
r
al
n
etwo
r
k
alg
o
r
ith
m
to
class
if
y
3
0
e
y
e
im
ag
es,
1
0
im
ag
es
o
f
p
eo
p
le
with
h
i
g
h
ch
o
lest
er
o
l
an
d
2
0
im
a
g
es
o
f
h
e
alth
y
p
eo
p
le.
Fo
u
r
s
tatis
tical
f
ea
tu
r
es
ar
e
ex
tr
ac
ted
f
r
o
m
th
e
GL
C
M
o
f
th
e
R
OI
.
T
h
e
cl
ass
if
icatio
n
ac
cu
r
ac
y
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
tem
was 9
6
.
6
7
%.
Yo
h
a
n
n
es
et
a
l
.
[
1
4
]
u
s
e
d
i
r
i
d
o
l
o
g
y
t
o
d
e
te
ct
h
e
ar
t
d
is
e
ase
u
s
i
n
g
b
ac
k
p
r
o
p
ag
ati
o
n
n
e
u
r
al
n
et
wo
r
k
alg
o
r
it
h
m
to
class
if
y
1
1
0
e
y
e
i
m
a
g
es
,
5
5
i
m
a
g
e
s
o
f
h
e
alt
h
y
i
n
d
i
v
i
d
u
als
a
n
d
5
5
i
m
a
g
es
o
f
i
n
d
i
v
i
d
u
als
wi
th
h
e
ar
t
d
is
e
ase
.
PC
A
a
n
d
C
an
n
y
e
d
g
e
ar
e
u
s
e
d
to
e
x
tr
ac
t
f
ea
t
u
r
es
f
r
o
m
th
e
R
OI
.
T
h
e
cl
ass
if
ic
ati
o
n
ac
cu
r
a
c
y
was
9
5
.
4
5
%
u
s
i
n
g
5
0
h
i
d
d
e
n
n
eu
r
o
n
s
,
0
.
0
1
f
o
r
e
r
r
o
r
li
m
it
,
5
0
PC
A
a
n
d
0
.
3
Si
g
m
a
f
o
r
C
an
n
y
e
d
g
e
d
et
ec
t
io
n
.
Hid
ay
an
ti
et
a
l.
[
1
5
]
u
s
ed
ir
i
d
o
lo
g
y
t
o
d
etec
t
u
p
p
er
s
to
m
a
ch
d
is
o
r
d
er
s
u
s
in
g
th
e
b
ac
k
-
p
r
o
p
ag
atio
n
n
eu
r
al
n
etwo
r
k
alg
o
r
ith
m
to
c
lass
if
y
2
0
p
air
s
o
f
ey
e
im
ag
es,
1
0
p
air
s
o
f
h
ea
lth
y
p
e
o
p
le
a
n
d
1
0
p
air
s
o
f
ey
e
im
ag
es o
f
p
e
o
p
le
with
u
p
p
er
s
to
m
ac
h
d
is
o
r
d
er
s
.
T
h
e
s
y
s
tem
'
s
d
iag
n
o
s
is
ac
cu
r
ac
y
was 5
5
%
.
Fer
n
an
d
ez
-
Gr
a
n
d
o
n
et
a
l.
[
1
6
]
u
s
ed
ir
id
o
lo
g
y
to
d
etec
t
d
iab
e
tes
u
s
in
g
th
e
ex
tr
em
e
lear
n
in
g
m
ac
h
in
e
(
E
L
M)
alg
o
r
ith
m
,
wh
ich
is
a
s
in
g
le
lay
er
f
ee
d
f
o
r
wa
r
d
n
e
u
r
al
n
etwo
r
k
(
SLFN)
lear
n
i
n
g
alg
o
r
ith
m
,
with
Ad
am
(
ad
ap
tiv
e
m
o
m
en
t
)
o
p
tim
izatio
n
with
2
5
6
n
e
u
r
o
n
s
in
t
h
e
h
i
d
d
en
lay
er
,
lear
n
in
g
r
ate
0
.
0
1
,
an
d
b
atch
s
ize
1
2
8
u
s
in
g
R
eL
U
ac
tiv
atio
n
f
u
n
cti
o
n
,
to
class
if
y
im
ag
es
o
f
th
e
r
ig
h
t
an
d
lef
t
e
y
es
o
f
1
2
4
h
ea
l
th
y
in
d
iv
i
d
u
als
an
d
1
0
6
in
d
iv
id
u
als with
d
iab
etes.
T
h
e
s
y
s
te
m
'
s
d
iag
n
o
s
tic
ac
cu
r
ac
y
was 9
9
.
9
2
% a
t 5
-
f
o
ld
s
.
Ö
z
b
i
l
g
i
n
e
t
a
l
.
[
1
7
]
u
s
e
d
i
r
i
d
o
lo
g
y
t
o
d
e
t
e
c
t
c
o
r
o
n
a
r
y
a
r
t
e
r
y
d
i
s
e
as
e
u
s
i
n
g
5
t
y
p
e
s
o
f
M
L
al
g
o
r
i
t
h
m
s
;
a
m
o
n
g
t
h
e
s
e
a
l
g
o
r
i
t
h
m
s
is
N
N
a
l
g
o
r
i
t
h
m
w
i
t
h
it
s
f
i
v
e
t
y
p
e
s
(
N
a
r
r
o
w
,
Me
d
i
u
m
,
W
id
e
,
B
i
-
l
a
y
e
r
e
d
,
a
n
d
Tri
-
l
a
y
e
r
e
d
)
.
E
y
e
i
m
a
g
e
s
o
f
1
9
8
p
e
o
p
l
e
w
e
r
e
u
s
e
d
,
1
0
4
o
f
w
h
o
m
w
e
r
e
h
e
a
l
t
h
y
a
n
d
9
4
o
f
w
h
o
m
h
a
d
c
o
r
o
n
a
r
y
a
r
t
e
r
y
d
i
s
e
as
e
.
1
3
6
f
e
a
t
u
r
e
s
w
e
r
e
e
x
t
r
a
c
t
e
d
f
r
o
m
t
h
e
h
e
ar
t
R
O
I
,
w
h
ic
h
w
e
r
e
a
n
a
l
y
z
ed
i
n
t
o
4
w
a
v
e
l
e
t
c
o
m
p
o
n
e
n
t
s
,
f
r
o
m
w
h
i
c
h
3
4
f
e
a
t
u
r
e
s
w
e
r
e
e
x
t
r
a
c
t
e
d
f
r
o
m
e
a
ch
c
o
m
p
o
n
e
n
t
,
c
o
n
s
i
s
t
i
n
g
o
f
5
s
t
a
t
is
t
ic
a
l
f
e
a
t
u
r
es
,
7
G
r
a
y
-
L
e
v
e
l
R
u
n
L
e
n
g
t
h
M
a
t
r
ix
G
L
R
L
M
f
e
a
t
u
r
es
,
a
n
d
2
2
G
L
C
M
f
e
a
t
u
r
es
.
T
h
e
b
e
s
t
d
i
a
g
n
o
s
i
s
a
c
c
u
r
ac
y
f
o
r
t
h
e
w
i
d
e
n
e
u
r
a
l
n
e
tw
o
r
k
(
W
N
N
)
t
y
p
e
o
n
l
y
w
a
s
9
2
%
f
o
r
t
h
e
t
o
p
5
0
f
e
a
t
u
r
e
s
s
e
l
e
ct
e
d
u
s
i
n
g
th
e
R
e
li
e
f
f
f
e
a
t
u
r
es
s
e
l
e
ct
i
o
n
m
e
t
h
o
d
.
Ah
m
ed
a
n
d
Yaseen
[
1
8
]
p
r
o
p
o
s
ed
a
n
o
n
-
in
v
asiv
e
ap
p
r
o
ac
h
f
o
r
d
iag
n
o
s
in
g
ty
p
e
2
d
iab
etes
b
ased
o
n
ir
id
o
lo
g
y
an
d
ML
al
g
o
r
ith
m
s
.
T
h
e
ap
p
r
o
ac
h
is
b
ased
o
n
ex
tr
ac
tin
g
1
0
f
ea
tu
r
es
f
r
o
m
a
s
in
g
le
R
OI
in
th
e
r
ig
h
t
ir
is
lo
ca
ted
b
etwe
en
th
e
7
an
d
8
o
'
clo
ck
p
o
s
itio
n
s
.
T
h
ese
f
ea
tu
r
es
ar
e
s
tatis
t
ical
f
ea
tu
r
es
s
u
ch
as
en
tr
o
p
y
,
GL
C
M,
an
d
W
av
elet
f
ea
tu
r
es.
T
wo
class
if
icat
io
n
m
eth
o
d
s
wer
e
p
r
esen
ted
u
s
in
g
m
u
ltip
le
ML
alg
o
r
ith
m
s
an
d
a
r
an
g
e
o
f
cr
o
s
s
-
v
alid
atio
n
f
o
ld
s
r
an
g
in
g
f
r
o
m
2
to
2
0
.
