I
nte
rna
t
io
na
l J
o
urna
l o
f
I
nfo
r
m
a
t
ics a
nd
Co
mm
u
n
ica
t
io
n T
ec
hn
o
lo
g
y
(
I
J
-
I
CT
)
Vo
l.
7
,
No
.
2
,
A
u
g
u
s
t
201
8
,
p
p
.
71
~
76
I
SS
N:
2252
-
8776
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
i
ct.
v
7
i2
.
p
p
7
1
-
76
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
JI
C
T
Bra
in Tu
m
o
r
De
t
ection
U
sing
Wa
t
hershed S
eg
m
ent
a
tion
Techniqu
es a
nd
Area Ca
lcula
tion
M
ee
na
k
s
hi P
a
re
e
k
*
,
C
.
K
J
ha
,
Sa
ura
bh
M
uk
herj
ee
,
Cha
nd
a
ni J
o
s
hi
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
Ba
n
a
sth
a
li
Un
iv
e
rsity
,
Ra
jas
th
a
n
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
p
r
8
,
2
0
1
8
R
ev
i
s
ed
J
u
n
1
9
,
2
0
1
8
A
cc
ep
ted
J
u
l
0
2
,
2
0
1
8
T
h
is
p
a
p
e
r
p
rim
a
ril
y
f
o
c
u
se
s
o
n
to
e
m
p
lo
y
a
n
o
v
e
l
a
p
p
r
o
a
c
h
to
c
las
sify
th
e
b
ra
in
tu
m
o
r
a
n
d
it
s
a
re
a
.
T
h
e
T
u
m
o
r
is an
u
n
c
o
n
tro
l
led
e
n
larg
e
m
e
n
t
o
f
ti
ss
u
e
s
in
a
n
y
p
o
rti
o
n
o
f
th
e
h
u
m
a
n
b
o
d
y
.
T
u
m
o
rs
a
re
o
f
s
e
v
e
ra
l
t
y
p
e
s a
n
d
h
a
v
e
so
m
e
d
if
fe
re
n
t
c
h
a
ra
c
teristics
.
Ac
c
o
rd
in
g
to
t
h
e
ir
c
h
a
ra
c
teristics
so
m
e
o
f
th
e
m
a
re
a
v
o
id
a
b
le
a
n
d
so
m
e
a
re
u
n
a
v
o
id
a
b
le.
Bra
in
tu
m
o
r
is
se
rio
u
s
a
n
d
li
f
e
th
re
a
ten
in
g
issu
e
s
n
o
w
d
a
y
s,
b
e
c
a
u
se
o
f
to
d
a
y
’s
h
e
c
ti
c
li
f
e
st
y
l
e
.
M
e
d
ica
l
im
a
g
in
g
p
lay
i
m
p
o
rtan
t
ro
le
to
d
iag
n
o
se
b
ra
in
tu
m
o
r
.
I
n
th
is
s
tu
d
y
a
n
a
u
to
m
a
ted
s
y
st
e
m
h
a
s
b
e
e
n
p
ro
p
o
se
d
to
d
e
tec
t
a
n
d
c
a
lcu
late
th
e
a
re
a
o
f
tu
m
o
r.
F
o
r
p
r
o
p
o
se
d
sy
ste
m
th
e
e
x
p
e
ri
m
e
n
t
c
a
rried
o
u
t
w
it
h
1
5
0
T
1
w
e
ig
h
ted
M
RI
im
a
g
e
s.
T
h
e
e
d
g
e
b
a
se
d
se
g
m
e
n
ta
ti
o
n
,
w
a
ters
h
e
d
se
g
m
e
n
tatio
n
h
a
s
a
p
p
li
e
d
f
o
r
tu
m
o
r,
a
n
d
w
a
ters
h
e
d
s
e
g
m
e
n
tati
o
n
h
a
s
u
se
d
t
o
e
x
trac
t
a
b
n
o
rm
a
l
c
e
ll
s
f
ro
m
th
e
n
o
rm
a
l
c
e
ll
s
to
g
e
t
th
e
tu
m
o
r
id
e
n
ti
f
ica
ti
o
n
o
f
in
v
o
lv
e
d
a
n
d
n
o
n
i
n
v
o
lv
e
d
a
re
a
s
so
th
a
t
th
e
ra
d
io
lo
g
ist
d
if
f
e
re
n
ti
a
te
th
e
a
ff
e
c
t
e
d
a
re
a
.
T
h
e
e
x
p
e
ri
m
e
n
t
re
su
lt
sh
o
w
s
tu
m
o
r
e
x
trac
ti
o
n
a
n
d
a
re
a
o
f
t
u
m
o
r
f
in
d
t
h
e
w
e
a
th
e
r
it
is
b
e
n
ig
n
a
n
d
m
a
li
g
n
a
n
t.
K
ey
w
o
r
d
:
Gar
d
ien
t
m
a
g
n
it
u
d
e
MRI
So
b
el
W
ater
s
h
ed
s
eg
m
e
n
tatio
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
:
Me
en
ak
s
h
i P
ar
ee
k
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
B
an
ast
h
ali
U
n
i
v
er
s
it
y
,
R
aj
asth
a
n
,
I
n
d
ia
.
E
m
ail: p
m
ee
n
a
k
s
h
i8
6
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
A
b
n
o
r
m
al
d
ev
elo
p
m
en
t
o
f
tis
s
u
es
i
n
t
h
e
b
r
ain
ca
u
s
es
t
h
e
b
r
ain
t
u
m
o
r
.
B
a
s
icall
y
B
R
A
I
N
i
s
th
e
co
r
e
p
ar
t
,
in
th
e
h
u
m
an
b
o
d
y
,
ev
er
y
p
ar
t
h
a
v
e
d
if
f
er
e
n
t
ce
lls
an
d
all
ce
lls
h
av
e
th
eir
o
w
n
ca
p
ab
ilit
ies,
s
o
m
e
ce
ll
g
r
o
w
s
w
it
h
th
eir
o
w
n
f
u
n
c
tio
n
alit
y
an
d
s
o
m
e
lo
s
e
th
eir
ca
p
ab
ilit
y
an
d
r
esi
s
t
an
d
g
r
o
w
ab
er
r
an
t.
T
h
ese
m
as
s
co
llectio
n
s
o
f
th
e
ce
ll
s
f
o
r
m
t
h
e
tis
s
u
e
w
h
ic
h
i
s
ca
lled
as
“
t
u
m
o
r
”.
