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
.
5
,
Octo
b
e
r
2
0
1
8
,
p
p
.
3
5
8
7
~
3
5
9
3
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v8
i
5
.
p
p
3
5
8
7
-
3593
3587
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
A
New
Approa
ch
to the
Det
ection
o
f
M
a
m
m
o
g
ra
m
B
o
unda
ry
M
o
ha
m
m
e
d R
m
ili
1
,
Abdel
ma
j
id E
l M
o
ut
a
o
ua
kk
il
2
,
M
o
us
a
t
a
ph
a
M
.
Sa
leck
3
,
M
a
k
s
i B
o
ucha
ib
4
,
F
a
t
iha
Adna
ni
5
,
E
l
M
ehdi E
l
A
ro
us
s
i
6
1,
2,
3
L
A
b
o
ra
to
ry
o
f
Re
se
a
rc
h
o
n
Op
ti
m
iza
ti
o
n
o
f
Em
e
r
g
e
n
t
S
y
ste
m
s,
Ne
tw
o
rk
a
n
d
Im
a
g
in
g
o
f
Co
m
p
u
ter S
c
ien
c
e
De
p
a
rtme
n
t
o
f
Ch
o
u
a
ï
b
Do
u
k
k
a
li
Un
iv
e
rsity
,
E
L
Ja
d
id
a
,
M
o
r
o
c
c
o
1,
5,
6
L
A
b
o
ra
to
ry
o
f
M
a
th
e
m
a
ti
c
s
Ap
p
li
e
d
o
n
P
h
y
sic
s an
d
In
d
u
stry
,
M
a
th
e
m
a
ti
c
s D
e
p
a
rt
m
e
n
t
o
f
Ch
o
u
a
ïb
Do
u
k
k
a
li
Un
iv
e
rsity
,
EL
Ja
d
id
a
,
M
o
r
o
c
c
o
4
De
p
a
rtme
n
t
o
f
Ra
d
io
lo
g
y
,
Ho
sp
i
tal
M
o
h
a
m
m
e
d
V
,
El
jad
i
d
a
,
M
o
ro
c
c
o
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
5
,
2
0
1
8
R
ev
i
s
ed
A
p
r
1
5
,
2
0
1
8
A
cc
ep
ted
A
p
r
22
,
2
0
1
8
M
a
m
m
o
g
ra
p
h
y
is
a
m
e
th
o
d
u
se
d
f
o
r
th
e
d
e
tec
ti
o
n
o
f
b
re
a
st
c
a
n
c
e
r.
c
o
m
p
u
ter
-
a
id
e
d
d
iag
n
o
stic
(CA
D)
s
y
ste
m
s
h
e
lp
th
e
ra
d
i
o
lo
g
i
st
in
th
e
d
e
tec
ti
o
n
a
n
d
in
terp
re
tati
o
n
o
f
m
a
ss
in
b
re
a
st
m
a
m
m
o
g
ra
p
h
y
.
On
e
o
f
th
e
im
p
o
rtan
t
in
f
o
rm
a
ti
o
n
o
f
a
m
a
ss
is
it
s
c
o
n
t
o
u
r
a
n
d
i
ts
f
o
rm
b
e
c
a
u
se
it
p
ro
v
id
e
s
v
a
lu
a
b
le
i
n
f
o
rm
a
ti
o
n
a
b
o
u
t
th
e
a
b
n
o
rm
a
li
ty
o
f
a
m
a
ss
.
T
h
e
a
c
c
u
ra
c
y
in
t
h
e
re
c
o
g
n
it
i
o
n
o
f
th
e
sh
a
p
e
o
f
a
m
a
ss
is
re
late
d
to
th
e
a
c
c
u
ra
c
y
o
f
th
e
d
e
tec
ted
m
a
ss
c
o
n
to
u
rs.
In
th
i
s
w
o
r
k
we
p
ro
p
o
se
a
n
e
w
a
p
p
ro
a
c
h
f
o
r
d
e
tec
ti
n
g
th
e
b
o
un
d
a
ries
o
f
les
io
n
in
m
a
m
m
o
g
ra
p
h
y
i
m
a
g
e
s
b
a
s
e
d
o
n
re
g
io
n
g
ro
w
in
g
a
lg
o
rit
h
m
w
it
h
o
u
t
u
si
n
g
th
e
th
re
sh
o
l
d
,
th
e
p
ro
p
o
se
d
m
e
th
o
d
re
q
u
ires
a
n
in
it
ial
re
c
tan
g
le
su
rr
o
u
n
d
i
n
g
th
e
les
io
n
se
lec
ted
m
a
n
u
a
ll
y
b
y
th
e
ra
d
io
l
o
g
ist
(Re
g
io
n
Of
In
tere
st),
w
h
e
re
th
e
re
g
io
n
g
ro
w
i
n
g
a
lg
o
rit
h
m
a
p
p
li
e
s
o
n
li
n
e
s
se
g
m
e
n
ts
th
a
t
a
tt
a
c
h
e
a
c
h
p
ix
e
l
o
f
th
is
re
c
tan
g
le
w
it
h
t
h
e
se
e
d
p
o
i
n
t,
su
c
h
a
s th
e
e
n
d
s (se
e
d
s) o
f
e
a
c
h
li
n
e
se
g
m
e
n
t
g
ro
w i
n
a
d
irec
ti
o
n
to
w
a
rd
s o
n
e
a
n
o
th
e
r.
T
h
e
p
r
o
p
o
se
d
a
p
p
ro
a
c
h
i
s
e
v
a
lu
a
ted
o
n
a
se
t
o
f
d
a
ta
w
it
h
2
0
m
a
ss
e
s
o
f
th
e
M
IA
S
b
a
s
e
w
h
o
se
c
o
n
to
u
rs
a
re
a
n
n
o
tate
d
m
a
n
u
a
ll
y
b
y
e
x
p
e
rt
ra
d
io
l
o
g
ists.
T
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
th
e
m
e
th
o
d
is
e
v
a
lu
a
ted
in
ter
m
s
o
f
sp
e
c
if
icit
y
,
se
n
siti
v
it
y
,
a
c
c
u
ra
c
y
a
n
d
o
v
e
rlap
.
A
ll
th
e
f
in
d
in
g
s
a
n
d
d
e
tails
o
f
a
p
p
ro
a
c
h
a
re
p
re
se
n
ted
i
n
d
e
tail.
