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.
10
,
No
.
6
,
Decem
b
er
2
0
2
0
,
p
p
.
6
0
0
1
~
6
0
0
7
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
10
i
6
.
pp
6
0
0
1
-
6
0
0
7
6001
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m/in
d
ex
.
p
h
p
/I
JE
C
E
An i
m
a
g
e
-
ba
sed g
a
ng
rene disea
se cl
a
ss
ificatio
n
P
ra
m
o
d Se
kh
a
ra
n Na
ir
1
,
T
s
rit
y
Asef
a
B
er
ihu
2
,
Va
run K
u
m
a
r
3
1,
2
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ti
n
g
T
e
c
h
n
o
l
o
g
y
,
Ak
su
m
Un
iv
e
rsit
y
,
Et
h
io
p
ia
3
De
p
a
rtme
n
t
o
f
M
a
th
e
m
a
ti
c
s
,
Ak
su
m
Un
iv
e
rsit
y
,
Et
h
io
p
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
16
,
2
0
1
9
R
ev
i
s
ed
Ma
y
4
,
2020
A
cc
ep
ted
Ma
y
1
9
,
2
0
2
0
G
a
n
g
r
e
n
e
d
ise
a
se
is
o
n
e
o
f
th
e
d
e
a
d
li
e
st
d
ise
a
se
s
o
n
th
e
g
lo
b
e
w
h
ich
is
c
a
u
se
d
b
y
lac
k
o
f
b
lo
o
d
su
p
p
ly
to
th
e
b
o
d
y
p
a
rts
o
r
a
n
y
k
in
d
o
f
in
f
e
c
ti
o
n
.
T
h
e
g
a
n
g
r
e
n
e
d
ise
a
se
o
f
ten
a
ff
e
c
ts
th
e
h
u
m
a
n
b
o
d
y
p
a
rts
su
c
h
a
s
f
in
g
e
rs,
li
m
b
s,
to
e
s
b
u
t
th
e
re
a
re
m
a
n
y
c
a
se
s
o
f
o
n
m
u
sc
les
a
n
d
o
rg
a
n
s.
I
n
th
is
p
a
p
e
r,
th
e
g
a
n
g
re
n
e
d
ise
a
s
e
c
la
ss
i
f
ica
ti
o
n
is
b
e
in
g
d
o
n
e
f
ro
m
th
e
g
i
v
e
n
i
m
a
g
e
s
o
f
h
ig
h
re
so
l
u
ti
o
n
.
T
h
e
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
(CNN
)
is
u
se
d
f
o
r
f
e
a
tu
re
e
x
trac
ti
o
n
o
n
d
ise
a
se
im
a
g
e
s.
Th
e
f
irst
la
y
e
r
o
f
th
e
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
w
a
s
u
se
d
to
c
a
p
tu
re
th
e
e
le
m
e
n
tar
y
i
m
a
g
e
f
e
a
tu
re
s
su
c
h
a
s
d
o
ts,
e
d
g
e
s
a
n
d
b
lo
b
s.
T
h
e
in
term
e
d
iate
la
y
e
rs
o
r
th
e
h
id
d
e
n
la
y
e
rs
o
f
th
e
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
e
x
trac
ts
d
e
tailed
ima
g
e
f
e
a
tu
re
s
su
c
h
a
s
sh
a
p
e
s,
b
rig
h
tn
e
ss
,
a
n
d
c
o
n
tras
t
a
s
w
e
ll
a
s
c
o
lo
r.
F
in
a
ll
y
,
th
e
CNN
e
x
tra
c
ted
f
e
a
tu
re
s
a
re
g
iv
e
n
to
th
e
S
u
p
p
o
r
t
V
e
c
to
r
M
a
c
h
in
e
t
o
c
las
sify
th
e
g
a
n
g
re
n
e
d
ise
a
se
.
T
h
e
e
x
p
e
ri
m
e
n
t
re
su
lt
s
sh
o
w
th
e
a
p
p
r
o
a
c
h
a
d
o
p
te
d
i
n
t
h
is
stu
d
y
p
e
rf
o
r
m
s b
e
tt
e
r
a
n
d
a
c
c
e
p
tab
le.
K
ey
w
o
r
d
s
:
C
NN
Featu
r
e
ex
tr
ac
tio
n
Gan
g
r
en
e
d
is
ea
s
e
Gan
g
r
en
e
d
is
ea
s
e
cla
s
s
i
f
icat
io
n
Ma
ch
i
n
e
l
ea
r
n
i
n
g
SVM
class
if
ier
Co
p
y
rig
h
t
©
2
0
2
0
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
P
r
am
o
d
Sek
h
ar
an
Nair
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ti
n
g
T
e
ch
n
o
lo
g
y
,
Ak
s
u
m
Un
iv
er
s
it
y
,
P
OB
1
0
1
0
A
k
s
u
m
,
E
t
h
io
p
ia.
E
m
ail:
p
r
a
m
o
d
s
n
air
@
y
a
h
o
o
.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Gan
g
r
en
e
is
a
d
is
ea
s
e
t
h
at
r
es
u
lts
i
n
t
h
e
d
eter
io
r
atio
n
o
r
lo
s
s
o
f
an
o
r
g
an
o
r
tis
s
u
e
u
s
u
all
y
ca
u
s
ed
b
y
a
d
ef
icien
c
y
o
f
b
lo
o
d
s
u
p
p
l
y
in
t
h
e
b
o
d
y
.
T
h
is
m
a
y
b
e
c
au
s
ed
b
y
i
n
f
ec
tio
u
s
o
r
in
f
la
m
m
ato
r
y
p
r
o
ce
s
s
es
b
ec
au
s
e
o
f
i
n
j
u
r
y
o
r
w
o
u
n
d
s
o
n
b
o
d
y
p
ar
ts
,
o
r
p
r
o
g
r
ess
i
v
e
ch
a
n
g
es
ar
is
i
n
g
f
r
o
m
ch
r
o
n
ic
d
is
ea
s
e
s
,
lik
e
d
iab
etes
m
el
lit
u
s
.
Ga
n
g
r
en
e
d
is
ea
s
e
co
u
ld
al
s
o
r
esu
lt
i
n
d
a
m
ag
e
o
f
t
h
e
t
is
s
u
e
ca
u
s
ed
d
ef
icien
c
y
o
f
b
lo
o
d
s
u
p
p
l
y
.
T
h
e
b
lo
o
d
s
u
p
p
l
y
m
a
y
c
u
t
o
f
f
to
th
e
af
f
ec
ted
p
ar
t
o
f
t
h
e
b
o
d
y
as
a
r
es
u
lt
o
f
it
m
a
y
lead
s
to
v
ar
io
u
s
p
r
o
b
lem
s
,
i
n
cl
u
d
in
g
i
n
f
ec
tio
n
,
v
asc
u
lar
d
is
ea
s
e
o
r
tr
au
m
a.
I
f
t
h
is
d
is
ea
s
e
is
w
id
e
s
p
r
ea
d
o
v
er
th
e
b
o
d
y
p
ar
ts
,
th
en
s
h
o
c
k
m
a
y
o
cc
u
r
,
ca
n
e
v
e
n
ca
u
s
e
d
ea
th
.
C
u
r
r
en
tl
y
,
Or
t
h
o
p
ed
is
ts
b
ase
t
h
e
s
y
m
p
to
m
s
f
o
r
th
e
d
ia
g
n
o
s
i
s
an
d
clas
s
i
f
icatio
n
o
f
Ga
n
g
r
e
n
e
d
is
ea
s
e
o
n
th
e
v
is
u
al
a
s
s
es
s
m
en
t
o
f
th
e
af
f
ec
ted
p
ar
t.
T
h
e
ex
p
er
t
i
n
s
p
ir
e
to
d
etec
t
th
e
d
i
s
ea
s
e
f
ea
t
u
r
es
o
r
s
y
m
p
to
m
s
a
s
th
e
ea
r
l
y
s
i
g
n
s
ar
e
a
n
u
m
b
s
e
n
s
atio
n
an
d
co
ld
n
ess
i
n
th
e
af
f
e
cted
p
ar
ts
,
s
tar
ts
to
ch
an
g
e
th
e
co
lo
r
o
f
th
e
b
o
d
y
p
ar
t,
u
s
u
al
l
y
c
h
a
n
g
i
n
g
f
r
o
m
r
ed
d
is
h
to
b
r
o
w
n
a
n
d
t
h
en
f
i
n
all
y
c
h
an
g
es
in
to
b
lac
k
co
lo
r
,
th
e
af
f
ec
ted
p
ar
t
s
h
r
i
v
els
an
d
b
ec
o
m
e
s
d
r
y
,
s
w
o
llen
a
n
d
t
h
en
d
ec
a
y
s
,
th
e
w
o
u
n
d
is
in
f
ec
ted
a
n
d
co
n
tai
n
s
d
is
ch
ar
g
e,
r
es
u
lt
in
g
i
n
b
lack
s
k
in
co
lo
r
,
k
i
lls
b
lo
o
d
v
ess
els.
T
h
is
f
ac
t
s
h
o
w
s
t
h
at
r
i
g
h
t
d
iag
n
o
s
is
to
g
a
n
g
r
e
n
e
d
is
e
ase
h
i
g
h
l
y
d
ep
en
d
s
o
n
th
e
e
x
p
er
ts
’
e
x
p
er
ien
ce
a
n
d
o
n
h
i
s
o
r
h
er
v
is
u
al
i
n
s
ig
h
t.