T
h
e
f
ir
s
t
m
eth
o
d
is
b
ased
o
n
a
s
in
g
le
class
if
icat
io
n
s
tag
e
with
m
u
ltip
le
alg
o
r
ith
m
s
.
T
h
is
m
eth
o
d
ac
h
iev
ed
th
e
h
ig
h
est
class
if
icatio
n
ac
cu
r
ac
y
d
u
r
in
g
tr
ain
in
g
o
f
7
8
.
5
%
at
5
-
f
o
l
d
cr
o
s
s
-
tr
ain
in
g
u
s
in
g
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM)
alg
o
r
ith
m
an
d
B
in
ar
y
GL
M
L
o
g
is
tic
R
eg
r
ess
io
n
alg
o
r
ith
m
.
T
h
e
s
ec
o
n
d
m
eth
o
d
aim
s
to
in
cr
e
ase
class
if
icatio
n
ac
cu
r
ac
y
u
s
in
g
two
s
tag
es
o
f
class
if
icatio
n
b
ased
o
n
d
i
f
f
er
e
n
t
ty
p
es
o
f
m
o
d
els
s
elec
ted
f
r
o
m
a
s
et
o
f
m
u
ltip
le
ML
s
m
o
d
els
an
d
r
ely
in
g
o
n
th
e
u
s
e
o
f
PC
A
with
a
v
ar
ian
c
e
r
atio
r
a
n
g
in
g
f
r
o
m
9
7
%
t
o
1
0
0
%.
T
h
e
h
ig
h
est
class
if
icatio
n
ac
cu
r
ac
y
r
ea
ch
ed
8
2
.
2
%
b
y
tr
ain
in
g
p
r
ed
ictio
n
s
in
th
e
f
ir
s
t
s
tag
e
f
r
o
m
t
wo
in
itial
clas
s
if
ier
s
-
t
r
ee
-
c
o
ar
s
e
t
r
ee
alg
o
r
ith
m
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
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
N
eu
r
a
l n
etw
o
r
k
-
b
a
s
ed
d
ia
g
n
o
s
is
o
f
typ
e
2
d
ia
b
etes
u
s
in
g
an
ir
id
o
lo
g
y
a
p
p
r
o
a
ch
(
A
la
a
A
b
d
u
lka
r
ee
m
A
h
med
)
1229
(
7
4
.
8
%
at
1
4
-
f
o
ld
,
an
d
th
e
PC
A
v
ar
ian
ce
is
9
7
%),
an
d
lin
ea
r
d
is
cr
im
in
an
t
alg
o
r
ith
m
an
aly
s
is
(
7
7
.
6
%
at
9
-
f
o
ld
,
an
d
th
e
PC
A
v
ar
ian
ce
is
1
0
0
%)
-
b
ef
o
r
e
im
p
r
o
v
in
g
th
e
class
if
icatio
n
u
s
in
g
b
in
ar
y
GL
M
l
o
g
is
tic
r
eg
r
ess
io
n
alg
o
r
ith
m
(
GL
M)
in
th
e
s
ec
o
n
d
s
tag
e.
Pr
ev
io
u
s
wo
r
k
s
s
h
o
w
t
h
at
th
e
u
s
e
o
f
f
i
v
e
n
e
u
r
al
n
etwo
r
k
a
lg
o
r
ith
m
m
o
d
els
an
d
a
r
an
g
e
o
f
k
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
,
in
ad
d
itio
n
to
a
s
in
g
le
R
OI
r
ep
r
esen
tin
g
o
n
e
o
f
th
e
p
an
cr
ea
tic
o
r
g
a
n
s
,
h
as n
o
t
b
ee
n
ex
p
licitly
u
s
ed
in
th
e
d
etec
tio
n
o
f
ty
p
e
2
d
iab
etes.
I
n
th
is
wo
r
k
,
a
ty
p
e
2
d
iab
ete
s
d
etec
tio
n
s
y
s
tem
is
p
r
o
p
o
s
ed
b
ased
o
n
ir
id
o
lo
g
y
,
im
ag
e
p
r
o
ce
s
s
in
g
,
an
d
AI
u
s
in
g
ML
o
f
th
e
NN
ty
p
e.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
is
m
ain
ly
b
ased
o
n
th
e
d
iag
n
o
s
is
o
f
th
e
r
ig
h
t ir
is
wit
h
o
n
e
r
e
g
io
n
o
f
in
ter
est
(
R
OI
)
r
ep
r
esen
tin
g
th
e
h
ea
d
o
f
th
e
p
an
cr
ea
s
.
1
1
2
s
tatis
tical
an
d
t
ex
tu
r
e
f
ea
tu
r
es
ar
e
ex
tr
ac
ted
f
r
o
m
th
is
r
eg
i
o
n
;
th
e
s
e
f
ea
tu
r
es
ar
e
ex
tr
ac
ted
o
n
th
e
p
r
in
cip
le
o
f
d
u
p
licate
o
f
f
ea
t
u
r
es
f
r
o
m
th
e
R
OI
at
ea
ch
o
f
th
e
f
o
u
r
wav
elet
co
ef
f
icien
ts
a
n
d
t
h
e
f
o
u
r
d
i
r
ec
tio
n
s
in
t
h
e
g
r
ay
-
lev
el
co
-
o
cc
u
r
r
e
n
ce
m
at
r
ix
(
GL
C
M)
.
An
d
th
en
th
ese
im
ag
es
ar
e
class
if
ied
in
to
n
o
r
m
al
im
ag
es
b
elo
n
g
in
g
to
h
e
alth
y
in
d
iv
id
u
als
o
r
d
iab
etic
im
ag
es
b
elo
n
g
in
g
to
in
d
iv
id
u
als
with
ty
p
e
2
d
iab
et
es
b
y
p
r
o
p
o
s
in
g
f
i
v
e
NN
m
o
d
els
with
a
r
an
g
e
o
f
k
-
f
o
ld
s
b
etwe
en
2
an
d
2
0
f
o
ld
s
.
T
h
e
b
est
class
if
icatio
n
ac
cu
r
ac
y
o
f
8
3
.
2
%
was
o
b
tain
e
d
b
y
th
e
n
ar
r
o
w
n
eu
r
a
l
n
etwo
r
k
(
NNN)
m
o
d
el
at
7
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
.
T
h
e
s
t
ag
es
o
f
b
u
ild
i
n
g
th
e
p
r
o
p
o
s
ed
s
y
s
tem
will
b
e
p
r
esen
ted
in
ea
ch
p
ar
a
g
r
ap
h
o
f
th
is
r
esear
c
h
p
a
p
er
b
ased
o
n
th
e
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
,
wh
ich
was
d
o
n
e
u
s
in
g
th
e
MA
T
L
AB
p
r
o
g
r
am
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
in
th
is
wo
r
k
to
b
u
ild
a
ty
p
e
2
d
iab
etes
d
etec
tio
n
s
y
s
tem
b
ased
o
n
ir
id
o
lo
g
y
in
cl
u
d
es
s
ix
s
tag
es,
wh
ich
in
clu
d
e
a
n
u
m
b
er
o
f
s
t
ep
s
th
at
ca
n
b
e
o
b
s
er
v
ed
in
th
e
b
lo
ck
d
iag
r
a
m
in
Fig
u
r
e
2
.
T
h
e
f
ir
s
t
s
tag
e
is
th
e
in
p
u
t
to
th
e
s
y
s
tem
,
wh
ich
is
a
d
ataset
of
im
ag
es
o
f
th
e
r
ig
h
t
ey
e
.
T
h
e
n
e
x
t
s
tag
e
is
th
e
s
tag
e
o
f
p
r
o
ce
s
s
in
g
th
o
s
e
im
ag
es,
wh
ic
h
in
clu
d
es
a
n
u
m
b
e
r
o
f
s
tep
s
u
n
til
o
b
tain
in
g
th
e
r
u
b
b
er
s
h
ee
t
o
f
th
e
ir
is
.
T
h
en
c
o
m
es
t
h
e
s
t
ag
e
o
f
ex
tr
ac
tin
g
th
e
R
OI
f
r
o
m
th
e
ir
is
r
u
b
b
er
s
h
ee
t,
f
o
l
lo
wed
b
y
th
e
s
tag
e
o
f
ex
tr
ac
tin
g
1
1
2
f
ea
tu
r
es
f
r
o
m
th
is
R
OI
,
to
f
in
ally
class
if
y
th
em
in
t
h
e
class
if
icatio
n
s
tag
e
,
in
wh
ich
f
iv
e
ty
p
es
of
p
r
o
p
o
s
e
d
NN
m
o
d
el
s
(
Nar
r
o
w,
Me
d
iu
m
,
W
id
e,
B
i
-
lay
er
ed
an
d
T
r
i
-
lay
e
r
ed
)
ar
e
u
s
ed
an
d
t
h
en
th
e
h
ea
lth
s
tatu
s
o
f
th
e
o
wn
er
s
o
f
th
ese
im
ag
es
is
p
r
ed
icted
a
n
d
d
iag
n
o
s
ed
,
wh
eth
er
t
h
ey
a
r
e
n
o
r
m
al
an
d
h
ea
lth
y
o
r
h
av
e
ty
p
e
2
d
iab
etes.