K
ey
w
o
r
d
:
L
i
n
e
s
e
g
m
e
n
t
Ma
m
m
o
g
r
ap
h
y
Ma
s
s
s
e
g
m
en
tatio
n
R
eg
io
n
g
r
o
w
i
n
g
al
g
o
r
ith
m
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
:
Mo
h
a
m
m
ed
R
m
ili,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
S
cie
n
ce
,
Un
i
v
er
s
it
y
C
h
o
u
aïb
Do
u
k
k
ali,
E
L
J
ad
id
a,
Mo
r
o
cc
o
.
E
m
ail:
g
m
r
m
il
i@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
C
u
r
r
en
tl
y
b
r
ea
s
t
ca
n
ce
r
is
th
e
s
ec
o
n
d
ca
u
s
e
o
f
w
o
m
en
’
s
d
ea
th
.
C
a
n
ce
r
af
f
ec
ts
w
o
m
e
n
b
et
w
ee
n
f
o
r
t
y
a
n
d
f
i
f
t
y
-
f
i
v
e
y
ea
r
s
o
ld
[
1
]
.
I
t
attac
k
s
w
o
m
e
n
m
o
s
t
[
2
]
.
Un
f
o
r
tu
n
atel
y
,
t
h
er
e
is
s
till
n
o
p
r
ev
e
n
tio
n
a
n
d
th
e
s
o
lu
tio
n
lies
i
n
th
e
ea
r
l
y
d
etec
tio
n
to
in
cr
ea
s
e
th
e
ef
f
ec
ti
v
en
e
s
s
o
f
tr
ea
t
m
en
t
an
d
r
ed
u
ce
th
e
r
is
k
o
f
m
o
r
ta
lit
y
.
I
n
b
r
ea
s
t
ca
n
ce
r
s
ett
in
g
,
th
e
e
f
f
ec
ti
v
en
e
s
s
o
f
th
is
p
ath
o
lo
g
y
t
r
ea
t
m
en
t
h
a
v
e
n
ee
d
t
h
e
ea
r
l
y
d
etec
tio
n
.
A
t
p
r
esen
t
Ma
m
m
o
g
r
ap
h
y
is
th
e
m
o
s
t
e
f
f
ec
tiv
e
tech
n
iq
u
e
f
o
r
t
h
e
ea
r
l
y
d
iag
n
o
s
i
s
o
f
b
r
ea
s
t
ca
n
ce
r
[
3
]
.
Diag
n
o
s
tic
s
u
p
p
o
r
t
o
f
tec
h
n
iq
u
es
is
b
ein
g
d
ev
e
lo
p
ed
to
f
ac
i
litate
t
h
e
w
o
r
k
o
f
r
ad
io
lo
g
is
t
s
.
A
cc
o
r
d
in
g
to
th
is
v
is
io
n
,
f
o
r
th
e
la
s
t
y
ea
r
s
C
o
m
p
u
ter
-
Ass
is
ted
Dia
g
n
o
s
is
b
ec
am
e
v
er
y
i
m
p
o
r
ta
n
t in
t
h
e
i
n
ter
n
atio
n
al
r
e
s
ea
r
ch
i
n
th
e
w
o
r
ld
[
4
]
.
Dete
ctio
n
a
n
d
s
eg
m
e
n
tatio
n
o
f
th
e
m
a
s
s
i
n
m
a
m
m
o
g
r
ap
h
y
f
r
o
m
b
ac
k
g
r
o
u
n
d
ti
s
s
u
e
i
s
a
m
aj
o
r
p
r
o
b
lem
.
esp
ec
iall
y
,
f
i
n
d
in
g
a
co
r
r
ec
t
m
as
s
ed
g
e
is
th
e
m
aj
o
r
k
e
y
f
o
r
g
o
o
d
m
a
s
s
i
n
ter
p
r
eta
tio
n
,
b
e
ca
u
s
e
m
as
s
in
ter
p
r
etatio
n
d
ep
en
d
s
o
n
t
h
e
ed
g
e,
m
ar
g
i
n
a
n
d
s
h
ap
e
ch
ar
a
cter
is
tics
o
f
a
m
a
m
m
ar
y
m
as
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
.
5
,
Octo
b
er
2
0
1
8
:
3
5
8
7
–
3
5
9
3
3588
I
n
m
a
m
m
o
g
r
ap
h
ic
d
iag
n
o
s
i
s
,
n
o
n
-
ca
n
ce
r
o
u
s
lesi
o
n
s
ca
n
b
e
m
is
in
ter
p
r
eted
as
ca
n
ce
r
(
f
als
e
p
o
s
itiv
e
v
alu
e)
,
w
h
ile
ca
n
ce
r
s
ca
n
b
e
m
is
in
ter
p
r
eted
as
n
o
n
-
ca
n
ce
r
o
u
s
l
esio
n
s
(
f
al
s
e
n
eg
a
tiv
e
v
alu
e)
.
C
o
r
r
esp
o
n
d
in
g
l
y
,
r
ad
io
lo
g
is
ts
f
ail
to
d
etec
t
1
0
%
to
3
0
%
o
f
b
r
ea
s
t
ca
n
ce
r
s
[
5
]
-
[
7
]
.
C
o
m
p
u
ter
-
aid
ed
d
etec
tio
n
(
C
AD)
s
y
s
te
m
s
h
av
e
b
ee
n
d
ev
elo
p
ed
to
r
ed
u
ce
t
h
e
co
s
t
an
d
i
m
p
r
o
v
e
t
h
e
ab
ilit
y
o
f
m
ed
ical
i
m
a
g
e
s
in
ter
p
r
etatio
n
a
n
d
d
is
tin
g
u
is
h
b
et
w
ee
n
b
en
ig
n
an
d
m
al
ig
n
a
n
t tis
s
u
e
s
[
8
]
-
[
1
0
]
.
Su
c
h
a
C
A
D
x
s
y
s
te
m
r
eq
u
ir
es
th
at
th
e
m
a
s
s
li
m
it
b
e
d
etec
ted
as
ac
cu
r
atel
y
as
p
o
s
s
ib
le.
