I
AE
S
I
nte
rna
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
7
,
No
.
2
,
J
u
n
e
201
8
,
p
p
.
71
~
77
I
SS
N:
2252
-
8938
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ai.
v
7
.
i2
.
p
p
7
1
-
77
71
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
JA
I
O
pti
m
i
z
a
tion o
f
Dig
ital H
is
topa
th
o
lo
g
y
Im
a
g
e
Q
ua
l
ity
F
ura
t
N.
T
a
w
f
ee
q
1
,
N
a
da
A.
S.
Alw
a
n
2
,
B
a
s
i
m
M
.
K
ha
s
h
m
a
n
3
Na
ti
o
n
a
l
Ca
n
c
e
r
Re
se
a
rc
h
Ce
n
ter,
Un
iv
e
rsity
o
f
Ba
g
h
d
a
d
,
Ira
q
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
1
3
,
2
0
1
8
R
ev
i
s
ed
A
p
r
1
8
,
2
0
1
8
A
cc
ep
ted
Ma
y
2
1
,
2
0
1
8
On
e
o
f
th
e
b
i
o
m
e
d
ica
l
ima
g
e
p
r
o
b
lem
s
is
th
e
a
p
p
e
a
ra
n
c
e
o
f
th
e
b
u
b
b
les
i
n
th
e
slid
e
t
h
a
t
c
o
u
ld
o
c
c
u
r
w
h
e
n
a
ir
p
a
ss
e
s
th
r
o
u
g
h
t
h
e
slid
e
d
u
ri
n
g
th
e
p
re
p
a
ra
ti
o
n
p
ro
c
e
ss
.
T
h
e
se
b
u
b
b
l
e
s
m
a
y
c
o
m
p
li
c
a
te
th
e
p
ro
c
e
ss
o
f
a
n
a
l
y
sin
g
th
e
h
ist
o
p
a
t
h
o
l
o
g
ica
l
im
a
g
e
s.
A
i
m
s:
T
h
e
o
b
jec
ti
v
e
o
f
th
is
stu
d
y
is
to
re
m
o
v
e
th
e
b
u
b
b
le
n
o
ise
f
ro
m
th
e
h
ist
o
p
a
th
o
l
o
g
y
i
m
a
g
e
s,
a
n
d
th
e
n
p
re
d
ict
th
e
ti
ss
u
e
s
th
a
t
u
n
d
e
rli
e
it
u
sin
g
t
h
e
f
u
z
z
y
c
o
n
tro
ll
e
r
in
c
a
se
s
o
f
re
m
o
te
p
a
th
o
l
o
g
ica
l
d
iag
n
o
sis.
M
e
th
o
d
s:
F
u
z
z
y
lo
g
ic
u
se
s
th
e
li
n
g
u
isti
c
d
e
f
in
it
io
n
to
re
c
o
g
n
ize
th
e
re
latio
n
sh
i
p
b
e
tw
e
e
n
th
e
i
n
p
u
t
a
n
d
th
e
a
c
ti
v
it
y
,
ra
th
e
r
th
a
n
u
si
n
g
d
if
f
icu
lt
n
u
m
e
rica
l
e
q
u
a
ti
o
n
.
M
a
in
ly
th
e
re
a
re
f
i
v
e
p
a
rts,
sta
rti
n
g
w
it
h
a
c
c
e
p
ti
n
g
th
e
im
a
g
e
,
p
a
s
sin
g
th
ro
u
g
h
re
m
o
v
in
g
th
e
b
u
b
b
les
,
a
n
d
e
n
d
i
n
g
w
it
h
p
re
d
ict
th
e
ti
ss
u
e
s.
T
h
e
se
w
e
r
e
i
m
p
le
m
e
n
ted
b
y
d
e
f
in
in
g
m
e
m
b
e
rsh
ip
f
u
n
c
ti
o
n
s
b
e
twe
e
n
c
o
lo
u
rs
ra
n
g
e
u
sin
g
M
A
TL
A
B.
Re
su
lt
s:
5
0
h
ist
o
p
a
t
h
o
l
o
g
ica
l
ima
g
e
s
we
re
tes
ted
o
n
f
o
u
r
ty
p
e
s
o
f
m
e
m
b
e
r
sh
ip
f
u
n
c
ti
o
n
s
(
M
F
);
th
e
re
su
l
ts
sh
o
w
th
a
t
(n
in
e
-
tri
a
n
g
u
lar)
M
F
g
e
t
7
5
.
4
%
c
o
rre
c
tl
y
p
re
d
icte
d
p
ix
e
ls
v
e
rsu
s
6
9
.
1
,
7
2
.
3
1
a
n
d
7
2
%
f
o
r
(f
iv
e
-
tri
a
n
g
u
lar
),
(f
iv
e
-
Ga
u
ss
ian
)
a
n
d
(
n
in
e
-
G
a
u
ss
ian
)
re
sp
e
c
ti
v
e
l
y
.
Co
n
c
lu
sio
n
s:
I
n
l
in
e
w
it
h
t
h
e
e
ra
o
f
d
ig
it
a
ll
y
d
riv
e
n
e
-
p
a
th
o
lo
g
y
,
th
is
p
ro
c
e
ss
is
e
ss
e
n
ti
a
ll
y
re
c
o
m
m
e
n
d
e
d
to
e
n
su
re
q
u
a
li
ty
in
terp
re
tatio
n
a
n
d
a
n
a
l
y
se
s
o
f
th
e
p
ro
c
e
ss
e
d
slid
e
s;
th
u
s
o
v
e
rc
o
m
in
g
re
le
v
a
n
t
li
m
it
a
ti
o
n
s
.
K
ey
w
o
r
d
:
A
r
te
f
ac
ts
B
u
b
b
le
ef
f
ec
t
s
E
-
p
ath
o
lo
g
y
Fu
zz
y
co
n
tr
o
ller
P
ix
el
p
r
ed
ictio
n
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
:
Fu
r
at
N.
T
a
w
f
ee
q
,
Natio
n
al
C
a
n
ce
r
R
e
s
ea
r
ch
C
e
n
ter
,
Un
i
v
er
s
i
y
o
f
B
ag
h
d
ad
,
B
ab
A
l
-
M
u
ad
u
m
,
B
ag
h
d
ad
,
I
r
aq
,
E
m
ail:
f
u
r
at
n
id
h
al@
y
a
h
o
o
.
co
m
1.