I
n
ad
d
itio
n
to
t
h
is
,
t
h
e
h
u
m
a
n
v
is
io
n
s
y
s
te
m
lack
s
p
r
ec
is
io
n
,
an
d
q
u
an
ti
f
icatio
n
in
th
e
w
a
y
g
ath
er
s
i
n
f
o
r
m
atio
n
f
r
o
m
an
i
m
a
g
e.
R
ec
en
tl
y
,
m
o
s
t
clin
ic
al
ce
n
ter
s
i
n
b
o
th
th
e
d
ev
elo
p
i
n
g
a
n
d
d
ev
elo
p
ed
co
u
n
tr
ies
h
a
v
e
at
lea
s
t
m
a
g
n
et
ic
r
eso
n
a
n
ce
i
m
ag
in
g
(
MRI
)
,
c
o
m
p
u
ted
to
m
o
g
r
ap
h
y
(
C
T
)
s
ca
n
a
n
d
s
o
m
e
o
t
h
er
ex
p
en
s
i
v
e
cli
n
ic
al
lab
o
r
ato
r
y
eq
u
ip
m
e
n
ts
,
s
o
it
is
d
i
f
f
ic
u
lt
to
s
er
v
e
t
h
e
co
m
m
u
n
i
t
y
e
s
p
ec
ia
ll
y
i
n
d
ev
elo
p
in
g
co
u
n
tr
ie
s
w
it
h
t
h
e
h
e
lp
o
f
M
R
I
an
d
C
T
s
ca
n
m
ac
h
i
n
es.
T
h
ese
m
ac
h
in
e
s
ar
e
n
o
t
s
m
ar
t
en
o
u
g
h
i
n
id
en
t
if
ica
tio
n
an
d
class
i
f
ica
tio
n
o
f
Ga
n
g
r
en
e
d
is
ea
s
e
t
y
p
e
s
,
th
is
r
e
s
ea
r
ch
m
o
tiv
a
ted
to
au
t
o
m
a
te
th
e
h
u
m
an
v
is
io
n
s
y
s
te
m
f
o
r
class
i
f
icatio
n
o
f
t
h
e
d
is
ea
s
e.
T
o
m
in
i
m
ize
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.
10
,
No
.
6
,
Decem
b
er
2020
:
6
0
0
1
-
6
0
0
7
6002
th
e
er
r
o
r
s
m
ad
e
b
y
th
e
p
h
y
s
ic
ian
s
d
u
r
in
g
m
a
n
u
al
d
ia
g
n
o
s
is
an
d
class
if
ica
tio
n
,
t
h
er
e
is
a
n
ee
d
o
f
d
ev
elo
p
in
g
s
u
c
h
a
p
r
o
to
t
y
p
e
f
o
r
d
iag
n
o
s
is
an
d
cla
s
s
i
f
icat
io
n
o
f
g
a
n
g
r
en
e
d
is
ea
s
e
to
r
ed
u
ce
m
an
m
ad
e
er
r
o
r
s
d
u
r
in
g
d
iag
n
o
s
i
s
o
f
t
h
e
d
is
ea
s
e.
T
h
is
r
esear
ch
s
i
m
p
li
f
ies
th
e
cla
s
s
i
f
i
ca
tio
n
o
f
t
h
e
d
is
ea
s
e
an
d
p
r
o
v
id
es
co
n
s
i
s
ten
t
an
d
s
atis
f
ac
to
r
y
w
a
y
to
co
r
r
ec
tl
y
class
i
f
y
d
i
f
f
er
en
t
t
y
p
es
o
f
Ga
n
g
r
e
n
e
d
is
ea
s
e
s
.
T
h
er
ef
o
r
e,
o
u
r
ef
f
o
r
t
is
ex
p
ec
te
d
to
f
ill
ex
is
ti
n
g
g
ap
s
b
y
d
e
v
el
o
p
in
g
an
i
m
a
g
e
-
b
ased
h
y
b
r
id
ap
p
r
o
ac
h
f
o
r
class
if
icatio
n
o
f
th
e
d
is
ea
s
e
u
s
i
n
g
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
et
w
o
r
k
(
C
NN)
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SV
M)
.
B
ase
d
o
n
th
e
liter
at
u
r
e
s
u
r
v
e
y
,
w
e
h
av
e
id
e
n
ti
f
ied
th
e
f
o
llo
win
g
p
r
o
b
le
m
s
i
n
g
an
g
r
en
e
d
is
ea
s
e
d
iag
n
o
s
is
:
Ma
n
m
ad
e
er
r
o
r
s
ar
e
co
m
m
o
n
i
n
d
iag
n
o
s
i
s
an
d
cla
s
s
i
f
icatio
n
o
f
g
a
n
g
r
e
n
e
d
is
ea
s
e
w
h
e
n
ca
r
r
ied
o
u
t
m
a
n
u
all
y
.
T
h
e
u
n
a
v
ailab
ilit
y
o
f
f
as
ter
d
iag
n
o
s
i
s
an
d
clas
s
i
f
icatio
n
ap
p
r
o
ac
h
to
h
elp
th
e
d
o
cto
r
.
2.
L
I
T
RE
AT
U
RE
R
E
VI
E
W
I
n
th
is
s
ec
tio
n
,
th
e
w
o
r
k
s
r
ela
ted
to
g
an
g
r
e
n
e
d
is
ea
s
e
d
iag
n
o
s
is
a
n
d
class
if
icatio
n
w
il
l
b
e
r
ev
ie
w
ed
.
T
h
er
e
ar
e
th
r
ee
ty
p
es o
f
g
an
g
r
en
e
d
is
ea
s
e
[
1
,
2
]
th
ese
ar
e:
a.
Dr
y
Gan
g
r
en
e
d
is
ea
s
e:
T
h
is
t
y
p
e
o
f
g
an
g
r
en
e
d
is
ea
s
e
is
co
m
m
o
n
in
p
eo
p
le
s
u
f
f
er
i
n
g
f
r
o
m
b
lo
o
d
v
ess
e
l
d
is
ea
s
e
o
r
d
iab
etes
an
d
au
to
im
m
u
n
e
d
is
ea
s
e.
U
s
u
a
ll
y
a
f
f
ec
ts
h
a
n
d
s
,
f
ee
t
a
n
d
tis
s
u
e.
I
n
f
e
ctio
n
is
t
y
p
icall
y
n
o
t p
r
esen
t i
n
d
r
y
Gan
g
r
en
e.
S
o
m
e
o
f
th
e
s
y
m
p
to
m
s
ar
e:
-
d
r
y
a
n
d
s
h
r
i
v
eled
s
k
in
t
h
at
c
h
a
n
g
e
s
co
lo
r
f
r
o
m
b
lu
e
to
b
lack
an
d
ev
en
tu
al
l
y
s
lo
u
g
h
s
o
f
f
-
clea
r
lin
e
o
f
d
e
m
ar
ca
tio
n
is
s
e
en
-
li
m
ited
to
th
e
d
e
m
ar
ca
tio
n
-
s
lo
w
g
r
ad
u
al
lo
s
s
o
f
b
lo
o
d
s
u
p
p
ly
-
co
ld
an
d
n
u
m
b
s
k
i
n
a
n
d
-
p
ain
m
a
y
o
r
m
a
y
n
o
t b
e
p
r
esen
t
b.
W
et
Gan
g
r
en
e
[
1
,
2
]
:
C
o
m
m
o
n
in
p
eo
p
le
w
it
h
w
o
u
n
d
s
o
r
h
av
in
g
b
o
d
y
p
ar
t
w
r
i
n
k
led
o
r
s
q
u
ee
ze
d
.
I
n
th
is
t
y
p
e
o
f
g
a
n
g
r
en
e
d
is
ea
s
e,
t
h
e
af
f
ec
ted
tis
s
u
e
s
w
e
lls
a
n
d
is
ca
lled
“w
et”
b
ec
au
s
e
o
f
p
r
ese
n
ce
o
f
d
is
ch
ar
g
e
o
f
f
lu
id
as
a
r
es
u
lt
o
f
t
h
e
d
i
s
ea
s
e.
B
y
i
n
f
ec
t
io
n
t
h
e
w
et
Gan
g
r
en
e
s
p
r
ea
d
s
r
ap
id
l
y
t
h
r
o
u
g
h
t
h
e
b
o
d
y
,
m
ak
in
g
w
et
Ga
n
g
r
e
n
e
a
v
er
y
s
er
io
u
s
a
n
d
p
o
ten
tiall
y
li
f
e
i
n
t
i
m
id
ati
n
g
co
n
d
itio
n
.
So
,
i
m
m
ed
iate
tr
ea
t
m
en
t
ad
v
is
ed
.
So
m
e
o
f
t
h
e
s
y
m
p
to
m
s
ar
e:
-
s
w
elli
n
g
a
n
d
p
ain
at
t
h
e
s
ite
o
f
in
f
ec
tio
n
-
ch
an
g
e
i
n
s
k
in
co
lo
r
f
r
o
m
r
ed
to
b
r
o
w
n
to
b
lack
-
b
lis
ter
s
o
r
s
o
r
e
th
at
p
r
o
d
u
ce
a
b
ad
s
m
e
lli
n
g
d
is
c
h
ar
g
e
o
r
p
u
s
-
lin
e
o
f
d
e
m
ar
ca
tio
n
is
v
a
g
u
e
a
n
d
-
s
u
d
d
en
lo
s
s
o
f
b
lo
o
d
s
u
p
p
l
y
c.
