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
.
5
7
0
9
~
5
7
1
3
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
10
i
6
.
pp
5
7
0
9
-
5
7
1
3
5709
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
Dev
elo
p
m
e
nt
o
f
alg
o
rith
m
f
o
r id
ent
ificatio
n of
m
a
lig
a
nt
g
ro
w
th
in cancer
using
ar
tif
icia
l n
eura
l n
e
t
w
o
r
k
R.
P
a
nd
ia
n
1
,
D.
N.
S
.
Ra
v
i K
u
m
a
r
2
,
R.
Ra
j
a
K
u
m
a
r
3
1,
2
S
c
h
o
o
l
o
f
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ics
En
g
in
e
e
rin
g
,
S
a
th
y
a
b
a
m
a
In
s
ti
tu
te
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
In
d
ia
3
S
c
h
o
o
l
o
f
S
c
ien
c
e
a
n
d
Hu
m
a
n
it
ies
S
a
th
y
a
b
a
m
a
In
stit
u
te
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Mar
23
,
2
0
20
R
ev
i
s
ed
Ma
y
6
,
2020
A
cc
ep
ted
Ma
y
1
5
,
2
0
2
0
T
h
e
p
re
c
ise
id
e
n
ti
f
ica
ti
o
n
a
n
d
c
h
a
ra
c
teriz
a
ti
o
n
o
f
sm
a
ll
p
u
lm
o
n
a
ry
n
o
d
u
les
a
t
lo
w
-
d
o
se
CT
is
a
n
e
c
e
ss
a
r
y
re
q
u
ire
m
e
n
t
f
o
r
th
e
c
o
m
p
letio
n
o
f
v
a
l
u
a
b
le
lu
n
g
c
a
n
c
e
r
sc
re
e
n
in
g
.
It
is
c
o
m
p
u
lso
r
y
to
d
e
v
e
lo
p
so
m
e
a
u
to
m
a
t
e
d
to
o
l,
in
o
r
d
e
r
to
d
e
tec
t
p
u
lm
o
n
a
r
y
n
o
d
u
les
a
t
lo
w
d
o
se
c
t
a
t
th
e
b
e
g
in
n
in
g
sta
g
e
it
se
l
f
.
T
h
e
v
a
rio
u
s
a
lg
o
rit
h
m
s
h
a
d
b
e
e
n
p
ro
p
o
se
d
e
a
rli
e
r
b
y
m
a
n
y
r
e
se
a
rc
h
e
r
s
w
it
h
in
th
e
p
a
st,
b
u
t
th
e
a
c
c
u
ra
c
y
o
f
p
re
d
ictio
n
is
u
s
u
a
ll
y
a
c
h
a
ll
e
n
g
in
g
tas
k
.
Du
rin
g
th
is
w
o
rk
,
a
m
a
n
-
m
a
d
e
n
e
u
ra
l
n
e
tw
o
r
b
a
se
d
m
e
th
o
d
o
lo
g
y
is
p
ro
p
o
se
d
to
se
e
k
o
u
t
t
h
e
irreg
u
lar
g
ro
w
th
o
f
lu
n
g
t
issu
e
s.
Hig
h
e
r
p
ro
b
a
b
il
it
y
o
f
d
e
tec
ti
o
n
is
tak
e
n
a
s
a
g
o
a
l
to
u
rg
e
a
n
a
u
to
m
a
ti
c
to
o
l
,
w
it
h
g
re
a
t
a
c
c
u
ra
c
y
.
T
h
e
b
e
st
f
e
a
tu
re
se
ts
d
e
riv
e
d
f
ro
m
Ha
ra
li
c
k
G
r
a
y
l
e
v
e
l
c
o
o
c
c
u
rre
n
c
e
M
a
tri
x
a
n
d
u
se
d
b
e
c
a
u
se
th
e
d
im
e
n
sio
n
re
d
u
c
ti
o
n
w
a
y
f
o
r
fe
e
d
in
g
n
e
u
ra
l
n
e
tw
o
rk
.
Du
rin
g
th
is
w
o
rk
,
a
b
in
a
r
y
Bi
n
a
ry
c
las
si
f
ier
n
e
u
ra
l
n
e
tw
o
rk
h
a
s
b
e
e
n
p
ro
p
o
se
d
to
sp
o
t
t
h
e
trad
it
io
n
a
l
i
m
a
g
e
s
o
u
t
o
f
a
ll
th
e
i
m
a
g
e
s.
T
h
e
p
o
ten
ti
a
l
o
f
th
e
p
ro
p
o
se
d
n
e
u
ra
l
n
e
tw
o
rk
h
a
s
b
e
e
n
q
u
a
n
ti
tativ
e
ly
c
o
m
p
u
ted
u
sin
g
c
o
n
f
u
sio
n
m
a
tri
x
a
n
d
l
o
c
a
ted
in
term
s o
f
a
c
c
u
ra
c
y
.
K
ey
w
o
r
d
s
:
C
las
s
i
f
icatio
n
C
T
im
a
g
e
GL
C
M
T
ex
tu
r
e
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
an
d
ian
R
,
Sch
o
o
l o
f
E
lectr
ical
an
d
E
lectr
o
n
ics E
n
g
i
n
ee
r
in
g
,
Sath
y
ab
a
m
a
I
n
s
tit
u
te
o
f
Scie
n
ce
an
d
T
ec
h
n
o
lo
g
y
,
C
h
e
n
n
ai,
T
am
il Na
d
u
,
I
n
d
ia
.
E
m
ail:
r
p
an
d
ia
n
m
e
@
r
ed
if
f
m
ai
l.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
I
t is t
h
e
w
a
y
to
w
ar
d
p
r
o
cu
r
in
g
m
o
r
e
elev
a
ted
lev
el
d
ata
o
f
a
p
ictu
r
e,
f
o
r
ex
a
m
p
le,
s
h
ad
i
n
g
,
s
h
ap
e
a
n
d
T
ex
tu
r
e.
I
t
is
o
n
e
o
f
th
e
s
i
g
n
i
f
ican
t
q
u
alit
ies
u
tili
ze
d
i
n
r
ec
o
g
n
izi
n
g
ite
m
s
o
r
R
e
g
io
n
o
f
en
t
h
u
s
ia
s
m
f
o
r
a
i
m
a
g
e
.
S
u
r
f
ac
e,
th
e
ex
a
m
p
l
e
o
f
d
ata
o
r
ex
h
ib
i
t
o
f
t
h
e
s
tr
u
ctu
r
e
s
et
u
p
i
n
a
i
m
a
g
e
,
i
s
a
h
u
g
e
co
m
p
o
n
en
t
o
f
m
an
y
i
m
a
g
es
t
y
p
es
[
1
]
.
Fro
m
a
g
en
er
al
p
er
s
p
ec
ti
v
e,
s
u
r
f
ac
e
allu
d
es
to
s
u
r
f
ac
e
attr
ib
u
tes
an
d
p
r
esen
ce
o
f
T
ex
tu
r
e
h
ig
h
li
g
h
ts
ca
n
b
e
r
em
o
v
ed
in
a
f
e
w
s
tr
ateg
ie
s
,
u
tili
zin
g
f
ac
tu
al,
a
u
x
il
iar
y
,
an
d
m
o
d
el
-
b
ased
an
d
ch
an
g
e
d
ata,
in
w
h
ic
h
th
e
m
o
s
t
w
el
l
-
k
n
o
w
n
w
a
y
i
s
u
til
izin
g
th
e
g
r
a
y
le
v
el
co
ev
en
t
m
atr
ix
(
GL
C
M)
.