Am
o
n
g
t
h
o
s
e
ce
lls
s
o
m
e
ar
e
ca
n
ce
r
o
u
s
o
r
s
o
m
e
ar
e
n
o
n
-
ca
n
ce
r
o
u
s
.
B
ased
o
n
th
o
s
e
ce
lls
,
th
e
tu
m
o
r
ca
n
d
ef
in
ed
in
t
w
o
ca
teg
o
r
ies
b
en
ig
n
a
n
d
m
ali
g
n
an
t
.
C
en
tr
al
B
r
ain
T
u
m
o
r
R
eg
i
s
tr
y
o
f
th
e
Un
ited
State
s
(
C
B
T
R
US)
in
Dec
em
b
er
2
0
1
5
p
u
b
lis
h
e
d
a
r
ep
o
r
t,
ac
c
o
r
d
in
g
to
th
is
s
tat
is
tical
r
ep
o
r
t
b
r
ain
t
u
m
o
r
i
s
t
h
e
s
ec
o
n
d
lead
in
g
ca
u
s
e
o
f
d
ea
th
in
ch
i
ld
r
en
a
n
d
L
eu
k
e
m
ia
is
f
ir
s
t
[1
]
.
B
asicall
y
b
r
ain
tu
m
o
r
ca
teg
o
r
ized
in
to
tw
o
p
ar
ts
:
B
en
ig
n
an
d
M
alig
n
a
n
t
.
T
h
e
W
o
r
ld
H
ea
lth
Or
g
a
n
izatio
n
(
W
HO)
h
ad
class
if
ied
t
u
m
o
r
i
n
to
4
Gr
ad
es,
Gr
ad
e
I
to
I
V.
G
r
ad
e
I
an
d
g
r
ad
e
I
I
a
r
e
lo
w
g
r
ad
e
w
h
ic
h
r
ep
r
esen
t
s
B
en
ig
n
T
u
m
o
r
.
Gr
ad
e
I
I
I
an
d
Gr
ad
e
I
V
ar
e
h
ig
h
g
r
ad
e
w
h
ic
h
r
ep
r
esen
ts
m
ali
g
n
an
t
tu
m
o
r
[2
]
.
Ma
n
y
d
i
f
f
er
en
t
i
m
a
g
in
g
m
o
d
alitie
s
ar
e
u
s
ed
in
th
e
last
t
w
o
d
ec
ad
es
to
id
en
tify
a
n
d
lo
ca
te
th
e
an
ato
m
ical
s
tr
u
ct
u
r
e
s
u
c
h
as
X
-
R
a
y
,
C
T
s
ca
n
s
a
n
d
MRI
[
3
]
.
B
u
t
d
u
e
to
t
h
e
ch
a
n
g
e
i
n
ti
m
e
th
e
h
ig
h
q
u
a
lit
y
i
m
ag
e
s
ar
e
u
s
ed
to
d
eter
m
i
n
e
t
u
m
o
r
,
w
h
ic
h
is
k
n
o
w
n
as
MRI
(
Ma
g
n
etic
R
eso
n
an
ce
I
m
ag
e)
.
T
1
w
ei
g
h
ted
an
d
T
2
w
ei
g
h
ted
i
m
ag
es
ar
e
p
ar
t
o
f
th
e
MRI
[
4
].
An
ato
m
ic
b
e
h
av
io
r
o
f
b
r
ain
is
s
h
o
w
n
t
h
r
o
u
g
h
t
h
e
MRI.
MRI
i
s
also
u
s
ed
f
o
r
th
e
s
tu
d
y
t
h
e
i
n
ter
n
a
l
s
tr
u
ct
u
r
e
o
f
th
e
h
u
m
a
n
b
o
d
y
.
R
ad
io
lo
g
is
t
v
is
u
alize
s
an
d
an
al
y
ze
s
t
h
o
s
e
i
m
ag
e
s
.
MRI
tec
h
n
iq
u
es
co
m
p
lete
l
y
b
ased
o
n
m
ag
n
etic
f
ie
ld
[
5
]
.
I
n
MRI
elec
tr
o
m
a
g
n
etic
w
a
v
e
s
ar
e
u
s
ed
an
d
th
ese
w
a
v
es
ar
e
tr
an
s
m
it
ted
in
th
e
h
u
m
a
n
b
r
ain
a
n
d
s
ig
n
al
ar
e
r
e
co
r
d
ed
an
d
r
ec
o
n
s
tr
u
cted
o
n
i
m
ag
e
s
a
n
d
th
e
s
e
i
m
a
g
es a
r
e
a
n
al
y
ze
d
b
y
co
m
p
u
ter
p
r
o
g
r
am
.
S
h
o
w
n
in
F
ig
u
r
e
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8776
IJ
-
I
C
T
Vo
l.
7
,
No
.
2
,
A
u
g
u
s
t
20
1
8
:
71
–
76
72
(
a)
(
b
)
(
c)
Fig
u
r
e
1
.
(
a)
No
r
m
al
B
r
ain
,
(
b
)
B
en
ig
n
T
u
m
o
r
,
(
c)
Ma
lig
n
an
t T
u
m
o
r
I
n
m
ed
ical
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
,
s
eg
m
e
n
taio
n
p
la
y
s
a
n
i
m
p
o
r
ta
n
t
r
o
le
f
o
r
m
o
d
elin
g
o
f
b
r
ain
a
n
d
co
n
s
tr
u
ct
b
r
ain
atlases
.
I
t’
s
a
ch
alle
n
g
i
n
g
tas
k
f
o
r
u
s
to
s
eg
m
e
n
t
p
r
o
p
e
r
r
eg
io
n
b
ec
au
s
e
DI
C
O
M
i
m
a
g
e
h
a
v
e
a
v
ar
iet
y
o
f
in
f
o
r
m
atio
n
,
s
u
c
h
ar
e
lo
ca
tio
n
,
s
h
ap
e,
in
te
n
s
it
y
,
etc.
S
o
,
th
at
it
is
a
ted
io
u
s
tas
k
to
s
e
g
m
e
n
t
r
eg
io
n
o
f
i
n
ter
est.
Fo
r
s
eg
m
en
tat
io
n
,
m
ed
ical
i
m
ag
in
g
h
as
d
i
f
f
er
e
n
t
s
e
g
m
en
ta
t
io
n
ap
p
r
o
ac
h
es,
lik
e
ed
g
e
b
as
ed
,
th
r
e
s
h
o
ld
b
ase,
r
eg
io
n
g
r
o
w
i
n
g
etc
[
6
]
.