T
h
e
m
o
s
t
wid
ely
u
s
ed
s
o
f
twar
e
t
o
o
l
f
o
r
ir
is
d
iag
n
o
s
tics
is
M
AT
L
AB
,
d
u
e
to
its
ab
ilit
y
to
p
r
o
ce
s
s
im
ag
es
q
u
ic
k
ly
,
ef
f
icien
tly
,
an
d
ac
cu
r
atel
y
to
d
etec
t
a
n
d
d
iag
n
o
s
e
d
is
ea
s
es
[
1
9
]
.
So
,
all
th
e
p
r
o
p
o
s
ed
o
p
er
atio
n
s
in
th
is
w
o
r
k
wer
e
d
o
n
e
u
s
in
g
MA
T
L
AB
v
er
s
io
n
R
2
0
2
4
a.
T
h
ese
s
tag
es
will
b
e
ex
p
lain
e
d
in
th
e
f
o
llo
win
g
p
ar
a
g
r
ap
h
s
.
Fig
u
r
e
2
.
T
h
e
b
lo
c
k
d
iag
r
am
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
2
.
1
.
Da
t
a
s
et
T
h
e
f
ir
s
t
s
tag
e
is
th
e
im
ag
e
d
ataset.
T
h
is
d
ata
was
o
b
tain
e
d
f
r
o
m
a
d
ataset
f
r
ee
ly
av
aila
b
le
o
n
th
e
GitHu
b
web
s
ite
,
as
r
ef
er
e
n
ce
d
in
r
e
f
er
en
ce
n
u
m
b
er
[
2
0
]
.
T
h
e
d
ata
c
o
n
s
is
ts
o
f
1
9
3
ca
s
es
o
f
m
ales
an
d
f
em
ales
d
iv
id
ed
in
to
1
0
4
ca
s
es
o
f
p
eo
p
le
with
co
n
tr
o
lled
d
iab
etes,
i.e
.
n
o
r
m
al
p
eo
p
le
(
m
ea
n
ag
e
5
7
.
5
±
1
4
.
2
y
ea
r
s
)
,
an
d
8
8
ca
s
es o
f
p
eo
p
le
with
d
i
ab
etes
ty
p
e
2
(
m
ea
n
ag
e
5
8
.
3
±
1
0
.
8
y
ea
r
s
)
.
I
n
th
is
wo
r
k
,
a
s
et
o
f
1
5
0
im
ag
es o
f
th
e
r
ig
h
t
ey
e,
d
iv
i
d
e
d
in
to
1
0
7
im
ag
es
(
5
7
im
ag
es
o
f
n
o
r
m
al
h
ea
lth
y
p
eo
p
le
an
d
5
0
im
a
g
es
o
f
p
eo
p
le
with
ty
p
e
2
d
ia
b
etes)
f
o
r
t
r
ain
in
g
an
d
4
3
im
ag
es
(
2
4
im
ag
es
o
f
n
o
r
m
al
h
ea
lth
y
p
eo
p
le
an
d
1
9
im
ag
es
o
f
p
eo
p
le
with
ty
p
e
2
d
iab
etes)
f
o
r
test
in
g
th
e
NN
m
o
d
els.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
1
2
2
6
-
1
2
3
7
1230
2
.
2
.
P
r
o
ce
s
s
ing
T
h
e
task
o
f
th
e
p
r
o
ce
s
s
in
g
s
tag
e
is
to
c
o
n
v
e
r
t
th
e
ey
e
im
ag
es
en
ter
in
g
th
e
s
y
s
tem
i
n
to
an
ir
is
r
ep
r
esen
tatio
n
i
n
th
e
f
o
r
m
o
f
a
r
u
b
b
er
s
h
ee
t.
T
h
is
s
tag
e
in
cl
u
d
es
s
ev
er
al
s
tep
s
,
as
s
h
o
wn
i
n
Fig
u
r
e
3
.
T
h
e
f
ir
s
t
s
tep
is
to
r
e
d
u
ce
th
e
im
a
g
e
s
i
ze
in
o
r
d
e
r
to
d
ec
r
e
ase
th
e
ti
m
e
r
eq
u
ir
ed
to
p
r
o
ce
s
s
ea
ch
i
m
ag
e
[
1
2
]
.
T
h
e
n
ex
t
s
tep
is
to
cr
o
p
th
e
im
ag
es
to
r
em
o
v
e
u
n
wa
n
ted
p
ar
ts
an
d
r
e
d
u
ce
th
e
co
m
p
lex
ity
o
f
th
e
im
a
g
e.
T
h
e
n
ex
t
s
tep
is
to
co
n
v
er
t th
e
im
a
g
e
f
r
o
m
c
o
lo
r
to
g
r
ay
s
ca
le
to
r
ed
u
ce
th
e
s
im
p
lific
atio
n
o
f
th
e
p
r
o
ce
ss
[
1
3
]
.
T
o
r
em
o
v
e
n
o
is
e
an
d
s
m
o
o
t
h
an
ey
e
im
a
g
e
w
h
ile
p
r
eser
v
in
g
ed
g
es
[
2
1
]
,
th
e
m
ed
ian
f
ilter
is
u
s
ed
in
th
e
s
tep
f
o
llo
win
g
th
e
p
r
ev
io
u
s
s
tep
s
.
T
h
e
im
p
o
r
ta
n
t step
f
o
r
ir
is
d
etec
tio
n
is
ed
g
e
d
etec
tio
n
.
C
an
n
y
ed
g
e
d
etec
tio
n
m
eth
o
d
was u
s
ed
in
th
is
p
r
o
p
o
s
ed
wo
r
k
with
a
th
r
esh
o
ld
is
0
.
0
5
an
d
s
ig
m
a
is
3
.
As
it
is
a
m
eth
o
d
u
s
ed
to
d
etec
t
ed
g
es
in
im
ag
es
d
u
e
to
its
h
ig
h
d
etec
tio
n
ac
cu
r
ac
y
a
n
d
n
o
is
e
r
em
o
v
al
ca
p
ab
ilit
ies
[
2
2
]
.
T
h
e
m
ain
a
n
d
im
p
o
r
tan
t
s
tep
i
n
th
is
s
tag
e
is
ir
is
lo
ca
lizatio
n
b
y
d
etec
tin
g
th
e
o
u
ter
an
d
in
n
e
r
b
o
r
d
e
r
s
o
f
th
e
ir
is
.
T
h
e
o
u
te
r
b
o
r
d
e
r
o
f
th
e
ir
is
ca
n
b
e
d
eter
m
in
ed
b
y
th
e
ci
r
c
u
lar
ed
g
e
s
ep
a
r
atin
g
th
e
i
r
is
f
r
o
m
th
e
s
cler
a,
wh
ile
th
e
in
n
er
b
o
r
d
er
o
f
t
h
e
ir
is
is
d
eter
m
in
ed
b
y
d
eter
m
i
n
in
g
t
h
e
b
o
r
d
er
o
f
t
h
e
p
u
p
il
[
8
]
.
T
h
e
f
in
al
s
tep
in
t
h
is
s
tag
e
is
th
e
n
o
r
m
aliza
tio
n
s
tep
,
i
n
wh
ich
th
e
cir
cu
lar
ir
is
is
tr
an
s
f
o
r
m
ed
i
n
to
a
r
ec
tan
g
u
lar
s
h
ap
e
to
f
ac
ilit
ate
an
aly
s
is
b
y
s
tan
d
ar
d
izin
g
it
to
a
f
ix
ed
s
h
a
p
e.
Dau
g
m
an
’
s
r
u
b
b
er
s
h
ee
t
m
o
d
el
alg
o
r
ith
m
w
as
u
s
ed
,
wh
ich
is
co
n
s
id
er
ed
th
e
m
o
s
t
co
m
m
o
n
m
eth
o
d
[
1
7
]
.
T
h
e
b
en
e
f
it
o
f
t
h
is
s
tep
is
to
s
tan
d
ar
d
ize
th
e
s
ize
o
f
th
e
ir
is
,
wh
ich
v
ar
ies
in
s
ize
d
ep
en
d
in
g
o
n
th
e
in
ten
s
ity
o
f
lig
h
t,
to
m
atc
h
th
e
s
ize
o
f
th
e
t
y
p
ical
ir
is
m
a
p
[
8
]
.
Af
te
r
th
at,
th
e
R
OI
f
o
r
t
h
e
p
an
c
r
ea
s
in
th
e
ey
e
is
d
eter
m
in
ed
.
Fig
u
r
e
3
.
T
h
e
p
r
o
ce
s
s
in
g
s
tag
e
2
.
3
.