I
NT
RO
D
UCT
I
O
N
His
to
p
ath
o
lo
g
y
is
th
e
f
ield
w
h
ic
h
s
t
u
d
ies
t
h
e
d
is
ea
s
ed
tis
s
u
es,
t
h
at
is
co
m
p
o
s
ed
o
f
t
h
r
ee
Gr
ee
k
ter
m
s
:
h
is
to
s
,
p
ath
o
s
a
n
d
lo
g
ia,
w
h
ic
h
m
ea
n
s
“st
u
d
y
i
n
g
d
is
ea
s
es
s
u
f
f
er
i
n
g
ti
s
s
u
e”
[
1
]
.
T
h
e
p
ath
o
lo
g
y
lab
r
ec
eiv
es
t
h
e
b
io
p
s
y
t
h
at
w
as
tak
en
f
r
o
m
th
e
p
atie
n
ts
,
w
h
ich
ar
e
th
en
s
tai
n
ed
,
p
lace
d
o
n
g
las
s
s
lid
es
to
h
ig
h
li
g
h
t p
ar
ticu
lar
s
tr
u
ct
u
r
es
[
2
]
.
T
h
e
s
lid
es
ar
e
u
s
u
al
l
y
m
o
u
n
t
ed
o
n
t
h
e
t
is
s
u
e
s
ec
tio
n
s
u
s
in
g
m
o
u
n
ti
n
g
m
ed
ia
to
p
r
o
tect
th
e
s
tai
n
ed
s
lid
es
f
r
o
m
d
a
m
ag
e.
D
u
r
in
g
t
h
at
p
r
o
ce
s
s
,
ar
tef
ac
ts
m
a
y
ap
p
ea
r
an
d
af
f
ec
t
t
h
e
s
tai
n
in
g
r
es
u
lts
.
T
h
ese
ar
tef
ac
t
s
m
a
y
b
e
an
y
s
tr
u
ctu
r
e
t
h
at
m
u
s
t
n
o
t
b
e
p
r
esen
t
in
t
h
e
tis
s
u
e
n
o
r
m
all
y
[
3
]
.
A
r
te
f
ac
ts
m
a
y
alter
th
e
i
m
p
o
r
tan
t
m
o
r
p
h
o
lo
g
ic
a
n
d
c
y
to
lo
g
ica
l
f
ea
t
u
r
es
o
f
t
h
e
ce
ll
s
lead
i
n
g
i
n
s
o
m
eti
m
es
to
co
m
p
le
te
o
b
s
cu
r
e
o
f
t
h
e
i
m
ag
e.
A
ir
b
u
b
b
les o
cc
u
r
eit
h
er
d
u
r
in
g
tis
s
u
e
f
lo
ati
n
g
i
n
t
h
e
w
ater
b
ath
o
r
d
u
r
in
g
co
v
er
in
g
[
4
]
.
Fo
llo
w
i
n
g
t
h
e
er
a
o
f
e
p
ath
o
l
o
g
y
,
a
n
d
alo
n
g
w
it
h
th
e
p
io
n
e
er
in
g
i
n
itiati
v
es
o
f
p
ath
o
lo
g
is
t
s
w
h
o
ar
e
u
s
i
n
g
d
ig
i
tal
i
m
a
g
i
n
g
s
y
s
te
m
s
,
in
t
h
i
s
p
ap
er
,
w
e
h
a
v
e
f
o
cu
s
ed
o
n
r
e
m
o
v
i
n
g
th
e
air
b
u
b
b
les
t
h
at
d
is
to
r
t
t
h
e
v
is
io
n
ac
cu
r
ac
y
a
n
d
th
u
s
i
m
p
ed
e
s
lid
e
in
ter
p
r
etatio
n
.
Dig
it
al
p
ath
o
lo
g
y
is
c
u
r
r
en
tl
y
co
n
s
id
er
ed
a
v
er
y
u
s
e
f
u
l
aid
in
ass
i
s
ti
n
g
d
ia
g
n
o
s
is
o
f
s
u
s
p
ec
ted
ca
s
es a
n
d
en
ab
li
n
g
ex
ch
an
g
e
o
f
r
e
m
o
te
co
n
s
u
ltatio
n
s
a
m
o
n
g
s
p
ec
ial
is
t
s
all
o
v
er
th
e
w
o
r
ld
[
5
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
7
,
No
.
2
,
J
u
n
e
20
1
8
:
71
–
77
72
Ma
n
y
P
r
o
b
lem
s
f
ac
ed
t
h
e
p
ath
o
lo
g
is
ts
d
u
r
in
g
t
h
eir
w
o
r
k
;
o
n
e
o
f
th
e
m
i
s
t
h
e
ap
p
ea
r
an
ce
o
f
b
u
b
b
le
in
th
e
d
ig
ita
l
i
m
a
g
e
s
lid
e.
T
h
e
o
b
j
ec
tiv
e
o
f
th
is
p
ap
er
is
to
d
esig
n
s
o
f
t
w
ar
e
f
o
r
r
em
o
v
i
n
g
t
h
is
ar
tef
ac
t
an
d
p
r
ed
ict
th
e
u
n
d
er
l
y
i
n
g
tis
s
u
e.
T
h
e
m
ain
b
en
e
f
it
o
f
f
u
zz
y
lo
g
ic
i
s
c
h
ar
ac
ter
ized
in
h
a
v
i
n
g
th
e
ab
ili
t
y
to
co
n
tr
o
l
n
o
n
li
n
e
ar
s
y
s
te
m
,
w
h
ic
h
w
o
u
ld
b
e
tr
o
u
b
leso
m
e
to
d
e
m
o
n
s
tr
ate
n
u
m
er
icall
y
[
6
]
.
Fu
zz
y
co
n
tr
o
l
tech
n
iq
u
e
s
ar
e
r
ep
r
esen
ted
b
y
a
m
atter
o
f
f
ac
t
an
d
tr
ials
in
s
tea
d
o
f
m
at
h
e
m
atica
l
m
o
d
el
s
.
Fu
zz
y
co
n
tr
o
l
s
y
s
te
m
s
in
c
lu
d
e
a
n
ex
te
n
s
i
v
e
n
u
m
b
er
o
f
i
n
p
u
t
s
;
m
o
s
t
ar
e
r
elate
d
to
s
o
m
e
co
n
d
itio
n
s
w
h
ic
h
ar
e
co
n
d
u
cted
w
h
e
n
t
h
e
r
elate
d
co
n
d
itio
n
is
tr
i
g
g
er
ed
.
A
cc
o
r
d
in
g
l
y
,
m
i
n
i
m
al
e
x
tr
a
co
m
p
u
tat
io
n
al
b
u
r
d
en
i
s
n
ee
d
ed
to
ac
co
m
m
o
d
ate
ad
d
itio
n
al
r
u
l
es [
7
]
.