2.
SE
G
M
E
NT
A
T
I
O
N
T
o
c
ar
r
y
o
u
t
i
m
a
g
e
s
eg
m
e
n
ta
tio
n
,
th
er
e
ar
e
m
a
n
y
e
x
i
s
ti
n
g
s
eg
m
e
n
tatio
n
tec
h
n
iq
u
es.
Se
g
m
en
tatio
n
p
lay
s
k
e
y
tas
k
f
o
r
Me
d
ical
im
ag
e
s
to
p
er
f
o
r
m
p
r
e
an
d
p
o
s
t
s
u
r
g
ical
p
lan
n
i
n
g
,
ea
r
l
y
d
et
ec
tio
n
.
T
o
ca
r
r
y
o
u
t
i
m
a
g
e
s
eg
m
e
n
tatio
n
,
th
er
e
ar
e
m
an
y
e
x
is
ti
n
g
s
e
g
m
e
n
tat
io
n
t
e
ch
n
iq
u
es.
Se
g
m
en
ta
tio
n
p
la
y
s
k
e
y
ta
s
k
f
o
r
m
ed
ica
l
i
m
a
g
es to
p
er
f
o
r
m
p
r
e
an
d
p
o
s
t su
r
g
ical
p
lan
n
i
n
g
,
ea
r
l
y
d
ete
ctio
n
.
2
.
1
.
Reg
io
n B
a
s
ed
Seg
m
ent
a
t
io
n
R
eg
io
n
b
ased
s
eg
m
e
n
tatio
n
tech
n
iq
u
e
in
cl
u
d
e
re
g
io
n
g
r
o
w
i
n
g
an
d
re
g
io
n
s
p
litt
in
g
an
d
m
er
g
in
g
.
B
y
r
eg
io
n
g
r
o
w
i
n
g
m
eth
o
d
,
p
ix
el
s
ar
e
g
r
o
u
p
ed
in
a
s
u
b
r
eg
io
n
f
r
o
m
lar
g
e
r
e
g
io
n
.
I
n
th
i
s
ap
p
r
o
ac
h
o
n
e
“seed
”
p
o
in
t
f
i
n
d
o
u
t f
ir
s
tl
y
,
w
h
er
e
th
e
n
ei
g
h
b
o
r
in
g
p
i
x
els
ar
e
g
r
o
w
in
g
,
t
h
at
h
a
v
e
id
en
tica
l
ch
ar
ac
ter
is
tic
s
o
f
t
h
e
s
ee
d
[
7
]
.
I
n
r
eg
io
n
s
p
litt
i
n
g
m
et
h
o
d
,
g
r
o
w
i
n
g
r
eg
io
n
s
ar
e
s
p
lit
in
to
p
d
o
w
n
d
ir
ec
tio
n
,
in
s
p
litt
i
n
g
r
e
m
o
te
p
ar
t
is
m
o
r
e
h
o
m
o
g
en
eo
u
s
t
h
a
n
t
h
e
w
h
o
le.
I
f
ad
j
ac
en
t
r
eg
io
n
ar
e
g
et,
s
e
lecte
d
r
eg
io
n
s
ar
e
m
er
g
ed
u
s
i
n
g
r
e
g
io
n
m
er
g
i
n
g
m
et
h
o
d
in
w
h
ich
w
ee
k
b
o
u
n
d
ar
ies
ar
e
m
er
g
ed
an
d
r
o
b
u
s
t
e
d
g
es
ar
e
e
m
b
o
s
s
ed
.
I
n
r
e
g
io
n
g
r
o
w
i
n
g
s
p
lit
a
n
d
m
er
g
e
m
et
h
o
d
is
th
e
a
m
b
i
g
u
o
u
s
.
E
v
er
y
r
eg
io
n
co
u
ld
b
e
d
i
v
id
ed
in
to
s
u
b
r
eg
io
n
s
,
a
n
d
t
h
e
s
u
i
tab
le
r
eg
io
n
s
co
u
ld
b
e
m
er
g
ed
in
to
a
o
n
e
r
eg
io
n
[
8
]
.
2
.
2
.
T
hres
ho
ldi
ng
B
a
s
ed
Seg
m
e
n
t
a
t
io
n
T
h
r
esh
o
ld
in
g
i
s
an
o
th
er
tec
h
n
iq
u
e
o
f
s
eg
m
e
n
tatio
n
.
I
t
is
an
in
te
n
s
it
y
b
ased
m
et
h
o
d
o
f
s
eg
m
en
tatio
n
.
I
n
th
i
s
m
et
h
o
d
f
ir
s
tl
y
f
i
n
d
th
e
p
ix
el
v
a
lu
e
o
f
i
m
a
g
es,
s
o
th
at
t
h
e
r
eg
io
n
o
f
i
n
ter
est
s
e
g
m
e
n
t.
T
h
en
ap
p
l
y
t
h
r
es
h
o
ld
v
alu
e
h
as
ap
p
lied
to
im
ag
e
p
ix
el
v
alu
e
s
,
th
o
s
e
r
eg
io
n
s
h
a
v
e
th
e
b
lack
b
ac
k
g
r
o
u
n
d
an
d
h
ig
h
er
i
n
ten
s
i
t
y
ca
n
al
s
o
b
e
s
eg
m
e
n
ted
[
9
]
.
T
h
r
esh
o
ld
v
alu
e
i
s
d
ec
id
ed
o
n
th
e
b
asis
o
f
ad
j
ac
en
t
p
ix
el,
an
d
g
et
s
eg
m
e
n
ted
p
ar
t
[
10
]
.
B
ec
au
s
e
o
f
i
n
ten
s
it
y
d
ep
en
d
e
n
t
i
m
a
g
e
h
av
e
n
o
i
s
e
a
n
d
w
ea
k
b
o
u
n
d
ar
ies,
to
r
e
m
o
v
e
n
o
is
e
d
etec
t
b
o
u
n
d
ar
ies
s
o
m
e
m
o
r
p
h
o
lo
g
ical
o
p
er
ati
o
n
s
ar
e
u
s
ed
w
it
h
th
r
es
h
o
ld
m
et
h
o
d
s
[
7
]
.
2
.
3
.
E
dg
e
o
r
B
o
un
da
ry
B
a
s
ed
Seg
m
ent
a
t
io
n
B
ec
au
s
e
o
f
th
e
i
n
te
n
s
it
y
s
o
m
e
ed
g
es
ar
e
s
tr
o
n
g
an
d
s
o
m
e
o
f
th
e
m
ar
e
s
tr
o
n
g
.