Gas
Ga
n
g
r
e
n
e
[
2
]
:
T
h
is
t
y
p
e
o
f
g
a
n
g
r
en
e
d
i
s
ea
s
e
i
s
r
ar
e
b
u
t
m
o
r
e
d
an
g
er
o
u
s
.
T
h
e
d
is
ea
s
e
o
cc
u
r
s
w
h
e
n
in
f
ec
tio
n
p
r
o
g
r
ess
es
d
ee
p
in
s
id
e
th
e
b
o
d
y
p
ar
ts
,
lik
e
m
u
s
cles
o
r
o
r
g
an
s
u
s
u
all
y
a
s
a
r
esu
lt
o
f
tr
au
m
a.
T
h
e
b
ac
ter
iu
m
th
at
ca
u
s
e
s
g
a
s
Gan
g
r
e
n
e
d
is
ea
s
e
i
s
ca
lled
clo
s
tr
id
ia,
w
h
ich
r
elea
s
e
s
to
x
i
n
s
o
r
p
o
is
o
n
s
th
a
t
ca
u
s
e
d
a
m
a
g
e
to
all
p
ar
ts
o
f
t
h
e
b
o
d
y
alo
n
g
w
it
h
g
as
is
tr
a
p
p
ed
w
ith
in
th
e
b
o
d
y
ti
s
s
u
e.
As
t
h
e
co
n
d
it
io
n
p
r
o
g
r
ess
es
t
h
e
s
k
i
n
b
ec
o
m
es
p
ale
an
d
g
r
a
y
an
d
t
h
is
r
e
s
u
l
ts
i
n
cr
ac
k
i
n
g
s
o
u
n
d
w
h
en
p
r
es
s
e
d
d
u
e
to
th
e
g
a
s
ac
cu
m
u
lat
io
n
w
it
h
i
n
th
e
tis
s
u
e.
Gas
Gan
g
r
en
e
d
is
ea
s
e
n
ee
d
s
i
m
m
ed
iate
m
ed
ical
tr
ea
t
m
e
n
t
b
ec
au
s
e
w
it
h
o
u
t tr
ea
t
m
e
n
t d
ea
th
m
a
y
o
cc
u
r
w
ith
in
4
8
h
o
u
r
s
.
T
h
e
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
[
3
]
is
u
s
ed
i
n
t
h
is
w
o
r
k
to
d
o
th
e
clas
s
i
f
icatio
n
o
f
d
ig
ital
i
m
ag
e
s
i
n
to
eith
er
o
f
t
h
e
ca
te
g
o
r
ies
o
f
g
a
n
g
r
e
n
e
d
is
e
a
s
es.
Su
p
p
o
r
t
v
ec
t
o
r
m
ac
h
i
n
es
r
ep
r
esen
t
an
ex
t
en
s
io
n
to
n
o
n
li
n
ea
r
m
o
d
el
s
o
f
th
e
g
e
n
er
alize
d
m
o
d
el
f
o
r
class
if
ica
tio
n
.
T
h
e
SV
M
alg
o
r
it
h
m
is
b
ased
o
n
t
h
e
s
tatis
t
ical
m
ac
h
in
e
lear
n
in
g
t
h
eo
r
y
[
4
]
.
A
n
d
f
u
r
t
h
er
m
o
r
e,
th
e
SVM
is
b
ased
o
n
th
e
co
n
ce
p
t
o
f
d
ec
is
io
n
p
l
an
es
u
s
ed
to
d
ef
in
e
d
ec
is
io
n
b
o
u
n
d
ar
ies.
A
d
ec
is
i
o
n
p
lan
e
s
ep
ar
ates
b
et
w
ee
n
a
s
et
o
f
o
b
j
ec
ts
h
av
i
n
g
d
if
f
er
en
t
class
m
e
m
b
er
s
h
ip
s
.
SVM
is
a
s
et
o
f
r
elate
d
s
u
p
er
v
is
ed
lear
n
i
n
g
m
et
h
o
d
s
u
s
ed
i
n
class
i
f
ica
tio
n
p
r
o
b
lem
s
[
5
]
an
d
r
eg
r
ess
io
n
[
6
]
.
C
las
s
i
f
icatio
n
tas
k
is
b
ased
o
n
d
r
a
w
i
n
g
s
ep
ar
atin
g
li
n
e
s
to
d
is
tin
g
u
is
h
b
et
w
ee
n
o
b
j
ec
t
s
o
f
d
i
f
f
er
e
n
t
cla
s
s
m
e
m
b
er
s
h
ip
s
k
n
o
w
n
a
s
h
y
p
e
r
p
lan
e
class
i
f
ier
s
.
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
s
ar
e
p
ar
ticu
lar
ly
s
u
i
ted
to
h
an
d
le
s
u
c
h
tas
k
s
.
SVM
is
a
b
in
ar
y
clas
s
i
f
ier
th
at
ass
u
m
es
o
n
l
y
t
w
o
v
al
u
e
s
a
s
lab
els
w
h
ic
h
ar
e
n
e
g
ati
v
e
a
n
d
p
o
s
itiv
e
.
Mu
lticla
s
s
SVM
is
u
s
ed
to
cla
s
s
i
f
y
o
b
j
ec
ts
w
i
th
m
o
r
e
t
h
a
n
t
w
o
cla
s
s
e
s
[
7
]
.
I
n
o
u
r
w
o
r
k
t
h
e
m
u
lticla
s
s
S
V
M
is
u
s
ed
f
o
r
class
i
f
y
d
if
f
er
en
t
t
y
p
e
s
o
f
g
a
n
g
r
e
n
e
d
is
ea
s
e
s
.
I
n
o
n
e
o
f
t
h
e
w
o
r
k
s
[
8
]
,
f
o
r
class
if
y
i
n
g
b
o
th
m
ela
n
o
c
y
tic
s
k
i
n
le
s
io
n
s
an
d
n
o
n
-
m
elan
o
c
y
tic
s
k
i
n
les
io
n
s
a
n
e
w
co
m
p
u
ter
-
aid
ed
m
e
th
o
d
w
as
i
m
p
le
m
en
ted
.
As
b
y
t
h
e
a
u
t
h
o
r
,
th
e
m
et
h
o
d
u
s
ed
as
f
o
u
r
tex
t
u
r
e
f
ea
tu
r
e
s
f
o
r
ex
tr
ac
tio
n
:
C
o
n
tr
ast,
C
o
r
r
elatio
n
,
Ho
m
o
g
en
ei
t
y
an
d
E
n
er
g
y
.
T
h
e
SVM
an
d
K
-
n
ea
r
est
n
ei
g
h
b
o
r
(
K
-
NN
)
class
i
f
icatio
n
tec
h
n
iq
u
e
s
ar
e
s
elec
ted
to
co
m
p
ar
e
th
e
p
er
f
o
r
m
a
n
ce
an
d
an
a
l
y
ze
t
h
e
ac
cu
r
ac
y
o
f
b
o
th
clas
s
i
f
ier
s
.
Au
to
m
a
ted
class
i
f
icatio
n
o
f
li
v
er
d
is
o
r
d
er
s
u
s
in
g
u
ltra
s
o
u
n
d
i
m
ag
e
s
[
9
]
w
a
s
p
r
o
p
o
s
ed
,
w
h
ich
s
h
o
w
s
an
i
n
n
o
v
ati
v
e
m
et
h
o
d
u
s
ed
i
n
r
ec
o
g
n
itio
n
o
f
f
att
y
li
v
er
d
is
ea
s
e
a
n
d
h
e
ter
o
g
en
eo
u
s
li
v
er
u
s
i
n
g
te
x
tu
r
al
an
al
y
s
is
o
f
li
v
er
u
ltra
s
o
u
n
d
i
m
a
g
es.
T
h
e
w
a
v
elet
p
ac
k
et
tr
an
s
f
o
r
m
w
a
s
u
s
ed
i
n
t
h
e
s
tu
d
y
to
e
x
tr
ac
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
A
n
ima
g
e
-
b
a
s
ed
g
a
n
g
r
en
e
d
is
ea
s
e
cla
s
s
ifica
tio
n
(
P
r
a
mo
d
S
ek
h
a
r
a
n
N
a
ir
)
6003
th
e
f
ea
t
u
r
es
s
u
c
h
a
s
m
ea
n
,
m
e
d
ian
a
n
d
s
ta
n
d
ar
d
d
ev
iatio
n
,
t
h
e
cla
s
s
i
f
icatio
n
tec
h
n
iq
u
e
u
s
ed
is
t
h
e
m
u
lticla
s
s
SVM,
a
n
d
an
ac
c
u
r
ac
y
o
f
9
5
%
w
as a
c
h
ie
v
ed
u
s
i
n
g
th
e
m
u
lti
class
SVM
f
o
r
class
i
f
ica
tio
n
.
An
o
th
er
s
tu
d
y
s
h
o
w
ca
s
ed
t
h
at
i
m
a
g
e
p
r
o
ce
s
s
in
g
tec
h
n
i
q
u
es
ca
n
b
e
ap
p
lied
to
L
u
n
g
ca
n
ce
r
d
etec
tio
n
[
1
0
]
.
