I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
11
,
No
.
4
,
A
u
g
u
s
t
2021
,
p
p
.
3
0
4
0
~
3
0
4
8
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
11
i
4
.
pp
3
0
4
0
-
3
0
4
8
3040
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
S
m
a
ll i
ntesti
ne bl
eeding
det
ection
using
colo
r t
hresh
o
ld and
m
o
rpho
lo
g
ica
l opera
tion in
WCE i
m
a
g
es
A.
Al
.
M
a
m
un
1
,
M
.
S
.
H
o
s
s
a
in
2
,
P.
P
.
Em
3
,
A.
T
a
ha
bil
der
4
,
R.
Su
lt
a
na
5
,
M
.
A.
I
s
la
m
6
1,
3
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
lo
g
y
,
M
u
lt
im
e
d
ia Un
iv
e
rsit
y
,
M
e
lak
a
,
M
a
la
y
sia
2,
6
De
p
a
rtm
e
n
t
o
f
EE
E,
P
a
b
n
a
Un
i
v
e
rsit
y
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
P
a
b
n
a
,
Ba
n
g
lad
e
sh
4
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
&
Co
m
p
u
ter E
n
g
in
e
e
rin
g
,
S
tev
e
n
s In
stit
u
te o
f
T
e
c
h
n
o
l
o
g
y
,
Ho
b
o
k
e
n
,
USA
5
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
,
Un
iv
e
rsity
o
f
Co
lo
ra
d
o
De
n
v
e
r
,
De
n
v
e
r
,
USA
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
2
7
,
2
0
20
R
ev
i
s
ed
Feb
2
7
,
2
0
21
A
cc
ep
ted
Mar
11
,
2
0
2
1
W
irele
ss
c
a
p
su
le
e
n
d
o
sc
o
p
y
(
WCE
)
is
a
sig
n
i
f
ica
n
t
m
o
d
e
rn
tec
h
n
i
q
u
e
f
o
r
o
b
se
rv
in
g
th
e
w
h
o
le
g
a
stro
e
n
ter
o
lo
g
ica
l
trac
t
to
d
iag
n
o
se
v
a
rio
u
s
d
ise
a
se
s
li
k
e
b
lee
d
in
g
,
u
lce
r,
tu
m
o
r,
Cro
h
n
'
s
d
ise
a
se
,
a
n
d
p
o
ly
p
s
in
a
n
o
n
-
in
v
a
siv
e
m
a
n
n
e
r.
Ho
w
e
v
e
r,
it
w
il
l
m
a
k
e
a
su
b
sta
n
ti
a
l
o
n
u
s
f
o
r
p
h
y
sic
ian
s
li
k
e
h
u
m
a
n
o
v
e
rsig
h
t
e
rro
rs
w
it
h
ti
m
e
c
o
n
su
m
p
ti
o
n
f
o
r
m
a
n
u
a
l
c
h
e
c
k
in
g
o
f
a
v
a
st
a
m
o
u
n
t
o
f
im
a
g
e
f
r
a
m
e
s.
T
h
e
se
p
ro
b
lem
s
m
o
ti
v
a
te
th
e
re
se
a
rc
h
e
rs
to
e
m
p
lo
y
a
c
o
m
p
u
ter
-
a
id
e
d
sy
ste
m
to
c
la
ss
ify
th
e
p
a
rti
c
u
lar
in
f
o
rm
a
ti
o
n
f
ro
m
th
e
i
m
a
g
e
f
ra
m
e
s.
T
h
e
r
e
f
o
re
,
a
c
o
m
p
u
ter
-
a
id
e
d
s
y
ste
m
b
a
se
d
o
n
th
e
c
o
lo
r
th
re
sh
o
l
d
a
n
d
m
o
rp
h
o
lo
g
ica
l
o
p
e
ra
ti
o
n
h
a
s
b
e
e
n
p
r
o
p
o
se
d
in
t
h
is
re
se
a
rc
h
to
re
c
o
g
n
ize
sp
e
c
if
ied
b
lee
d
in
g
ima
g
e
s
f
ro
m
th
e
W
CE.
Be
sid
e
s,
A
u
n
iq
u
e
c
las
si
f
ier,
q
u
a
d
ra
ti
c
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(QSV
M
)
h
a
s
b
e
e
n
e
m
p
lo
y
e
d
f
o
r
c
las
si
fy
in
g
th
e
b
lee
d
in
g
a
n
d
n
o
n
-
b
lee
d
in
g
im
a
g
e
s
w
it
h
th
e
sta
ti
sti
c
a
l
fe
a
tu
re
v
e
c
to
r
in
HSV
c
o
lo
r
s
p
a
c
e
.
Af
t
e
r
e
x
ten
siv
e
e
x
p
e
ri
m
e
n
ts
o
n
c
li
n
ica
l
d
a
ta,
9
5
.
8
%
a
c
c
u
ra
c
y
,
9
5
%
se
n
siti
v
it
y
,
9
7
%
sp
e
c
i
f
icit
y
,
8
0
%
p
re
c
isio
n
,
9
9
%
n
e
g
a
ti
v
e
p
re
d
icte
d
v
a
lu
e
a
n
d
8
5
%
F
1
sc
o
re
h
a
s
b
e
e
n
a
c
h
iev
e
d
,
w
h
ich
o
u
t
p
e
rf
o
rm
s
so
m
e
o
f
th
e
e
x
isti
n
g
m
e
th
o
d
s
in
t
h
is
re
g
a
rd
.
It
is
e
x
p
e
c
ted
th
a
t
th
is
m
e
th
o
d
o
l
o
g
y
w
o
u
ld
b
ri
n
g
a
sig
n
if
ica
n
t
c
o
n
tri
b
u
ti
o
n
t
o
th
e
W
CE
tec
h
n
o
l
o
g
y
.
K
ey
w
o
r
d
s
:
B
leed
in
g
d
etec
tio
n
C
o
lo
r
th
r
esh
o
ld
HSV
co
lo
r
s
p
ac
e
Mo
r
p
h
o
lo
g
ical
o
p
er
atio
n
QSVM
W
ir
eless
ca
p
s
u
le
e
n
d
o
s
co
p
y
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
:
A
b
d
u
l
lah
A
l M
a
m
u
n
Facu
lt
y
o
f
E
n
g
i
n
ee
r
i
n
g
a
n
d
T
e
ch
n
o
lo
g
y
Mu
lti
m
ed
ia
U
n
iv
er
s
it
y
Ay
er
Ker
o
h
,
Me
lak
a
-
7
5
4
0
,
M
ala
y
s
ia
E
m
ail:
m
a
m
u
n
1
3
0
2
0
3
@
g
m
ai
l
.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
r
ec
en
t
y
ea
r
s
,
t
h
e
d
is
ea
s
e
s
r
elate
d
to
th
e
g
a
s
tr
o
in
te
s
ti
n
al
tr
ac
t
(
GI
)
,
esp
ec
iall
y
i
n
th
e
eso
p
h
ag
u
s
,
s
to
m
ac
h
,
s
m
al
l
i
n
te
s
ti
n
e
an
d
l
ar
g
e
in
t
e
s
ti
n
e
ta
k
e
t
h
e
atte
n
ti
o
n
o
f
t
h
e
r
esear
ch
er
s
b
ec
au
s
e
o
f
its
lo
u
s
y
i
m
p
ac
t
ar
o
u
n
d
th
e
w
o
r
ld
.
I
t
h
as
b
ee
n
f
o
u
n
d
f
r
o
m
s
u
r
v
eilla
n
ce
t
h
at
a
p
p
r
o
x
im
a
tel
y
2
7
.
8
%
o
f
p
eo
p
le
in
So
u
t
h
Asi
a
an
d
ar
o
u
n
d
1
.
6
m
m
(
m
i
llio
n
)
Am
e
r
ican
p
eo
p
le
ar
e
a
f
f
ec
ted
an
d
d
ied
of
i
n
f
la
m
m
ato
r
y
b
o
w
e
l
d
is
ea
s
e
a
n
d
ab
o
u
t
8
0
th
o
u
s
an
d
[
1
]
.
So
,
it
h
as
b
ec
o
m
e
a
n
i
m
p
o
r
tan
t
tas
k
to
d
ev
e
l
o
p
th
e
cu
r
i
n
g
tec
h
n
iq
u
e
f
o
r
G
I
tr
ac
t
p
r
o
b
lem
s
.
T
h
e
d
iag
n
o
s
t
ic
p
r
o
ce
d
u
r
e
f
o
r
th
e
s
e
d
is
ea
s
es
is
th
e
co
n
v
e
n
tio
n
al
f
ib
er
-
o
p
tic
en
d
o
s
co
p
y
,
w
h
ich
c
au
s
e
s
m
u
c
h
p
an
ic
f
o
r
th
e
p
ea
s
an
ts
.
Alo
n
g
w
i
th
t
h
is
,
it
ca
n
n
o
t
ch
ec
k
u
p
t
h
e
w
h
o
le
ar
ea
en
t
ir
el
y
,
e
s
p
ec
iall
y
t
h
e
s
m
al
l
i
n
test
in
e
[
2
]
.
T
o
s
o
lv
e
th
i
s
ch
al
len
g
e
W
C
E
tech
n
iq
u
e
s
h
o
w
s
a
tr
e
m
en
d
o
u
s
r
ev
o
lu
t
io
n
b
y
w
h
ic
h
p
h
y
s
ici
an
s
ca
n
d
etec
t
m
o
r
e
ab
n
o
r
m
alitie
s
in
t
h
e
G
I
tr
ac
t
alo
n
g
w
it
h
b
leed
in
g
.
I
n
W
C
E
tech
n
o
lo
g
y
,
t
h
er
e
h
as
a
ca
p
s
u
le
-
s
h
ap
ed
d
ev
ice
w
it
h
a
ca
m
er
a,
l
ig
h
t
s
o
u
r
ce
,
w
ir
ele
s
s
tr
an
s
m
it
ter
an
d
b
at
te
r
y
.
I
t
also
n
ee
d
s
s
o
m
e
a
s
s
o
cia
ted
d
ev
ices
s
u
c
h
a
s
i
m
a
g
e
s
e
n
s
o
r
s
,
i
m
a
g
e
r
ec
eiv
e
r
an
d
co
m
p
u
ter
w
ith
b
leed
i
n
g
d
etec
tin
g
to
o
ls
.
T
h
is
d
ev
ice
i
s
s
w
allo
w
ed
to
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
S
ma
ll in
test
in
e
b
leed
in
g
d
etec
tio
n
u
s
in
g
c
o
lo
r
th
r
esh
o
ld
a
n
d
…
(
A
.
A
l.
Ma
mu
n
)
3041
p
atien
t
t
h
at
p
ass
e
s
t
h
r
o
u
g
h
t
h
e
GI
tr
ac
t
a
n
d
ca
p
t
u
r
e
v
id
eo
s
.
A
p
p
r
o
x
i
m
atel
y
ei
g
h
t
h
o
u
r
s
ar
e
n
ee
d
ed
f
o
r
t
h
e
w
h
o
le
p
r
o
ce
d
u
r
e
,
an
d
th
i
s
v
id
eo
is
co
n
v
er
ted
i
n
to
i
m
a
g
e
f
r
a
m
e
s
,
w
h
ich
is
n
o
t
p
o
s
s
ib
le
f
o
r
clin
ician
s
to
ch
ec
k
th
ese
i
m
a
g
es
m
an
u
all
y
.