C
o
n
s
eq
u
en
tl
y
h
e
s
eg
m
e
n
tatio
n
alg
o
r
it
h
m
s
h
o
u
ld
d
etec
t
an
ac
cu
r
ate
li
m
i
t
o
f
th
e
m
ass
.
i
n
C
ADx
s
y
s
te
m
s
th
e
ac
cu
r
a
c
y
o
f
t
h
e
s
e
g
m
e
n
tatio
n
o
f
t
h
e
b
r
ea
s
t
m
as
s
co
n
to
u
r
p
lay
s
a
n
i
m
p
o
r
tan
t
r
o
le
i
n
m
as
s
clas
s
i
f
icatio
n
,
b
ec
au
s
e
s
in
ce
m
o
s
t
o
f
t
h
e
cr
u
cial
p
r
o
p
er
ties
o
f
th
e
m
a
m
m
ar
y
m
as
s
es
t
h
at
d
e
f
i
n
e
m
ali
g
n
a
n
c
y
ar
e
r
elate
d
to
its
m
o
r
p
h
o
lo
g
y
.
C
o
n
s
eq
u
e
n
tl
y
,
t
h
e
m
ali
g
n
an
t
m
a
s
s
e
s
f
o
r
m
ir
r
eg
u
lar
f
o
r
m
s
;
C
o
n
v
er
s
el
y
,
t
h
e
b
en
ig
n
m
a
s
s
es
f
o
r
m
r
eg
u
lar
f
o
r
m
s
.
A
l
s
ar
o
r
i
et
a
l
[
1
1
]
,
h
av
e
ap
p
li
ed
th
e
Mu
ltip
le
-
T
h
r
esh
o
ld
in
g
m
et
h
o
d
OT
SU
to
s
eg
m
en
t
t
h
e
r
eg
io
n
o
f
in
ter
est
(
R
OI
)
.
T
h
en
T
h
e
tex
tu
r
e
ch
ar
ac
ter
is
tics
o
f
th
e
s
e
g
m
en
ted
R
OI
w
h
ic
h
ar
e
u
s
ed
to
cl
ass
i
f
y
t
h
e
R
OI
as
ab
n
o
r
m
al
o
r
n
o
r
m
al
t
is
s
u
e
b
y
u
s
i
n
g
a
Ne
u
r
al
Net
w
o
r
k
,
I
n
f
o
r
m
at
io
n
(
A
NN)
.
An
an
d
et
a
l
[
1
2
]
,
u
s
ed
a
h
y
b
r
id
o
f
Fu
zz
y
c
-
Me
a
n
s
al
g
o
r
ith
m
an
d
Sel
f
Or
g
a
n
izi
n
g
Ma
p
alg
o
r
ith
m
to
s
e
g
m
en
t
th
e
b
r
ea
s
t
i
m
ag
e
a
n
d
th
e
n
ca
teg
o
r
ize
t
h
e
t
u
m
o
u
r
:
a
f
f
ec
te
d
b
r
ea
s
t
i
m
a
g
es
an
d
n
o
r
m
a
l
b
r
ea
s
t
i
m
ag
e
s
.
S
h
ar
ee
f
[
1
3
]
ap
p
lied
an
al
g
o
r
ith
m
b
ased
o
n
th
e
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
an
d
s
e
g
m
e
n
tat
io
n
w
ater
s
h
ed
tr
a
n
s
f
o
r
m
atio
n
.
T
h
is
ap
p
r
o
ac
h
h
as
o
b
tain
ed
a
v
er
y
s
i
m
ilar
d
ia
g
n
o
s
is
o
f
b
r
ea
s
t t
u
m
o
u
r
i
n
t
y
p
e
s
o
f
m
ed
ical
i
m
ag
e
s
[
1
4
]
,
pr
o
p
o
s
ed
a
n
e
w
al
g
o
r
ith
m
s
eg
m
e
n
tatio
n
to
i
m
p
r
o
v
e
th
e
co
n
to
u
r
o
f
a
m
a
s
s
o
f
a
g
iv
e
n
r
eg
io
n
o
f
i
n
ter
est
b
ased
o
n
t
h
e
r
eg
io
n
g
r
o
w
i
n
g
alg
o
r
ith
m
w
it
h
t
h
e
ab
il
it
y
to
ad
ap
tiv
el
y
ad
j
u
s
t
th
e
t
h
r
es
h
o
ld
v
alu
e.
Ved
an
ar
a
y
an
a
n
e
t
a
l
[
1
5
]
,
p
r
o
p
o
s
e
a
s
eg
m
e
n
tatio
n
tec
h
n
iq
u
e
b
ase
d
o
n
m
o
d
i
f
ied
e
x
p
ec
tatio
n
s
Ma
x
i
m
izatio
n
a
n
d
Mo
d
if
ied
Sn
a
k
e
A
l
g
o
r
ith
m
to
is
o
late
th
e
ab
n
o
r
m
ali
t
y
.
An
d
f
o
r
d
escr
ib
in
g
ab
n
o
r
m
alit
y
,
t
h
is
ap
p
r
o
ac
h
u
s
es
th
e
f
o
llo
win
g
f
ea
t
u
r
es
:
A
r
ea
,
Min
o
r
A
x
i
s
L
en
g
t
h
,
Ma
j
o
r
Ax
is
L
e
n
g
t
h
,
P
er
im
e
ter
,
Or
ien
tatio
n
,
C
e
n
tr
o
id
,
E
cc
en
tr
ici
t
y
,
E
q
u
i
v
Dia
m
eter
,
So
lid
it
y
an
d
co
n
v
e
x
ar
ea
.
T
h
e
b
ac
k
p
r
o
p
ag
atio
n
n
et
w
o
r
k
is
u
s
ed
to
d
eter
m
in
e
t
h
e
p
r
esen
ce
o
f
ca
n
ce
r
.
S.
M.
L
.
d
e
L
i
m
a
et
a
l
[
1
6
]
,
p
r
o
p
o
s
ed
a
m
eth
o
d
f
o
r
d
etec
tin
g
an
d
class
i
f
y
i
n
g
b
r
ea
s
t
l
esio
n
s
u
s
i
n
g
f
ea
t
u
r
e
ex
tr
ac
tio
n
b
ased
o
n
t
h
e
C
a
lcu
l
atio
n
o
f
Z
er
n
i
k
e
Mo
m
e
n
t
s
f
r
o
m
a
s
er
ies
o
f
m
u
l
ti
-
r
e
s
o
lu
tio
n
i
m
a
g
e
co
m
p
o
n
e
n
t
s
o
b
tain
ed
b
y
t
h
e
s
er
ies
o
f
w
a
v
elets.
