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.
8
,
No
.
5
,
Octo
b
e
r
2
0
1
8
,
p
p
.
3
3
9
2
~
3
3
9
8
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
8
i
5
.
pp
3
3
9
2
-
3398
3392
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
Feature
Ex
tractio
n of Ch
est
X
-
ra
y
I
m
a
g
es a
nd A
na
ly
sis
U
sing
PCA
a
nd
k
P
CA
Ro
o
pa
H
1
,
Ash
a
T
2
1
De
p
a
rtme
n
t
o
f
I.
S
.
E,
Ba
n
g
a
lo
re
I
n
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
,
K.
R.
Ro
a
d
,
Ba
n
g
a
lo
re
,
I
n
d
ia
2
De
p
a
rtme
n
t
o
f
C.
S
.
E,
Ba
n
g
a
lo
re
In
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
,
K.
R.
Ro
a
d
,
Ba
n
g
a
lo
re
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
9
,
2
0
1
7
R
ev
i
s
ed
Feb
2
2
,
2
0
1
8
A
cc
ep
ted
Mar
8
,
2
0
1
8
T
u
b
e
rc
u
lo
sis
(T
B)
is
a
n
in
f
e
c
ti
o
u
s
d
ise
a
se
c
a
u
se
d
b
y
m
y
c
o
b
a
c
ter
iu
m
w
h
ich
c
a
n
b
e
d
iag
n
o
se
d
b
y
it
s
v
a
r
io
u
s
sy
m
p
to
m
s
li
k
e
f
e
v
e
r,
c
o
u
g
h
,
e
tc.
T
u
b
e
rc
u
lo
sis
c
a
n
a
lso
b
e
a
n
a
l
y
z
e
d
b
y
u
n
d
e
rsta
n
d
i
n
g
th
e
c
h
e
st
x
-
ra
y
o
f
th
e
p
a
ti
e
n
t
w
h
ich
is
re
v
e
a
led
b
y
a
n
e
x
p
e
rt
p
h
y
sic
ian
.
T
h
e
c
h
e
st
x
-
ra
y
i
m
a
g
e
c
o
n
tain
s
m
a
n
y
f
e
a
tu
re
s
w
h
ich
c
a
n
n
o
t
b
e
d
irec
tl
y
u
se
d
b
y
a
n
y
c
o
m
p
u
ter
s
y
ste
m
f
o
r
a
n
a
l
y
z
in
g
th
e
d
ise
a
se
.
F
e
a
tu
re
s
o
f
c
h
e
st
x
-
ra
y
i
m
a
g
e
s
m
u
st
b
e
u
n
d
e
rst
o
o
d
a
n
d
e
x
trac
ted
,
so
th
a
t
it
c
a
n
b
e
p
r
o
c
e
ss
e
d
to
a
f
o
rm
to
b
e
f
e
d
to
a
n
y
c
o
m
p
u
ter
s
y
ste
m
f
o
r
d
ise
a
se
a
n
a
l
y
sis.
T
h
is
p
a
p
e
r
p
re
se
n
ts
f
e
a
tu
re
e
x
trac
ti
o
n
o
f
c
h
e
st
x
-
r
a
y
i
m
a
g
e
w
h
ich
c
a
n
b
e
u
se
d
a
s
a
n
in
p
u
t
f
o
r
a
n
y
d
a
ta
m
in
in
g
a
lg
o
rit
h
m
f
o
r
T
B
d
ise
a
se
a
n
a
l
y
sis.
S
o
tex
tu
re
a
n
d
sh
a
p
e
b
a
se
d
f
e
a
tu
re
s
a
re
e
x
trac
ted
f
ro
m
x
-
r
a
y
i
m
a
g
e
u
sin
g
im
a
g
e
p
ro
c
e
ss
in
g
c
o
n
c
e
p
ts
.
T
h
e
f
e
a
tu
re
s
e
x
trac
t
e
d
a
re
a
n
a
l
y
z
e
d
u
sin
g
p
ri
n
c
ip
a
l
c
o
m
p
o
n
e
n
t
a
n
a
ly
sis
(P
CA
)
a
n
d
k
e
rn
e
l
p
ri
n
c
ip
a
l
c
o
m
p
o
n
e
n
t
a
n
a
ly
sis
(k
P
CA
)
tec
h
n
iq
u
e
s.
F
il
ter
a
n
d
w
ra
p
p
e
r
f
e
a
tu
re
se
lec
ti
o
n
m
e
th
o
d
u
si
n
g
li
n
e
a
r
re
g
re
ss
io
n
m
o
d
e
l
w
e
re
a
p
p
li
e
d
o
n
t
h
e
se
tec
h
n
i
q
u
e
s.
T
h
e
p
e
rf
o
rm
a
n
c
e
o
f
P
CA
a
n
d
k
P
CA
a
re
a
n
a
ly
z
e
d
a
n
d
f
o
u
n
d
t
h
a
t
t
h
e
a
c
c
u
ra
c
y
o
f
P
CA
u
si
n
g
w
ra
p
p
e
r
a
p
p
ro
a
c
h
is
9
6
.
0
7
%
w
h
e
n
c
o
m
p
a
re
d
to
th
e
a
c
c
u
ra
c
y
o
f
k
P
CA
w
h
ich
is
6
2
.
5
0
%
.
P
CA
p
e
rf
o
r
m
s
w
e
ll
th
a
n
k
P
CA
w
it
h
a
g
o
o
d
a
c
c
u
ra
c
y
.
K
ey
w
o
r
d
:
C
las
s
i
f
icatio
n
Featu
r
e
ex
tr
ac
tio
n
I
m
ag
e
m
i
n
i
n
g
T
u
b
er
cu
lo
s
is
Co
p
y
rig
h
t
©
2
0
1
8
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
:
R
o
o
p
a
H,
Dep
ar
t
m
en
t o
f
I
n
f
o
r
m
atio
n
Sc
ien
ce
an
d
E
n
g
i
n
ee
r
in
g
,
B
an
g
alo
r
e
I
n
s
ti
tu
te
O
f
T
ec
h
n
o
lo
g
y
,
K
R
R
o
ad
,
B
an
g
alo
r
e
-
5
6
0
0
0
4
,
Ka
r
n
atak
a,
I
n
d
ia
.
E
m
ail:
r
o
o
p
atej
as@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Me
d
ical
i
m
ag
e
s
ar
e
co
m
p
le
x
in
n
a
tu
r
e.
T
h
e
in
f
o
r
m
a
tio
n
p
r
esen
t
in
a
m
ed
ical
i
m
a
g
e
m
u
s
t
b
e
an
al
y
ze
d
an
d
in
v
es
tig
a
ted
f
o
r
an
y
s
p
ec
i
f
ic
ap
p
licatio
n
.
R
a
w
i
m
ag
e
co
n
tai
n
s
m
an
y
p
r
o
p
er
t
ies
ass
o
ciate
d
w
i
t
h
it
ca
lled
as
f
ea
tu
r
es.
Feat
u
r
es
ca
n
b
e
o
f
lo
w
le
v
el
f
ea
t
u
r
e
a
n
d
h
i
g
h
lev
el
f
ea
tu
r
e.
Fro
m
t
h
e
o
r
ig
in
al
i
m
ag
e,
lo
w
lev
el
f
ea
t
u
r
es
ar
e
ex
tr
ac
ted
b
u
t
h
i
g
h
lev
el
f
ea
t
u
r
es
ar
e
e
x
tr
ac
ted
b
ased
o
n
lo
w
le
v
el
f
ea
t
u
r
e
s
.
Feat
u
r
es
co
n
tai
n
in
f
o
r
m
atio
n
l
ik
e
co
lo
r
,
tex
t
u
r
e,
s
h
ap
e
o
r
co
n
tex
t.