So
,
th
e
ap
p
lied
co
m
p
u
ter
-
b
ased
s
y
s
te
m
r
e
m
o
v
es
t
h
e
b
u
r
d
en
o
f
th
e
p
h
y
s
icia
n
s
a
n
d
m
ak
e
s
t
h
eir
w
o
r
k
ea
s
y
to
id
en
t
if
y
a
n
o
t
h
er
d
is
ea
s
e
alo
n
g
w
it
h
b
leed
in
g
at
t
h
e
s
a
m
e
ti
m
e
[
3
]
.
2.
RE
L
AT
I
VE
WO
RK
S
B
leed
in
g
d
etec
tio
n
is
v
er
y
m
u
ch
v
ital
f
r
o
m
t
h
e
clin
ical
p
er
s
p
ec
tiv
e
d
u
e
to
m
a
n
y
o
f
th
e
GI
tr
ac
t
d
is
ea
s
e
r
ec
o
g
n
itio
n
d
ep
en
d
s
o
n
it
[
4
]
.
Dis
ti
n
ct
t
y
p
es
o
f
co
m
p
u
ter
-
aid
ed
s
y
s
te
m
s
h
a
v
e
alr
e
ad
y
b
ee
n
i
n
tr
o
d
u
ce
d
in
to
W
C
E
i
m
ag
e
s
to
d
ed
u
ce
th
e
b
u
r
d
en
o
f
th
e
p
h
y
s
icia
n
s
f
o
r
d
etec
tin
g
th
e
b
leed
i
n
g
.
Ho
w
e
v
er
,
t
h
ese
tech
n
iq
u
es
p
r
o
v
id
ed
u
n
s
atis
f
a
cto
r
y
r
es
u
lts
i
n
ter
m
s
o
f
s
e
n
s
itiv
it
y
an
d
s
p
ec
i
f
icit
y
,
s
u
c
h
as
Su
s
p
ec
ted
B
lo
o
d
I
n
d
icato
r
[
5
]
.
I
n
itiall
y
,
a
f
r
a
m
e
w
o
r
k
w
as
d
e
s
ig
n
ed
to
d
et
ec
t
b
leed
in
g
p
o
r
tio
n
i
n
w
h
ic
h
t
h
e
s
p
ec
if
ic
it
y
an
d
s
en
s
iti
v
it
y
w
er
e
o
n
l
y
4
1
.
8
% a
n
d
2
1
.
5
%.
A
s
u
p
er
p
ix
el
tec
h
n
i
q
u
e
h
as b
ee
n
ap
p
lied
b
y
Si
v
ak
u
m
ar
et
a
l.
[
6
]
w
it
h
a
Naiv
e
B
ay
e
s
class
i
f
ier
to
d
etec
t
th
e
b
leed
in
g
r
eg
io
n
ac
cu
r
atel
y
.
Ho
w
e
v
er
,
th
e
m
o
d
el
h
a
s
b
ee
n
tr
ain
ed
o
n
l
y
t
w
o
s
tati
s
tical
f
ea
t
u
r
es
a
n
d
d
i
d
n
o
t
v
a
lid
ate
w
it
h
t
h
e
o
t
h
er
ex
iti
n
g
tec
h
n
iq
u
es.
T
h
e
i
n
f
o
r
m
atio
n
lo
s
s
ca
n
b
e
r
ed
u
ce
d
u
p
to
a
s
ig
n
i
f
ica
n
ce
lev
el
b
y
u
s
i
n
g
m
u
ltip
le
r
an
d
o
m
tr
ai
n
i
n
g
d
atasets
an
d
ac
h
ie
v
ed
h
ig
h
er
s
p
ec
i
f
ic
it
y
an
d
s
en
s
iti
v
it
y
b
y
ap
p
l
y
i
n
g
t
h
e
s
u
p
p
o
r
t v
ec
to
r
m
ac
h
i
n
e.
Ko
n
s
ta
n
ti
n
et
a
l.
h
a
v
e
i
n
tr
o
d
u
ce
d
a
b
leed
in
g
d
etec
tio
n
te
ch
n
iq
u
e
u
tili
zi
n
g
th
e
tex
t
u
r
e
an
d
co
lo
r
f
ea
t
u
r
es
t
h
at
w
o
u
ld
p
r
o
v
id
e
t
h
e
co
m
p
le
te
co
lo
r
i
n
f
o
r
m
atio
n
.
Ne
v
er
th
e
less
,
th
e
co
lo
r
in
f
o
r
m
at
io
n
tec
h
n
o
lo
g
y
p
r
o
v
id
es
lo
w
er
p
er
f
o
r
m
a
n
ce
r
esu
lt
s
co
m
p
ar
ed
to
th
e
o
t
h
er
ex
is
t
in
g
m
et
h
o
d
s
[
7
]
.
T
h
e
f
r
eq
u
en
c
y
s
p
ec
tr
u
m
o
f
ch
ar
ac
ter
is
tic
s
p
atter
n
is
u
s
e
d
b
ased
o
n
n
o
r
m
alize
d
g
r
a
y
lev
el
co
-
o
cc
u
r
r
en
ce
m
atr
ix
a
n
d
also
ac
h
ie
v
ed
a
s
atis
f
ac
to
r
y
b
leed
in
g
d
etec
tio
n
r
ate
[8
]
.
A
u
n
iq
u
e
t
w
o
-
f
o
ld
s
y
s
te
m
i
s
in
tr
o
d
u
ce
d
to
d
etec
t
th
e
b
leed
in
g
p
o
r
tio
n
in
g
i
n
w
h
ic
h
K
-
m
ea
n
s
clu
s
ter
i
n
g
an
d
SVM
class
if
ier
h
as
b
ee
n
ap
p
lied
to
ex
tr
ac
t
th
e
clu
s
ter
ce
n
t
er
an
d
d
is
tin
g
u
is
h
t
h
e
b
leed
in
g
i
m
a
g
es
co
r
r
esp
o
n
d
en
tl
y
[
9
]
.
A
c
h
an
g
ea
b
le
co
lo
r
d
o
m
ai
n
h
as
b
ee
n
i
m
p
le
m
e
n
ted
in
s
tead
o
f
t
h
e
R
GB
co
lo
r
m
o
d
el
to
r
ed
u
ce
th
e
co
m
p
u
ta
tio
n
al
ti
m
e.
B
esid
es,
t
h
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
h
as
b
ee
n
ap
p
lied
to
th
e
s
tatis
tical
f
ea
tu
r
es
d
ep
en
d
in
g
o
n
h
i
g
h
er
a
n
d
lo
w
er
v
al
u
es
to
class
i
f
y
t
h
e
b
leed
in
g
an
d
n
o
n
-
b
leed
in
g
i
m
ag
e
e
f
f
icie
n
tl
y
[
4
]
.
In
[
1
0
]
,
th
e
a
u
t
h
o
r
s
e
x
tr
ac
ted
d
if
f
er
e
n
t
co
lo
r
f
ea
tu
r
e
s
f
r
o
m
t
h
e
i
m
a
g
es
b
y
e
m
p
lo
y
i
n
g
t
h
e
h
is
to
g
r
a
m
tech
n
iq
u
e,
an
d
SVM
cla
s
s
i
f
i
er
ap
p
lied
to
d
is
tin
ct
i
m
a
g
es
.
A
u
th
o
r
s
p
r
o
p
o
s
ed
in
[
1
1
]
a
co
m
p
o
u
n
d
m
o
d
el
n
a
m
ed
Y.
I
/Q
to
e
x
tr
ac
t
t
h
e
i
n
f
o
r
m
atio
n
ab
o
u
t
th
e
c
h
r
o
m
i
n
an
ce
a
n
d
lu
m
i
n
a
n
ce
f
o
r
ac
q
u
ir
in
g
t
h
e
r
eg
io
n
o
f
in
ter
est
o
f
th
e
i
m
ag
e
s
a
n
d
t
h
e
SVM
c
lass
if
ier
tech
n
iq
u
e
e
m
p
lo
y
ed
f
o
r
a
s
atis
f
ac
to
r
y
r
es
u
l
t.
I
n
[
1
2
]
,
au
t
h
o
r
s
f
o
r
m
ed
a
p
ix
el
i
n
ten
s
it
y
r
atio
n
o
f
R
/G
(
R
ed
/Gr
ee
n
)
f
r
o
m
t
h
e
R
GB
co
lo
r
m
o
d
el
to
ac
h
ie
v
e
d
if
f
er
e
n
t
s
tati
s
tical
f
ea
t
u
r
es
an
d
K
-
n
ea
r
es
t
n
ei
g
h
b
o
r
class
if
ier
u
s
ed
f
o
r
class
i
f
i
ca
tio
n
.
Au
t
h
o
r
s
e
m
p
lo
y
ed
in
te
n
s
it
y
f
lu
ct
u
atio
n
o
f
th
e
p
i
x
els
in
th
e
R
GB
co
lo
r
m
o
d
el
w
it
h
s
tatis
t
ical
c
h
ar
ac
t
er
is
tics
a
n
al
y
s
i
s
i
n
[
1
3
]
.
T
h
o
u
g
h
th
e
s
e
tec
h
n
iq
u
e
s
h
av
e
d
o
n
e
tr
e
m
e
n
d
o
u
s
w
o
r
k
o
n
b
leed
in
g
d
etec
tio
n
f
r
o
m
W
C
E
i
m
a
g
es,
t
h
ese
s
till
h
av
e
th
e
li
m
itatio
n
o
f
co
m
p
u
tatio
n
al
co
m
p
le
x
it
y
a
n
d
lo
w
er
p
er
f
o
r
m
a
n
ce
r
es
u
lt
s
.
C
o
lo
r
th
r
es
h
o
ld
tec
h
n
iq
u
es
o
n
d
if
f
er
en
t
co
lo
r
s
p
ac
es
h
a
v
e
b
ee
n
ap
p
lied
f
o
r
d
etec
tin
g
d
i
f
f
er
en
t
ab
n
o
r
m
alitie
s
.
Ho
w
e
v
er
,
it
co
u
ld
n
'
t
d
is
tin
g
u
is
h
t
h
e
in
f
o
r
m
ati
v
e
p
o
r
tio
n
f
r
o
m
t
h
e
b
ac
k
g
r
o
u
n
d
f
o
r
all
t
h
e
i
m
a
g
es
[
2
,
3
,
5
,
1
4
-
18]
.
I
n
th
i
s
p
ap
er
,
a
u
n
iq
u
e
tec
h
n
iq
u
e
f
o
r
ac
cu
r
atel
y
b
leed
in
g
id
e
n
ti
f
icatio
n
o
f
W
C
E
i
m
a
g
e
s
i
n
HSV
co
lo
r
s
p
ac
e
h
a
s
b
ee
n
p
r
o
p
o
s
ed
.
First
o
f
a
ll,
t
h
e
v
id
eo
f
o
o
tag
e
h
as
b
ee
n
co
n
v
er
ted
i
n
to
t
h
e
i
m
a
g
e
f
r
a
m
e
a
n
d
r
e
m
o
v
e
th
e
n
o
n
-
i
n
f
o
r
m
ati
v
e
p
o
r
tio
n
u
s
in
g
s
o
m
e
p
r
e
-
p
r
o
ce
s
s
i
n
g
tec
h
n
iq
u
es.
A
f
ter
t
h
e
p
r
o
ce
s
s
o
f
d
elu
s
io
n
r
e
m
o
v
al
an
d
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
s
,
s
o
m
e
s
tati
s
tical
f
ea
tu
r
e
s
(
e.
g
.