C
h
a
g
h
ar
i
et
a
l
[
1
7
]
,
p
r
esen
ted
a
n
e
w
m
eth
o
d
to
d
etec
t
th
e
m
a
s
s
i
n
th
e
m
a
m
m
o
g
r
a
m
b
ased
o
n
ce
llu
lar
lear
n
i
n
g
au
to
m
ata
a
lg
o
r
ith
m
.
m
a
m
m
o
g
a
m
h
as
lo
w
co
n
tr
as
t
o
f
m
icr
o
ca
lcif
icatio
n
s
an
d
n
o
is
e,
K.
T
aif
i
et
a
l
[
1
8
]
,
p
r
o
p
o
s
ed
a
h
y
b
r
id
m
et
h
o
d
,
to
en
h
an
ce
th
e
co
n
tr
ast
o
f
a
m
a
m
m
o
g
r
ap
h
y
i
m
ag
e,
co
m
b
i
n
in
g
co
n
to
u
r
let
a
n
d
h
o
m
o
m
o
r
p
h
ic
f
ilter
i
n
g
.
Mu
s
ta
f
a
et
a
l
[
1
9
]
,
p
r
esen
ts
a
m
et
h
o
d
f
o
r
s
eg
m
e
n
ti
n
g
le
s
io
n
s
u
s
in
g
t
h
e
ac
ti
v
e
C
h
a
n
-
Vese
co
n
to
u
r
an
d
t
h
e
lo
ca
lized
ac
ti
v
e
co
n
to
u
r
.
t
h
en
,
t
h
e
ef
f
ec
tiv
e
n
e
s
s
o
f
t
h
ese
b
o
th
m
e
th
o
d
s
ar
e
co
m
p
ar
ed
an
d
ch
o
s
en
to
b
e
th
e
b
est
m
et
h
o
d
.
I
n
th
i
s
w
o
r
k
,
a
n
e
w
m
eth
o
d
to
s
eg
m
en
t
th
e
co
n
to
u
r
o
f
m
a
s
s
e
s
is
d
esi
g
n
ed
b
ased
o
n
R
e
g
io
n
Gr
o
w
in
g
A
l
g
o
r
ith
m
th
a
t
i
s
ap
p
lied
in
t
h
is
r
esear
ch
o
n
ea
c
h
l
in
e
s
e
g
m
en
t
t
h
at
at
tach
ea
ch
p
ix
el
o
f
th
e
r
ec
tan
g
le
to
th
e
s
ee
d
p
o
in
t,
w
h
ic
h
p
r
esen
t
s
th
e
r
eg
io
n
o
f
i
n
ter
est.
T
h
is
p
ap
er
is
o
r
g
an
ized
as
f
o
llo
w
s
.
I
n
Sectio
n
(
2
)
,
w
e
p
r
esen
t
th
e
m
eth
o
d
o
lo
g
y
f
o
r
m
as
s
s
eg
m
e
n
tatio
n
.
Sectio
n
(
3
)
in
v
o
lv
es
s
o
m
e
e
x
p
er
i
m
e
n
ts
to
v
er
if
y
an
d
d
i
s
cu
s
s
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
.
C
o
n
cl
u
s
io
n
an
d
f
u
tu
r
e
w
o
r
k
i
s
d
is
cu
s
s
ed
i
n
Sectio
n
(
4
)
.
2.
M
E
T
H
O
D
O
L
O
G
Y
I
n
th
i
s
s
ec
tio
n
,
w
e
d
escr
ib
e
t
h
e
s
tep
s
o
f
t
h
e
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
:
i
m
ag
e
ac
q
u
is
itio
n
,
p
r
etr
ea
t
m
e
n
t,
an
d
Ma
s
s
ac
c
u
r
ate
s
eg
m
e
n
tatio
n
.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
o
lo
g
y
o
f
b
r
ea
s
t
m
as
s
s
e
g
m
e
n
tat
io
n
ca
n
b
e
s
ch
e
m
atica
ll
y
d
escr
ib
ed
in
Fi
g
u
r
e
1
.
2
.
1
.
I
m
a
g
e
a
cquis
it
io
n
T
h
e
cr
ed
it
o
f
th
e
m
a
m
m
o
g
r
a
m
s
p
r
o
v
id
ed
in
t
h
i
s
w
o
r
k
ar
e
tak
en
f
r
o
m
Ma
m
m
o
g
r
ap
h
y
I
m
a
g
e
An
al
y
s
i
s
So
ciet
y
(
MI
A
S)
[
2
0
]
.
T
h
e
MI
A
S
o
f
f
er
ed
s
o
m
e
co
r
r
esp
o
n
d
in
g
in
f
o
r
m
at
io
n
o
f
l
esio
n
ar
ea
s
u
c
h
as
t
y
p
e,
lo
ca
tio
n
,
s
ev
er
it
y
,
ce
n
tr
al
co
o
r
d
in
ate
an
d
r
ad
iu
s
b
y
ex
p
er
ts
an
d
ea
ch
i
m
ag
e
i
s
1
0
2
4
×1
0
2
4
p
ix
els.
2
.
2
.
P
re
t
re
a
t
m
e
nt
Ma
m
m
o
g
r
a
m
s
ar
e
h
i
g
h
l
y
n
o
is
y
i
m
ag
e
s
.
Si
n
ce
o
u
r
ap
p
r
o
ac
h
is
b
ased
o
n
p
ix
el
i
n
ten
s
itie
s
,
n
o
is
e
m
a
y
d
is
to
r
t th
e
r
esu
l
ts
.
S
o
,
a
f
ilter
i
n
g
o
p
er
atio
n
is
r
eq
u
ir
ed
.
I
n
o
u
r
p
r
o
p
o
s
ed
m
et
h
o
d
t
h
e
f
ir
s
t
s
tep
i
n
v
o
l
v
es
p
r
etr
ea
t
m
e
n
t
u
s
i
n
g
Me
d
ian
Fil
ter
,
I
t
i
s
a
n
o
n
li
n
ea
r
f
ilter
w
h
ic
h
is
e
f
f
icie
n
t
i
n
r
e
m
o
v
in
g
s
al
t
an
d
p
ep
p
er
n
o
is
e
te
n
d
s
to
k
ee
p
t
h
e
s
h
ar
p
n
es
s
o
f
i
m
ag
e
ed
g
es
w
h
il
e
r
e
m
o
v
i
n
g
n
o
is
e
[
2
1
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
A
N
ew A
p
p
r
o
a
ch
to
th
e
Dete
ct
io
n
o
f Ma
mmo
g
r
a
m
B
o
u
n
d
a
r
y
(
Mo
h
a
mme
d
R
mili
)
3589
2
.