T
u
b
er
cu
lo
s
is
(
T
B
)
[
9
]
is
an
in
f
ec
tio
u
s
d
is
ea
s
e
ca
u
s
ed
b
y
m
y
co
b
ac
ter
iu
m
w
h
ic
h
u
s
u
al
l
y
a
f
f
ec
t
s
lu
n
g
s
.
T
B
is
tr
an
s
m
itted
f
r
o
m
o
n
e
p
er
s
o
n
to
an
o
th
er
th
r
o
u
g
h
air
w
h
e
n
an
i
n
f
ec
ted
p
er
s
o
n
s
n
ee
ze
s
o
r
co
u
g
h
s
.
T
B
m
o
s
tl
y
o
cc
u
r
s
i
n
lu
n
g
s
b
u
t
ca
n
al
s
o
o
cc
u
r
in
o
th
er
p
ar
ts
o
f
th
e
b
o
d
y
lik
e
b
r
ain
,
s
p
in
e,
k
id
n
e
y
a
n
d
b
o
n
es.
T
h
e
m
ai
n
s
y
m
p
to
m
s
o
f
T
B
ar
e
lo
s
s
o
f
w
e
ig
h
t,
f
e
v
er
,
ch
ills
,
w
ea
k
n
es
s
,
ch
e
s
t
x
-
r
a
y
i
m
ag
e
f
i
n
d
in
g
s
a
n
d
co
u
g
h
.
E
v
er
y
y
ea
r
W
o
r
ld
T
B
Da
y
r
ec
o
g
n
ized
o
n
Ma
r
ch
2
4
is
an
o
p
p
o
r
tu
n
it
y
to
r
aise
a
w
a
r
en
es
s
ab
o
u
t
T
B
an
d
s
u
p
p
o
r
t
w
o
r
ld
w
id
e
T
B
p
r
ev
en
tio
n
an
d
co
n
tr
o
l
ef
f
o
r
ts
.
T
h
e
W
o
r
ld
Hea
lth
Or
g
an
izatio
n
(
W
HO)
[
1
2
]
m
o
n
i
to
r
s
th
e
le
v
el
o
f
T
B
in
ev
er
y
co
u
n
tr
y
in
t
h
e
w
o
r
ld
.
W
o
r
ld
w
id
e
m
o
r
e
t
h
a
n
9
m
ill
io
n
p
eo
p
le
d
ev
elo
p
T
B
an
n
u
a
ll
y
an
d
1
.
5
m
ill
io
n
d
ie
f
r
o
m
t
h
e
d
i
s
ea
s
e.
Featu
r
es
r
ep
r
esen
t
in
f
o
r
m
at
io
n
in
a
n
i
m
ag
e.
T
o
u
n
d
er
s
ta
n
d
th
e
in
f
o
r
m
a
tio
n
p
r
esen
t
in
a
n
i
m
ag
e,
i
t
m
u
s
t
b
e
an
al
y
ze
d
an
d
m
ea
s
u
r
ed
in
v
ar
io
u
s
an
g
les
to
g
et
r
elev
an
t
i
n
f
o
r
m
atio
n
i
n
a
p
ar
ticu
lar
d
o
m
ain
li
k
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
F
ea
tu
r
e
E
xtra
ctio
n
o
f C
h
est X
-
r
a
y
I
ma
g
es a
n
d
A
n
a
lysi
s
u
s
in
g
P
C
A
a
n
d
k
P
C
A
(
R
o
o
p
a
H
)
3393
m
ed
ical
i
m
ag
e,
s
atellite
i
m
a
g
es,
etc.
,
s
o
,
f
ea
tu
r
e
e
x
tr
ac
tio
n
[
1
3
]
,
[
1
4
]
p
lay
s
a
n
i
m
p
o
r
ta
n
t
r
o
le
in
an
al
y
zi
n
g
m
ed
ical
i
m
a
g
e
li
k
e
T
B
im
a
g
e.
P
C
A
is
a
l
in
ea
r
m
et
h
o
d
w
h
ic
h
u
s
es a
n
o
r
t
h
o
g
o
n
al
tr
an
s
f
o
r
m
atio
n
to
co
n
v
er
t set
o
f
v
al
u
es
o
f
p
o
s
s
ib
l
y
co
r
r
elate
d
f
ea
tu
r
es
i
n
to
a
s
et
o
f
u
n
co
r
r
elate
d
f
ea
tu
r
es
n
a
m
ed
as
p
r
in
c
ip
al
co
m
p
o
n
e
n
ts
.
I
t
p
u
ts
all
d
ata
alo
n
g
t
h
e
ax
es
w
h
er
e
th
e
v
ar
ia
n
ce
o
f
f
ir
s
t
p
r
in
cip
al
co
m
p
o
n
e
n
t
is
h
i
g
h
est
w
h
e
n
co
m
p
ar
ed
to
o
th
er
p
r
in
cip
al
co
m
p
o
n
e
n
t
s
.
Her
e
th
e
a
x
es
co
r
r
esp
o
n
d
to
th
e
lar
g
est
E
ig
e
n
v
al
u
es
o
f
t
h
e
d
ata.
k
P
C
A
is
a
n
o
n
li
n
ea
r
tec
h
n
iq
u
e
w
h
ic
h
i
s
an
e
x
te
n
s
io
n
o
f
P
C
A
t
h
at
u
s
e
s
k
er
n
el
m
et
h
o
d
s
.
P
r
in
cip
al
co
m
p
o
n
e
n
ts
ar
e
co
m
p
u
ted
u
s
in
g
k
er
n
el
f
u
n
c
ti
o
n
s
b
y
n
o
n
lin
ea
r
m
ap
p
in
g
o
f
in
p
u
t
f
ea
t
u
r
e
s
p
ac
e.
T
h
ese
f
ea
tu
r
es
ar
e
f
i
n
all
y
p
lace
d
in
a
n
o
n
li
n
ea
r
l
y
tr
a
n
s
f
o
r
m
ed
s
p
ac
e.
Feat
u
r
es
ex
tr
ac
ted
[
1
0
]
ar
e
an
aly
ze
d
an
d
co
m
p
ar
ed
o
n
lin
ea
r
an
d
n
o
n
li
n
ea
r
f
ea
t
u
r
e
s
p
ac
e,
th
e
n
t
h
eir
p
er
f
o
r
m
a
n
ce
ar
e
m
ea
s
u
r
ed
u
s
i
n
g
d
ata
m
i
n
i
n
g
m
o
d
els
li
k
e
li
n
ea
r
r
e
g
r
ess
io
n
m
o
d
el.
L
in
ea
r
r
e
g
r
ess
io
n
m
o
d
el
is
a
m
eth
o
d
to
f
i
n
d
a
r
elatio
n
s
h
ip
b
et
w
ee
n
o
n
e
d
ep
en
d
en
t
v
ar
iab
le
an
d
s
er
ie
s
o
f
ch
a
n
g
i
n
g
in
d
ep
en
d
e
n
t v
ar
ia
b
les b
y
f
itt
in
g
a
li
n
ea
r
eq
u
atio
n
to
o
b
s
er
v
ed
d
ata.
P
er
n
er
et
a
l
[
2
]
h
av
e
d
is
cu
s
s
e
d
ab
o
u
t
f
r
am
e
w
o
r
k
o
f
i
m
a
g
e
m
i
n
in
g
,
d
ev
elo
p
ed
d
ata
m
i
n
in
g
an
d
i
m
a
g
e
p
r
o
ce
s
s
in
g
to
o
l
w
h
ich
is
h
elp
f
u
l
f
o
r
m
ed
ical
i
m
a
g
e
a
n
al
y
s
i
s
.
Descr
ip
tio
n
s
o
f
li
s
t
o
f
attr
i
b
u
tes
a
s
g
iv
e
n
b
y
ex
p
er
ts
ar
e
s
to
r
ed
in
a
d
atab
as
e
th
en
a
class
if
ica
tio
n
tec
h
n
iq
u
e
d
ec
is
io
n
tr
ee
in
d
u
c
tio
n
tr
ee
is
ap
p
lied
to
th
is
to
ex
tr
ac
t e
x
p
er
t k
n
o
w
led
g
e.