GL
C
M
co
n
tain
s
th
e
s
ec
o
n
d
-
r
eq
u
e
s
t
f
a
ctu
al
d
ata
o
f
s
p
atial
r
elatio
n
s
h
i
p
o
f
p
ix
els o
f
a
i
m
ag
e
[
2
]
.
Gen
er
all
y
,
t
h
e
ex
ac
t
n
es
s
o
f
an
y
ar
r
an
g
e
m
en
t
f
r
a
m
e
w
o
r
k
m
o
s
tl
y
r
elie
s
u
p
o
n
t
h
e
b
est
p
o
s
s
ib
le
d
ec
is
io
n
o
f
t
h
e
h
ig
h
li
g
h
ts
.
T
h
u
s
it
is
f
u
n
d
a
m
e
n
tal
to
lo
ca
te
a
d
ec
en
t
ar
r
a
n
g
e
m
e
n
t
o
f
h
ig
h
lig
h
t
s
.
E
s
s
en
t
ial
p
er
io
d
o
f
s
tr
u
ctu
r
e
i
n
an
y
g
r
o
u
p
in
g
f
r
a
m
e
w
o
r
k
is
th
e
c
h
o
ice
o
f
a
d
ec
en
t a
r
r
an
g
e
m
en
t o
f
h
ig
h
li
g
h
t
s
w
h
ic
h
h
a
v
e
th
e
ca
p
ac
it
y
o
f
s
i
g
n
d
etac
h
m
en
t
i
n
th
e
co
m
p
o
n
en
t
s
p
ac
e.
An
o
r
d
er
ca
lcu
latio
n
w
i
ll
c
o
n
s
is
ten
tl
y
g
i
v
e
an
o
u
tco
m
e,
y
et
a
p
o
o
r
elem
en
t
p
o
r
tr
ay
al
w
i
ll
p
r
o
m
p
t
an
o
u
tco
m
e
t
h
at
d
o
esn
'
t
m
ir
r
o
r
t
h
e
g
e
n
u
i
n
e
id
ea
o
f
th
e
h
id
d
en
i
n
f
o
r
m
atio
n
.
T
h
e
in
f
o
r
m
atio
n
o
u
g
h
t
to
b
e
s
tr
ea
m
li
n
ed
w
i
th
o
u
t
lo
s
s
o
f
d
ata
.
Fin
d
in
g
th
e
b
est
h
ig
h
li
g
h
ts
is
a
tr
o
u
b
leso
m
e
ass
i
g
n
m
e
n
t,
an
d
it
f
r
eq
u
e
n
tl
y
m
u
s
t
b
e
p
r
ac
ticed
th
r
o
u
g
h
an
ex
p
er
i
m
en
ta
tio
n
p
r
o
ce
d
u
r
e.
I
n
th
is
w
o
r
k
,
a
d
i
m
le
v
el
co
-
ev
e
n
t
g
r
id
(
G
L
C
M
)
is
u
tili
ze
d
,
w
h
ich
is
a
m
ea
s
u
r
ab
le
tech
n
iq
u
e
t
h
at
u
s
e
s
th
e
s
p
atia
l r
elatio
n
s
h
ip
o
f
p
ix
els.
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
:
5
7
0
9
-
5
7
1
3
5710
Dav
is
e
t
al.
,
[
3
]
s
tar
ted
th
e
u
s
e
o
f
d
i
m
le
v
el
co
-
ev
e
n
t
g
r
id
(
GL
C
M)
s
o
as
to
d
is
co
v
er
th
e
h
ig
h
li
g
h
t
s
th
at
ar
e
to
b
e
p
r
o
d
u
ce
d
d
e
p
en
d
en
t
o
n
a
p
ix
el's
n
ei
g
h
b
o
r
h
o
o
d
.
Dav
is
e
t
al.
,
p
r
o
ce
ed
e
d
w
i
t
h
cr
af
ted
b
y
i
n
s
u
c
h
a
m
eth
o
d
o
f
t
h
e
d
ir
ec
tio
n
al
d
is
p
er
s
io
n
o
f
G
L
C
M
in
c
lu
d
es
an
d
p
r
o
p
o
s
ed
a
lo
t
o
f
p
o
lar
g
r
a
m
m
ea
s
u
r
e
m
e
n
t
s
w
h
ic
h
ar
e
r
o
tatio
n
al
l
y
in
v
ar
ia
n
t.
Har
alic
k
et
al.
,
[
4
]
r
ec
o
m
m
en
d
ed
t
h
at
r
e
v
o
lu
t
io
n
i
n
v
ar
i
an
t
h
i
g
h
l
ig
h
t
s
co
u
ld
b
e
ac
q
u
ir
ed
f
r
o
m
co
-
e
v
e
n
t
n
et
w
o
r
k
s
b
y
ta
k
i
n
g
t
h
e
n
o
r
m
al
a
n
d
s
co
p
e
o
f
ea
ch
ele
m
e
n
t t
y
p
e
o
v
er
th
e
f
o
u
r
p
o
in
t
s
th
at
is
u
tili
ze
d
.
T
h
e
d
ar
k
lev
el
d
is
tin
ctio
n
in
s
i
g
h
t
s
is
a
n
o
th
er
s
u
r
f
ac
e
d
ep
ictio
n
tech
n
iq
u
e,
w
h
ic
h
is
f
ir
m
l
y
id
en
ti
f
ied
w
it
h
G
L
C
M,
W
esz
k
a
et
al
.,
[
5
]
.
A
co
-
ev
en
t
g
r
id
,
ad
d
itio
n
all
y
allu
d
ed
to
as
co
-
ev
en
t
ap
p
r
o
p
r
iatio
n
,
is
ch
ar
ac
ter
ized
o
v
er
a
p
ictu
r
e
to
b
e
th
e
d
is
s
e
m
in
a
tio
n
o
f
co
-
h
ap
p
en
in
g
estee
m
s
at
a
g
iv
e
n
b
alan
ce
.
I
t
s
p
ea
k
s
to
th
e
s
ep
ar
atio
n
an
d
r
ak
is
h
s
p
atial
r
elatio
n
s
h
ip
o
v
er
a
p
ictu
r
e
s
u
b
-
lo
ca
le
o
f
ex
p
licit
s
ize.
T
h
e
GL
C
M
is
m
ad
e
f
r
o
m
a
d
i
m
s
ca
le
p
ictu
r
e.
T
h
e
GL
C
M
i
s
d
eter
m
in
ed
h
o
w
r
e
g
u
lar
l
y
a
p
ix
el
w
it
h
d
i
m
lev
e
l
(
g
r
ay
s
ca
le
f
o
r
ce
o
r
T
o
n
e)
estee
m
I
h
ap
p
en
s
eit
h
er
o
n
a
le
v
el
p
la
n
e,
v
er
ticall
y
,
o
r
co
r
n
er
to
co
r
n
er
to
ad
j
o
in
in
g
p
i
x
els
w
it
h
th
e
w
o
r
t
h
j
.