T
h
e
f
u
zz
y
co
n
tr
o
ller
h
as
f
o
u
r
p
r
i
m
ar
y
p
ar
ts
a
s
s
h
o
w
n
i
n
Fi
g
u
r
e
1
:
s
tar
ti
n
g
w
it
h
"
r
u
le
-
b
a
s
e"
w
h
ic
h
h
o
ld
s
th
e
in
f
o
r
m
at
io
n
,
as
a
n
ar
r
an
g
e
m
en
t
o
f
r
u
les,
o
n
t
h
e
b
est
w
a
y
to
co
n
tr
o
l
th
e
s
y
s
te
m
.
T
h
e
"
in
f
er
en
ce
m
ec
h
a
n
i
s
m
"
as
s
es
s
es
w
h
ic
h
co
n
tr
o
l
r
u
les
ar
e
s
i
g
n
i
f
ica
n
t
at
th
e
cu
r
r
e
n
t
ti
m
e,
a
n
d
late
r
o
n
ch
o
o
s
e
s
w
h
a
t
co
n
tr
ib
u
tio
n
o
u
g
h
t
to
b
e
p
lan
n
ed
.
T
h
e
“f
u
zz
i
f
icatio
n
”
i
n
t
er
f
ac
e
ch
a
n
g
e
s
t
h
e
in
p
u
ts
to
b
e
d
ec
ip
h
er
ed
an
d
m
atc
h
ed
w
i
th
t
h
e
r
u
le
s
av
ail
ab
le
in
th
e
“
r
u
le
-
b
ase.
Fi
n
al
l
y
,
th
e
“
d
ef
u
zz
i
f
icatio
n
”
in
te
r
f
ac
e
ch
a
n
g
e
s
th
e
d
ec
is
io
n
ap
p
r
o
v
ed
b
y
th
e
i
n
f
er
en
ce
m
ec
h
a
n
is
m
i
n
to
th
e
co
n
tr
ib
u
tio
n
s
o
f
th
e
p
la
n
n
ed
s
y
s
te
m
[
8
]
.
Fig
u
r
e
1
.
Fu
zz
y
C
o
n
tr
o
ller
A
r
ch
itect
u
r
e
2.
RE
S
E
ARCH
M
E
T
H
O
D
Ou
r
s
y
s
te
m
co
n
s
i
s
ts
o
f
f
i
v
e
m
ai
n
p
ar
ts
e
x
ec
u
ted
u
s
in
g
MA
T
L
A
B
2
0
1
6
a,
s
tar
tin
g
w
it
h
i
n
p
u
t
h
is
to
p
at
h
o
lo
g
y
i
m
a
g
e,
w
h
ich
w
a
s
co
r
r
u
p
ted
o
r
d
am
ag
ed
w
i
th
b
u
b
b
le,
en
d
i
n
g
w
i
th
a
clea
r
i
m
a
g
e
w
it
h
o
u
t
t
h
e
b
u
b
b
les.
2
.
1
.
I
np
ut
I
m
a
g
e
T
h
e
s
y
s
te
m
s
tar
ts
b
y
ac
ce
p
ti
n
g
an
y
t
y
p
e
o
f
h
is
to
p
ath
o
lo
g
ic
al
i
m
a
g
e
co
n
tai
n
in
g
b
u
b
b
les
a
s
an
in
p
u
t,
as sh
o
w
n
i
n
Fi
g
u
r
e
2
.
Fig
u
r
e
2
.
His
to
p
ath
o
lo
g
ical
i
m
ag
e
w
it
h
b
u
b
b
le
2
.2
.
B
ub
ble D
et
ec
t
io
n
T
h
e
b
u
b
b
le
d
etec
tio
n
p
r
o
ce
s
s
is
i
m
p
le
m
e
n
ted
b
y
t
w
o
s
ta
g
es
;
f
ir
s
tl
y
th
e
p
r
o
g
r
a
m
w
i
ll
as
k
th
e
u
s
er
t
o
s
elec
t
th
r
ee
p
o
in
t
s
o
n
th
e
o
u
te
r
cir
cu
m
f
er
en
ce
o
f
t
h
e
b
u
b
b
le.
Seco
n
d
l
y
,
th
e
u
s
er
w
ill
b
e
as
k
ed
ag
ai
n
to
s
elec
t
th
r
ee
p
o
in
ts
o
n
t
h
e
i
n
n
er
cir
cu
m
f
er
e
n
ce
o
f
th
e
b
u
b
b
le.
T
h
e
id
ea
b
eh
in
d
s
elec
ti
n
g
th
r
ee
p
o
in
ts
o
n
l
y
in
ea
ch
ti
m
e
i
s
ex
p
lai
n
ed
o
n
th
e
b
ase
s
th
at
o
n
e
a
n
d
o
n
l
y
o
n
e
u
n
iq
u
e
c
ir
cle
w
il
l p
ass
t
h
r
o
u
g
h
t
h
r
ee
n
o
n
-
co
lli
n
ea
r
p
o
in
ts
w
h
ic
h
is
t
h
e
m
in
i
m
u
m
r
eq
u
ir
e
m
en
ts
to
d
ef
i
n
e
a
cir
cle.
Fro
m
th
e
p
r
ev
io
u
s
s
elec
tio
n
s
,
th
e
ce
n
tr
e
p
o
in
t
a
n
d
r
ad
iu
s
co
u
ld
b
e
d
ef
in
ed
as b
el
o
w
:
(
x
−
x
c
)
2
+
(
y
−
y
c
)
2
−
r
2
=
0
(
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
Op
timiz
a
tio
n
o
f D
ig
ita
l H
is
to
p
a
th
o
lo
g
y
I
ma
g
e
Q
u
a
lity (
F
u
r
a
t N.
Ta
w
feeq
)
73
W
h
er
e
(
x
c,
y
c)
is
t
h
e
co
o
r
d
in
ates
o
f
t
h
e
ce
n
tr
e,
(
x
,
y
)
is
t
h
e
co
o
r
d
in
ates
f
o
r
an
y
p
o
i
n
t
t
h
at
la
y
o
n
t
h
e
cir
cle
cir
cu
m
f
er
en
ce
a
n
d
r
is
th
e
r
ad
iu
s
.
T
h
u
s
,
it
w
i
ll
b
e
ea
s
y
to
d
r
a
w
t
w
o
cir
cles,
o
n
e
co
v
er
s
th
e
w
h
o
l
e
b
u
b
b
le
(
o
u
ter
-
cir
cle)
an
d
o
th
er
co
v
er
s
th
e
i
n
n
er
-
cir
cle
as s
h
o
w
n
i
n
Fi
g
u
r
e
3
.