T
h
i
s
to
o
l
w
as
u
s
ed
f
o
r
v
ar
io
u
s
ap
p
licatio
n
s
l
ik
e
b
r
ea
s
t M
R
I
d
at
a,
etc.
A
s
h
a
et
a
l
[
8
]
u
s
ed
d
ata
m
i
n
i
n
g
tech
n
iq
u
e
s
lik
e
Ass
o
ciatio
n
R
u
le
Mi
n
in
g
(
AR
M)
o
n
T
B
d
ata
s
ets
to
i
m
p
r
o
v
e
T
B
d
is
ea
s
e
p
r
ed
ictio
n
.
T
h
e
s
y
m
p
to
m
s
o
f
T
B
ar
e
c
o
n
s
id
er
ed
an
d
m
an
y
d
escr
ip
tiv
e
r
u
les
w
er
e
w
r
it
ten
an
d
t
h
ese
w
er
e
co
m
b
i
n
ed
w
it
h
an
as
s
o
ciatio
n
class
i
f
icatio
n
tech
n
iq
u
e
u
s
ed
f
o
r
p
r
e
d
ictin
g
T
B
.
P
ed
r
o
et
a
l
[
3
]
ex
tr
ac
ted
tex
tu
r
e
an
d
s
h
ap
e
b
ased
f
ea
t
u
r
es
f
r
o
m
MRI
d
ata,
ap
p
lied
s
tati
s
tical
ass
o
ciatio
n
r
u
le
s
,
a
n
d
u
s
ed
co
n
ti
n
u
o
u
s
f
ea
tu
r
e
s
elec
tio
n
co
n
ce
p
t
s
to
f
i
n
d
p
atter
n
s
f
r
o
m
t
h
ese
d
ata.
M.
Su
g
an
t
h
i
et
a
l
[
6
]
u
s
ed
M
u
lti
o
b
j
ec
tiv
e
Ge
n
etic
A
l
g
o
r
it
h
m
(
MO
G
A
)
to
ex
tr
ac
t
tex
t
u
r
e
an
d
s
h
ap
e
b
ased
f
ea
t
u
r
es
f
r
o
m
b
r
ea
s
t
tu
m
o
r
d
ata.
L
i
–
Yeh
C
h
u
n
g
et
a
l
[
7
]
u
s
ed
f
ea
tu
r
e
s
elec
tio
n
an
d
T
ag
u
ch
i
g
en
et
ic
alg
o
r
ith
m
to
g
e
th
er
o
n
DN
A
m
icr
o
ar
r
ay
d
ata
th
e
n
KNN
w
i
th
L
ea
v
e
O
n
e
O
u
t
C
r
o
s
s
Valid
at
io
n
(
L
OO
C
V)
w
a
s
u
s
ed
to
ev
al
u
ate
t
h
e
p
er
f
o
r
m
a
n
ce
.
Ma
h
m
o
o
d
ab
ad
i
et
a
l
[
4
]
u
s
ed
P
C
A
to
ex
tr
ac
t
f
ea
t
u
r
es
o
f
b
r
ain
MRS
d
ata
th
e
n
Si
m
p
l
e
Gen
etic
A
l
g
o
r
ith
m
(
S
G
A
)
is
u
s
ed
to
d
is
cr
i
m
i
n
ate
th
e
s
e
f
ea
tu
r
es.
L
i
u
Yih
u
i
et
al
[
5
]
ex
tr
ac
ted
w
a
v
elet
f
ea
t
u
r
es
f
r
o
m
m
icr
o
ar
r
a
y
d
ata
th
en
Su
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
(
SVM)
w
a
s
u
s
ed
f
o
r
clas
s
if
icatio
n
.
Z
y
o
u
t
et
a
l
[
1
1
]
ex
tr
ac
ted
tex
t
u
al
p
atter
n
f
r
o
m
m
a
m
m
o
g
r
a
m
i
m
a
g
es
an
d
P
ar
ticle
S
w
ar
m
Op
ti
m
iza
tio
n
(
P
SO)
w
as
a
p
p
lied
to
s
elec
t
t
h
e
m
o
s
t
d
is
cr
i
m
i
n
ativ
e
f
ea
t
u
r
es
t
h
en
SV
M
w
a
s
u
s
ed
f
o
r
class
if
icatio
n
.
R
o
o
p
a
et
a
l
[
1
5
]
u
s
ed
cit
y
b
lo
ck
d
is
tan
c
e
m
ea
s
u
r
e
f
o
r
s
e
g
m
e
n
ti
n
g
ch
e
s
t
x
-
r
a
y
i
m
ag
e
w
h
ic
h
h
elp
s
in
d
i
ag
n
o
s
is
o
f
T
B
.
R
esear
ch
o
n
f
ea
t
u
r
e
ex
tr
ac
tio
n
o
f
v
ar
io
u
s
i
m
a
g
e
d
ata
o
n
d
if
f
er
en
t
d
o
m
ai
n
ap
p
licatio
n
s
h
av
e
b
ee
n
ca
r
r
ied
o
n
b
u
t
n
o
t
o
n
th
e
ch
es
t
x
-
r
a
y
i
m
a
g
e
r
elate
d
to
T
B
d
is
ea
s
e.
T
h
e
ai
m
o
f
th
i
s
p
ap
er
is
to
an
al
y
ze
ch
es
t
x
-
r
ay
i
m
a
g
e
to
ex
tr
ac
t
r
elev
a
n
t
f
ea
tu
r
e
s
th
at
r
ep
r
es
en
t
s
s
y
m
p
to
m
s
o
f
T
B
b
y
ap
p
l
y
i
n
g
i
m
ag
e
p
r
o
ce
s
s
i
n
g
co
n
ce
p
ts
.
T
h
e
ex
tr
ac
ted
f
ea
t
u
r
es
ar
e
ex
a
m
i
n
ed
u
s
i
n
g
P
C
A
an
d
k
P
C
A
,
th
e
n
t
h
e
tr
an
s
f
o
r
m
ed
f
ea
t
u
r
e
s
p
ac
e
is
s
u
b
j
ec
ted
to
lin
ea
r
r
eg
r
ess
io
n
m
o
d
el
f
o
r
class
i
f
y
i
n
g
t
h
e
T
B
d
is
ea
s
e.
T
h
e
p
ap
e
r
is
o
r
g
an
ized
as
f
o
llo
w
s
.
Sect
io
n
2
d
is
cu
s
s
es
ab
o
u
t
p
r
o
p
o
s
ed
m
eth
o
d
f
o
r
ex
tr
a
ctin
g
an
d
s
elec
ti
n
g
f
ea
t
u
r
es
f
r
o
m
x
-
r
a
y
i
m
a
g
es
,
a
n
al
y
ze
u
s
i
n
g
P
C
A
a
n
d
k
P
C
A
b
y
ap
p
l
y
i
n
g
li
n
ea
r
r
eg
r
es
s
io
n
m
o
d
el.
E
x
p
er
i
m
e
n
tal
i
llu
s
tr
ati
o
n
an
d
r
es
u
lt
s
ar
e
d
escr
ib
ed
in
d
etail
i
n
S
ec
tio
n
s
3
.
T
h
is
p
ap
er
is
c
o
n
cl
u
d
ed
in
S
ec
tio
n
4
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
C
h
e
s
t
x
-
r
a
y
i
m
ag
e
co
n
tai
n
s
r
elev
an
t,
ir
r
ele
v
an
t
a
n
d
r
ed
u
n
d
an
t
i
n
f
o
r
m
atio
n
.
Feat
u
r
es
w
h
ic
h
ar
e
r
elev
an
t
a
n
d
in
f
o
r
m
ati
v
e
w
ith
r
esp
ec
t
to
T
B
d
is
ea
s
e
s
h
o
u
l
d
b
e
c
o
n
s
id
er
ed
.
