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.
9
,
No
.
4
,
A
u
g
u
s
t
201
9
,
p
p
.
2
4
6
0
~
2
4
6
8
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
9
i
4
.
p
p
2
4
6
0
-
2468
2460
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
Liv
e and
dea
d cel
ls co
unting
f
ro
m
m
icro
sco
pic
t
ry
p
a
n blue
sta
ining
i
m
a
g
es
u
sing
thresho
ldin
g
a
nd
m
o
rp
ho
lo
g
ica
l
o
pera
tion tech
niq
ues
Su
M
o
n Aung
1
,
K
a
ny
a
na
t
t
K
a
no
k
w
iro
o
n
2
,
T
o
ng
ha
t
ha
i
P
ha
ira
t
a
na
3
,
Su
ra
po
ng
Cha
t
pu
n
4
1,
3
,4
I
n
stit
u
te
o
f
Bio
m
e
d
ica
l
En
g
in
e
e
rin
g
,
F
a
c
u
lt
y
o
f
M
e
d
icin
e
,
P
ri
n
c
e
o
f
S
o
n
g
k
la Un
iv
e
rsit
y
,
T
h
a
il
a
n
d
2
De
p
a
rt
m
e
n
t
o
f
Bio
m
e
d
ica
l
S
c
ien
c
e
s,
F
a
c
u
lt
y
o
f
M
e
d
icin
e
,
P
ri
n
c
e
o
f
S
o
n
g
k
la Un
iv
e
rsity
,
T
h
a
il
a
n
d
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
4
,
2
0
1
8
R
ev
i
s
ed
Ma
r
1
5
,
2
0
1
9
A
cc
ep
ted
Ma
r
2
2
,
2
0
1
9
Ce
ll
c
o
u
n
ti
n
g
is
a
re
q
u
ired
p
r
o
c
e
d
u
re
in
b
i
o
m
e
d
ica
l
e
x
p
e
ri
m
e
n
ts
a
n
d
d
ru
g
tes
ti
n
g
.
M
a
n
u
a
l
c
e
ll
c
o
u
n
ti
n
g
p
e
rf
o
r
m
e
d
w
it
h
a
h
e
m
o
c
y
to
m
e
ter
is
ti
m
e
c
o
n
su
m
in
g
a
n
d
in
d
iv
id
u
a
l
d
e
p
e
n
d
e
n
c
e
.
T
h
is
stu
d
y
re
p
o
rted
th
e
d
e
v
e
lo
p
m
e
n
t
o
f
a
c
o
m
p
u
ter
-
a
ss
isted
p
ro
g
ra
m
f
o
r
tr
y
p
a
n
b
lu
e
sta
in
e
d
-
c
e
ll
c
o
u
n
ti
n
g
u
sin
g
d
ig
it
a
l
ima
g
e
a
n
a
l
y
sis.
I
m
a
g
e
s
o
f
tr
y
p
a
n
b
lu
e
-
sta
in
e
d
b
re
a
st
c
a
n
c
e
r
c
e
ll
s
li
n
e
w
e
r
e
o
b
tain
e
d
b
y
a
m
icro
sc
o
p
e
w
it
h
a
d
ig
it
a
l
c
a
m
e
ra
.
Un
d
e
sire
d
n
o
ise
a
n
d
d
e
b
ris
w
e
re
re
m
o
v
e
d
b
y
a
p
p
ly
in
g
a
g
u
id
e
d
im
a
g
e
f
il
ter.
Co
lo
r
sp
a
c
e
HSV
(Hu
e
,
S
a
tu
ra
ti
o
n
a
n
d
V
a
l
u
e
)
c
o
n
v
e
rsio
n
a
n
d
g
ra
y
s
c
a
le
c
o
n
v
e
r
sio
n
w
e
re
p
e
rf
o
r
m
e
d
f
o
r
d
isti
n
g
u
ish
in
g
b
e
tw
e
e
n
li
v
e
a
n
d
d
e
a
d
c
e
ll
s.
I
m
a
g
e
th
re
sh
o
l
d
i
n
g
a
n
d
m
o
rp
h
o
l
o
g
ica
l
o
p
e
ra
to
rs
w
e
re
a
p
p
li
e
d
f
o
r
im
a
g
e
se
g
m
e
n
tatio
n
.
L
iv
e
a
n
d
d
e
a
d
c
e
l
ls
w
e
re
c
o
u
n
ted
a
f
ter
ima
g
e
se
g
m
e
n
tatio
n
a
n
d
th
e
re
su
l
ts
w
e
re
c
o
m
p
a
re
d
w
it
h
m
a
n
u
a
l
c
o
u
n
ti
n
g
b
y
th
re
e
w
e
ll
-
e
x
p
e
rien
c
e
d
c
o
u
n
ters
.
T
h
e
c
o
m
p
u
ter
-
a
ss
isted
c
e
ll
c
o
u
n
ti
n
g
f
ro
m
th
irt
y
-
si
x
try
p
a
n
b
lu
e
-
sta
in
e
d
m
icro
sc
o
p
ic
ima
g
e
s
h
a
d
a
h
ig
h
c
o
rre
latio
n
c
o
e
ff
icie
n
t
w
it
h
th
e
li
v
e
c
e
ll
re
su
lt
s o
f
th
e
e
x
p
e
rts
(r=
0
.
9
9
).
T
h
e
c
o
rre
latio
n
c
o
e
ff
ici
e
n
t
o
f
th
e
n
u
m
b
e
r
o
f
d
e
a
d
c
e
ll
s
c
o
m
p
a
rin
g
th
e
c
o
m
p
u
ter
-
a
ss
isted
c
o
u
n
t
a
n
d
th
e
e
x
p
e
rts’
c
o
u
n
t
w
a
s
0
.
7
4
.
Ou
r
a
p
p
r
o
a
c
h
o
f
f
e
rs
h
ig
h
a
c
c
u
ra
c
y
(
>
8
5
%
)
o
n
c
o
u
n
t
in
g
li
v
e
c
e
ll
s
c
o
m
p
a
re
d
w
it
h
th
e
e
x
p
e
rts’
c
o
u
n
ti
n
g
.
T
h
is
a
u
to
m
a
ted
c
e
ll
c
o
u
n
t
in
g
a
p
p
ro
a
c
h
c
a
n
a
ss
ist
b
io
m
e
d
ica
l
re
s
e
a
rc
h
e
rs
f
o
r
b
o
th
li
v
e
a
n
d
d
e
a
d
c
e
ll
s c
o
u
n
ti
n
g
.
K
ey
w
o
r
d
s
:
C
ell
co
u
n
ti
n
g
Gu
id
ed
i
m
a
g
e
f
ilter
I
m
ag
e
t
h
r
es
h
o
ld
in
g
Mo
r
p
h
o
lo
g
ical
o
p
er
ato
r
T
r
y
p
an
b
lu
e
Co
p
y
rig
h
t
©
2
0
1
9
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
:
Su
r
ap
o
n
g
C
h
atp
u
n
,
I
n
s
tit
u
te
o
f
B
io
m
ed
ical
E
n
g
in
ee
r
in
g
,
Facu
lt
y
o
f
Me
d
ici
n
e,
P
r
in
ce
o
f
So
n
g
k
la
U
n
i
v
er
s
it
y
,
15
Kan
j
an
a
v
an
ich
R
o
ad
,
Hat
y
ai,
So
n
g
k
h
la
9
0
1
1
0
,
T
h
ailan
d
.
E
m
ail:
s
u
r
ap
o
n
g
.
c@
p
s
u
.
ac
.
th
1.
I
NT
RO
D
UCT
I
O
N
I
n
ca
n
ce
r
d
r
u
g
d
is
co
v
er
y
r
ese
ar
ch
es,
m
a
n
y
asp
ec
ts
o
f
n
o
v
e
l
d
r
u
g
tr
ea
t
m
en
t
s
o
n
ca
n
ce
r
c
ells
h
av
e
b
ee
n
s
tu
d
ied
,
in
cl
u
d
in
g
m
o
r
p
h
o
lo
g
ical
an
d
ce
ll
u
lar
s
tr
u
c
tu
r
e
ch
an
g
e
s
an
d
d
r
u
g
r
esp
o
n
s
e
[
1
-
3
]
.
On
e
s
i
m
p
le
in
v
e
s
ti
g
atio
n
to
ev
al
u
ate
t
h
e
e
f
f
icac
y
o
f
ca
n
ce
r
d
r
u
g
tr
ea
t
m
e
n
ts
i
s
t
h
e
id
en
t
if
icatio
n
o
f
ap
o
p
to
tic
ce
lls
an
d
li
v
e
ce
lls
[
4
]
.
A
p
o
p
to
s
is
is
a
p
r
o
g
r
a
m
m
ab
le
ce
l
l
d
ea
th
,
wh
ich
ca
n
b
e
ca
te
g
o
r
icall
y
o
b
s
er
v
ed
f
r
o
m
ce
ll
m
o
r
p
h
o
lo
g
ical
c
h
a
n
g
e
s
.
C
o
u
n
tin
g
v
iab
le
ce
lls
o
r
liv
e
ce
lls
p
er
to
tal
ce
lls
a
f
ter
i
n
v
itro
d
r
u
g
tr
ea
t
m
e
n
t
i
s
a
co
m
m
o
n
tas
k
f
o
r
b
io
lo
g
is
t
s
an
d
b
io
m
ed
ical
r
esear
ch
er
s
w
h
en
t
h
e
y
e
v
al
u
ate
th
e
e
f
f
icac
y
.
Ma
n
u
al
ce
ll
co
u
n
ti
n
g
b
y
a
b
io
m
ed
ical
ex
p
er
t
w
it
h
a
tall
y
co
u
n
ter
is
a
co
n
v
e
n
tio
n
al
m
et
h
o
d
b
u
t
th
e
co
u
n
ti
n
g
r
esu
lt
i
s
an
in
d
iv
id
u
al
d
e
p
en
d
en
ce
,
a
n
d
it
is
ted
io
u
s
an
d
ti
m
e
-
co
n
s
u
m
i
n
g
.
T
o
o
v
er
co
m
e
t
h
e
d
r
a
w
b
a
ck
s
o
f
m
an
u
al
ce
l
l
co
u
n
ti
n
g
,
s
e
v
er
al
s
o
f
t
w
ar
e
p
ac
k
ag
e
s
s
u
c
h
as
I
m
a
g
eJ
,
Fij
i,
C
ellP
r
o
f
iler
T
M,
C
ellC
,
I
m
ag
e
-
P
r
o
P
lu
s
a
n
d
Me
taM
o
r
p
h
®,
h
av
e
d
e
v
elo
p
ed
p
lu
g
in
s
f
o
r
ce
ll a
n
al
y
s
is
a
n
d
ce
ll c
o
u
n
t
i
n
g
[
5
-
1
1
]
.
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
Live
a
n
d
d
e
a
d
ce
lls
co
u
n
tin
g
f
r
o
m
micro
s
co
p
ic
tr
yp
a
n
b
lu
e
s
ta
in
in
g
ima
g
es u
s
in
g
…
(
S
u
Mo
n
A
u
n
g
)
2461
C
o
m
p
u
ter
-
as
s
i
s
ted
ce
ll
co
u
n
tin
g
u
s
i
n
g
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
an
d
an
al
y
s
is
h
as
b
ee
n
co
n
ti
n
u
o
u
s
l
y
d
ev
elo
p
ed
an
d
im
p
r
o
v
ed
to
p
r
o
v
id
e
th
e
r
eq
u
ir
em
e
n
t
s
o
f
h
ig
h
r
eliab
ilit
y
,
s
p
ec
i
f
icit
y
an
d
s
en
s
iti
v
it
y
f
o
r
d
if
f
er
e
n
t
ce
ll
t
y
p
es
an
d
test
p
r
o
to
co
ls
.