Fig
u
r
e
3
.
T
h
e
o
u
tp
u
t a
f
ter
s
ele
ctin
g
s
i
x
p
o
in
ts
b
y
t
h
e
u
s
er
.
A
:
Af
ter
s
elec
ti
n
g
th
r
ee
p
o
in
t
s
f
r
o
m
o
u
ter
-
cir
cle.
B
: A
f
ter
s
elec
ti
n
g
t
h
r
ee
p
o
in
ts
f
r
o
m
in
n
er
-
cir
cle
2
.3
.
Rem
o
v
ing
T
he
B
ub
ble
Af
ter
t
h
e
b
u
b
b
le
w
a
s
d
etec
te
d
in
t
h
e
p
r
ev
io
u
s
s
ta
g
e,
t
h
e
i
m
p
o
r
ta
n
ce
o
f
r
e
m
o
v
in
g
th
e
b
u
b
b
le
tak
e
s
p
lace
at
t
h
is
lev
e
l.
T
h
is
h
ap
p
en
s
b
y
co
m
p
ar
i
n
g
b
et
w
ee
n
t
h
e
t
w
o
i
m
ag
e
s
s
h
o
w
n
i
n
Fi
g
u
r
e
4
;
th
e
d
if
f
er
e
n
ce
be
t
w
ee
n
i
m
a
g
e
(
A
)
a
n
d
i
m
ag
e
(
B
)
r
ep
r
esen
ts
t
h
e
b
u
b
b
le.
T
h
e
o
u
tp
u
t
o
f
t
h
is
s
ta
g
e
i
s
a
h
i
s
to
p
ath
o
lo
g
y
i
m
a
g
e
w
it
h
o
u
t b
u
b
b
les
w
h
ich
w
i
ll b
e
r
ep
lace
d
b
y
tr
an
s
p
ar
en
t p
i
x
els
as sh
o
w
n
in
Fig
u
r
e
4
-
c.
Fig
u
r
e
4
.
T
h
e
d
if
f
er
en
ce
b
et
wee
n
i
m
a
g
e
(
a)
an
d
i
m
a
g
e
(
b
)
r
ep
r
esen
ts
t
h
e
b
u
b
b
le
(
c)
R
e
m
o
v
i
n
g
b
u
b
b
le
f
r
o
m
i
m
ag
e
Def
i
n
itel
y
,
th
e
ac
c
u
r
ac
y
o
f
s
el
ec
tin
g
th
e
s
ix
p
o
in
t
s
b
y
t
h
e
u
s
er
w
ill
i
m
p
r
o
v
e
th
e
p
r
o
ce
s
s
o
f
r
em
o
v
i
n
g
o
f
th
e
p
ix
el
s
t
h
at
la
y
o
n
a
b
u
b
b
le.
T
h
e
n
ea
r
est
i
n
n
er
a
n
d
o
u
t
er
b
o
u
n
d
ar
ies
o
f
th
e
c
ir
cle
ar
o
u
n
d
t
h
e
b
u
b
b
le,
th
e
m
o
r
e
ac
c
u
r
ate
i
n
r
e
m
o
v
i
n
g
t
h
e
b
u
b
b
le
p
ix
e
ls
a
n
d
p
r
ev
e
n
t
in
g
lo
s
s
o
f
p
i
x
els
th
a
t
d
o
n
o
t
la
y
in
th
e
b
u
b
b
le
(
co
r
r
u
p
ted
p
ix
els).
2
.4
.
P
re
dict
io
n
I
n
th
i
s
s
ta
g
e,
th
e
F
u
zz
y
co
n
t
r
o
ller
w
a
s
u
s
ed
to
p
r
ed
ict
p
i
x
els
t
h
at
w
er
e
r
e
m
o
v
ed
i
n
th
e
p
r
ev
io
u
s
s
tag
e.
Ho
w
e
v
er
,
th
er
e
ar
e
s
til
l
s
o
m
e
i
m
p
o
r
tan
t
p
r
ep
ar
atio
n
s
w
h
ich
ar
e
n
ee
d
ed
b
ef
o
r
e
p
r
ed
ictio
n
.
First,
t
h
e
b
u
b
b
le
r
eg
io
n
s
h
o
u
ld
b
e
d
iv
id
ed
in
to
f
o
u
r
p
ar
ts
(
u
p
p
er
lef
t,
u
p
p
er
r
ig
h
t,
lo
w
er
le
f
t,
a
n
d
lo
w
er
r
i
g
h
t)
as
s
h
o
wn
in
Fi
g
u
r
e
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
7
,
No
.
2
,
J
u
n
e
20
1
8
:
71
–
77
74
Fig
u
r
e
5
.
B
u
b
b
le
r
eg
io
n
s
Fig
u
r
e
6
.
T
h
e
p
lace
s
o
f
p
ix
el
n
eig
h
b
o
r
s
r
elate
d
to
th
e
tr
an
s
p
ar
en
t p
i
x
els
E
ac
h
tr
an
s
p
ar
en
t
p
i
x
el
w
ill
ta
k
e
f
o
u
r
n
ei
g
h
b
o
u
r
s
ac
co
r
d
in
g
to
its
r
e
g
io
n
to
p
r
ed
ict
th
r
ee
v
alu
es
(
r
ed
,
g
r
ee
n
a
n
d
b
lu
e
co
m
p
o
n
e
n
ts
)
.
T
h
e
p
lace
s
o
f
n
ei
g
h
b
o
u
r
i
n
g
p
i
x
el
p
lace
s
d
i
f
f
er
f
r
o
m
r
eg
io
n
t
o
r
eg
io
n
;
Fi
g
u
r
e
6
d
escr
ib
es
th
e
p
lace
s
o
f
t
h
ese
n
eig
h
b
o
u
r
s
.
T
h
is
w
a
y
p
r
ev
en
t
s
a
co
lo
u
r
f
r
o
m
s
ep
ar
ati
n
g
w
ild
l
y
a
n
d
to
ac
h
iev
e
a
h
ig
h
p
er
ce
n
ta
g
e
o
f
co
r
r
ec
tio
n
in
f
in
d
i
n
g
t
h
e
d
esire
d
p
ix
el
co
lo
u
r
.