T
h
is
s
t
u
d
y
w
a
s
b
ased
o
n
t
h
e
i
m
a
g
e
p
r
o
ce
s
s
in
g
tec
h
n
iq
u
es.
F
u
r
th
er
m
o
r
e,
s
tu
d
y
s
h
o
w
s
t
h
at,
i
m
a
g
e
p
r
ep
r
o
ce
s
s
in
g
i
n
t
h
e
ea
r
l
y
s
ta
g
es
o
f
d
is
ea
s
e
d
iag
n
o
s
i
s
p
r
o
ce
s
s
,
i
m
p
r
o
v
ed
th
e
ac
cu
r
ac
y
an
d
th
e
r
es
u
lt
.
I
n
th
e
s
t
u
d
y
,
th
r
ee
s
ta
g
e
i
m
a
g
e
p
r
o
ce
s
s
in
g
w
er
e
u
s
ed
:
en
h
an
ce
m
e
n
t,
s
e
g
m
en
ta
tio
n
u
s
i
n
g
m
ar
k
er
-
co
n
tr
o
lled
w
ater
s
h
ed
,
f
e
at
u
r
e
ex
tr
ac
tio
n
Gab
o
r
f
ilter
s
tag
e.
T
h
e
w
ater
s
h
ed
s
eg
m
e
n
tatio
n
tech
n
iq
u
e
h
ad
b
etter
ac
cu
r
ac
y
(
8
4
.
5
5
%)
co
m
p
ar
ed
to
o
th
er
a
p
p
r
o
ac
h
es [
1
1
,
1
2
]
.
T
h
e
ac
cu
r
ac
y
o
f
co
m
p
u
ter
v
is
io
n
ap
p
licatio
n
s
i
s
i
m
p
r
o
v
e
d
[
1
3
]
w
it
h
t
h
e
s
u
r
g
e
in
t
h
e
u
s
ag
e
o
f
co
n
v
o
lu
tio
n
al
n
et
w
o
r
k
s
an
d
it
s
tech
n
iq
u
e
s
.
A
tec
h
n
iq
u
e
b
as
ed
o
n
m
ac
h
i
n
e
lear
n
i
n
g
a
n
d
co
m
p
u
ter
v
i
s
io
n
[
1
4
]
w
a
s
u
s
ed
i
n
p
lan
t
lea
f
d
is
ea
s
e
class
i
f
icat
io
n
u
s
i
n
g
C
NN
[
1
5
]
,
w
h
ich
h
a
s
b
ee
n
u
t
ilized
f
o
r
th
e
d
etec
tio
n
a
n
d
class
i
f
icatio
n
o
f
p
lan
t
lea
f
d
is
ea
s
e.
T
h
e
p
ap
er
w
as
f
o
c
u
s
ed
o
n
th
e
ea
r
ly
cla
s
s
i
f
icatio
n
an
d
d
etec
tio
n
o
f
th
e
p
lan
t
lea
f
d
is
ea
s
es.
T
h
e
au
t
h
o
r
s
u
s
ed
a
co
n
v
o
lu
t
io
n
al
n
eu
r
al
n
et
w
o
r
k
f
o
r
f
ea
t
u
r
e
ex
tr
ac
tio
n
a
n
d
class
i
f
icatio
n
.
T
h
e
au
th
o
r
s
d
id
n
o
t
tr
ain
th
e
en
tire
d
ee
p
co
n
v
o
lu
tio
n
al
n
e
u
r
al
n
et
w
o
r
k
(
DC
NN)
f
r
o
m
th
e
s
cr
atc
h
w
it
h
a
r
an
d
o
m
i
n
it
ializatio
n
,
i
n
s
tead
,
p
r
e
-
tr
ai
n
a
DC
NN
o
n
a
v
er
y
lar
g
e
d
ataset
w
a
s
u
s
ed
an
d
th
e
y
tr
ain
ed
DC
NN
w
e
ig
h
ts
to
clas
s
if
y
t
h
e
p
lan
t
lea
f
d
is
ea
s
e
f
o
r
f
o
u
r
t
y
p
e
s
o
f
leav
e
s
s
u
ch
u
s
Ap
p
le,
Gr
ap
e,
C
o
r
n
,
an
d
Stra
w
b
er
r
y
.
O
n
e
a
n
o
th
er
w
o
r
k
o
n
p
lan
t
d
is
ea
s
e
cl
ass
i
f
icatio
n
w
a
s
p
r
o
p
o
s
ed
[
1
6
]
b
y
u
s
i
n
g
C
NN
.
T
h
is
s
tu
d
y
h
a
s
u
s
ed
th
e
s
o
y
b
e
an
lea
f
i
m
a
g
e
s
to
id
en
ti
f
y
th
r
e
e
d
if
f
er
e
n
t
d
is
ea
s
e
s
o
n
s
o
y
b
ea
n
.
T
h
e
au
th
o
r
s
h
a
v
e
u
s
ed
th
e
p
r
e
tr
ain
ed
C
N
N
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
clas
s
if
ic
atio
n
o
f
t
h
e
d
is
ea
s
es.
T
h
e
r
e
i
s
an
o
th
e
r
w
o
r
k
[
1
7
]
u
s
e
s
th
e
S
i
am
es
e
C
N
N
,
m
u
lt
i
p
l
e
i
n
s
t
an
c
es
o
f
th
e
s
am
e
m
o
d
e
l
,
f
o
r
c
l
as
s
if
y
t
h
e
x
-
r
ay
im
ag
e
o
f
th
e
ch
e
s
t
t
o
c
l
a
s
s
if
y
th
e
p
n
eu
m
o
n
i
a
d
is
e
ase
.
T
h
i
s
p
a
p
e
r
w
a
s
f
o
cu
s
e
d
o
n
th
e
c
l
ass
if
i
c
at
i
o
n
o
f
t
h
e
x
-
r
ay
im
ag
e
in
t
o
an
y
o
f
th
e
t
h
r
e
e
c
la
s
s
es
.
T
w
o
c
l
as
s
es
w
e
r
e
th
e
tw
o
d
i
f
f
e
r
e
n
t
c
au
s
es
o
f
p
n
eu
m
o
n
i
a
a
n
d
t
h
e
o
th
e
r
o
n
e
is
n
o
n
in
f
e
ct
e
d
x
-
r
ay
im
ag
e
.
T
h
e
C
NN
i
s
w
i
d
e
ly
u
s
e
d
i
n
f
ea
tu
r
e
ex
t
r
a
c
ti
o
n
f
r
o
m
t
h
e
im
ag
es
.
On
e
o
f
t
h
e
r
ec
en
t
w
o
r
k
s
[
1
8
]
p
r
o
p
o
s
es
t
h
e
f
ea
tu
r
e
ex
t
r
a
ct
i
o
n
o
f
f
ac
e
im
ag
es
t
o
d
o
th
e
ag
e
-
in
v
a
r
i
an
t
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
.
I
n
m
o
s
t
o
f
th
e
r
esear
c
h
w
o
r
k
s
[
1
9
,
2
0
]
r
elate
d
to
d
is
ea
s
e
class
i
f
icatio
n
,
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
w
a
s
in
th
e
cr
u
cial
p
ar
t
o
f
d
i
s
ea
s
e
d
iag
n
o
s
is
p
r
o
ce
s
s
u
s
i
n
g
m
ac
h
i
n
e
lear
n
i
n
g
al
g
o
r
ith
m
s
.
I
m
a
g
e
p
r
e
-
p
r
o
ce
s
s
in
g
is
th
e
f
ir
s
t
s
tep
i
n
i
m
a
g
e
p
r
o
ce
s
s
in
g
a
n
d
p
r
e
-
p
r
o
ce
s
s
i
n
g
h
e
lp
s
to
i
m
p
r
o
v
e
th
e
q
u
alit
y
o
f
t
h
e
i
m
a
g
e
[
2
1
]
s
o
t
h
at
th
e
i
m
ag
e
i
s
s
u
itab
le
to
ex
tr
ac
t
th
e
f
ea
tu
r
es.
D
u
e
to
d
if
f
er
en
t
f
ac
to
r
s
,
th
e
i
m
a
g
e
ca
p
tu
r
ed
b
y
th
e
d
ig
ita
l
ca
m
er
a
m
a
y
n
o
t
b
e
clea
r
an
d
in
ac
ce
p
tab
le
r
eso
lu
tio
n
.
T
h
er
ef
o
r
e,
d
if
f
er
e
n
t
p
r
e
-
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
ar
e
ap
p
lied
t
o
i
m
a
g
es
to
i
m
p
r
o
v
e
th
e
i
m
a
g
e
q
u
alit
y
.
T
h
is
i
n
cl
u
d
es
r
e
m
o
v
a
l
o
f
n
o
is
es,
ad
j
u
s
t
m
e
n
t
o
f
i
n
te
n
s
it
y
o
r
b
r
ig
h
t
n
es
s
an
d
ad
d
itio
n
o
f
ed
g
e
d
etec
to
r
s
b
ased
o
n
th
e
p
r
ef
er
r
ed
f
ea
tu
r
e
s
f
o
r
th
e
cla
s
s
i
f
icatio
n
.