Reg
i
o
n o
f
i
nte
re
s
t
(
RO
I
)
T
h
e
m
o
s
t
i
m
p
o
r
t
a
n
t
s
t
a
g
e
i
n
d
ia
g
n
o
s
i
n
g
t
y
p
e
2
d
i
a
b
e
t
es
b
y
i
r
is
is
s
el
e
c
ti
n
g
a
n
d
d
e
f
i
n
i
n
g
t
h
e
r
e
g
i
o
n
o
f
i
n
t
e
r
e
s
t
(
R
O
I
)
t
o
e
x
t
r
a
c
t
f
e
at
u
r
e
s
f
r
o
m
i
t
i
n
t
h
e
n
e
x
t
s
t
a
g
e
.
T
h
e
R
O
I
is
a
s
p
e
ci
f
i
c
r
e
g
i
o
n
i
n
t
h
e
i
r
i
s
t
h
at
r
e
p
r
e
s
e
n
ts
t
h
e
p
a
n
c
r
e
as
t
o
d
i
a
g
n
o
s
e
d
i
a
b
et
e
s
.
I
n
t
h
is
p
r
o
p
o
s
e
d
w
o
r
k
,
o
n
e
R
O
I
w
as
e
x
t
r
a
c
t
e
d
b
e
t
we
e
n
7
a
n
d
8
o
'
c
l
o
c
k
f
r
o
m
t
h
e
r
i
g
h
t
e
y
e
o
n
l
y
,
w
h
i
c
h
r
e
p
r
es
e
n
ts
t
h
e
h
e
a
d
o
f
t
h
e
p
a
n
c
r
e
as
.
W
h
i
c
h
w
a
s
c
r
o
p
p
e
d
f
r
o
m
t
h
e
i
r
i
s
r
u
b
b
e
r
s
h
ee
t
wi
t
h
p
a
r
t
8
s
p
e
ci
f
i
c
a
ll
y
o
u
t
o
f
1
2
p
a
r
t
s
i
n
t
o
w
h
i
c
h
t
h
e
r
u
b
b
e
r
s
h
ee
t
w
as
d
i
v
i
d
e
d
.
F
i
g
u
r
e
4
s
h
o
w
s
t
h
e
m
e
c
h
a
n
is
i
m
e
m
p
l
o
y
e
d
t
o
d
e
t
e
r
m
i
n
e
a
n
d
F
ig
u
r
e
4
(
a
)
e
x
t
r
a
c
t
t
h
e
p
a
n
c
r
e
a
s
-
r
e
l
a
t
e
d
r
e
g
i
o
n
o
f
i
n
t
e
r
e
s
t
(
R
O
I
)
f
r
o
m
t
h
e
r
i
g
h
t
i
r
i
s
i
m
a
g
e
.
T
h
e
n
o
r
m
a
li
z
e
d
i
r
i
s
w
as
d
i
v
i
d
e
d
i
n
t
o
1
2
p
r
e
d
e
f
i
n
e
d
p
ar
t
s
,
a
n
d
F
i
g
u
r
e
4
(
b
)
s
h
o
w
s
t
h
a
t
t
h
e
R
O
I
r
el
a
ti
v
e
to
p
a
r
t
8
i
s
c
h
o
s
e
n
a
s
t
h
e
p
a
n
c
r
e
a
s
R
O
I
f
o
r
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
n
d
a
n
a
l
y
s
is
.
2
.
4
.
F
e
a
t
u
r
e
s
e
x
t
r
a
c
t
i
o
n
Af
ter
d
eter
m
in
in
g
th
e
R
OI
in
th
e
r
ig
h
t
ir
is
,
wh
ich
r
ep
r
esen
ts
th
e
h
ea
d
o
f
th
e
p
an
c
r
ea
s
to
d
iag
n
o
s
e
d
iab
etes,
a
n
u
m
b
er
o
f
s
tatis
tic
al
an
d
tex
tu
r
al
f
ea
tu
r
es
ar
e
ex
t
r
ac
ted
f
r
o
m
it.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
in
th
is
wo
r
k
ex
tr
ac
ted
1
1
2
f
ea
tu
r
es
f
r
o
m
t
h
e
R
OI
b
ased
o
n
th
e
p
r
in
cip
l
e
o
f
d
u
p
licatin
g
th
e
f
ea
tu
r
es
ex
tr
ac
ted
f
r
o
m
th
e
R
OI
,
as
s
h
o
wn
in
Fig
u
r
e
5
.
W
h
er
e
8
s
t
atis
tical
f
ea
tu
r
es
wer
e
ex
tr
ac
ted
d
ir
ec
tly
f
r
o
m
th
e
R
OI
,
n
am
ely
Me
an
,
Stan
d
ar
d
d
ev
iatio
n
,
E
n
tr
o
p
y
,
Sk
ewn
ess
,
k
u
r
to
s
is
,
Nu
m
b
er
o
f
b
in
s
,
Nu
m
b
er
o
f
b
in
s
wh
en
wid
th
=1
0
a
n
d
Per
ce
n
tiles
o
f
im
ag
e
h
is
to
g
r
a
m
,
an
d
4
tex
tu
r
e
f
ea
tu
r
es
f
r
o
m
th
e
g
r
a
y
lev
el
co
-
o
cc
u
r
r
en
ce
m
atr
ix
(
GL
C
M)
,
n
am
ely
co
n
tr
ast,
co
r
r
elatio
n
,
en
er
g
y
,
a
n
d
h
o
m
o
g
e
n
eity
,
at
all
f
o
u
r
d
ir
ec
tio
n
s
o
f
p
ix
el
(
=
0
°
,
45
°
,
90
°
,
135
°
)
at
d
is
tan
ce
(
d
=1
)
,
s
o
th
at
t
h
e
to
tal
b
ec
o
m
es
1
6
tex
t
u
r
e
f
ea
t
u
r
es.
I
n
ad
d
itio
n
,
2
-
D
d
is
cr
ete
wav
elet
tr
an
s
f
o
r
m
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
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
N
eu
r
a
l n
etw
o
r
k
-
b
a
s
ed
d
ia
g
n
o
s
is
o
f
typ
e
2
d
ia
b
etes
u
s
in
g
an
ir
id
o
lo
g
y
a
p
p
r
o
a
ch
(
A
la
a
A
b
d
u
lka
r
ee
m
A
h
med
)
1231
(
DW
T
)
ar
e
u
s
ed
to
ex
tr
ac
t
f
o
u
r
co
ef
f
icien
ts
f
r
o
m
th
e
f
ir
s
t
lev
el,
n
am
ely
Ap
p
r
o
x
im
atio
n
co
ef
f
icien
t
(
cA)
,
h
o
r
izo
n
tal
c
o
ef
f
icien
t
(
cH)
,
v
er
tical
co
ef
f
icien
t
(
cV)
an
d
d
iag
o
n
al
co
e
f
f
icien
t
(
cD)
an
d
f
r
o
m
ea
c
h
o
f
th
ese
f
o
u
r
co
ef
f
icien
ts
,
6
s
tatis
tic
al
f
ea
tu
r
es
n
am
el
y
m
ea
n
,
s
tan
d
a
r
d
d
ev
iatio
n
,
en
t
r
o
p
y
,
S
k
ewn
ess
,
k
u
r
to
s
is
,
p
er
ce
n
tiles
o
f
im
ag
e
h
is
to
g
r
a
m
an
d
4
f
ea
tu
r
es
f
r
o
m
th
e
GL
C
M
ar
e
ex
tr
ac
ted
,
n
am
ely
co
n
tr
ast,
co
r
r
elatio
n
,
en
er
g
y
an
d
h
o
m
o
g
en
eity
an
d
at
all
f
o
u
r
d
ir
ec
tio
n
s
,
s
o
th
at
th
e
to
tal
b
ec
o
m
es
1
6
tex
tu
r
e
f
ea
tu
r
es.
T
h
u
s
,
th
e
to
tal
n
u
m
b
er
o
f
f
ea
t
u
r
es
ex
t
r
ac
ted
f
r
o
m
th
e
wav
elets
b
e
co
m
es
8
8
s
tatis
tical
an
d
tex
tu
r
al
f
ea
tu
r
es.
T
h
e
f
o
llo
win
g
is
a
d
escr
ip
tio
n
o
f
t
h
e
GL
C
M
an
d
th
e
DW
T
.
(
a)
(
b
)
Fig
u
r
e
4
.
Dete
r
m
i
n
atio
n
an
d
e
x
tr
ac
tio
n
o
f
th
e
p
a
n
cr
ea
s
r
elat
ed
R
OI
f
r
o
m
th
e
r
ig
h
t i
r
is
im
ag
e
(
a)
p
an
cr
ea
s
R
OI
id
en
tifie
d
in
th
e
r
ig
h
t ir
is
an
d
(
b
)
e
x
tr
ac
ted
R
OI
f
r
o
m
p
ar
t 8
o
f
th
e
n
o
r
m
alize
d
ir
is
th
at
is
d
iv
id
ed
in
to
1
2
p
a
r
ts
Fig
u
r
e
5
.
T
h
e
d
iag
r
am
o
f
ex
tr
a
cted
f
ea
tu
r
es
f
r
o
m
R
OI
2
.