I
n
th
i
s
p
ap
er
,
f
o
u
r
test
s
w
il
l
b
e
ca
r
r
ied
o
u
t,
ea
ch
o
n
e
h
as
n
u
m
b
er
an
d
t
y
p
e
o
f
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
s
(
MF)
to
m
a
k
e
a
co
m
p
ar
ativ
e
s
t
u
d
y
a
n
d
f
i
n
d
th
e
b
est
w
a
y
f
o
r
p
r
ed
ictio
n
,
T
ab
le
1
d
e
s
cr
ib
es th
e
s
e
f
o
u
r
te
s
ts
.
T
ab
le
1
.
Me
m
b
er
s
h
ip
f
u
n
ctio
n
s
p
ar
am
e
ter
s
N
o
.
o
f
M
e
mb
e
r
sh
i
p
F
u
n
c
t
i
o
n
Ty
p
e
o
f
M
e
mb
e
r
sh
i
p
F
u
n
c
t
i
o
n
T
e
st
o
n
e
5
T
r
i
a
n
g
l
e
T
e
st
t
w
o
5
G
a
u
ssi
a
n
T
e
st
t
h
r
e
e
9
T
r
i
a
n
g
l
e
T
e
st
f
o
u
r
9
G
a
u
ssi
a
n
A
cc
o
r
d
in
g
to
Fi
g
u
r
e
6
,
ea
ch
t
est
h
a
s
f
o
u
r
i
n
p
u
t
s
an
d
o
n
e
o
u
tp
u
t
(
f
o
u
r
n
ei
g
h
b
o
u
r
s
an
d
o
n
e
r
eq
u
ir
ed
p
ix
el
r
esp
ec
ti
v
el
y
)
th
a
t
ar
e
ca
lled
MI
SO
(
m
u
lt
i
-
in
p
u
ts
,
s
i
n
g
le
o
u
tp
u
t)
.
E
ac
h
te
s
t
w
a
s
e
x
ec
u
ted
t
h
r
ee
ti
m
es
to
f
i
n
d
r
ed
,
g
r
ee
n
an
d
b
lu
e
v
alu
e
s
.
Fo
r
ex
a
m
p
le
in
test
o
n
e,
th
e
r
e
ar
e
f
o
u
r
v
alu
es
f
o
r
r
ed
co
m
p
o
n
en
ts
ta
k
en
f
r
o
m
th
e
f
o
u
r
n
eig
h
b
o
u
r
s
to
f
i
n
d
t
h
e
r
ed
v
alu
e
f
o
r
th
e
tr
an
s
p
ar
en
t
p
ix
el
as
s
h
o
w
n
i
n
Fig
u
r
es
7
a
n
d
8
.
A
s
u
b
j
ec
tiv
e
th
r
es
h
o
ld
w
a
s
ap
p
lied
f
o
r
d
et
ac
h
m
e
n
t
b
et
w
ee
n
0
an
d
2
5
5
,
an
d
in
t
h
is
p
ap
er
,
it
m
a
y
b
e
t
r
ian
g
le
o
r
Gau
s
s
ia
n
w
h
ic
h
allo
w
s
a
n
o
v
er
lap
an
d
g
r
ad
u
al
c
h
a
n
g
e
s
b
et
w
ee
n
M
Fs
;
th
u
s
allo
w
i
n
g
f
u
zz
y
to
f
in
d
t
h
e
v
al
u
e
t
h
at
d
id
n
’
t
lie
ex
ac
tl
y
in
t
h
e
ce
n
tr
e
o
f
MF
b
y
co
m
p
ar
i
n
g
a
m
o
n
g
s
to
r
ed
i
n
p
u
t M
F.
Fig
u
r
e
7
.
I
n
p
u
t
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
s
in
T
est o
n
e
Fig
u
r
e
8
.
Ou
tp
u
t
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
s
i
n
T
est o
n
e
T
h
e
s
am
e
w
a
y
h
a
s
b
ee
n
ex
ec
u
ted
to
f
in
d
g
r
ee
n
an
d
b
lu
e
v
alu
es,
an
d
s
o
o
n
f
o
r
th
e
n
e
x
t
p
ix
els.
T
h
e
f
u
zz
y
al
g
o
r
ith
m
is
b
ased
o
n
a
co
llectio
n
o
f
lo
g
ic
r
u
les
i
n
t
h
e
f
o
r
m
o
f
If
-
T
h
en
s
tate
m
e
n
ts
(
I
F
A
an
d
B
an
d
C
an
d
D
T
HE
N
Z
)
,
w
h
er
e
I
F
p
ar
t
is
ca
lled
th
e
“
a
n
tece
d
en
t”
a
n
d
T
HE
N
p
ar
t
is
ca
lled
th
e
“c
o
n
s
eq
u
e
n
t”
w
h
ic
h
m
er
g
ed
to
p
r
o
d
u
ce
“
F
u
zz
y
C
o
n
d
itio
n
al
S
tate
m
en
t
s
”
[
9
]
.
Fig
u
r
e
9
s
h
o
w
s
t
h
e
r
u
le
-
b
ase
f
o
r
test
o
n
e;
it
i
s
n
o
ted
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
Op
timiz
a
tio
n
o
f D
ig
ita
l H
is
to
p
a
th
o
lo
g
y
I
ma
g
e
Q
u
a
lity (
F
u
r
a
t N.
Ta
w
feeq
)
75
th
at
th
er
e
ar
e
f
o
u
r
i
n
p
u
t
s
a
n
d
o
n
e
o
u
tp
u
t
M
F.
E
q
u
at
io
n
2
s
h
o
w
s
an
e
x
a
m
p
le
o
f
a
r
u
le
i
n
t
est
o
n
e
w
h
ic
h
u
s
e
s
Ma
m
d
an
i
f
u
zz
y
lo
g
ic
co
n
tr
o
l.
Fig
u
r
e
9
.
R
u
le
-
b
ase
f
o
r
T
est O
n
e
if
in
p
u
t
1
r
e
d
=
MF
1
A
ND
in
p
u
t
2
r
e
d
=
MF
1
A
ND
i
np
u
t
3
r
e
d
=
MF
1
A
ND
in
p
u
t
4
r
e
d
=
MF
1
T
H
EN
out
p
u
t
1
r
e
d
=
MF
1
(
2
)
W
h
er
e
in
p
u
t1
r
ed
,
in
p
u
t2
r
ed
,
i
n
p
u
t3
r
ed
an
d
in
p
u
t4
r
ed
ar
e
th
e
v
alu
es
o
f
r
ed
co
m
p
o
n
e
n
t
f
o
r
th
e
f
o
u
r
n
eig
h
b
o
u
r
p
ix
el
s
,
o
u
tp
u
t1
R
E
D
is
th
e
r
ed
v
al
u
e
o
f
d
esire
p
ix
e
l a
n
d
MF
is
t
h
e
m
e
m
b
er
s
h
ip
f
u
n
ct
io
n
.