Fo
r
ex
a
m
p
le,
Su
i
et
a
l.
[
1
2
]
d
ev
elo
p
e
d
a
ce
ll
co
u
n
ti
n
g
m
et
h
o
d
f
o
r
h
o
s
t
ce
lls
i
n
a
b
r
ig
h
t
f
ield
f
o
r
in
s
ec
t c
ells
b
y
u
s
in
g
a
n
o
n
lin
ea
r
tr
a
n
s
f
o
r
m
ed
s
l
id
in
g
b
an
d
f
ilter
.
T
h
e
y
o
b
tai
n
ed
a
lo
w
er
r
o
r
r
ate
an
d
a
h
ig
h
ac
cu
r
ac
y
w
h
e
n
co
m
p
ar
in
g
th
eir
m
eth
o
d
w
it
h
a
m
a
n
u
a
l
co
u
n
t
in
g
.
A
ce
ll
co
u
n
ti
n
g
m
et
h
o
d
f
o
r
w
h
ite
b
lo
o
d
ce
lls
w
a
s
d
ev
elo
p
ed
u
s
in
g
Ma
tlab
to
ev
a
lu
a
te
h
e
m
atic
p
ath
o
lo
g
ies
i
n
ter
m
s
o
f
n
u
m
b
er
s
,
s
ize
s
an
d
t
y
p
e
s
o
f
w
h
ite
b
lo
o
d
ce
lls
[
1
3
]
.
T
h
e
y
ap
p
lied
i
m
a
g
e
en
h
an
ce
m
e
n
t
an
d
i
m
a
g
e
s
e
g
m
e
n
tat
io
n
a
s
p
r
e
-
p
r
o
ce
s
s
in
g
s
tep
s
a
n
d
u
s
ed
a
n
eu
r
al
n
et
w
o
r
k
f
o
r
clas
s
i
f
icat
io
n
.
P
iccin
i
n
i
et
al.
[
1
4
]
u
s
ed
a
f
u
l
l
y
au
to
m
ated
m
o
s
aici
n
g
m
eth
o
d
to
i
m
p
r
o
v
e
th
e
r
eliab
ili
t
y
a
n
d
r
ep
r
o
d
u
cib
ilit
y
o
f
li
v
e
a
n
d
d
ea
d
ce
ll
co
u
n
ti
n
g
.
Mo
u
el
h
i
a
n
d
co
lleag
u
e
s
[
1
5
]
also
d
escr
ib
e
d
au
to
m
atic
i
m
a
g
e
s
e
g
m
en
ta
ti
o
n
w
it
h
ac
ti
v
e
co
n
to
u
r
f
o
r
s
tai
n
ed
n
u
cle
i
in
b
r
ea
s
t
ca
n
ce
r
tis
s
u
e
w
h
ic
h
co
u
ld
s
eg
m
en
t to
u
c
h
in
g
n
u
cle
i to
g
et
t
h
e
to
tal
n
u
m
b
er
o
f
b
r
ea
s
t c
an
ce
r
n
u
clei.
T
h
e
q
u
alit
y
o
f
li
g
h
t
m
icr
o
s
co
p
y
d
i
g
ital
i
m
ag
e
s
tak
e
n
f
r
o
m
h
e
m
o
c
y
to
m
e
tr
y
s
i
g
n
i
f
ican
tl
y
i
n
f
lu
e
n
ce
s
v
is
u
al
a
n
al
y
s
i
s
,
in
cl
u
d
in
g
ce
ll
co
u
n
ti
n
g
.
T
h
er
ef
o
r
e,
m
o
s
t
li
g
h
t
m
icr
o
s
co
p
y
d
i
g
ital
i
m
a
g
e
s
n
ee
d
to
u
n
d
er
g
o
a
p
r
e
-
p
r
o
ce
s
s
in
g
s
tep
b
ef
o
r
e
ce
l
l
s
e
g
m
e
n
tat
io
n
i
s
p
er
f
o
r
m
ed
.
No
is
e
f
ilter
i
n
g
is
o
n
e
o
f
t
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
s
tep
s
in
e
v
er
y
d
i
g
ital
i
m
a
g
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
e.
A
m
e
d
ia
n
f
ilter
is
a
p
o
p
u
lar
n
o
is
e
f
il
ter
w
h
ic
h
is
u
s
ed
to
r
e
m
o
v
e
s
alt
an
d
p
ep
p
er
n
o
is
e
i
n
d
ig
i
ta
l
i
m
a
g
es
[
1
6
-
1
9
]
.
I
t
h
as
b
ee
n
r
ep
o
r
ted
th
at
i
m
p
u
l
s
e
n
o
i
s
e
in
h
ig
h
-
d
en
s
it
y
n
o
i
s
y
i
m
a
g
es
ca
n
b
e
e
f
f
ec
ti
v
el
y
r
em
o
v
ed
b
y
u
s
i
n
g
an
i
m
p
r
o
v
e
d
alg
o
r
ith
m
s
u
c
h
a
s
a
d
ec
is
i
o
n
b
ased
ad
ap
tiv
e
n
eig
h
b
o
r
h
o
o
d
m
ed
ian
f
ilter
[
2
0
]
.
Ma
h
m
o
o
d
an
d
Ma
n
s
o
r
[
2
1
]
u
s
ed
a
m
o
r
p
h
o
lo
g
ica
l
to
o
l
w
i
th
th
e
Ho
u
g
h
tr
an
s
f
o
r
m
tech
n
iq
u
e
to
d
etec
t
an
d
esti
m
ate
t
h
e
n
u
m
b
er
o
f
r
ed
b
lo
o
d
ce
lls
in
b
lo
o
d
s
a
m
p
le
i
m
a
g
es.
L
ie
w
et
al.
[
2
2
]
ap
p
lied
im
a
g
e
p
r
o
ce
s
s
in
g
m
e
t
h
o
d
s
to
d
ev
elo
p
a
p
r
o
to
ty
p
e
f
o
r
a
ce
ll
d
etec
tio
n
alg
o
r
it
h
m
u
s
in
g
cir
cu
lar
Ho
u
g
h
tr
an
s
f
o
r
m
to
d
etec
t
th
e
n
u
m
b
er
o
f
ce
lls
i
n
b
ee
co
m
b
s
f
r
o
m
d
ig
ital
i
m
a
g
es.
A
lt
h
o
u
g
h
th
er
e
ar
e
m
an
y
m
et
h
o
d
s
f
o
r
ce
ll
d
etec
t
io
n
an
d
ce
ll
co
u
n
ti
n
g
,
co
m
p
u
ter
-
as
s
is
ted
ce
l
l
co
u
n
ti
n
g
m
et
h
o
d
s
ar
e
s
t
ill
b
ei
n
g
d
ev
elo
p
ed
to
im
p
r
o
v
e
t
h
e
co
u
n
ti
n
g
ac
c
u
r
ac
y
a
n
d
to
m
atc
h
w
it
h
n
e
w
ap
p
licatio
n
s
.
Fu
r
t
h
e
r
m
o
r
e,
th
er
e
is
f
e
w
au
to
m
ated
co
u
n
ti
n
g
s
o
f
t
w
ar
e
f
o
r
tr
y
p
an
b
lu
e
s
tai
n
ed
ce
lls
i
n
b
io
m
ed
ical
r
esear
c
h
.
I
n
th
i
s
p
ap
er
,
w
e
d
ev
elo
p
ed
an
au
to
m
ated
co
u
n
t
in
g
ap
p
r
o
a
ch
f
o
r
tr
y
p
an
b
lu
e
-
s
tai
n
ed
ce
lls
w
h
ic
h
i
s
b
ased
o
n
s
i
m
p
le
d
ig
ital
i
m
ag
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
in
c
lu
d
in
g
i
m
ag
e
n
o
is
e
r
ed
u
ctio
n
,
i
m
ag
e
e
n
h
a
n
ce
m
e
n
t,
i
m
a
g
e
s
e
g
m
en
ta
tio
n
a
n
d
i
m
ag
e
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
s
.
T
o
ev
alu
ate
th
e
e
f
f
ec
ti
v
en
e
s
s
o
f
o
u
r
ap
p
r
o
ac
h
,
b
o
th
liv
e
a
n
d
d
ea
d
ce
lls
w
er
e
q
u
a
n
t
if
ied
u
s
i
n
g
t
h
i
s
p
r
o
p
o
s
ed
m
eth
o
d
an
d
co
m
p
ar
ed
w
it
h
m
an
u
al
co
u
n
ti
n
g
b
y
t
h
r
ee
w
ell
-
e
x
p
er
ien
ce
d
co
u
n
ter
s
an
d
I
m
a
g
eJ
,
o
p
en
s
o
u
r
ce
s
o
f
t
w
ar
e.
2.
RE
S
E
ARCH
M
E
T
H
O
D
2
.
1
.
Sa
m
p
le
prepa
ra
t
io
n a
nd
i
m
a
g
e
a
cqui
s
it
io
n
A
h
u
m
a
n
b
r
ea
s
t
ca
n
ce
r
ce
ll
lin
e
(
MD
A
-
MB
-
231
)
p
u
r
ch
ased
f
r
o
m
t
h
e
Am
er
ica
n
T
y
p
e
C
u
lt
u
r
e
C
o
llectio
n
(
A
T
C
C
,
C
a
n
ad
a
)
w
a
s
u
s
ed
as
an
e
x
a
m
p
le
i
n
t
h
is
s
t
u
d
y
.
An
o
v
er
v
ie
w
o
f
t
h
e
s
t
u
d
y
p
r
o
ce
d
u
r
e
i
s
s
h
o
w
n
i
n
F
ig
u
r
e
1
.
T
h
e
s
a
m
p
l
e
p
r
ep
ar
atio
n
g
en
er
all
y
f
o
llo
wed
th
e
p
r
o
ce
d
u
r
e
o
f
P
ic
ci
n
i
n
i
et
al
.
[
14
]
.
I
n
b
r
ief
,
th
e
ce
lls
w
er
e
d
etac
h
ed
f
r
o
m
th
e
f
las
k
b
y
s
h
o
r
t
ex
p
o
s
u
r
e
to
tr
y
p
s
in
/
E
DT
A
,
w
as
h
ed
in
t
h
e
cu
lt
u
r
e
m
ed
ia
b
y
ce
n
tr
if
u
g
atio
n
a
n
d
r
e
-
s
u
s
p
en
d
ed
in
5
m
L
o
f
f
r
es
h
m
ed
i
u
m
.
Af
ter
tr
y
p
s
in
iza
tio
n
,
th
e
ce
lls
w
er
e
s
tain
ed
w
ith
tr
y
p
an
b
lu
e
s
o
l
u
tio
n
an
d
th
e
n
2
0
µL
o
f
th
i
s
m
i
x
t
u
r
e
w
as p
la
ce
d
in
a
h
e
m
o
c
y
to
m
e
ter
co
u
n
t
in
g
c
h
a
m
b
er
.
Fig
u
r
e
1
.
T
r
y
p
an
b
lu
e
-
s
tai
n
ed
MD
A
-
MB
-
2
3
1
ce
lls
in
t
h
e
h
e
m
o
c
y
to
m
eter
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.
9
,
No
.