T
h
e
ed
g
e
-
b
ased
s
eg
m
e
n
tatio
n
[
2
1
]
m
et
h
o
d
ch
an
g
e
s
r
ap
id
ly
b
ased
o
n
a
ch
an
g
e
i
n
i
m
a
g
e
in
ten
s
it
y
v
alu
e
an
d
t
h
e
c
h
a
n
g
e
in
a
s
in
g
le
in
te
n
s
it
y
v
a
lu
e
d
o
es
n
o
t d
eli
v
er
b
etter
r
esu
lt o
f
ed
g
e
s
.
E
d
g
e
d
etec
tio
n
m
et
h
o
d
is
u
s
ed
to
lo
ca
tin
g
th
e
ed
g
e
s
w
h
er
e
ei
th
er
t
h
e
f
ir
s
t
d
er
iv
a
tiv
e
o
f
in
te
n
s
it
y
i
s
g
r
ea
ter
t
h
a
n
a
p
ar
ticu
lar
th
r
es
h
o
ld
o
r
th
e
s
ec
o
n
d
d
er
iv
ativ
e
h
as
z
er
o
cr
o
s
s
in
g
s
.
T
h
e
f
ir
s
t
s
tep
i
n
ed
g
e
-
b
ased
s
eg
m
e
n
tatio
n
is
d
etec
tin
g
t
h
e
ed
g
e
s
an
d
th
e
n
co
n
n
ec
tin
g
t
h
e
m
to
g
e
th
er
to
m
a
k
e
th
e
o
b
j
ec
t b
o
u
n
d
ar
ies an
d
s
eg
m
e
n
t t
h
e
n
ec
e
s
s
ar
y
ar
ea
s
.
I
n
c
o
n
c
lu
s
i
o
n
s
eg
m
en
t
at
i
o
n
i
s
t
h
e
c
o
m
m
o
n
im
ag
e
p
r
o
c
e
s
s
in
g
m
e
th
o
d
,
w
h
e
r
e
an
im
ag
e
is
d
i
v
i
d
e
d
o
r
p
a
r
t
i
t
i
o
n
e
d
in
t
o
d
i
f
f
e
r
e
n
t
c
o
n
s
t
it
u
en
t p
a
r
t
s
w
it
h
s
im
il
a
r
f
e
atu
r
es
l
ik
e
,
p
i
x
e
l
in
t
e
n
s
ity
v
a
lu
e
,
c
o
lo
r
a
n
d
t
ex
tu
r
e
[
2
2
]
.
T
h
e
s
im
p
l
es
t
m
e
th
o
d
d
iv
i
d
es
th
e
im
a
g
e
p
ix
e
ls
w
ith
r
e
s
p
e
c
t
to
t
h
ei
r
in
t
en
s
i
ty
l
ev
e
l
.
T
h
e
s
e
m
e
th
o
d
s
a
r
e
u
s
e
d
o
n
im
ag
es
w
it
h
b
r
ig
h
t
e
r
o
b
je
c
t
s
th
a
n
th
e
i
r
b
a
ck
g
r
o
u
n
d
.
T
h
e
s
e
l
ec
t
i
o
n
o
f
t
h
e
m
eth
o
d
s
i
s
e
ith
e
r
m
a
n
u
a
l
o
r
a
u
t
o
m
a
t
i
c
b
a
s
e
d
o
n
p
r
i
o
r
k
n
o
w
l
e
d
g
e
o
r
in
f
o
r
m
a
t
i
o
n
o
f
im
ag
e
f
ea
tu
r
e
s
[
2
3
,
2
4
]
.
3.
RE
S
E
ARCH
M
E
T
H
O
D
I
n
ter
v
ie
w
s
w
er
e
u
s
ed
f
o
r
d
ata
g
at
h
er
in
g
a
n
d
d
ata
co
llect
io
n
.
P
h
y
s
ic
ian
s
a
n
d
n
u
r
s
e
s
ar
e
i
n
ter
v
ie
w
ed
o
n
g
a
n
g
r
e
n
e
d
is
ea
s
e.
T
h
e
m
ed
ical
i
m
a
g
es
co
llected
f
o
r
Gan
g
r
en
e
d
is
ea
s
e
w
er
e
cla
s
s
i
f
ied
i
n
to
th
r
ee
ca
teg
o
r
ies
o
f
g
a
n
g
r
en
e
d
is
ea
s
e,
n
a
m
el
y
w
et
Gan
g
r
en
e,
d
r
y
Ga
n
g
r
e
n
e,
g
as
Gan
g
r
en
e.
T
h
e
d
i
f
f
er
e
n
t
t
y
p
es
o
f
g
an
g
r
en
e
d
is
ea
s
e
i
m
ag
e
s
ar
e
s
h
o
w
n
i
n
F
ig
u
r
e
1
.
T
h
e
u
s
e
o
f
m
ac
h
in
e
lear
n
in
g
al
g
o
r
ith
m
s
to
class
i
f
y
m
ed
ical
i
m
a
g
e
s
in
to
s
ep
ar
ate
ca
teg
o
r
ies
[2
5
]
is
n
o
w
ad
a
y
s
a
co
m
m
o
n
co
m
p
u
tin
g
an
d
d
ata
s
cien
ce
tas
k
.
Ma
ch
in
e
lear
n
i
ng
alg
o
r
ith
m
s
n
ee
d
a
s
p
ec
ial
f
ea
t
u
r
e
ex
tr
ac
tio
n
to
o
l
a
n
d
a
p
r
o
p
er
l
y
p
r
ep
ar
ed
d
ataset.
T
h
e
m
e
d
ical
i
m
a
g
es
u
s
ed
i
n
th
is
w
o
r
k
w
h
ic
h
ar
e
co
llecte
d
f
r
o
m
d
i
f
f
er
en
t
i
m
a
g
e
s
o
u
r
ce
s
w
er
e
cr
o
p
p
ed
o
u
t
in
u
n
i
f
o
r
m
r
eso
l
u
tio
n
o
f
224
-
by
-
224
-
by
-
3
to
m
a
k
e
t
h
e
d
ataset
to
b
e
s
i
m
ilar
i
n
s
ize
an
d
r
eso
lu
tio
n
.
P
r
ep
ar
in
g
a
p
r
o
p
er
l
y
lab
eled
d
atase
t
w
it
h
m
ed
ical
i
m
ag
e
s
f
o
r
d
if
f
er
en
t
t
y
p
e
s
o
f
Ga
n
g
r
e
n
e
d
is
ea
s
e
is
an
i
m
p
o
r
tan
t
s
tep
in
t
h
e
clas
s
if
ica
tio
n
p
r
o
ce
s
s
.
W
e
h
av
e
co
n
d
u
cted
in
ter
v
ie
w
s
w
ith
m
ed
ical
ex
p
er
ts
s
u
c
h
as,
o
r
th
o
p
ed
is
ts
(
p
h
y
s
icia
n
s
)
to
co
r
r
ec
tly
s
elec
t
th
e
m
ed
ical
i
m
a
g
es
f
o
r
Gan
g
r
en
e
d
is
ea
s
e
f
r
o
m
s
p
ec
ialized
h
o
s
p
itals
.
T
h
e
Gan
g
r
e
n
e
cla
s
s
i
f
icat
io
n
p
r
o
b
lem
ca
n
b
e
s
o
l
v
ed
th
r
o
u
g
h
a
s
u
p
er
v
i
s
ed
m
ac
h
i
n
e
lear
n
i
n
g
m
e
t
h
o
d
.
I
n
th
is
w
o
r
k
t
h
e
C
NN
w
a
s
u
s
ed
to
ex
tr
ac
t
th
e
f
ea
tu
r
e
s
f
r
o
m
th
e
i
m
ag
e
d
ataset.
SV
M
w
as
u
s
ed
to
class
i
f
y
th
e
ex
tr
ac
ted
i
m
a
g
e
f
ea
tu
r
e
s
i
n
to
d
if
f
er
en
t
g
a
n
g
r
e
n
e
d
is
ea
s
e
ca
teg
o
r
ies.
T
h
e
ar
ch
itect
u
r
e
o
f
th
e
i
m
a
g
e
-
b
ased
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.
10
,
No
.
6
,
Decem
b
er
2020
:
6
0
0
1
-
6
0
0
7
6004
h
y
b
r
id
ap
p
r
o
ac
h
f
o
r
g
an
g
r
e
n
e
d
is
ea
s
e
class
i
f
icat
io
n
s
y
s
te
m
is
s
h
o
w
n
i
n
F
i
g
u
r
e
2
.
MA
T
L
A
B
is
u
s
ed
to
i
m
p
le
m
en
t t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
.
Fig
u
r
e
1
.
T
h
r
ee
ty
p
es o
f
g
an
g
r
en
e
d
is
ea
s
e
a
n
d
th
eir
lab
els
T
ra
ini
ng
/
T
est
Fig
u
r
e
2
.
A
r
ch
itectu
r
e
f
o
r
g
an
g
r
en
e
d
is
ea
s
e
class
if
ica
tio
n
4.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
NS
I
n
th
i
s
s
ec
tio
n
,
t
h
e
e
x
p
er
i
m
e
n
t
al
r
esu
lt
s
o
n
p
er
f
o
r
m
an
ce
o
f
S
VM
class
if
ier
w
i
th
th
e
co
n
f
u
s
i
o
n
m
atr
i
x
is
d
is
cu
s
s
ed
.
4
.
1
.