4
.
1
.
G
ra
y
-
lev
el
co
-
o
cc
urre
nce
m
a
t
rix
(
G
L
CM
)
f
ea
t
ures
I
t
is
a
s
ec
o
n
d
-
o
r
d
er
s
tatis
tical
m
eth
o
d
th
at
ca
lc
u
lates
th
e
f
r
eq
u
en
cy
o
f
p
ai
r
s
o
f
p
ix
els
th
a
t
h
av
e
th
e
s
am
e
g
r
ay
lev
el
[
1
3
]
.
I
t
is
also
a
s
p
atial
g
r
ay
-
lev
el
d
e
p
en
d
en
ce
m
atr
ix
wh
ich
c
h
ar
ac
ter
i
ze
s
,
q
u
an
tifie
s
,
an
d
ex
p
lo
r
es
th
e
d
is
tr
ib
u
tio
n
o
f
g
r
ay
-
lev
el
in
te
n
s
ities
.
I
n
f
o
r
m
ati
o
n
a
b
o
u
t
th
e
in
te
n
s
ity
o
f
th
e
g
r
ay
lev
el
is
p
r
o
v
id
ed
o
n
ly
b
y
s
tatis
tical
f
ea
tu
r
es
an
d
GL
C
M
-
b
ased
f
ea
tu
r
es
ex
tr
ac
ted
f
r
o
m
t
h
e
R
OI
wer
e
ex
tr
a
cted
to
d
eter
m
in
e
t
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
1
2
2
6
-
1
2
3
7
1232
r
elatio
n
s
h
ip
b
etwe
en
th
e
in
ter
-
p
ix
el.
I
f
I
(
x
,
y
)
is
th
e
g
r
ay
-
le
v
el
im
ag
e
an
d
h
as
G
g
r
ay
lev
els
th
en
G×
G
is
th
e
n
u
m
b
er
o
f
p
o
s
s
ib
le
p
air
s
i
n
th
e
g
r
ay
lev
el,
th
e
f
r
e
q
u
en
c
y
o
f
th
ese
p
air
s
is
ca
lcu
lated
an
d
s
to
r
ed
in
th
e
f
o
r
m
o
f
a
GL
C
M
Ma
t
r
ix
G×
G
[
6
]
.
2
.
4
.
2
.
2
-
D
dis
cr
et
e
wa
v
elet
t
r
a
ns
f
o
rm
(
DWT
)
T
h
e
u
s
e
o
f
DW
T
in
n
o
n
-
s
tatio
n
ar
y
im
ag
e
an
aly
s
is
is
h
ig
h
ly
ad
v
an
tag
e
o
u
s
[
1
1
]
.
I
ts
u
t
ilit
y
is
to
p
er
f
o
r
m
th
e
ex
tr
ac
tio
n
o
f
im
p
o
r
tan
t
f
ea
tu
r
es
f
r
o
m
th
e
ir
is
im
ag
e,
wh
er
e
it
an
aly
ze
s
th
e
o
r
ig
in
al
ir
is
im
ag
e
o
f
s
ize
N×
N
in
to
4
s
u
b
s
am
p
les
o
f
im
ag
es
ea
ch
o
f
s
ize
N/2
×N
/
2
wh
ich
ar
e
a
p
p
r
o
x
im
atio
n
(
L
L
)
,
h
o
r
izo
n
tal
(
HL
)
,
v
er
tical
(
L
H)
,
an
d
d
iag
o
n
al
(
H
H)
[
2
3
]
.
2
.
5
.
Cla
s
s
if
ica
t
io
n
Af
ter
th
e
f
ea
tu
r
e
e
x
tr
ac
tio
n
s
tag
e
f
r
o
m
th
e
R
OI
,
th
e
m
o
s
t
im
p
o
r
tan
t
s
tag
e
b
e
g
in
s
with
th
e
class
if
icatio
n
s
tag
e.
T
h
e
m
o
s
t
wid
ely
u
s
ed
AI
tech
n
iq
u
es
in
clas
s
if
icatio
n
an
d
p
r
ed
i
ctio
n
,
in
clu
d
e
ML
tech
n
iq
u
es th
at
m
ain
l
y
u
s
e
ar
ti
f
icial
n
eu
r
al
n
etwo
r
k
s
(
ANN)
to
tr
y
to
s
im
u
late
h
o
w
liv
in
g
o
r
g
an
is
m
s
lear
n
.
ML
tech
n
iq
u
es
ar
e
ap
p
lie
d
in
v
ar
io
u
s
m
ed
ical
ap
p
licatio
n
s
,
wh
ich
in
v
o
lv
e
a
n
u
m
b
er
o
f
t
ec
h
n
iq
u
es
an
d
ap
p
r
o
ac
h
es
[
2
4
]
.
T
h
ese
tech
n
iq
u
es
h
elp
an
aly
ze
an
d
p
r
o
ce
s
s
d
ata,
p
r
o
v
id
in
g
s
o
lu
tio
n
s
with
h
ig
h
ac
cu
r
ac
y
an
d
tim
e.
T
h
ese
two
cr
iter
ia
a
r
e
th
e
m
o
s
t
im
p
o
r
ta
n
t
cr
iter
ia
in
d
iag
n
o
s
in
g
d
is
ea
s
es
th
at
r
es
ea
r
ch
er
s
ar
e
tr
y
in
g
to
im
p
r
o
v
e
[
2
5
]
.
T
h
e
m
eth
o
d
o
f
d
iag
n
o
s
in
g
d
iab
etes
u
s
i
n
g
ir
is
an
aly
s
is
an
d
ML
m
o
d
els
h
as
s
ig
n
if
ican
t
p
o
ten
tial f
o
r
r
ed
u
ci
n
g
p
atie
n
t
d
is
co
m
f
o
r
t d
u
r
in
g
d
iag
n
o
s
is
[
1
8
]
.
NN
ar
e
a
s
u
b
f
ield
o
f
ML
an
d
f
o
r
m
th
e
f
o
u
n
d
atio
n
o
f
d
ee
p
l
ea
r
n
in
g
(
DL
)
.
T
h
eir
aim
is
to
p
r
o
d
u
ce
AI
b
y
d
esig
n
in
g
c
o
m
p
u
ter
s
y
s
tem
s
th
at
s
im
u
late
th
e
h
u
m
an
n
er
v
o
u
s
s
y
s
tem
.
ML
ca
n
p
er
f
o
r
m
task
s
s
im
ilar
to
th
o
s
e
p
er
f
o
r
m
ed
b
y
h
u
m
a
n
s
u
s
in
g
NNs
wh
o
s
e
co
m
p
u
ta
tio
n
al
s
tr
u
ctu
r
e
s
im
u
lates
h
u
m
an
n
eu
r
o
n
s
[
2
6
]
.
I
n
th
is
p
r
o
p
o
s
ed
wo
r
k
,
f
i
v
e
N
N
m
o
d
els w
er
e
u
s
ed
,
as
d
escr
i
b
ed
:
2
.
5
.
1
.
Na
rr
o
w
neura
l net
wo
r
k
(
NNN)
mo
del
I
t
h
as
a
s
in
g
le
f
u
lly
co
n
n
ec
ted
h
id
d
en
lay
er
[
2
7
]
,
[
2
8
]
.
E
a
ch
lay
er
co
n
s
is
ts
o
f
a
s
m
all
n
u
m
b
er
o
f
n
eu
r
o
n
s
.
On
e
o
f
th
e
p
r
o
b
lem
s
with
th
is
m
o
d
el
is
th
at
i
t
m
ay
lim
it
its
ab
ilit
y
to
ca
p
tu
r
e
co
m
p
lex
r
elatio
n
s
h
ip
s
,
b
u
t its
ad
v
an
tag
es a
r
e
t
h
at
it p
r
o
v
id
es a
lo
wer
p
r
o
b
a
b
ilit
y
o
f
o
v
er
f
itti
n
g
a
n
d
f
aster
tr
ai
n
in
g
p
r
o
ce
s
s
es
[
2
9
]
.
2
.
5
.
2
.
M
edium
neura
l net
wo
rk
(
M
NN)
m
o
del
I
t
h
as
s
in
g
le
f
u
lly
co
n
n
ec
ted
h
id
d
en
lay
er
[
2
7
]
,
[
2
8
]
.
E
ac
h
lay
er
co
n
s
is
ts
o
f
a
m
o
d
er
ate
n
u
m
b
er
o
f
n
eu
r
o
n
s
.
T
h
e
b
en
ef
its
o
f
th
i
s
m
o
d
el
ar
ch
itectu
r
e
ar
e
th
e
b
alan
ce
b
etwe
en
tr
ain
in
g
d
y
n
am
ics
an
d
m
o
d
el
co
m
p
lex
ity
[
2
9
]
.
2
.
5
.
3
.
Wide neura
l net
wo
rk
(
WNN)
m
o
del
I
t
h
as
a
s
in
g
le
f
u
lly
c
o
n
n
ec
te
d
h
id
d
en
lay
er
[
2
7
]
,
[
2
8
]
.