4
,
A
u
g
u
s
t
201
9
:
2
4
6
0
-
2468
2462
I
m
ag
e
s
o
f
th
e
s
tain
ed
ce
ll
s
w
e
r
e
o
b
tain
ed
b
y
an
in
v
er
ted
Ol
y
m
p
u
s
I
X5
1
m
icr
o
s
co
p
e
eq
u
ip
p
ed
w
i
th
a
d
ig
ital
Ol
y
m
p
u
s
DP
7
2
ca
m
er
a
w
i
th
2
/
3
-
in
c
h
C
C
D
.
T
h
e
i
m
ag
e
s
w
er
e
ac
q
u
ir
ed
in
t
h
e
b
r
ig
h
t
f
ield
b
y
u
s
in
g
Ol
y
m
p
u
s
UP
L
an
F
L
N
1
0
x
0
.
1
3
as
s
tan
d
ar
d
o
b
j
ec
tiv
e
len
s
.
A
n
e
x
a
m
p
le
o
f
d
ig
ital
tr
y
p
an
b
lu
e
-
s
tai
n
ed
ce
ll
i
m
a
g
es
is
s
h
o
w
n
i
n
Fi
g
u
r
e
2
.
T
h
e
i
m
ag
e
s
w
er
e
cr
o
p
p
e
d
t
o
a
1
6
-
s
q
u
ar
e
g
r
id
an
d
th
e
n
i
m
ag
e
p
r
o
ce
s
s
i
n
g
an
al
y
s
is
w
as p
er
f
o
r
m
ed
as s
h
o
w
n
i
n
th
e
ce
ll c
o
u
n
ti
n
g
ap
p
r
o
a
ch
f
lo
w
c
h
ar
t a
s
p
r
esen
ted
in
F
ig
u
r
e
3
.
Fig
u
r
e
2
.
An
e
x
a
m
p
le
o
f
an
o
r
ig
i
n
al
tr
y
p
a
n
b
lu
e
–
s
tai
n
ed
i
m
a
g
e
Fig
u
r
e
3
.
Ov
er
v
ie
w
o
f
th
e
i
m
a
g
e
p
r
o
ce
s
s
in
g
f
o
r
liv
e
an
d
d
ea
d
ce
lls
co
u
n
ti
n
g
2
.
2
.
I
m
a
g
e
f
ilte
ring
I
n
o
u
r
s
tu
d
y
,
t
h
er
e
ar
e
p
iles
o
f
d
eb
r
is
(
d
ar
k
s
p
o
ts
)
in
tr
y
p
a
n
b
lu
e
-
s
tain
ed
m
icr
o
s
co
p
ic
i
m
a
g
es
f
r
o
m
th
e
h
e
m
o
c
y
to
m
eter
w
h
ich
ca
n
ca
u
s
e
ce
ll
ar
ti
f
ac
t
s
as
s
h
o
w
n
i
n
Fi
g
u
r
e
2
.
W
e
ap
p
lied
a
g
u
id
ed
i
m
a
g
e
f
ilter
t
h
at
s
p
atiall
y
d
is
tr
ib
u
ted
th
e
f
ilter
i
n
g
s
tr
e
n
g
th
s
w
ith
lo
w
-
le
v
el
f
ea
tu
r
es
to
th
e
i
m
a
g
e
to
s
m
o
o
th
an
d
r
e
m
o
v
e
th
e
s
m
al
l
d
eb
r
is
f
r
o
m
b
ac
k
g
r
o
u
n
d
in
cl
u
d
in
g
m
ai
n
tai
n
in
g
t
h
e
ed
g
e
f
ea
t
u
r
e
s
o
f
i
m
a
g
e
a
n
d
in
tr
o
d
u
ci
n
g
less
ar
tif
ac
ts
[
2
3
,
2
4
]
.
T
h
e
f
ilter
in
g
p
r
o
ce
s
s
n
ee
d
s
co
n
s
tr
ain
t
s
f
r
o
m
t
h
e
in
p
u
t
p
to
d
eter
m
i
n
e
th
e
lin
ea
r
co
ef
f
icien
ts
(
a
k
,
b
k
)
.
T
h
e
f
ilter
in
g
o
u
tp
u
t
q
is
a
lin
ea
r
tr
an
s
f
o
r
m
o
f
t
h
e
g
u
id
an
ce
I
in
a
w
i
n
d
o
w
k
ce
n
ter
ed
at
th
e
p
ix
el
k
s
in
ce
t
h
e
i
n
p
u
t p
n
ee
d
s
to
s
u
b
t
r
ac
t so
m
e
u
n
w
a
n
ted
co
m
p
o
n
e
n
ts
n
s
u
ch
a
s
n
o
is
e
/
tex
tu
r
es a
s
f
o
llo
w
s
:
q
i
=
a
k
I
i
+
b
k
,
i
k
(
1
)
q
i
=
p
i
-
n
i
(
2
)
Fu
r
t
h
er
m
o
r
e,
th
e
n
ei
g
h
b
o
r
h
o
o
d
s
ize
ar
o
u
n
d
ea
ch
p
i
x
el
as
a
s
ca
lar
o
r
t
w
o
-
e
le
m
e
n
t
v
ec
to
r
,
[
M,
N
]
w
as
30
to
r
e
m
o
v
e
s
m
all
d
eb
r
is
in
t
h
e
b
ac
k
g
r
o
u
n
d
.
2
.
3
.
Co
lo
r
s
pa
ce
a
nd
g
ra
y
s
c
a
le
co
nv
er
s
io
n
I
n
o
u
r
s
t
u
d
y
,
w
e
co
n
v
er
ted
a
co
lo
r
s
p
ac
e
o
f
t
h
e
tr
y
p
a
n
b
l
u
e
s
tai
n
ed
i
m
ag
e
s
w
h
ic
h
w
as
o
r
ig
i
n
all
y
R
GB
i
m
a
g
es
b
y
ap
p
l
y
i
n
g
H
S
V
(
Hu
e
Sat
u
r
atio
n
a
n
d
Valu
e
)
co
lo
r
s
p
ac
e
.
T
h
e
HSV
co
lo
r
s
p
ac
e
is
q
u
ite
s
i
m
ilar
to
th
e
w
a
y
i
n
w
h
ic
h
h
u
m
a
n
s
p
er
ce
iv
e
co
lo
r
an
d
m
o
r
e
s
u
ita
b
le
f
o
r
i
m
a
g
e
s
eg
m
e
n
tatio
n
a
n
d
an
al
y
s
is
t
h
a
n
t
h
e
R
GB
m
o
d
el
.
T
h
e
HSV
co
n
v
er
ted
im
a
g
es
w
er
e
th
e
n
u
s
ed
to
p
er
f
o
r
m
liv
e
ce
ll
s
s
eg
m
e
n
t
atio
n
.
Fu
r
t
h
er
m
o
r
e,
th
e
o
r
ig
i
n
al
R
GB
i
m
a
g
es
w
er
e
also
co
n
v
er
ted
to
g
r
a
y
s
ca
le
f
o
r
d
ea
d
ce
lls
d
etec
tio
n
.
2
.
4
.
I
m
a
g
e
s
eg
m
ent
a
t
io
n
T
h
e
s
eg
m
en
ta
tio
n
s
tep
is
v
er
y
cr
u
cial
b
ec
au
s
e
th
e
ac
c
u
r
a
c
y
o
f
t
h
e
s
u
b
s
eq
u
en
t
p
r
o
ce
s
s
es
m
ai
n
l
y
d
ep
en
d
s
o
n
th
e
co
r
r
ec
t
s
eg
m
e
n
tatio
n
.
P
r
io
r
t
o
im
a
g
e
s
e
g
m
e
n
tatio
n
,
t
h
e
b
r
ig
h
tn
e
s
s
o
f
a
HSV
co
n
v
er
ted
i
m
ag
e
is
ad
j
u
s
ted
f
o
r
g
etti
n
g
t
h
e
b
etter
co
n
tr
ast
.
Ou
r
ap
p
r
o
ac
h
u
til
ized
Ots
u
’
s
th
r
es
h
o
ld
in
g
m
et
h
o
d
to
ex
tr
ac
t
f
o
r
eg
r
o
u
n
d
(
liv
e
ce
lls
)
f
r
o
m
t
h
e
b
ac
k
g
r
o
u
n
d
an
d
to
tu
r
n
th
e
im
a
g
e
to
b
lack
an
d
w
h
ite
[
25
]
.
As
o
u
r
tr
y
p
an
b
lu
e
-
s
tai
n
ed
m
icr
o
s
co
p
ic
i
m
a
g
es
s
till
co
n
tain
ed
co
u
n
ter
f
eit
s
t
r
u
ct
u
r
es
i
n
t
h
e
n
u
clei,
h
o
wev
er
,
w
h
ic
h
ca
u
s
ed
d
if
f
ic
u
lt
y
f
o
r
ex
tr
ac
tio
n
a
n
d
s
eg
m
en
tatio
n
.
T
o
elim
i
n
ate
th
i
s
d
r
a
w
b
ac
k
,
t
w
o
o
p
er
atio
n
s
b
ased
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
Live
a
n
d
d
e
a
d
ce
lls
co
u
n
tin
g
f
r
o
m
micro
s
co
p
ic
tr
yp
a
n
b
lu
e
s
ta
in
in
g
ima
g
es u
s
in
g
…
(
S
u
Mo
n
A
u
n
g
)
2463
m
o
r
p
h
o
lo
g
ical
r
ec
o
n
s
tr
u
ctio
n
w
er
e
u
s
ed
:
o
p
en
in
g
a
n
d
d
ilati
o
n
.
T
h
e
f
ir
s
t
o
p
er
atio
n
r
e
m
o
v
es
th
e
d
i
s
co
n
n
ec
ted
b
r
ig
h
t
o
b
j
ec
ts
th
at
ar
e
s
m
a
ll
er
th
an
th
e
s
tr
u
ct
u
r
i
n
g
e
le
m
e
n
t
[
26
]
.
Si
m
ilar
l
y
,
t
h
e
s
ec
o
n
d
o
n
e
r
e
m
o
v
es
th
e
d
is
co
n
n
ec
ted
d
ar
k
o
b
j
ec
ts
s
m
a
ller
th
an
t
h
e
s
tr
u
ct
u
r
in
g
ele
m
e
n
t
.
A
d
is
k
-
s
h
ap
ed
s
tr
u
ctu
r
i
n
g
ele
m
e
n
t
w
it
h
r
ad
iu
s
“
n
”
w
as
ass
ig
n
ed
i
n
t
h
e
al
g
o
r
ith
m
.
T
h
e
am
o
u
n
t
o
f
d
etail
p
r
esen
ted
i
n
t
h
e
i
m
a
g
e
d
ep
en
d
s
o
n
t
h
e
s
ize
o
f
t
h
e
s
tr
u
ct
u
r
in
g
ele
m
e
n
t
w
it
h
r
ad
iu
s
“
n
”.
Fu
r
th
er
m
o
r
e,
w
e
ap
p
lied
th
e
ef
f
ec
tiv
e
th
r
e
s
h
o
ld
v
alu
e
f
r
o
m
th
e
h
is
to
g
r
a
m
o
f
a
g
r
a
y
s
ca
le
i
m
ag
e
to
o
b
tain
o
n
l
y
d
ea
d
ce
lls
in
t
h
e
b
lack
an
d
w
h
ite
i
m
a
g
e
.
2
.
5
.