,
m
ea
n
,
s
tan
d
ar
d
d
ev
iatio
n
)
ar
e
ex
tr
ac
ted
f
r
o
m
th
e
o
u
tp
u
t
i
m
ag
e
s
to
h
av
e
th
e
f
ea
t
u
r
e
v
ec
to
r
.
T
h
is
f
ea
tu
r
e
v
ec
to
r
h
as
b
ee
n
u
s
ed
in
a
QSVM
cla
s
s
i
f
ier
to
d
etec
t
th
e
b
leed
in
g
a
n
d
n
o
n
-
b
leed
i
n
g
i
m
ag
es.
O
u
r
p
r
o
p
o
s
ed
m
eth
o
d
h
a
s
test
ed
o
n
t
h
e
p
u
b
licl
y
a
v
aila
b
le
clin
ical
d
ata
s
et,
an
d
s
atis
f
ac
to
r
y
b
leed
in
g
d
ete
ctio
n
r
esu
l
ts
ar
e
o
b
tain
ed
.
3.
RE
S
E
ARCH
M
E
T
H
O
D
I
n
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
,
co
lo
r
th
r
esh
o
ld
an
d
m
o
r
p
h
o
lo
g
i
ca
l
o
p
er
atio
n
-
b
ased
tech
n
iq
u
e
h
as
b
ee
n
ap
p
lied
f
o
r
b
leed
in
g
d
etec
tio
n
.
T
h
e
p
icto
r
ial
r
ep
r
esen
tatio
n
o
f
t
h
e
w
h
o
le
p
r
o
p
o
s
ed
ap
p
r
o
a
ch
h
as
b
ee
n
s
h
o
w
n
in
Fig
u
r
e
1
.
An
a
n
n
o
tated
b
leed
in
g
an
d
n
o
n
-
b
leed
in
g
d
ata
s
et
h
a
v
e
b
ee
n
cr
ea
ted
f
o
r
class
if
y
in
g
th
e
b
leed
in
g
i
m
a
g
es
f
r
o
m
t
h
e
n
o
n
-
bl
ee
d
i
n
g
i
m
ag
e.
T
h
e
an
n
o
tated
d
ataset
ca
n
b
e
m
ad
e
b
y
co
n
v
er
ti
n
g
t
h
e
v
id
eo
clip
f
r
o
m
W
C
E
lik
e
P
illC
a
m
*
SB
in
to
t
h
e
i
m
a
g
e
s
.
A
r
o
u
n
d
2
3
9
3
,
an
n
o
tated
b
leed
in
g
a
n
d
n
o
n
-
b
le
ed
in
g
i
m
a
g
es
h
av
e
b
ee
n
u
s
ed
to
an
al
y
ze
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
,
w
h
ich
i
s
av
ailab
le
in
[
1
9
]
.
In
[
2
0
]
,
th
ey
o
f
f
er
a
b
leed
in
g
d
etec
tio
n
tech
n
iq
u
e
u
s
i
n
g
2
3
0
0
W
C
E
im
ag
e
s
,
th
o
u
g
h
2
3
9
3
im
a
g
es
h
av
e
b
ee
n
u
s
ed
in
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
.
3
.
1
.
Co
l
o
r
t
hresh
o
ld
No
w
t
h
e
i
m
p
o
r
ta
n
t
p
ar
t
is
to
s
elec
t
th
e
i
n
f
o
r
m
ati
v
e
p
o
r
tio
n
o
r
o
b
j
ec
t
f
r
o
m
t
h
e
i
m
a
g
e
an
d
r
e
m
o
v
e
t
h
e
o
th
er
n
o
n
-
i
n
f
o
r
m
ati
v
e
p
ar
t
f
r
o
m
th
e
p
ict
u
r
e,
w
h
ic
h
p
r
o
v
id
es
a
m
o
r
e
ac
cu
r
ate
an
d
e
f
f
ic
i
en
t
r
es
u
lt
i
n
f
ea
t
u
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
4
,
A
u
g
u
s
t
2021
:
3
0
4
0
-
3048
3042
ex
tr
ac
tio
n
an
d
clas
s
i
f
icatio
n
.
On
e
o
f
th
e
s
tep
s
f
o
r
th
e
tas
k
is
th
e
co
lo
r
th
r
esh
o
ld
,
w
h
ich
r
em
o
v
es
th
e
n
o
n
-
b
leed
in
g
ar
ea
f
r
o
m
t
h
e
i
m
a
g
e
s
an
d
s
to
r
es
th
e
i
n
f
o
r
m
atio
n
o
f
th
e
r
e
m
ai
n
i
n
g
r
eq
u
ir
ed
b
leed
in
g
p
o
r
tio
n
.
W
e
h
av
e
d
i
s
tr
ib
u
ted
th
e
i
m
a
g
e
i
n
t
o
th
r
ee
co
lo
r
ch
an
n
el
s
an
d
g
i
v
e
th
e
co
lo
r
th
r
es
h
o
ld
f
o
r
d
if
f
er
e
n
t
v
al
u
es
f
o
r
th
e
co
r
r
esp
o
n
d
in
g
c
h
a
n
n
el
s
.
F
ig
u
r
e
2
s
h
o
w
s
t
h
e
co
lo
r
t
h
r
es
h
o
l
d
i
m
a
g
e,
s
till
i
m
p
r
o
v
e
m
e
n
t
i
s
n
ec
e
s
s
ar
y
o
n
th
a
t
i
m
a
g
e
,
an
d
th
e
f
o
llo
w
i
n
g
s
eq
u
en
tial p
r
o
ce
s
s
d
o
es th
i
s
.
Fig
u
r
e
1
.
Ov
er
all
r
ep
r
esen
tatio
n
o
f
t
h
e
p
r
o
p
o
s
ed
m
eth
o
d
Fig
u
r
e
2
.
C
o
lo
r
th
r
esh
o
ld
i
m
a
g
e
3
.
2
.
E
nh
a
nce
m
e
nt
o
f
s
eg
m
e
nte
d i
m
a
g
e
T
h
e
s
eg
m
e
n
ted
i
m
a
g
e
i
s
a
b
in
ar
y
i
m
a
g
e
th
a
t
s
ta
n
d
s
f
o
r
1
an
d
0
an
d
d
escr
ib
es
f
o
r
th
e
w
h
i
t
e
an
d
b
lack
p
o
r
tio
n
o
f
th
e
i
m
ag
e
r
esp
ec
t
f
u
ll
y
.
Af
ter
th
e
t
h
r
es
h
o
ld
,
th
er
e
ar
e
m
an
y
n
o
i
s
es,
an
d
u
n
w
a
n
ted
p
ar
ts
o
f
h
o
les
ex
is
t
in
th
e
i
m
a
g
e.
Her
e
h
o
les
r
ep
r
esen
t
t
h
e
p
ix
e
ls
o
f
b
ac
k
g
r
o
u
n
d
w
h
ic
h
ar
e
u
n
ab
le
to
f
ill
f
r
o
m
th
e
ed
g
e
co
r
n
er
o
f
t
h
e
i
m
a
g
es
i
n
th
e
b
ac
k
g
r
o
u
n
d
,
w
h
ic
h
h
as
b
ee
n
f
ix
ed
b
y
So
ille
's
m
eth
o
d
.
Si
n
ce
t
h
e
f
ir
s
t
ti
m
e
,
s
o
m
e
u
n
w
an
ted
p
o
r
tio
n
s
s
til
l
e
x
is
t,
w
e
h
a
v
e
ap
p
lied
th
i
s
m
et
h
o
d
tw
ice
ti
m
es
f
o
r
m
o
r
e
clar
i
f
ied
r
esu
lt
s
.
T
h
e
o
u
tp
u
t
i
m
a
g
e
h
a
s
b
ee
n
s
h
ar
p
ed
u
s
in
g
u
n
s
h
ar
p
m
as
k
in
g
.
3
.
3
.
F
ilet
ing
a
nd
m
o
rp
ho
lo
g
ica
l o
pera
t
io
n
A
m
u
l
tid
i
m
e
n
s
io
n
al
i
m
ag
e
N
-
D
f
ilter
h
as
b
ee
n
e
m
p
lo
y
ed
to
r
ed
u
ce
th
e
p
r
o
b
ab
ilit
y
o
f
o
v
er
f
lo
ws
ele
m
e
n
ts
f
r
o
m
a
s
p
ec
i
f
ic
r
an
g
e
o
f
v
al
u
es
a
n
d
o
b
tain
r
o
u
n
d
v
alu
e
s
.
I
t
also
h
a
s
t
h
e
ca
p
ab
ilit
y
o
f
co
m
p
ar
i
n
g
it
w
it
h
t
h
e
tar
g
et
v
a
lu
e.
A
2
-
D
m
ed
ian
f
il
ter
h
as
b
ee
n
u
s
ed
f
o
r
g
etti
n
g
t
h
e
d
etailed
r
es
u
lt
o
n
ev
er
y
o
u
tp
u
t
p
i
x
el
to
o
b
tain
th
e
m
ed
ia
n
v
a
lu
e
s
o
f
co
r
r
esp
o
n
d
in
g
n
ei
g
h
b
o
r
h
o
o
d
p
ix
els
o
f
t
h
e
in
p
u
t
i
m
ag
e.
B
ef
o
r
e
ap
p
ly
i
n
g
t
h
e
w
ater
s
h
ed
tr
a
n
s
f
o
r
m
,
a
lev
e
l
i
s
f
ix
ed
to
r
ed
u
ce
t
h
e
v
ar
ian
ce
o
f
i
n
ter
clas
s
o
f
w
h
ite
a
n
d
b
la
ck
p
ix
e
ls
b
y
Ot
s
u
's
m
et
h
o
d
.
T
h
e
p
r
o
ce
s
s
o
f
w
a
ter
s
h
ad
e
tr
an
s
f
o
r
m
w
ill
r
ev
er
t
w
i
th
a
lev
e
led
m
atr
i
x
w
h
ich
d
is
ti
n
g
u
i
s
h
e
s
th
e
w
a
ter
r
eg
io
n
o
f
th
at
i
m
ag
e.
I
t
w
ill
d
etec
t
th
e
"
ca
tch
m
e
n
t
b
asi
n
s
"
o
r
"
w
ater
s
h
ed
r
id
g
e
lin
es"
b
y
co
n
s
id
er
in
g
th
e
i
m
a
g
e
as
t
h
e
s
u
r
f
ac
e
i
n
w
h
ic
h
s
li
g
h
t
p
i
x
els
d
escr
ib
e
h
i
g
h
s
u
p
er
io
r
ity
a
n
d
r
e
v
er
s
e
f
o
r
th
e
d
ar
k
p
ix
el
s
.
T
h
is
is
d
o
n
e
b
y
u
s
in
g
B
r
ad
le
y
'
s
m
et
h
o
d
,
w
h
ic
h
p
r
o
v
id
es
t
h
e
an
alo
g
o
u
s
o
u
tp
u
t
o
f
t
h
e
in
p
u
t
i
m
a
g
e
b
y
u
til
izin
g
1
/8
th
ti
m
e
s
o
f
t
h
e
s
ize
o
f
t
h
e
n
ei
g
h
b
o
r
h
o
o
d
i
m
a
g
e.
Fer
n
an
d
M
e
y
er
tec
h
n
iq
u
e
h
as
b
ee
n
e
m
p
lo
y
ed
to
o
b
tain
th
e
w
ater
s
h
ad
e
r
eg
io
n
s
o
f
th
e
g
i
v
en
i
m
ag
e.