A
n
o
tab
le
f
ac
t
u
al
ap
p
ar
atu
s
f
o
r
r
em
o
v
in
g
s
ec
o
n
d
-
r
eq
u
e
s
t
s
u
r
f
ac
e
d
ata
f
r
o
m
p
ictu
r
es
is
t
h
e
d
ar
k
lev
el
co
-
e
v
e
n
t.
T
h
e
G
L
C
M
l
attice
is
o
n
e
o
f
t
h
e
m
o
s
t
w
el
l
k
n
o
w
n
a
n
d
v
iab
le
w
ells
p
r
i
n
g
s
o
f
h
ig
h
li
g
h
ts
i
n
s
u
r
f
ac
e
ex
a
m
i
n
atio
n
.
Fo
r
a
d
is
tr
ict,
c
h
ar
ac
ter
ized
b
y
a
cli
en
t
d
eter
m
in
ed
w
i
n
d
o
w
,
G
L
C
M
i
s
t
h
e
lattice
o
f
th
o
s
e
es
ti
m
atio
n
s
o
v
er
all
d
i
m
lev
el
s
ets.
I
n
th
is
tec
h
n
iq
u
e,
h
ig
h
li
g
h
ts
ar
e
d
eter
m
in
ed
d
ep
en
d
en
t
o
n
th
e
to
tal
co
n
tr
asts
b
et
w
ee
n
s
et
s
o
f
d
i
m
le
v
el
s
o
r
n
o
r
m
al
d
i
m
lev
el
s
r
ath
er
th
a
n
u
n
iq
u
e
d
ar
k
l
e
v
el
p
ix
el
v
al
u
es
[
6
]
.
T
h
is
m
et
h
o
d
o
lo
g
y
m
ak
e
s
th
e
m
ea
s
u
r
e
m
e
n
t
s
s
o
m
e
w
h
at
m
o
r
e
p
o
w
er
f
u
l
to
b
r
ig
h
ten
i
n
g
v
ar
ietie
s
t
h
an
o
n
ac
co
u
n
t
o
f
G
L
C
M.
T
h
e
p
ap
er
is
o
r
g
a
n
ized
as
f
o
llo
w
s
.
T
h
e
i
m
ag
e
i
n
f
o
r
m
atio
n
b
a
s
e
is
p
o
r
tr
ay
ed
i
n
s
eg
m
e
n
t
2
.
T
h
e
co
m
p
o
n
en
t
e
x
tr
ac
tio
n
s
tr
ate
g
ies
ar
e
p
o
r
tr
ay
ed
in
s
eg
m
en
t
3
.
T
h
e
ar
r
an
g
e
m
e
n
t
s
tr
ate
g
y
is
li
s
ted
in
ar
ea
4
.
T
h
e
ex
a
m
i
n
atio
n
w
o
r
k
i
s
f
in
i
s
h
ed
u
p
in
s
e
g
m
e
n
t 5
.
2.
I
M
AG
E
DAT
AB
ASE
T
h
e
i
m
ag
e
s
u
s
ed
f
o
r
te
s
ti
n
g
th
e
al
g
o
r
ith
m
s
d
ev
elo
p
ed
ar
e
m
ed
ical
i
m
ag
e
s
.
I
n
t
h
i
s
w
o
r
k
a
ls
o
,
th
e
n
o
r
m
al
l
u
n
g
i
m
ag
e
s
an
d
a
ca
n
ce
r
af
f
ec
ted
lu
n
g
i
m
a
g
es
ar
e
tak
e
n
f
r
o
m
f
i
f
t
y
d
i
f
f
er
en
t
p
eo
p
les
to
ch
ar
ac
ter
ize
th
e
l
u
n
g
ca
n
ce
r
.
T
h
e
i
m
a
g
e
d
ata
f
o
r
th
i
s
r
es
ea
r
ch
w
o
r
k
i
s
g
r
o
u
p
ed
as
n
o
r
m
al
a
n
d
ab
n
o
r
m
a
l
i
m
a
g
es.
T
h
e
Me
d
ical
I
m
ag
e
s
ar
e
C
T
L
u
n
g
ax
ia
l
v
ie
w
i
m
a
g
es,
C
T
L
u
n
g
s
ag
i
tt
al
v
ie
w
i
m
ag
es
a
n
d
C
T
L
u
n
g
co
r
o
n
el
v
ie
w
i
m
a
g
es
ar
e
ta
k
en
f
r
o
m
te
n
d
if
f
er
e
n
t
p
eo
p
le
in
DI
C
OM
f
o
r
m
at.
A
s
a
m
p
le
o
f
n
o
r
m
al
C
T
lu
n
g
an
d
ca
n
ce
r
af
f
ec
ted
C
T
lu
n
g
i
m
ag
es a
r
e
s
h
o
w
n
i
n
F
i
g
u
r
e
s
1
an
d
2
[7
,
8
]
.
Fig
u
r
e
1.
C
T
im
a
g
es o
f
n
o
r
m
a
l lu
n
g
i
m
a
g
e
in
DI
C
O
M
Fig
u
r
e
2.
C
T
im
a
g
es o
f
l
u
n
g
c
an
ce
r
i
m
a
g
e
i
n
DI
C
OM
3.
H
ARALI
C
T
E
XT
URE F
E
A
T
UR
E
S
Har
alick
i
m
p
le
m
en
ted
f
o
u
r
te
en
tex
tu
r
e
f
ea
t
u
r
es
f
r
o
m
G
L
C
M
f
o
r
a
n
i
m
ag
e
.
T
h
ese
f
e
atu
r
es
ar
e
as f
o
llo
w
s
:
-
E
n
tr
o
p
y
:
I
t is a
m
ea
s
u
r
e
o
f
r
a
n
d
o
m
n
es
s
o
f
t
h
e
in
p
u
t i
m
ag
e.
Ma
th
e
m
atica
ll
y
,
it c
an
b
e
r
ep
r
esen
ted
b
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
Dev
elo
p
men
t o
f a
lg
o
r
ith
m
fo
r
id
en
tifi
ca
tio
n
o
f m
a
lig
a
n
t g
r
o
w
th
in
ca
n
ce
r
u
s
in
g
a
r
tifi
cia
l
.
.
.
(
R
.
P
a
n
d
ia
n
)
5711
∑
P
(
i
,
j
)
∗
[
−
l
n
P
(
i
,
j
)
]
N
−
1
i
,
j
=
0
(
1
)
-
C
o
n
t
r
a
s
t
:
I
t
w
i
ll
m
e
as
u
r
e
th
e
in
t
e
n
s
ity
o
r
g
r
ay
-
l
ev
el
v
a
r
i
a
ti
o
n
s
b
e
tw
e
en
th
e
r
ef
e
r
en
c
e
p
i
x
e
l
an
d
i
t
s
n
e
ig
h
b
o
r
.
C
o
n
tr
ast =
∑
n2
N
−
1
n
=
0
∑
i
−
j
=
n
Pd
(
i
,
j
)
(
2
)
-
C
o
r
r
e
l
a
ti
o
n
:
T
h
is
f
e
a
tu
r
e
m
e
asu
r
es
h
o
w
a
p
ix
e
l
is
c
o
r
r
e
la
t
e
d
to
i
t
s
n
e
ig
h
b
o
r
h
o
o
d
.