C
o
nfusi
o
n
m
a
t
ri
x
o
f
SVM
cl
a
s
s
if
ier
T
h
e
co
n
f
u
s
io
n
m
atr
i
x
s
h
o
w
s
i
n
T
ab
le
1
is
u
s
ed
to
s
h
o
w
ca
s
e
th
e
ac
cu
r
ac
y
o
f
SVM
clas
s
i
f
i
er
o
n
a
s
et
o
f
test
d
ata
s
et
f
o
r
w
h
ich
t
h
e
o
b
s
er
v
ed
v
alu
es
o
f
g
a
n
g
r
e
n
e
d
is
ea
s
e
i
m
ag
e
s
ar
e
k
n
o
w
n
.
T
h
e
o
u
tp
u
ts
f
r
o
m
th
e
co
n
f
u
s
io
n
m
a
tr
ix
s
ar
e
s
h
o
w
n
i
n
T
ab
le
s
1
(
a)
an
d
1
(
b
)
.
T
h
e
Fig
u
r
e
2
s
h
o
w
s
th
e
g
r
ap
h
i
ca
l
e
x
p
lan
atio
n
o
f
th
e
tab
les.
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
A
n
ima
g
e
-
b
a
s
ed
g
a
n
g
r
en
e
d
is
ea
s
e
cla
s
s
ifica
tio
n
(
P
r
a
mo
d
S
ek
h
a
r
a
n
N
a
ir
)
6005
S
in
c
e
th
e
r
e
a
r
e
th
r
e
e
c
l
ass
e
s
o
f
G
an
g
r
en
e
d
is
e
as
e
s
a
n
d
th
e
f
o
u
r
th
o
n
e
th
a
t
f
o
r
n
o
t
a
g
a
n
g
r
en
e
d
is
e
as
e,
c
o
n
f
u
s
i
o
n
m
at
r
ix
f
o
r
t
h
e
c
l
ass
e
s
w
e
r
e
g
en
e
r
a
t
e
d
.
B
u
t
,
t
o
m
e
asu
r
e
th
e
o
v
e
r
a
l
l
p
e
r
f
o
r
m
an
c
e
a
n
d
a
c
cu
r
a
cy
o
f
t
h
e
SV
M
c
l
as
s
if
i
e
r
th
e
ag
g
r
eg
a
t
e
o
f
th
e
p
r
e
c
i
s
i
o
n
an
d
r
e
c
a
l
l
f
r
o
m
t
h
e
S
V
M
w
e
r
e
c
o
n
s
i
d
e
r
ed
.
T
h
e
im
p
l
em
en
t
e
d
c
l
a
s
s
if
ie
r
o
n
ly
g
en
e
r
at
e
s
th
e
f
in
al
c
o
n
f
u
s
i
o
n
m
a
t
r
ix
an
d
th
e
c
o
r
r
e
s
p
o
n
d
i
n
g
av
e
r
a
g
e
a
cc
u
r
a
cy
a
s
s
h
o
w
n
in
T
a
b
l
e
s
1
(
a
)
a
n
d
1
(
b
)
.
T
ab
le
1
.
(
a
)
C
o
n
f
u
s
io
n
m
atr
i
x
tab
u
lated
ac
co
r
d
in
g
to
th
e
tr
u
e
p
o
s
iti
v
e
N
u
mb
e
r
W
e
t
D
r
y
G
a
s
O
t
h
e
r
W
e
t
8
0
0
2
D
r
y
2
7
.
3
0
0
.
6
G
a
s
0
0
10
0
O
t
h
e
r
1
.
3
0
0
8
.
6
T
ab
le
1
.
(
b
)
C
o
n
f
u
s
io
n
m
atr
i
x
tab
u
lated
ac
co
r
d
in
g
to
th
e
tr
u
e
n
eg
a
tiv
e
N
u
mb
e
r
W
e
t
D
r
y
G
a
s
O
t
h
e
r
W
e
t
0
.
8
0
0
0
0
0
0
.
2
0
0
0
D
r
y
0
.
2
0
0
0
0
.
7
3
3
3
0
0
.
0
6
6
7
G
a
s
0
0
1
.
0
0
0
0
O
t
h
e
r
0
.
1
3
3
3
0
0
0
.
8
6
6
7
Fig
u
r
e
2
.
C
o
n
f
u
s
io
n
m
atr
ix
,
tr
u
e
p
o
s
itiv
e
v
s
tr
u
e
n
e
g
ati
v
e
4
.
2
.
C
o
m
pa
ra
t
iv
e
s
t
ud
y
I
n
th
is
s
ec
tio
n
,
r
elate
d
w
o
r
k
s
o
n
d
is
ea
s
e
c
lass
if
icatio
n
ar
e
co
m
p
ar
ed
.
T
a
b
le
2
s
h
o
w
s
t
h
e
r
elate
d
w
o
r
k
s
w
ith
o
u
r
w
o
r
k
an
d
th
e
ac
cu
r
ac
y
o
f
clas
s
if
icatio
n
.
T
h
e
r
esu
lt
o
f
o
u
r
co
m
p
ar
ativ
e
s
t
u
d
y
i
n
T
ab
le
2
s
h
o
w
s
th
at,
t
h
e
o
v
er
all
ac
c
u
r
ac
y
f
o
r
d
if
f
er
e
n
t
d
i
s
ea
s
e
cla
s
s
i
f
icat
io
n
alg
o
r
it
h
m
s
w
er
e
b
et
w
ee
n
6
8
.
3
0
an
d
9
5
p
er
ce
n
t.
T
h
e
ac
cu
r
ac
y
o
f
o
u
r
p
r
o
p
o
s
ed
i
m
ag
e
-
b
ased
h
y
b
r
id
ap
p
r
o
ac
h
u
s
i
n
g
C
NN
an
d
SVM
is
8
5
%.
T
h
e
ac
cu
r
ac
y
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
i
s
il
lu
s
tr
a
ted
in
F
ig
u
r
e
3.
A
s
s
h
o
w
n
i
n
F
ig
u
r
e
3
,
th
e
ac
c
u
r
ac
y
o
f
t
h
e
SVM
o
n
cla
s
s
i
f
y
i
n
g
g
an
g
r
en
e
d
is
ea
s
e
i
s
b
et
w
ee
n
8
2
an
d
8
8
p
er
ce
n
ta
g
e.
T
h
is
s
h
o
w
s
t
h
at,
t
h
e
C
N
N
a
n
d
SVM
h
y
b
r
id
ap
p
r
o
ac
h
h
as
b
etter
ac
ce
p
tab
le
ac
cu
r
ac
y
co
m
p
ar
ed
w
it
h
o
th
er
clas
s
i
f
icati
o
n
ap
p
r
o
ac
h
es.
T
ab
le
2
.
C
o
m
p
ar
ativ
e
s
tu
d
y
o
n
r
elate
d
p
r
o
p
o
s
ed
w
o
r
k
R
e
l
a
t
e
d
a
n
d
p
r
o
p
o
se
d
w
o
r
k
M
e
t
h
o
d
o
l
o
g
y
A
c
c
u
r
a
c
y
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
v
a
r
i
o
u
s
sk
i
n
l
e
si
o
n
u
si
n
g
S
V
M
a
n
d
K
N
N
c
l
a
ssi
f
i
e
r
[
8
]
S
V
M
,
K
N
N
b
o
t
h
f
o
r
c
l
a
ssi
f
i
c
a
t
i
o
n
S
V
M
7
5
.
9
5
%
K
N
N
6
8
.
3
0
%
A
u
t
o
mat
e
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
l
i
v
e
r
d
i
so
r
d
e
r
s u
si
n
g
u
l
t
r
a
so
u
n
d
i
m
a
g
e
s [9
]
W
a
v
e
l
e
t
P
a
c
k
e
t
T
r
a
n
sf
o
r
m fo
r
se
g
men
t
a
t
i
o
n
,
S
V
M
f
o
r
C
l
a
ssi
f
i
c
a
t
i
o
n
9
5
%,
L
u
n
g
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
u
si
n
g
i
m
a
g
e
p
r
o
c
e
ssi
n
g
t
o
o
l
b
o
x
[
1
0
]
F
o
r
f
e
a
t
u
r
e
Ex
t
r
a
c
t
i
o
n
G
a
b
o
r
f
i
l
t
e
r
st
a
g
e
,
M
a
r
k
e
r
-
C
o
n
t
r
o
l
l
e
d
W
a
t
e
r
sh
e
d
f
o
r
S
e
g
me
n
t
a
t
i
o
n
8
4
.
5
5
%
D
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
c
a
n
c
e
r
o
u
s t
i
ssu
e
s
i
n
d
i
g
i
t
a
l
m
a
mm
o
g
r
a
ms
[
1
1
]
G
r
a
y
L
e
v
e
l
C
o
-
O
c
c
u
r
r
e
n
c
e
M
a
t
r
i
c
e
s (
G
L
C
M
s)
F
o
r
f
e
a
t
u
r
e
Ex
t
r
a
c
t
i
o
n
,
S
V
M
f
o
r
C
l
a
ss
i
f
i
c
a
t
i
o
n
9
5
%
S
k
i
n
l
e
si
o
n
c
l
a
ssi
f
i
c
a
t
i
o
n
f
r
o
m d
e
r
mo
sco
p
i
c
i
mag
e
s
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s [2
0
]
C
N
N
f
o
r
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
n
d
C
l
a
ssi
f
i
c
a
t
i
o
n
7
8
.