T
h
e
x
-
r
a
y
i
m
ag
e
m
u
s
t
f
ir
s
t
b
e
p
r
ep
r
o
ce
s
s
ed
an
d
t
h
e
n
i
m
p
o
r
tan
t
f
ea
t
u
r
es
ar
e
e
x
tr
ac
ted
f
r
o
m
th
e
a
f
f
ec
ted
r
eg
io
n
o
f
x
-
r
a
y
u
s
in
g
i
m
a
g
e
p
r
o
ce
s
s
in
g
m
et
h
o
d
s
.
T
h
e
f
o
llo
w
i
n
g
f
ig
u
r
e
Fi
g
u
r
e
1
s
h
o
w
s
th
e
p
r
o
p
o
s
ed
s
tep
s
in
v
o
lv
ed
in
ex
tr
ac
tin
g
an
d
s
elec
ti
n
g
f
ea
t
u
r
es f
r
o
m
a
x
-
r
a
y
i
m
ag
e,
t
h
e
n
an
al
y
s
e
it
u
s
in
g
d
ata
m
i
n
i
n
g
cla
s
s
i
f
icatio
n
tech
n
iq
u
e.
Fig
u
r
e
1
.
X
-
r
a
y
i
m
a
g
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
a
n
d
s
elec
tio
n
T
h
e
m
ai
n
s
tep
s
in
v
o
lv
ed
i
n
an
al
y
zi
n
g
a
n
d
ex
tr
ac
ti
n
g
f
ea
t
u
r
e
s
f
r
o
m
x
-
r
a
y
i
m
ag
e
b
y
ap
p
l
y
in
g
i
m
a
g
e
p
r
o
ce
s
s
in
g
a
n
d
d
ata
m
i
n
i
n
g
tec
h
n
iq
u
es
ar
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.
8
,
No
.
5
,
Octo
b
er
2
0
1
8
:
3
3
9
2
–
3
3
9
8
3394
First,
an
x
-
r
a
y
i
m
ag
e
i
s
tak
e
n
as in
p
u
t.
P
r
ep
r
o
ce
s
s
in
g
:
P
r
ep
r
o
ce
s
s
in
g
o
f
th
e
x
-
r
a
y
i
m
a
g
e
is
d
o
n
e
to
r
e
m
o
v
e
n
o
is
e
a
n
d
r
ed
u
n
d
an
t d
ata
if
p
r
esen
t a
n
y
.
T
h
is
is
d
o
n
e
u
s
i
n
g
Ga
u
s
s
ia
n
b
lu
r
f
ilte
r
m
e
th
o
d
.
Featu
r
e
E
x
tr
ac
t
io
n
:
Geo
m
etr
ic
f
ea
tu
r
e
s
an
d
T
ex
t
u
r
e
b
ased
f
ea
t
u
r
es
ca
n
b
e
u
s
ed
to
m
ea
s
u
r
e
th
e
c
h
ar
ac
ter
is
tics
o
f
T
B
.
B
o
th
th
e
s
h
ap
e
d
escr
ip
to
r
s
an
d
tex
tu
r
e
d
escr
ip
to
r
s
w
er
e
e
x
tr
ac
ted
f
r
o
m
x
-
r
a
y
i
m
a
g
e.
E
x
tr
ac
ti
n
g
a
s
m
a
n
y
f
ea
t
u
r
es f
r
o
m
t
h
e
r
eg
io
n
o
f
i
n
t
er
est o
f
T
B
is
o
n
e
th
e
co
n
ce
r
n
in
t
h
is
w
o
r
k
w
h
ic
h
i
s
d
o
n
e
b
y
ap
p
ly
i
n
g
r
o
ip
o
ly
()
f
u
n
ctio
n
u
s
in
g
m
atlab
s
o
f
t
w
ar
e.
Sh
ap
e
b
ased
f
ea
tu
r
es
w
er
e
u
s
ed
to
m
ea
s
u
r
e
th
e
r
eg
io
n
o
f
in
ter
est
in
a
T
B
i
m
a
g
e.
T
h
e
s
tatis
tics
li
k
e
A
r
ea
,
P
er
i
m
eter
,
C
o
o
r
d
in
ates
o
f
r
eg
io
n
ce
n
tr
o
id
,
Ma
j
o
r
Ax
is
L
e
n
g
th
,
Mi
n
o
r
A
x
is
L
en
g
t
h
,
E
cc
en
tr
icit
y
,
Or
ien
tatio
n
,
etc.
,
ar
e
s
o
m
e
o
f
t
h
e
ch
ar
ac
ter
is
t
ics
o
f
s
h
ap
e
b
ased
f
ea
tu
r
e
e
x
tr
ac
tio
n
w
h
ich
is
o
b
tai
n
ed
b
y
an
al
y
z
in
g
ex
ter
n
al
b
o
u
n
d
ar
y
o
f
th
e
x
-
r
a
y
i
m
a
g
e.
T
h
ese
f
e
atu
r
es
ar
e
o
b
tain
ed
b
y
u
s
i
n
g
f
u
n
ctio
n
ca
lled
as
r
eg
io
n
p
r
o
p
s
().
T
ex
tu
r
e
d
escr
ip
to
r
s
p
r
o
p
o
s
ed
b
y
Har
alick
[
1
]
d
ef
in
es
f
o
u
r
te
en
s
ta
tis
tic
s
t
h
at
ca
n
b
e
ca
lcu
l
ated
f
r
o
m
th
e
co
-
o
cc
u
r
r
en
ce
m
atr
ix
o
f
th
e
i
m
a
g
e.
T
ex
tu
r
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
r
e
f
er
s
to
s
u
r
f
ac
e
ch
ar
ac
ter
is
tic
s
an
d
ap
p
ea
r
an
ce
o
f
an
o
b
j
ec
t
in
an
i
m
ag
e.
E
n
tr
o
p
y
c
a
n
b
e
f
o
u
n
d
b
y
u
s
in
g
en
tr
o
p
y
(
)
,
g
r
a
y
cr
o
p
s
(
)
f
u
n
ctio
n
ca
n
b
e
u
s
ed
to
e
x
tr
ac
t
Ho
m
o
g
e
n
eit
y
,
C
o
n
tr
as
t,
E
n
er
g
y
,
C
o
r
r
elati
o
n
.
n
u
m
el(
U
L
)
w
h
er
e
UL
r
ep
r
esen
ts
u
n
i
f
o
r
m
i
t
y
,
Me
an
,
Stan
d
ar
d
Dev
iatio
n
ca
n
b
e
ca
lcu
lated
u
s
i
n
g
SD=
s
q
r
t(
VR
)
W
h
er
e
VR
r
ep
r
esen
t
s
th
e
v
ar
ia
n
ce
a
n
d
Sk
e
w
n
es
s
b
y
u
s
i
n
g
f
u
n
ct
io
n
s
k
e
w
n
ess
(
)
.
All
t
h
ese
f
ea
tu
r
e
s
v
alu
e
s
w
er
e
ex
tr
ac
ted
f
r
o
m
c
h
est
x
-
r
a
y
i
m
a
g
es.
P
r
in
cip
al
C
o
m
p
o
n
en
t
A
n
al
y
s
is
(
P
C
A
)
an
d
Ker
n
el
P
r
in
cip
al
C
o
m
p
o
n
en
t
An
al
y
s
i
s
(
k
P
C
A
)
:
P
C
A
is
a
li
n
ea
r
m
et
h
o
d
w
h
e
n
ap
p
lied
to
th
e
ex
tr
ac
ted
f
ea
tu
r
es
o
f
s
t
ep
3
r
esu
lts
i
n
ax
e
s
th
a
t
co
n
tain
s
co
r
r
esp
o
n
d
in
g
p
r
in
cip
al
E
ig
e
n
v
ec
to
r
s
w
h
ic
h
r
ep
r
esen
ts
t
h
e
d
ata
th
at
is
s
p
r
ea
d
o
u
t
alo
n
g
t
h
is
a
x
es.