Ce
ll c
o
un
t
ing
T
h
e
p
r
o
ce
s
s
o
f
co
u
n
tin
g
t
h
e
ce
lls
w
as
ac
h
iev
ed
b
y
ap
p
l
y
i
n
g
t
h
e
lab
eli
n
g
tec
h
n
iq
u
e
to
th
e
b
in
a
r
y
i
m
a
g
es
a
f
ter
th
r
es
h
o
ld
in
g
to
d
is
tin
g
u
is
h
o
b
j
ec
ts
f
r
o
m
th
e
b
ac
k
g
r
o
u
n
d
an
d
th
e
n
w
e
m
ea
s
u
r
ed
th
e
g
eo
m
etr
i
c
p
r
o
p
er
ties
u
s
in
g
a
ce
n
tr
o
id
an
d
a
b
o
u
n
d
ar
y
t
o
s
elec
t
liv
e
a
n
d
d
ea
d
ce
lls
f
r
o
m
lab
eled
r
eg
io
n
s
.
Fu
r
t
h
er
m
o
r
e,
t
h
e
co
u
n
ti
n
g
r
es
u
lts
b
y
o
u
r
ap
p
r
o
ac
h
w
er
e
co
m
p
ar
ed
to
th
e
m
an
u
al
co
u
n
ti
n
g
b
y
t
h
r
ee
e
x
p
er
ts
a
s
w
ell
as
co
m
p
ar
i
n
g
to
au
to
m
atic
ce
ll
co
u
n
tin
g
w
it
h
I
m
ag
eJ
u
s
in
g
C
e
llC
o
u
n
tin
g
Ma
cr
o
2
-
v1
.
01
.
ij
m
(
o
p
en
-
s
o
u
r
ce
s
o
f
t
w
ar
e
).
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
test
in
g
w
a
s
ca
r
r
ied
o
u
t
u
s
in
g
th
ir
t
y
s
i
x
tr
y
p
a
n
b
lu
e
-
s
ta
in
ed
m
icr
o
s
co
p
ic
i
m
a
g
es.
T
h
e
d
eb
r
is
in
th
e
i
m
a
g
e
s
w
a
s
r
e
m
o
v
ed
a
f
ter
ap
p
ly
i
n
g
a
n
i
m
a
g
e
-
g
u
id
ed
f
il
ter
as
s
h
o
w
n
i
n
Fi
g
u
r
e
4
.
As
w
e
p
er
f
o
r
m
ed
co
lo
r
s
p
ac
e
co
n
v
er
s
io
n
,
t
h
e
i
m
ag
e
s
b
ased
o
n
HSV
c
h
an
n
el
s
ar
e
s
h
o
w
n
i
n
F
ig
u
r
e
5
.
I
t
ca
n
b
e
s
ee
n
t
h
at
t
h
e
i
m
a
g
e
w
it
h
t
h
e
s
atu
r
atio
n
ch
a
n
n
el
as
s
h
o
w
n
i
n
Fig
u
r
e
5
b
g
av
e
a
b
etter
co
n
tr
ast
o
f
liv
e
ce
lls
as
co
m
p
ar
ed
to
o
th
er
ch
an
n
el
s
.
T
h
en
af
ter
b
r
ig
h
t
n
e
s
s
ad
j
u
s
t
m
en
t,
t
h
e
li
v
e
ce
lls
b
ec
a
m
e
clea
r
l
y
e
x
tr
ac
ted
f
r
o
m
th
e
b
ac
k
g
r
o
u
n
d
as
s
h
o
w
n
in
Fi
g
u
r
e
6
.
A
s
w
e
u
s
ed
Ots
u
’
s
t
h
r
es
h
o
ld
in
g
to
s
e
g
m
en
t
th
e
liv
e
ce
l
ls
f
r
o
m
t
h
e
b
ac
k
g
r
o
u
n
d
an
d
th
e
n
u
cle
i
o
f
li
v
e
ce
lls
w
er
e
o
p
en
e
d
an
d
d
ilated
af
ter
th
e
th
r
es
h
o
l
d
in
g
,
t
h
e
r
esu
l
t
o
f
s
e
g
m
e
n
tat
io
n
s
t
ep
f
o
r
liv
e
ce
ll
is
d
e
m
o
n
s
tr
ated
in
Fig
u
r
e
7
a.
T
h
e
im
a
g
e
s
e
g
m
e
n
tatio
n
o
f
d
ea
d
ce
lls
af
ter
u
s
i
n
g
t
h
e
h
i
s
to
g
r
a
m
th
r
es
h
o
ld
in
g
is
p
r
esen
ted
in
Fi
g
u
r
e
7
b
.
Af
ter
th
e
i
m
a
g
e
s
eg
m
e
n
tatio
n
,
t
h
e
i
m
ag
e
w
as
p
r
o
ce
s
s
ed
w
it
h
t
h
e
co
u
n
ti
n
g
al
g
o
r
ith
m
to
id
en
tify
a
n
d
co
u
n
t
b
o
th
liv
e
an
d
d
ea
d
ce
lls
.
T
h
e
f
in
al
i
m
a
g
es
s
h
o
w
in
g
th
e
li
v
e
an
d
d
ea
d
ce
lls
id
en
tific
atio
n
ar
e
r
esp
ec
tiv
el
y
p
r
ese
n
ted
in
F
ig
u
r
e
8
an
d
Fi
g
u
r
e
9.
Fig
u
r
e
4
.
E
x
a
m
p
les o
f
(
a
)
o
r
ig
in
al
i
m
ag
e
a
n
d
(
b
)
i
m
a
g
e
a
f
ter
g
u
id
ed
i
m
a
g
e
f
ilter
p
r
o
ce
s
s
Fig
u
r
e
5
.
I
m
a
g
es a
f
ter
HSV
co
lo
r
s
p
ac
e
co
n
v
er
s
io
n
:
(
a
)
Hu
e
c
h
an
n
el
i
m
a
g
e,
(
b
)
Sat
u
r
atio
n
c
h
an
n
el
i
m
a
g
e
an
d
(
c
)
Valu
e
c
h
an
n
el
i
m
a
g
e
Fig
u
r
e
6
.
Satu
r
atio
n
c
h
an
n
el
im
a
g
e
af
ter
b
r
ig
h
t
n
es
s
ad
j
u
s
tm
en
t
s
h
o
w
i
n
g
b
etter
co
n
tr
as
t o
f
li
v
e
ce
lls
f
r
o
m
th
e
b
ac
k
g
r
o
u
n
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t
201
9
:
2
4
6
0
-
2468
2464
T
h
e
liv
e
ce
ll
s
ar
e
m
ar
k
ed
with
y
ello
w
cir
cle
s
w
h
ile
t
h
e
d
ea
d
ce
lls
ar
e
m
ar
k
ed
as
b
l
u
e
cir
cles
.
As
s
h
o
w
n
in
Fig
u
r
e
8
,
it
w
as
n
o
ticed
th
at
s
o
m
e
liv
e
ce
lls
co
u
ld
n
o
t
b
e
d
etec
ted
an
d
co
u
n
t
ed
d
u
e
to
th
eir
n
o
n
-
d
is
tin
ct
iv
e
n
u
cle
i
.
Fig
u
r
e
1
0
s
h
o
w
s
t
h
e
p
lo
t
o
f
th
e
n
u
m
b
er
o
f
liv
e
an
d
d
ea
d
ce
lls
co
u
n
t
ed
b
y
o
u
r
ap
p
r
o
ac
h
ag
ain
s
t
t
h
e
a
v
er
ag
ed
r
es
u
lt
s
f
r
o
m
m
a
n
u
al
co
u
n
ti
n
g
.
Ou
r
ap
p
r
o
ac
h
p
r
o
v
id
ed
a
v
er
y
s
i
m
i
lar
co
u
n
ti
n
g
r
es
u
lt
o
f
liv
e
ce
lls
to
th
e
e
x
p
er
ts
’
co
u
n
ti
n
g
r
es
u
lt
w
it
h
a
h
i
g
h
co
r
r
elatio
n
co
ef
f
icie
n
t
(
r
=
0
.
99
)
w
h
er
ea
s
a
co
r
r
el
atio
n
co
ef
f
icie
n
t i
n
ca
s
e
o
f
t
h
e
d
ea
d
ce
lls
co
u
n
ti
n
g
i
s
0
.
74
.
Fig
u
r
e
7
.
I
m
a
g
e
a
f
ter
ap
p
ly
in
g
Ots
u
’
s
m
et
h
o
d
s
h
o
w
i
n
g
a
b
lack
an
d
w
h
ite
i
m
ag
e
w
i
th
(
a
)
liv
e
ce
ll
s
an
d
(
b
)
d
ea
d
ce
lls
Fig
u
r
e
8
.
E
x
a
m
p
le
o
f
i
m
a
g
e
s
h
o
w
in
g
li
v
e
ce
lls
d
etec
tio
n
m
a
r
k
ed
w
it
h
y
ello
w
cir
cle
Fig
u
r
e
9
.
E
x
a
m
p
le
o
f
i
m
ag
e
s
h
o
w
in
g
d
ea
d
ce
lls
d
etec
tio
n
m
ar
k
ed
w
it
h
b
lu
e
cir
cle
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
Live
a
n
d
d
e
a
d
ce
lls
co
u
n
tin
g
f
r
o
m
micro
s
co
p
ic
tr
yp
a
n
b
lu
e
s
ta
in
in
g
ima
g
es u
s
in
g
…
(
S
u
Mo
n
A
u
n
g
)
2465
Fig
u
r
e
1
0
.
C
o
r
r
elatio
n
p
lo
ts
b
et
w
ee
n
t
h
e
co
u
n
tin
g
r
es
u
lt
s
b
y
t
h
e
n
e
w
ap
p
r
o
ac
h
an
d
ex
p
er
ts
f
o
r
(
a
)
liv
e
ce
ll
s
an
d
(
b
)
d
ea
d
ce
lls
I
n
co
m
p
ar
is
o
n
w
i
th
th
e
e
x
p
e
r
ts
,
th
e
ac
c
u
r
ac
y
p
er
ce
n
ta
g
es
o
f
ce
ll
co
u
n
ti
n
g
f
r
o
m
3
6
i
m
ag
es
w
er
e
d
eter
m
in
ed
.
W
e
o
b
tain
ed
8
3
±
6
%
an
d
6
3
±
1
0
%
f
o
r
th
e
a
v
er
ag
e
ac
cu
r
ac
y
o
f
li
v
e
ce
ll
co
u
n
ti
n
g
a
n
d
d
ea
d
ce
ll
co
u
n
ti
n
g
r
esp
ec
tiv
el
y
.
W
e
also
ca
lcu
lated
th
e
av
er
ag
e
ti
m
e
co
n
s
u
m
p
tio
n
p
er
im
a
g
e
f
r
o
m
ea
ch
ex
p
er
t
an
d
o
u
r
ap
p
r
o
ac
h
as
illu
s
tr
ated
i
n
Fi
g
u
r
e
11
.
Ou
r
ap
p
r
o
ac
h
co
n
s
u
m
ed
s
h
o
r
ter
ti
m
e
t
h
a
n
m
a
n
u
al
c
o
u
n
ti
n
g
b
y
e
x
p
er
ts
.
I
t
is
clea
r
ly
n
o
ticed
th
a
t
th
er
e
is
a
v
ar
iatio
n
in
co
u
n
t
in
g
t
i
m
e
a
m
o
n
g
t
h
e
ex
p
er
ts
.
