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
.
3
,
J
u
n
e
201
8
,
p
p
.
1
7
3
1
~
1
7
4
0
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v8
i
3
.
p
p
1
7
3
1
-
1740
1731
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
Auto
m
a
tic
Le
u
k
e
m
ia
C
ell Coun
tin
g
using
Iterative
Dista
nce
T
ra
nsfo
r
m
f
o
r
Co
nv
ex
Set
s
Nenden S
it
i F
a
t
o
na
h
,
H
a
nd
a
y
a
ni T
j
a
nd
ra
s
a
,
Cha
s
t
ine F
a
t
icha
h
De
p
a
rte
m
e
n
t
o
f
In
f
o
r
m
a
ti
c
,
In
stit
u
te
T
e
k
n
o
lo
g
i
S
e
p
u
lu
h
No
p
e
m
b
e
r
,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
4
,
2
0
1
8
R
ev
i
s
ed
Ma
y
2
,
2
0
1
8
A
cc
ep
ted
Ma
y
11
,
2
0
1
8
T
h
e
c
a
l
c
u
latio
n
o
f
w
h
it
e
b
lo
o
d
c
e
ll
s
o
n
th
e
a
c
u
te
leu
k
e
m
ia
m
icro
sc
o
p
ic
im
a
g
e
s
is
o
n
e
o
f
th
e
sta
g
e
s
in
th
e
d
iag
n
o
sis
o
f
L
e
u
k
e
m
ia
d
ise
a
se
.
T
h
e
m
a
in
c
o
n
stra
in
t
o
n
c
a
lcu
lati
n
g
th
e
n
u
m
b
e
r
o
f
w
h
it
e
b
lo
o
d
c
e
ll
s
is
t
h
e
p
re
c
isio
n
i
n
th
e
a
re
a
o
f
o
v
e
rlap
p
in
g
w
h
it
e
b
l
o
o
d
c
e
ll
s.
T
h
e
re
se
a
rc
h
o
n
th
e
c
a
lcu
latio
n
o
f
th
e
n
u
m
b
e
r
o
f
w
h
it
e
b
lo
o
d
c
e
ll
s
o
v
e
rlap
p
in
g
g
e
n
e
ra
ll
y
b
a
se
d
o
n
g
e
o
m
e
tr
y
.
Ho
w
e
v
e
r,
th
e
re
w
a
s
stil
l
a
c
a
lcu
latio
n
e
rro
r
d
u
e
t
o
o
v
e
r
se
g
m
e
n
t
o
r
u
n
d
e
r
se
g
m
e
n
t.
T
h
is
p
a
p
e
r
p
ro
p
o
se
d
a
n
Itera
ti
v
e
Dista
n
c
e
T
ra
n
s
f
o
r
m
fo
r
Co
n
v
e
x
S
e
ts
(IDT
CS
)
m
e
th
o
d
t
o
d
e
term
i
n
e
th
e
m
a
r
k
e
rs
a
n
d
c
a
lcu
late
th
e
n
u
m
b
e
r
o
f
o
v
e
rlap
p
in
g
w
h
it
e
b
l
o
o
d
c
e
ll
s.
De
ter
m
in
a
ti
o
n
o
f
m
a
rk
e
r
w
a
s
p
e
rf
o
r
m
e
d
o
n
e
v
e
r
y
c
e
ll
b
o
th
in
sin
g
le
a
n
d
o
v
e
rlap
p
i
n
g
w
h
it
e
b
lo
o
d
c
e
ll
a
re
a
.
In
th
is
stu
d
y
,
th
e
re
w
e
re
tree
sta
g
e
s
:
se
g
m
e
n
ta
ti
o
n
o
f
w
h
it
e
b
lo
o
d
c
e
ll
s,
m
a
rk
e
r
d
e
tec
ti
o
n
a
n
d
w
h
it
e
b
l
o
o
d
c
e
ll
c
o
u
n
t
,
a
n
d
c
o
n
t
o
u
r
e
stim
a
ti
o
n
o
f
e
v
e
r
y
w
h
it
e
b
lo
o
d
c
e
ll
.
T
h
e
u
se
d
d
a
ta
tes
ti
n
g
wa
s
m
icro
sc
o
p
ic
a
c
u
te
leu
k
e
m
ia
i
m
a
g
e
d
a
t
a
o
f
A
c
u
te
Ly
m
p
h
o
b
las
ti
c
L
e
u
k
e
m
ia
(
ALL
)
a
n
d
A
c
u
te
M
y
e
lo
b
las
ti
c
L
e
u
k
e
m
i
a
(A
M
L
).
Ba
se
d
o
n
t
h
e
tes
t
re
su
lt
s,
Itera
t
iv
e
Dista
n
c
e
T
ra
n
sf
o
r
m
f
o
r
Co
n
v
e
x
S
e
ts
IDT
CS
m
e
th
o
d
p
e
rf
o
rm
s
b
e
tt
e
r
t
h
a
n
Dista
n
c
e
T
r
a
n
sf
o
r
m
(
DT
)
a
n
d
Ulti
m
a
te
Ero
sio
n
f
o
r
Co
n
v
e
x
S
e
ts
(
UECS
)
m
e
th
o
d
.
K
ey
w
o
r
d
:
A
c
u
te
le
u
k
e
m
ia
A
c
u
te
l
y
m
p
h
o
b
last
ic
le
u
k
e
m
ia
A
c
u
te
m
y
lo
b
las
tic
leu
k
e
m
ia
I
ter
ativ
e
d
is
ta
n
ce
tr
an
s
f
o
r
m
f
o
r
co
n
v
e
x
s
et
s
W
h
ite
b
lo
o
d
ce
ll
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
:
Nen
d
en
S
iti Fato
n
a
h
,
Dep
ar
te
m
en
t o
f
I
n
f
o
r
m
atic,
I
n
s
tit
u
te
T
ek
n
o
lo
g
i Sep
u
l
u
h
N
o
p
em
b
er
,
I
n
d
o
n
esia.
E
m
ail:
n
en
d
e
n
@
m
er
c
u
b
u
a
n
a.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
L
e
u
k
e
m
ia
i
s
o
n
e
o
f
t
h
e
m
o
s
t
d
an
g
er
o
u
s
d
is
ea
s
es
a
n
d
th
e
i
m
p
ac
t
is
v
er
y
d
ea
d
l
y
i
f
n
o
t
q
u
ick
l
y
o
v
er
co
m
e.
L
eu
k
e
m
ia
i
s
ca
u
s
e
d
b
y
a
n
ab
n
o
r
m
al
d
e
v
elo
p
m
e
n
t
o
f
w
h
ite
b
lo
o
d
ce
lls
p
r
o
d
u
ce
d
b
y
b
o
n
e
m
ar
r
o
w
[
1
]
.
R
esear
ch
o
n
ac
u
te
leu
k
e
m
ia
ce
lls
h
a
s
b
ee
n
d
o
n
e
to
s
u
p
p
o
r
t
th
e
m
ed
ical
d
iag
n
o
s
i
s
,
w
h
e
th
er
it
is
ab
o
u
t
leu
k
o
c
y
te
s
e
g
m
en
tatio
n
o
r
s
e
g
m
e
n
tat
io
n
o
f
n
u
cleu
s
ce
lls
.
Ma
n
u
a
l
ca
lcu
la
tio
n
s
w
ill
ce
r
t
ain
l
y
lead
to
less
ef
f
ec
tiv
e
a
n
d
w
ea
k
n
e
s
s
o
f
ac
c
u
r
ac
y
d
u
e
to
th
e
f
ac
to
r
o
f
s
u
b
j
ec
tiv
it
y
.
A
co
m
p
u
ter
ized
s
y
s
te
m
ca
n
b
e
u
s
ed
as
a
s
u
p
p
o
r
t
to
o
l
f
o
r
p
h
y
s
ic
ian
s
o
r
p
ath
o
lo
g
y
s
p
ec
iali
s
ts
in
o
r
d
er
to
im
p
r
o
v
e
an
d
ac
ce
ler
ate
th
e
p
r
o
ce
s
s
o
f
m
o
r
p
h
o
lo
g
ical
a
n
al
y
s
is
[
2
]
.
Saat
in
i
b
eb
er
ap
a
p
en
eliti
an
m
e
n
g
g
u
n
ak
a
n
a
n
alis
a
d
a
r
i
d
ata
citr
a
u
n
t
u
k
m
en
d
ia
g
n
o
s
a
s
eb
u
a
h
p
en
y
ak
it
s
ep
er
ti p
ad
a
liter
atu
r
[3
]
,
[
4]
.
On
e
o
f
t
h
e
s
ta
g
es
o
f
th
e
le
u
k
e
m
ia
d
ia
g
n
o
s
is
s
y
s
te
m
in
t
h
e
b
lo
o
d
ce
ll
i
m
a
g
e
d
ata
d
o
es
t
h
e
w
h
ite
b
lo
o
d
ce
lls
s
eg
m
en
tatio
n
.
T
h
e
p
r
o
ce
s
s
o
f
s
eg
m
e
n
tatio
n
is
an
i
m
p
o
r
tan
t
s
tep
b
ec
au
s
e
t
h
e
r
esu
lt
s
o
f
g
o
o
d
s
eg
m
e
n
tatio
n
w
ill
g
e
t
a
n
ac
c
u
r
ate
f
ea
tu
r
e
s
o
as
to
i
m
p
r
o
v
e
t
h
e
ac
c
u
r
ac
y
o
f
th
e
d
iag
n
o
s
is
.
C
u
r
r
en
t
l
y
,
th
e
p
r
o
ce
s
s
o
f
s
eg
m
e
n
tatio
n
o
f
wh
ite
b
lo
o
d
ce
lls
h
as
b
ee
n
d
o
n
e
b
y
m
a
n
y
r
esear
c
h
er
s
[
6
]
-
[
1
3
]
.
I
n
a
r
esear
ch
[
6
]
,
s
eg
m
e
n
tatio
n
p
r
o
ce
s
s
is
d
o
n
e
b
y
th
r
e
s
h
o
ld
i
n
g
u
s
in
g
Z
ac
k
A
l
g
o
r
ith
m
a
n
d
eli
m
i
n
ati
n
g
b
ac
k
g
r
o
u
n
d
u
s
i
n
g
ar
ith
m
etic
p
r
o
ce
s
s
.
Seg
m
en
tat
io
n
b
ased
o
n
th
e
p
ar
am
e
tr
ic
m
o
d
el
ap
p
r
o
ac
h
o
f
a
Gau
s
s
ia
n
m
i
x
t
u
r
e
(
GM
)
w
as
u
s
ed
i
n
th
e
s
t
u
d
y
[
7
]
.
I
n
th
e
s
tu
d
y
b
y
H
u
an
g
et
al.
[
8
]
,
leu
k
o
c
y
te
s
eg
m
e
n
tatio
n
b
y
u
s
i
n
g
Ots
u
t
h
r
es
h
o
ld
in
g
m
et
h
o
d
w
as
p
r
e
v
io
u
s
l
y
d
o
n
e
i
n
t
h
e
p
r
o
ce
s
s
o
f
i
m
a
g
e
r
ep
air
.
T
h
e
s
eg
m
e
n
tatio
n
o
f
th
e
n
u
cle
u
s
u
s
in
g
th
e
Gr
a
m
-
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
.
3
,
J
u
n
e
2
0
1
8
:
1
7
3
1
–
1740
1732
Sch
m
id
t
o
r
th
o
g
o
n
aliza
tio
n
m
e
th
o
d
an
d
th
e
s
n
ak
e
al
g
o
r
ith
m
f
o
r
cy
to
p
las
m
s
e
g
m
e
n
tat
io
n
w
a
s
p
er
f
o
r
m
ed
i
n
th
e
s
tu
d
y
[
9
]
.
I
n
[
1
0
]
,
th
e
r
esear
ch
p
r
o
p
o
s
ed
an
I
n
ter
est
-
b
a
s
ed
O
r
d
er
in
g
Sc
h
e
m
e
(
I
OS)
f
o
r
Fu
z
z
y
Mo
r
p
h
o
lo
g
y
o
n
th
e
s
eg
m
e
n
tatio
n
o
f
W
h
ite
B
l
o
o
d
C
ell
(
W
B
C
)
i
m
a
g
er
y
s
o
a
s
to
i
m
p
r
o
v
e
t
h
e
ac
c
u
r
ac
y
o
f
t
h
e
s
e
g
m
e
n
tatio
n
o
f
th
e
n
u
cle
u
s
.