3.
R
E
SU
L
T
S
A
ND
AN
AL
Y
SI
S
I
n
th
i
s
s
ec
tio
n
,
it
is
e
x
p
lai
n
ed
th
e
r
esu
lts
o
f
r
esear
ch
an
d
at
th
e
s
a
m
e
ti
m
e
is
g
iv
e
n
t
h
e
co
m
p
r
e
h
en
s
iv
e
d
is
c
u
s
s
io
n
.
R
e
s
u
lt
s
ca
n
b
e
p
r
ese
n
ted
i
n
f
i
g
u
r
es,
g
r
ap
h
s
,
tab
le
s
a
n
d
o
th
er
s
t
h
at
m
a
k
e
t
h
e
r
ea
d
er
u
n
d
er
s
ta
n
d
ea
s
il
y
[
2
]
,
[
5
]
.
T
h
e
d
is
cu
s
s
io
n
ca
n
b
e
m
ad
e
in
s
e
v
er
al
s
u
b
-
c
h
ap
ter
s
.
Fif
t
y
d
i
f
f
er
e
n
t
h
is
to
p
at
h
o
lo
g
ic
al
i
m
a
g
es
w
er
e
e
x
ec
u
ted
in
t
h
e
f
o
u
r
test
s
m
en
t
io
n
ed
i
n
T
a
b
le
1
.
T
h
e
w
a
y
u
s
ed
to
f
in
d
t
h
e
p
er
ce
n
ta
g
e
o
f
co
r
r
ec
t
p
ix
els
w
as
m
ea
s
u
r
ed
b
y
ta
k
i
n
g
t
h
e
r
ed
,
g
r
ee
n
an
d
b
lu
e
v
al
u
es
t
h
at
w
er
e
p
r
o
d
u
ce
d
b
y
t
h
e
f
u
zz
y
c
o
n
tr
o
ller
,
an
d
t
h
en
co
m
p
ar
ed
w
it
h
a
r
ef
er
e
n
ce
i
m
a
g
e
(
w
h
ich
is
t
h
e
s
a
m
e
as
in
p
u
t
i
m
a
g
e
b
u
t b
ef
o
r
e
b
ein
g
co
r
r
u
p
ted
b
y
b
u
b
b
le)
.
T
h
en
th
e
d
if
f
er
en
ce
b
et
w
ee
n
t
h
e
m
w
as
f
o
u
n
d
as b
elo
w
:
if
|
in
p
u
t
r
e
d
−
ori
gin
a
l
r
e
d
|
A
ND
|
in
p
u
t
g
r
e
e
n
−
ori
gin
a
l
g
r
e
e
n
|
A
ND
|
in
p
u
t
b
lu
e
−
ori
gin
a
l
b
lu
e
|
≤
20
T
H
EN
p
ixe
l
is
corre
ct
=
ye
s
(
3
)
W
h
er
e
in
p
u
tr
ed
,
in
p
u
t
g
r
ee
n
a
n
d
in
p
u
tb
lu
e
ar
e
t
h
e
v
al
u
es
o
f
r
ed
,
g
r
ee
n
an
d
b
l
u
e
r
esp
ec
ti
v
el
y
f
o
r
th
e
p
ix
els t
h
at
w
er
e
co
r
r
u
p
ted
b
y
t
h
e
b
u
b
b
le
an
d
o
r
ig
i
n
alr
ed
,
o
r
ig
in
a
lg
r
ee
n
an
d
o
r
ig
in
alb
l
u
e
a
r
e
th
e
v
al
u
e
s
o
f
r
ed
,
g
r
ee
n
a
n
d
b
lu
e
r
esp
ec
tiv
el
y
f
o
r
th
e
r
ef
er
en
ce
p
ix
e
ls
.
T
h
e
id
ea
b
ey
o
n
d
tak
i
n
g
2
0
in
s
tead
o
f
ze
r
o
is
b
ased
o
n
th
e
f
in
d
in
g
s
th
at
t
h
e
d
i
f
f
er
e
n
ce
o
f
2
0
d
id
n
o
t
s
h
o
w
an
o
b
v
io
u
s
ef
f
ec
t
o
n
t
h
e
co
lo
u
r
d
eg
r
ee
.
T
h
at
w
as
p
r
o
v
ed
as
s
h
o
w
n
i
n
Fi
g
u
r
e
10
w
h
ic
h
ill
u
s
tr
ates
t
h
e
w
o
r
s
t
ca
s
es
i
f
t
h
e
2
0
is
ta
k
en
in
co
n
s
id
er
atio
n
f
o
r
th
e
p
ix
e
l
h
a
v
i
n
g
7
0
,
3
0
an
d
2
0
0
f
o
r
r
ed
,
g
r
ee
n
a
n
d
b
lu
e
r
esp
ec
tiv
el
y
.
Af
ter
t
h
e
n
u
m
b
er
o
f
co
r
r
ec
ted
p
ix
els
h
a
s
b
ee
n
ca
lcu
la
ted
,
th
en
t
h
e
p
er
ce
n
tag
e
o
f
co
r
r
ec
tio
n
s
h
o
u
ld
b
e
ca
lcu
lated
also
b
y
u
s
in
g
b
elo
w
eq
u
atio
n
.
P
e
rce
ntage
of
corre
ct
io
n
=
No
.
of
co
r
r
e
ct
e
d
p
i
x
e
ls
To
tal
no
.
of
p
i
x
e
ls
i
ns
i
d
e
b
u
b
b
le
∗
100
(
4
)
T
ab
le
2
s
h
o
w
s
t
h
e
p
er
ce
n
ta
g
e
o
f
co
r
r
ec
tio
n
af
ter
ap
p
ly
i
n
g
th
e
f
o
u
r
test
s
,
w
e
ca
n
n
o
ti
ce
th
at
th
e
h
i
g
h
er
p
er
ce
n
tag
e
i
s
i
n
te
s
t
t
h
r
ee
(
n
i
n
e
MF
s
w
i
th
tr
ian
g
le
t
y
p
e)
.
As
a
te
s
t
s
a
m
p
le
s
,
f
in
a
l
o
u
tp
u
t,
t
h
e
i
n
p
u
t
i
m
ag
e
(
b
u
b
b
le
ex
is
ts
)
an
d
t
h
e
o
r
ig
i
n
a
l i
m
a
g
e
(
b
u
b
b
le
d
id
n
’
t e
x
is
t)
a
r
e
s
h
o
w
n
i
n
T
a
b
le
3
.