3
.
Neig
hb
o
rho
o
d
W
h
en
p
r
o
ce
s
s
i
n
g
a
n
i
m
a
g
e,
is
n
ec
ess
ar
y
to
ad
d
a
d
ef
in
itio
n
o
f
th
e
n
e
i
g
h
b
o
r
h
o
o
d
b
et
w
ee
n
th
e
p
ix
el
s
.
I
n
t
h
e
2
D
ca
s
e,
i
t
i
s
n
ec
es
s
ar
y
to
s
p
ec
i
f
y
w
h
et
h
er
a
p
i
x
el
is
co
n
s
id
er
ed
h
a
s
n
ei
g
h
b
o
r
s
t
h
e
p
ix
els
w
h
ich
h
a
v
e
o
n
e
s
id
e
in
co
m
m
o
n
w
it
h
it a
l
o
n
e
o
r
also
th
o
s
e
th
at
s
h
ar
e
a
v
er
tex
w
i
th
it.
I
n
o
u
r
w
o
r
k
,
t
w
o
p
i
x
el
s
ar
e
co
n
s
id
er
ed
n
ei
g
h
b
o
r
s
if
th
e
y
h
a
v
e
at
least
o
n
e
co
r
n
er
i
n
co
m
m
o
n
,
s
o
t
h
at
ea
ch
p
ix
el
i
s
n
o
t a
t t
h
e
ed
g
e
o
f
th
e
i
m
a
g
e
w
it
h
8
n
ei
g
h
b
o
r
in
g
p
ix
els,
w
h
ich
i
s
th
e
m
a
x
i
m
u
m
.
2
.
4
.
B
re
a
s
t
m
a
s
s
co
nto
ur
s
eg
m
e
n
t
a
t
io
n a
lg
o
rit
h
m
I
n
th
i
s
ap
p
r
o
ac
h
w
e
ce
n
tr
e
o
n
d
etec
tio
n
th
e
m
ass
l
i
m
it
s
.
We
p
r
o
p
o
s
e
a
n
e
w
b
r
ea
s
t
m
as
s
s
eg
m
e
n
tatio
n
m
et
h
o
d
f
o
r
a
g
iv
e
n
R
OI
in
m
a
m
m
o
g
r
ap
h
i
c
i
m
ag
e.
T
h
is
m
et
h
o
d
r
eq
u
ir
es
a
m
as
s
-
li
m
iti
n
g
r
ec
tan
g
le
th
a
t
is
d
r
a
w
n
m
an
u
a
ll
y
b
y
th
e
u
s
er
an
d
g
i
v
en
to
th
e
s
y
s
te
m
as
in
p
u
t.
i
n
t
h
is
w
o
r
k
W
e
d
o
n
o
t
p
r
ef
er
to
u
s
e
th
e
r
e
s
u
l
t
o
f
a
m
eth
o
d
o
f
s
e
g
m
en
ta
ti
o
n
,
b
ec
au
s
e
f
als
e
p
o
s
itiv
e
s
ca
n
p
r
o
ce
ed
in
m
a
ch
in
e
s
e
g
m
en
ta
tio
n
tech
n
iq
u
es
[
2
2
]
T
h
e
d
etec
tio
n
o
f
b
r
ea
s
t
m
a
s
s
i
n
a
m
a
m
m
o
g
r
ap
h
ic
i
m
a
g
e
is
b
ased
o
n
th
e
la
w
t
h
at
th
e
p
ix
e
ls
w
it
h
i
n
a
m
as
s
h
a
v
e
d
if
f
er
en
t
c
h
ar
ac
ter
i
s
tics
f
r
o
m
th
e
o
t
h
er
p
ix
els
t
h
at
s
u
r
r
o
u
n
d
i
n
g
th
e
m
ass
.
T
h
ese
ch
ar
ac
ter
is
tic
s
m
a
y
b
e
ass
o
ciate
d
to
th
e
in
te
n
s
it
y
o
f
th
e
g
r
a
y
le
v
el,
t
h
e
m
o
r
p
h
o
lo
g
ical
ch
ar
a
cter
i
s
tics
o
r
th
e
te
x
t
u
r
e.
Me
th
o
d
s
o
f
b
r
ea
s
t
m
a
s
s
s
e
g
m
en
tatio
n
ca
n
b
e
cla
s
s
i
f
ied
i
n
to
t
h
r
ee
g
r
o
u
p
s
:
co
n
to
u
r
-
b
as
ed
,
r
eg
io
n
-
b
ased
an
d
g
r
o
u
p
-
b
ased
.
C
o
n
t
o
u
r
-
b
ased
m
et
h
o
d
s
d
e
p
en
d
o
n
th
e
b
o
u
n
d
ar
y
o
f
r
eg
io
n
s
,
w
h
ile
R
e
g
io
n
-
b
ased
m
et
h
o
d
s
d
iv
id
e
th
e
i
m
a
g
e
in
t
o
s
p
ati
all
y
co
n
n
ec
ted
h
o
m
o
g
e
n
eo
u
s
r
eg
io
n
s
an
d
,
th
e
g
r
o
u
p
in
g
m
eth
o
d
s
ar
r
an
g
e
th
e
p
ix
e
ls
t
h
at
h
a
v
e
t
h
e
s
a
m
e
p
r
o
p
er
ties
an
d
ca
n
p
r
o
d
u
ct
u
n
co
n
n
ec
ted
r
eg
io
n
s
.
Gi
v
e
n
t
h
at
w
e
ar
e
ai
m
in
g
to
i
m
p
r
o
v
e
a
r
eg
io
n
'
s
m
as
s
li
m
it,
w
e
p
r
o
p
o
s
e
an
i
m
p
r
o
v
e
m
e
n
t
in
t
h
e
r
eg
io
n
g
r
o
w
i
n
g
a
p
p
r
o
ac
h
,
w
h
ich
i
s
o
n
e
o
f
th
e
k
n
o
w
n
m
et
h
o
d
s
in
t
h
e
r
eg
i
o
n
.
I
n
o
u
r
ap
p
r
o
ac
h
th
e
in
i
tial
p
o
in
ts
ar
e
t
h
e
p
o
in
ts
o
f
t
h
e
r
ec
tan
g
le
a
n
d
its
ce
n
ter
.