I
t
t
h
e
e
q
u
a
ti
o
n
is
g
iv
en
b
y
(
i
−
µi
)
(
j
−
µj
)
∗
P
(
i
,
j
)
σ
i
σ
j
(
3
)
-
Ho
m
o
g
e
n
eit
y
L
:
T
h
e
eq
u
atio
n
is
g
i
v
e
n
b
y
∑
{
P
(
i
,
j
)
|
1
+
(
i
−
j
)
}
N
−
1
i
,
j
=
0
(
4
)
-
E
n
er
g
y
:
it is
r
ep
r
esen
ted
b
y
E
=
∑
P
(
i
,
j
)
2
N
−
1
i
,
j
=
0
(
5
)
-
Au
to
co
r
r
elatio
n
: I
t is t
h
e
m
ea
s
u
r
e
o
f
th
e
co
ar
s
e
n
es
s
o
f
th
e
i
m
ag
e
.
I
f
lo
w
v
al
u
e,
tex
tu
r
e
is
r
o
u
g
h
.
-
Dis
s
i
m
ilar
i
t
y
: I
t i
s
a
m
ea
s
u
r
e
o
f
d
is
s
i
m
ilar
it
y
b
et
w
ee
n
g
r
a
y
p
ix
els o
f
a
n
i
m
ag
e.
-
C
lu
s
ter
s
h
ad
e
: T
h
e
clu
s
ter
s
h
a
d
e
w
ill
g
iv
e
i
n
f
o
r
m
atio
n
ab
o
u
t
th
e
s
k
e
w
n
e
s
s
o
f
th
e
m
atr
i
x
.
-
Var
ian
ce
: T
h
e
eq
u
atio
n
i
s
g
i
v
e
n
b
y
∑
∑
(
i
−
µ
)
N
−
1
j
=
0
2
Pd
ϴ
(
i
,
j
)
2
N
−
1
i
=
0
(
6
)
-
An
g
u
lar
s
ec
o
n
d
m
o
m
e
n
t
(
A
S
M)
:
T
h
e
eq
u
atio
n
is
g
i
v
e
n
b
y
∑
∑
Pd
ϴ
(
i
,
j
)
N
−
1
j
=
0
2
N
−
1
i
=
0
(
7
)
-
I
n
v
er
s
e
d
i
f
f
er
en
ce
m
o
m
e
n
t
(
I
DM
)
:
I
DM
m
ea
s
u
r
es
t
h
e
c
lo
s
en
es
s
o
f
t
h
e
d
is
tr
ib
u
tio
n
o
f
th
e
G
L
C
M
ele
m
e
n
ts
to
t
h
e
GL
C
M
d
iag
o
n
al.
Her
e
Fas
t
F
u
zz
y
C
m
ea
n
s
alg
o
r
ith
m
u
s
ed
f
o
r
s
eg
m
e
n
ta
tio
n
.
T
h
r
esh
o
ld
s
e
g
m
en
ta
tio
n
is
ca
lled
th
e
th
r
es
h
o
ld
p
r
o
ce
s
s
,
th
e
ea
s
iest
f
o
r
o
f
s
eg
m
e
n
tatio
n
o
f
i
m
a
g
es.
T
h
is
ap
p
r
o
ac
h
is
b
as
ed
o
n
a
clip
-
lev
el
(
o
r
th
r
esh
o
ld
v
alu
e)
t
o
tu
r
n
a
g
r
a
y
-
s
ca
le
i
m
a
g
e
in
to
a
b
in
ar
y
o
n
e.
T
h
e
tr
ick
to
th
is
ap
p
r
o
ac
h
is
to
p
i
th
e
th
r
ea
d
v
alu
e
[
9
]
.
T
h
e
s
eg
m
e
n
tatio
n
g
o
al
is
to
r
ed
u
ce
o
r
alter
an
i
m
ag
es
p
o
r
tr
a
y
al
i
n
to
o
n
e
t
h
at
i
s
m
o
r
e
co
n
cr
ete
u
n
it
s
i
m
p
ler
to
i
n
ter
p
r
et.
I
m
a
k
e
s
e
g
m
e
n
tat
io
n
u
s
u
all
y
u
s
e
d
i
n
t
h
e
C
T
i
m
ag
e
s
to
id
en
tify
n
o
r
m
al
an
d
ca
n
ce
r
.
I
n
th
i
s
r
esear
ch
w
o
r
k
m
a
n
y
cla
s
s
i
f
ic
atio
n
al
g
o
r
ith
m
s
h
a
v
e
b
ee
n
d
ev
elo
p
ed
f
o
r
f
in
d
i
n
g
ca
n
ce
r
i
n
L
u
n
g
i
m
a
g
es
[
1
0
]
.
I
n
th
i
s
w
o
r
k
,
th
e
id
e
n
ti
f
icatio
n
task
d
o
n
e
b
y
clas
s
i
f
icatio
n
m
eth
o
d
f
r
o
m
a
s
et
o
f
g
r
o
u
p
s
t
h
e
i
m
a
g
es [
1
1
]
.
4.
RE
SU
L
T
AND
DI
SCUS
SI
O
N
T
h
is
s
ec
tio
n
ce
n
ter
s
ar
o
u
n
d
b
ac
k
-
p
r
o
p
ag
atio
n
n
e
u
r
al
n
et
wo
r
k
(
B
P
N
)
s
y
s
te
m
-
b
ased
clas
s
if
ier
s
th
a
t
ar
e
ap
p
r
o
p
r
iate
f
o
r
d
ec
id
in
g
s
ick
n
es
s
[
1
2
]
.
On
e
o
f
t
h
e
g
e
n
er
all
y
ex
p
er
ie
n
ce
d
d
y
n
a
m
ic
er
r
an
d
s
o
f
h
u
m
a
n
m
o
v
e
m
e
n
t
is
o
r
d
er
.
T
h
e
o
r
d
er
ca
n
b
e
ch
ar
ac
ter
ized
as
t
h
e
d
is
tin
g
u
is
h
i
n
g
p
r
o
o
f
u
n
d
er
tak
in
g
to
w
h
ic
h
a
lo
t
o
f
t
h
e
g
at
h
er
in
g
,
a
n
o
th
e
r
p
er
ce
p
tio
n
h
as
a
p
lace
,
b
a
s
ed
o
n
p
r
ep
ar
in
g
a
lo
t
o
f
in
f
o
r
m
atio
n
co
n
tai
n
i
n
g
o
b
s
er
v
atio
n
[
1
3
,
1
4
]
.
I
n
th
is
e
x
a
m
in
at
io
n
w
o
r
k
,
th
e
d
iv
er
s
e
C
T
im
a
g
es
ar
e
th
e
g
at
h
er
i
n
g
s
an
d
th
e
p
r
ep
ar
atio
n
in
f
o
r
m
atio
n
i
n
co
r
p
o
r
ate
th
e
h
i
g
h
l
ig
h
t
s
,
w
h
ic
h
w
er
e
r
e
m
o
v
ed
f
r
o
m
t
y
p
ical
a
n
d
s
tr
an
g
e
i
m
a
g
es
[
1
5
,
1
6
]
.