L
a
ter
in
th
e
s
tu
d
y
[
1
1
]
u
s
i
n
g
Ot
s
u
th
r
es
h
o
ld
in
g
an
d
K
-
Me
a
n
s
m
et
h
o
d
to
d
e
tect
ce
lls
.
I
n
[
1
2
]
,
[
13]
,
th
e
s
tu
d
ies
p
er
f
o
r
m
ed
th
e
p
r
o
ce
s
s
o
f
s
eg
m
en
tin
g
w
h
ite
b
lo
o
d
ce
lls
u
s
i
n
g
m
o
r
p
h
o
lo
g
i
ca
l o
p
er
atio
n
s
.
B
ased
o
n
p
r
ev
io
u
s
s
t
u
d
ies,
s
o
lv
i
n
g
t
h
e
p
r
o
b
le
m
o
f
s
e
g
m
en
t
atio
n
o
n
t
h
e
i
m
a
g
e
o
f
b
lo
o
d
ce
lls
w
it
h
w
h
ite
b
lo
o
d
ce
ll
o
b
j
ec
t
th
at
s
till
o
v
er
lap
p
in
g
n
ee
d
to
b
e
d
ev
elo
p
ed
.
T
h
e
p
r
o
b
lem
is
r
elat
ed
to
th
e
s
till
o
v
er
s
eg
m
e
n
t a
n
d
u
n
d
er
s
eg
m
e
n
t
o
n
t
h
e
r
es
u
lt
s
o
f
s
eg
m
e
n
tatio
n
o
f
w
h
ite
b
lo
o
d
ce
lls
,
th
u
s
r
ed
u
cin
g
t
h
e
ac
c
u
r
ac
y
o
f
ce
ll c
o
u
n
t c
alc
u
latio
n
s
.
Naz
lib
ilek
et
al.
[
1
2
]
p
er
f
o
r
m
ed
w
h
i
te
b
lo
o
d
ce
ll
ca
lcu
la
tio
n
s
u
s
i
n
g
g
eo
m
etr
ic
ap
p
r
o
ac
h
es
f
r
o
m
co
m
p
o
n
e
n
t
-
co
n
n
ec
ted
a
n
d
lab
elin
g
p
r
o
ce
s
s
es.
C
o
u
n
ti
n
g
o
v
e
r
lap
p
in
g
ce
ll
s
w
it
h
a
g
eo
m
etr
y
ap
p
r
o
ac
h
w
a
s
als
o
p
er
f
o
r
m
ed
i
n
t
h
e
s
tu
d
y
[
1
3
]
u
s
in
g
t
h
e
ec
ce
n
tr
icit
y
an
d
t
h
r
es
h
o
ld
in
g
r
eg
io
n
.
I
n
t
h
e
s
tu
d
y
[
6
]
,
P
u
tzu
et
al.
u
s
ed
s
o
lid
it
y
a
n
d
th
r
es
h
o
ld
in
g
also
f
o
r
th
e
d
etec
tio
n
a
n
d
ca
lcu
lati
o
n
o
f
ce
ll n
u
m
b
er
s
.
I
n
p
r
ev
io
u
s
s
t
u
d
i
es
,
t
h
e
r
esea
r
ch
er
s
g
e
n
er
all
y
d
id
th
e
d
etec
tio
n
an
d
ca
lcu
la
tio
n
o
f
w
h
ite
b
lo
o
d
ce
l
l
co
u
n
t
s
o
n
o
v
er
lap
p
in
g
ce
lls
u
s
in
g
a
g
eo
m
etr
ic
ap
p
r
o
ac
h
.
T
o
ca
lcu
late
th
e
n
u
m
b
er
o
f
o
v
e
r
lap
p
in
g
ce
lls
,
t
h
e
y
g
en
er
al
ly
di
v
id
ed
a
lar
g
er
ar
ea
o
f
o
v
er
lap
p
in
g
w
h
ite
b
lo
o
d
ce
lls
b
y
th
e
a
v
er
ag
e
o
f
t
h
e
s
in
g
le
ce
ll
ar
ea
s
.
Ho
w
e
v
er
,
th
e
ar
ea
o
f
s
in
g
le
wh
ite
b
lo
o
d
ce
lls
v
ar
ies
in
s
ize,
i
.
e
.
th
er
e
is
a
s
in
g
le
ce
ll
ar
ea
th
at
al
m
o
s
t
eq
u
al
to
th
e
w
id
t
h
o
f
t
h
e
o
v
er
lap
p
in
g
c
ell
ar
ea
s
o
t
h
at
t
h
e
ce
ll
co
u
n
t b
ec
o
m
e
s
le
s
s
ac
c
u
r
ate.
I
n
[
1
4
]
,
th
e
s
tu
d
y
p
r
o
p
o
s
ed
an
a
u
to
m
a
ted
m
o
r
p
h
o
lo
g
ical
an
al
y
s
is
m
et
h
o
d
f
o
r
n
a
n
o
p
ar
ticle
tan
g
e
n
t
o
b
j
ec
ts
to
s
ep
ar
ate
th
e
tan
g
led
o
r
o
v
er
lap
p
in
g
p
ar
ticle
s
b
y
iter
atin
g
t
h
e
er
o
s
io
n
m
o
r
p
h
o
lo
g
y
p
r
o
ce
s
s
to
o
b
tain
m
ar
k
er
s
o
n
ea
ch
ce
ll.
T
h
i
s
r
esear
ch
p
r
o
p
o
s
ed
th
e
Ult
i
m
a
t
e
E
r
o
s
io
n
f
o
r
C
o
n
v
e
x
Se
ts
(
U
E
C
S)
m
et
h
o
d
to
id
en
ti
f
y
s
ee
d
p
o
in
ts
in
a
r
eg
io
n
o
f
in
ter
est.
T
h
is
s
tu
d
y
p
r
es
en
ted
a
f
r
a
m
e
w
o
r
k
f
o
r
cl
u
s
ter
s
o
f
co
n
v
e
x
i
n
ter
s
ec
ti
n
g
o
b
j
ec
ts
w
ith
th
r
ee
ap
p
r
o
ac
h
es:
s
ee
d
p
o
in
t
e
x
tr
a
ctio
n
,
co
n
to
u
r
ev
id
e
n
ce
e
x
tr
ac
tio
n
,
an
d
e
s
ti
m
ated
co
n
to
u
r
s
th
at
h
a
v
e
b
ee
n
m
ar
k
ed
.
Z
a
f
ar
i
[
1
5
]
co
m
p
ar
ed
s
o
m
e
o
f
t
h
e
m
et
h
o
d
s
o
f
o
b
j
ec
t
d
etec
tio
n
t
h
at
i
s
o
v
er
lap
p
in
g
o
r
ta
n
g
e
n
t.
T
h
e
co
m
p
ar
ab
le
m
et
h
o
d
s
in
cl
u
d
e
d
th
e
Di
s
ta
n
ce
T
r
an
s
f
o
r
m
(
DT
)
m
et
h
o
d
an
d
t
h
e
UE
C
S
m
et
h
o
d
p
r
o
p
o
s
ed
b
y
t
h
e
r
esear
ch
er
s
[
1
4
]
.
B
ased
o
n
th
is
r
esear
ch
r
esu
lt
o
f
DT
m
et
h
o
d
test
,
it
is
v
er
y
g
o
o
d
to
m
ar
k
o
b
j
ec
t
s
w
h
ich
g
en
er
all
y
o
f
th
e
s
a
m
e
s
ize.
T
h
e
n
u
m
b
er
o
f
o
b
j
ec
ts
id
en
ti
f
ied
b
y
th
i
s
m
et
h
o
d
is
h
i
g
h
l
y
d
ep
e
n
d
en
t
o
n
th
e
g
i
v
e
n
th
r
es
h
o
ld
v
al
u
e
o
f
ρ
.
Fo
r
o
v
er
lap
p
in
g
ce
lls
,
i
f
t
h
e
th
r
es
h
o
ld
v
alu
e
i
s
s
m
all
,
it
ca
u
s
es
l
ar
g
e
o
b
j
ec
ts
f
ail
to
s
eg
m
e
n
t
w
ell,
w
h
ile
a
lar
g
e
ρ
v
alu
e
al
s
o
ca
u
s
es
u
n
d
er
s
e
g
m
en
t
atio
n
b
ec
a
u
s
e
t
h
er
e
ar
e
o
b
ject
s
lo
s
t
d
u
e
to
th
e
th
r
es
h
o
ld
p
r
o
ce
s
s
.
T
h
is
ca
u
s
es
th
e
m
et
h
o
d
to
f
ail
to
b
e
u
s
ed
to
s
ep
ar
ate
th
e
o
v
er
lap
p
in
g
o
b
j
ec
ts
.
I
n
co
n
tr
ast
to
th
e
DT
m
et
h
o
d
,
th
e
UE
C
S
m
et
h
o
d
[
1
4
]
is
v
er
y
g
o
o
d
f
o
r
s
eg
m
en
t
in
g
u
n
if
o
r
m
l
y
s
iz
ed
i
m
a
g
es
b
u
t
o
v
er
s
eg
m
e
n
t
atio
n
m
a
y
o
cc
u
r
if
t
h
e
s
h
ap
e
o
f
t
h
e
ce
ll is
n
o
t g
o
o
d
at
th
e
ed
g
es.
T
h
is
r
esear
ch
p
r
o
p
o
s
es
I
ter
ati
v
e
Dis
ta
n
ce
T
r
an
s
f
o
r
m
Fo
r
C
o
n
v
e
x
Sets
(
I
DT
C
S)
m
et
h
o
d
.
Un
li
k
e
th
e
u
s
u
al
DT
,
th
e
I
DT
C
S
m
et
h
o
d
r
ep
ea
ts
th
e
DT
p
r
o
ce
s
s
u
n
til
n
o
o
b
j
ec
t
is
lef
t
an
d
t
h
e
ce
ll
w
i
ll
b
e
m
ar
k
ed
i
f
th
e
s
ize
o
f
co
n
ca
v
i
t
y
i
s
le
s
s
t
h
a
n
t
h
e
t
h
r
esh
o
ld
v
alu
e
(
ρ
)
.
T
h
e
r
es
u
lt
o
f
th
e
I
DT
C
S
m
et
h
o
d
is
t
h
at
all
t
h
e
o
v
er
lap
p
in
g
o
b
j
ec
ts
ar
e
s
u
cc
e
s
s
f
u
l
l
y
m
ar
k
ed
as
s
in
g
le
o
b
j
e
cts.
I
DT
C
S
is
n
a
m
ed
f
o
r
th
e
iter
ativ
e
p
r
o
ce
s
s
to
Dis
ta
n
ce
T
r
an
s
f
o
r
m
m
e
th
o
d
t
o
g
et
a
m
ar
k
er
o
f
ea
ch
o
b
j
ec
t.
T
h
e
co
n
ce
p
t
lik
e
s
th
e
UE
C
S
m
et
h
o
d
b
u
t
t
h
e
d
if
f
er
e
n
ce
UE
C
S
d
o
iter
ativ
el
y
to
th
e
er
o
s
io
n
m
o
r
p
h
o
lo
g
y
p
r
o
ce
s
s
to
g
et
m
ar
k
er
s
o
f
ea
ch
o
b
j
ec
t.
T
h
e
s
tu
d
y
w
a
s
d
iv
id
ed
in
to
th
r
ee
s
ta
g
es:
s
eg
m
en
ta
tio
n
o
f
w
h
ite
b
lo
o
d
ce
lls
,
m
ar
k
er
d
etec
tio
n
an
d
c
alcu
latio
n
o
f
w
h
i
te
b
lo
o
d
ce
ll
co
u
n
t,
an
d
co
n
to
u
r
esti
m
atio
n
s
ta
g
e
o
f
ea
ch
w
h
it
e
b
lo
o
d
ce
ll.