Ou
r
s
eg
m
en
tatio
n
ap
p
r
o
ac
h
w
id
en
s
ea
ch
r
eg
io
n
o
r
an
in
itial
p
o
in
t
b
y
n
ei
g
h
b
o
r
in
g
p
ix
el
s
s
i
m
ilar
in
o
n
e
d
ir
ec
tio
n
o
n
a
li
n
e
s
eg
m
e
n
t
s
o
t
h
at
th
e
en
d
s
o
f
e
ac
h
li
n
e
s
eg
m
e
n
t
w
id
e
n
i
n
a
d
ir
ec
tio
n
to
w
ar
d
s
o
n
e
a
n
o
th
er
,
th
e
p
r
o
ce
s
s
s
to
p
s
w
h
e
n
ea
ch
p
i
x
el
i
n
t
h
e
li
n
e
s
e
g
m
e
n
t
b
i
n
d
s
to
a
r
eg
io
n
,
w
it
h
o
u
t
u
s
in
g
t
h
e
t
h
r
es
h
o
ld
.
A
s
i
m
ilar
ter
m
m
ea
n
s
a
p
ix
el
w
h
o
s
e
E
u
clid
ea
n
d
i
s
tan
c
e
f
r
o
m
its
i
n
te
n
s
i
t
y
to
m
ea
n
o
f
th
e
r
eg
io
n
i
s
m
in
i
m
al.
I
n
th
e
f
o
llo
w
i
n
g
,
w
e
p
r
esen
t
th
e
s
tep
s
o
f
o
u
r
m
et
h
o
d
s
u
ch
as
S
=
{S
1
.
.
.
S
n
}
th
e
p
i
x
els
o
f
t
h
e
r
ec
tan
g
le
,
S
0
its
ce
n
ter
an
d
p
i
)
th
e
E
u
clid
ea
n
d
is
ta
n
ce
b
et
w
ee
n
p
i
an
d
ar
e
clo
s
er
ce
n
tr
o
id
to
th
e
g
r
o
u
p
,
P
r
ed
(p
i
)
b
e
th
e
p
r
e
d
ec
ess
o
r
o
f
a
p
i
x
el
p
i
a
n
d
V
(
p
)
b
e
t
h
e
i
n
t
e
n
s
i
t
y
o
f
g
r
a
y
l
e
v
e
l
o
f
t
h
e
t
h
e
p
i
x
e
l
p
.
Step
1
: M
ed
ian
f
ilter
is
ap
p
lie
d
to
r
em
o
v
e
t
h
e
n
o
is
e
f
r
o
m
m
a
m
m
o
g
r
ap
h
y
i
m
ag
e.
Step
2
:
in
th
i
s
s
tep
,
a
r
ec
tan
g
l
e
s
u
r
r
o
u
n
d
i
n
g
th
e
m
as
s
h
as
b
e
en
cr
ea
ted
,
an
d
th
e
n
f
o
r
ea
ch
p
ix
el
o
f
th
e
r
ec
tan
g
le
Si an
d
its
ce
n
ter
S
0
a
lin
e
s
e
g
m
en
t
[S
0
, S
i
]
w
i
ll b
e
cr
ea
ted
.
Step
3
: I
n
th
is
s
tep
w
e
ap
p
l
y
t
h
e
alg
o
r
it
h
m
1
o
n
ea
c
h
li
n
e
s
e
g
m
e
n
t.
A
l
g
o
r
ith
m
1
:
A
l
g
o
r
ith
m
o
f
Se
g
m
e
n
tat
io
n
I
n
p
u
t
:
l
i
n
e
seg
men
t
[
s
0
,
s
c
]
O
u
t
p
u
t
:
Set
Seg
men
t
ed
Po
i
n
t
s
i
n
[
s
0
,
s
c
],
t
h
e
p
i
x
el
s
i
n
t
h
e
same
g
r
o
u
p
h
av
e
t
h
e
same
p
r
ed
ec
esso
r
Let
F b
e
an
em
p
t
y
p
r
i
o
r
i
t
y
q
u
e
u
e
.
(s
c
)
←
0;
(s
0
)
←
0;
P
r
e
d
(
s
c
)
←
sc
;
P
r
e
d
(
s
0
)
←
s
0;
ad
d
S
c
an
d
S
0
t
o
F
f
o
r
ea
ch
p
i
x
el
p
i
n
[
s
0
,
s
c
],
w
i
t
h
p
≠
s0
an
d
p
≠
sc
(
p
)
←
;
en
d
f
o
r
w
h
i
l
e
F i
s n
o
t
em
p
t
y
d
o
ch
o
o
se
p
i
n
F as
(
p
)
i
s mi
n
i
mu
m
t
ak
e
p
o
u
t
o
f
F
Let
P'
b
e
t
h
e
su
cc
ess
o
r
o
f
P a
n
d
V
c
b
e
t
h
e
mea
n
o
f
g
r
a
y
l
ev
el
o
f
t
h
e
g
r
o
u
p
w
h
i
ch
co
n
t
ai
n
s p
if
(
p
'
)
>
|
V
(
p
'
)
-
V
c
|
so
(
p
')
←|
V
(
p
'
)
-
V
c
|
P
r
e
d
(
p
')
←
P
r
e
d
(
p
)
;
ad
d
P'
t
o
F
en
d
i
f
en
d
w
h
i
l
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
.
5
,
Octo
b
er
2
0
1
8
:
3
5
8
7
–
3
5
9
3
3590
Fig
u
r
e
1
.
B
lo
ck
d
iag
r
a
m
o
f
m
ass
s
e
g
m
en
ta
tio
n
m
et
h
o
d
o
lo
g
y
3.
E
XP
E
R
I
M
E
NT
R
E
SU
L
T
S AN
D
DIS
CUSS
I
O
N
Ou
r
p
r
o
p
o
s
ed
m
eth
o
d
w
a
s
te
s
ted
o
n
2
0
m
a
m
m
o
g
r
a
m
s
w
it
h
ab
n
o
r
m
al
m
a
m
m
ar
y
r
e
g
io
n
s
f
r
o
m
t
h
e
MI
A
S d
atab
ase.
T
h
e
ex
p
er
i
m
e
n
tal
r
es
u
lts
ar
e
s
h
o
w
n
i
n
Fi
g
u
r
e
3
.
3
.
1
.