I
n
t
h
is
w
o
r
k
,
t
h
e
B
P
N
o
r
g
an
ize
is
u
til
ized
f
o
r
c
h
ar
ac
ter
izin
g
t
h
e
C
T
i
m
ag
e
s
.
T
h
e
h
i
g
h
li
g
h
t
s
ar
e
s
ep
ar
ated
f
r
o
m
C
T
i
m
a
g
es
o
f
o
r
d
in
ar
y
lu
n
g
an
d
m
al
ig
n
a
n
t
g
r
o
w
th
i
n
f
l
u
en
ce
d
l
u
n
g
ar
e
ta
k
en
in
to
th
e
ex
a
m
i
n
atio
n
.
GL
C
M
b
ased
h
ig
h
li
g
h
ts
ar
e
e
x
tr
e
m
el
y
h
e
lp
f
u
l
in
d
i
s
ti
n
g
u
i
s
h
i
n
g
s
ic
k
n
e
s
s
e
s
s
i
n
ce
th
e
h
i
g
h
lig
h
t
s
ar
e
i
n
d
icati
n
g
th
e
w
id
e
co
n
tr
ast
b
et
w
ee
n
t
h
e
t
w
o
clas
s
es
[
1
7
,
1
8
]
.
T
h
e
B
P
N
is
u
t
ilized
to
ar
r
an
g
e
t
h
ese
i
m
a
g
es
[
1
9
,
20
]
.
T
h
e
ex
ac
t
n
ess
o
f
t
h
e
s
y
s
te
m
i
s
c
h
an
g
e
d
s
o
as
to
i
m
p
r
o
v
e
th
e
o
r
d
er
o
f
th
e
clas
s
es
d
ep
en
d
en
t
o
n
t
h
e
ca
p
ac
it
y
o
f
cr
ea
ted
ca
lcu
la
t
io
n
.
T
h
e
in
f
er
r
ed
h
i
g
h
li
g
h
ts
,
w
h
ich
ar
e
tab
u
lated
i
n
T
ab
le
1
,
g
iv
es
a
w
i
d
e
d
is
ti
n
ctio
n
b
et
w
ee
n
t
h
e
t
y
p
ical
an
d
m
ali
g
n
an
t
g
r
o
w
th
p
ict
u
r
es
an
d
th
e
p
r
o
p
o
s
ed
p
r
ess
u
r
e
ca
lc
u
latio
n
s
d
o
n
'
t
i
n
f
lu
e
n
ce
t
h
e
q
u
alitie
s
m
u
c
h
.
T
h
e
id
ea
l
ca
l
cu
lat
io
n
i
s
p
i
ck
ed
d
ep
en
d
en
t
o
n
th
e
ar
r
an
g
e
m
e
n
t
ac
cu
r
ac
y
[
2
1
,
2
2
]
.
T
h
e
GL
C
M
f
ea
tu
r
e
s
ar
e
an
al
y
s
ed
in
t
h
is
w
o
r
k
,
s
o
as
to
ch
ar
ac
ter
ize
th
e
lu
n
g
C
T
i
m
a
g
es.
T
h
e
v
ar
i
atio
n
b
et
w
ee
n
t
h
e
n
o
r
m
a
l
i
m
a
g
e
an
d
ca
n
ce
r
i
m
ag
e,
clea
r
l
y
r
ev
ea
l
th
e
ca
p
ab
ilit
y
o
f
th
i
s
m
et
h
o
d
to
class
i
f
y
th
e
n
o
r
m
al
i
m
a
g
e
f
r
o
m
t
h
e
ca
n
ce
r
i
m
ag
e
[
2
3
-
2
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
:
5
7
0
9
-
5
7
1
3
5712
T
ab
le
1
.
GL
C
M
i
m
a
g
e
f
ea
t
u
r
e
o
f
n
o
r
m
al
a
n
d
c
an
ce
r
l
u
n
g
i
m
ag
e
F
e
a
t
u
r
e
s
N
o
r
mal
L
u
n
g
C
a
n
c
e
r
L
u
n
g
I
mag
e
e
n
t
r
o
p
y
5
.
7
3
3
.
5
6
A
u
t
o
c
o
r
r
e
l
a
t
i
o
n
2
1
.
5
6
7
.
3
4
C
o
n
t
r
a
st
0
.
5
6
0
.
3
1
C
o
r
r
e
l
a
t
i
o
n
0
.
9
3
0
.
9
5
C
l
u
st
e
r
p
r
o
mi
e
n
c
e
5
3
5
.
4
6
2
3
4
.
7
8
C
l
u
st
e
r
sh
a
d
e
8
2
.
9
6
7
8
.
9
5
D
i
ssi
m
i
l
a
r
i
t
y
0
.
2
5
0
.
2
3
S
u
m o
f
s
q
u
a
r
e
2
1
.
7
1
8
.
0
4
S
u
m o
f
a
v
e
r
a
g
e
8
.
5
2
4
.
4
5
S
u
m o
f
v
a
r
i
a
n
c
e
6
1
.
9
3
1
9
.
4
7
I
n
f
o
r
mat
i
o
n
me
a
s
u
r
e
o
f
c
o
r
r
e
l
a
t
i
o
n
0
.
6
1
0
.
6
3
I
N
M
0
.
9
7
0
.
4
3
En
e
r
g
y
0
.
3
1
0
.
1
8
M
a
x
i
m
u
m
p
r
o
b
a
l
i
t
y
0
.
5
2
0
.
3
6
H
o
mo
g
e
n
e
i
t
y
0
.
9
1
0
.
6
7
5.
CO
NCLU
SI
O
N
I
n
th
i
s
w
o
r
k
,
t
h
e
alg
o
r
it
h
m
is
d
ev
elo
p
ed
f
o
r
class
if
y
th
e
b
io
m
ed
ical
i
m
a
g
es.
T
h
e
f
e
atu
r
es
ar
e
ex
tr
ac
ted
f
r
o
m
C
T
i
m
a
g
es
o
f
n
o
r
m
al
L
u
n
g
a
n
d
C
a
n
ce
r
af
f
e
cted
L
u
n
g
is
tak
e
n
i
n
to
t
h
e
s
t
u
d
y
.
E
v
en
t
h
o
u
g
h
,
ea
ch
d
is
ea
s
e
t
y
p
e
h
a
s
u
n
iq
u
e
ch
ar
ac
ter
is
tic
s
an
d
p
atter
n
s
,
s
o
m
e
s
i
m
ilar
it
ies
ar
e
also
f
o
u
n
d
a
m
o
n
g
th
e
s
e
ca
teg
o
r
ies
t
h
at
w
il
l
lead
t
o
d
if
f
ic
u
lt
y
i
n
d
esi
g
n
in
g
a
class
i
f
ier
w
it
h
a
co
r
r
ec
t
d
ec
is
io
n
b
o
u
n
d
ar
y
.
Hen
ce
,
t
h
e
s
e
lectio
n
o
f
f
ea
t
u
r
es
is
a
co
m
p
le
x
p
r
o
b
le
m
,
w
h
i
ch
i
s
o
v
er
co
m
e
b
y
ca
r
e
f
u
l
tr
ia
l
an
d
er
r
o
r
p
r
o
ce
s
s
.