6
6
%
A
n
i
mag
e
-
b
a
se
d
g
a
n
g
r
e
n
e
d
i
se
a
se
c
l
a
ssi
f
i
c
a
t
i
o
n
C
N
N
f
o
r
F
e
a
t
u
r
e
Ex
t
r
a
c
t
i
o
n
,
S
V
M
f
o
r
C
l
a
ssi
f
i
c
a
t
i
o
n
8
5
%
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.
10
,
No
.
6
,
Decem
b
er
2020
:
6
0
0
1
-
6
0
0
7
6006
Fig
u
r
e
3
.
A
cc
u
r
ac
y
o
f
S
VM
g
an
g
r
e
n
e
d
is
ea
s
e
cla
s
s
i
f
icatio
n
5.
CO
NCLU
SI
O
N
I
n
th
is
p
ap
er
,
th
e
C
NN
w
as
u
s
ed
f
o
r
class
i
f
icatio
n
an
d
f
ea
t
u
r
e
ex
tr
ac
tio
n
o
f
g
a
n
g
r
e
n
e
d
is
ea
s
e
i
m
a
g
e
s
.
An
d
a
m
u
lticla
s
s
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
w
a
s
u
s
ed
f
o
r
th
e
class
i
f
icat
io
n
o
f
i
m
a
g
es
.
T
h
e
class
if
ica
tio
n
alg
o
r
ith
m
w
as
tr
ain
ed
w
it
h
th
e
f
ea
tu
r
es
ex
tr
ac
ted
f
r
o
m
d
if
f
er
en
t
i
m
a
g
es
u
s
i
n
g
co
n
v
o
lu
t
io
n
al
n
e
u
r
al
n
et
w
o
r
k
.
W
e
h
av
e
ap
p
lied
th
e
s
ta
n
d
ar
d
m
u
lticla
s
s
cla
s
s
i
f
ier
u
s
in
g
th
e
f
ea
t
u
r
es
to
cla
s
s
i
f
y
t
h
e
i
m
a
g
e
s
in
to
d
i
f
f
er
en
t
t
y
p
e
o
f
Gan
g
r
en
e
d
is
ea
s
es.
T
h
e
m
u
lticla
s
s
SV
M
class
i
f
ier
w
a
s
ap
p
lied
to
ac
h
iev
e
ef
f
ec
tiv
e
class
i
f
icatio
n
w
it
h
m
u
ltip
le
cla
s
s
es
.
T
o
th
e
g
r
e
atest
e
x
ten
t,
Ga
n
g
r
e
n
e
d
is
ea
s
e
class
i
f
icat
io
n
w
a
s
a
u
to
m
at
ed
u
s
i
n
g
an
i
m
ag
e
an
al
y
s
is
tec
h
n
iq
u
e.
Usi
n
g
t
h
e
test
d
ata,
th
e
th
r
ee
class
es
o
f
Gan
g
r
en
e
d
is
ea
s
e
s
,
d
r
y
,
w
et,
g
as
w
er
e
class
i
f
ied
u
s
i
n
g
t
h
e
SVM
clas
s
i
f
ier
an
d
r
esu
lt
a
n
al
y
s
i
s
s
h
o
w
n
a
n
av
er
ag
e
o
f
8
5
p
er
ce
n
t
ac
c
u
r
ac
y
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
ac
cu
r
ac
y
ca
n
b
e
i
m
p
r
o
v
ed
as w
e
ad
d
m
o
r
e
g
a
n
g
r
e
n
e
d
is
ea
s
e
i
m
ag
e
s
i
n
th
e
tr
ai
n
i
n
g
s
et.
RE
F
E
R
E
NC
E
S
[1
]
S
.
S
.
M
.
Z
.
A
li
, “
GA
N
G
RENE,
N
IBRT
-
G
EHC
T
e
c
h
n
ica
l
Re
p
o
rt,
”
p
p
.
1
-
1
6
,
2
0
1
2
.
[2
]
B.
S
tap
p
-
Ca
u
d
e
ll
,
“
G
a
n
g
re
n
e
:
Re
c
o
g
n
izin
g
a
n
d
trea
ti
n
g
c
e
ll
u
lar
n
e
c
ro
sis,
”
Asso
c
ia
ti
o
n
o
f
S
u
rg
ica
l
T
e
c
h
n
o
l
o
g
ists
,
p
p
.
5
4
7
-
5
5
2
,
2
0
0
8
.
[3
]
D.
K.
S
riv
a
sta
v
a
a
n
d
L
.
Bh
a
m
b
h
u
,
“
Da
ta Cl
a
ss
i
f
ic
a
ti
o
n
u
sin
g
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
,
”
J
o
u
r
n
a
l
o
f
T
h
e
o
re
ti
c
a
l
a
n
d
Ap
p
li
e
d
In
fo
rm
a
t
io
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
1
2
,
n
o
.
1
,
p
p
.
1
-
7
,
20
09
.
[4
]
T
.
Ha
stie
,
e
t
a
l.
,
“
Th
e
E
l
e
m
e
n
t
s
o
f
S
t
a
t
i
st
i
c
a
l
Le
a
r
n
i
n
g
:
D
a
t
a
M
in
in
g
,
In
fe
r
e
n
c
e
,
a
n
d
P
r
e
d
i
c
ti
o
n
,
”
S
p
ri
n
g
e
r
S
e
ries
in
S
tatist
ics
,
S
p
ri
n
g
e
r,
2
0
0
9
.
[5
]
S
.
W
id
o
d
o
,
R.
N.
R
o
h
m
a
h
,
B.
Ha
n
d
a
g
a
,
a
n
d
L
.
D.
D.
A
rin
i
,
“
L
u
n
g
d
ise
a
se
s
d
e
tec
ti
o
n
c
a
u
se
d
b
y
s
m
o
k
in
g
u
sin
g
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
,
”
T
EL
KO
M
NIKA
T
e
lec
o
mm
u
n
ica
ti
o
n
,
Co
mp
u
ti
n
g
,
El
e
c
tro
n
ics
a
n
d
C
o
n
tr
o
l
,
v
o
l.
1
7
,
n
o
.
3
,
p
p
.
1
2
5
6
-
1
2
6
6
,
Ju
n
.
20
19
.
[6
]
R.
P
riy
a
a
n
d
P
.
A
ru
n
a
,
“
Re
v
iew
o
f
a
u
to
m
a
ted
d
iag
n
o
sis
o
f
d
iab
e
ti
c
re
ti
n
o
p
a
th
y
u
sin
g
th
e
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
,”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
A
p
p
li
e
d
En
g
i
n
e
e
rin
g
Res
e
a
rc
h
,
v
o
l.
1
,
n
o
.
4
,
p
p
.
8
4
4
-
8
6
3
,
2
0
1
1
.
[7
]
K
.
Cra
m
m
e
r
a
n
d
Y
.
S
in
g
e
r,
“
On
th
e
A
lg
o
rit
h
m
ic
I
m
p
le
m
e
n
tatio
n
o
f
M
u
lt
icla
ss
Ke
rn
e
l
-
b
a
se
d
V
e
c
to
r
M
a
c
h
i
n
e
s
,
”
J
o
u
rn
a
l
o
f
M
a
c
h
i
n
e
L
e
a
rn
in
g
Res
e
a
rc
h
,
v
o
l.
2
,
p
p
.
2
6
5
-
2
9
2
,
2
0
0
1
.
[8
]
F
.
Niz
a
r
a
n
d
G
.
S
.
S
.
Ku
m
a
r
,
“
Clas
si
f
ic
a
ti
o
n
o
f
V
a
rio
u
s
S
k
in
L
e
sio
n
s
u
sin
g
S
V
M
a
n
d
KN
N
Clas
si
f
iers
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
f
In
n
o
v
a
ti
v
e
Res
e
a
rc
h
in
Co
mp
u
ter
a
n
d
Co
mm
u
n
ica
ti
o
n
E
n
g
i
n
e
e
rin
g
,
v
o
l.
4
,
n
o
.
8
,
p
p
.
1
4
7
1
0
-
1
4
7
1
5
,
2
0
1
6
.
[9
]
F
.
A
.
A
.
M
in
h
a
s,
e
t
a
l.
,
“
A
u
to
m
a
ted
Clas
sif
i
c
a
ti
o
n
o
f
L
iv
e
r
D
iso
rd
e
rs
u
si
n
g
Ultras
o
u
n
d
Im
a
g
e
s,
”
J
o
u
rn
a
l
o
f
M
e
d
ica
l
S
y
ste
ms
,
v
o
l.
3
6
,
n
o
.
5
,
p
p
.
3
1
6
3
-
3
1
7
2
,
2
0
1
2
.
[1
0
]
A
.
G
a
i
k
w
a
d
,
e
t
a
l.
,
“
L
u
n
g
c
a
n
c
e
r
d
e
tec
ti
o
n
u
si
n
g
d
ig
it
a
l
Im
a
g
e
p
ro
c
e
ss
in
g
On
CT
sc
a
n
I
m
a
g
e
s
,
”
In
ter
n
a
ti
o
n
a
l
Res
e
a
rc
h
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
(
IRJET
)
,
v
o
l.
3
,
n
o
.
0
4
,
p
p
.
2
3
7
9
-
2
3
8
1
,
2
0
1
6
.