Fig
u
r
e
11
s
h
o
w
s
t
w
o
co
n
s
ec
u
tiv
e
M
Fs
in
tes
t
o
n
e
an
d
t
w
o
r
esp
ec
tiv
el
y
.
A
cc
o
r
d
in
g
to
Fi
g
u
r
e
1
1
(
a)
,
th
e
p
er
ce
n
ta
g
e
o
f
o
v
er
lap
p
ed
ar
ea
(
in
d
ex
ed
b
y
y
ello
w
co
lo
u
r
)
f
r
o
m
a
n
y
M
F i
s
2
5
%,
m
ea
s
u
r
ed
b
y
d
i
v
id
in
g
th
e
ar
ea
o
f
o
v
er
lap
p
ed
r
eg
io
n
f
r
o
m
th
e
w
h
o
le
tr
ia
n
g
le.
On
o
th
er
h
a
n
d
s
,
i
n
Fi
g
u
r
e
1
1
(
b
)
,
th
e
p
r
o
b
a
b
ilit
y
d
e
n
s
it
y
f
u
n
ctio
n
f
o
r
th
e
o
v
er
lap
p
ed
n
o
r
m
al
d
is
tr
ib
u
tio
n
t
h
at
i
s
also
in
d
ex
ed
i
n
y
ello
w
co
lo
u
r
is
less
t
h
a
n
2
5
% [
1
0
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
7
,
No
.
2
,
J
u
n
e
20
1
8
:
71
–
77
76
Fig
u
r
e
10
.
T
h
e
w
o
r
s
t c
ase
s
if
v
alu
e
o
f
2
0
is
tak
e
n
f
o
r
d
if
f
er
e
n
ce
Fig
u
r
e
1
1
.
T
w
o
co
n
s
ec
u
tiv
e
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
s
,
(
a)
f
o
r
test
o
n
e,
(
b
)
f
o
r
test
t
w
o
T
ab
le
2
.
P
er
ce
n
tag
e
o
f
co
r
r
ec
tio
n
f
o
r
th
e
f
o
u
r
test
s
T
e
st
N
o
.
%
o
f
c
o
r
r
e
c
t
i
o
n
O
n
e
6
9
.
1
Tw
o
7
2
.
3
1
T
h
r
e
e
7
5
.
4
F
o
u
r
72
T
ab
le
3
.
Fin
al
R
es
u
lts
(
a
)
T
h
e
in
p
u
t i
m
a
g
e
(
co
r
r
u
p
ted
b
y
b
u
b
b
le)
,
(
b
)
T
h
e
o
r
ig
in
al
i
m
ag
e
a
n
d
(
c
)
Ou
r
s
y
s
te
m
o
u
tp
u
t
a
b
c
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
Op
timiz
a
tio
n
o
f D
ig
ita
l H
is
to
p
a
th
o
lo
g
y
I
ma
g
e
Q
u
a
lity (
F
u
r
a
t N.
Ta
w
feeq
)
77
T
ab
le
3
.
Fin
al
R
es
u
lts
(
a
)
: T
h
e
in
p
u
t i
m
a
g
e
(
co
r
r
u
p
ted
b
y
b
u
b
b
le)
,
(
b
)
:
T
h
e
o
r
ig
in
al
i
m
a
g
e
an
d
(
c
)
: O
u
r
s
y
s
te
m
o
u
tp
u
t
a
b
c
4
.
CO
NCLU
SI
O
N
I
n
o
u
r
s
y
s
te
m
,
w
e
u
s
e
i
m
a
g
e
p
r
o
ce
s
s
in
g
tec
h
n
iq
u
e
s
to
d
etec
t
an
d
r
e
m
o
v
e
b
u
b
b
le
ar
tef
ac
t
p
ix
els,
an
d
th
en
f
u
zz
y
co
n
tr
o
ller
is
u
s
ed
f
o
r
p
ix
el
s
p
r
ed
icatio
n
.
Fo
u
r
t
ests
in
d
if
f
er
en
t
t
y
p
e
s
a
n
d
n
u
m
b
er
o
f
MFs
w
er
e
ca
r
r
ied
o
u
t
to
f
in
d
t
h
e
ac
cu
r
ate
m
eth
o
d
.
A
cc
o
r
d
in
g
to
o
u
r
r
esu
lt
s
,
th
e
b
est
p
r
ed
icti
o
n
p
er
ce
n
tag
e
w
a
s
d
is
p
la
y
ed
w
h
e
n
ap
p
l
y
in
g
n
i
n
e
MFs
w
i
th
tr
ian
g
le
t
y
p
e
(
7
5
.
4
%).
T
h
is
p
er
ce
n
tag
e
r
ep
r
esen
t
s
th
e
co
r
r
ec
t
co
lo
u
r
s
o
f
p
ix
els
(
co
m
p
ar
i
n
g
w
it
h
t
h
e
i
m
ag
e
w
i
th
o
u
t
b
u
b
b
le)
th
at
h
av
e
b
ee
n
r
e
m
o
v
ed
i
n
p
r
ev
io
u
s
s
tep
.
I
t
h
as
b
ee
n
o
b
s
er
v
ed
th
at
t
h
e
i
n
cr
ea
s
e
i
n
th
e
n
u
m
b
er
o
f
M
Fs
lead
to
h
ig
h
er
p
er
ce
n
tag
e
o
f
co
r
r
ec
tio
n
i
n
t
h
e
p
r
ed
ictio
n
p
r
o
ce
s
s
,
w
h
ile
w
id
er
o
v
er
lap
p
in
g
i
n
t
h
e
ar
ea
b
et
w
ee
n
M
F
le
ad
to
f
a
u
lt
p
r
ed
ictio
n
in
p
ix
el
co
lo
u
r
s
,
esp
ec
i
all
y
if
t
h
e
n
u
m
b
er
o
f
r
u
le
s
i
s
s
m
all
b
ec
a
u
s
e
it
w
i
ll
b
e
f
ar
a
w
a
y
f
r
o
m
g
ett
in
g
t
h
e
d
es
ir
ed
co
lo
u
r
.
A
ll
t
h
e
af
o
r
e
m
e
n
tio
n
ed
r
es
u
lt
s
w
er
e
d
ir
ec
tl
y
p
r
o
p
o
r
tio
n
al
to
th
e
i
n
cr
ea
s
e
i
n
t
h
e
n
u
m
b
er
o
f
M
Fs
.