Mo
r
eo
v
er
,
ef
f
icien
t
f
ea
t
u
r
e
s
elec
tio
n
is
s
til
l
a
p
r
o
b
lem
i
n
m
ed
ical
I
m
a
g
es
an
d
it
ca
n
b
e
ad
d
r
ess
ed
in
f
u
t
u
r
e,
in
a
n
e
f
f
ec
tiv
e
m
an
n
er
to
ac
h
iev
e
b
etter
r
es
u
lts
.
T
h
e
cla
s
s
if
ica
tio
n
ac
c
u
r
ac
y
o
f
th
e
B
i
n
ar
y
cla
s
s
i
f
ier
f
i
n
d
s
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
s
s
u
ita
b
le
f
o
r
id
en
tify
i
n
g
t
h
e
ca
n
ce
r
d
is
ea
s
e.
ACK
NO
WL
E
D
G
E
M
E
NT
S
W
e
w
o
u
ld
li
k
e
to
th
a
n
k
t
h
e
m
a
n
a
g
e
m
e
n
t
o
f
Sat
h
y
ab
a
m
a
I
n
s
t
itu
te
o
f
Scie
n
ce
a
n
d
T
ec
h
n
o
lo
g
y
C
h
e
n
n
ai,
T
am
il Na
d
u
f
o
r
allo
w
i
n
g
u
s
to
co
n
d
u
ct
s
t
u
d
y
.
RE
F
E
R
E
NC
E
S
[1
]
A
.
S
a
id
a
n
d
W
.
A
.
P
e
a
rlso
n
,
“
A
n
im
a
g
e
m
u
lt
i
re
so
lu
ti
o
n
re
p
re
se
n
t
a
ti
o
n
f
o
r
l
o
ss
les
s
a
n
d
lo
ss
y
c
o
m
p
re
ss
io
n
,
”
I
EE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Ima
g
e
Pro
c
e
ss
in
g
,
v
o
l.
5
,
n
o
.
9
,
pp
.
1
3
0
3
-
1
3
1
0
,
1
9
9
6
.
[2
]
C
.
De
n
g
,
e
t
a
l.
,
“
C
o
n
ten
t
-
b
a
se
d
i
m
a
g
e
c
o
m
p
re
ss
io
n
f
o
r
a
rb
it
ra
ry
-
r
e
so
lu
ti
o
n
d
isp
lay
d
e
v
ice
s
,”
Pro
c
e
e
d
in
g
s
o
f
2
0
1
1
IEE
E
In
t
e
rn
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Co
mm
u
n
ica
t
io
n
s
,
p
p
.
1
-
5
,
2
0
1
1
.
[3
]
L
.
S
.
Da
v
is
,
e
t
a
l.
,
“
T
e
x
tu
re
a
n
a
ly
sis
u
sin
g
g
e
n
e
ra
li
z
e
d
c
o
-
o
c
c
u
rre
n
c
e
m
a
tri
c
e
s,
”
IEE
E
T
r
a
n
sa
c
ti
o
n
s
o
n
Pa
tt
e
rn
A
n
a
lys
is a
n
d
M
a
c
h
i
n
e
In
t
e
ll
ig
e
n
c
e
,
v
o
l.
P
A
M
I
-
1,
n
o
.
3
,
pp
.
251
-
2
5
9
,
1
9
7
9
.
[4
]
R.
M
.
Ha
ra
li
c
k
,
e
t
a
l.
,
“
T
e
x
tu
ra
l
fe
a
tu
re
s
f
o
r
i
m
a
g
e
c
las
sif
ic
a
ti
o
n
,
”
IEE
E
T
ra
n
s
a
c
ti
o
n
s
o
n
S
y
ste
ms
,
M
a
n
,
and
Cy
b
e
rn
e
ti
c
s
:
S
y
ste
ms
,
v
o
l.
S
M
C
-
3,
n
o
.
6
,
pp
.
6
1
0
-
6
2
1
,
1
9
7
3
.
[5
]
J.
S
.
W
e
sz
k
a
,
e
t
a
l.
,
“
A
Co
m
p
a
ra
t
iv
e
S
tu
d
y
o
f
Tex
tu
re
M
e
a
su
re
s
f
o
r
T
e
rra
in
Clas
si
f
ic
a
ti
o
n
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
S
y
ste
ms
,
M
a
n
,
a
n
d
Cy
b
e
rn
e
ti
c
s
:
S
y
ste
ms
,
v
o
l.
SMC
-
6,
n
o
.
4
,
p
p
.
269
-
2
8
5
,
1
9
7
6
.
[6
]
R.
P
a
n
d
ian
,
e
t
a
l.
,
“
Ch
a
ra
c
teriz
a
ti
o
n
o
f
CT
c
a
n
c
e
r
lu
n
g
im
a
g
e
u
sin
g
im
a
g
e
c
o
m
p
re
ss
io
n
a
lg
o
rit
h
m
s
a
n
d
f
e
a
tu
re
Ex
trac
ti
o
n
,
”
J
o
u
rn
a
l
o
f
sc
ien
ti
fi
c
a
n
d
in
d
u
stri
a
l
re
se
a
rc
h
,
v
o
l
.
7
5
,
n
o
.
1
2
,
pp
.
7
4
7
-
7
5
1
,
2
0
1
6
.
[7
]
R
.
P
a
n
d
ian
a
n
d
T
.
V
ig
n
e
sw
a
ra
n
,
“
A
d
a
p
ti
v
e
w
a
v
e
let
p
a
c
k
e
t
b
a
sis
se
lec
ti
o
n
f
o
r
z
e
ro
tree
i
m
a
g
e
c
o
d
in
g
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
S
ig
n
a
l
a
n
d
Im
a
g
i
n
g
S
y
ste
ms
En
g
in
e
e
rin
g
,
v
o
l
.
9,
n
o
.
6
,
pp
.
3
8
8
-
3
9
2
,
2
0
1
6
.
[8
]
A
.
El
-
Ba
z
l,
e
t
a
l.
,
“
A
u
to
m
a
ti
c
id
e
n
ti
f
ica
ti
o
n
o
f
lu
n
g
a
b
n
o
rm
a
li
ti
e
s
in
c
h
e
st
sp
iral
CT
sc
a
n
s
,
”
I
EE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Aco
u
stics
,
S
p
e
e
c
h
,
a
n
d
S
ig
n
a
l
Pro
c
e
ss
in
g
,
v
o
l
.
2
,
pp
.
2
6
1
-
2
6
4
,
2
0
0
3
.
[9
]
R.
P
a
n
d
ian
,
“
Ev
a
lu
a
ti
o
n
o
f
ima
g
e
c
o
m
p
re
s
sio
n
a
lg
o
rit
h
m
,
”
2
0
1
5
I
EE
E
Un
d
e
r
wa
ter
T
e
c
h
n
o
l
o
g
y
(
UT)
,
pp
.
1
-
3,
2
0
1
5
.
[1
0
]
K.
Ka
n
a
z
a
w
a
,
e
t
a
l
.