I
t
p
u
ts
all
f
ea
t
u
r
es
alo
n
g
t
h
e
ax
e
s
w
h
er
e
th
e
v
ar
ia
n
ce
o
f
f
ir
s
t
p
r
in
cip
a
l
co
m
p
o
n
en
t
is
h
i
g
h
e
s
t
w
h
en
co
m
p
ar
ed
to
o
th
er
p
r
i
n
cip
al
co
m
p
o
n
en
ts
.
Her
e
t
h
e
ax
e
s
co
r
r
esp
o
n
d
to
th
e
lar
g
est
E
i
g
e
n
v
al
u
e
s
o
f
t
h
e
d
ata
.
P
C
A
m
ax
i
m
izes
v
ar
ian
ce
o
f
e
x
tr
ac
ted
f
ea
t
u
r
es
w
h
ic
h
ar
e
u
n
co
r
r
elate
d
.
k
P
C
A
i
s
a
n
o
n
li
n
ea
r
tec
h
n
iq
u
e
w
h
ic
h
i
s
an
ex
te
n
s
io
n
o
f
P
C
A
t
h
at
u
s
e
s
k
er
n
el
m
et
h
o
d
s
.
k
P
C
A
i
s
ap
p
lied
t
o
ex
tr
ac
ted
f
ea
tu
r
e
s
w
h
er
e
p
r
in
cip
al
co
m
p
o
n
en
t
s
a
r
e
co
m
p
u
ted
u
s
i
n
g
R
ad
ial
B
a
s
is
k
er
n
el
f
u
n
ctio
n
s
w
it
h
g
a
m
m
a=
1
.
0
0
.
T
h
ese
f
ea
t
u
r
es
ar
e
f
i
n
all
y
p
lace
d
in
a
n
o
n
lin
ea
r
l
y
tr
a
n
s
f
o
r
m
ed
s
p
ac
e.
L
in
ea
r
R
e
g
r
ess
io
n
class
i
f
icatio
n
m
o
d
el:
T
h
e
p
er
f
o
r
m
an
ce
s
o
f
tr
a
n
s
f
o
r
m
ed
f
ea
t
u
r
e
s
p
ac
e
ar
e
m
ea
s
u
r
ed
u
s
in
g
li
n
ea
r
r
eg
r
ess
io
n
m
o
d
el.
L
in
ea
r
r
eg
r
ess
io
n
m
o
d
el
is
ap
p
lied
o
n
th
e
r
es
u
lt
o
f
P
C
A
an
d
k
P
C
A
.
Her
e
f
ea
t
u
r
es
ar
e
s
elec
t
ed
u
s
i
n
g
M5
p
r
i
m
e
m
et
h
o
d
b
y
eli
m
i
n
ati
n
g
co
llin
e
ar
f
ea
tu
r
es
w
i
th
a
m
i
n
i
m
u
m
to
ler
an
ce
o
f
0
.
0
5
.
Fin
al
R
es
u
lt:
F
ea
tu
r
es
o
b
tain
ed
f
r
o
m
x
-
r
a
y
i
m
ag
e
s
ar
e
class
i
f
ied
as
a
f
f
ec
ted
o
r
n
o
r
m
al
i
m
ag
e
b
y
u
s
in
g
l
in
ea
r
r
eg
r
ess
io
n
m
o
d
el
an
d
th
e
p
er
f
o
r
m
a
n
ce
o
f
P
C
A
an
d
k
P
C
A
with
r
esp
ec
t
to
f
ilter
a
n
d
w
r
ap
p
er
f
ea
tu
r
e
s
elec
tio
n
m
et
h
o
d
s
w
er
e
e
v
alu
a
ted
u
s
i
n
g
1
0
-
f
o
ld
cr
o
s
s
v
alid
atio
n
te
c
h
n
iq
u
e.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
C
o
n
s
id
er
T
B
af
f
ec
ted
i
m
a
g
e,
in
itial
l
y
th
e
i
m
a
g
e
i
s
p
r
ep
r
o
ce
s
s
ed
to
r
e
m
o
v
e
n
o
is
e
u
s
in
g
Gau
s
s
ia
n
f
u
n
ctio
n
.
T
h
en
te
x
t
u
r
e
a
n
d
s
h
ap
e
b
ased
f
ea
t
u
r
es
ar
e
ex
tr
ac
ted
u
s
i
n
g
m
atlab
b
ased
o
n
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
co
n
ce
p
ts
.
T
h
e
r
es
u
lts
o
f
f
ea
tu
r
e
ex
tr
ac
tio
n
m
et
h
o
d
o
f
T
B
x
-
r
a
y
i
m
a
g
e
ar
e
i
llu
s
tr
ated
i
n
Fig
u
r
e
2
,
Fi
g
u
r
e
3
a
n
d
Fig
u
r
e
4
r
esp
ec
tiv
el
y
.
Fig
u
r
e
2
.
T
B
i
m
a
g
e
Fig
u
r
e
3
.
Ma
r
k
ed
i
m
ag
e
Fig
u
r
e
4
.
Ma
s
k
ed
i
m
a
g
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
F
ea
tu
r
e
E
xtra
ctio
n
o
f C
h
est X
-
r
a
y
I
ma
g
es a
n
d
A
n
a
lysi
s
u
s
in
g
P
C
A
a
n
d
k
P
C
A
(
R
o
o
p
a
H
)
3395
T
h
e
af
f
ec
ted
r
e
g
io
n
o
f
T
B
i
m
ag
e
is
m
ar
k
ed
a
n
d
th
e
n
t
h
e
m
ar
k
ed
r
eg
io
n
is
m
a
s
k
ed
to
e
x
t
r
ac
t
s
h
ap
e
b
ased
an
d
te
x
t
u
r
e
b
ased
f
ea
tu
r
e
w
h
ic
h
ar
e
s
h
o
w
n
in
Fi
g
u
r
e
3
an
d
Fig
u
r
e
4
r
esp
ec
ti
v
el
y
.
B
y
u
s
i
n
g
th
e
i
m
a
g
e
p
r
o
ce
s
s
in
g
m
et
h
o
d
s
,
tex
t
u
r
e
b
ased
an
d
s
h
ap
e
b
ased
f
ea
t
u
r
es
v
alu
e
s
ex
tr
ac
ted
f
r
o
m
t
h
e
m
a
s
k
ed
i
m
a
g
e
o
f
T
B
ar
e
s
to
r
ed
in
a
f
ile.
T
h
e
ex
tr
ac
ted
v
alu
es o
f
a
s
i
n
g
le
T
B
i
m
ag
e
ar
e
s
h
o
w
n
i
n
th
e
T
ab
le
1
.
T
ab
le
1
.
E
x
tr
ac
ted
F
ea
tu
r
e
V
alu
es o
f
a
s
in
g
le
T
B
I
m
a
g
e
En
t
r
o
p
y
2
.
0
9
5
4
S
k
e
w
n
e
ss
0
.
2
7
2
4
S
N
R
6
.
1
2
0
5
H
o
mo
g
e
n
e
i
t
y
0
.
9
9
6
4
C
o
n
t
r
a
st
0
.
1
6
En
e
r
g
y
0
.
4
9
9
1
C
o
r
r
e
l
a
t
i
o
n
0
.
9
9
3
3
T
o
t
a
l
M
e
a
n
1
1
0
.
4
3
1
3
V
a
r
i
a
n
c
e
1
1
0
.
0
1
1
2
S
t
a
n
d
a
r
d
D
e
v
i
a
t
i
o
n
1
0
.
4
8
8
6
U
n
i
f
o
r
mi
t
y
1
1
1
A
r
e
a
1
7
4
4
P
e
r
i
me
t
e
r
1
7
2
.
6
2
5
M
a
j
o
r
A
x
i
s
6
5
.
7
9
9
8
M
i
n
o
r
A
x
i
s
3
6
.
1
2
8
6
Ec
c
e
n
t
r
i
c
i
t
y
0
.