T
h
e
f
ir
s
t
s
tag
e
ai
m
s
to
g
et
t
h
e
w
h
it
e
b
lo
o
d
ce
ll
ar
ea
co
v
er
in
g
t
h
e
wh
o
le
ce
ll
ar
ea
an
d
th
e
n
u
cle
u
s
ar
ea
.
T
h
e
s
ec
o
n
d
s
tag
e
ai
m
s
t
o
g
et
th
e
m
ar
k
er
o
f
ea
ch
ce
ll
b
o
th
i
n
t
h
e
s
in
g
le
a
n
d
o
v
er
lap
p
in
g
w
h
ite
b
lo
o
d
ce
ll
ar
ea
,
th
en
th
e
p
r
o
ce
s
s
o
f
ca
lc
u
lati
n
g
th
e
n
u
m
b
er
o
f
w
h
ite
b
lo
o
d
ce
lls
ca
n
b
e
d
o
n
e.
I
n
th
i
s
s
ec
o
n
d
s
ta
g
e,
th
e
o
v
er
lap
p
in
g
w
h
ite
b
lo
o
d
ce
ll
ar
ea
ca
n
b
e
d
etec
ted
b
y
m
o
r
e
th
a
n
o
n
e
m
ar
k
er
n
u
m
b
er
i
n
t
h
e
ar
ea
.
T
h
e
th
ir
d
s
tag
e
ai
m
s
to
g
et
t
h
e
co
n
to
u
r
s
o
f
ev
er
y
s
in
g
le
w
h
ite
b
lo
o
d
ce
ll in
th
e
ar
ea
o
f
s
in
g
le
an
d
o
v
er
lap
p
in
g
w
h
ite
b
lo
o
d
ce
lls
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
Stag
e
s
o
f
th
e
p
r
o
ce
s
s
o
f
s
eg
m
en
tatio
n
a
n
d
ca
l
cu
latio
n
o
f
w
h
ite
b
lo
o
d
ce
ll
co
u
n
t
is
an
i
m
p
o
r
tan
t
s
tag
e
in
th
e
d
iag
n
o
s
i
s
o
f
L
e
u
k
e
m
ia
d
is
ea
s
e.
I
n
g
en
er
al,
th
e
d
esi
g
n
o
f
th
e
s
eg
m
en
tatio
n
p
r
o
ce
s
s
an
d
th
e
ca
lcu
latio
n
o
f
th
e
n
u
m
b
er
o
f
w
h
ite
b
lo
o
d
ce
lls
in
cl
u
d
e
s
eg
m
e
n
tatio
n
o
f
w
h
i
te
b
lo
o
d
ce
ll
a
r
ea
,
s
tack
ce
ll
d
etec
tio
n
,
ce
ll
co
u
n
t
ca
lc
u
latio
n
,
an
d
s
tack
c
ell
s
ep
ar
atio
n
.
T
h
is
s
t
u
d
y
p
r
o
p
o
s
ed
th
e
d
esig
n
o
f
th
e
s
eg
m
e
n
tatio
n
p
r
o
ce
s
s
an
d
th
e
ca
lcu
la
tio
n
o
f
th
e
n
u
m
b
e
r
o
f
w
h
i
te
b
lo
o
d
ce
lls
in
clu
d
e
s
eg
m
en
tat
io
n
o
f
w
h
ite
b
lo
o
d
ce
ll
ar
ea
,
m
ar
k
er
d
etec
tio
n
an
d
w
h
i
te
b
lo
o
d
ce
l
l
co
u
n
t,
an
d
es
ti
m
a
tio
n
o
f
w
h
ite
b
lo
o
d
ce
ll
co
n
to
u
r
.
Dete
ctio
n
o
f
m
ar
k
er
s
an
d
ca
lcu
latio
n
o
f
t
h
e
n
u
m
b
er
o
f
w
h
ite
b
lo
o
d
ce
lls
w
er
e
p
er
f
o
r
m
ed
f
ir
s
t
in
th
is
s
t
u
d
y
w
ith
o
u
t
t
h
e
d
etec
tio
n
o
f
o
v
er
lap
p
in
g
ce
ll
s
.
T
h
e
p
u
r
p
o
s
e
o
f
th
e
d
etec
tio
n
p
r
o
ce
s
s
o
f
w
h
ite
b
lo
o
d
ce
ll
m
ar
k
er
is
to
g
et
a
m
ar
k
er
o
f
ev
er
y
w
h
ite
b
lo
o
d
ce
lls
i
n
w
h
ite
b
lo
o
d
ce
ll
ar
ea
eith
er
s
in
g
le
o
r
o
v
er
lap
p
in
g
.
A
w
h
ite
b
lo
o
d
ce
ll
ar
ea
th
at
h
as
m
o
r
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:
2
0
8
8
-
8708
A
u
to
ma
tic
Leu
ke
mia
C
ell
C
o
u
n
tin
g
u
s
in
g
I
tera
tive
Di
s
ta
n
ce
Tr
a
n
s
fo
r
m
fo
r
C
o
n
ve
x
…
(
N
en
d
en
S
iti F
a
to
n
a
h
)
1733
th
an
o
n
e
m
ar
k
er
is
an
o
v
er
la
p
p
in
g
w
h
ite
b
lo
o
d
ce
ll
ar
ea
.
T
h
e
d
esig
n
o
f
t
h
e
s
e
g
m
e
n
tat
i
o
n
p
r
o
ce
s
s
an
d
th
e
ca
lcu
latio
n
o
f
t
h
e
w
h
ite
b
lo
o
d
co
u
n
t c
a
n
b
e
s
ee
n
i
n
Fi
g
u
r
e
1
.
Fig
u
r
e
1
.
Seg
m
en
ta
tio
n
p
r
o
ce
s
s
d
esig
n
an
d
ca
lc
u
latio
n
o
f
w
h
ite
b
lo
o
d
ce
ll c
o
u
n
t
T
h
e
in
p
u
t
d
ata
f
o
r
t
h
is
r
esear
c
h
is
m
icr
o
s
co
p
ic
i
m
a
g
e
s
o
f
ac
u
te
le
u
k
e
m
ia
w
h
ic
h
co
n
s
is
t
o
f
i
m
a
g
es
o
f
A
c
u
te
L
y
m
p
h
o
b
las
tic
L
e
u
k
e
m
ia
(
AL
L
)
a
n
d
A
c
u
te
M
y
elo
i
d
L
eu
k
e
m
ia
(
A
M
L
)
.
T
h
e
f
ir
s
t
s
tag
e
i
n
Fig
u
r
e
1
is
th
e
p
r
o
ce
s
s
o
f
s
eg
m
e
n
ti
n
g
wh
ite
b
lo
o
d
ce
lls
ai
m
ed
at
o
b
t
ain
i
n
g
t
h
e
ce
ll
ar
ea
o
f
th
e
w
h
ite
b
lo
o
d
ce
lls
.
T
h
e
s
ec
o
n
d
s
tag
e
i
s
th
e
d
eter
m
i
n
at
io
n
o
f
th
e
m
ar
k
er
o
f
ea
ch
w
h
it
e
b
lo
o
d
ce
ll
an
d
th
e
ca
lcu
latio
n
o
f
th
e
n
u
m
b
er
o
f
w
h
ite
b
lo
o
d
ce
lls
.
Ma
r
k
er
d
etec
tio
n
is
d
o
n
e
o
n
t
h
e
s
i
n
g
le
a
n
d
o
v
er
lap
p
in
g
w
h
ite
b
lo
o
d
ce
ll
ar
ea
s
o
th
at
f
r
o
m
th
e
r
es
u
lt
o
f
t
h
e
m
ar
k
er
d
etec
tio
n
p
r
o
ce
s
s
ca
n
b
e
k
n
o
w
n
wh
er
e
th
e
w
h
i
te
b
lo
o
d
ce
ll
ar
ea
is
p
iled
m
ar
k
ed
b
y
th
e
n
u
m
b
er
o
f
m
ar
k
s
m
o
r
e
th
an
o
n
e.
T
h
e
th
ir
d
s
tag
e
is
t
h
e
esti
m
at
io
n
o
f
t
h
e
ed
g
e
o
r
co
n
to
u
r
o
f
ea
ch
w
h
ite
b
lo
o
d
ce
ll
ar
ea
o
f
s
in
g
le
an
d
o
v
er
lap
p
in
g
w
h
i
te
b
lo
o
d
ce
lls
,
s
o
th
e
o
u
tp
u
t
f
r
o
m
t
h
i
s
s
ta
g
e
s
h
o
w
s
t
h
e
r
es
u
lts
o
f
th
e
s
ep
ar
atio
n
o
f
ea
c
h
ce
ll i
n
t
h
e
ar
ea
o
f
o
v
er
lap
p
in
g
w
h
ite
b
lo
o
d
ce
lls
.
2
.
1
.
Descript
io
n o
f
t
he
m
icro
s
co
p
ic
da
t
a
s
et
o
f
a
cut
e
leuk
e
m
ia
i
m
a
g
es
T
h
e
d
ataset
u
s
ed
is
t
h
e
m
ic
r
o
s
co
p
ic
i
m
ag
e
s
o
f
Acu
te
L
y
m
p
h
o
c
y
tic
L
eu
k
e
m
ia
(
AL
L
)
an
d
th
e
m
icr
o
s
co
p
ic
i
m
ag
e
o
f
A
c
u
te
M
y
elo
id
L
eu
k
e
m
ia
(
A
M
L
)
.
T
h
e
AL
L
i
m
ag
e
d
ataset
is
o
b
tain
ed
f
r
o
m
th
e
AL
L
-
I
DB
1
d
ataset
[
1
6
]
w
h
ic
h
is
t
h
e
p
er
ip
h
er
al
b
lo
o
d
s
m
ea
r
s
a
m
p
le
d
ataset
o
f
p
atie
n
ts
w
i
th
AL
L
an
d
n
o
n
-
AL
L
p
atien
ts
co
llected
at
t
h
e
T
ettam
aa
ti
R
esear
c
h
C
e
n
ter
r
esear
ch
ce
n
ter
,
Mo
n
za
,
I
tal
y
.
T
h
e
A
M
L
i
m
a
g
e
d
ataset
w
a
s
o
b
tain
ed
f
r
o
m
th
e
L
o
ca
l
Go
v
er
n
m
en
t
Hea
l
th
L
a
b
o
r
ato
r
y
o
f
So
u
t
h
Kali
m
an
tan
,
B
an
j
ar
m
a
s
i
n
,
I
n
d
o
n
esia
[
1
7
]
.
T
h
e
n
u
m
b
er
o
f
b
lo
o
d
s
m
ea
r
s
a
m
p
les
u
s
ed
in
th
i
s
s
t
u
d
y
,
f
o
r
AL
L
i
m
ag
e
d
ata
i
s
3
1
s
a
m
p
les,
an
d
AM
L
i
m
a
g
e
d
ata
is
5
0
s
a
m
p
le
s
.
E
x
a
m
p
le
s
o
f
b
lo
o
d
s
m
ea
r
s
f
r
o
m
AL
L
an
d
A
M
L
i
m
a
g
e
d
a
ta
ca
n
b
e
s
ee
n
in
Fig
u
r
e
2
.
Fig
u
r
e
2
.
E
x
a
m
p
les o
f
b
lo
o
d
s
m
ea
r
ac
u
te
l
y
m
p
h
o
b
last
ic
le
u
k
e
m
ia
(
AL
L
)
an
d
ac
u
te
m
y
e
lo
id
leu
k
e
m
ia
(
A
M
L
)
i
m
ag
e
s
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
.
3
,
J
u
n
e
2
0
1
8
:
1
7
3
1
–
1740
1734
2
.
2
.
Seg
m
e
nta
t
io
n o
f
w
hite
blo
o
d c
ells
T
h
e
f
ir
s
t
s
ta
g
e
i
n
t
h
i
s
s
t
u
d
y
is
th
e
p
r
o
ce
s
s
o
f
s
eg
m
e
n
tatio
n
o
f
w
h
ite
b
lo
o
d
ce
lls
.