,
“
Co
m
p
u
ter
a
id
e
d
d
iag
n
o
sis
f
o
r
p
u
lm
o
n
a
ry
n
o
d
u
les
b
a
se
d
o
n
h
e
li
c
a
l
CT
im
a
g
e
,
”
Co
mp
u
ter
ize
d
M
e
d
ica
l
Ima
g
in
g
a
n
d
Gr
a
p
h
ics
,
v
o
l
.
22,
n
o
.
2
,
pp
.
1
5
7
-
1
6
7
,
1
9
9
8
.
[1
1
]
D.
T
.
L
in
a
a
n
d
C.
R.
Ya
n
,
“
L
u
n
g
n
o
d
u
les
id
e
n
ti
f
ica
ti
o
n
ru
les
e
x
trac
ti
o
n
w
it
h
n
e
u
ra
l
f
u
z
z
y
n
e
t
w
o
rk
,
”
Pro
c
e
e
d
in
g
o
f
th
e
9
t
h
I
n
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
Ne
u
r
a
l
I
n
fo
rm
a
ti
o
n
Pr
o
c
e
ss
in
g
,
v
o
l
.
4,
pp
.
2
0
4
9
-
2
0
5
3
,
2
0
0
2
.
[1
2
]
G
.
P
.
Zh
a
n
g
,
et
al
.
,
“
Ne
u
ra
l
n
e
tw
o
rk
s
f
o
r
c
las
sif
ic
a
ti
o
n
su
rv
e
y
,
”
I
EEE
T
ra
n
sa
c
ti
o
n
s
on
S
y
st
e
ms
,
M
a
n
,
a
nd
Cy
b
e
rn
e
ti
c
s
Pa
rt C
,
vol
.
3
0
,
n
o
.
4
,
pp
.
4
5
1
-
46
2
,
2
0
0
2
.
[1
3
]
C
.
De
n
g
,
e
t
a
l.
,
“
Co
n
ten
t
-
Ba
se
d
I
m
a
g
e
Co
m
p
re
s
sio
n
f
o
r
A
rb
it
ra
r
y
-
Re
so
lu
ti
o
n
Disp
lay
De
v
i
c
e
s,
”
IE
EE
T
ra
n
s
a
c
ti
o
n
o
n
M
u
l
ti
me
d
ia
,
v
o
l.
1
4
,
n
o
.
4
,
pp
.
1
1
2
7
-
1
1
3
9
,
2
0
1
2
.
[1
4
]
I.
M
a
g
lo
g
ian
n
is,
e
t
a
l.
,
“
W
a
v
e
let
h
ROI
c
o
d
i
n
g
su
p
p
o
rt
f
o
r
m
o
b
il
e
a
c
c
e
ss
to
DICO
M
i
m
a
g
e
s
o
v
e
r
h
e
tero
g
e
n
e
o
u
s
ra
d
io
n
e
tw
o
rk
s
,”
T
ra
n
s
a
c
ti
o
n
s o
n
In
fo
rm
a
t
io
n
T
e
c
h
n
o
l
o
g
y
i
n
Bi
o
me
d
icin
e
, v
o
l
.
1
3
,
n
o
.
4
,
pp
.
4
5
8
-
4
6
6
,
2
0
0
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
Dev
elo
p
men
t o
f a
lg
o
r
ith
m
fo
r
id
en
tifi
ca
tio
n
o
f m
a
lig
a
n
t g
r
o
w
th
in
ca
n
ce
r
u
s
in
g
a
r
tifi
cia
l
.
.
.
(
R
.
P
a
n
d
ia
n
)
5713
[1
5
]
D.
Dra
g
a
n
a
n
d
D
.
Iv
e
ti
c
,
“
A
n
a
p
p
ro
a
c
h
to
DICO
M
e
x
ten
sio
n
f
o
r
m
e
d
ica
l
ima
g
e
stre
a
m
in
g
,
”
DAAA
M
I
n
ter
n
a
ti
o
n
a
l
S
c
ien
ti
fi
c
B
ook
,
p
p
.
25
-
35,
2
0
0
9
.
[1
6
]
R.
A
.
Os
o
rn
io
-
R
io
s
,
“I
d
e
n
ti
f
ica
ti
o
n
o
f
p
o
siti
o
n
i
n
g
sy
ste
m
f
o
r
in
d
u
strial
a
p
p
li
c
a
ti
o
n
u
si
n
g
n
e
u
ra
l
n
e
t
w
o
rk
,
”
J
o
u
rn
a
l
of
S
c
i
e
n
ti
fi
c
a
n
d
In
d
u
stri
a
l
Res
e
a
rc
h
,
v
o
l.
76,
n
o
.
3
,
pp
.
1
4
1
-
1
4
4
,
2
0
1
7
.
[1
7
]
W
.
J.
Ch
o
i
,
e
t
a
l
.,
“
A
u
to
m
a
ted
P
u
lm
o
n
a
ry
No
d
u
le
De
tec
ti
o
n
Ba
se
d
o
n
T
h
re
e
-
Dim
e
n
sio
n
a
l
S
h
a
p
e
-
Ba
se
d
F
e
a
tu
re
De
sc
rip
to
r
,
”
Co
mp
u
t
er
M
e
th
o
d
s
a
n
d
Pr
o
g
r
a
ms
in
Bi
o
me
d
ici
n
e
,
v
o
l.
1
1
3
,
n
o
.
1
,
pp
.
37
-
54,
2
0
1
4
.
[1
8
]
D.
M
.
P
e
ñ
a
,
e
t
a
l.
,
“
A
u
to
Dia
g
n
o
stics
o
f
L
u
n
g
No
d
u
les
Us
in
g
M
in
im
a
l
Ch
a
ra
c
teristics
Ex
tra
c
ti
o
n
T
e
c
h
n
iq
u
e
,
”
Dia
g
n
o
stics
,
v
o
l
.
6
,
n
o
.
1
,
p
p
.
1
3
,
2
0
1
6
.
[1
9
]
N.
Ca
m
a
rli
n
g
,
e
t
a
l.
,
“
Co
m
b
in
a
ti
o
n
o
f
Co
m
p
u
ter
-
A
id
e
d
De
tec
ti
o
n
A
lg
o
rit
h
m
s
f
o
r
A
u
to
m
a
ti
c
L
u
n
g
No
d
u
le
Id
e
n
ti
f
ica
ti
o
n
,
”
In
t
e
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
mp
u
t
er
Assist
ed
Ra
d
i
o
l
o
g
y
a
n
d
S
u
rg
e
ry
,
v
o
l.
7
,
n
o
.
3
,
pp
.
4
5
5
4
6
4
,
2
0
1
2
.
[2
0
]
A
.
Tera
m
o
to
a
n
d
H.
F
u
ji
ta
,
“
F
a
st
L
u
n
g
No
d
u
le
De
tec
ti
o
n
in
Ch
e
st
CT
Im
a
g
e
s
Us
in
g
C
y
li
n
d
rica
l
No
d
u
le
-
En
h
a
n
c
e
m
e
n
t
F
il
ter
,”
In
t
e
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
m
p
u
t
er
Assi
st
ed
Ra
d
i
o
l
o
g
y
a
n
d
S
u
rg
e
ry
,
v
o
l.
8
,
n
o
.
2
,
pp
.
1
9
3
-
2
0
5
,
2
0
1
3
.
[2
1
]
S
.
R.
S
u
ra
lk
a
r
a
n
d
P
.