I
m
a
g
e
ed
g
es
ar
e
d
ep
en
d
in
g
o
n
in
ten
s
it
y
o
f
p
i
x
els.
So
m
e
lin
e
s
ar
e
r
o
o
f
an
d
r
a
m
p
ed
g
es.
I
f
t
h
e
in
t
h
e
i
m
a
g
e
g
r
a
y
to
n
e
is
h
i
g
h
,
th
en
it
tr
an
s
f
o
r
m
s
i
n
th
e
ed
g
es
.
T
h
e
ed
g
es
r
ep
r
esen
t
co
n
tin
u
i
t
y
an
d
d
is
co
n
ti
n
u
it
y
o
f
a
n
o
b
j
e
ct.
T
o
d
etec
t
ed
g
es
p
er
w
itt
e
d
g
e
d
etec
tio
n
,
r
o
b
er
t
e
d
g
e
d
etec
tio
n
an
d
s
o
b
el
ed
g
e
d
etec
tio
n
m
et
h
o
d
s
ar
e
u
s
ed
f
o
r
ed
g
e
d
etec
tio
n
[
11
]
.
3.
P
RO
P
O
SE
D
M
E
T
H
O
DO
L
O
G
Y
T
h
e
pr
o
p
o
s
ed
s
y
s
te
m
m
ai
n
l
y
h
as
f
o
u
r
m
o
d
u
les,
I
m
ag
e
ac
q
u
is
itio
n
,
s
e
g
m
e
n
tatio
n
,
tu
m
o
r
d
etec
tio
n
an
d
ar
ea
ca
lcu
latio
n
an
d
co
v
er
a
g
e
o
f
th
e
tu
m
o
r
.
Se
g
m
e
n
tatio
n
is
ca
r
r
ied
o
u
t
w
it
h
w
ate
r
s
h
ed
tech
n
iq
u
e.
T
h
e
f
o
llo
w
in
g
F
i
g
u
r
e
2
s
h
o
w
i
n
g
t
h
e
p
r
o
p
o
s
ed
w
o
r
k
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
I
C
T
I
SS
N:
2252
-
8776
B
r
a
in
Tu
mo
r
Dete
ctio
n
U
s
in
g
W
a
th
er
s
h
ed
S
eg
men
ta
tio
n
Tech
n
iq
u
es a
n
d
A
r
ea
.
.
.
(
Meen
a
ksh
i P
a
r
ee
k
)
73
Fig
u
r
e
2
.
P
r
o
ce
s
s
o
f
B
r
ain
T
u
m
o
r
Se
g
m
e
n
tatio
n
a
n
d
I
ts
A
r
ea
C
alcu
la
tio
n
I
n
th
i
s
s
ec
tio
n
,
w
e
p
r
o
p
o
s
ed
a
s
y
s
te
m
th
a
t
co
u
ld
s
e
g
m
en
t
an
d
ex
tr
ac
t
t
h
e
t
u
m
o
r
f
r
o
m
M
R
I
i
m
ag
e
s
.
A
ll
ex
p
er
i
m
e
n
tal
w
o
r
k
is
d
o
n
e
w
it
h
MRI
i
m
a
g
e
s
an
d
M
A
T
L
A
B
.
T
h
e
f
o
llo
w
i
n
g
s
tep
s
ar
e
u
s
ed
to
d
etec
t
an
d
s
eg
m
e
n
t
th
e
tu
m
o
r
an
d
f
in
d
it
s
ar
ea
.
a.
I
n
p
u
t M
R
I
i
m
a
g
e.
b.
C
o
n
v
er
t i
m
a
g
e
i
n
g
r
a
y
i
m
a
g
e
u
s
i
n
g
r
g
b
2
g
r
a
y
f
u
n
ct
io
n
i
n
MA
T
L
A
B
f
o
r
s
e
g
m
en
t
at
io
n
.
c.
I
n
th
e
t
h
ir
d
s
tep
r
e
m
o
v
e
all
s
m
all
co
n
n
ec
t
o
b
j
ec
t
th
o
s
e
ar
e
h
av
e
f
e
w
er
t
h
an
p
i
x
el
P
f
r
o
m
b
in
ar
y
i
m
ag
e
u
s
i
n
g
a
b
w
ar
ea
o
p
en
f
u
n
ctio
n
i
n
M
A
T
L
A
B
.
d.
I
n
th
e
f
o
u
r
t
h
s
tep
su
p
p
r
ess
lig
h
t str
u
ctu
r
e
s
co
n
n
ec
ted
to
i
m
a
g
e
b
o
r
d
er
w
it
h
i
m
clea
r
b
o
r
d
er
f
u
n
ct
io
n
.
e.
I
n
th
e
f
i
f
th
s
tep
,
f
o
r
g
r
ad
ien
t o
f
th
e
i
m
a
g
e
u
s
i
n
g
So
b
el
Op
er
ato
r
.
f.
I
n
th
e
s
i
x
t
h
s
tep
wa
ter
s
h
ed
is
ap
p
lied
to
ex
tr
ac
t
d
if
f
er
en
t
p
i
x
els
f
r
o
m
t
h
e
b
ac
k
g
r
o
u
n
d
f
o
r
s
eg
m
e
n
tatio
n
an
d
d
etec
tio
n
.
g.
A
t t
h
e
las
t step
c
alcu
la
te
th
e
ar
ea
o
f
th
e
t
u
m
o
r
s
e
g
m
en
ted
p
ar
t
3
.1
.
I
m
a
g
e
Ac
qu
is
iitio
n
T
h
e
p
r
o
p
o
s
ed
ex
p
er
im
e
n
t
ca
r
r
ied
o
u
t
w
it
h
d
if
f
er
e
n
t
m
o
d
u
le
.
I
m
a
g
e
ac
q
u
is
it
io
n
is
f
ir
s
t
m
o
d
u
le.
W
e
h
ad
d
o
n
e
ex
p
er
i
m
en
ta
tio
n
w
it
h
1
5
0
MRI
im
ag
e
s
tak
e
n
f
r
o
m
“f
i
g
s
h
ar
e
b
r
ain
d
ata
s
et”.
T
h
is
b
r
ain
tu
m
o
r
d
ataset
co
n
tain
i
n
g
3
0
6
4
T
1
-
w
e
ig
h
ted
co
n
tr
ast
-
en
h
a
n
ce
d
i
m
a
g
e
o
f
2
3
3
p
atien
ts
w
it
h
t
w
o
k
i
n
d
s
o
f
b
r
ain
tu
m
o
r
,
f
o
r
th
e
ex
p
er
i
m
e
n
t 5
0
MRI
i
m
a
g
es a
r
e
ca
r
r
ied
o
u
t.