I
f
i
is
th
e
o
u
tp
u
t
o
f
t
h
e
tech
n
iq
u
e,
t
h
en
i
≥0.
W
h
en
,
i=0
;
A
b
s
en
ce
o
f
w
ater
s
h
ed
r
eg
io
n
,
i=1
; I
n
itial
w
ater
s
h
ed
r
eg
io
n
,
i=2
; Sec
o
n
d
w
ater
s
h
ed
r
eg
io
n
an
d
s
o
o
n
.
T
h
e
in
f
o
r
m
a
tiv
e
p
o
r
ti
o
n
o
f
i
m
ag
e
s
h
as
b
ee
n
e
x
tr
ac
ted
,
wh
ich
is
co
m
p
le
tel
y
s
ep
ar
ated
f
r
o
m
t
h
e
b
ac
k
g
r
o
u
n
d
as
w
ell
to
t
h
e
o
t
h
er
o
b
j
ec
t
if
it
p
r
esen
ts
.
I
t
's
a
v
er
y
e
f
f
ec
ti
v
e
w
a
y
to
d
is
ti
n
g
u
i
s
h
t
h
e
s
p
ec
if
ied
o
b
j
ec
t f
r
o
m
th
e
s
p
ec
i
f
ied
b
ac
k
g
r
o
u
n
d
o
f
th
e
i
m
ag
e
an
d
a
ls
o
f
r
o
m
o
n
e
o
b
j
ec
t
to
an
o
t
h
er
[
2
1
]
.
Af
ter
co
m
p
letel
y
s
ep
ar
atin
g
t
h
e
i
n
f
o
r
m
ati
v
e
p
o
r
tio
n
o
f
th
at
i
m
ag
e
f
r
o
m
t
h
e
b
ac
k
g
r
o
u
n
d
as
w
ell
to
t
h
e
d
if
f
er
en
t
o
b
j
ec
t,
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
-
8708
S
ma
ll in
test
in
e
b
leed
in
g
d
etec
tio
n
u
s
in
g
c
o
lo
r
th
r
esh
o
ld
a
n
d
…
(
A
.
A
l.
Ma
mu
n
)
3043
Mo
r
p
h
o
lo
g
y
is
ap
p
lied
.
I
t
is
th
e
p
r
o
ce
d
u
r
e
to
p
r
o
ce
s
s
th
e
i
m
ag
e
f
o
llo
w
i
n
g
s
h
ap
e.
T
h
is
p
r
o
ce
d
u
r
e
em
p
lo
y
s
t
h
e
s
tr
u
ct
u
r
al
ele
m
e
n
t
f
r
o
m
s
tr
e
w
i
n
g
,
w
h
ic
h
w
e
ap
p
lied
to
th
at
p
ar
ticu
lar
i
m
a
g
e
an
d
w
ill
p
r
o
v
id
e
th
e
i
m
a
g
e
w
ith
an
alo
g
o
u
s
s
ize.
I
n
t
h
is
o
p
er
ati
o
n
,
ev
er
y
p
i
x
el
v
alu
e
s
f
r
o
m
t
h
e
o
u
tp
u
t i
m
a
g
e
w
ill co
m
p
ar
e
w
it
h
t
h
e
p
ix
e
l v
al
u
e
s
o
f
t
h
e
g
iv
e
n
i
m
a
g
e
as
s
o
ciate
d
w
it
h
th
e
n
ei
g
h
b
o
r
s
[
2
2
]
.
B
y
s
e
lectin
g
a
n
ap
p
r
o
p
r
iate
m
o
d
el
o
f
s
h
ap
e
a
n
d
s
ize
o
f
th
e
n
ei
g
h
b
o
r
s
,
w
e
h
a
v
e
ch
ar
ac
ter
ized
th
e
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
is
v
er
y
s
u
s
ce
p
tib
le
to
th
e
g
iv
e
n
i
m
a
g
e
i
n
a
co
n
s
id
er
ab
le
w
a
y
.
I
n
th
e
ca
s
e
o
f
th
is
o
p
er
atio
n
,
w
e
h
a
v
e
u
s
e
d
d
ilatio
n
an
d
er
o
s
io
n
w
i
t
h
th
e
s
tr
u
ctu
r
al
ele
m
e
n
t
f
r
o
m
s
tr
e
w
i
n
g
.
Her
e
th
e
d
ila
tio
n
an
d
er
o
s
io
n
ap
p
en
d
ed
an
d
eli
m
in
ated
t
h
e
p
ix
el
s
to
th
e
co
r
r
esp
o
n
d
in
g
b
o
u
n
d
ar
ies
o
f
th
e
o
b
j
ec
t.
De
p
en
d
in
g
o
n
t
h
e
p
r
o
p
er
m
o
d
el
o
f
s
h
ap
e
a
n
d
s
ize
o
f
t
h
e
s
tr
u
ctu
r
al
ele
m
en
t
s
t
h
e
n
u
m
b
er
o
f
p
i
x
els
is
ap
p
e
n
d
e
d
an
d
eli
m
i
n
ated
.
Af
ter
co
m
p
letin
g
th
e
m
o
r
p
h
o
lo
g
ica
l
o
p
er
atio
n
,
w
e
g
o
t
t
h
e
ap
p
r
o
p
r
iate
in
f
o
r
m
ati
v
e
p
o
r
tio
n
f
r
o
m
t
h
e
i
m
a
g
e
an
d
s
ee
m
to
b
e
m
o
r
e
ac
cu
r
ate
as
s
h
o
w
n
in
Fig
u
r
e
3
.
I
n
th
e
ca
s
e
o
f
d
ilatio
n
o
f
S
an
d
T
,
⊕
=
{
│
(
̂
)
∩
≠
∅
}
(1
)
Ag
ai
n
,
in
t
h
e
ca
s
e
o
f
er
o
s
io
n
o
f
S
an
d
T
,
⊖
=
{
│
(
̂
)
⊆
}
(2
)
W
h
er
e,
̂
r
ef
er
s
to
th
e
r
ep
er
cu
s
s
io
n
s
o
f
̂
s
s
tr
u
ct
u
r
e
ele
m
en
t
(
a
)
(
b
)
(
c
)
(
d
)
(
e
)
Fig
u
r
e
3
.
T
h
e
o
u
tp
u
t o
f
th
e
e
n
t
ir
e
p
r
o
ce
s
s
:
(a
)
B
lee
d
in
g
an
d
n
o
n
-
b
leed
in
g
i
m
a
g
e
(
to
p
an
d
b
o
tto
m
r
esp
ec
tf
u
ll
y
)
,
(
b
)
th
r
esh
o
ld
i
m
ag
e
,
(
c
)
en
h
a
n
ce
d
s
eg
m
e
n
ted
i
m
ag
e
,
(
d
)
af
ter
th
e
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
,
(e
)
HSV
co
lo
r
s
p
ac
e
f
o
r
th
e
ex
tr
ac
ted
i
m
ag
e.
3
.
4
.
F
e
a
t
ure
s
elec
t
io
n f
o
r
bl
ee
din
g
d
et
ec
t
io
n
T
h
e
p
r
o
ce
s
s
o
f
f
ea
tu
r
e
ex
tr
ac
tio
n
ca
n
b
e
r
ef
er
r
ed
to
as
th
e
d
im
e
n
s
io
n
al
r
etr
en
ch
m
e
n
t
th
at
ca
n
b
e
r
ep
r
esen
ted
as
a
p
ar
ticu
lar
s
ec
tio
n
o
f
i
m
ag
e
s
e
f
f
ic
ien
t
l
y
in
a
s
p
ec
i
f
ied
v
ec
to
r
o
f
f
ea
t
u
r
es.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
u
s
ed
d
is
t
in
ct
s
tati
s
tica
l
f
ea
t
u
r
es
l
ik
e
m
ea
n
,
m
o
d
e,
v
ar
ian
ce
,
en
tr
o
p
y
,
s
k
e
w
n
es
s
m
ax
i
m
a,
an
d
m
o
m
e
n
t
to
ex
tr
ac
t
t
h
e
f
ea
t
u
r
es
a
n
d
m
a
k
e
p
r
o
p
er
ca
lcu
latio
n
s
f
r
o
m
th
e
s
eg
m
e
n
ted
i
m
ag
e.
T
h
ese
c
h
ar
ac
ter
ized
f
ea
tu
r
es
ar
e
ex
tr
ac
ted
f
r
o
m
th
e
p
r
o
p
o
s
ed
HSV
co
lo
r
m
o
d
el
s
i
n
ce
th
e
HSV
co
lo
r
m
o
d
el
p
r
o
v
id
e
s
th
e
b
est
p
o
s
s
ib
l
e
r
esu
lt i
n
th
e
p
r
o
p
o
s
ed
m
e
th
o
d
o
lo
g
y
.
3
.
5
.
Q
SVM
c
l
a
s
s
if
ier
I
n
th
e
p
r
o
p
o
s
ed
tech
n
iq
u
e,
th
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SV
M)
h
as
b
ee
n
u
s
ed
f
o
r
class
i
f
ic
atio
n
.
SVM
is
a
cla
s
s
i
f
ier
tec
h
n
iq
u
e
u
s
in
g
th
e
n
o
n
p
ar
a
m
etr
ic
ar
r
an
g
e
m
e
n
t
i
n
k
er
n
el
f
u
n
ctio
n
.
W
e
u
s
e
a
q
u
ad
r
atic
SV
M
(
QSVM)
class
i
f
ier
tec
h
n
iq
u
e
f
o
r
s
ep
ar
atin
g
b
leed
in
g
an
d
n
o
n
-
b
leed
in
g
p
o
r
tio
n
.
Sa
y
,
w
e
h
av
e
co
n
s
id
er
ed
n
tr
ain
i
n
g
d
ata
b
i
,
∈
ℝ
f
o
r
i
=1
,
n
ea
c
h
eith
er
i
n
b
leed
in
g
o
r
n
o
n
-
b
leed
in
g
.
T
h
en
u
s
ed
as a
s
ep
ar
ati
n
g
r
u
le
:
≥
(3
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
4
,
A
u
g
u
s
t
2021
:
3
0
4
0
-
3048
3044
W
h
er
e,
∈
ℝ
is
a
v
ar
iab
le
w
ith
∈
ℝ
,
∈
ℝ
is
th
e
class
if
ier
p
ar
am
e
ter
s
.
Her
e,
w
e
h
a
v
e
u
s
ed
k
er
n
el
f
u
n
ct
io
n
d
en
o
ted
b
y
(
,
)
)
w
h
er
e
x
bl
m
ea
n
s
b
leed
in
g
,
an
d
x
nbl
m
ea
n
s
n
o
n
-
b
leed
in
g
,
(
,
)
=
(
.
)
;
Her
e
d
is
th
e
d
eg
r
ee
o
f
th
e
p
o
ly
n
o
m
ia
l.
No
w
,
to
g
et
ω
an
d
γ
f
r
o
m
as (
4
)
,
min
ω
∈
ℝ
N
,
γ
∈
ℝ
,
y
∈
ℝ
+
n
1
2
y
T
D
[
K
(
x
bl
,
x
n
b
l
)
K
(
x
bl
,
x
n
b
l
)
]
Dy
−
C
e
T
y
(4
)
W
h
er
e,
=
[
(
,
)
(
,
)
]
=
−
Fo
r
th
e
clas
s
if
icatio
n
,
w
e
h
a
v
e
u
s
ed
a
2
5
%
h
o
ld
o
u
t
v
al
id
atio
n
tec
h
n
iq
u
e
to
s
p
lit
th
e
s
e
s
a
m
p
les
in
to
tr
ain
i
n
g
a
n
d
test
in
g
d
ata.