Fu
r
t
h
er
m
o
r
e,
Fig
u
r
e
1
2
d
em
o
n
s
tr
ate
s
th
e
a
v
er
ag
e
n
u
m
b
er
o
f
li
v
e
a
n
d
to
tal
ce
lls
f
r
o
m
m
a
n
u
al,
I
m
a
g
eJ
an
d
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
.
I
t
s
h
o
w
s
t
h
at
o
u
r
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
h
ad
th
e
av
er
ag
e
n
u
m
b
er
o
f
li
v
e
ce
lls
s
li
g
h
tl
y
h
ig
h
er
t
h
an
m
a
n
u
al
co
u
n
ti
n
g
an
d
it
w
as
b
etter
th
a
n
th
e
I
m
ag
eJ
u
s
i
n
g
C
ellC
o
u
n
t
in
g
Ma
cr
o
2
-
v1
.
01
.
ij
m
.
I
n
ad
d
i
tio
n
,
o
u
r
ap
p
r
o
ac
h
co
u
ld
d
etec
t th
e
d
ea
d
ce
lls
w
h
er
ea
s
I
m
ag
eJ
w
it
h
C
ell
C
o
u
n
ti
n
g
Ma
cr
o
2
-
p
l
u
g
in
co
u
ld
n
o
t d
o
th
at
.
W
e
s
h
o
w
ed
t
h
at
th
e
g
u
id
ed
i
m
a
g
e
f
ilter
i
n
g
p
r
o
v
id
ed
s
m
o
o
th
ed
g
e
m
ai
n
te
n
a
n
ce
to
o
u
r
o
b
j
ec
ts
,
lead
in
g
to
a
b
etter
q
u
alit
y
in
p
u
t
i
m
a
g
e
f
o
r
o
u
r
ap
p
r
o
ac
h
[
2
4
]
.
A
s
o
u
r
r
esu
lt
s
,
th
e
ac
cu
r
ac
y
o
f
li
v
e
ce
lls
co
u
n
ti
n
g
,
f
o
r
ea
c
h
i
m
a
g
e,
w
a
s
v
er
y
h
i
g
h
(
>8
3
%)
d
u
e
to
th
e
g
o
o
d
co
n
tr
ast
b
et
wee
n
f
o
r
eg
r
o
u
n
d
a
n
d
b
ac
k
g
r
o
u
n
d
a
f
ter
p
r
ep
r
o
ce
s
s
in
g
w
it
h
t
h
e
i
m
a
g
e
n
o
is
e
r
ed
u
ctio
n
u
s
i
n
g
a
g
u
id
ed
i
m
ag
e
f
i
lter
an
d
a
s
at
u
r
ated
ch
an
n
el
[
2
7
]
.
W
e
ex
p
er
ien
ce
d
a
s
im
ilar
h
i
g
h
ac
cu
r
ac
y
o
f
li
v
e
ce
lls
co
u
n
tin
g
u
s
i
n
g
s
i
m
ila
r
s
a
m
p
le
i
m
a
g
es
in
o
u
r
p
r
ev
io
u
s
w
o
r
k
u
s
i
n
g
a
K
-
m
ea
n
c
lu
s
ter
in
g
tec
h
n
iq
u
e
[
2
8
]
.
Ho
w
e
v
er
,
th
i
s
n
e
w
s
i
m
p
le
m
et
h
o
d
p
r
o
v
id
ed
a
h
ig
h
er
ac
c
u
r
ac
y
.
W
it
h
th
is
ap
p
r
o
ac
h
,
th
e
b
r
ig
h
t
n
es
s
o
f
liv
e
ce
ll
s
is
c
lear
l
y
d
i
f
f
er
en
t
f
r
o
m
t
h
e
i
m
ag
e
b
ac
k
g
r
o
u
n
d
,
w
h
ic
h
i
s
a
d
is
ti
n
ct
ad
v
a
n
ta
g
e
f
o
r
i
m
a
g
e
t
h
r
esh
o
ld
in
g
f
o
r
liv
e
ce
lls
d
etec
t
io
n
.
P
iccin
i
n
i
an
d
co
lleag
u
e
s
[
1
4
]
p
r
esen
ted
a
h
ig
h
ac
cu
r
ac
y
o
f
li
v
e
ce
ll
s
co
u
n
ti
n
g
u
s
i
n
g
a
n
a
u
to
m
a
ted
i
m
a
g
e
m
o
s
aic
in
g
tech
n
iq
u
e
f
o
r
A
5
4
9
an
d
KKP
ce
ll
li
n
es.
T
h
e
h
i
g
h
ac
c
u
r
ac
y
o
f
li
v
e
ce
ll
co
u
n
ti
n
g
in
b
o
th
t
h
eir
r
es
u
lts
an
d
o
u
r
s
p
ar
ticu
lar
l
y
r
elate
s
to
th
e
clea
r
l
y
d
is
tin
g
u
is
h
ab
le
s
h
ap
e
o
f
liv
e
ce
lls
an
d
a
g
o
o
d
b
a
ck
g
r
o
u
n
d
co
n
tr
ast.
Ho
w
e
v
er
,
s
o
m
e
i
m
a
g
es
w
e
c
o
u
ld
n
o
t
co
m
p
letel
y
d
etec
t
all
liv
e
ce
lls
b
ec
au
s
e
th
er
e
w
as
n
eit
h
er
s
tr
u
ct
u
r
e
in
n
u
cle
u
s
n
o
r
s
m
aller
s
tr
u
ctu
r
e
th
an
o
u
r
v
al
u
e
s
o
f
s
tr
u
ct
u
r
in
g
elem
e
n
t
’
s
r
ad
iu
s
in
n
u
cle
u
s
.
T
h
is
ca
u
s
ed
s
o
m
e
i
m
a
g
es
g
o
t
a
n
ac
c
u
r
ac
y
les
s
th
a
n
9
0
%.
Fu
r
t
h
er
m
o
r
e,
o
u
r
ap
p
r
o
ac
h
d
id
n
o
t
r
eq
u
ir
e
m
an
u
al
t
h
r
es
h
o
ld
in
g
ad
j
u
s
t
m
e
n
t th
er
e
f
o
r
e
it r
ed
u
ce
d
ti
m
e
co
n
s
u
m
i
n
g
.
Fig
u
r
e
1
1
.
T
im
e
co
n
s
u
m
p
tio
n
f
o
r
ce
ll c
o
u
n
ti
n
g
m
ea
s
u
r
ed
b
y
t
h
r
ee
ex
p
er
ts
a
n
d
o
u
r
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
Fig
u
r
e
1
2
.
A
p
lo
t o
f
t
h
e
a
v
er
ag
e
n
u
m
b
er
o
f
li
v
e,
d
ea
d
an
d
to
tal
ce
lls
co
u
n
ted
b
y
m
a
n
u
al
co
u
n
ti
n
g
,
I
m
ag
eJ
an
d
o
u
r
ap
p
r
o
ac
h
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.
9
,
No
.
4
,
A
u
g
u
s
t
201
9
:
2
4
6
0
-
2468
2466
Ou
r
ap
p
r
o
ac
h
p
r
o
v
id
ed
less
n
u
m
b
er
o
f
d
ea
d
ce
lls
co
m
p
a
r
ed
to
m
an
u
al
co
u
n
tin
g
b
y
t
h
e
ex
p
er
ts
.
T
h
is
m
ig
h
t
h
av
e
b
ee
n
ca
u
s
e
d
b
y
th
e
i
n
ef
f
ec
ti
v
e
n
es
s
o
f
d
ea
d
ce
ll
s
eg
m
e
n
tatio
n
.
I
t
s
h
o
u
ld
b
e
n
o
ted
th
at
s
eg
m
e
n
tatio
n
r
esu
lts
d
ep
en
d
o
n
t
h
e
q
u
al
it
y
o
f
p
r
ep
ar
atio
n
a
n
d
th
e
co
lo
r
in
g
o
f
tr
y
p
an
b
lu
e
-
s
tain
ed
m
icr
o
s
co
p
ic
i
m
a
g
es
.
Ov
er
s
tr
ai
n
in
g
a
n
d
p
o
o
r
d
ig
itizatio
n
ca
n
ad
v
er
s
el
y
a
f
f
ec
t
s
e
g
m
en
ta
tio
n
r
es
u
lt
s
[
29]
.
T
h
ese
q
u
an
d
ar
ies
in
f
r
eq
u
en
t
l
y
o
cc
u
r
an
d
ca
n
b
e
r
e
m
ed
ie
d
w
it
h
a
m
o
r
e
r
ig
o
r
o
u
s
q
u
alit
y
co
n
tr
o
l
d
u
r
in
g
t
h
e
s
a
m
p
le
p
r
ep
ar
atio
n
an
d
i
m
a
g
e
ac
q
u
i
s
itio
n
.
Mo
r
eo
v
er
,
d
ea
d
ce
lls
f
r
o
m
ap
o
p
to
s
is
p
r
esen
ted
in
f
r
ag
m
e
n
ts
ca
n
lead
to
o
v
er
co
u
n
ti
n
g
[
30
]
.
T
h
er
ef
o
r
e,
th
e
co
u
n
ti
n
g
o
f
d
ea
d
ce
lls
s
till
h
as
er
r
o
n
eo
u
s
r
es
u
lts
m
u
c
h
m
o
r
e
t
h
a
n
li
v
e
ce
ll
s
co
u
n
ti
n
g
.
Fo
r
ex
a
m
p
le,
t
h
e
a
p
p
r
o
ac
h
u
s
in
g
a
u
to
m
ated
i
m
a
g
e
m
o
s
aic
k
in
g
h
ad
f
a
ls
e
p
o
s
it
iv
e
r
es
u
lt
s
o
n
d
ea
d
ce
ll
co
u
n
ti
n
g
co
m
p
ar
ed
to
th
e
ex
p
er
ts
m
u
c
h
m
o
r
e
th
a
n
t
h
e
l
iv
e
ce
lls
co
u
n
t
in
g
[
14
]
.
I
t
r
e
m
ain
s
a
c
h
alle
n
g
e
to
i
m
p
r
o
v
e
t
h
e
ac
cu
r
ac
y
o
f
d
ea
d
ce
lls
co
u
n
t
in
g
b
y
i
m
p
r
o
v
in
g
eit
h
er
i
m
a
g
e
n
o
is
e
r
ed
u
ctio
n
o
r
i
m
a
g
e
s
eg
m
e
n
tatio
n
a
s
w
ell
as c
o
u
n
ti
n
g
lo
g
ic
f
o
r
f
r
a
g
m
en
ted
d
ea
d
ce
ll
.
C
o
m
p
ar
in
g
t
h
e
r
es
u
lt
s
o
f
ce
ll
co
u
n
tin
g
b
et
w
ee
n
o
u
r
ap
p
r
o
ac
h
an
d
I
m
a
g
eJ
w
ith
au
to
m
atic
ce
l
l
co
u
n
ti
n
g
p
lu
g
i
n
,
o
u
r
ap
p
r
o
ac
h
co
u
ld
g
i
v
e
t
h
e
n
u
m
b
er
o
f
b
o
t
h
li
v
e
ce
ll
s
an
d
d
ea
d
ce
lls
w
h
er
ea
s
I
m
a
g
eJ
co
u
ld
d
etec
t
o
n
l
y
li
v
e
ce
lls
.
T
h
is
in
d
icate
s
th
at
t
h
e
I
m
a
g
eJ
p
lu
g
i
n
f
o
r
au
to
m
atic
ce
ll
co
u
n
ti
n
g
d
o
es
n
o
t
s
er
v
e
o
u
r
tr
y
p
an
b
lu
e
s
tai
n
ed
i
m
a
g
es
a
n
d
r
eq
u
ir
e
m
en
ts
.