T
h
is
p
r
o
ce
s
s
ai
m
s
to
s
ep
ar
ate
th
e
ar
ea
o
f
w
h
ite
b
lo
o
d
ce
lls
w
ith
o
th
er
co
m
p
o
n
e
n
ts
s
u
c
h
as
r
ed
b
lo
o
d
ce
lls
an
d
b
ac
k
g
r
o
u
n
d
.
Flo
w
d
iag
r
a
m
s
o
f
ex
i
s
ti
n
g
p
r
o
ce
s
s
e
s
at
th
e
s
ta
g
e
o
f
s
e
g
m
en
tatio
n
o
f
w
h
ite
b
lo
o
d
ce
lls
ca
n
b
e
s
ee
n
in
Fi
g
u
r
e
3
.
Fig
u
r
e
3.
E
x
a
m
p
le
s
ta
g
es o
f
s
e
g
m
e
n
tat
io
n
o
f
w
h
ite
b
lo
o
d
ce
lls
T
h
e
in
p
u
t
i
m
a
g
e
at
th
e
s
tag
e
o
f
w
h
ite
b
lo
o
d
ce
ll
s
eg
m
e
n
t
atio
n
is
a
m
icr
o
s
co
p
ic
i
m
a
g
e
o
f
ac
u
te
leu
k
e
m
ia,
th
e
n
tr
an
s
f
o
r
m
ed
f
r
o
m
t
h
e
R
GB
co
lo
r
s
p
ac
e
to
th
e
H
SV
co
lo
r
s
p
ac
e.
T
h
e
n
ex
t
p
r
o
ce
s
s
i
s
th
r
es
h
o
ld
in
g
u
s
i
n
g
Ots
u
m
et
h
o
d
to
g
et
th
e
o
b
j
ec
t
ar
ea
o
f
ce
lls
i
n
t
h
e
f
o
r
m
o
f
w
h
ite
b
lo
o
d
ce
lls
an
d
r
ed
b
lo
o
d
ce
lls
b
y
s
ep
ar
atin
g
th
e
ce
ll
o
b
j
ec
t
f
r
o
m
th
e
b
ac
k
g
r
o
u
n
d
.
T
h
e
r
esu
lt
o
f
th
e
t
h
r
esh
o
ld
i
n
g
p
r
o
ce
s
s
is
a
b
in
ar
y
i
m
a
g
e
w
i
th
o
n
l
y
t
w
o
co
m
p
o
n
en
ts
:
ce
ll
s
a
n
d
b
ac
k
g
r
o
u
n
d
.
T
h
e
b
i
n
ar
y
i
m
a
g
e
is
u
s
ed
as
a
m
as
k
to
o
b
tain
th
e
H
u
e
co
m
p
o
n
en
t
o
f
r
ed
an
d
w
h
ite
b
lo
o
d
ce
ll
o
b
j
ec
ts
in
t
h
e
H
SV
co
lo
r
s
p
ac
e.
T
o
d
eter
m
in
e
w
h
eth
er
th
e
ca
n
d
id
ate
o
f
a
ce
ll
o
b
j
ec
t
is
a
w
h
ite
b
lo
o
d
ce
ll
(
W
B
C
)
,
it
is
n
ec
es
s
ar
y
to
ch
ec
k
t
h
e
Hu
e
c
o
m
p
o
n
en
t
b
y
u
s
in
g
h
is
to
g
r
a
m
an
al
y
s
is
.
I
n
t
h
is
r
esear
ch
,
t
h
e
T
th
r
es
h
o
ld
v
al
u
e
f
o
r
AL
L
i
m
a
g
e
d
ata
i
s
d
if
f
e
r
en
t
f
r
o
m
t
h
e
A
M
L
i
m
a
g
e
d
ata
d
u
e
to
th
e
d
if
f
e
r
en
ce
o
f
l
ig
h
ti
n
g
an
d
t
h
e
s
t
ain
i
n
g
p
r
o
ce
s
s
.
I
n
t
h
e
AL
L
i
m
a
g
e,
i
f
t
h
e
H
u
e
co
m
p
o
n
e
n
t
i
s
less
t
h
an
t
h
e
T
v
alu
e
(
T
=
0
.
8
3
)
th
en
th
e
ce
ll
o
b
j
ec
t
is
a
w
h
ite
b
lo
o
d
ce
ll
(
W
B
C
)
ca
n
d
id
ate,
o
th
er
w
is
e
it
is
a
r
ed
b
lo
o
d
ce
l
l
(
R
B
C
)
.
W
h
ile
o
n
th
e
AM
L
i
m
ag
e,
i
f
th
e
H
u
e
co
m
p
o
n
e
n
t
i
s
s
m
al
ler
th
a
n
th
e
v
alu
e
o
f
T
,
w
h
ic
h
h
a
s
t
h
e
r
an
g
e
o
f
0
.
8
9
-
0
.
9
5
,
th
en
th
e
ce
ll
o
b
j
ec
t
is
a
w
h
ite
b
lo
o
d
ce
lls
(
W
B
C
)
,
o
th
er
w
is
e
i
t
is
a
r
ed
b
lo
o
d
ce
ll
(
R
B
C
)
.
T
h
e
n
ex
t
p
r
o
ce
s
s
is
to
r
e
m
o
v
e
o
b
j
ec
ts
th
at
ar
e
ca
teg
o
r
ized
as
n
o
is
e
a
n
d
r
e
m
o
v
e
o
b
j
ec
ts
th
at
ar
e
o
n
t
h
e
ed
g
e
o
f
t
h
e
i
m
a
g
e.
T
h
e
p
r
o
ce
s
s
o
f
r
e
m
o
v
i
n
g
t
h
e
n
o
is
e
o
b
j
ec
t
b
y
ca
lcu
lati
n
g
t
h
e
ar
ea
an
d
s
o
lid
it
y
o
f
t
h
e
o
b
j
ec
t
is
th
at
i
f
t
h
e
ce
ll
o
b
j
ec
t
is
less
t
h
an
A
an
d
t
h
e
s
o
lid
it
y
is
s
m
a
ller
th
a
n
S
t
h
en
th
e
o
b
j
ec
t
is
r
e
m
o
v
ed
.
I
n
th
is
r
ese
a
r
ch
,
th
er
e
ar
e
d
if
f
er
en
t
v
al
u
e
s
o
f
A
an
d
S
f
o
r
A
L
L
a
n
d
AM
L
i
m
a
g
es
b
e
ca
u
s
e
o
f
d
if
f
er
en
t
s
izes
o
f
AL
L
a
n
d
A
M
L
w
h
ite
b
lo
o
d
ce
lls
.
T
h
er
ef
o
r
,
th
is
s
tu
d
y
u
s
es
t
h
e
v
a
lu
e
o
f
A
=
2
0
0
0
f
o
r
AL
L
ce
ll
s
an
d
A
=
7
0
0
0
f
o
r
A
ML
ce
ll
s
s
i
n
ce
th
e
AL
L
ce
ll
s
ar
e
s
m
aller
t
h
an
t
h
e
A
M
L
ce
ll
s
.
W
h
ile
th
e
cr
iter
ia
f
o
r
th
e
s
o
lid
it
y
v
alu
e
i
s
s
m
a
l
ler
th
an
S,
th
e
r
esear
ch
u
s
ed
th
e
v
al
u
e
o
f
S
=
0
.
6
7
f
o
r
b
o
th
AL
L
an
d
A
M
L
i
m
a
g
es.
Nex
t,
ev
er
y
ce
ll
lo
ca
t
ed
o
n
t
h
e
i
m
a
g
e
ed
g
es
i
s
r
e
m
o
v
ed
s
i
n
ce
it
is
r
eg
ar
d
ed
as
an
i
m
p
er
f
ec
t
o
b
j
ec
t
o
f
th
e
ce
ll.
T
h
e
r
esu
lt
o
f
t
h
e
W
B
C
s
eg
m
e
n
tatio
n
s
tag
e
i
s
a
b
in
ar
y
i
m
ag
e
w
i
th
o
n
l
y
t
w
o
co
m
p
o
n
en
ts
,
t
h
e
W
B
C
o
b
j
ec
ts
,
an
d
th
e
b
ac
k
g
r
o
u
n
d
.
2
.
3
.
M
a
rk
er
det
ec
t
io
n a
nd
ca
lcul
a
t
io
n o
f
w
hite
blo
o
d c
ell
co
u
nt
T
h
e
s
ec
o
n
d
s
tag
e
in
t
h
i
s
s
t
u
d
y
is
m
ar
k
er
d
etec
tio
n
a
n
d
ca
lcu
latio
n
o
f
w
h
ite
b
lo
o
d
ce
ll
co
u
n
t.
T
h
e
in
p
u
t
i
n
th
is
s
ec
o
n
d
s
ta
g
e
is
a
b
in
ar
y
w
h
i
te
b
lo
o
d
ce
ll
im
ag
e
w
h
ic
h
is
t
h
e
r
esu
lt
o
f
s
e
g
m
e
n
tat
io
n
o
f
w
h
ite
b
lo
o
d
ce
lls
.
So
m
e
p
r
ev
io
u
s
s
tu
d
ies
g
e
n
er
all
y
ca
lcu
la
te
th
e
n
u
m
b
er
o
f
w
h
i
te
b
lo
o
d
ce
lls
(
W
B
C
)
b
ased
o
n
g
eo
m
etr
y
s
u
ch
a
s
ar
ea
,
s
o
lid
it
y
,
o
r
ec
ce
n
tr
icit
y
.
Ho
w
e
v
er
,
th
is
g
eo
m
e
tr
y
-
b
ased
m
et
h
o
d
is
a
co
n
s
tr
ai
n
t
if
a
s
in
g
le
ce
ll
ar
ea
is
al
m
o
s
t
t
h
e
s
a
m
e
as
t
h
e
o
v
er
lap
p
i
n
g
ar
ea
.
A
n
o
t
h
er
m
et
h
o
d
u
s
e
d
w
ater
s
h
ed
-
b
ased
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:
2
0
8
8
-
8708
A
u
to
ma
tic
Leu
ke
mia
C
ell
C
o
u
n
tin
g
u
s
in
g
I
tera
tive
Di
s
ta
n
ce
Tr
a
n
s
fo
r
m
fo
r
C
o
n
ve
x
…
(
N
en
d
en
S
iti F
a
to
n
a
h
)
1735
co
m
p
u
tatio
n
f
o
r
w
h
i
te
b
lo
o
d
ce
lls
,
b
u
t
th
e
n
u
m
b
er
o
f
ce
lls
is
s
till
n
o
t
ac
cu
r
ate
d
u
e
to
o
v
er
s
eg
m
e
n
tat
io
n
.
I
n
th
is
r
esear
c
h
,
th
e
m
eth
o
d
u
s
e
d
f
o
r
d
etec
tio
n
o
f
a
ce
ll
m
ar
k
er
is
b
ased
o
n
Dis
tan
ce
T
r
an
s
f
o
r
m
(
DT
)
b
ec
au
s
e
DT
ca
n
b
e
u
s
ed
to
d
etec
t
th
e
n
u
m
b
er
o
f
o
b
j
ec
ts
in
an
i
m
ag
e.
B
ased
o
n
th
e
p
r
ev
io
u
s
r
esea
r
ch
,
th
e
DT
m
et
h
o
d
is
v
er
y
g
o
o
d
f
o
r
m
ar
k
i
n
g
o
b
j
e
cts
o
f
th
e
s
a
m
e
s
ize
a
n
d
s
h
ap
e,
b
u
t
f
o
r
th
e
o
b
j
ec
ts
o
f
v
ar
iet
y
s
ize
s
a
n
d
s
h
ap
es,
th
e
DT
m
e
th
o
d
r
esu
l
ts
i
n
u
n
d
er
-
s
e
g
m
e
n
tat
io
n
o
r
o
v
er
-
s
e
g
m
e
n
tatio
n
[
1
5
]
.