7
5
%
o
f
t
h
e
i
m
a
g
e
d
ata
w
er
e
in
th
e
tr
ai
n
i
n
g
d
ata
s
et
a
n
d
2
5
%
w
er
e
i
n
t
h
e
te
s
ti
n
g
d
ataset.
Af
ter
ap
p
l
y
i
n
g
Q
SV
M
class
i
f
ier
in
t
h
e
f
ea
tu
r
e
v
e
cto
r
,
th
e
b
leed
in
g
an
d
n
o
n
-
b
leed
in
g
i
m
a
g
es
h
av
e
b
ee
n
class
i
f
ied
.
4.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
NS
I
n
ca
s
e
o
f
b
leed
in
g
d
etec
tio
n
c
o
m
m
o
n
l
y
f
ac
ed
f
o
u
r
p
o
s
s
ib
le
ev
en
t
s
t
h
at
ar
e
s
h
o
w
n
b
elo
w
:
T
r
u
e
p
o
s
itiv
e
(
TP
);
A
ct
u
all
y
,
b
leed
in
g
i
m
ag
e
s
T
r
u
e
n
eg
ativ
e
(
TN
);
A
ct
u
all
y
,
n
o
n
-
b
leed
in
g
i
m
ag
e
s
Fals
e
p
o
s
iti
v
e
(
FP
);
A
ct
u
all
y
,
b
leed
in
g
b
u
t d
etec
t a
s
n
o
n
-
b
le
ed
in
g
i
m
a
g
es
Fals
e
n
e
g
ati
v
e
(
FN
);
A
ct
u
all
y
,
n
o
n
-
b
leed
in
g
b
u
t r
ec
o
g
n
ize
as
b
leed
in
g
i
m
ag
e
s
T
h
e
o
n
l
y
ac
cu
r
ac
y
d
o
es
n
o
t
p
r
o
v
id
e
th
e
r
eliab
l
y
o
f
a
m
e
th
o
d
.
A
ls
o
n
ee
d
ed
s
o
m
e
o
t
h
er
p
ar
am
eter
s
s
u
c
h
as se
n
s
iti
v
it
y
,
s
p
ec
if
ic
it
y
,
p
r
ec
is
io
n
,
F1
s
co
r
e,
an
d
n
eg
at
iv
e
p
r
ed
icted
v
alu
e
.
to
j
u
s
ti
f
y
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
a
tech
n
iq
u
e.
T
h
e
p
r
o
p
o
s
ed
m
e
th
o
d
h
as
ac
h
ie
v
ed
th
e
b
es
t
p
o
s
s
ib
le
r
es
u
lt
o
f
ac
cu
r
ac
y
9
5
.
8
%,
s
en
s
iti
v
it
y
9
5
%,
s
p
ec
if
icit
y
9
7
%,
p
r
ec
is
io
n
8
0
%,
n
eg
ati
v
e
p
r
ed
icted
v
alu
e
9
9
%
an
d
F1
s
co
r
e
8
6
.
9
%,
d
e
p
icted
in
Fig
u
r
e
4
.
Ag
ai
n
,
Fi
g
u
r
e
5
s
h
o
w
s
t
h
e
p
er
f
o
r
m
an
ce
s
o
f
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
in
f
o
u
r
d
if
f
er
en
t
co
lo
r
s
p
ac
es
lik
e
H
SV,
R
GB
,
L
*
a
*
b
*
,
an
d
Y
C
b
C
r
.
I
t
p
r
o
v
id
es
ev
id
en
ce
th
at
HS
V
co
lo
r
s
p
ac
e
p
r
o
v
id
es
th
e
b
est
p
o
s
s
ib
le
r
esu
lt
ex
ce
p
t
f
o
r
p
r
ec
is
io
n
,
h
i
g
h
er
i
n
R
GB
co
lo
r
s
p
ac
e.
B
u
t
co
n
s
id
er
in
g
th
e
h
i
g
h
er
v
al
u
es
o
f
o
th
er
p
er
f
o
r
m
an
c
e
p
ar
am
eter
s
,
HSV
co
lo
r
s
p
ac
e
h
as
b
ee
n
p
r
o
p
o
s
ed
.
Fu
r
th
e
r
m
o
r
e,
Fig
u
r
e
6
s
h
o
w
s
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
in
f
o
u
r
d
is
t
in
ct
t
y
p
e
s
o
f
cla
s
s
i
f
ier
s
,
s
u
c
h
as
Fin
e
Ga
u
s
s
ia
n
S
VM
,
W
KNN,
C
SVM,
a
n
d
QSVM,
f
o
r
s
elec
ti
n
g
t
h
e
p
r
o
p
er
class
if
ier
.
B
y
co
m
p
ar
i
n
g
t
h
ese
f
o
u
r
class
i
f
ier
s
,
QSV
M
is
th
e
m
o
s
t
s
u
itab
l
e
class
i
f
ier
f
o
r
b
leed
in
g
d
etec
tio
n
,
co
n
s
id
er
in
g
t
h
e
p
r
o
p
o
s
ed
m
eth
o
d
p
r
o
v
in
g
h
i
g
h
er
p
er
f
o
r
m
an
ce
r
esu
l
ts
.
Fig
u
r
e
4
.
Ov
er
all
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
I
n
th
e
p
r
o
p
o
s
ed
tech
n
iq
u
e,
th
r
ee
s
tep
s
h
a
v
e
b
ee
n
ap
p
lied
,
lik
e
(
1
)
C
o
lo
r
th
r
esh
o
ld
,
(
2
)
E
n
h
an
ce
m
e
n
t
o
f
s
eg
m
e
n
ted
i
m
ag
e
s
an
d
(
3
)
Fil
ter
in
g
a
n
d
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
b
ef
o
r
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
h
as
g
r
ad
u
al
l
y
i
n
cr
ea
s
e
d
in
co
n
s
ec
u
t
iv
e
t
h
ese
t
h
r
ee
s
t
ep
s
,
w
h
ich
p
r
o
v
id
e
th
e
w
o
r
t
h
i
n
es
s
o
f
th
e
th
r
ee
s
t
a
g
e
s
.
T
h
e
p
er
f
o
r
m
a
n
ce
in
th
e
s
u
cc
es
s
iv
e
t
h
r
ee
s
tep
s
h
as
b
ee
n
s
h
o
w
n
i
n
Fig
u
r
e
7
in
w
h
ic
h
1
,
2
an
d
3
r
ep
r
esen
t
t
h
e
co
r
r
esp
o
n
d
in
g
s
tep
s
,
an
d
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
h
a
s
ac
h
ie
v
ed
h
ig
h
er
p
er
f
o
r
m
a
n
ce
i
n
th
e
la
s
t
p
h
a
s
e
o
f
f
ilter
i
n
g
an
d
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
S
ma
ll in
test
in
e
b
leed
in
g
d
etec
tio
n
u
s
in
g
c
o
lo
r
th
r
esh
o
ld
a
n
d
…
(
A
.
A
l.
Ma
mu
n
)
3045
Fig
u
r
e
5
.
P
er
f
o
r
m
a
n
ce
r
esu
lt
o
f
th
e
p
r
o
p
o
s
ed
m
e
th
o
d
b
y
v
ar
y
in
g
d
i
s
ti
n
ct
co
lo
r
m
o
d
els
Fig
u
r
e
6
.
P
er
f
o
r
m
a
n
ce
r
esu
lt
o
f
th
e
p
r
o
p
o
s
ed
m
e
th
o
d
b
y
v
ar
y
in
g
d
i
s
ti
n
ct
clas
s
if
ier
s
Fig
u
r
e
7
.
P
er
f
o
r
m
a
n
ce
r
esu
lt
s
in
th
r
ee
co
n
s
ec
u
tiv
e
s
tep
s
o
f
t
h
e
p
r
o
p
o
s
ed
m
eth
o
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
4
,
A
u
g
u
s
t
2021
:
3
0
4
0
-
3048
3046
T
h
o
u
g
h
r
ev
o
l
u
tio
n
ar
y
w
o
r
k
s
h
av
e
b
ee
n
i
m
p
le
m
e
n
ted
f
o
r
d
etec
tin
g
th
e
b
leed
in
g
p
o
r
tio
n
,
th
e
p
r
o
p
o
s
ed
m
eth
o
d
i
s
u
n
iq
u
e
a
n
d
also
e
n
r
ich
e
s
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
is
r
e
s
ea
r
ch
f
ield
.
A
co
m
p
ar
ab
ilit
y
s
tu
d
y
b
et
w
ee
n
th
e
e
x
i
s
ti
n
g
m
et
h
o
d
s
an
d
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
ar
e
p
r
esen
ted
in
1
.
Fro
m
T
ab
le
1
,
it
is
v
is
u
alize
d
th
a
t
th
e
p
r
o
p
o
s
ed
tech
n
iq
u
e
i
s
a
n
i
m
p
r
o
v
ed
ed
itio
n
o
f
t
h
e
b
leed
in
g
d
etec
tio
n
r
e
s
ea
r
ch
f
ield
i
n
ter
m
s
o
f
ac
c
u
r
ac
y
an
d
s
en
s
iti
v
it
y
co
m
p
ar
ed
w
i
th
th
e
ex
i
s
ti
n
g
w
o
r
k
.
T
h
o
u
g
h
Ku
n
d
u
et
a
l.
[
2
0
]
ex
a
m
in
ed
2
3
0
0
co
lo
r
im
a
g
es
f
r
o
m
W
C
E
f
o
r
e
v
alu
a
tin
g
th
eir
b
le
ed
in
g
d
etec
t
io
n
al
g
o
r
ith
m
,
2
3
9
3
i
m
ag
e
s
h
av
e
b
ee
n
e
x
a
m
i
n
ed
in
t
h
i
s
p
r
o
p
o
s
ed
m
et
h
o
d
,
w
h
ich
is
a
v
ailab
le
i
n
[
2
3
]
.
I
n
ad
d
itio
n
,
th
is
p
r
o
p
o
s
ed
m
e
th
o
d
also
a
n
al
y
s
is
w
it
h
s
o
m
e
o
th
er
ad
d
itio
n
al
p
er
f
o
r
m
a
n
ce
p
ar
a
m
eter
s
li
k
e
p
r
ec
is
io
n
,
F1
s
co
r
e,
an
d
n
eg
ativ
e
-
p
r
ed
icted
v
alu
e.
I
n
a
n
u
t
s
h
ell,
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
is
an
ac
cu
r
ate
m
o
d
el
o
f
b
leed
in
g
d
etec
tio
n
.
T
ab
le
1
.
P
er
f
o
r
m
a
n
ce
co
m
p
ar
i
s
o
n
w
it
h
d
is
ti
n
ct
co
lo
r
m
o
d
els
M
e
t
h
o
d
s
A
c
c
u
r
a
c
y
S
e
n
si
t
i
v
i
t
y
S
p
e
c
i
f
i
c
i
t
y
U
n
i
f
o
r
m L
B
P
[
5
]
9
1
.
5
7
9
.
2
5
9
4
.
5
6
Tw
o
f
o
l
d
S
y
st
e
m
[
9
]
9
5
.
7
5
92
9
6
.
5
B
i
n
a
r
y
f
e
a
t
u
r
e
v
e
c
t
o
r
[
2
4
]
91
9
3
.
1
2
8
8
.
3
9
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
[
2
5
]
9
0
.