E
a
ch
lay
er
co
n
s
is
ts
o
f
a
lar
g
er
n
u
m
b
er
o
f
n
eu
r
o
n
s
.
I
ts
s
tr
u
ctu
r
e
is
ch
ar
a
cter
ized
b
y
id
e
n
tify
in
g
co
m
p
lex
p
atter
n
s
.
I
ts
d
is
ad
v
a
n
tag
es
in
clu
d
e
ch
allen
g
es
wh
en
o
v
e
r
f
itti
n
g
o
cc
u
r
s
[
2
9
]
.
2
.
5
.
4
.
B
i
-
la
y
er
ed
neura
l net
wo
rk
(
B
NN)
mo
del
I
t
h
as
two
f
u
lly
co
n
n
ec
ted
h
id
d
en
lay
er
s
[
2
7
]
,
[
2
8
]
.
T
h
e
s
tr
u
ctu
r
e
o
f
th
is
m
o
d
el
co
n
s
is
ts
o
f
two
b
asic
lay
er
s
,
wh
ich
ar
e
th
e
h
id
d
e
n
lay
er
an
d
th
e
o
u
t
p
u
t
lay
er
.
I
ts
s
tr
u
ctu
r
e
is
ch
ar
ac
ter
ized
b
y
s
im
p
licity
o
f
in
ter
p
r
etatio
n
[
2
9
]
.
2
.
5
.
5
.
T
ri
-
la
y
er
ed
neura
l net
wo
rk
(
T
NN)
mo
del
I
t
h
as
th
r
ee
f
u
lly
co
n
n
ec
ted
h
id
d
en
lay
e
r
s
[
2
7
]
,
[
2
8
]
.
T
h
e
s
tr
u
ctu
r
e
o
f
th
is
m
o
d
el
c
o
n
s
is
ts
o
f
th
r
ee
lay
er
s
:
th
e
in
p
u
t
lay
er
,
th
e
co
n
ce
alm
en
t
lay
er
,
an
d
th
e
o
u
tp
u
t
lay
er
.
T
h
e
b
en
e
f
its
o
f
th
is
m
o
d
el
ar
e
to
en
h
an
ce
th
e
n
etwo
r
k
'
s
ab
ilit
y
to
lear
n
m
o
r
e
co
m
p
r
eh
e
n
s
iv
e
r
ep
r
esen
t
ati
o
n
s
o
f
th
e
in
p
u
t d
ata
[
2
9
]
.
T
o
ev
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
ML
m
o
d
els,
th
e
cr
o
s
s
-
v
alid
atio
n
tech
n
iq
u
e
is
u
s
ed
.
C
r
o
s
s
-
v
alid
atio
n
is
th
e
p
r
o
ce
s
s
o
f
d
iv
i
d
in
g
th
e
tr
ain
in
g
d
ata
in
t
o
k
-
f
o
ld
s
o
r
s
u
b
s
ets
to
tr
ain
th
e
m
o
d
el
an
d
ev
alu
ate
it
k
tim
es.
E
ac
h
tim
e,
one
-
f
o
ld
f
r
o
m
th
e
s
et
o
f
k
-
f
o
ld
s
is
u
s
ed
f
o
r
test
in
g
an
d
th
e
r
e
m
ain
in
g
f
o
ld
s
ar
e
u
s
ed
f
o
r
tr
ain
in
g
.
T
h
is
p
r
o
ce
s
s
is
r
ep
ea
ted
k
tim
es,
ea
ch
tim
e
u
s
in
g
a
d
if
f
er
en
t
f
o
ld
in
th
e
test
to
en
s
u
r
e
a
m
o
r
e
r
o
b
u
s
t
ev
alu
atio
n
o
f
th
e
m
o
d
el,
a
n
d
t
h
e
f
in
al
ac
cu
r
ac
y
is
th
e
av
e
r
ag
e
o
f
th
e
d
ef
ec
tiv
e
ac
cu
r
ac
y
at
ea
ch
iter
atio
n
[
3
0
]
.
I
n
th
is
wo
r
k
,
th
e
r
a
n
g
e
o
f
k
-
f
o
ld
f
r
o
m
2
t
o
2
0
f
o
ld
s
was u
s
ed
to
o
b
tain
th
e
m
o
s
t a
p
p
r
o
p
r
iate
f
o
ld
with
th
e
b
est
p
e
r
f
o
r
m
an
ce
ac
cu
r
ac
y
f
o
r
th
e
f
iv
e
class
if
ier
m
o
d
e
ls
.
Su
p
er
v
is
ed
ML
r
eq
u
ir
es
f
ea
tu
r
e
d
ata
to
b
e
a
lab
eled
to
tr
ain
alg
o
r
ith
m
s
with
to
co
m
p
lete
th
e
class
if
icatio
n
p
r
o
ce
s
s
an
d
p
r
ed
ict
th
e
d
iag
n
o
s
is
o
f
th
e
d
is
ea
s
e
later
.
I
n
th
is
wo
r
k
,
th
e
lab
el
(
0
)
is
f
o
r
n
o
r
m
al
an
d
th
e
lab
el
(
1
)
is
f
o
r
d
iab
etic
p
atien
ts
.
T
h
e
p
er
f
o
r
m
a
n
ce
r
esu
lts
o
f
th
e
ML
alg
o
r
ith
m
s
f
o
r
class
if
icatio
n
ar
e
ev
al
u
ated
b
y
6
m
etr
i
cs,
n
am
ely
ac
cu
r
ac
y
,
s
p
ec
if
icity
,
s
en
s
itiv
i
ty
,
p
r
ec
is
io
n
,
F1
-
s
co
r
e
an
d
A
UC
,
as
s
h
o
wn
in
T
ab
le
1
,
b
as
ed
o
n
th
e
v
alid
atio
n
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
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
N
eu
r
a
l n
etw
o
r
k
-
b
a
s
ed
d
ia
g
n
o
s
is
o
f
typ
e
2
d
ia
b
etes
u
s
in
g
an
ir
id
o
lo
g
y
a
p
p
r
o
a
ch
(
A
la
a
A
b
d
u
lka
r
ee
m
A
h
med
)
1233
m
atr
ix
v
al
u
es,
n
am
el
y
f
alse
p
o
s
itiv
e
(
FP
)
,
tr
u
e
p
o
s
itiv
e
(
T
P),
f
alse
n
e
g
ativ
e
(
FN)
,
an
d
tr
u
e
n
eg
ativ
e
(
T
N)
[
3
1
]
,
as
s
h
o
wn
in
Fig
u
r
e
6
(
a)
.
I
n
th
is
wo
r
k
,
th
e
NN
m
o
d
els
av
ailab
le
in
th
e
Statis
t
ics
an
d
Ma
ch
in
e
L
ea
r
n
in
g
T
o
o
lb
o
x
2
4
.
1
in
class
if
icatio
n
lear
n
er
Ap
p
licatio
n
in
th
e
MA
T
L
AB
v
er
s
io
n
R
2
0
2
4
,
we
r
e
u
s
ed
.
T
ab
le
1
.
Ma
ch
i
n
e
lear
n
in
g
cla
s
s
if
icatio
n
p
er
f
o
r
m
a
n
ce
m
etr
ic
s
M
e
t
r
i
c
s
D
e
f
i
n
i
t
i
o
n
F
o
r
mu
l
a
A
c
c
u
r
a
c
y
I
t
i
s t
h
e
r
a
t
i
o
o
f
t
h
e
c
o
r
r
e
c
t
l
y
p
r
e
d
i
c
t
e
d
sa
mp
l
e
s
(
t
r
u
e
p
o
s
i
t
i
v
e
s
a
n
d
t
r
u
e
n
e
g
a
t
i
v
e
s)
t
o
t
h
e
t
o
t
a
l
n
u
m
b
e
r
o
f
p
r
e
d
i
c
t
e
d
s
a
m
p
l
e
s
[
3
2
]
.
+
+
+
+
×
100%
,
[
2
]
S
p
e
c
i
f
i
c
i
t
y
o
r
t
r
u
e
n
e
g
a
t
i
v
e
r
a
t
e
(
TN
R
)
t
h
e
n
u
m
b
e
r
o
f
a
c
c
u
r
a
t
e
n
e
g
a
t
i
v
e
p
r
e
d
i
c
t
i
o
n
s
t
o
t
h
e
t
o
t
a
l
n
u
mb
e
r
o
f
n
e
g
a
t
i
v
e
p
r
e
d
i
c
t
i
o
n
s
[
6
]
.
+
×
100%
,
[
2
]
S
e
n
s
i
t
i
v
i
t
y
o
r
t
r
u
e
p
o
s
i
t
i
v
e
r
a
t
e
(
TPR)
[
6
]
I
s t
h
e
n
u
mb
e
r
o
f
sam
p
l
e
s fr
o
m
a
c
e
r
t
a
i
n
c
l
a
ss
t
h
a
t
a
r
e
c
o
r
r
e
c
t
l
y
c
l
a
ss
i
f
i
e
d
[
6
]
.