T
h
is
s
t
u
d
y
p
r
o
p
o
s
es th
e
I
ter
ati
v
e
Di
s
ta
n
ce
T
r
an
s
f
o
r
m
f
o
r
C
o
n
v
e
x
Sets
(
I
DT
C
S)
m
e
th
o
d
b
y
r
ep
ea
tin
g
th
e
DT
p
r
o
ce
s
s
u
n
til
n
o
o
b
j
ec
t
is
lef
t
a
n
d
th
e
ce
ll
w
i
ll
b
e
m
ar
k
ed
i
f
th
e
s
ize
o
f
th
e
co
n
ca
v
e
is
les
s
th
a
n
t
h
e
th
r
es
h
o
ld
v
alu
e
(
ρ
)
.
T
h
e
co
n
ce
p
t
is
lik
e
in
th
e
m
et
h
o
d
o
f
Ulti
m
a
te
E
r
o
s
io
n
f
o
r
C
o
n
v
e
x
Sets
(
UE
C
S)
u
s
i
n
g
iter
ativ
e
p
r
o
ce
s
s
to
er
o
s
io
n
m
o
r
p
h
o
lo
g
y
p
r
o
ce
s
s
b
u
t
d
if
f
er
en
t
f
r
o
m
I
DT
C
S
m
et
h
o
d
to
DT
p
r
o
ce
s
s
.
T
h
e
ad
v
an
ta
g
e
o
f
u
s
i
n
g
th
i
s
iter
ati
v
e
tec
h
n
iq
u
e,
ev
er
y
to
u
ch
ed
c
ell
o
r
o
v
er
lap
p
in
g
ce
l
l
is
g
et
ti
n
g
s
m
aller
a
n
d
m
o
r
e
s
ep
ar
ated
b
y
u
s
i
n
g
th
e
co
n
ce
p
t
o
f
co
n
ca
v
it
y
.
DT
is
ca
lcu
l
ated
b
ased
o
n
t
h
e
d
is
tan
ce
o
f
ea
ch
p
i
x
el
to
th
e
n
ea
r
est n
o
n
-
ze
r
o
p
ix
el
u
s
in
g
t
h
e
E
u
clid
ea
n
d
is
t
a
n
ce
f
o
r
m
u
la
.
T
h
e
ca
lcu
latio
n
o
f
co
n
ca
v
it
y
i
s
as
i
n
[
1
4
]
,
[
1
8
]
b
y
u
s
in
g
E
q
u
atio
n
(
1
)
f
o
r
t
h
e
a
s
s
u
m
p
tio
n
I
is
t
h
e
s
et,
O
is
th
e
co
n
v
e
x
h
u
ll
o
f
I
.
V
is
th
e
d
if
f
er
e
n
ce
o
f
s
et
O
w
ith
s
et
I
,
V
is
th
e
co
n
ca
v
e
s
et
o
f
I
.
T
h
e
ch
o
r
d
o
f
Vj
is
th
e
s
lice
Vj
an
d
∂Ο,
w
h
ile
t
h
e
ar
c
o
f
Vj
is
th
e
s
lice
o
f
Vj
an
d
∂I
.
Su
p
p
o
s
e
th
at
th
er
e
is
a
s
et
o
f
V,
Vj
is
th
e
b
o
u
n
d
ar
y
o
f
th
e
s
et
to
j
th
e
n
th
e
s
ize
o
f
t
h
e
co
n
ca
v
i
t
y
c
(
V)
is
eq
u
al
to
t
h
e
lar
g
est
r
a
tio
o
f
th
e
d
is
ta
n
ce
b
et
w
ee
n
t
h
e
c
h
o
r
d
an
d
ar
c,
with
th
e
len
g
t
h
o
f
t
h
e
li
n
e
f
r
o
m
th
e
ch
o
r
d
.
T
h
e
v
ar
iab
le
d
is
t
h
e
lar
g
est
d
is
ta
n
ce
be
t
w
ee
n
ch
o
r
d
an
d
ar
c
ele
m
en
ts
.
T
h
e
v
ar
iab
le
l is th
e
le
n
g
th
o
f
th
e
c
h
o
r
d
lin
e.
(
)
(
)
(
)
(
1
)
T
h
e
alg
o
r
ith
m
o
f
I
ter
ativ
e
D
is
tan
ce
Dis
tan
ce
T
r
an
s
f
o
r
m
f
o
r
C
o
n
v
e
x
Se
t
(
I
DT
C
S)
m
et
h
o
d
is
a
s
f
o
llo
w
s
:
I
t
er
a
t
iv
e
Dis
t
a
nce
T
ra
ns
f
o
rm
F
o
r
Co
nv
ex
Set
(
I
D
T
CS)
Alg
o
rit
h
m
I
n
p
u
t: B
in
ar
y
s
il
h
o
u
et
te
i
m
a
g
e
Ou
tp
u
t: Ob
j
ec
t m
ar
k
er
(
M
)
P
ar
am
eter
:
d
is
ta
n
ce
tr
an
s
f
o
r
m
th
r
es
h
o
ld
an
d
co
n
ca
v
it
y
t
h
r
es
h
o
ld
.
1.
P
er
f
o
r
m
s
m
ar
t
f
illi
n
g
an
d
s
m
o
o
th
in
g
o
b
j
ec
t a
lg
o
r
ith
m
o
n
2.
I
n
itialize
(
)
3.
C
o
m
p
u
te
d
is
tan
ce
tr
a
n
s
f
o
r
m
o
f
(
)
an
d
n
o
r
m
alize
to
[
0
,
1
]
4.
C
r
ea
te
a
n
e
w
b
in
ar
y
i
m
ag
e
b
y
th
r
es
h
o
ld
in
g
th
e
i
m
a
g
e
u
s
i
n
g
5.
C
o
m
p
u
te
th
e
co
n
ca
v
it
y
o
f
all
o
b
j
ec
ts
.
6.
Ma
r
k
th
e
o
b
j
ec
t if
s
ize
o
f
t
h
e
c
o
n
ca
v
it
y
les
s
th
a
n
7.
R
ep
ea
t step
3
to
6
u
n
til
(
)
(
)
I
n
t
h
e
I
DT
C
S
a
lg
o
r
it
h
m
,
t
h
e
f
ir
s
t
p
r
o
ce
s
s
is
to
d
o
th
e
s
m
ar
t
f
i
lli
n
g
an
d
s
m
o
o
t
h
i
n
g
p
r
o
ce
s
s
t
h
at
ai
m
s
to
clo
s
e
th
e
s
m
all
h
o
le
i
n
th
e
ce
l
l
b
ec
au
s
e
t
h
e
p
r
o
ce
s
s
o
f
s
eg
m
e
n
ta
tio
n
o
f
w
h
ite
b
lo
o
d
ce
lls
is
n
o
t
p
er
f
ec
t
an
d
th
e
s
m
o
o
th
in
g
t
h
e
ed
g
e
s
o
f
w
h
it
e
b
lo
o
d
ce
lls
.
T
h
e
n
ex
t
p
r
o
ce
s
s
i
n
th
e
I
DT
C
S
al
g
o
r
ith
m
is
ca
lcu
la
tin
g
t
h
e
d
is
tan
ce
tr
a
n
s
f
o
r
m
a
n
d
t
h
en
n
o
r
m
al
ized
.
T
h
e
f
o
llo
w
in
g
p
r
o
ce
s
s
i
s
to
cr
ea
te
a
b
in
ar
y
i
m
a
g
e
f
r
o
m
t
h
e
r
es
u
lt
o
f
d
is
tan
ce
tr
a
n
s
f
o
r
m
w
i
th
t
h
e
t
h
r
esh
o
ld
ρ
1
.
C
a
lcu
la
te
all
o
b
j
ec
ts
w
it
h
t
h
e
co
n
ca
v
it
y
E
q
u
atio
n
(
1
)
an
d
m
ar
k
th
e
o
b
j
ec
t
if
t
h
e
s
ize
o
f
co
n
ca
v
it
y
is
s
m
a
ller
t
h
an
th
e
t
h
r
esh
o
ld
ρ
2
.
R
ep
ea
t
s
tep
s
3
-
6
u
n
t
il
n
o
o
b
j
ec
t
is
lef
t.
I
n
t
h
i
s
s
tu
d
y
,
t
h
e
v
al
u
es
ρ
1
an
d
ρ
2
u
s
ed
o
n
t
h
e
I
DT
C
S
alg
o
r
it
h
m
ar
e
0
.
2
an
d
0
.
1
5
.
S
m
ar
t
f
i
llin
g
a
n
d
s
m
o
o
t
h
in
g
alg
o
r
ith
m
u
s
ed
in
I
DT
C
S a
l
g
o
r
ith
m
is
as
f
o
llo
w
s
:
S
m
a
rt
F
ill
ing
a
nd
S
m
o
o
t
hin
g
Alg
o
rit
h
m
I
n
p
u
t:
B
in
ar
y
s
il
h
o
u
e
tte
i
m
ag
e
Ou
tp
u
t: B
in
ar
y
s
il
h
o
u
ette
i
m
a
g
e
1.
Set
=
i
m
f
ill(
,
'h
o
le'
)
;
2.
C
o
m
p
u
te
3.
C
alcu
late
m
ea
n
an
d
s
tan
d
ar
d
d
ev
iatio
n
o
f
all
o
b
j
ec
ts
in
b
ased
o
n
its
s
ize.
4.
Dele
te
all
o
b
j
ec
ts
w
ith
s
ize
les
s
th
a
n
th
e
s
u
m
m
atio
n
o
f
m
ea
n
an
d
s
tan
d
ar
d
d
ev
iatio
n
.
5.
C
o
m
p
u
te
6.
C
o
m
p
u
te
=
i
m
to
p
h
a
t(
,
s
tr
el(
„
d
i
s
k
‟
,
1
0
)
)
7.
C
o
m
p
u
te
P
r
o
ce
s
s
1
-
5
o
n
s
m
ar
t
f
i
lli
n
g
an
d
s
m
o
o
t
h
i
n
g
a
lg
o
r
it
h
m
is
a
f
illi
n
g
p
r
o
ce
s
s
t
h
at
ai
m
s
to
clo
s
e
th
e
ex
is
t
in
g
h
o
le
s
in
w
h
ite
b
lo
o
d
ce
lls
b
u
t
it
d
o
es
n
o
t
clo
s
e
t
h
e
h
o
le
s
b
et
w
ee
n
ce
ll
s
i
n
t
h
e
a
r
ea
o
f
w
h
ite
b
lo
o
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
3
,
J
u
n
e
2
0
1
8
:
1
7
3
1
–
1740
1736
ce
lls
th
at
ar
e
o
v
er
lap
p
in
g
.
W
h
ile
th
e
p
r
o
ce
s
s
6
-
7
is
a
s
m
o
o
th
in
g
p
r
o
ce
s
s
th
at
ai
m
s
to
s
m
o
o
t
h
th
e
ed
g
e
s
o
f
w
h
ite
b
lo
o
d
ce
lls
u
s
i
n
g
m
o
r
p
h
o
lo
g
ical
m
et
h
o
d
o
f
to
p
h
at.
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
3
.
1
.
E
x
peri
m
e
nta
l
re
s
ults
o
f
w
hite
blo
o
d c
ell
s
eg
m
e
nta
t
io
n
o
n a
cut
e
leuk
e
m
ia
i
m
a
g
es
T
h
e
f
ir
s
t
s
tag
e
o
f
th
i
s
s
t
u
d
y
w
as
th
e
s
e
g
m
e
n
tatio
n
o
f
wh
ite
b
lo
o
d
ce
lls
(
W
B
C
)
o
n
m
icr
o
s
co
p
ic
i
m
a
g
es o
f
A
c
u
te
L
y
m
p
h
o
c
y
tic
L
e
u
k
e
m
ia
(
A
L
L
)
a
n
d
A
c
u
te
M
y
elo
id
L
eu
k
e
m
ia
(
A
M
L
)
.
T
h
e
o
u
tp
u
t o
f
th
e
f
ir
s
t
s
tag
e
i
s
th
e
i
m
a
g
e
o
f
s
eg
m
e
n
tatio
n
o
f
w
h
ite
b
lo
o
d
ce
lls
th
at
s
h
o
w
s
th
e
s
ep
ar
atio
n
o
f
t
h
e
w
h
ite
b
lo
o
d
ce
ll
o
b
j
ec
t
s
w
ith
o
th
er
o
b
j
ec
t
s
.