9
2
-
-
Pr
o
p
o
sed
m
e
t
h
o
d
9
5
.
8
95
97
Fin
all
y
,
w
e
w
a
n
t
to
s
a
y
t
h
at
th
e
p
r
o
p
o
s
ed
tech
n
iq
u
e
f
o
r
b
lee
d
in
g
d
etec
tio
n
p
r
o
v
id
es
t
h
e
o
u
tp
er
f
o
r
m
s
to
o
th
er
s
.
I
n
[
2
0
]
,
th
e
y
o
f
f
er
a
b
leed
in
g
d
etec
tio
n
tec
h
n
iq
u
e
u
s
i
n
g
2
3
0
0
W
C
E
im
a
g
es,
b
u
t
w
e
h
av
e
u
s
ed
2
3
9
3
,
av
ailab
le
o
n
t
h
e
w
eb
s
ite
[
2
6
]
.
T
h
e
clar
if
icatio
n
o
f
t
h
e
s
p
ec
i
f
ied
s
e
g
m
e
n
tat
io
n
tec
h
n
iq
u
e
o
r
p
r
o
ce
s
s
in
g
i
s
also
p
o
s
s
ib
le
f
o
r
g
iv
in
g
m
o
r
e
r
elia
b
ilit
y
to
o
u
r
p
r
o
p
o
s
ed
m
eth
o
d
.
T
h
e
co
m
p
ar
is
o
n
b
et
w
ee
n
o
u
r
p
r
o
p
o
s
ed
m
et
h
o
d
an
d
th
e
ex
is
ti
n
g
m
e
th
o
d
s
[
5
,
9
,
2
4
,
2
5
]
a
r
e
s
h
o
w
n
in
T
ab
le
1
.
5.
CO
NCLU
SI
O
N
A
u
n
iq
u
e
m
et
h
o
d
h
as
b
ee
n
p
r
o
p
o
s
ed
in
th
is
r
esear
ch
ar
ticle
in
w
h
ic
h
th
e
co
lo
r
th
r
esh
o
ld
an
d
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
h
a
v
e
b
ee
n
ap
p
lied
to
d
etec
t
th
e
b
leed
in
g
in
W
C
E
i
m
ag
e
s
.
I
n
itiall
y
,
th
e
co
lo
r
th
r
es
h
o
ld
i
m
ag
e
s
h
av
e
b
ee
n
e
n
h
a
n
ce
d
to
e
n
li
g
h
te
n
t
h
e
i
n
f
o
r
m
ati
v
e
p
o
r
tio
n
in
t
h
e
i
m
a
g
e
f
r
a
m
es.
A
f
ter
t
h
at,
w
e
ap
p
ly
t
h
e
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
to
p
u
r
i
f
y
t
h
e
ac
t
u
al
b
leed
i
n
g
p
o
r
tio
n
i
n
t
h
o
s
e
i
m
a
g
es.
Fi
n
all
y
,
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
h
as
ac
h
iev
ed
ac
c
u
r
ac
y
9
5
.
8
%,
s
e
n
s
iti
v
it
y
9
5
%,
s
p
ec
if
icit
y
9
7
%,
p
r
ec
is
io
n
8
0
%,
n
e
g
ati
v
e
p
r
ed
icted
v
alu
e
9
9
%
a
n
d
F1
s
co
r
e
8
6
.
9
%
b
y
ex
a
m
i
n
ed
th
e
QS
VM
c
lass
i
f
ier
f
r
o
m
s
tati
s
tical
f
ea
t
u
r
e
v
ec
to
r
w
it
h
2
5
%
h
o
ld
o
u
t
v
alid
atio
n
,
w
h
ic
h
o
u
t
p
er
f
o
r
m
s
s
o
m
e
o
f
th
e
e
x
is
tin
g
r
esear
ch
o
f
b
leed
in
g
d
etec
ti
o
n
.
I
t
is
o
p
ti
m
is
ti
c
ab
o
u
t
h
av
i
n
g
a
s
i
g
n
if
ica
n
t
i
m
p
ac
t
o
n
th
is
r
esear
ch
o
u
tp
u
t
in
th
e
b
leed
i
n
g
d
etec
tio
n
te
ch
n
iq
u
e.
T
h
e
f
u
t
u
r
e
p
lan
e
is
to
i
m
p
r
o
v
i
s
e
m
o
r
e
ad
v
an
ce
d
f
ea
tu
r
e
s
an
d
clas
s
if
ier
s
to
id
en
tify
th
e
b
leed
in
g
p
o
r
tio
n
m
o
r
e
ef
f
icie
n
tl
y
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
e
r
esear
ch
d
escr
ib
ed
in
th
i
s
p
ap
er
w
as
s
u
p
p
o
r
ted
b
y
M
ala
y
s
ia
n
Mi
n
is
tr
y
o
f
Hi
g
h
er
E
d
u
ca
tio
n
(
MO
HE
)
f
o
r
Fu
n
d
a
m
e
n
tal
R
e
s
ea
r
ch
Gr
an
t Sc
h
e
m
e
(
FR
G
S/1
/
2
0
1
8
/
T
K0
3
/MM
U/0
2
/1
)
.
RE
F
E
R
E
NC
E
S
[1
]
G
.
G
.
Ka
p
lan
a
n
d
S
.
C.
Ng
,
“
Un
d
e
rsta
n
d
i
n
g
a
n
d
P
re
v
e
n
ti
n
g
th
e
G
lo
b
a
l
I
n
c
re
a
se
o
f
In
f
la
m
m
a
to
r
y
B
o
w
e
l
Dise
a
se
,
”
Ga
stro
e
n
ter
o
l
o
g
y
,
v
o
l.
1
5
2
,
n
o
.
2
,
p
p
.
3
1
3
-
3
2
1
,
2
0
1
7
,
d
o
i:
1
0
.
1
0
5
3
/
j.
g
a
stro
.
2
0
1
6
.
1
0
.
0
2
0
[2
]
M
.
S
.
H
o
ss
a
in
,
A
.
A
l
M
a
m
u
n
,
M
.
G
.
Ha
sa
n
,
a
n
d
M
.
M
.
H
o
ss
a
in
,
“
Eas
y
S
c
h
e
m
e
f
o
r
Ulc
e
r
De
t
e
c
ti
o
n
i
n
W
irele
ss
Ca
p
su
le
En
d
o
sc
o
p
y
Im
a
g
e
s,”
in
1
st
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ad
v
a
n
c
e
s
in
S
c
ien
c
e
,
En
g
in
e
e
rin
g
a
n
d
Ro
b
o
ti
c
s
T
e
c
h
n
o
l
o
g
y
2
0
1
9
,
ICAS
ER
T
2
0
1
9
,
M
a
y
2
0
1
9
,
p
p
.
1
-
5
,
d
o
i:
1
0
.
1
1
0
9
/ICA
S
ERT
.
2
0
1
9
.
8
9
3
4
5
1
0
.
[3
]
A
.
A
l
M
a
m
u
n
,
M
.
S
.
Ho
ss
a
in
,
M
.
M
.
Ho
ss
a
in
,
a
n
d
M
.
G
.
Ha
sa
n
,
“
Disc
re
ti
o
n
W
a
y
f
o
r
Blee
d
i
n
g
De
tec
ti
o
n
in
W
irele
ss
Ca
p
su
le
En
d
o
sc
o
p
y
I
m
a
g
e
s,”
in
1
st
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ad
v
a
n
c
e
s
in
S
c
ien
c
e
,
E
n
g
i
n
e
e
rin
g
a
n
d
Ro
b
o
ti
c
s T
e
c
h
n
o
l
o
g
y
2
0
1
9
,
ICAS
ER
T
2
0
1
9
,
2
0
1
9
,
d
o
i:
1
0
.
1
1
0
9
/IC
A
S
ER
T
.
2
0
1
9
.
8
9
3
4
5
8
9
.
[4
]
T
.
G
h
o
sh
,
S
.
A
.
F
a
tt
a
h
,
a
n
d
K.
A
.
Wah
id
,
“
A
u
to
m
a
ti
c
Co
m
p
u
ter
A
id
e
d
Blee
d
in
g
De
tec
ti
o
n
S
c
h
e
m
e
f
o
r
W
irele
ss
Ca
p
su
le
En
d
o
sc
o
p
y
(
W
CE)
V
id
e
o
Ba
se
d
o
n
Hig
h
e
r
a
n
d
L
o
w
e
r
O
rd
e
r
S
tatisti
c
a
l
F
e
a
tu
re
s
in
a
Co
m
p
o
site
Co
lo
r,
”
J
.
M
e
d
.
Bi
o
l
.
E
n
g
.
,
v
o
l.
3
8
,
n
o
.
3
,
p
p
.
4
8
2
-
4
9
6
,
2
0
1
8
,
d
o
i:
1
0
.
1
0
0
7
/s
4
0
8
4
6
-
0
1
7
-
0
3
1
8
-
1
.
[5
]
J.
M
.
Bu
sc
a
g
li
a
e
t
a
l.
,
“
P
e
rf
o
rm
a
n
c
e
Ch
a
ra
c
t
e
risti
c
s
o
f
th
e
S
u
sp
e
c
ted
Blo
o
d
In
d
ica
to
r
F
e
a
tu
re
in
Ca
p
su
le
En
d
o
sc
o
p
y
A
c
c
o
rd
in
g
to
In
d
ica
t
io
n
f
o
r
S
tu
d
y
,
”
Cli
n
.
Ga
stro
e
n
ter
o
l.
He
p
a
t
o
l.
,
v
o
l.
6
,
n
o
.
3
,
p
p
.
2
9
8
–
3
0
1
,
2
0
0
8
,
d
o
i:
1
0
.
1
0
1
6
/j
.
c
g
h
.
2
0
0
7
.
1
2
.
0
2
9
.
[6
]
P
.
S
iv
a
k
u
m
a
r
a
n
d
B.
M
.
Ku
m
a
r,
“
A
n
o
v
e
l
m
e
th
o
d
to
d
e
tec
t
b
lee
d
in
g
f
ra
m
e
a
n
d
re
g
io
n
in
w
irele
ss
c
a
p
su
le
e
n
d
o
sc
o
p
y
v
id
e
o
,
”
Clu
ste
r Co
mp
u
t.
,
v
o
l.
2
2
,
n
o
.
5
,
p
p
.
1
2
2
1
9
-
1
2
2
2
5
,
S
e
p
.
2
0
1
9
,
d
o
i:
1
0
.
1
0
0
7
/s
1
0
5
8
6
-
0
1
7
-
1
5
8
4
-
y
.
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
-
8708
S
ma
ll in
test
in
e
b
leed
in
g
d
etec
tio
n
u
s
in
g
c
o
lo
r
th
r
esh
o
ld
a
n
d
…
(
A
.
A
l.
Ma
mu
n
)
3047
[7
]
K.
P
o
g
o
re
lo
v
e
t
a
l
.
,
“
Blee
d
i
n
g
d
e
tec
ti
o
n
i
n
w
irele
ss
c
a
p
su
le
e
n
d
o
sc
o
p
y
v
id
e
o
s
-
Co
lo
r
v
e
rsu
s
tex
tu
re
f
e
a
tu
re
s,”
J
.
Ap
p
l.
Cli
n
.
M
e
d
.
Ph
y
s.,
v
o
l.
2
0
,
n
o
.
8
,
p
p
.
1
4
1
-
1
5
4
,
A
u
g
.
2
0
1
9
,
d
o
i:
1
0
.
1
0
0
2
/ac
m
2
.