S
u
c
h
ap
p
licab
le
tech
n
iq
u
e
is
s
p
ec
if
ica
ll
y
r
ec
o
m
m
en
d
ed
w
h
e
n
att
e
m
p
ti
n
g
t
o
d
iag
n
o
s
e
s
tai
n
ed
p
ath
o
lo
g
y
s
lid
es
o
n
r
e
m
o
te
b
asis
.
T
h
e
li
m
itat
io
n
s
ap
p
ea
r
w
h
en
t
h
e
s
ize
o
f
b
u
b
b
le
is
to
o
b
ig
,
th
at
lead
to
d
ec
r
ea
s
in
g
t
h
e
p
r
ed
ictio
n
p
er
ce
n
tag
e.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
e
au
th
o
r
s
w
o
u
ld
l
ik
e
to
ac
k
n
o
w
led
g
e
t
h
e
s
u
p
p
o
r
t
o
f
th
e
w
o
r
k
i
n
g
s
taf
f
in
th
e
P
ath
o
lo
g
y
R
esear
c
h
Dep
ar
t
m
en
t o
f
th
e
Nat
io
n
al
C
an
ce
r
R
esear
c
h
C
e
n
tr
e
,
Un
i
v
er
s
it
y
o
f
B
ag
h
d
ad
,
I
r
aq
.
RE
F
E
R
E
NC
E
S
[1
]
F
ra
n
c
is
W
,
W
il
li
a
m
K,
L
ib
e
ro
A
.
A
Co
lo
u
r
A
tl
a
s
a
n
d
T
e
x
tb
o
o
k
o
f
th
e
Histo
p
a
t
h
o
l
o
g
y
o
f
M
y
c
o
ti
c
Dise
a
se
s.
1
st
e
d
.
L
o
n
d
o
n
:
W
o
lf
e
M
e
d
ica
l
P
u
b
li
c
a
ti
o
n
s L
td
.
1
9
8
0
.
[2
]
Nik
o
las
S
,
M
it
k
o
V
,
A
n
d
ré
H,
a
n
d
P
a
u
l
J.
G
o
in
g
f
u
ll
y
d
ig
it
a
l:
p
e
rsp
e
c
ti
v
e
o
f
a
Du
tch
a
c
a
d
e
m
i
c
p
a
th
o
lo
g
y
lab
.
J
o
u
rn
a
l
o
f
P
a
th
o
lo
g
y
In
f
o
rm
a
ti
c
s
.
2
0
1
3
;
4
(
5
).
[3
]
V
a
ru
n
R,
Na
v
e
e
n
P
,
S
w
a
ti
A
,
G
e
e
tp
riy
a
K,
Lalit
a
Y
,
Ra
c
h
n
a
S
.
A
rte
f
a
c
ts:
A
Dia
g
n
o
stic
Dilem
m
a
-
A
Re
v
ie
w
.
J
o
u
rn
a
l
o
f
Cli
n
ica
l
a
n
d
Di
a
g
n
o
sti
c
Res
e
a
rc
h
.
2
0
1
3
;
7
(
1
0
):
2
4
0
8
-
2
4
1
3
.
[4
]
S
a
m
a
r
K,
M
a
n
ish
a
T
,
M
e
g
h
a
J,
Am
i
D.
A
rti
f
a
c
ts
in
Histo
p
a
t
h
o
lo
g
y
:
A
P
o
ten
ti
a
l
Ca
u
se
o
f
M
isin
terp
re
tatio
n
.
Res
e
a
rc
h
a
n
d
Rev
iews
:
J
o
u
rn
a
l
o
f
De
n
ta
l
S
c
ien
c
e
s.
2
0
1
4
;
2
(2
):
2
3
-
31.
[5
]
G
o
n
z
a
lo
R,
W
il
li
a
m
C,
A
n
d
re
w
L
,
Eu
g
e
n
e
T
,
J
e
ff
M
,
A
n
il
P
,
L
iro
n
P
.
Dig
it
a
l
P
a
t
h
o
l
o
g
y
Co
n
su
lt
a
ti
o
n
s
-
a
Ne
w
Era
in
Dig
it
a
l
Im
a
g
in
g
,
Ch
a
ll
e
n
g
e
s a
n
d
P
ra
c
ti
c
a
l
A
p
p
li
c
a
ti
o
n
s.
J
o
u
rn
a
l
o
f
Dig
it
a
l
Ima
g
in
g
.
2
0
1
3
;
2
6
(4
):
6
6
8
-
6
7
7
.
[6
]
Isiz
o
h
A
,
Ok
id
e
S
,
A
n
a
z
i
a
A
,
Og
u
C.
T
e
m
p
e
ra
tu
re
Co
n
tro
l
S
y
ste
m
Us
in
g
F
u
z
z
y
L
o
g
ic
T
e
c
h
n
iq
u
e
.
IJ
AR
AI
.
2
0
1
2
;
1
(3
):
2
7
-
3
1
.
[7
]
G
u
a
n
ro
n
g
C,
T
ru
n
g
T
.
Ed
it
o
rs
.
In
tro
d
u
c
ti
o
n
t
o
F
u
z
z
y
S
e
ts,
F
u
z
z
y
L
o
g
ic,
a
n
d
F
u
z
z
y
Co
n
tro
l
S
y
ste
m
s.
Ne
w
Yo
rk
:
CRC P
re
ss
.
2
0
0
1
.
[8
]
Ke
v
in
M
,
S
tep
h
e
n
Y.
Ed
it
o
rs
.
F
u
z
z
y
Co
n
tro
l,
Ca
li
f
o
rn
ia:
A
d
d
iso
n
W
e
sle
y
L
o
n
g
m
a
n
.
1
9
9
8
.
[9
]
L
o
tf
i
A
.
Ou
tl
in
e
o
f
a
Ne
w
A
p
p
ro
a
c
h
to
t
h
e
A
n
a
l
y
sis
Co
m
p
le
x
S
y
s
tem
s
a
n
d
De
c
isio
n
P
ro
c
e
ss
e
s.
IEE
E
T
ra
n
s
S
y
st
.
M
a
n
Cib
e
rn
.
1
9
7
3
;
3
(1
)
:
2
8
-
4
4
.
[1
0
]
L
in
a
c
re
J
.
Ov
e
rl
a
p
p
in
g
n
o
rm
a
l
d
istri
b
u
ti
o
n
s
.
Ra
sc
h
M
e
a
su
re
me
n
t
T
ra
n
sa
c
ti
o
n
s
.
1
9
9
6
;
1
0
(
1
):
4
8
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.