T
h
e
r
esu
lt
s
o
f
ea
c
h
p
r
o
ce
s
s
i
n
t
h
is
s
ta
g
e
o
f
w
h
ite
b
lo
o
d
ce
ll
s
e
g
m
e
n
tat
io
n
ca
n
b
e
s
ee
n
i
n
Fi
g
u
r
e
4
an
d
Fi
g
u
r
e
5
.
Fig
u
r
e
4
s
h
o
w
s
t
h
e
r
es
u
lt
s
o
f
ea
ch
p
r
o
ce
s
s
in
t
h
e
f
ir
s
t
s
ta
g
e
o
f
a
n
AL
L
i
m
a
g
e
w
h
i
le
F
ig
u
r
e
5
s
h
o
w
s
th
e
re
s
u
lts
o
f
a
n
A
M
L
i
m
ag
e.
Fig
u
r
e
4
(
a)
an
d
Fig
u
r
e
5
(
a)
s
h
o
w
th
e
ac
u
te
le
u
k
e
m
ia
i
m
ag
es,
an
d
Fi
g
u
r
e
4
(
b
)
an
d
Fig
u
r
e
5
(
b
)
p
r
esen
t
th
e
tr
an
s
f
o
r
m
ed
i
m
a
g
es
u
s
in
g
th
e
H
u
e
Sat
u
r
atio
n
Va
l
u
e
(
HSV)
co
lo
r
s
p
ac
e.
Fig
u
r
e
4
(
c)
an
d
Fig
u
r
e
5
(
c)
s
h
o
w
t
h
e
r
e
s
u
l
t
s
o
f
t
h
e
th
r
e
s
h
o
ld
in
g
p
r
o
ce
s
s
to
s
ep
ar
ate
t
h
e
b
lo
o
d
ce
ll
o
b
j
ec
t
w
it
h
th
e
b
ac
k
g
r
o
u
n
d
.
T
h
e
n
ex
t
p
r
o
ce
s
s
g
ets
t
h
e
H
u
e
v
al
u
e
i
n
f
o
r
m
atio
n
o
n
t
h
e
b
lo
o
d
ce
ll
o
b
j
e
ct
an
d
th
e
r
esu
lts
ar
e
s
h
o
w
n
i
n
Fi
g
u
r
e
4
(
d
)
an
d
Fi
g
u
r
e
5
(
d
)
.
A
f
ter
th
at,
t
h
e
p
r
o
ce
s
s
o
f
o
b
tain
i
n
g
w
h
ite
b
lo
o
d
ce
ll
(
W
B
C
)
ca
n
d
id
ate
s
w
it
h
t
h
e
cr
iter
ia
o
f
Hu
e
v
al
u
e
less
th
a
n
th
e
t
h
r
esh
o
ld
(
T
)
g
iv
e
s
th
e
r
esu
lts
as
s
h
o
w
n
i
n
Fig
u
r
e
4
(
d
)
an
d
Fig
u
r
e
5
(
d
)
.
A
n
d
th
e
last
p
r
o
ce
s
s
at
th
is
s
tag
e
o
f
W
B
C
s
eg
m
en
tatio
n
is
r
e
m
o
v
i
n
g
t
h
e
n
o
i
s
e
(
s
m
all
o
b
j
ec
t)
an
d
th
e
o
b
j
ec
t o
n
th
e
ed
g
e
s
o
f
t
h
e
i
m
ag
e
a
n
d
th
e
r
es
u
lt
s
ar
e
g
i
v
en
by
F
ig
u
r
e
4
(
e)
an
d
Fig
u
r
e
5
(
e)
.
Fig
u
r
e
4.
R
esu
lts
o
f
ea
c
h
p
r
o
ce
s
s
i
n
th
e
s
e
g
m
e
n
tatio
n
s
tag
e
o
f
w
h
ite
b
lo
o
d
ce
lls
in
an
AL
L
i
m
ag
e
(
a)
AL
L
i
m
a
g
e
(
b
)
HSV
i
m
a
g
e
(
c)
T
h
r
esh
o
ld
in
g
(
d
)
Hu
e
v
al
u
e
o
n
b
l
o
o
d
ce
ll o
b
j
ec
t (
e)
W
B
C
AL
L
(
f
)
W
B
C
AL
L
Seg
m
en
tatio
n
Fig
u
r
e
5.
R
esu
lts
o
f
ea
c
h
p
r
o
ce
s
s
at
th
e
s
ta
g
e
o
f
w
h
ite
b
lo
o
d
ce
ll seg
m
e
n
tatio
n
i
n
t
h
e
A
M
L
i
m
ag
e
(
a)
Or
ig
in
al
A
M
L
i
m
a
g
e
(
b
)
HSV
i
m
a
g
e
(
c)
T
h
r
esh
o
ld
in
g
(
d
)
Hu
e
v
al
u
e
o
n
b
lo
o
d
ce
ll
o
b
j
ec
t (
e)
W
B
C
Ob
j
ec
t Can
d
id
ate
s
(
f
)
W
B
C
A
M
L
Se
g
m
en
ta
tio
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:
2
0
8
8
-
8708
A
u
to
ma
tic
Leu
ke
mia
C
ell
C
o
u
n
tin
g
u
s
in
g
I
tera
tive
Di
s
ta
n
ce
Tr
a
n
s
fo
r
m
fo
r
C
o
n
ve
x
…
(
N
en
d
en
S
iti F
a
to
n
a
h
)
1737
3
.
2
.
T
he
ex
peri
m
e
nta
l r
esu
lt
s
o
f
m
a
r
k
er
det
ec
t
io
n
o
n WB
C
o
v
er
la
pp
ing
i
n a
cut
e
leu
k
e
m
i
a
i
m
a
g
es
T
h
e
s
ec
o
n
d
s
tag
e
in
th
i
s
s
tu
d
y
w
a
s
m
ar
k
er
d
etec
tio
n
an
d
W
B
C
co
u
n
t
ca
lcu
latio
n
o
n
m
icr
o
s
co
p
ic
i
m
a
g
es
o
f
ac
u
te
le
u
k
e
m
ia.
T
h
is
r
esear
c
h
p
r
o
p
o
s
es
I
ter
ativ
e
Dis
tan
ce
T
r
an
s
f
o
r
m
Fo
r
C
o
n
v
e
x
Set
s
(
I
DT
C
S)
m
et
h
o
d
f
o
r
W
B
C
m
ar
k
er
d
etec
tio
n
.
T
h
e
r
esu
lt
o
f
ea
c
h
iter
atio
n
o
f
I
DT
C
S
m
et
h
o
d
f
o
r
m
ar
k
er
d
etec
tio
n
o
n
W
B
C
Ov
er
lap
p
in
g
ca
n
b
e
s
ee
n
in
Fig
u
r
e
6
.
Fig
u
r
e
6
.
E
x
a
m
p
le
o
f
a
r
es
u
lt
o
f
a
m
ar
k
er
d
etec
tio
n
(
Seed
p
o
in
t)
u
s
i
n
g
I
DT
C
S
m
et
h
o
d
(
a)
W
B
C
s
eg
m
e
n
tat
io
n
i
m
a
g
e
(
b
)
f
illi
n
g
i
m
a
g
e
(
c)
i
m
ag
e
o
f
d
if
f
er
en
ce
; (
d
)
th
e
co
m
b
in
ed
i
m
a
g
e
o
f
b
an
d
c;
(
e)
th
r
o
u
g
h
(
l)
th
e
it
er
atio
n
o
f
t
h
e
DT
p
r
o
ce
s
s
; (
m
)
r
esu
l
t o
f
m
ar
k
er
d
etec
tio
n
Usi
n
g
t
h
e
I
DT
C
S
m
et
h
o
d
,
Fig
u
r
e
6
s
h
o
w
s
t
h
at
t
h
e
m
ar
k
er
s
o
f
ea
ch
ce
l
l o
n
th
e
o
v
er
lap
p
in
g
W
B
C
ca
n
b
e
d
etec
ted
p
r
o
p
er
ly
.
T
h
e
m
et
h
o
d
is
n
a
m
ed
I
DT
C
S
b
ec
a
u
s
e
it
r
ep
ea
ts
t
h
e
DT
p
r
o
ce
s
s
u
n
t
il
n
o
o
b
j
ec
t
is
lef
t
an
d
th
e
ce
ll
w
ill b
e
m
ar
k
ed
if
th
e
s
ize
o
f
co
n
ca
v
it
y
i
s
les
s
t
h
an
t
h
e
t
h
r
es
h
o
ld
v
al
u
e.
I
DT
C
S
lo
o
p
r
esu
lts
ca
n
b
e
s
ee
n
i
n
Fi
g
u
r
e
6
(
e)
to
Fig
u
r
e
6
(
l)
.
I
n
th
is
r
esear
c
h
,
w
e
u
s
e
Di
s
tan
ce
T
r
an
s
f
o
r
m
w
it
h
t
h
r
es
h
o
ld
ρ
1
=
0
.
2
an
d
th
e
s
ize
o
f
co
n
ca
v
it
y
w
it
h
t
h
r
es
h
o
l
d
v
alu
e
ρ
2
=
0
.
1
5
.
I
n
t
h
is
s
t
u
d
y
,
th
e
r
es
u
lts
o
f
I
D
T
C
S
p
r
o
p
o
s
al
m
e
th
o
d
w
er
e
c
o
m
p
ar
ed
w
it
h
Dis
ta
n
ce
T
r
an
s
f
o
r
m
(
DT
)
an
d
Ulti
m
ate
E
r
o
s
io
n
Fo
r
C
o
n
v
ex
Sets
(
UE
C
S)
m
eth
o
d
.
A
n
ex
a
m
p
le
o
f
W
B
C
m
ar
k
er
d
etec
tio
n
test
r
e
s
u
l
ts
o
n
AL
L
i
m
a
g
es
u
s
in
g
DT
,
UE
C
S,
an
d
I
DT
C
S
m
e
th
o
d
s
ca
n
b
e
s
ee
n
i
n
Fi
g
u
r
e
7
.
E
x
a
m
p
l
es
o
f
W
B
C
m
ar
k
er
d
etec
tio
n
test
r
es
u
lts
o
n
A
M
L
i
m
a
g
es
u
s
i
n
g
DT
,
UE
C
S,
an
d
I
DT
C
S m
e
th
o
d
s
ca
n
b
e
s
ee
n
i
n
Fi
g
u
r
e
8
.
T
h
e
D
T
m
et
h
o
d
is
ex
ce
llen
t
f
o
r
m
ar
k
i
n
g
o
b
j
ec
ts
th
at
ar
e
g
en
er
all
y
t
h
e
s
a
m
e
s
ize.
B
u
t
in
F
i
g
u
r
e
7
(
b
)
o
f
th
e
AL
L
i
m
a
g
e,
t
h
e
r
es
u
lt
o
f
th
e
DT
m
et
h
o
d
is
u
n
d
er
s
e
g
m
e
n
t
d
u
e
to
th
e
s
h
ap
e
an
d
a
r
ea
o
f
th
e
d
i
f
f
er
e
n
t
ce
lls
.
W
h
er
ea
s
i
n
t
h
e
A
M
L
i
m
ag
e
d
ata
s
et
t
h
e
DT
m
eth
o
d
is
q
u
ite
s
u
cc
e
s
s
f
u
l
f
o
r
m
ar
k
e
r
d
etec
tio
n
b
ec
au
s
e
g
en
er
all
y
t
h
e
W
B
C
o
b
j
ec
ts
h
av
e
th
e
s
a
m
e
s
ize,
as
s
h
o
w
n
i
n
Fig
u
r
e
8
(
b
)
.
T
h
e
r
esu
lt
o
f
m
ar
k
er
d
etec
tio
n
u
s
i
n
g
UE
C
S
m
et
h
o
d
ca
n
b
e
s
ee
n
i
n
Fig
u
r
e
7
(
c)
an
d
Fig
u
r
e
8
(
c)
,
th
er
e
ar
e
m
o
r
e
o
v
er
s
e
g
m
e
n
t
a
tio
n
o
r
n
u
m
b
er
o
f
m
ar
k
er
s
i
s
g
r
ea
ter
t
h
an
t
h
e
ac
t
u
al
ce
ll n
u
m
b
er
.