3
.
2
.
Wa
t
er
s
hed Seg
m
ent
a
t
io
n
T
h
er
e
ar
e
m
an
y
s
eg
m
e
n
tati
o
n
tech
n
iq
u
e
s
.
I
n
o
u
r
w
o
r
k
w
e
h
a
v
e
u
s
ed
w
ater
s
h
ed
.
W
ater
s
h
ed
s
eg
m
e
n
tatio
n
is
a
f
a
m
o
u
s
“
ed
g
e
b
ased
s
eg
m
e
n
tatio
n
”
al
g
o
r
ith
m
.
B
asical
l
y
w
at
er
s
h
ed
ter
m
is
u
s
ed
i
n
g
eo
g
r
ap
h
y
also
,
r
elate
d
to
th
e
w
ater
,
m
ea
n
s
w
ater
i
s
d
r
ain
ed
i
n
t
h
e
p
ar
tic
u
lar
ar
ea
[
3
]
.
T
he
w
a
ter
s
h
ed
s
eg
m
en
tatio
n
d
ep
en
d
s
u
p
o
n
th
e
f
lo
w
o
f
w
ater
,
w
h
en
t
w
o
d
if
f
er
en
t
w
ater
b
o
d
ies
ar
e
m
e
eti
n
g
t
h
e
n
th
e
y
b
u
i
ld
d
a
m
s
.
T
h
e
w
ater
m
o
u
n
ted
u
n
t
il
all
p
ea
k
s
in
t
h
e
m
ap
ar
e
ab
s
o
r
b
e
d
.
I
n
im
a
g
e
p
r
o
ce
s
s
in
g
th
e
d
a
m
s
ar
e
“
W
ater
s
h
e
d
”
an
d
im
a
g
es
ar
e
s
eg
m
e
n
ted
b
y
d
a
m
s
an
d
all
s
eg
m
e
n
ted
p
ar
t
is
ca
tch
m
e
n
t
b
asin
[
12
]
.
M
ain
l
y
w
ater
s
h
ed
is
“
Gr
ad
ien
t
B
ased
Seg
m
en
ta
tio
n
”
m
et
h
o
d
,
g
r
ad
ien
t
v
a
lu
e
s
d
ep
en
d
o
n
th
e
p
ix
e
l’
s
in
te
n
s
it
y
.
T
h
e
h
i
g
h
er
in
te
n
s
it
y
g
r
ad
ien
t
r
eg
io
n
i
s
“
W
ater
s
h
ed
”,
w
h
ic
h
is
d
iv
id
ed
in
n
ea
r
est lo
ca
l
m
i
n
i
m
a
li
k
e
“B
asin
”
[
13]
.
I
n
th
i
s
p
ap
er
w
a
ter
s
h
ed
s
e
g
m
e
n
tatio
n
h
a
v
e
u
s
ed
f
o
r
b
r
ain
tu
m
o
r
s
e
g
m
e
n
tatio
n
f
r
o
m
M
R
I
im
ag
e
s
.
W
e
ass
u
m
e
h
is
h
i
g
h
est
i
n
ten
s
it
y
p
o
in
t,
f
o
r
th
e
i
m
a
g
e
g
r
ad
ien
t
m
ap
p
in
g
,
w
e
c
h
ec
k
all
t
h
e
p
ix
el
s
in
h
,
an
d
s
e
g
m
e
n
t
i
m
a
g
e
u
s
i
n
g
th
eir
n
ea
r
est
p
ix
el
[
1
4
]
.
F
o
llo
w
in
g
s
tep
s
ar
e
f
o
r
w
ater
s
h
ed
s
eg
m
e
n
tatio
n
tech
n
iq
u
e,
h
o
w
i
t
w
il
l
w
o
r
k
.
a.
W
e
ch
ec
k
th
e
n
e
i
g
h
b
o
r
in
g
p
ix
el
f
r
o
m
ca
tc
h
m
e
n
t
t
h
e
n
,
w
e
e
x
a
m
in
e
t
h
e
n
e
ig
h
b
o
r
in
g
p
ix
el
in
h
ei
g
h
t
h
,
i
f
w
e
f
o
u
n
d
th
e
p
ix
e
ls
t
h
en
w
e
la
b
eled
it a
n
d
r
ep
ea
t th
is
p
r
o
ce
s
s
.
b.
I
f
o
u
r
s
ea
r
ch
ed
p
ix
el
is
in
n
ea
r
est
p
ix
el
an
d
h
av
e
t
w
o
d
if
f
er
e
n
t
L
ab
els
th
e
n
w
e
d
ec
lar
e
th
is
as
a
n
e
w
L
ab
e
l
W
th
at
is
o
u
r
“w
ater
s
h
ed
p
ix
el”.
I
n
th
i
s
s
i
tu
at
io
n
a
d
a
m
is
b
u
ilt
w
h
ic
h
s
ep
ar
ate
2
b
asin
s
o
r
2
d
if
f
er
e
n
t
L
ab
els.
c.
Af
ter
t
h
at,
all
w
ater
s
h
ed
p
ix
el
s
ar
e
clu
b
an
d
s
e
g
m
e
n
t
t
h
e
o
b
j
ec
t
w
h
ic
h
w
e
w
a
n
t
to
s
eg
m
e
n
t.
A
t
t
h
e
f
in
al
s
tep
w
h
er
e
w
e
g
et
w
h
at
w
e
f
i
n
d
m
ea
n
s
t
h
er
e
is
n
o
m
o
r
e
n
ei
g
h
b
o
r
in
g
p
i
x
el
to
ch
ec
k
in
h
[
1
4
]
.
Sh
o
w
n
in
F
ig
u
r
e
3
an
d
Fig
u
r
e
4
.
i
n
p
u
t
M
RI
Im
age
s
S
e
gm
e
n
t
at
i
on
(
Wat
e
r
s
h
e
d
)
T
u
m
o
r
De
t
e
c
t
i
on
Ar
e
a
Calc
u
la
t
i
on
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8776
IJ
-
I
C
T
Vo
l.
7
,
No
.
2
,
A
u
g
u
s
t
20
1
8
:
71
–
76
74
Fig
u
r
e
3
.