+
×
100%
,
[
2
]
P
r
e
c
i
s
i
o
n
I
t
i
s t
h
e
n
u
mb
e
r
o
f
t
i
mes
t
h
e
c
l
a
ssi
f
i
e
r
p
r
e
d
i
c
t
s
c
o
r
r
e
c
t
l
y
w
h
e
r
e
i
t
g
i
v
e
s
d
e
t
a
i
l
e
d
c
h
a
r
a
c
t
e
r
i
st
i
c
s
o
f
t
h
e
c
l
a
ss
i
f
i
e
r
[
6
]
.
+
×
100%
,
[
2
]
F
a
l
se
p
o
si
t
i
v
e
r
a
t
e
(
F
P
R
)
I
t
i
s t
h
e
p
r
o
b
a
b
i
l
i
t
y
o
f
a
n
e
r
r
o
r
,
i
.
e
.
w
h
e
n
t
h
e
r
e
i
s
a
n
e
g
a
t
i
v
e
v
a
l
u
e
i
t
i
s
r
e
p
o
r
t
e
d
a
s a
p
o
s
i
t
i
v
e
v
a
l
u
e
[
2
]
.
o
r
i
s
t
h
e
n
u
m
b
e
r
o
f
sam
p
l
e
s
t
h
a
t
a
r
e
i
n
c
o
r
r
e
c
t
l
y
c
l
a
ssi
f
i
e
d
[
6
]
.
+
×
100%
,
[
2
]
F1
-
sc
o
r
e
D
e
scri
b
e
s
t
h
e
r
e
l
a
t
i
o
n
sh
i
p
b
e
t
w
e
e
n
t
h
e
a
c
c
u
r
a
c
y
o
f
t
h
e
c
l
a
ss
i
f
i
e
r
a
n
d
i
t
s
sen
s
i
t
i
v
i
t
y
[
6
]
.
2
2
+
+
×
100%
,
[
6
]
R
O
C
R
e
c
e
i
v
e
r
o
p
e
r
a
t
i
n
g
c
h
a
r
a
c
t
e
r
i
s
t
i
c
c
u
r
v
e
[
3
1
]
i
s
b
e
t
w
e
e
n
t
h
e
f
a
l
se
p
o
s
i
t
i
v
e
r
a
t
e
a
n
d
t
h
e
t
r
u
e
p
o
si
t
i
v
e
r
a
t
e
f
o
r
t
h
e
c
l
a
ssi
f
i
e
r
s
[
1
1
]
.
-
AUC
A
r
e
a
u
n
d
e
r
t
h
e
c
u
r
v
e
(
R
O
C
)
r
e
p
r
e
s
e
n
t
s t
h
e
a
b
i
l
i
t
y
t
o
a
c
c
e
ss
t
h
e
e
n
t
i
r
e
o
p
e
r
a
t
i
n
g
r
a
n
g
e
o
f
t
h
e
c
l
a
ssi
f
i
e
r
[
1
1
]
.
∫
+
1
0
+
,
[
3
3
]
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
r
esu
lts
o
f
th
e
class
if
icatio
n
ac
cu
r
ac
y
o
f
th
e
f
iv
e
NN
m
o
d
els
an
d
t
h
eir
r
elatio
n
s
h
ip
to
t
h
e
ch
an
g
e
in
th
e
p
r
o
p
o
s
ed
k
-
f
o
ld
r
an
g
e
ar
e
p
r
esen
ted
in
th
is
s
ec
tio
n
.
I
t
was
n
o
tice
d
in
T
ab
le
2
th
at
th
e
tr
ain
in
g
r
esu
lts
f
o
r
ea
c
h
alg
o
r
ith
m
m
o
d
el
y
iel
d
e
s
lig
h
ty
d
if
f
er
e
n
t
class
if
icatio
n
ac
c
u
r
ac
ies
at
ea
c
h
k
-
f
o
ld
.
Fig
u
r
e
6
t
h
e
h
ig
h
est
ac
cu
r
ac
y
o
b
tain
e
d
f
r
o
m
th
e
N
N
m
o
d
els
was
ac
h
iev
ed
b
y
th
e
NNN
m
o
d
el
,
r
ea
ch
in
g
8
3
.
2
% a
t
7
-
f
o
ld
.
I
t
ca
n
b
e
n
o
tice
d
in
th
e
Valid
atio
n
C
o
n
f
u
s
io
n
Ma
tr
ix
in
Fig
u
r
e
6
(
b
)
f
o
r
NNN
m
o
d
el
at
th
e
h
ig
h
es
t
ac
cu
r
ac
y
th
at
th
e
n
u
m
b
er
o
f
in
c
o
r
r
ec
tly
d
etec
te
d
im
ag
es
is
1
8
im
ag
es
o
u
t
o
f
1
0
7
a
n
d
th
e
m
o
s
t
in
co
r
r
ec
tl
y
d
etec
ted
ar
e
th
e
im
ag
es
o
f
h
ea
lth
y
p
e
o
p
le
c
o
m
p
ar
ed
to
t
h
o
s
e
with
d
iab
et
es
.
As
f
o
r
Fig
u
r
e
6
(
c)
,
it
i
llu
s
tr
ates
th
e
R
OC
cu
r
v
e,
s
h
o
win
g
th
e
o
p
er
atin
g
ar
ea
s
f
o
r
b
o
th
n
o
r
m
al
(
lab
el
0
)
an
d
Diab
etes (
lab
el
1
)
,
with
a
n
AUC
of
0
.
8
6
7
4
.
As
f
o
r
test
in
g
th
e
NNN
m
o
d
el
u
s
in
g
4
3
im
a
g
es,
it
was
f
o
u
n
d
th
at
th
e
ac
cu
r
ac
y
was
7
4
.
4
1
%
,
wh
er
e
it
was
n
o
tice
d
th
at
th
e
to
tal
ac
c
u
r
ac
y
o
f
tr
ai
n
in
g
with
test
in
g
f
o
r
all
im
ag
es
was
8
0
.
6
6
%
,
as
in
d
icate
d
b
y
th
e
o
th
er
m
etr
ics
f
o
r
ea
c
h
ca
s
e
i
n
T
ab
le
3
.
To
co
m
p
ar
e
th
e
cu
r
r
en
t
wo
r
k
with
p
r
ev
i
o
u
s
s
tu
d
ies
on
d
iab
etes
d
iag
n
o
s
is
u
s
in
g
NN
alg
o
r
ith
m
m
o
d
els,
T
ab
le
4
p
r
es
en
ts
a
co
m
p
ar
is
o
n
o
f
b
o
th
th
e
m
eth
o
d
o
lo
g
y
e
m
p
lo
y
e
d
a
n
d
th
e
class
if
icatio
n
r
esu
lts
.
T
ab
le
2
.
T
h
e
ac
cu
r
ac
y
r
esu
lts
o
f
NN
m
o
d
els at
1
0
7
im
ag
e
(
5
7
-
No
r
m
al,
5
0
-
Diab
etic)
,
1
1
2
f
ea
tu
r
es,
an
d
with
k
-
f
o
ld
k
-
f
o
l
d
NNN
a
c
c
u
r
a
c
y
%
M
N
N
a
c
c
u
r
a
c
y
%
W
N
N
a
c
c
u
r
a
c
y
%
B
N
N
a
c
c
u
r
a
c
y
%
TN
N
a
c
c
u
r
a
c
y
%
2
6
4
.
5
%
6
8
.
2
%
6
8
.
2
%
6
4
.
5
%
6
6
.
4
%
3
7
5
.
7
%
7
3
.
8
%
7
3
.
8
%
7
2
%
7
4
.
8
%
4
7
4
.
8
%
7
2
%
7
4
.
8
%
7
6
.
6
%
7
2
.
9
%
5
7
3
.
8
%
7
4
.
8
%
7
5
.
7
%
7
2
%
7
1
%
6
7
7
.
6
%
7
5
.
7
%
7
7
.
6
%
7
7
.
6
%
7
4
.
8
%
7
8
3
.
2
%
7
6
.
6
%
7
7
.
6
%
7
8
.
5
%
7
2
.
9
%
8
7
8
.
5
%
7
6
.
6
%
7
7
.
6
%
7
2
.
9
%
7
6
.
6
%
9
7
6
.
6
%
7
2
.
9
%
7
5
.
7
%
7
4
.
8
%
7
5
.
7
%
10
7
9
.
4
%
7
2
.
9
%
7
3
.
8
%
7
3
.
8
%
7
3
.
8
%
11
7
2
.
9
%
7
3
.
8
%
6
9
.
2
%
7
2
.
9
%
7
0
.
1
%
12
7
9
.
4
%
7
5
.
7
%
7
4
.
8
%
7
2
%
7
3
.
8
%
13
7
4
.
8
%
7
7
.
6
%
7
8
.
5
%
7
5
.
7
%
7
5
.
7
%
14
7
4
.
8
%
7
9
.