Usi
n
g
t
h
e
I
DT
C
S
m
et
h
o
d
th
e
W
B
C
m
ar
k
er
d
etec
tio
n
r
es
u
lt
s
ar
e
m
o
r
e
ac
cu
r
ate
ev
e
n
i
n
o
v
er
lap
p
in
g
ce
lls
w
it
h
ce
l
l
s
ize
v
ar
iatio
n
as
in
Fi
g
u
r
e
7
(
d
)
an
d
Fig
u
r
e
8
(
d
)
.
I
t
ca
n
also
b
e
s
ee
n
f
r
o
m
th
e
co
m
p
ar
is
o
n
o
f
r
ec
ap
itu
latio
n
r
es
u
lt
o
f
m
ar
k
e
r
o
r
ce
ll
co
u
n
t
ca
lcu
lat
io
n
u
s
i
n
g
DT
,
UE
C
S
an
d
I
DT
C
S
m
eth
o
d
as
in
T
ab
le
1
an
d
T
ab
le
2
.
T
a
b
le
1
s
h
o
w
s
th
e
r
esu
l
ts
o
f
t
h
e
co
m
p
ar
is
o
n
o
f
th
e
ca
lc
u
lated
n
u
m
b
er
o
f
m
ar
k
er
s
o
n
ea
c
h
ce
ll
i
n
AL
L
i
m
ag
e
s
w
h
er
ea
s
T
ab
le
2
is
th
e
r
es
u
lt
s
f
o
r
th
e
A
M
L
i
m
a
g
e
s
.
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
.
3
,
J
u
n
e
2
0
1
8
:
1
7
3
1
–
1740
1738
Fig
u
r
e
7.
Dete
ctio
n
o
f
W
B
C
m
ar
k
er
s
u
s
in
g
DT
,
UE
C
S a
n
d
I
DT
C
S m
e
th
o
d
s
o
n
o
v
er
lap
p
i
n
g
AL
L
(
a)
A
L
L
o
r
ig
in
al
i
m
a
g
e
(
b
)
DT
m
ar
k
er
r
esu
lt
s
(
c)
UE
C
S
m
ar
k
er
r
esu
l
ts
(
d
)
m
ar
k
er
r
esu
lt
s
o
f
I
DT
C
S
Fig
u
r
e
8.
R
esu
lts
W
B
C
m
ar
k
e
r
d
etec
tio
n
u
s
i
n
g
DT
,
UE
C
S a
n
d
I
DT
C
S o
n
o
v
er
lap
p
in
g
A
M
L
(
a)
o
r
ig
in
al
i
m
a
g
e
A
M
L
,
(
b
)
th
e
r
esu
lt
s
o
f
th
e
DT
m
ar
k
er
,
(
c)
th
e
r
esu
lt
s
o
f
UE
C
S
m
ar
k
er
,
(
d
)
th
e
r
esu
l
ts
o
f
I
DT
C
S
m
ar
k
er
T
ab
le
1
.
C
o
m
p
ar
is
o
n
o
f
th
e
ca
lcu
lated
n
u
m
b
er
o
f
m
ar
k
er
s
o
n
ea
ch
ce
ll o
n
W
B
C
o
v
er
lap
p
in
g
o
n
AL
L
i
m
a
g
e
s
u
s
i
n
g
DT
,
UE
C
S a
n
d
I
DT
C
S
M
e
t
h
o
d
DT
U
EC
S
I
D
T
C
S
c
o
r
r
e
c
t
9
13
22
O
v
e
r
s
e
g
m
e
n
4
11
7
U
n
d
e
r
se
g
me
n
18
7
2
A
k
u
r
a
si
(
%)
0
.
2
9
0
.
4
1
0
.
7
0
I
n
T
ab
le
1
,
I
D
T
C
S
m
et
h
o
d
h
a
s
h
i
g
h
er
ac
cu
r
ac
y
th
a
n
t
h
e
r
esu
lt
o
f
DT
o
r
UE
C
S
m
e
th
o
d
.
T
h
e
I
DT
C
S
m
et
h
o
d
p
r
o
d
u
ce
s
th
e
s
a
m
e
n
u
m
b
er
o
f
m
ar
k
er
s
w
i
th
t
h
e
g
r
o
u
n
d
tr
u
th
o
f
2
2
im
a
g
es
o
f
3
0
AL
L
i
m
a
g
es
a
n
d
o
b
tain
s
a
n
ac
cu
r
ac
y
o
f
0
.
7
0
.
T
h
e
I
D
T
C
S
m
et
h
o
d
ca
n
d
etec
t
th
e
n
u
m
b
e
r
o
f
m
ar
k
er
s
clo
s
er
to
th
e
ac
tu
al
n
u
m
b
er
o
f
ce
lls
co
m
p
ar
ed
to
t
h
e
DT
an
d
UE
C
S
m
e
th
o
d
.
Si
m
ilar
to
t
h
e
UE
C
S
m
e
th
o
d
,
I
DT
C
S
m
et
h
o
d
is
m
o
r
e
lik
e
l
y
to
o
v
er
s
eg
m
e
n
t
th
a
n
u
n
d
er
s
e
g
m
e
n
t
u
n
li
k
e
th
e
DT
m
et
h
o
d
.
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:
2
0
8
8
-
8708
A
u
to
ma
tic
Leu
ke
mia
C
ell
C
o
u
n
tin
g
u
s
in
g
I
tera
tive
Di
s
ta
n
ce
Tr
a
n
s
fo
r
m
fo
r
C
o
n
ve
x
…
(
N
en
d
en
S
iti F
a
to
n
a
h
)
1739
T
ab
le
2
.
C
o
m
p
ar
is
o
n
o
f
ca
lcu
l
atio
n
r
esu
l
t o
f
ce
ll o
v
er
lap
p
in
g
n
u
m
b
er
o
n
A
M
L
i
m
a
g
e
u
s
i
n
g
DT
,
UE
C
S,
an
d
I
DT
C
S
M
e
t
h
o
d
DT
U
EC
S
I
D
T
C
S
c
o
r
r
e
c
t
42
25
48
O
v
e
r
s
e
g
m
e
n
1
24
2
U
n
d
e
r
se
g
me
n
7
1
0
A
k
u
r
a
si
(
%)
0
.
8
4
0
.
5
0
0
.
9
6
I
n
T
ab
le
2
,
I
DT
C
S
m
eth
o
d
al
s
o
h
a
s
h
ig
h
er
ac
c
u
r
ac
y
th
a
n
DT
o
r
UE
C
S
m
e
th
o
d
.
I
DT
C
S
m
et
h
o
d
ca
n
d
etec
t
m
ar
k
er
s
eq
u
al
to
th
e
g
r
o
u
n
d
t
h
r
u
t
h
o
f
4
8
i
m
a
g
es
f
r
o
m
5
0
i
m
ag
e
s
,
w
h
ile
DT
m
e
th
o
d
o
b
tain
s
a
s
m
u
ch
a
s
4
2
i
m
a
g
es
a
n
d
UE
C
S
o
b
tain
s
2
5
i
m
a
g
e
s
co
r
r
ec
tl
y
p
r
o
ce
s
s
ed
.
Fo
r
th
e
A
M
L
i
m
a
g
e
d
ataset,
t
h
e
test
r
esu
lts
s
h
o
w
n
o
u
n
d
er
s
e
g
m
en
t
a
tio
n
o
cc
u
r
r
ed
u
s
i
n
g
t
h
e
I
DT
C
S
m
et
h
o
d
.
T
h
e
test
r
es
u
lt
s
s
h
o
w
t
h
at
UE
C
S
m
et
h
o
d
is
m
o
r
e
lik
el
y
to
o
v
er
s
eg
m
e
n
t
o
n
W
B
C
m
ar
k
er
d
etec
tio
n
p
r
o
ce
s
s
w
h
ile
DT
m
eth
o
d
is
m
o
r
e
u
n
d
er
s
eg
m
en
t
.
4.
CO
NCLU
SI
O
N
I
n
t
h
is
p
ap
er
,
w
e
p
r
o
p
o
s
e
an
I
ter
ativ
e
D
is
ta
n
ce
T
r
an
s
f
o
r
m
f
o
r
C
o
n
v
e
x
Sets
(
I
DT
C
S)
m
eth
o
d
f
o
r
d
etec
tin
g
ce
l
l
m
ar
k
er
s
o
n
o
v
e
r
lap
p
in
g
w
h
ite
b
lo
o
d
ce
lls
(
W
B
C
)
.
T
h
e
I
D
T
C
S
m
eth
o
d
r
ep
ea
ts
th
e
DT
p
r
o
ce
s
s
u
n
t
il
n
o
o
b
j
ec
t
is
lef
t
an
d
th
e
ce
ll
w
i
ll
b
e
m
ar
k
ed
if
t
h
e
s
ize
o
f
co
n
ca
v
it
y
is
le
s
s
t
h
an
t
h
e
t
h
r
es
h
o
ld
v
alu
e
(
ρ
)
.
T
h
e
r
esu
lt
o
f
th
e
I
DT
C
S
m
eth
o
d
is
th
at
all
th
e
o
v
er
lap
p
in
g
o
b
j
ec
ts
ar
e
s
u
cc
ess
f
u
l
l
y
m
ar
k
ed
as
s
in
g
le
o
b
j
ec
ts
.
I
t
is
n
a
m
ed
I
DT
C
S
b
ec
a
u
s
e
t
h
e
p
r
o
ce
s
s
i
s
d
o
n
e
iter
at
iv
el
y
in
Di
s
ta
n
ce
T
r
an
s
f
o
r
m
m
et
h
o
d
to
g
et
a
m
ar
k
er
o
f
ea
ch
o
b
j
ec
t.
Fr
o
m
th
e
te
s
t
r
esu
lt
s
o
n
t
w
o
d
ataset
s
o
f
AL
L
an
d
A
M
L
i
m
a
g
es,
I
DT
C
S
m
e
th
o
d
h
as
h
ig
h
er
ac
cu
r
ac
y
t
h
a
n
DT
an
d
UE
C
S
m
et
h
o
d
.
T
h
e
I
D
T
C
S
m
et
h
o
d
o
b
tain
s
an
ac
cu
r
ac
y
o
f
0
.
7
0
f
o
r
AL
L
a
n
d
0
.
9
6
f
o
r
th
e
A
M
L
i
m
ag
e
s
.
W
h
ile
UE
C
S
h
as
an
ac
cu
r
ac
y
o
f
0
.
4
1
f
o
r
AL
L
i
m
ag
e
s
a
n
d
5
0
%
f
o
r
A
M
L
i
m
ag
e
s
.
DT
o
b
tain
ed
an
ac
c
u
r
ac
y
o
f
0
.
2
9
f
o
r
AL
L
a
n
d
0
.
8
4
f
o
r
AM
L
i
m
ag
es.
T
h
e
a
u
to
m
a
tic
ca
lc
u
latio
n
o
f
t
h
e
n
u
m
b
er
o
f
w
h
ite
b
lo
o
d
ce
lls
w
i
ll
ac
cu
r
at
el
y
s
u
p
p
o
r
t
th
e
d
o
cto
r
o
r
p
ath
o
lo
g
is
t
i
n
d
iag
n
o
s
in
g
t
h
e
lev
e
l
o
f
ac
u
te
le
u
k
e
m
i
a
d
is
ea
s
e.
T
h
e
n
ex
t
r
es
ea
r
ch
i
s
t
o
g
et
an
esti
m
ate
o
f
t
h
e
co
n
to
u
r
s
o
f
W
B
C
ce
ll
s
a
f
ter
s
ep
ar
atin
g
th
e
to
u
ch
ed
o
r
o
v
er
lap
p
in
g
ce
lls
i
n
o
r
d
er
t
o
o
b
tain
a
m
o
r
e
ac
cu
r
ate
ar
ea
a
n
d
f
o
r
m
o
f
w
h
i
te
b
lo
o
d
ce
lls
.