Va
lid
a
t
io
n
m
ea
s
ures
T
h
e
r
esu
lts
ar
e
ev
al
u
ated
u
s
in
g
p
er
f
o
r
m
a
n
ce
m
ea
s
u
r
e
s
:
s
p
ec
if
icit
y
,
s
e
n
s
i
tiv
it
y
,
ac
c
u
r
ac
y
a
n
d
o
v
er
lap
,
ca
n
b
e
ca
lcu
lated
u
s
in
g
t
h
e
n
u
m
b
er
o
f
s
a
m
p
le
s
co
r
r
ec
tl
y
clas
s
if
ied
as
f
o
llo
w
s
.
(
)
(
1
)
(
)
(
2
)
(
)
(
3
)
(
)
(
4
)
w
h
er
e
T
P
n
u
m
b
er
o
f
tr
u
e
p
o
s
itiv
e
,
FP
n
u
m
b
er
o
f
f
al
s
e
n
e
g
ativ
e,
FN
n
u
m
b
er
o
f
f
al
s
e
n
e
g
ati
v
e,
T
N
n
u
m
b
er
o
f
tr
u
e
n
eg
a
tiv
e(
s
ee
Fi
g
u
r
e
2
)
.
3
.
2
.
Seg
m
e
nta
t
io
n r
esu
lt
s
T
h
e
co
m
p
ar
is
o
n
s
o
f
th
e
s
eg
m
en
tatio
n
r
es
u
lt
s
b
et
w
ee
n
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
an
d
th
e
m
an
u
all
y
s
eg
m
e
n
ted
i
m
a
g
e
b
y
r
ad
io
lo
g
is
t
ar
e
s
h
o
w
n
i
n
Fig
u
r
e
3
.
I
n
Fig
u
r
e
3
,
th
e
b
lu
e
co
n
to
u
r
s
ar
e
th
e
s
eg
m
en
tatio
n
r
esu
lt
s
u
s
i
n
g
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
an
d
th
e
b
lack
co
n
to
u
r
s
ar
e
th
e
r
esu
lts
o
b
tain
ed
b
y
a
r
ad
io
lo
g
is
t.
Fro
m
Fig
u
r
e
3
,
w
e
ca
n
f
i
n
d
th
at
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
ca
n
o
b
tain
g
o
o
d
r
esu
lts
.
T
ab
le
1
s
h
o
w
s
t
h
e
r
esu
lt
s
o
f
q
u
an
tita
tiv
e
a
n
al
y
s
is
a
n
d
f
r
o
m
th
e
r
es
u
lts
w
e
ca
n
also
p
r
o
v
e
th
e
ef
f
ec
ti
v
en
e
s
s
o
f
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
h
as
a
f
e
w
li
m
itatio
n
s
s
u
c
h
as
th
e
o
b
j
ec
t
to
b
e
s
eg
m
e
n
ted
is
alr
ea
d
y
R
OI
i
m
a
g
es
t
h
at
h
av
e
b
ee
n
p
r
ev
io
u
s
l
y
s
e
lecte
d
in
w
h
o
le
m
a
m
m
o
g
r
a
m
s
.
T
h
u
s
,
a
m
a
s
s
d
etec
tio
n
s
tep
m
u
s
t
b
e
m
er
g
ed
in
to
t
h
e
alg
o
r
ith
m
i
n
th
e
f
u
tu
r
e.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
p
r
o
v
id
es
a
v
er
ag
e
s
e
n
s
iti
v
it
y
o
f
0
.
8
3
,
av
er
ag
e
s
p
ec
i
f
icit
y
o
f
0
.
9
7
,
ac
cu
r
ac
y
o
f
0.
9
1
an
d
o
v
er
lap
o
f
0
.
7
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
A
N
ew A
p
p
r
o
a
ch
to
th
e
Dete
ct
io
n
o
f Ma
mmo
g
r
a
m
B
o
u
n
d
a
r
y
(
Mo
h
a
mme
d
R
mili
)
3591
Fig
u
r
e
2
.
T
r
u
e
p
o
s
itiv
e,
f
al
s
e
p
o
s
itiv
e,
tr
u
e
n
eg
at
iv
e
a
n
d
f
al
s
e
n
eg
ati
v
e
d
ef
in
it
io
n
T
ab
le
1
.
Valid
atio
n
Me
asu
r
e
D
a
ta
o
f
2
0
M
ass
es
I
mag
e
S
e
n
si
t
i
v
i
t
y
S
p
e
c
i
f
i
c
i
t
y
A
c
c
u
r
a
c
y
O
v
e
r
l
a
p
md
b
0
1
0
0
,
9
1
0
,
9
8
0
,
9
6
0
,
8
7
md
b
0
0
5
0
,
8
4
0
,
9
8
0
,
9
3
0
,
8
2
md
b
0
1
2
0
,
8
1
0
,
9
8
0
,
9
1
0
,
7
8
md
b
0
1
5
0
,
8
0
1
,
0
0
0
,
9
1
0
,
8
0
md
b
0
2
1
0
,
9
5
0
,
9
9
0
,
9
8
0
,
9
3
md
b
0
2
3
0
,
8
2
0
,
9
8
0
,
9
4
0
,
8
0
md
b
0
2
5
0
,
8
5
0
,
9
8
0
,
9
5
0
,
8
0
md
b
0
2
8
0
,
9
5
0
,
9
7
0
,
9
6
0
,
9
0
md
b
0
6
9
0
,
7
8
0
,
9
4
0
,
8
8
0
,
7
1
md
b
0
9
2
0
,
8
1
0
,
9
1
0
,
8
5
0
,
6
7
md
b
0
9
7
0
,
7
0
0
,
9
6
0
,
8
3
0
,
6
0
md
b
1
3
2
0
,
9
8
0
,
9
8
0
,
9
8
0
,
8
9
md
b
1
3
2
0
,
8
2
1
,
0
0
0
,
9
4
0
,
8
1
md
b
1
3
4
0
,
8
4
0
,
9
9
0
,
9
4
0
,
8
4
md
b
1
4
2
0
,
8
9
0
,
9
7
0
,
9
6
0
,
7
7
md
b
1
4
4
0
,
7
1
0
,
9
7
0
,
8
7
0
,
6
7
md
b
2
0
2
0
,
8
4
0
,
9
9
0
,
9
3
0
,
8
2
md
b
2
6
7
0
,
7
5
0
,
9
9
0
,
8
9
0
,
7
4
md
b
2
7
1
0
,
6
9
0
,
8
1
0
,
7
1
0
,
6
8
md
b
1
8
4
0
,
9
6
0
,
9
4
0
,
9
5
0
,
8
6
A
v
e
r
a
g
e
0
,
8
3
0
,
9
7
0
,
9
1
0
,
7
9
R
es
u
lts
o
b
tai
n
ed
f
r
o
m
o
u
r
ap
p
r
o
ac
h
ar
e
co
m
p
ar
ed
w
ith
o
th
er
e
x
is
t
in
g
m
eth
o
d
s
f
o
r
b
r
ea
s
t
s
eg
m
e
n
tatio
n
,
T
ab
le
2
s
h
o
w
s
t
h
e
r
esu
l
ts
o
f
t
h
i
s
co
m
p
ar
is
o
n
.