8
3
5
8
Fo
r
th
e
i
m
p
le
m
en
tatio
n
w
e
h
a
v
e
co
n
s
id
er
ed
4
7
T
B
af
f
ec
ted
i
m
a
g
es
an
d
3
0
n
o
r
m
al
i
m
ag
e
s
.
Featu
r
es
f
r
o
m
x
-
r
a
y
i
m
ag
e
s
w
er
e
ex
tr
ac
ted
u
s
in
g
m
atlab
s
o
f
t
w
a
r
e
an
d
f
ea
tu
r
e
s
elec
tio
n
an
d
ev
alu
atio
n
u
s
i
n
g
class
i
f
icatio
n
m
o
d
el
w
as p
er
f
o
r
m
ed
b
y
u
s
in
g
R
ap
id
m
in
er
s
o
f
t
w
ar
e.
A
ll
ex
tr
ac
ted
f
ea
t
u
r
es
v
al
u
es
f
r
o
m
th
e
s
e
7
7
i
m
a
g
es
ar
e
s
to
r
ed
in
a
f
ile.
T
h
is
f
ile
w
as
u
s
ed
as
an
in
p
u
t
f
o
r
P
C
A
an
d
k
P
C
A
.
First
f
ilt
er
b
a
s
ed
f
ea
tu
r
e
s
elec
tio
n
m
e
th
o
d
w
as
ap
p
lied
o
n
P
C
A
an
d
k
P
C
A
s
ep
ar
atel
y
,
an
d
th
en
t
h
i
s
w
a
s
f
ed
to
lin
e
ar
r
eg
r
ess
io
n
clas
s
if
icatio
n
m
o
d
el
to
class
if
y
t
h
e
x
-
r
a
y
i
m
ag
e
as
af
f
ec
ted
o
r
n
o
r
m
al.
L
a
ter
w
r
ap
p
er
b
ased
f
ea
t
u
r
e
s
elec
tio
n
m
eth
o
d
w
as
ap
p
lied
o
n
P
C
A
an
d
k
P
C
A
s
e
p
ar
ately
,
t
h
en
a
g
ain
th
is
w
a
s
f
ed
to
lin
ea
r
r
eg
r
ess
i
o
n
class
i
f
icatio
n
m
o
d
el
to
class
i
f
y
t
h
e
x
-
r
a
y
i
m
a
g
e
as
af
f
ec
ted
o
r
n
o
r
m
al
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
clas
s
i
f
icati
o
n
m
o
d
el
w
a
s
an
a
l
y
ze
d
u
s
i
n
g
10
-
f
o
ld
cr
o
s
s
v
alid
atio
n
tech
n
i
q
u
e
.
Featu
r
es
e
x
tr
ac
ted
f
r
o
m
T
B
an
d
n
o
r
m
al
i
m
a
g
e
s
ar
e
r
ep
r
e
s
en
ted
in
a
lin
ea
r
an
d
n
o
n
lin
ea
r
f
ea
tu
r
e
s
p
ac
e.
Fil
ter
an
d
W
r
ap
p
er
f
ea
tu
r
e
s
elec
tio
n
m
et
h
o
d
ar
e
ap
p
li
ed
o
n
th
ese
ex
tr
ac
ted
f
ea
tu
r
es.
P
C
A
is
ap
p
lied
o
n
th
e
o
b
tain
ed
f
ea
tu
r
e
s
p
ac
e
w
h
i
ch
m
ax
i
m
ize
s
t
h
e
v
ar
ia
n
ce
o
f
ex
tr
ac
ted
f
ea
t
u
r
es
t
h
at
ar
e
u
n
c
o
r
r
elate
d
.
k
P
C
A
i
s
also
ap
p
lied
o
n
th
is
f
ea
tu
r
e
s
p
ac
e
s
o
th
at
t
h
e
f
ea
t
u
r
es
ar
e
p
la
ce
d
in
a
n
o
n
li
n
ea
r
l
y
tr
an
s
f
o
r
m
ed
s
p
ac
e.
Featu
r
es
f
r
o
m
f
ea
t
u
r
e
s
p
ac
e
ar
e
s
u
b
j
ec
ted
to
lin
ea
r
r
eg
r
ess
io
n
m
o
d
el.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
lin
ea
r
r
eg
r
es
s
io
n
class
i
f
icatio
n
m
o
d
el
w
a
s
ev
al
u
ated
u
s
in
g
1
0
f
o
ld
cr
o
s
s
v
al
id
atio
n
an
d
t
h
e
r
esu
lts
ar
e
s
h
o
w
n
in
T
ab
le
2
f
o
r
f
ilter
ap
p
r
o
ac
h
an
d
T
ab
le
3
f
o
r
w
r
ap
p
er
ap
p
r
o
ac
h
.
T
h
e
o
v
er
all
r
esu
l
ts
o
f
li
n
ea
r
r
eg
r
es
s
io
n
c
l
ass
i
f
icatio
n
m
o
d
el
ar
e
g
iv
e
n
in
T
ab
le
4
.
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.
8
,
No
.
5
,
Octo
b
er
2
0
1
8
:
3
3
9
2
–
3
3
9
8
3396
T
ab
le
2
.
R
esu
lt o
f
L
i
n
ea
r
R
e
g
r
ess
io
n
C
las
s
i
f
icatio
n
Mo
d
e
l
wh
er
e
Featu
r
e
Selec
tio
n
w
a
s
d
o
n
e
u
s
in
g
Fi
lter
Me
th
o
d
P
C
A
k
P
C
A
T
ab
le
3
.
R
esu
lt
o
f
L
i
n
ea
r
R
e
g
r
ess
io
n
C
las
s
i
f
icatio
n
Mo
d
el
W
h
er
e
Featu
r
e
Selectio
n
w
a
s
d
o
n
e
u
s
i
n
g
W
r
ap
p
er
Me
th
o
d
P
C
A
k
P
C
A
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
F
ea
tu
r
e
E
xtra
ctio
n
o
f C
h
est X
-
r
a
y
I
ma
g
es a
n
d
A
n
a
lysi
s
u
s
in
g
P
C
A
a
n
d
k
P
C
A
(
R
o
o
p
a
H
)
3397
T
ab
le
4
.
C
o
m
p
ar
iti
v
e
R
es
u
lt
s
o
f
P
C
A
a
n
d
k
P
C
A
u
s
i
n
g
F
ilter
an
d
W
r
ap
p
e
r
Featu
r
e
Selectio
n
Me
th
o
d
4.
CO
NCLU
SI
O
N
T
h
e
cu
r
r
en
t
w
o
r
k
p
r
o
p
o
s
ed
u
s
e
s
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
co
n
c
ep
ts
to
ex
tr
ac
t
r
elev
a
n
t
an
d
i
m
p
o
r
tan
t
f
ea
t
u
r
es
f
r
o
m
a
c
h
es
t
x
-
r
a
y
i
m
ag
e
to
d
iag
n
o
is
e
w
h
et
h
er
a
p
er
s
o
n
is
T
B
in
f
ec
ted
o
r
n
o
t
,
w
h
ic
h
b
r
o
ad
l
y
en
co
m
p
as
s
d
ata
p
r
ep
r
o
ce
s
s
in
g
an
d
f
ea
t
u
r
e
ex
tr
ac
tio
n
p
r
o
ce
s
s
.
Fi
lter
an
d
w
r
ap
p
er
f
ea
t
u
r
e
s
elec
tio
n
m
et
h
o
d
s
ar
e
i
m
p
le
m
e
n
ted
o
n
th
e
s
e
e
x
t
r
ac
ted
f
ea
t
u
r
es.
T
h
e
f
ea
t
u
r
es
o
b
tain
ed
ar
e
h
ig
h
l
y
p
r
o
j
ec
ted
to
a
f
ea
t
u
r
e
s
p
ac
e
w
h
er
e
P
C
A
o
r
k
P
C
A
ar
e
ap
p
lied
o
n
th
is
s
p
ac
e.