W
ith
an
ac
cu
r
ate
W
B
C
ar
ea
an
d
s
h
ap
e
it c
an
i
m
p
r
o
v
e
th
e
ac
cu
r
ac
y
o
f
th
e
ac
u
t
e
l
eu
k
e
m
ia
cla
s
s
i
f
icatio
n
p
r
o
ce
s
s
.
RE
F
E
R
E
NC
E
S
[1
]
Na
ti
o
n
a
l
Ca
n
c
e
r
In
stit
u
te,
“
W
h
a
t
Yo
u
Ne
e
d
T
o
Kn
o
w
A
b
o
u
t
L
e
u
k
e
m
ia,”
U.S
.
De
p
a
rtme
n
t
o
f
He
a
lt
h
a
n
d
Hu
m
a
n
S
e
rv
ice
s
,
2
0
1
3
.
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
:/
/
d
o
c
p
lay
e
r.
n
e
t/
3
2
7
0
3
0
7
4
-
W
h
a
t
-
y
o
u
-
n
e
e
d
-
to
-
k
n
o
w
-
a
b
o
u
t
-
l
e
u
k
e
m
ia.h
tm
l.
[2
]
M
.
M
y
e
lo
m
a
,
R.
S
.
Ril
e
y
,
a
n
d
D.
P
h
,
“
L
e
u
k
e
m
ia &
M
u
lt
ip
le M
y
e
lo
m
a
,
”
n
o
.
8
0
4
,
1
9
9
9
.
[3
]
M
.
U.
A
k
r
a
m
,
I.
Ja
m
a
l,
a
n
d
A
.
T
a
riq
,
“
Blo
o
d
V
e
ss
e
l
En
h
a
n
c
e
m
e
n
t
a
n
d
S
e
g
m
e
n
tatio
n
f
o
r
S
c
re
e
n
in
g
o
f
Dia
b
e
ti
c
Re
ti
n
o
p
a
t
h
y
,
”
v
o
l.
1
0
,
n
o
.
2
,
p
p
.
3
2
7
-
3
3
4
,
2
0
1
2
.
[4
]
H.
T
jan
d
ra
sa
,
A
.
W
ij
a
y
a
n
ti
,
a
n
d
N.
S
u
c
iati,
“
Op
ti
c
Ne
rv
e
He
a
d
S
e
g
m
e
n
tatio
n
Us
in
g
Ho
u
g
h
T
ra
n
sfo
rm
a
n
d
A
c
ti
v
e
Co
n
t
o
u
rs,” v
o
l
.
1
0
,
n
o
.
3
,
p
p
.
5
3
1
-
5
3
6
,
2
0
1
2
.
[5
]
R.
S
u
p
r
iy
a
n
ti
,
A
.
Ch
risa
n
ty
,
Y.
Ra
m
a
d
h
a
n
i,
a
n
d
W
.
S
isw
a
n
d
a
ri,
“
Co
m
p
u
ter
A
id
e
d
Dia
g
n
o
sis
f
o
r
S
c
re
e
n
in
g
th
e
S
h
a
p
e
a
n
d
S
ize
o
f
L
e
u
k
o
c
y
t
e
Ce
ll
Nu
c
leu
s b
a
se
d
o
n
M
o
r
p
h
o
lo
g
ica
l
Im
a
g
e
,
”
v
o
l.
8
,
n
o
.
1
,
p
p
.
1
5
0
-
1
5
8
,
2
0
1
8
.
[6
]
L
.
P
u
tzu
,
G
.
Ca
o
c
c
i,
a
n
d
C
.
Di
R
u
b
e
rto
,
“
L
e
u
c
o
c
y
t
e
c
las
si
f
ica
ti
o
n
f
o
r
leu
k
a
e
m
ia
d
e
tec
ti
o
n
u
s
i
n
g
ima
g
e
p
ro
c
e
ss
in
g
tec
h
n
iq
u
e
s,”
Arti
f.
I
n
tell.
M
e
d
.
,
v
o
l.
6
2
,
n
o
.
3
,
p
p
.
1
7
9
-
1
9
1
,
2
0
1
4
.
[7
]
V
.
Os
u
n
a
-
En
c
iso
,
E.
C
u
e
v
a
s,
a
n
d
H.
S
o
ss
a
,
“
A
c
o
m
p
a
riso
n
o
f
n
a
tu
re
in
sp
ired
a
lg
o
rit
h
m
s
f
o
r
m
u
lt
i
-
th
re
sh
o
l
d
im
a
g
e
se
g
m
e
n
tatio
n
,
”
Ex
p
e
rt S
y
st.
A
p
p
l.
,
v
o
l.
4
0
,
n
o
.
4
,
p
p
.
1
2
1
3
-
1
2
1
9
,
2
0
1
3
.
[8
]
D.
Hu
a
n
g
,
K.
Hu
n
g
,
a
n
d
Y.
Ch
a
n
,
“
T
h
e
Jo
u
rn
a
l
o
f
S
y
ste
m
s an
d
S
o
f
tw
a
r
e
A
c
o
m
p
u
ter as
siste
d
m
e
th
o
d
f
o
r
leu
k
o
c
y
te
n
u
c
leu
s se
g
m
e
n
tatio
n
a
n
d
re
c
o
g
n
i
ti
o
n
in
b
l
o
o
d
sm
e
a
r
i
m
a
g
e
s,”
J
.
S
y
st.
S
o
ft
w
.
,
v
o
l
.
8
5
,
n
o
.
9
,
p
p
.
2
1
0
4
-
2
1
1
8
,
2
0
1
2
.
[9
]
S
.
H.
Re
z
a
to
f
ig
h
i
a
n
d
H.
S
o
lt
a
n
i
a
n
-
Zad
e
h
,
“
A
u
to
m
a
ti
c
re
c
o
g
n
it
io
n
o
f
f
iv
e
t
y
p
e
s
o
f
w
h
it
e
b
lo
o
d
c
e
ll
s
in
p
e
ri
p
h
e
ra
l
b
lo
o
d
,
”
C
o
mp
u
t.
M
e
d
.
Ima
g
in
g
G
ra
p
h
.
,
v
o
l.
3
5
,
n
o
.
4
,
p
p
.
3
3
3
-
3
4
3
,
2
0
1
1
.
[1
0
]
C.
F
a
ti
c
h
a
h
,
M
.
L
.
T
a
n
g
e
l,
M
.
R.
W
id
y
a
n
to
,
F
.
Do
n
g
,
a
n
d
K.
Hiro
t
a
,
“
In
tere
st
-
b
a
se
d
o
rd
e
rin
g
f
o
r
f
u
z
z
y
m
o
rp
h
o
lo
g
y
o
n
w
h
it
e
b
lo
o
d
c
e
ll
im
a
g
e
se
g
m
e
n
tatio
n
,
”
J
.
A
d
v
.
Co
m
p
u
t
.
In
tell.
I
n
tell.
I
n
fo
rm
a
ti
c
s
,
v
o
l.
1
6
,
n
o
.
1
,
p
p
.
7
6
-
8
6
,
2
0
1
2
.
[1
1
]
F
.
S
c
o
tt
i,
“
Ro
b
u
st
se
g
m
e
n
tatio
n
a
n
d
m
e
a
su
re
m
e
n
ts
te
c
h
n
iq
u
e
s
o
f
w
h
it
e
c
e
ll
s
in
b
lo
o
d
m
icro
sc
o
p
e
im
a
g
e
s,”
Co
n
f.
Rec
.
-
IEE
E
I
n
stru
m.
M
e
a
s.
T
e
c
h
n
o
l.
Co
n
f.
,
n
o
.
A
p
ril
,
p
p
.
4
3
-
4
8
,
2
0
0
6
.
[1
2
]
S
.
Na
z
li
b
il
e
k
,
D.
Ka
ra
c
o
r,
T
.
Erca
n
,
M
.
H.
S
a
z
li
,
O.
Ka
len
d
e
r,
a
n
d
Y.
Eg
e
,
“
A
u
to
m
a
ti
c
se
g
m
e
n
tatio
n
,
c
o
u
n
ti
n
g
,
siz
e
d
e
term
in
a
ti
o
n
a
n
d
c
las
sif
ica
ti
o
n
o
f
w
h
it
e
b
lo
o
d
c
e
ll
s,”
M
e
a
s.
J
.
I
n
t.
M
e
a
s.
Co
n
fed
.
,
v
o
l
.
5
5
,
p
p
.
5
8
-
6
5
,
2
0
1
4
.
[1
3
]
C.
F
a
ti
c
h
a
h
,
D.
P
u
rw
it
a
sa
ri,
V
.
H
a
riad
i,
a
n
d
F
.
Ef
fe
n
d
y
,
“
O
v
e
rlap
p
in
g
W
h
it
e
Blo
o
d
Ce
ll
S
e
g
m
e
n
tatio
n
a
n
d
,
”
v
o
l
.
7
,
n
o
.
3
,
p
p
.
1
2
7
1
-
1
2
8
6
,
2
0
1
4
.
[1
4
]
C.
P
a
rk
,
J.
Z.
Hu
a
n
g
,
J.
X
.
J
i,
a
n
d
S
.
M
e
m
b
e
r,
“
S
e
g
m
e
n
tatio
n
,
I
n
f
e
re
n
c
e
,
a
n
d
Clas
si
f
ic
a
ti
o
n
o
f
P
a
rti
a
ll
y
Ov
e
rlap
p
in
g
Na
n
o
p
a
rti
c
les
,
”
IEE
E
T
ra
n
s.
P
a
tt
e
rn
A
n
a
l
.
M
a
c
h
.
In
t
e
ll
.
,
v
o
l.
3
5
,
n
o
.
3
,
p
p
.
6
6
9
-
6
8
1
,
2
0
1
3
.
[1
5
]
S
.
Zaf
a
ri,
“
S
e
g
m
e
n
tatio
n
o
f
Ov
e
rlap
p
in
g
Co
n
v
e
x
Ob
jec
ts,
”
L
a
p
p
e
e
n
ra
n
ta
Un
iv
e
rsity
o
f
Tec
h
n
o
l
o
g
y
S
c
h
o
o
l
o
f
In
d
u
strial
En
g
i
n
e
e
rin
g
a
n
d
M
a
n
a
g
e
m
e
n
t
De
g
r
e
e
P
ro
g
ra
m
in
Co
m
p
u
ter S
c
ien
c
e
,
2
0
1
4
.
[1
6
]
R.
D.
L
a
b
a
ti
,
V.
P
i
u
ri,
a
n
d
F
.
S
c
o
tt
i,
“
A
ll
-
IDB:
T
h
e
a
c
u
te
ly
m
p
h
o
b
las
ti
c
leu
k
e
m
ia
i
m
a
g
e
d
a
t
a
b
a
se
f
o
r
i
m
a
g
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
.
3
,
J
u
n
e
2
0
1
8
:
1
7
3
1
–
1740
1740
p
ro
c
e
ss
in
g
,
”
2
0
1
1
1
8
th
IEE
E
I
n
t.
Co
n
f.
Ima
g
e
Pro
c
e
ss
.
,
p
p
.
2
0
4
5
-
2
0
4
8
,
2
0
1
1
.
[1
7
]
D.
A
r
y
o
,
“
T
o
u
c
h
e
d
W
h
it
e
Bl
o
o
d
Ce
ll
s
S
e
g
m
e
n
tatio
n
a
n
d
S
e
p
a
ra
ti
o
n
u
sin
g
K
-
M
e
a
n
s
M
e
t
h
o
d
a
n
d
Hie
ra
rc
h
ica
l
Clu
ste
rin
g
A
n
a
l
y
sis o
n
A
c
u
te M
y
e
lo
id
L
e
u
m
e
k
i
a
I
m
a
g
e
,
”
In
stit
u
t
T
e
k
n
o
lo
g
i
S
e
p
u
lu
h
No
p
e
m
b
e
r,
2
0
1
6
.
[1
8
]
A
.
Ro
se
n
f
e
ld
,
“
M
e
a
su
rin
g
th
e
siz
e
s o
f
c
o
n
c
a
v
it
ie
s,
”
v
o
l.
3
,
Ja
n
u
a
ry
,
p
p
.
7
1
-
7
5
,
1
9
8
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.