W
ater
s
h
ed
Seg
m
en
t
atio
n
w
it
h
C
atch
m
e
n
t B
asi
n
Fig
u
r
e
4
.
W
ater
s
h
ed
P
r
in
cip
le
o
f
Si
m
p
l
if
ied
T
o
T
w
o
Di
m
en
s
io
n
W
ater
s
h
ed
s
e
g
m
e
n
tat
io
n
i
s
ed
g
e
b
ased
s
e
g
m
e
n
tatio
n
w
h
ich
f
ir
s
t
u
s
es
i
m
ag
e
ac
q
u
is
i
tio
n
tec
h
n
iq
u
e
a
n
d
th
en
t
h
e
g
r
ad
ien
t
m
a
g
n
itu
d
e
o
f
th
e
i
m
ag
e
i
s
p
er
f
o
r
m
ed
[
15
]
.
Gr
ad
ien
t
o
f
f
at
co
o
r
d
in
ates
(
x
,
y
)
is
d
ef
in
ed
as
t
w
o
d
i
m
e
n
s
io
n
al
co
lu
m
n
v
ec
t
o
r
s
h
o
w
n
i
n
E
q
u
atio
n
(
1
)
a
n
d
th
e
m
a
g
n
itu
d
e
o
f
v
ec
to
r
∇
f
d
en
o
ted
as
M(
x
,
y
)
as
in
E
q
u
at
io
n
(
2
)
.
Gx
A
n
d
g
x
a
r
e
s
o
b
el
o
p
er
ato
r
s
,
ca
lled
as
m
as
k
co
e
f
f
ic
ien
t
3,
s
h
o
w
n
i
n
E
q
u
atio
n
(
3
)
an
d
(
4
)
[
7
]
.
I
n
s
o
b
el
o
p
er
ato
r
t
w
o
co
n
v
o
lu
tio
n
k
er
n
el
ar
e
u
s
ed
v
er
tic
al
an
d
h
o
r
izo
n
tal
to
d
etec
t c
o
n
tr
ast [
1
6
]
.
=
(
)
=
[
]
=
(
1
)
[
,
]
=
(
∇
)
=
√
2
+
2
(
2
)
=
=
(
7
+
2
8
+
9
)
−
(
1
+
2
2
+
9
)
(
3
)
=
=
(
7
+
2
8
+
9
)
−
(
1
+
2
2
+
9
)
(
4
)
4.
RE
SU
L
T
AND
DI
SCUS
SI
O
N
I
n
th
is
s
ec
tio
n
w
e
d
is
c
u
s
s
ab
o
u
t
th
e
ex
p
er
i
m
en
t
r
es
u
lt.
Fo
r
s
eg
m
e
n
tatio
n
an
d
to
d
etec
t
tu
m
o
r
w
e
d
ev
elo
p
ed
GUI
in
MA
T
L
A
B
.
T
h
e
tu
m
o
r
is
s
eg
m
e
n
ted
,
u
s
i
n
g
th
e
w
ater
s
h
ed
s
eg
m
e
n
tatio
n
m
et
h
o
d
.
W
ater
s
h
ed
s
eg
m
e
n
t
is
v
er
y
u
s
ef
u
l
i
n
m
e
d
ical
f
ield
b
ec
au
s
e
th
i
s
m
et
h
o
d
s
o
lv
e
th
e
p
i
x
el
o
v
er
lap
p
in
g
p
r
o
b
lem
in
g
r
a
y
s
ca
le
i
m
a
g
e
.
W
e
d
ev
elo
p
ed
a
GUI
f
o
r
o
u
r
p
r
o
p
o
s
ed
s
y
s
te
m
,
f
ir
s
t
l
y
s
y
s
te
m
tak
e
M
R
I
i
m
a
g
es
f
r
o
m
d
at
ab
ase,
an
d
ex
tr
ac
t
s
e
g
m
e
n
ted
tu
m
o
r
p
ar
t.
W
ith
t
h
e
h
elp
o
f
th
r
e
s
h
o
ld
i
n
g
,
w
e
d
ec
id
e
w
h
et
h
er
th
e
tu
m
o
r
is
“
B
e
n
i
g
n
”
a
n
d
“
Ma
li
g
n
an
t”
an
d
ca
lcu
lated
th
e
tu
m
o
r
co
v
er
a
g
e
an
d
t
u
m
o
r
ar
ea
.
W
e
ca
lcu
late
th
e
t
u
m
o
r
ar
e
a
o
n
th
r
ee
d
if
f
er
en
t
ca
s
es
o
f
i
m
a
g
e
s
s
u
c
h
as
n
o
n
tu
m
o
r
,
b
en
i
g
n
t
u
m
o
r
an
d
m
al
i
g
n
a
n
t
t
u
m
o
r
.
T
h
e
f
o
llo
w
i
n
g
GUI
s
h
o
w
s
th
e
t
h
r
ee
d
if
f
er
e
n
t c
ase
s
.
I
n
ca
s
e
o
f
n
o
r
m
al
b
r
ain
i
m
a
g
e
w
e
g
et
t
h
e
tu
m
o
r
ar
ea
is
0
m
m
2
a
n
d
n
o
s
e
g
m
en
ted
tu
m
o
r
p
ar
t.
5.
B
I
NARY
RO
B
UST
I
NVAR
I
A
NT
SC
AL
AB
L
E
K
E
Y
P
O
I
NT
S (
B
RIS
K
)
T
H
E
M
E
T
H
O
D
Descr
ip
tio
n
o
f
th
e
k
e
y
s
ta
g
es
in
B
R
I
SK,
n
a
m
el
y
f
ea
t
u
r
e
d
etec
tio
n
,
d
escr
ip
to
r
c
o
m
p
o
s
itio
n
an
d
k
e
y
p
o
in
t
m
atc
h
i
n
g
to
th
e
le
v
el
o
f
d
etail
th
at
t
h
e
m
o
tiv
a
ted
r
ea
d
er
ca
n
u
n
d
er
s
tan
d
a
n
d
r
ep
r
o
d
u
ce
.
I
t is i
m
p
o
r
tan
t
to
n
o
te
t
h
at
t
h
e
m
o
d
u
lar
it
y
o
f
t
h
e
m
et
h
o
d
allo
w
s
t
h
e
u
s
e
o
f
th
e
B
R
I
SK
d
etec
to
r
i
n
co
m
b
i
n
atio
n
w
it
h
a
n
y
o
t
h
er
k
e
y
p
o
in
t
d
escr
ip
to
r
an
d
v
ice
v
er
s
a,
o
p
tim
izin
g
f
o
r
t
h
e
d
esire
d
p
er
f
o
r
m
an
c
e
an
d
t
h
e
ta
s
k
at
h
a
n
d
[
9
].