1
2
6
6
2
.
[8
]
A
.
R.
Ha
ss
a
n
a
n
d
M
.
A
.
Ha
q
u
e
,
“
Co
m
p
u
ter
-
a
id
e
d
g
a
stro
in
tes
ti
n
a
l
h
e
m
o
rrh
a
g
e
d
e
tec
ti
o
n
i
n
w
irele
ss
c
a
p
su
le
e
n
d
o
sc
o
p
y
v
id
e
o
s,”
Co
mp
u
t.
M
e
th
o
d
s
Pro
g
r
a
ms
Bi
o
me
d
.
,
v
o
l.
1
2
2
,
n
o
.
3
,
p
p
.
3
4
1
-
3
5
3
,
2
0
1
5
,
d
o
i:
1
0
.
1
0
1
6
/j
.
c
m
p
b
.
2
0
1
5
.
0
9
.
0
0
5
.
[9
]
Y.
Yu
a
n
,
B.
L
i,
a
n
d
M
.
Q.
H.
M
e
n
g
,
“
Blee
d
in
g
F
ra
m
e
a
n
d
Re
g
io
n
De
tec
ti
o
n
in
th
e
W
irele
ss
Ca
p
su
le
En
d
o
sc
o
p
y
V
id
e
o
,
”
IEE
E
J
.
Bi
o
me
d
.
He
a
l.
In
fo
rm
a
ti
c
s,
v
o
l.
2
0
,
n
o
.
2
,
p
p
.
6
2
4
-
6
3
0
,
M
a
r.
2
0
1
6
,
d
o
i:
1
0
.
1
1
0
9
/JBHI.2
0
1
5
.
2
3
9
9
5
0
2
.
[1
0
]
T
.
G
h
o
sh
,
S
.
K.
Ba
sh
a
r,
S
.
A
.
F
a
tt
a
h
,
C
.
S
h
a
h
n
a
z
,
a
n
d
K.
A
.
W
a
h
id
,
“
A
n
a
u
to
m
a
ti
c
b
lee
d
in
g
d
e
tec
ti
o
n
sc
h
e
m
e
in
w
irele
ss
c
a
p
su
le
e
n
d
o
sc
o
p
y
b
a
se
d
o
n
sta
ti
stica
l
f
e
a
tu
re
s
in
h
u
e
sp
a
c
e
,
”
2
0
1
4
1
7
th
In
t.
Co
n
f.
Co
mp
u
t.
In
f
.
T
e
c
h
n
o
l
.
ICCIT
2
0
1
4
,
p
p
.
3
5
4
-
3
5
7
,
2
0
0
3
,
d
o
i:
1
0
.
1
1
0
9
/ICCIT
e
c
h
n
.
2
0
1
4
.
7
0
7
3
1
0
0
.
[1
1
]
T.
G
h
o
sh
e
t
a
l.
,
“
A
n
a
u
to
m
a
ti
c
b
lee
d
in
g
d
e
tec
ti
o
n
tec
h
n
iq
u
e
in
w
irele
ss
c
a
p
su
le en
d
o
sc
o
p
y
f
ro
m
re
g
io
n
o
f
in
tere
st,”
In
t.
C
o
n
f
.
Dig
i
t.
S
ig
n
a
l
Pro
c
e
ss
.
DS
P,
v
o
l.
2
0
1
5
-
S
e
p
te,
p
p
.
1
2
9
3
-
1
2
9
7
,
2
0
1
5
,
d
o
i:
1
0
.
1
1
0
9
/ICD
S
P
.
2
0
1
5
.
7
2
5
2
0
9
0
.
[1
2
]
T
.
G
h
o
sh
,
S
.
K.
Ba
sh
a
r,
M
.
S
.
A
l
a
m
,
K.
W
a
h
id
,
a
n
d
S
.
A
.
F
a
tt
a
h
,
“
A
sta
ti
stica
l
f
e
a
tu
re
b
a
se
d
n
o
v
e
l
m
e
th
o
d
t
o
d
e
tec
t
b
lee
d
in
g
in
w
irele
ss
c
a
p
su
le
e
n
d
o
sc
o
p
y
i
m
a
g
e
s,”
2
0
1
4
I
n
t.
Co
n
f.
In
f
o
rm
a
ti
c
s,
El
e
c
tro
n
.
Vi
si
o
n
,
ICIEV
2
0
1
4
,
p
p
.
2
–
5
,
2
0
1
4
,
d
o
i:
1
0
.
1
1
0
9
/ICIE
V
.
2
0
1
4
.
6
8
5
0
7
7
7
.
[1
3
]
T
.
G
h
o
sh
,
S
.
A
.
F
a
tt
a
h
,
C.
S
h
a
h
n
a
z
,
a
n
d
K.
A
.
Wah
id
,
“
A
n
a
u
to
m
a
t
ic b
lee
d
in
g
d
e
tec
ti
o
n
sc
h
e
m
e
in
wire
les
s c
a
p
su
le
e
n
d
o
sc
o
p
y
b
a
se
d
o
n
h
isto
g
ra
m
o
f
a
n
RG
B
-
in
d
e
x
e
d
im
a
g
e
,
”
in
2
0
1
4
3
6
th
An
n
u
a
l
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
f
th
e
IEE
E
En
g
i
n
e
e
rin
g
i
n
M
e
d
icin
e
a
n
d
B
io
l
o
g
y
S
o
c
iety
,
EM
BC
2
0
1
4
,
2
0
1
4
,
p
p
.
4
6
8
3
-
4
6
8
6
,
d
o
i:
1
0
.
1
1
0
9
/E
M
BC
.
2
0
1
4
.
6
9
4
4
6
6
9
.
[1
4
]
A
.
A
l
M
a
m
u
n
a
n
d
M
.
S
.
Ho
ss
a
in
,
“
Ulc
e
r
De
tec
ti
o
n
i
n
Im
a
g
e
Co
n
v
e
rted
f
ro
m
V
id
e
o
F
o
o
tag
e
o
f
Wi
re
les
s
Ca
p
su
le
En
d
o
sc
o
p
y
,
”
in
1
st
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ad
v
a
n
c
e
s
in
S
c
ien
c
e
,
En
g
in
e
e
rin
g
a
n
d
Ro
b
o
ti
c
s
T
e
c
h
n
o
l
o
g
y
2
0
1
9
,
ICAS
ER
T
2
0
1
9
,
2
0
1
9
,
d
o
i:
1
0
.
1
1
0
9
/ICA
S
ERT
.
2
0
1
9
.
8
9
3
4
5
9
7
.
[1
5
]
S
.
Na
rji
m
,
A
.
A
l
M
a
m
u
n
,
a
n
d
D.
Ku
n
d
u
,
“
Dia
g
n
o
sis
o
f
a
c
u
te
ly
m
p
h
o
b
las
ti
c
le
u
k
e
m
ia
f
ro
m
m
icro
s
c
o
p
ic
im
a
g
e
o
f
p
e
rip
h
e
ra
l
b
lo
o
d
sm
e
a
r
u
sin
g
i
m
a
g
e
p
ro
c
e
ss
in
g
tec
h
n
iq
u
e
,
”
in
L
e
c
t
u
re
No
tes
o
f
th
e
In
sti
tu
te
fo
r
C
o
mp
u
ter
S
c
ien
c
e
s,
S
o
c
ia
l
-
In
f
o
rm
a
ti
c
s
a
n
d
T
e
lec
o
m
mu
n
ica
t
io
n
s
En
g
i
n
e
e
rin
g
,
L
NIC
S
T
,
v
o
l.
3
2
5
L
NICST
,
2
0
2
0
,
p
p
.
5
1
5
–
5
2
6
,
d
o
i:
1
0
.
1
0
0
7
/9
7
8
-
3
-
0
3
0
-
5
2
8
5
6
-
0
_
4
1
.
[1
6
]
A
.
A
l
M
a
m
u
n
,
P
.
P
.
Em
,
T
.
G
h
o
sh
,
M
.
M
.
Ho
ss
a
in
,
M
.
G
.
Ha
s
a
n
,
a
n
d
M
.
G
.
S
a
d
e
q
u
e
,
“
Blee
d
i
n
g
re
c
o
g
n
it
i
o
n
tec
h
n
iq
u
e
i
n
w
irele
ss
c
a
p
su
le
e
n
d
o
sc
o
p
y
ima
g
e
s
u
sin
g
f
u
z
z
y
lo
g
ic
a
n
d
p
rin
c
i
p
a
l
c
o
m
p
o
n
e
n
t
a
n
a
ly
sis
,
”
In
t.
J
.
El
e
c
tr
.
Co
mp
u
t
.
E
n
g
.
,
v
o
l.
1
1
,
n
o
.
3
,
p
.
2
6
8
8
,
Ju
n
.
2
0
2
1
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jec
e
.
v
1
1
i3
.
p
p
2
6
8
8
-
2
6
9
5
.
[1
7
]
A
.
A
l
M
a
m
u
n
,
M
.
S
.
H
o
ss
a
in
,
M
.
E.
K
h
a
ll
il
,
A
.
T
a
h
a
b
il
d
e
r,
T
.
K.
Da
s,
a
n
d
R.
Isla
m
,
“
Co
n
v
e
n
ien
t
W
a
y
to
De
tec
t
Ulc
e
r
in
W
irele
ss
Ca
p
su
le
En
d
o
sc
o
p
y
th
ro
u
g
h
F
u
z
z
y
L
o
g
i
c
T
e
c
h
n
i
q
u
e
,
”
i
n
2
0
2
0
I
EE
E
Reg
io
n
1
0
S
y
mp
o
si
u
m
,
T
ENS
Y
M
P
2
0
2
0
,
Ju
n
.
2
0
2
0
,
p
p
.
8
8
0
-
8
8
3
,
d
o
i:
1
0
.
1
1
0
9
/T
ENS
YM
P
5
0
0
1
7
.
2
0
2
0
.
9
2
3
1
0
0
4
.
[1
8
]
M
.
S
.
Ho
ss
a
in
,
A
.
A
l
M
a
m
u
n
,
T
.
G
h
o
sh
,
M
.
G
.
Ha
sa
n
,
M
.
M
.
Ho
ss
a
in
,
a
n
d
A
.
T
a
h
a
b
il
d
e
r,
“
Ul
c
e
r
d
e
tec
ti
o
n
i
n
w
irele
ss
c
a
p
su
le
e
n
d
o
sc
o
p
y
u
sin
g
lo
c
a
ll
y
c
o
m
p
u
ted
f
e
a
tu
re
s,”
in
L
e
c
tu
re
N
o
tes
o
f
th
e
I
n
stit
u
t
e
fo
r
Co
m
p
u
ter
S
c
ien
c
e
s,
S
o
c
ia
l
-
I
n
f
o
rm
a
ti
c
s
a
n
d
T
e
lec
o
mm
u
n
ica
ti
o
n
s
E
n
g
i
n
e
e
rin
g
,
L
NICS
T
,
v
o
l
.
3
2
5
L
NICST
,
2
0
2
0
,
p
p
.
4
9
1
-
5
0
2
,
d
o
i:
1
0
.
1
0
0
7
/9
7
8
-
3
-
0
3
0
-
5
2
8
5
6
-
0
_
3
9
.
[1
9
]
V
.
C
h
a
risis,
L
.
Ha
d
ji
leo
n
ti
a
d
is,
a
n
d
G
.