T
h
en
li
n
ea
r
r
eg
r
ess
io
n
clas
s
i
f
icatio
n
m
o
d
el
is
ap
p
lied
to
an
a
l
y
ze
t
h
e
T
B
d
is
ea
s
e.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
P
C
A
an
d
k
P
C
A
ar
e
e
x
a
m
in
ed
a
n
d
f
o
u
n
d
th
at
t
h
e
ac
c
u
r
ac
y
o
f
P
C
A
u
s
i
n
g
w
r
ap
p
er
ap
p
r
o
ac
h
9
6
.
0
7
%
is
b
etter
w
h
e
n
co
m
p
ar
ed
to
th
e
ac
cu
r
ac
y
o
f
k
P
C
A
w
h
ich
is
6
2
.
5
0
%.
Fu
t
u
r
e
w
o
r
k
w
ill b
e
co
n
s
id
er
e
d
o
n
m
o
r
e
i
m
ag
e
s
an
d
ca
r
r
y
o
u
t
th
e
i
m
p
le
m
e
n
tatio
n
o
n
th
i
s
h
u
g
e
d
ata
s
et.
RE
F
E
R
E
NC
E
S
[1
]
Ha
ra
li
c
k
,
Ro
b
e
rt
M
,
“
S
tatisti
c
a
l
a
n
d
St
ru
c
t
u
ra
l
A
p
p
ro
a
c
h
e
s
t
o
T
e
x
tu
re
”
,
Pro
c
e
e
d
in
g
s
o
f
t
h
e
IEE
E
,
6
7
.
5
,
p
p
.
7
8
6
-
8
0
4
,
1
9
7
9
.
[2
]
P
e
r
n
e
r,
P
e
tr
a
,
“
Im
a
g
e
M
in
in
g
:
Iss
u
e
s,
F
ra
m
e
w
o
rk
,
a
G
e
n
e
ri
c
T
o
o
l
a
n
d
it
s
A
p
p
li
c
a
t
i
o
n
t
o
m
e
d
ica
l
-
i
m
a
g
e
d
iag
n
o
sis
”
,
E
n
g
i
n
e
e
rin
g
A
p
p
li
c
a
ti
o
n
s
o
f
Arti
f
icia
l
I
n
telli
g
e
n
c
e
,
1
5
.
2
,
p
p
.
2
0
5
-
2
1
6
,
2
0
0
2
.
[3
]
Bu
g
a
tt
i,
P
e
d
ro
He
n
riq
u
e
,
e
t
a
l
.
,
“
Co
n
ten
t
-
b
a
se
d
re
tri
e
v
a
l
o
f
m
e
d
ica
l
i
m
a
g
e
s
b
y
c
o
n
ti
n
u
o
u
s
f
e
a
tu
re
se
lec
ti
o
n
”
,
Co
mp
u
ter
-
b
a
se
d
M
e
d
i
c
a
l
S
y
ste
ms
,
2
0
0
8
.
C
BM
S
'0
8
.
2
1
st
IEE
E
I
n
ter
n
a
t
io
n
a
l
S
y
mp
o
siu
m
o
n
.
IEE
E,
2
0
0
8
.
[4
]
M
a
h
m
o
o
d
a
b
a
d
i,
S
.
Zare
i,
e
t
a
l
.
,
“
P
CA
-
S
GA
I
m
p
le
m
e
n
tatio
n
i
n
C
las
sif
ica
ti
o
n
a
n
d
D
ise
a
se
S
p
e
c
if
ic
F
e
a
tu
re
Ex
trac
ti
o
n
o
f
th
e
b
ra
in
M
RS
s
ig
n
a
ls
”
,
En
g
i
n
e
e
rin
g
i
n
M
e
d
icin
e
a
n
d
Bi
o
l
o
g
y
S
o
c
iety
,
2
0
0
8
.
EM
BS
2
0
0
8
.
3
0
th
An
n
u
a
l
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
f
th
e
I
EE
E
.
IEE
E,
2
0
0
8
.
[5
]
L
iu
,
Yih
u
i
,
“
W
a
v
e
let
F
e
a
tu
re
Ex
trac
ti
o
n
f
o
r
H
ig
h
-
d
im
e
n
sio
n
a
l
M
icro
a
rra
y
D
a
ta
”
,
Ne
u
ro
c
o
mp
u
ti
n
g
,
7
2
.
4
,
pp.
9
8
5
-
990
,
2
0
0
9
.
[6
]
S
u
g
a
n
th
i
,
M
.
,
a
n
d
M
.
M
a
d
h
e
sw
a
ra
n
,
“
M
a
m
m
o
g
ra
m
T
u
m
o
r
Clas
sif
ica
ti
o
n
u
sin
g
M
u
lt
im
o
d
a
l
F
e
a
tu
r
e
s
a
n
d
G
e
n
e
ti
c
A
l
g
o
rit
h
m
”
,
Co
n
tro
l
,
Au
t
o
ma
ti
o
n
,
Co
mm
u
n
ic
a
ti
o
n
a
n
d
E
n
e
rg
y
Co
n
se
rv
a
ti
o
n
,
2
0
0
9
.
INCACE
C
2
0
0
9
.
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
.
IEE
E
,
2
0
0
9
.
[7
]
Ch
u
a
n
g
,
L
i
-
Ye
h
,
e
t
a
l
.
,
“
A
H
y
b
ri
d
F
e
a
tu
re
S
e
lec
ti
o
n
M
e
th
o
d
f
o
r
DN
A
M
icro
a
rra
y
D
a
ta
”
,
Co
mp
u
ter
s
in
B
io
lo
g
y
a
n
d
M
e
d
icin
e
,
4
1
.
4
,
p
p
,
2
2
8
-
2
3
7
,
2
0
1
1
.
[8
]
A
sh
a
.
T
,
Dr.
S
.
Na
t
a
ra
jan
,
Dr.
K.
N.
B.
M
u
rth
y
,
“
A
S
tu
d
y
o
f
As
so
c
iativ
e
Cla
ss
i
f
iers
w
it
h
Di
ff
e
re
n
t
Ru
le
Ev
a
lu
a
ti
o
n
M
e
a
su
re
s
f
o
r
T
u
b
e
rc
u
lo
sis
P
re
d
ictio
n
”
,
IJ
CA
S
p
e
c
ia
l
Iss
u
e
o
n
“
Arti
fi
c
i
a
l
In
tell
ig
e
n
c
e
T
e
c
h
n
iq
u
e
s
-
No
v
e
l
Ap
p
ro
a
c
h
e
s &
Pra
c
ti
c
a
l
Ap
p
li
c
a
t
io
n
s,
A
IT
,
2
0
1
1
.
[9
]
A
sh
a
,
T
.
,
e
t
a
l
.
,
“
Da
ta
M
in
in
g
T
e
c
h
n
iq
u
e
s
in
th
e
D
iag
n
o
sis
o
f
T
u
b
e
rc
u
lo
sis
”
,
INT
ECH
Op
e
n
A
c
c
e
ss
P
u
b
li
sh
e
r,
2
0
1
2
.
[1
0
]
Ra
d
,
A
b
d
o
lv
a
h
a
b
Eh
sa
n
i,
M
o
h
d
S
h
a
f
r
y
M
o
h
d
Ra
h
im
,
a
n
d
A
li
re
z
a
No
ro
u
z
i
,
“
Dig
it
a
l
D
e
n
tal
x
-
ra
y
I
m
a
g
e
S
e
g
m
e
n
tatio
n
a
n
d
F
e
a
tu
re
Ex
trac
ti
o
n
”
,
I
n
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
E
lec
trica
l
En
g
in
e
e
rin
g
a
n
d
Co
m
p
u
t
e
r
S
c
ien
c
e
,
1
1
.
6
,
p
p
.
3
1
0
9
-
3
1
1
4
,
2
0
1
3
.