I
t
s
ee
m
s
I
m
ag
eJ
co
u
ld
au
to
m
atica
ll
y
co
u
n
t
ce
lls
w
it
h
g
o
o
d
co
n
tr
ast
b
et
w
ee
n
ce
ll
s
a
n
d
b
ac
k
g
r
o
u
n
d
t
h
er
ef
o
r
e
d
ea
d
ce
lls
in
o
u
r
i
m
ag
e
s
ar
e
q
u
ite
d
i
f
f
i
cu
lt
to
b
e
d
etec
ted
.
I
t
m
i
g
h
t
b
e
n
ec
ess
ar
y
to
d
o
an
i
m
ag
e
p
r
ep
r
o
ce
s
s
in
g
f
o
r
o
u
r
i
m
ag
e
s
b
ef
o
r
e
an
al
y
zi
n
g
w
i
th
I
m
a
g
eJ
.
On
t
h
e
ot
h
er
h
an
d
,
o
u
r
ap
p
r
o
ac
h
alr
ea
d
y
i
n
cl
u
d
ed
th
e
i
m
a
g
e
p
r
e
p
r
o
ce
s
s
in
g
s
u
c
h
as
n
o
is
e
f
ilt
er
in
g
an
d
co
n
tr
as
t
en
h
a
n
ce
m
en
t to
i
m
p
r
o
v
e
th
e
i
m
ag
e
q
u
alit
y
in
t
h
e
al
g
o
r
ith
m
.
T
h
is
s
tu
d
y
w
a
s
b
ased
o
n
o
n
l
y
3
6
tr
y
p
an
b
lu
e
-
s
tai
n
ed
i
m
a
g
es
f
r
o
m
o
n
e
ce
ll
lin
e
w
h
ich
co
u
l
d
lim
it
th
e
g
en
er
aliza
tio
n
o
f
t
h
e
r
es
u
lts
f
o
r
o
th
er
ce
ll
lin
es
.
Fu
r
th
er
m
o
r
e,
th
er
e
w
er
e
s
e
v
er
al
li
m
itati
o
n
s
w
h
ich
a
f
f
ec
ted
th
e
co
u
n
ti
n
g
ac
c
u
r
ac
y
.
Fo
r
ex
a
m
p
le,
w
e
a
s
s
u
m
ed
th
at
t
h
e
c
ell
d
ia
m
eter
s
i
n
all
i
m
ag
e
s
wer
e
ab
o
u
t
th
e
s
a
m
e
s
ize,
w
h
ile
i
n
f
ac
t
t
h
e
d
ea
d
ce
lls
in
o
u
r
s
t
u
d
y
h
ad
v
ar
io
u
s
d
ia
m
eter
s
,
esp
ec
iall
y
w
h
e
n
t
h
e
ce
lls
co
u
n
ted
b
y
o
u
r
ap
p
r
o
ac
h
w
as
g
r
ea
ter
t
h
a
n
t
h
e
r
esu
lt
s
co
u
n
ted
b
y
t
h
e
ex
p
er
t
s
.
T
h
e
q
u
alit
y
o
f
i
m
ag
e
also
a
f
f
ec
ts
o
u
r
co
u
n
ti
n
g
s
u
c
h
as
th
e
b
r
ig
h
t
n
es
s
o
f
th
e
i
m
a
g
e
b
ac
k
g
r
o
u
n
d
.
Fu
r
th
er
m
o
r
e,
lo
w
co
n
tr
ast
ca
n
i
n
f
l
u
en
ce
th
e
i
m
ag
e
s
eg
m
e
n
tatio
n
an
d
lead
to
lo
wer
ac
cu
r
ac
y
o
f
ce
ll
co
u
n
ti
n
g
.
As
o
u
r
tr
y
p
an
b
lu
e
-
s
ta
in
ed
m
icr
o
s
co
p
ic
i
m
ag
e
s
h
av
e
a
d
ar
k
b
ac
k
g
r
o
u
n
d
,
th
e
c
o
lo
r
o
f
th
e
d
ea
d
ce
lls
is
q
u
ite
s
i
m
ilar
to
th
e
b
ac
k
g
r
o
u
n
d
,
w
h
ich
r
eq
u
ir
es
s
e
v
er
al
tr
ials
f
o
r
d
e
ad
ce
lls
s
eg
m
e
n
tati
o
n
.
Mo
r
eo
v
er
,
w
e
ap
p
lied
a
m
ea
n
t
h
r
esh
o
ld
v
al
u
e
b
ased
o
n
3
6
im
a
g
e
s
f
o
r
d
ea
d
ce
lls
s
e
g
m
e
n
tatio
n
,
th
u
s
it
is
n
ec
es
s
ar
y
to
r
ec
alc
u
late
th
e
m
ea
n
t
h
r
esh
o
ld
v
al
u
e
i
f
t
h
e
n
u
m
b
er
o
f
i
m
a
g
es
o
r
i
m
a
g
e
b
ac
k
g
r
o
u
n
d
i
s
ch
a
n
g
ed
.
I
n
ad
d
itio
n
,
e
m
p
lo
y
in
g
a
lar
g
e
s
tr
u
ct
u
r
in
g
ele
m
e
n
t c
a
n
o
v
er
s
i
m
p
li
f
y
t
h
e
i
m
ag
e,
w
h
ile
u
s
in
g
to
o
s
m
al
l
a
s
tr
u
ctu
r
in
g
ele
m
e
n
t
d
o
es
n
o
t
al
w
a
y
s
p
r
o
d
u
ce
d
esira
b
le
r
esu
l
ts
as
m
a
n
y
o
f
th
e
s
u
b
s
tr
u
ct
u
r
es
w
it
h
i
n
th
e
lar
g
e
n
u
clei
r
e
m
ai
n
,
af
f
ec
ti
n
g
th
e
s
eg
m
e
n
tatio
n
p
er
f
o
r
m
an
ce
.
T
h
er
ef
o
r
e,
o
p
t
i
m
u
m
p
ar
am
eter
s
s
h
o
u
ld
b
e
d
eter
m
i
n
ed
s
u
c
h
as t
h
r
es
h
o
ld
v
al
u
e
an
d
r
ad
iu
s
o
f
s
tr
u
ct
u
r
i
n
g
ele
m
e
n
t
.
4.
CO
NCLU
SI
O
N
I
n
th
i
s
s
t
u
d
y
,
w
e
p
r
esen
t
a
co
m
p
u
ter
-
a
s
s
i
s
ted
ce
ll
co
u
n
ti
n
g
ap
p
r
o
ac
h
o
n
tr
y
p
an
b
lu
e
-
s
tai
n
ed
m
icr
o
s
co
p
ic
i
m
ag
e
s
o
f
a
b
r
ea
s
t
ca
n
ce
r
ce
ll
l
in
e.
T
h
e
r
es
u
lt
s
o
f
ce
ll
co
u
n
ti
n
g
f
r
o
m
th
e
tr
y
p
a
n
b
l
u
e
-
s
tai
n
e
d
m
icr
o
s
co
p
ic
i
m
a
g
es
u
s
i
n
g
o
u
r
ap
p
r
o
ac
h
ac
h
iev
ed
a
r
e
m
ar
k
ab
le
ac
cu
r
ac
y
co
m
p
ar
ed
to
th
r
ee
ex
p
er
ts
,
esp
ec
iall
y
i
n
co
u
n
t
in
g
th
e
n
u
m
b
er
o
f
li
v
e
ce
lls
.
Ou
r
s
i
m
p
le
m
et
h
o
d
co
u
ld
id
en
tify
o
v
er
lap
p
in
g
ce
lls
a
n
d
co
u
n
t
th
e
m
co
r
r
ec
tl
y
.
T
h
is
a
u
to
m
ate
d
co
u
n
tin
g
ap
p
r
o
ac
h
is
b
en
e
f
ic
ial
to
b
io
lo
g
is
ts
an
d
b
io
m
ed
ica
l r
esear
ch
er
s
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
e
au
t
h
o
r
s
w
o
u
ld
li
k
e
to
ac
k
n
o
w
led
g
e
t
h
e
T
h
aila
n
d
'
s
E
d
u
ca
tio
n
H
u
b
f
o
r
t
h
e
So
u
t
h
er
n
R
e
g
io
n
o
f
ASE
A
N
C
o
u
n
tr
ies
(
T
E
H
-
AC
)
s
ch
o
lar
s
h
ip
g
iv
e
n
to
M
s
.
Su
Mo
n
A
u
n
g
f
r
o
m
t
h
e
Gr
ad
u
a
te
Sch
o
o
l,
P
r
in
ce
o
f
So
n
g
k
la
U
n
i
v
er
s
it
y
.
W
e
w
o
u
l
d
lik
e
to
th
an
k
A
s
s
o
ciate
P
r
o
f
ess
o
r
P
o
r
n
ch
ai
P
h
u
k
p
attar
a
n
o
n
t
f
r
o
m
th
e
Fac
u
lt
y
o
f
E
n
g
i
n
ee
r
in
g
,
P
r
in
ce
o
f
So
n
g
k
la
U
n
iv
er
s
it
y
f
o
r
ad
v
ice
o
n
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
.
W
e
ap
p
r
ec
iated
o
u
r
tech
n
ica
l
d
is
cu
s
s
io
n
s
w
it
h
Ms
.
A
d
eli
n
e
Ver
el
an
d
Ms
.
P
am
i
n
a
B
er
n
o
u
,
in
ter
n
s
h
ip
s
t
u
d
en
t
s
f
r
o
m
T
elec
o
m
P
h
y
s
iq
u
e
Stra
s
b
o
u
r
g
,
Fra
n
ce
.
W
e
also
th
an
k
t
h
e
I
n
ter
n
at
io
n
al
Af
f
air
s
O
f
f
ice
o
f
t
h
e
Fac
u
lt
y
o
f
M
ed
icin
e,
P
r
in
ce
o
f
So
n
g
k
la
U
n
i
v
er
s
it
y
f
o
r
ed
itin
g
th
e
E
n
g
lis
h
o
f
t
h
e
m
an
u
s
cr
ip
t
.
RE
F
E
R
E
NC
E
S
[
1
]
J
.
Y
.
F
a
n
g
,
e
t
a
l
,
“
F
ro
m
c
o
m
p
e
ten
c
y
to
d
o
rm
a
n
c
y
:
a
3
D
m
o
d
e
l
t
o
st
u
d
y
c
a
n
c
e
r
c
e
ll
s
a
n
d
d
r
u
g
re
sp
o
n
siv
e
n
e
ss
,”
J
o
u
rn
a
l
o
f
tra
n
sla
t
io
n
a
l
me
d
icin
e
,
1
4
;
38
,
2
0
1
6
.
[
2
]
S
.
W
.
F
e
sik
,
“
P
ro
m
o
ti
n
g
a
p
o
p
t
o
sis
a
s
a
stra
te
g
y
f
o
r
c
a
n
c
e
r
d
r
u
g
d
isc
o
v
e
r
y
,”
Na
t
u
re
Rev
iews
Ca
n
c
e
r
,
5
(
1
1
)
;
876
-
8
8
5
,
2
0
0
5
.
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
Live
a
n
d
d
e
a
d
ce
lls
co
u
n
tin
g
f
r
o
m
micro
s
co
p
ic
tr
yp
a
n
b
lu
e
s
ta
in
in
g
ima
g
es u
s
in
g
…
(
S
u
Mo
n
A
u
n
g
)
2467
[
3
]
Y
.