4
%
7
4
.
8
%
7
2
%
7
4
.
8
%
15
6
7
.
3
%
7
3
.
8
%
7
2
.
9
%
7
3
.
8
%
7
0
.
1
%
16
7
5
.
7
%
7
2
.
9
%
7
4
.
8
%
7
0
.
1
%
7
3
.
8
%
17
7
2
.
9
%
7
2
.
9
%
7
2
.
9
%
7
2
.
9
%
7
9
.
4
%
18
7
6
.
6
%
7
7
.
6
%
7
4
.
8
%
7
8
.
5
%
7
7
.
6
%
19
7
2
%
7
2
.
9
%
7
7
.
6
%
7
6
.
6
%
7
4
.
8
%
20
7
6
.
6
%
7
4
.
8
%
7
3
.
8
%
7
8
.
5
%
7
3
.
8
%
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
3
,
Sep
tem
b
er
20
2
6
:
1
2
2
6
-
1
2
3
7
1234
(
a)
(
b
)
(
c)
Fig
u
r
e
6
.
Per
f
o
r
m
an
c
e
ev
alu
at
io
n
o
f
t
h
e
NNN
m
o
d
el
th
at
ac
co
m
p
lis
h
tr
ain
in
g
ac
cu
r
ac
y
o
f
8
3
.
2
%
u
s
in
g
7
-
f
o
ld
cr
o
s
s
v
alid
atio
n
(
a)
g
en
er
al
c
o
n
f
u
s
io
n
m
atr
ix
p
e
r
f
o
r
m
a
n
ce
p
ar
a
m
eter
s
,
(
b
)
v
ali
d
atio
n
co
n
f
u
s
io
n
m
atr
ix
p
a
r
am
eter
s
,
an
d
(
c)
th
e
r
ec
eiv
e
r
o
p
e
r
atin
g
ch
ar
ac
ter
is
tic
(
R
OC
)
cu
r
v
e
with
th
e
co
r
r
esp
o
n
d
in
g
AUC
T
ab
le
3
.
All m
etr
ics r
esu
lts
f
o
r
th
e
h
ig
h
est ac
cu
r
ac
y
o
f
NNN
m
o
d
els at
7
-
f
o
ld
R
e
s
u
l
t
t
y
p
e
I
mag
e
n
o
F
a
l
se
p
r
e
d
i
c
t
e
d
TN
FP
FN
TP
A
c
c
u
r
a
c
y
S
p
e
c
i
f
i
c
i
t
y
S
e
n
s
i
t
i
v
i
t
y
P
r
e
c
i
s
i
o
n
F1
-
sco
r
e
AUC
Tr
a
i
n
i
n
g
1
0
7
18
46
11
7
43
8
3
.
2
%
8
0
.
7
%
8
6
%
7
9
.
6
2
%
8
2
.
6
9
%
0
.
8
6
7
4
Te
st
i
n
g
43
11
15
9
2
17
7
4
.
4
1
%
6
2
.
5
%
8
9
.
4
7
%
6
5
.
3
8
%
7
5
.
5
5
%
~
0
.
8
9
4
7
Tr
a
i
n
i
n
g
+
Te
s
t
i
n
g
1
5
0
29
61
20
9
60
8
0
.
6
6
%
7
5
.
3
%
8
6
.
9
5
%
7
5
%
8
0
.
5
3
%
~
0
.
8
6
9
5
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
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
N
eu
r
a
l n
etw
o
r
k
-
b
a
s
ed
d
ia
g
n
o
s
is
o
f
typ
e
2
d
ia
b
etes
u
s
in
g
an
ir
id
o
lo
g
y
a
p
p
r
o
a
ch
(
A
la
a
A
b
d
u
lka
r
ee
m
A
h
med
)
1235
T
ab
le
4
.
C
o
m
p
a
r
is
o
n
b
etwe
en
cu
r
r
en
t a
n
d
p
r
ev
io
u
s
wo
r
k
o
n
d
iab
etes d
iag
n
o
s
is
b
ased
o
n
NN
m
o
d
els
Y
e
a
r
a
n
d
R
e
f
e
r
e
n
c
e
R
i
g
h
t
i
r
i
s
Le
f
t
i
r
i
s
R
O
I
i
n
r
i
g
h
t
i
r
i
s
(7
-
8)
R
O
I
i
n
l
e
f
t
i
r
i
s
(4
-
5)
R
O
I
i
n
l
e
f
t
i
r
i
s
(7
-
8)
S
u
m
o
f
t
h
e
t
h
r
e
e
R
O
I
i
n
b
o
t
h
i
r
i
ses
P
C
A
%
F
e
a
t
u
r
e
sel
e
c
t
i
o
n
F
e
a
t
u
r
e
s
n
u
m
b
e
r
a
n
d
t
y
p
e
s
k
-
f
o
l
d
N
N
t
y
p
e
A
c
c
u
r
a
c
y
%
2
0
1
5
[
1
0
]
✓
-
-
-
-
-
✓
-
a
d
a
p
t
i
v
e
h
i
s
t
o
g
r
a
m
e
q
u
a
l
i
z
a
t
i
o
n
-
f
e
e
d
-
f
o
r
w
a
r
d
b
a
c
k
-
p
r
o
p
a
g
a
t
i
o
n
N
N
-
2
0
1
7
[
1
1
]
✓
-
-
-
-
-
-
-
6
3
f
e
a
t
u
r
e
s
st
a
t
i
st
i
c
a
l
a
n
d
w
a
v
e
l
e
t
10
b
a
c
k
-
p
r
o
p
a
g
a
t
i
o
n
N
N
6
7
.
2
9
%
2
0
1
7
[
7
]
-
-
-
-
-
✓
-
t
-
t
e
s
t
5
0
f
e
a
t
u
r
e
s
st
a
t
i
st
i
c
a
l
,
G
LC
M
a
n
d
w
a
v
e
l
e
t
10
NN
6
7
.
2
9
%
2
0
2
3
[
1
6
]
✓
✓
-
-
-
-
✓
c
h
i
-
sq
u
a
r
e
-
5
ELM
(
(
S
LFN
)
)
w
i
t
h
A
d
a
m
9
9
.
9
2
%
Th
i
s
w
o
r
k
-
-
✓
-
-
-
-
-
1
1
2
f
e
a
t
u
r
e
s
S
t
a
t
i
st
i
c
a
l
,
G
LC
M
a
n
d
w
a
v
e
l
e
t
7
NNN
8
3
.
2
%
4.
CO
NCLU
SI
O
N
T
h
is
wo
r
k
ex
h
ib
its
th
e
f
ea
s
ib
ilit
y
o
f
d
etec
tin
g
t
y
p
e
2
d
iab
ete
s
v
ia
ir
id
o
lo
g
y
u
s
in
g
ML
tech
n
iq
u
es.
B
y
ex
tr
ac
tin
g
s
tatis
tical
an
d
tex
t
u
r
e
f
ea
tu
r
es
f
r
o
m
th
e
r
ig
h
t
i
r
is
an
d
tr
ain
i
n
g
NN
m
o
d
els,
th
e
class
if
icatio
n
ac
cu
r
ac
y
is
8
3
.
2
% u
s
in
g
th
e
NNN
m
o
d
e
l
at
7
-
f
o
l
d
cr
o
s
s
-
v
alid
atio
n
.
T
h
e
r
esu
lts
s
h
o
w
th
at
ir
id
o
lo
g
y
co
m
b
in
e
d
with
AI
ca
n
be
an
ef
f
ec
tiv
e
an
d
n
o
n
-
in
v
asiv
e
d
iag
n
o
s
tic
to
o
l.
Fu
tu
r
e
r
esear
ch
s
h
o
u
ld
co
n
ce
n
tr
ate
o
n
en
h
an
cin
g
m
o
d
el
ac
c
u
r
ac
y
th
r
o
u
g
h
ad
v
an
ce
d
f
ea
tu
r
e
s
elec
tio
n
alg
o
r
ith
m
s
,
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
es,
an
d
m
o
r
e
d
iv
e
r
s
e
d
atasets
.
I
n
teg
r
a
tin
g
th
is
m
eth
o
d
i
n
to
clin
ical
p
r
ac
tice
co
u
ld
im
p
r
o
v
e
ea
r
ly
d
iab
etes
d
etec
tio
n
,
r
ed
u
cin
g
d
ep
e
n
d
en
ce
o
n
tr
a
d
itio
n
al
b
lo
o
d
test
s
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
No
f
u
n
d
in
g
in
v
o
lv
e
d
.
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
t
r
ib
u
to
r
R
o
les
T
a
x
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
i
d
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
Alaa
Ab
d
u
lk
ar
ee
m
Ah
m
ed
✓
✓
✓
✓
✓
✓
✓
✓
✓
Mo
h
am
m
ad
T
ar
iq
Yaseen
✓
✓
✓
✓
✓
✓
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
No
co
n
f
lict o
f
in
ter
est.
Evaluation Warning : The document was created with Spire.PDF for Python.