S
e
rg
iad
is,
“
En
h
a
n
c
e
d
Ulc
e
r
Re
c
o
g
n
it
io
n
f
ro
m
Ca
p
su
le
En
d
o
sc
o
p
ic
Im
a
g
e
s
Us
in
g
T
e
x
tu
re
A
n
a
l
y
sis,”
in
Ne
w
A
d
v
a
n
c
e
s in
th
e
Ba
sic
a
n
d
Cli
n
ica
l
G
a
stro
e
n
tero
lo
g
y
,
In
T
e
c
h
,
2
0
1
2
.
[2
0
]
A
.
K.
Ku
n
d
u
,
S
.
A
.
F
a
tt
a
h
,
a
n
d
M
.
N.
Rizv
e
,
“
A
n
a
u
to
m
a
ti
c
b
l
e
e
d
in
g
f
ra
m
e
a
n
d
re
g
io
n
d
e
tec
ti
o
n
sc
h
e
m
e
f
o
r
w
irele
ss
c
a
p
su
le
e
n
d
o
sc
o
p
y
v
id
e
o
s
b
a
se
d
o
n
i
n
terp
lan
e
i
n
ten
sity
v
a
riatio
n
p
r
o
f
il
e
in
n
o
rm
a
li
z
e
d
RGB
c
o
lo
r
s
p
a
c
e
,
”
J
.
He
a
lt
h
c
.
E
n
g
.
,
v
o
l
.
2
0
1
8
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
1
8
/
9
4
2
3
0
6
2
.
[2
1
]
F
.
M
e
y
e
r,
“
T
o
p
o
g
ra
p
h
ic
d
istan
c
e
a
n
d
w
a
ters
h
e
d
li
n
e
s,”
S
ig
n
a
l
Pro
c
e
ss
in
g
,
v
o
l.
3
8
,
n
o
.
1
,
p
p
.
1
1
3
-
1
2
5
,
1
9
9
4
,
d
o
i:
1
0
.
1
0
1
6
/0
1
6
5
-
1
6
8
4
(9
4
)9
0
0
6
0
-
4
.
[2
2
]
R.
C.
G
o
n
z
a
lez
,
R.
E.
W
o
o
d
s,
a
n
d
S
.
L
.
Ed
d
in
s,
“
Dig
it
a
l_
Im
a
g
e
_
P
r
o
c
e
ss
in
g
_
Us
in
g
_
M
a
tl
a
b
(B
o
o
k
ZZ
.
o
rg
).
p
d
f
,
”
2
0
0
4
.
[2
3
]
“
Da
ta
m
in
in
g
v
ia
m
a
th
e
m
a
ti
c
a
l
p
r
o
g
ra
m
m
in
g
a
n
d
m
a
c
h
in
e
lea
rn
in
g
|
G
u
id
e
b
o
o
k
s
,
”
.
[2
4
]
S
.
Zh
o
u
,
X
.
S
o
n
g
,
M
.
A
.
S
id
d
iq
u
e
,
J.
Xu
,
a
n
d
P
.
Zh
o
u
,
“
Blee
d
in
g
d
e
tec
ti
o
n
i
n
w
irele
ss
c
a
p
su
le
e
n
d
o
sc
o
p
y
i
m
a
g
e
s
b
a
se
d
o
n
b
i
n
a
ry
f
e
a
tu
re
v
e
c
to
r,
”
in
5
t
h
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
In
tell
ig
e
n
t
Co
n
tro
l
a
n
d
In
fo
rm
a
ti
o
n
Pro
c
e
ss
in
g
,
ICICIP
2
0
1
4
-
Pro
c
e
e
d
i
n
g
s,
Au
g
.
2
0
1
5
,
p
p
.
2
9
–
3
3
,
d
o
i
:
1
0
.
1
1
0
9
/IC
ICIP
.
2
0
1
4
.
7
0
1
0
3
0
3
.
[2
5
]
O.
Bc
h
ir,
M
.
M
.
Be
n
Ism
a
il
,
a
n
d
N.
A
lZ
a
h
ra
n
i,
“
M
u
lt
i
p
le
b
lee
d
in
g
d
e
tec
ti
o
n
i
n
w
irele
ss
c
a
p
su
le
e
n
d
o
sc
o
p
y
,
”
S
ig
n
a
l
,
Ima
g
e
Vi
d
e
o
Pro
c
e
ss
.
,
v
o
l
.
1
3
,
n
o
.
1
,
p
p
.
1
2
1
–
1
2
6
,
F
e
b
.
2
0
1
9
,
d
o
i:
1
0
.
1
0
0
7
/s1
1
7
6
0
-
0
1
8
-
1
3
3
6
-
3
.
[2
6
]
“
T
h
e
c
a
p
su
le en
d
o
sc
o
p
y
w
e
b
site,
”
2
0
1
6
,
[
O
n
li
n
e
],
A
v
a
ib
le:
h
tt
p
s://
ww
w
.
c
a
p
su
lee
n
d
o
sc
o
p
y
.
o
rg
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Abd
u
ll
a
h
Al
M
a
m
u
n
h
a
s
re
c
e
iv
e
d
a
B.
S
c
.
d
e
g
re
e
in
E
lec
tri
c
a
l
a
n
d
El
e
c
tro
n
ic
E
n
g
in
e
e
rin
g
f
ro
m
P
a
b
n
a
Un
iv
e
rsity
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
in
2
0
1
8
.
No
w
h
e
is
p
u
rsu
i
n
g
M
.
En
g
.
S
c
.
a
t
M
u
lt
im
e
d
ia
Un
iv
e
rsit
y
(M
M
U)
in
th
e
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
lo
g
y
sin
c
e
2
0
1
9
.
He
is
a
lso
w
o
rk
in
g
a
s
a
lec
tu
re
r
(o
n
st
u
d
y
lea
v
e
)
sin
c
e
No
v
e
m
b
e
r
2
0
1
9
in
EE
E
a
t
F
e
n
i
Un
iv
e
rsity
,
F
e
n
i,
Ba
n
g
lad
e
sh
.
His
re
se
a
rc
h
in
tere
st
i
n
c
lu
d
e
s
c
o
m
p
u
ter
v
isio
n
;
im
a
g
e
p
ro
c
e
ss
in
g
,
sig
n
a
l
p
ro
c
e
ss
in
g
,
d
e
e
p
lea
rn
in
g
a
n
d
m
a
c
h
in
e
lea
rn
i
n
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
4
,
A
u
g
u
s
t
2021
:
3
0
4
0
-
3048
3048
M
d
.
S
o
h
a
g
H
o
ss
a
i
n
h
a
s
re
c
e
i
v
e
d
a
B.
S
c
.
d
e
g
re
e
in
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ic
En
g
i
n
e
e
rin
g
f
ro
m
P
a
b
n
a
Un
iv
e
rsity
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
in
2
0
1
8
.
His
re
se
a
rc
h
in
tere
st
in
c
l
u
d
e
s
c
o
m
p
u
ter
v
isio
n
,
im
a
g
e
p
ro
c
e
ss
in
g
,
sig
n
a
l
p
ro
c
e
ss
in
g
,
d
e
e
p
lea
rn
i
n
g
a
n
d
m
a
c
h
in
e
lea
rn
i
n
g
.
E
m
P
o
h
Pi
n
g
is
c
u
rre
n
tl
y
a
lec
tu
re
r
a
t
th
e
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
M
u
lt
im
e
d
ia
Un
iv
e
rsit
y
.
P
o
h
P
in
g
re
se
a
rc
h
e
s
v
e
h
icle
sa
f
e
t
y
,
d
a
ta
f
u
sio
n
,
f
u
z
z
y
c
o
n
tr
o
l,
a
n
d
im
a
g
e
p
ro
c
e
ss
in
g
.
His c
u
rre
n
t
p
r
o
jec
t
is "
lan
e
d
e
p
a
rtu
re
e
stim
a
ti
o
n
u
sin
g
v
isio
n
a
n
d
v
e
h
icle
d
y
n
a
m
ica
l
'
s sta
te."
An
i
k
T
a
h
a
b
il
d
e
r
is
p
u
rsu
in
g
h
is P
h
.
D.
a
t
t
h
e
De
p
a
rtm
e
n
t
o
f
El
e
c
tr
ica
l
&
Co
m
p
u
ter
En
g
in
e
e
rin
g
o
f
th
e
S
tev
e
n
s
In
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
,
Ho
b
o
k
e
n
,
NJ
-
0
7
3
0
7
,
USA
.
He
g
o
t
h
is
M
S
T
d
e
g
re
e
f
ro
m
W
e
ste
rn
Ca
ro
li
n
a
Un
iv
e
rsity
,
Cu
ll
o
w
h
e
e
,
NC
-
2
8
7
2
3
,
USA
.
He
a
lso
e
a
rn
e
d
a
B
.
S
c
.
d
e
g
re
e
in
El
e
c
tri
c
a
l
a
n
d
E
lec
tro
n
ic E
n
g
in
e
e
rin
g
f
ro
m
P
a
b
n
a
U
n
iv
e
rsity
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
P
a
b
n
a
-
6
6
0
0
,
Ba
n
g
lad
e
sh
.
His
re
se
a
rc
h
in
tere
st
in
c
lu
d
e
s
c
o
m
p
u
ter
v
is
io
n
,
m
a
c
h
in
e
lea
rn
in
g
,
d
e
e
p
lea
rn
in
g
,
a
n
d
ro
b
o
t
ic
s.
Rum
a
n
a
S
u
lta
n
a
h
a
s
c
o
m
p
lete
d
Ba
c
h
e
lo
r
o
f
S
c
ien
c
e
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
f
ro
m
In
tern
a
ti
o
n
a
l
Isla
m
i
c
Un
iv
e
rsity
,
Ba
n
g
lad
e
sh
.
S
h
e
a
lso
g
o
t
a
n
M
S
T
d
e
g
re
e
f
ro
m
W
e
ste
rn
Ca
ro
li
n
a
Un
iv
e
rsit
y
,
USA
.
S
h
e
i
s
n
o
w
e
n
ro
ll
in
g
i
n
a
P
HD
p
r
o
g
ra
m
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
In
f
o
r
m
a
ti
o
n
S
y
ste
m
s
a
t
th
e
Un
iv
e
rsity
o
f
Co
lo
ra
d
o
De
n
v
e
r.
He
r
re
s
e
a
rc
h
in
tere
st
in
c
lu
d
e
s
im
a
g
e
p
ro
c
e
ss
in
g
,
c
o
m
p
u
ter v
isio
n
,
A
I
w
it
h
re
in
f
o
rc
e
m
e
n
t
lea
rn
in
g
,
m
a
c
h
in
e
lea
rn
i
n
g
a
n
d
d
e
e
p
lea
n
i
n
g
.
M
d
.
Ar
ifu
l
Is
la
m
h
a
s
r
e
c
e
i
v
e
d
a
B.
S
c
.
d
e
g
re
e
in
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ic
En
g
i
n
e
e
rin
g
f
ro
m
P
a
b
n
a
Un
iv
e
rsity
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
in
2
0
1
6
.
N
o
w
h
e
is p
u
rsu
in
g
M
.
En
g
.
S
c
.
a
t
Ra
jsh
a
h
i
Un
iv
e
rsit
y
o
f
En
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
lo
g
y
.
His
re
se
a
r
c
h
in
t
e
re
st
in
c
lu
d
e
s
EE
G
,
im
a
g
e
p
ro
c
e
ss
in
g
,
sig
n
a
l
p
r
o
c
e
ss
in
g
,
m
a
c
h
in
e
lea
rn
i
n
g
a
n
d
d
e
e
p
lea
rn
i
n
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.