[1
1
]
Zy
o
u
t,
Im
a
d
,
Jo
a
n
n
a
Cz
a
j
k
o
w
s
k
a
,
a
n
d
M
a
rc
in
G
rz
e
g
o
rz
e
k
,
“
M
u
lt
i
-
sc
a
le
T
e
x
tu
ra
l
F
e
a
tu
re
Ex
tr
a
c
ti
o
n
a
n
d
P
a
rt
icle
S
w
a
r
m
Op
ti
m
iz
a
ti
o
n
Ba
se
d
M
o
d
e
l
S
e
lec
ti
o
n
f
o
r
F
a
lse
P
o
siti
v
e
Re
d
u
c
ti
o
n
In
M
a
m
m
o
g
ra
p
h
y
”
,
Co
mp
u
ter
ize
d
M
e
d
ica
l
Ima
g
in
g
a
n
d
Gr
a
p
h
ics
,
46
,
p
p
.
95
-
1
0
7
,
2
0
1
5
.
[1
2
]
G
lo
b
a
lT
u
b
e
rc
u
lo
sisR
e
p
o
rt
2
0
1
5
-
h
tt
p
:/
/a
p
p
s.w
h
o
.
i
n
t/
iri
s/
b
it
stre
a
m
/1
0
6
6
5
/
1
9
1
1
0
2
/
1
/9
7
8
9
2
4
1
5
6
5
0
5
9
_
e
n
g
.
p
d
f
[1
3
]
A
li
,
Ro
z
n
iza
,
Am
ir
Hu
ss
a
in
,
a
n
d
M
u
sta
f
a
M
a
n
,
“
F
e
a
tu
re
E
x
trac
ti
o
n
a
n
d
C
las
sif
ica
ti
o
n
f
o
r
M
u
l
ti
p
le
S
p
e
c
ies
o
f
Gy
ro
d
a
c
t
y
lu
s ec
to
p
a
ra
site
”
,
In
d
o
n
e
sia
n
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
En
g
i
n
e
e
rin
g
a
n
d
Co
mp
u
ter
S
c
ien
c
e
,
1
3
.
3
,
p
p
.
5
0
3
-
5
1
1
,
2
0
1
5
.
[1
4
]
F
a
rid
a
h
a
n
d
Ba
lza
Ac
h
m
a
d
,
“
Li
p
Im
a
g
e
F
e
a
tu
re
Ex
trac
ti
o
n
Util
izin
g
S
n
a
k
e
'
s
Co
n
tro
l
P
o
i
n
ts
f
o
r
L
ip
Re
a
d
in
g
A
p
p
li
c
a
ti
o
n
s
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
E
lec
trica
l
a
n
d
Co
mp
u
ter
E
n
g
i
n
e
e
rin
g
,
5
.
4
,
p.
7
2
0
,
2
0
1
5
.
F
e
a
t
u
r
e
S
e
l
e
c
t
i
o
n
M
e
t
h
o
d
F
i
l
t
e
r
A
p
p
r
o
a
c
h
W
r
a
p
p
e
r
A
p
p
r
o
a
c
h
P
C
A
k
P
C
A
P
C
A
k
P
C
A
A
c
c
u
r
a
c
y
9
5
.
6
5
%
6
0
.
8
7
%
9
6
.
0
7
%
6
2
.
5
0
%
P
r
e
c
i
si
o
n
9
0
%
u
n
k
n
o
w
n
9
6
.
0
7
%
u
n
k
n
o
w
n
R
e
c
a
l
l
1
0
0
%
0
.
0
0
%
9
5
%
0
.
0
0
%
A
U
C
(
o
p
t
i
mi
st
i
c
)
.
0
.
9
2
9
1
0
.
9
8
1
A
U
C
0
.
9
2
9
0
.
5
0
.
9
8
0
.
5
A
U
C
(
p
e
ssi
mi
st
i
c
)
0
.
9
2
9
0
0
.
9
8
0
R
M
S
E
0
.
4
1
8
±
0
.
0
0
0
.
4
6
3
±
0
.
0
0
0
.
4
2
2
±
0
.
0
0
2
0
.
4
9
3
±
0
.
0
0
4
S
q
u
a
r
e
d
Er
r
o
r
0
.
1
7
4
±
0
.
0
7
9
0
.
2
1
4
±
0
.
0
8
1
0
.
1
7
9
±
0
.
0
1
7
0
.
2
4
3
±
0
.
0
0
4
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.
8
,
No
.
5
,
Octo
b
er
2
0
1
8
:
3
3
9
2
–
3
3
9
8
3398
[1
5
]
Ro
o
p
a
H
a
n
d
A
sh
a
T
,
“
S
e
g
m
e
n
t
a
ti
o
n
o
f
X
-
Ra
y
I
m
a
g
e
u
sin
g
Cit
y
Blo
c
k
Dista
n
c
e
M
e
a
su
re
”
,
2
0
1
6
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
n
tro
l,
I
n
stru
me
n
ta
t
io
n
,
Co
mm
u
n
ica
ti
o
n
a
n
d
Co
mp
u
t
a
ti
o
n
a
l
T
e
c
h
n
o
lo
g
i
e
s
(
ICCICCT
),
Ku
m
a
r
a
c
o
il
,
p
p
.
1
8
6
-
1
8
9
,
2
0
1
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ro
o
p
a
.
H
re
c
e
iv
e
d
M
.
S
c
d
e
g
re
e
i
n
M
a
th
e
m
a
ti
c
s
f
ro
m
Ba
n
g
a
lo
re
Un
iv
e
rsity
in
2
0
0
2
a
n
d
M
.
T
e
c
h
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
f
ro
m
Un
iv
e
rsit
y
o
f
M
y
s
o
re
in
2
0
0
6
.
S
h
e
is
c
u
rre
n
tl
y
w
o
rk
in
g
a
s
a
n
A
ss
ist
a
n
t
P
r
o
f
e
ss
o
r
in
th
e
De
p
a
rtm
e
n
t
o
f
In
f
o
r
m
a
ti
o
n
S
c
ien
c
e
&
En
g
in
e
e
rin
g
,
Ba
n
g
a
lo
re
In
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
,
a
n
d
Ba
n
g
a
lo
re
.
S
h
e
is
c
u
rre
n
tl
y
p
u
rsu
in
g
h
e
r
P
h
D
i
n
Co
m
p
u
ter S
c
ien
c
e
a
t
V
T
U i
n
th
e
a
re
a
o
f
d
a
ta
m
in
in
g
.
Dr
.
As
h
a
.
T
is
a
P
ro
f
e
ss
o
r
&
P
G
Co
o
r
d
i
n
a
to
r
i
n
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
&
En
g
in
e
e
rin
g
,
Ba
n
g
a
lo
re
In
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
,
B
a
n
g
a
lo
re
.
S
h
e
o
b
tain
e
d
h
e
r
P
h
.
D
in
Co
m
p
u
ter
a
n
d
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
f
ro
m
V
isv
e
sv
a
ra
y
a
T
e
c
h
n
o
lo
g
ica
l
Un
iv
e
rsit
y
,
Ka
rn
a
tak
a
.
S
h
e
h
a
s
p
u
b
li
sh
e
d
a
ro
u
n
d
2
4
p
a
p
e
rs
in
I
n
tern
a
ti
o
n
a
l/
Na
ti
o
n
a
l
jo
u
rn
a
ls
a
n
d
Co
n
f
e
re
n
c
e
s.
He
r
re
se
a
r
c
h
in
tere
sts
in
c
lu
d
e
Da
ta
M
in
in
g
,
M
e
d
ica
l
In
f
o
r
m
a
ti
c
s,
P
a
tt
e
rn
Re
c
o
g
n
it
io
n
,
Big
d
a
ta
m
a
n
a
g
e
m
e
n
t
e
tc.,
e
m
a
il
:
a
sh
a
.
m
a
sth
i@g
m
a
il
.
c
o
m
Evaluation Warning : The document was created with Spire.PDF for Python.