Sh
o
w
n
a
s
i
n
Fig
u
r
e
5
,
Fig
u
r
e
6
,
an
d
Fig
u
r
e
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
I
C
T
I
SS
N:
2252
-
8776
B
r
a
in
Tu
mo
r
Dete
ctio
n
U
s
in
g
W
a
th
er
s
h
ed
S
eg
men
ta
tio
n
Tech
n
iq
u
es a
n
d
A
r
ea
.
.
.
(
Meen
a
ksh
i P
a
r
ee
k
)
75
Fig
u
r
e
5
.
GUI
f
o
r
No
r
m
al
B
r
ain
I
m
a
g
e
Fig
u
r
e
6
.
GUI
f
o
r
B
en
ig
n
T
u
m
o
r
I
m
ag
e
Fig
u
r
e
7
.
GUI
f
o
r
Ma
lig
n
a
t T
u
m
o
r
I
m
ag
e
6.
CO
NCLU
SI
O
N
AND
F
U
T
U
RE
WO
RK
I
n
m
ed
ical
i
m
a
g
e
p
r
o
ce
s
s
in
g
t
h
er
e
ar
e
s
o
m
an
y
s
e
g
m
en
tatio
n
tech
n
iq
u
es.
I
n
t
h
is
p
ap
er
w
e
p
r
esen
t
an
au
to
m
ated
s
y
s
te
m
to
d
etec
t
an
d
class
i
f
y
t
h
e
b
r
ain
tu
m
o
r
.
T
h
esh
o
ld
in
g
is
ap
p
lied
to
e
x
tr
ac
t
o
b
j
ec
t
f
r
o
m
b
ac
k
g
r
o
u
n
d
.
Fo
r
th
e
s
e
g
m
en
t
atio
n
w
e
u
s
ed
w
ater
s
h
ed
m
e
th
o
d
an
d
w
e
class
if
y
t
h
e
tu
m
o
r
i
n
t
w
o
clas
s
e
s
“
B
en
i
g
n
”
a
n
d
“
Ma
li
g
n
a
n
t”.
W
e
ca
lcu
late
th
e
t
u
m
o
r
ar
ea
w
i
th
th
r
ee
ca
s
e
s
s
u
c
h
as
n
o
r
m
al
b
r
ai
n
i
m
a
g
e,
m
a
lig
n
a
n
t
i
m
a
g
e
an
d
b
en
i
g
n
i
m
a
g
e.
W
e
g
et
0
mm
2
w
it
h
n
o
r
m
al
i
m
ag
e.
W
ater
s
h
ed
s
e
g
m
e
n
t
h
a
v
e
o
n
e
d
is
ad
v
an
ta
g
e
i
s
o
v
er
s
e
g
m
e
n
ta
tio
n
.
T
o
o
v
er
co
m
e
th
i
s
ad
v
a
n
t
ag
e
m
ar
k
er
co
n
tr
o
ller
ar
e
u
s
ed
.
I
n
o
u
r
f
u
tu
r
e
w
o
r
k
w
e
u
s
e
w
ater
s
h
ed
m
et
h
o
d
w
it
h
m
ar
k
er
co
n
tr
o
ll
er
an
d
s
o
m
e
f
u
zz
y
tech
n
iq
u
es a
n
d
class
if
y
t
h
e
tu
m
o
r
w
i
th
S
VM
clas
s
if
ier
.
RE
F
E
R
E
NC
E
S
[
1
]
S
e
h
g
a
l,
A
.
,
G
o
e
l,
S
.
,
M
a
n
g
ip
u
d
i
,
P
.
,
M
e
h
ra
,
A
.
,
Ty
a
g
i,
D.,
“
Au
to
ma
ti
c
b
r
a
in
tu
m
o
r
se
g
me
n
t
a
ti
o
n
a
n
d
e
x
tra
c
ti
o
n
i
n
M
R
ima
g
e
s.
In
Ad
v
a
n
c
e
s in
S
i
g
n
a
l
Pro
c
e
ss
in
g
(
CAS
P)
”
,
C
o
n
f
e
re
n
c
e
o
n
(
p
p
.
1
0
4
-
1
0
7
),
J
u
n
e
2
0
1
6
.
IE
EE
.
[
2
]
L
iu
,
J.,
L
i,
M
.
,
W
a
n
g
,
J.,
W
u
,
F
.
,
L
iu
,
T
.
,
P
a
n
,
Y.
,
“
A
su
rv
e
y
o
f
M
RI
-
b
a
se
d
b
ra
i
n
t
u
m
o
r
se
g
m
e
n
t
a
ti
o
n
m
e
th
o
d
s”
.
T
sin
g
h
u
a
S
c
ie
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
1
9
(
6
),
5
7
8
-
5
9
5
.
2
0
1
4
.
[
3
]
Dh
a
g
e
,
P
.
,
P
h
e
g
a
d
e
,
M
.
R.
,
S
h
a
h
,
S
.
K.
,
“
W
a
ter
sh
e
d
se
g
me
n
t
a
ti
o
n
b
r
a
in
tu
m
o
r
d
e
tec
ti
o
n
.
I
n
Per
v
a
siv
e
Co
mp
u
ti
n
g
(
ICPC)
”
,
2
0
1
5
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
(p
p
.
1
-
5
)
,
Ja
n
u
a
ry
2
0
1
5
.
IEE
E.
[
4
]
S
h
a
rm
a
,
M
.
,
&
S
i
n
g
h
,
S
.
,
“
A
M
o
d
if
ied
a
n
d
Im
p
ro
v
e
d
M
e
t
h
o
d
f
o
r
D
e
tec
ti
o
n
o
f
T
u
m
o
r
in
Bra
in
Ca
n
c
e
r”
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
m
p
u
ter
A
p
p
l
ica
ti
o
n
s
,
9
1
(
6
),
2
0
1
4
.
[
5
]
G
o
n
d
a
l,
A
.
H.,
&
Kh
a
n
,
M
.
N.
A
.
,
“
A
re
v
ie
w
o
f
f
u
ll
y
a
u
to
m
a
te
d
tec
h
n
i
q
u
e
s
f
o
r
b
ra
in
t
u
m
o
r
d
e
t
e
c
ti
o
n
f
ro
m
M
R
im
a
g
e
s
”
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
M
o
d
e
rn
E
d
u
c
a
ti
o
n
a
n
d
Co
m
p
u
te
r S
c
ien
c
e
(
IJ
M
ECS
)
,
5
(2
),
5
5
.