M
.
P
a
ti
l,
“
Co
rre
latio
n
b
a
se
d
F
i
n
g
e
rp
rin
t
I
m
a
g
e
S
e
g
m
e
n
tatio
n
,
”
In
t
e
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
mp
u
t
er
A
p
p
l
ica
ti
o
n
s
,
v
o
l.
6
8
,
n
o
.
7
,
p
p
.
1
-
3,
2
0
1
3
.
[2
2
]
M
.
F
.
F
a
h
m
y
a
n
d
M
.
A
.
T
h
a
b
e
t,
“
A
f
in
g
e
rp
rin
t
se
g
m
e
n
tatio
n
tec
h
n
i
q
u
e
b
a
se
d
o
n
m
o
rp
h
o
lo
g
ica
l
p
ro
c
e
ss
in
g
,
”
i
n
IEE
E
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
si
u
m
o
n
S
i
g
n
a
l
Pr
o
c
e
ss
in
g
a
n
d
In
fo
rm
a
t
io
n
T
e
c
h
n
o
lo
g
y
,
p
p
.
0
0
0
2
1
5
-
0
0
0
2
2
0
,
2
0
1
3
.
[2
3
]
K.
S
h
re
e
d
a
rsh
a
n
a
n
d
S
e
lv
i
S.
S
.
,
“
Cro
w
d
Re
c
o
g
n
it
io
n
S
y
ste
m
Ba
s
e
d
o
n
Op
ti
c
a
l
F
l
o
w
A
lo
n
g
w
it
h
S
V
M
c
las
sif
ier,
”
In
t
e
rn
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
lec
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
.
4
,
p
p
.
2
4
5
1
-
2
4
5
9
,
2
0
1
9
.
[2
4
]
A
.
A
.
A
b
d
u
ll
a
h
,
A
.
F
.
D.
G
io
n
g
,
a
n
d
N.
A
.
H.
Za
h
ri
,
“
Ce
rv
ica
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
(CNN
)
a
lg
o
rit
h
m
,
”
In
d
o
n
e
sia
J
o
u
rn
a
l
o
f
E
lec
trica
l
En
g
i
n
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
,
v
o
l.
1
4
,
n
o
.
1
,
p
p
.
2
1
0
-
2
1
8
,
2
0
19
.
[2
5
]
M
.
Y.
Ka
m
il
a
n
d
A
.
M
.
S
a
li
h
,
“
M
a
m
m
o
g
ra
p
h
y
I
m
a
g
e
s
S
e
g
m
e
n
tatio
n
v
ia
F
u
z
z
y
C
-
m
e
a
n
a
n
d
K
-
m
e
a
n
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
I
n
telli
g
e
n
t
E
n
g
i
n
e
e
rin
g
a
n
d
S
y
ste
ms
,
v
o
l.
1
2
,
n
o
.
1
,
p
p
.
2
2
-
2
9
,
2
0
1
9
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
R.
Pa
n
d
i
a
n
is
c
u
rre
n
tl
y
w
o
rk
in
g
a
s
a
n
A
ss
o
c
iate
P
ro
f
e
ss
o
r
in
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
ics
a
n
d
In
stru
m
e
n
tatio
n
En
g
i
n
e
e
rin
g
a
t
S
a
th
y
a
b
a
m
a
In
stit
u
te
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
Ch
e
n
n
a
i,
T
a
m
il
Na
d
u
,
In
d
ia.
He
h
a
s
g
ra
d
u
a
ted
f
ro
m
M
a
d
ra
s
Un
iv
e
rsit
y
,
Ch
e
n
n
a
i
i
n
1
9
9
9
w
it
h
Ba
c
h
e
lo
r'
s
De
g
re
e
in
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ics
En
g
in
e
e
rin
g
.
He
h
a
s
o
b
tain
e
d
h
is
M
.
E
De
g
re
e
in
A
p
p
li
e
d
El
e
c
tro
n
ics
f
ro
m
A
n
n
a
Un
i
v
e
rsit
y
,
Ch
e
n
n
a
i
2
0
0
7
.
He
h
a
s
o
b
tain
e
d
h
is
P
h
.
D
.
f
ro
m
S
a
th
y
a
b
a
m
a
In
stit
u
te
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
.
D.N.S
Ra
v
i
K
u
m
a
r
h
a
s
c
o
m
p
lete
d
h
is
M
.
S
c
.
(A
p
p
li
e
d
El
e
c
tro
n
ics
)
in
t
h
e
y
e
a
r
2
0
0
3
f
ro
m
Bh
a
ra
th
iy
a
r
Un
iv
e
rs
it
y
Co
i
m
b
a
to
re
,
In
d
ia
a
n
d
M
.
E
(
(
A
p
p
li
e
d
El
e
c
t
ro
n
ics
)
in
t
h
e
y
e
a
r
2
0
0
6
f
ro
m
S
a
th
y
a
b
a
m
a
In
stit
u
te
o
f
S
c
ien
c
e
&
T
e
c
h
n
o
lo
g
y
Ch
e
n
n
a
i
In
d
ia.He
is
p
u
rsin
g
P
h
D
in
th
e
f
ield
o
f
V
e
h
icu
lar
Co
m
m
u
n
ica
ti
o
n
(Distrib
u
te
d
Em
b
e
d
d
e
d
S
y
st
e
m
s
)
f
r
o
m
S
a
th
y
a
b
a
m
a
In
stit
u
te
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
sin
c
e
2
0
1
5
,
C
h
e
n
n
a
i
In
d
ia.H
is
f
ield
o
f
in
tres
ts
in
c
lu
d
e
s
Em
b
e
d
d
e
d
S
y
st
e
m
s
,
V
e
h
icu
lar
Co
m
m
u
n
ica
ti
o
n
a
n
d
Ro
b
o
ti
c
s.
He
is
c
u
rre
n
tl
y
w
o
rk
in
g
o
n
S
m
a
rt
c
a
r
T
e
c
h
n
o
lo
g
y
(V
2
V
).
A
p
a
rt
f
ro
m
re
se
a
rc
h
a
n
in
n
o
v
a
to
r
t
o
sp
a
rk
sta
rt
u
p
i
d
e
a
s to
im
p
lem
e
n
tatio
n
Dr
.
R.
Ra
ja
k
u
m
a
r
is
a
P
ro
f
e
ss
o
r
in
De
p
a
rtm
e
n
t
o
f
M
a
th
e
m
a
ti
c
s
h
a
v
in
g
e
x
p
e
rien
c
e
o
f
2
5
y
e
a
rs
in
tea
c
h
in
g
a
n
d
w
o
rk
in
g
in
o
u
r
Un
iv
e
rsit
y
f
o
r
th
e
p
a
st
1
3
y
e
a
rs
w
it
h
Do
c
to
ra
te
in
th
e
f
ield
o
f
Ch
a
o
s
T
h
e
o
ry
,
jo
in
e
d
S
a
th
y
a
b
a
m
a
Un
iv
e
rsit
y
a
s
L
e
c
tu
re
rin
2
0
0
3
,
c
o
m
p
lete
d
P
h
D
i
n
t
h
e
y
e
a
r
2
0
1
3
f
ro
m
S
a
th
y
a
b
a
m
a
In
stit
u
te o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.