Ko
n
d
o
,
“
T
h
e
ro
le
o
f
a
u
to
p
h
a
g
y
in
c
a
n
c
e
r
d
e
v
e
lo
p
m
e
n
t
a
n
d
re
s
p
o
n
se
to
th
e
ra
p
y
,”
Na
tu
re
Rev
ie
ws
Ca
n
c
e
r
,
5
(9
);
726
-
7
3
4
,
2
0
0
5
.
[
4
]
S
.
W
.
L
o
we
a
n
d
A
.
W
.
L
in
, “
A
p
o
p
to
sis
in
c
a
n
c
e
r
,”
Ca
rc
in
o
g
e
n
e
sis
.
2
1
(
3
);
4
8
5
-
4
9
5
,
2
0
0
0
.
[
5
]
A
.
E
.
Ca
rp
e
n
ter,
e
t
a
l
.
,
“
Ce
ll
P
r
o
f
il
e
r
:
ima
g
e
a
n
a
l
y
sis
so
f
t
w
a
re
f
o
r
id
e
n
ti
fy
in
g
a
n
d
q
u
a
n
t
ify
in
g
c
e
ll
p
h
e
n
o
ty
p
e
s
,”
Ge
n
o
me
Bi
o
l
o
g
y
,
7
(
1
0
),
R1
0
0
,
2
0
1
6
.
[
6
]
J
.
S
c
h
in
d
e
li
n
,
e
t
a
l
.
,
“
F
ij
i
:
a
n
o
p
e
n
-
so
u
rc
e
p
latf
o
rm
f
o
r
b
io
lo
g
ica
l
-
ima
g
e
a
n
a
l
y
sis
,”
Na
tu
re
M
e
th
o
d
s
,
9
(7
);
6
7
6
-
682
,
2
0
1
2
.
[
7
]
J
.
S
e
li
n
u
m
m
i,
e
t
a
l
.
,
“
S
o
f
tw
a
re
f
o
r
q
u
a
n
ti
f
ica
ti
o
n
o
f
lab
e
led
b
a
c
teria
f
ro
m
d
ig
it
a
l
m
icro
sc
o
p
e
im
a
g
e
s
b
y
a
u
to
m
a
ted
im
a
g
e
a
n
a
l
y
sis
,”
Bi
o
T
e
c
h
n
i
q
u
e
s
,
3
9
(
6
),
8
5
9
-
8
6
2
,
2
0
0
5
.
[
8
]
I
.
V
.
Grish
a
g
in
,
“
A
u
t
o
m
a
ti
c
c
e
ll
c
o
u
n
ti
n
g
w
it
h
Im
a
g
e
,
”
An
a
lytica
l
Bi
o
c
h
e
mistry
;
4
7
3
;
6
3
-
65
,
2
0
1
5
.
[
9
]
J
.
P
.
V
a
y
r
y
n
e
n
,
e
t
a
l.
,
“
A
n
im
p
ro
v
e
d
ima
g
e
a
n
a
l
y
sis
m
e
th
o
d
f
o
r
c
e
ll
c
o
u
n
ti
n
g
len
d
s
c
re
d
ib
i
li
ty
to
th
e
p
r
o
g
n
o
stic
sig
n
if
ica
n
c
e
o
f
T
c
e
ll
s in
c
o
lo
re
c
tal
c
a
n
c
e
r
,”
Vi
rc
h
o
ws Arc
h
iv
,
4
6
0
(
5
)
,
4
5
5
-
4
6
5
,
2
0
1
2
.
[
10
]
R
.
J
.
Blatt,
e
t
a
l.
,
“
A
u
to
m
a
t
e
d
q
u
a
n
ti
tativ
e
a
n
a
ly
si
s o
f
a
n
g
io
g
e
n
e
sis
in
th
e
ra
t
a
o
rta m
o
d
e
l
u
sin
g
Im
a
g
e
-
P
r
o
P
lu
s
4
.
1,
”
Co
mp
u
ter
M
e
th
o
d
s
a
n
d
Pro
g
ra
m
s in
Bi
o
me
d
icin
e
,
7
5
(1
)
,
75
-
79
,
2
0
0
4
.
[
11
]
P
.
J
.
Na
ra
y
a
n
,
e
t
a
l.
,
“
Hig
h
th
ro
u
g
h
p
u
t
q
u
a
n
ti
f
ica
ti
o
n
o
f
c
e
ll
s
w
it
h
c
o
m
p
lex
m
o
rp
h
o
lo
g
y
in
m
ix
e
d
c
u
l
tu
re
s
,”
J
o
u
rn
a
l
o
f
n
e
u
ro
sc
ien
c
e
me
th
o
d
s
,
1
6
4
(
2
)
,
339
-
3
4
9
,
2
0
0
7
.
[
12
]
D
.
S
u
i,
e
t
a
l
.
,
“
Brig
h
t
f
ield
m
icro
sc
o
p
ic
c
e
ll
s
c
o
u
n
ti
n
g
m
e
th
o
d
f
o
r
BEV
S
u
sin
g
n
o
n
li
n
e
a
r
c
o
n
v
e
rg
e
n
c
e
in
d
e
x
slid
in
g
b
a
n
d
f
il
ter
,”
Bi
o
me
d
ica
l
En
g
in
e
e
r
in
g
O
n
li
n
e
,
1
3
(1
)
,
1
4
7
,
2
0
1
4
.
[
13
]
S
.
Na
z
li
b
il
e
k
,
e
t
a
l
,
“
A
u
to
m
a
ti
c
s
e
g
m
e
n
tatio
n
,
c
o
u
n
ti
n
g
,
siz
e
d
e
ter
m
in
a
ti
o
n
a
n
d
c
las
sif
ica
ti
o
n
o
f
w
h
it
e
b
l
o
o
d
c
e
ll
s
,”
M
e
a
su
re
me
n
t
,
55
,
58
-
65
,
2
0
1
4
.
[
14
]
F
.
P
icc
in
i
n
i,
e
t
a
l
,
“
Im
p
ro
v
in
g
re
li
a
b
il
it
y
o
f
li
v
e
/
d
e
a
d
c
e
ll
c
o
u
n
ti
n
g
th
ro
u
g
h
a
u
t
o
m
a
ted
i
m
a
g
e
m
o
sa
ick
in
g
,”
Co
mp
u
ter
M
e
th
o
d
s
a
n
d
Pro
g
ra
m
s in
Bi
o
me
d
icin
e
,
1
1
7
(
3
)
,
4
4
8
-
463
,
2
0
1
4
.
[
15
]
A
.
M
o
u
e
lh
i,
e
t
a
l.
,
“
A
u
to
m
a
ti
c
ima
g
e
s
e
g
m
e
n
tatio
n
o
f
n
u
c
lea
r
sta
in
e
d
b
re
a
st
ti
ss
u
e
se
c
ti
o
n
s
u
si
n
g
c
o
lo
r
a
c
ti
v
e
c
o
n
to
u
r
m
o
d
e
l
a
n
d
a
n
im
p
ro
v
e
d
w
a
t
e
rsh
e
d
m
e
th
o
d
,”
Bi
o
me
d
ica
l
S
ig
n
a
l
Pro
c
e
ss
in
g
a
n
d
Co
n
tro
l
,
8
(5
),
4
2
1
-
436
,
2
0
1
4
.
[
16
]
Y
.
Zh
u
a
n
d
C
.
Hu
a
n
g
,
“
A
n
im
p
ro
v
e
d
m
e
d
ian
f
il
terin
g
a
lg
o
rit
h
m
fo
r
im
a
g
e
n
o
ise
re
d
u
c
ti
o
n
,”
Ph
y
sic
s
Pro
c
e
d
ia
,
25
,
609
-
6
1
2
,
2
0
1
2
.
[
17
]
T
.
S
o
n
i
a
n
d
N
.
Ra
th
o
r
,
“
Re
m
o
v
a
l
o
f
Hig
h
De
n
sit
y
I
m
p
u
lse
No
ise
u
sin
g
Ef
f
i
c
ien
t
M
e
d
ian
F
il
ter
f
o
r
Dig
it
a
l
I
m
a
g
e
,”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
Ap
p
l
ica
ti
o
n
s
,
1
1
5
(5
)
,
25
-
31
,
2
0
1
5
.
[
18
]
H
.
Zen
g
,
e
t
a
l
.
,
“
A
n
im
p
ro
v
e
d
a
lg
o
rit
h
m
f
o
r
im
p
u
lse
n
o
ise
b
y
m
e
d
ian
f
il
ter
,”
AA
S
RI
Pr
o
c
e
d
ia
,
1
,
68
-
73
,
2
0
1
2
.
[
19
]
C
.
S
u
n
,
e
t
a
l
.
,
“
A
n
e
ff
icie
n
t
m
e
th
o
d
f
o
r
sa
lt
-
a
n
d
-
p
e
p
p
e
r
n
o
ise
r
e
m
o
v
a
l
b
a
se
d
o
n
s
h
e
a
rlet
tran
sf
o
rm
a
n
d
n
o
ise
d
e
tec
ti
o
n
,”
AEU
-
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
tro
n
ics
a
n
d
Co
mm
u
n
ica
ti
o
n
s
,
6
9
(
1
2
)
,
1
8
2
3
-
1
8
3
2
,
2
0
1
5
.
[
20
]
A
.
K
.
S
a
m
a
n
tara
y
a
n
d
P
.
M
a
ll
ick
,
“
De
c
isio
n
Ba
se
d
A
d
a
p
ti
v
e
Ne
ig
h
b
o
r
h
o
o
d
M
e
d
ian
F
i
lt
e
r
,”
Pro
c
e
d
ia
C
o
mp
u
ter
S
c
ien
c
e
,
48
,
2
2
2
-
2
2
7
,
2
0
1
5
.
[
21
]
N
.
H
.
M
a
h
m
o
o
d
a
n
d
M
.
A
.
M
a
n
so
r
,
“
Re
d
b
lo
o
d
c
e
ll
s
e
stim
a
ti
o
n
u
sin
g
Ho
u
g
h
tran
sf
o
rm
tec
h
n
iq
u
e
,”
S
ig
n
a
l
&
Ima
g
e
Pro
c
e
ss
in
g
,
3
(2
)
,
53
,
2
0
1
2
.
[
22
]
L
.
H
.
L
ie
w
,
e
t
a
l.
,
“
Ce
ll
d
e
tec
ti
o
n
fo
r
b
e
e
c
o
m
b
ima
g
e
s
u
sin
g
c
irc
u
la
r
H
o
u
g
h
tr
a
n
sf
o
rm
a
ti
o
n
,”
S
c
ien
c
e
a
n
d
S
o
c
ial
Re
se
a
rc
h
(
CS
S
R
)
.
Ku
a
la L
u
m
p
u
r,
M
a
lay
sia
,
191
-
1
9
5
,
2
0
1
0
.
[
23
]
S
.
Ha
o
,
e
t
a
l.
,
“
Im
a
g
e
d
e
tail
e
n
h
a
n
c
e
m
e
n
t
w
it
h
sp
a
ti
a
ll
y
g
u
id
e
d
f
il
ters
,”
S
ig
n
a
l
Pr
o
c
e
ss
in
g
,
1
2
0
,
7
8
9
-
7
9
6
,
2
0
1
6
.
[
24
]
K
.
He
,
e
t
a
l
.