[
6
]
Ba
wa
g
e
,
R.
c
h
a
n
d
a
n
e
,
N.,
P
h
a
d
V
.
Zarg
a
r,
S
.
,
“
K
-
M
e
a
n
s
Clu
s
terin
g
b
a
se
d
Bra
in
T
u
m
o
r
De
te
c
ti
o
n
a
n
d
A
re
a
Ca
l
c
u
latio
n
in
M
RI
W
it
h
G
ra
p
h
i
c
a
l
u
se
r
In
terf
a
c
e
”
.
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
E
n
g
i
n
e
e
rin
g
Res
e
a
rc
h
&
T
e
c
h
n
o
lo
g
y
(
IJ
ER
T
),
4
(1
1
)
:
3
7
8
.
[
7
]
Ba
ra
i
y
a
,
N.,
&
M
o
d
i
,
H.,
“
Co
m
p
a
ra
ti
v
e
stu
d
y
o
f
d
if
fe
re
n
t
m
e
th
o
d
s
f
o
r
b
ra
in
tu
m
o
r
e
x
trac
ti
o
n
f
ro
m
M
RI
im
a
g
e
s
u
sin
g
im
a
g
e
p
ro
c
e
ss
i
n
g
”
.
In
d
ia
n
J
o
u
rn
a
l
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
9
(
4
)
,
2
0
1
6
.
[
8
]
S
o
n
a
w
a
n
e
,
M
.
S
.
,
D
h
a
w
a
le,
C.
A
.
,
“
A
b
rie
f
s
u
rv
e
y
o
n
im
a
g
e
se
g
me
n
t
a
ti
o
n
me
th
o
d
s
”
.
I
n
IJCA
P
r
o
c
e
e
d
in
g
s
o
n
Na
ti
o
n
a
l
c
o
n
f
e
re
n
c
e
o
n
Dig
it
a
l
Im
a
g
e
a
n
d
S
ig
n
a
l
P
ro
c
e
ss
in
g
.
2
0
1
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8776
IJ
-
I
C
T
Vo
l.
7
,
No
.
2
,
A
u
g
u
s
t
20
1
8
:
71
–
76
76
[
9
]
L
a
k
sh
m
i,
A
.
,
A
ri
v
o
li
,
T
.
,
“
Bra
i
n
T
u
mo
r
S
e
g
me
n
t
a
ti
o
n
a
n
d
i
ts
Are
a
Ca
lcu
la
ti
o
n
i
n
Br
a
in
M
R
Ima
g
e
s
u
sin
g
K
-
M
e
a
n
Clu
ste
rin
g
a
n
d
F
u
zz
y
C
-
M
e
a
n
Al
g
o
rit
h
m
”
.
2
0
1
5
.
[
1
0
]
Kh
a
n
,
M
.
W
.
,
“
A
su
rv
e
y
:
i
m
a
g
e
se
g
m
e
n
tatio
n
tec
h
n
iq
u
e
s”
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
F
u
t
u
re
Co
mp
u
ter
a
n
d
Co
mm
u
n
ica
ti
o
n
,
3
(2
)
,
8
9
,
2
0
1
4
.
[
1
1
]
Zaito
u
n
,
N.
M
.
,
&
A
q
e
l,
M
.
J.,
“
S
u
rv
e
y
o
n
ima
g
e
se
g
me
n
t
a
ti
o
n
tec
h
n
iq
u
e
s
”
.
P
r
o
c
e
d
ia
Co
m
p
u
ter
S
c
ien
c
e
,
6
5
,
7
9
7
-
8
0
6
,
2
0
1
5
.
[
1
2
]
Ba
lafa
r,
M
.
A
.
,
Ra
m
li
,
A
.
R.
,
S
a
rip
a
n
,
M
.
I.
,
M
a
sh
o
h
o
r,
S
.
,
“
Re
v
iew
o
f
b
ra
in
M
RI
im
a
g
e
se
g
m
e
n
tatio
n
m
e
th
o
d
s”
.
Arti
fi
c
ia
l
I
n
telli
g
e
n
c
e
Rev
iew
,
3
3
(
3
),
2
6
1
-
2
7
4
,
2
0
1
0
.
[
1
3
]
S
a
lm
a
n
,
N.,
“
Im
a
g
e
se
g
m
e
n
tatio
n
b
a
se
d
o
n
w
a
ters
h
e
d
a
n
d
e
d
g
e
d
e
t
e
c
ti
o
n
tec
h
n
iq
u
e
s”
.
I
n
t.
Ara
b
J
.
In
f.
T
e
c
h
n
o
l
.
,
3
(2
)
,
104
-
1
1
0
,
2
0
0
6
.
[
1
4
]
Ju
n
g
,
C.
R.
,
S
c
h
a
rc
a
n
sk
i,
J.,
“
Ro
b
u
st
w
a
ters
h
e
d
se
g
m
e
n
tatio
n
u
si
n
g
w
a
v
e
lets”
.
Ima
g
e
a
n
d
Vi
si
o
n
C
o
mp
u
t
in
g
.
2
3
(7
)
,
661
-
6
6
9
,
2
0
0
5
.
[
1
5
]
S
a
lm
a
n
,
S
.
D.,
&
Ba
h
ra
n
i,
A
.
A
.
,
“
S
e
g
m
e
n
tatio
n
o
f
tu
m
o
r
t
issu
e
in
g
ra
y
m
e
d
ica
l
i
m
a
g
e
s
u
sin
g
w
a
ters
h
e
d
tran
sf
o
r
m
a
ti
o
n
m
e
th
o
d
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
me
n
ts i
n
Co
mp
u
t
in
g
T
e
c
h
n
o
l
o
g
y
,
2
(4
)
,
2
0
1
0
.
[
1
6
]
Jo
sh
i,
C.
,
P
u
ro
h
it
,
G
.
N.,
M
u
k
h
e
r
jee
,
S
.
,
M
u
lt
is
p
e
c
tral
S
a
telli
te
Im
a
g
e
Re
tri
e
v
a
l
Us
in
g
T
h
e
Co
m
b
in
a
ti
o
n
o
f
F
e
a
tu
re
s
Co
lo
r,
S
h
a
p
e
a
n
d
T
e
x
tu
re
.
Evaluation Warning : The document was created with Spire.PDF for Python.