[1
1
]
R.
Yo
g
a
m
a
n
g
a
la
m
a
n
d
B.
Ka
rth
ik
e
y
a
n
,
“
S
e
g
m
e
n
tatio
n
T
e
c
h
n
i
q
u
e
s
Co
m
p
a
riso
n
in
Im
a
g
e
P
ro
c
e
ss
in
g
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
(
IJ
ET
)
,
v
o
l
.
5
,
n
o
.
1
,
p
p
.
3
0
7
-
3
1
3
,
2
0
1
3
.
[1
2
]
D
.
Ka
u
r
a
n
d
Y.
Ka
u
r
,
“
V
a
ri
o
u
s
I
m
a
g
e
S
e
g
m
e
n
tatio
n
T
e
c
h
n
iq
u
e
s:
A
R
e
v
ie
w
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Co
mp
u
ter
S
c
ien
c
e
a
n
d
M
o
b
il
e
Co
m
p
u
ti
n
g
(
IJ
CS
M
C)
,
v
o
l.
3
,
n
o
.
5
,
p
p
.
8
0
9
-
8
1
4
,
2
0
1
4
.
[1
3
]
P
.
P
a
tel
a
n
d
A
.
T
h
a
k
k
a
r
,
“
T
h
e
u
p
su
rg
e
o
f
d
e
e
p
lea
rn
in
g
f
o
r
c
o
m
p
u
ter
v
isio
n
a
p
p
li
c
a
ti
o
n
s
,
”
I
n
ter
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
1
0
,
n
o
.
1
,
p
p
.
5
3
8
-
5
4
8
,
F
eb
.
2
0
2
0
.
[1
4
]
T
.
A
.
As
se
g
ie
a
n
d
P
.
S
.
Na
ir,
“
Ha
n
d
w
rit
ten
d
ig
it
s
re
c
o
g
n
it
i
o
n
w
it
h
d
e
c
isio
n
tree
c
las
sif
ic
a
ti
o
n
:
a
m
a
c
h
in
e
lea
rn
in
g
a
p
p
ro
a
c
h
,
”
I
n
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
9
,
n
o.
5
,
p
p
.
4
4
4
6
-
4
4
5
1
,
Oc
t
.
2
0
1
9
.
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
A
n
ima
g
e
-
b
a
s
ed
g
a
n
g
r
en
e
d
is
ea
s
e
cla
s
s
ifica
tio
n
(
P
r
a
mo
d
S
ek
h
a
r
a
n
N
a
ir
)
6007
[1
5
]
K.
Re
n
u
g
a
m
b
a
l
a
n
d
B.
S
e
n
th
il
ra
ja,
“
A
p
p
li
c
a
ti
o
n
o
f
Im
a
g
e
P
ro
c
e
ss
in
g
T
e
c
h
n
iq
u
e
s
in
P
lan
t
Dise
a
se
Re
c
o
g
n
it
io
n
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
in
e
e
rin
g
Res
e
a
rc
h
&
T
e
c
h
n
o
lo
g
y
(
IJ
ER
T
)
,
v
o
l.
4
,
n
o
.
3
,
p
p
.
9
1
9
-
9
2
3
,
2
0
1
5
.
[1
6
]
S
.
B.
Ja
d
h
a
v
,
e
t
a
l.
,
“
Co
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
s
f
o
r
lea
f
i
m
a
g
e
-
b
a
se
d
p
lan
t
d
ise
a
se
c
las
sif
i
c
a
ti
o
n
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Arti
fi
c
i
a
l
I
n
telli
g
e
n
c
e
(
IJ
-
AI)
,
v
o
l.
8
,
n
o
.
4
,
p
p
.
3
2
8
-
3
4
1
,
De
c
.
2
0
1
9
.
[1
7
]
H.
P
ra
se
ty
o
,
a
n
d
B.
A
.
P
.
A
k
a
rd
ih
a
s
,
“
Ba
ti
k
i
m
a
g
e
re
tri
e
v
a
l
u
sin
g
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
,
”
T
EL
KOM
NIKA
T
e
lec
o
mm
u
n
ica
ti
o
n
,
Co
m
p
u
t
in
g
,
El
e
c
tro
n
ics
a
n
d
C
o
n
tro
l
,
v
o
l.
1
7
,
n
o
.
6
,
p
p
.
3
0
1
0
-
3
0
1
8
,
De
c
.
20
19
.
[1
8
]
A
.
A
.
M
o
u
sta
f
a
,
e
t
a
l.
,
“
Op
ti
m
iz
a
ti
o
n
o
f
d
e
e
p
lea
rn
in
g
f
e
a
tu
re
s
fo
r
a
g
e
-
in
v
a
rian
t
f
a
c
e
re
c
o
g
n
it
io
n
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
t
e
r E
n
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
1
0
,
n
o
.
2
,
p
p
.
1
8
3
3
-
1
8
4
1
,
A
p
r
2
0
2
0
.
[1
9
]
A
.
A
.
A
b
d
u
ll
a
h
,
e
t
a
l.
,
“
Ce
rv
ic
a
l
c
a
n
c
e
r
d
e
tec
ti
o
n
m
e
th
o
d
u
sin
g
a
n
im
p
ro
v
e
d
c
e
ll
u
lar
n
e
u
ra
l
n
e
tw
o
rk
(CN
N)
a
lg
o
rit
h
m
,
”
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
t
ric
a
l
En
g
i
n
e
e
rin
g
a
n
d
C
o
mp
u
ter
S
c
ien
c
e
,
v
o
l.
1
4
,
n
o
.
1
,
p
p
.
2
1
0
-
2
1
8
,
A
p
r
.
2
0
1
9
.
[2
0
]
N.
Ka
m
a
ru
d
d
in
,
A
.
W
a
h
a
b
,
a
n
d
Y.
Ro
z
a
id
i
,
“
Ne
u
ro
-
p
h
y
sio
lo
g
ica
l
p
o
rn
a
d
d
ictio
n
d
e
tec
ti
o
n
u
sin
g
m
a
c
h
in
e
lea
rn
in
g
a
p
p
ro
a
c
h
,
”
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l.
1
6
,
n
o
.
2
,
p
p
.
744
-
7
5
1
,
No
v
.
20
19
.
[2
1
]
Y.
T
a
n
g
,
“
D
e
e
p
L
e
a
rn
in
g
u
sin
g
L
in
e
a
r
S
u
p
p
o
r
t
V
e
c
to
r
M
a
c
h
in
e
s,
”
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
M
a
c
h
in
e
L
e
a
r
n
in
g
,
Ch
a
ll
e
n
g
e
s in
Rep
re
se
n
ta
t
io
n
L
e
a
rn
in
g
W
o
rk
sh
o
p
,
A
tl
a
n
ta G
e
o
rg
ia,
USA
,
2
0
1
3
.
[2
2
]
J.
Na
g
i
,
“
T
h
e
A
p
p
li
c
a
ti
o
n
o
f
I
m
a
g
e
P
ro
c
e
ss
in
g
a
n
d
M
a
c
h
in
e
L
e
a
rn
in
g
T
e
c
h
n
iq
u
e
s
f
o
r
De
tec
ti
o
n
a
n
d
Clas
s
if
ica
ti
o
n
o
f
Ca
n
c
e
ro
u
s
T
issu
e
s
i
n
Dig
it
a
l
M
a
m
m
o
g
r
a
m
s,
”
F
a
c
u
lt
y
o
f
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
Un
iv
e
rsit
y
o
f
M
a
la
y
a
Ku
a
la L
u
m
p
u
r,
p
p
.
1
-
3
3
2
,
2
0
1
1
.
[2
3
]
G
.
Do
u
g
h
e
rt
y
,
“
Dig
it
a
l
I
m
a
g
e
P
ro
c
e
ss
in
g
f
o
r
M
e
d
ica
l
A
p
p
li
c
a
ti
o
n
s,
”
Ne
w
Yo
rk
,
Ca
m
b
rid
g
e
U
n
iv
e
rsity
P
re
ss
,
2
0
0
9
.
[2
4
]
T
.
Ba
th
in
i,
a
n
d
B.
G
a
d
g
a
y
,
“
H
y
b
rid
e
n
h
a
n
c
e
d
ICA
&
KSV
M
b
a
se
d
b
ra
in
tu
m
o
r
im
a
g
e
se
g
m
e
n
tatio
n
”
In
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
Co
m
p
u
t
e
r
S
c
ien
c
e
,
v
o
l.
1
4
,
n
o
.
1
,
p
p
.
4
7
8
-
4
8
9
,
A
p
r
.
20
19
.
[2
5
]
A
.
R
.
L
o
p
e
z
,
“
S
k
in
le
sio
n
d
e
tec
ti
o
n
f
ro
m
d
e
r
m
o
sc
o
p
ic
i
m
a
g
e
s
u
sin
g
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
,
”
A
De
g
r
e
e
T
h
e
sis
S
u
b
m
it
ted
to
t
h
e
F
a
c
u
lt
y
o
f
th
e
Esc
o
la
T`
e
c
n
ica
d
’En
g
in
y
e
ri
a
d
e
T
e
lec
o
m
u
n
ica
c
i
´
o
d
e
Ba
rc
e
lo
n
a
Un
iv
e
rsitat
P
o
li
t`
e
c
n
ica
d
e
Ca
talu
n
y
a
,
2
0
1
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.