,
“
G
u
id
e
d
Im
a
g
e
F
il
terin
g
,
”
IEE
E
T
r
a
n
sa
c
ti
o
n
s
o
n
P
a
tt
e
rn
An
a
lys
is
a
n
d
M
a
c
h
in
e
I
n
tel
li
g
e
n
c
e
,
3
5
(
6
)
,
1
3
9
7
-
1
4
0
9
,
2
0
1
3
.
[
25
]
N
.
Otsu
., “
A
t
h
re
sh
o
ld
se
lec
ti
o
n
m
e
th
o
d
f
ro
m
g
ra
y
-
lev
e
l
h
isto
g
ra
m
s
,”
Au
to
ma
ti
c
a
,
11
,
23
-
27
,
1
9
7
5
.
[
26
]
M
.
V
e
ta,
e
t
a
l.
,
“
A
u
to
m
a
ti
c
n
u
c
lei
se
g
m
e
n
tatio
n
i
n
H&
E
sta
in
e
d
b
re
a
st
c
a
n
c
e
r
h
isto
p
a
t
h
o
l
o
g
y
i
m
a
g
e
s
,”
PL
o
S
On
e
,
8
(7
),
e
7
0
2
2
1
,
2
0
1
3
.
[
27
]
P
.
Ch
o
u
d
h
ry
,
“
Hig
h
-
T
h
ro
u
g
h
p
u
t
M
e
th
o
d
f
o
r
A
u
to
m
a
ted
Co
lo
n
y
a
n
d
Ce
ll
C
o
u
n
ti
n
g
b
y
Dig
it
a
l
Im
a
g
e
A
n
a
l
y
sis
Ba
se
d
o
n
E
d
g
e
De
tec
ti
o
n
,”
PL
o
S
On
e
,
1
1
(2
)
,
e
0
1
4
8
4
6
9
,
2
0
1
6
.
[
28
]
F
.
Ch
o
b
n
g
a
m
,
e
t
a
l.
,
“
P
re
li
m
in
a
ry
re
su
lt
s
o
f
d
e
a
th
c
e
ll
c
o
u
n
ti
n
g
b
a
se
d
o
n
K
-
m
e
a
n
c
lu
ste
rin
g
,”
T
h
e
5
th
2
0
1
2
Bi
o
me
d
ica
l
En
g
in
e
e
rin
g
I
n
ter
n
a
t
i
o
n
a
l
Co
n
fer
e
n
c
e
(
BM
Ei
CON
)
,
U
b
o
n
Ra
tch
a
th
a
n
i,
T
h
a
il
a
n
d
,
1
-
4
,
2
0
1
2
.
[
29
]
Y
.
Ya
g
i
a
n
d
J
.
R
.
G
il
b
e
rtso
n
,
“
Dig
it
a
l
ima
g
in
g
in
p
a
th
o
l
o
g
y
:
th
e
c
a
se
f
o
r
sta
n
d
a
rd
iza
ti
o
n
,”
J
o
u
rn
a
l
o
f
T
e
lem
e
d
icin
e
a
n
d
T
e
lec
a
re
,
1
1
(3
)
,
1
0
9
-
1
1
6
,
2
0
0
5
.
[
30
]
Y
.
H
.
Ch
o
i
a
n
d
Y
.
H
.
Yo
o
,
“
T
a
x
o
l
-
in
d
u
c
e
d
g
ro
w
th
a
rre
st
a
n
d
a
p
o
p
to
sis
is
a
ss
o
c
iate
d
w
it
h
th
e
u
p
r
e
g
u
latio
n
o
f
th
e
Cd
k
in
h
ib
it
o
r,
p
2
1
W
A
F
1
/
CIP
1
,
i
n
h
u
m
a
n
b
re
a
st ca
n
c
e
r
c
e
ll
s
,
”
On
c
o
lo
g
y
Rep
o
rts
,
2
8
(6
),
2
1
6
3
-
2
1
6
9
,
2
0
1
2
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
S
u
M
o
n
A
u
n
g
re
c
e
iv
e
d
h
e
r
b
a
c
h
e
lo
r
d
e
g
re
e
o
f
te
c
h
n
o
l
o
g
y
a
n
d
b
a
c
h
e
lo
r
d
e
g
re
e
o
f
e
n
g
in
e
e
rin
g
f
ro
m
M
a
n
d
a
lay
T
e
c
h
n
o
lo
g
ica
l
Un
iv
e
rsity
,
M
y
a
n
m
a
r
in
2
0
1
2
a
n
d
2
0
1
3
r
e
sp
e
c
ti
v
e
l
y
.
No
w
,
sh
e
is
stu
d
y
in
g
a
m
a
ste
r
d
e
g
re
e
in
Bio
m
e
d
ica
l
En
g
in
e
e
rin
g
a
t
F
a
c
u
l
ty
o
f
M
e
d
icin
e
,
P
rin
c
e
o
f
S
o
n
g
k
la
Un
iv
e
rsit
y
.
S
h
e
w
a
s
a
w
a
rd
e
d
f
o
r
T
h
a
il
a
n
d
’
s
Ed
u
c
a
ti
o
n
Hu
b
f
o
r
A
S
EA
N
c
o
u
n
tri
e
s
(
T
E
H
-
AC
)
sc
h
o
lars
h
ip
f
o
r
M
a
ste
r
De
g
re
e
P
r
o
g
ra
m
(
2
0
1
5
-
2
0
1
7
)
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.
9
,
No
.
4
,
A
u
g
u
s
t
201
9
:
2
4
6
0
-
2468
2468
K
a
n
y
a
n
a
tt
K
a
n
o
k
w
iro
o
n
re
c
e
i
v
e
d
th
e
B
.
Sc
.
d
e
g
re
e
(
w
it
h
h
o
n
o
rs
)
in
Bi
o
tec
h
n
o
lo
g
y
in
2
0
0
0
a
n
d
Ph
.
D
.
d
e
g
re
e
s
in
Bio
c
h
e
m
istr
y
f
r
o
m
P
rin
c
e
o
f
S
o
n
g
k
la
Un
iv
e
rsity
,
Ha
t
Ya
i,
S
o
n
g
k
h
la,
T
h
a
il
a
n
d
in
2
0
0
7
.
S
h
e
sta
rted
h
e
r
c
a
re
e
r
a
s
a
lec
tu
re
r
a
t
F
a
c
u
lt
y
o
f
S
c
ien
c
e
a
n
d
In
d
u
str
ial
T
e
c
h
n
o
lo
g
y
,
P
rin
c
e
o
f
S
o
n
g
k
la
Un
iv
e
rsity
,
S
u
ra
t
T
h
a
n
i
Ca
m
p
u
s
in
2
0
0
8
.
S
h
e
is
c
u
r
re
n
t
ly
a
n
A
ss
istan
t
P
ro
f
e
ss
o
r
a
t
De
p
a
rtme
n
t
o
f
Bio
m
e
d
ica
l
S
c
ie
n
c
e
s,
F
a
c
u
lt
y
o
f
M
e
d
icin
e
,
P
ri
n
c
e
o
f
S
o
n
g
k
la
Un
iv
e
rsit
y
.
He
r
re
se
a
rc
h
in
tere
sts
c
o
v
e
r
th
e
m
o
lec
u
lar
m
e
c
h
a
n
is
m
a
n
d
b
io
m
a
rk
e
r
id
e
n
ti
f
ica
ti
o
n
o
f
b
re
a
s
t
tu
m
o
rig
e
n
e
sis in
b
re
a
st ca
n
c
e
r
.
To
n
g
h
a
t
h
a
i
Ph
a
ira
t
a
n
a
re
c
e
iv
e
d
h
e
r
B
.
Sc
.
in
P
h
y
sic
s
in
2
0
0
9
f
ro
m
P
rin
c
e
o
f
S
o
n
g
k
la
Un
iv
e
rsity
,
T
h
a
il
a
n
d
.
S
h
e
w
a
s
a
wa
rd
e
d
M
.
Sc
.
in
2
0
1
1
u
n
d
e
r
th
e
s
u
p
e
rv
isio
n
o
f
P
ro
f
.
M
o
l
ly
S
tev
e
n
s
a
n
d
P
h
D
i
n
2
0
1
6
u
n
d
e
r
th
e
d
irec
ti
o
n
o
f
P
r
o
f
.
M
a
rty
n
Bo
u
telle
in
Bio
m
e
d
ica
l
En
g
in
e
e
rin
g
f
ro
m
I
m
p
e
rial
Co
ll
e
g
e
L
o
n
d
o
n
,
U
n
it
e
d
Kin
g
d
o
m
.
S
h
e
is
c
u
rre
n
tl
y
a
lec
tu
re
r
a
n
d
a
re
se
a
rc
h
e
r
a
t
t
h
e
I
n
stit
u
te
o
f
Bio
m
e
d
ica
l
En
g
in
e
e
rin
g
,
F
a
c
u
lt
y
o
f
M
e
d
icin
e
,
P
ri
n
c
e
o
f
S
o
n
g
k
la
Un
iv
e
rsity
,
S
o
n
g
k
h
la,
T
h
a
il
a
n
d
.
He
r
c
u
rre
n
t
re
se
a
rc
h
in
tere
sts
f
o
c
u
s
o
n
e
lec
tr
o
c
h
e
m
ica
l
b
io
se
n
so
rs
a
n
d
m
icr
o
f
lu
id
ics
f
o
r
th
e
d
e
v
e
lo
p
m
e
n
t
o
f
c
li
n
ica
l
d
iag
n
o
st
ic sy
st
e
m
s a
n
d
p
h
y
sio
lo
g
ica
l
m
o
n
it
o
ri
n
g
in
re
a
l
-
ti
m
e
.
S
u
r
a
p
o
n
g
Cha
t
p
u
n
re
c
e
iv
e
d
h
is
B
.
En
g
in
M
e
c
h
a
n
ica
l
E
n
g
in
e
e
rin
g
in
1
9
9
6
f
ro
m
Ch
u
lalo
n
g
k
o
rn
Un
iv
e
rsit
y
,
T
h
a
il
a
n
d
.
He
re
c
e
i
v
e
d
h
is
M
.
En
g
in
M
e
c
h
a
n
ica
l
En
g
in
e
e
rin
g
in
2
0
0
3
f
ro
m
Un
iv
e
rsit
y
o
f
T
o
k
y
o
,
Ja
p
a
n
.
He
w
a
s
a
wa
rd
e
d
P
h
.
D
.
in
Bio
e
n
g
in
e
e
rin
g
f
ro
m
U
n
iv
e
rsity
o
f
Ca
li
f
o
rn
ia,
S
a
n
Die
g
o
,
Un
it
e
d
S
tate
.
He
jo
in
e
d
th
e
In
st
it
u
te
o
f
Bio
m
e
d
ica
l
En
g
in
e
e
rin
g
,
F
a
c
u
lt
y
o
f
M
e
d
icin
e
,
P
r
i
n
c
e
o
f
S
o
n
g
k
la
Un
iv
e
rsit
y
a
s
a
lec
tu
re
r
in
2
0
1
0
.
No
w
,
h
e
is
a
n
a
ss
ista
n
t
p
r
o
f
e
ss
o
r
.
His
c
u
rre
n
t
re
se
a
r
c
h
in
tere
sts
in
c
lu
d
e
c
a
rd
i
o
v
a
sc
u
lar
e
n
g
in
e
e
rin
g
,
b
i
o
m
e
c
h
a
n
ics
,
i
m
a
g
e
a
n
d
sig
n
a
l
a
n
a
ly
sis
a
n
d
m
e
d
ica
l
d
e
v
ice
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.