T
ab
le
2
.
P
er
f
o
r
m
a
n
ce
C
o
m
p
ar
is
o
n
P
a
p
e
r
R
e
f
e
r
e
n
c
e
P
r
o
p
o
se
d
M
e
t
h
o
d
R
e
su
l
t
s
A
c
c
u
r
a
c
y
S
p
e
c
i
f
i
c
i
t
y
S
e
n
si
t
i
v
i
t
y
O
v
e
r
l
a
p
[
2
3
]
M
a
r
k
e
r
-
C
o
n
t
r
o
l
l
e
d
W
a
t
e
r
sh
e
d
a
n
d
M
o
r
p
h
o
l
o
g
i
c
a
l
g
r
a
d
i
e
n
t
--
--
--
0
.
7
2
[
2
4
]
B
H
EA
-
ED
A
-
B
B
D
A
-
P
M
D
A
-
A
S
B
-
S
R
G
A
0
.
9
9
0
.
9
2
0
.
9
4
--
[
2
5
]
M
e
a
n
sh
i
f
t
a
n
d
I
r
i
s fi
l
t
e
r
--
--
0
.
8
1
0
.
6
0
[
2
6
]
R
e
g
i
o
n
G
r
o
w
i
n
g
D
y
n
a
mi
c
P
r
o
g
r
a
mm
i
n
g
-
B
a
se
d
--
--
--
--
--
--
0
.
8
3
0
.
7
2
P
r
o
p
o
se
d
R
e
g
i
o
n
G
r
o
w
i
n
g
0
,
9
1
0
,
9
7
0
,
8
3
0
,
7
9
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
.
5
,
Octo
b
er
2
0
1
8
:
3
5
8
7
–
3
5
9
3
3592
(
a)
(
b
)
(
c)
(
d
)
(
e)
a
1
b1
c1
d1
e1
a1
-
en
lar
g
e
b1
-
e
n
lar
g
e
c1
-
en
lar
g
e
d1
-
en
lar
g
e
e1
-
en
lar
g
e
a2
b2
c2
d2
e2
Fig
u
r
e
3
.
E
x
p
er
i
m
en
tal
r
esu
lts
o
f
m
a
m
m
o
g
r
a
m
s
f
r
o
m
MI
A
S
d
atab
ase: (
a)
-
(
e)
Or
ig
in
al
i
m
a
g
es,
(a
-
1)
-
(e
-
1
)
R
es
u
lt
s
b
y
t
h
e
p
r
o
p
o
s
ed
m
e
th
o
d
,
(a
-
2)
-
(e
-
2
)
T
h
e
g
r
o
u
n
d
tr
u
th
4.
CO
NCLU
SI
O
N
I
n
t
h
is
w
o
r
k
,
w
e
p
r
esen
t
a
n
e
w
ap
p
r
o
ac
h
to
th
e
d
etec
tio
n
o
f
m
a
m
m
o
g
r
a
m
b
o
u
n
d
ar
y
f
o
r
a
g
i
v
e
n
R
OI
in
m
a
m
m
o
g
r
a
m
s
.
T
h
e
ap
p
r
o
ac
h
is
a
n
ex
te
n
d
ed
v
er
s
io
n
o
f
th
e
r
eg
io
n
g
r
o
w
i
n
g
al
g
o
r
ith
m
.
T
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
is
e
v
a
lu
ated
u
s
i
n
g
a
r
e
f
er
en
ce
m
a
m
m
o
g
r
ap
h
y
d
ata
s
et
MI
AS,
w
h
er
e
ex
p
er
t
r
ad
io
lo
g
is
ts
h
a
v
e
ch
o
s
en
b
o
u
n
d
ar
ies.
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
eth
o
d
is
e
v
alu
a
ted
u
s
i
n
g
p
er
f
o
r
m
an
c
e
m
ea
s
u
r
es
:
s
p
ec
if
icit
y
,
s
e
n
s
it
iv
it
y
,
ac
c
u
r
ac
y
a
n
d
o
v
er
lap
.
w
e
d
ev
elo
p
ed
a
d
ata
s
et
co
n
tai
n
i
n
g
2
0
m
as
s
es.
W
e
ha
v
e
s
h
o
w
n
th
a
t o
u
r
m
et
h
o
d
g
iv
es
g
o
o
d
r
esu
lts
.
T
h
e
m
ar
g
i
n
s
,
co
n
to
u
r
an
d
s
h
a
p
e
o
f
m
a
s
s
i
m
p
licate
v
al
u
ab
le
in
f
o
r
m
atio
n
to
d
eter
m
i
n
e
t
h
e
s
ev
er
it
y
o
f
th
e
m
a
m
m
ar
y
m
as
s
.
s
o
I
t i
s
i
m
p
o
r
tan
t to
f
i
n
d
t
h
e
m
as
s
as p
r
e
cise a
s
p
o
s
s
ib
le.
Af
ter
s
e
g
m
en
tatio
n
o
f
th
e
b
r
ea
s
t
m
as
s
ar
ea
ac
cu
r
atel
y
,
th
e
p
r
o
p
er
ties
o
f
t
h
e
s
e
g
m
e
n
ted
m
as
s
ca
n
b
e
ex
tr
ac
ted
an
d
an
a
l
y
ze
d
to
d
eter
m
i
n
e
m
as
s
m
ali
g
n
a
n
c
y
.
I
t is
s
u
r
e
th
at
th
e
q
u
alit
y
o
f
t
h
e
m
as
s
p
r
o
p
er
ties
ex
tr
ac
ted
d
ep
en
d
s
o
n
t
h
e
s
u
cc
ess
r
ate
o
f
th
e
m
a
s
s
s
eg
m
e
n
tatio
n
alg
o
r
it
h
m
s
u
s
e
d
.
I
n
th
e
f
u
t
u
r
e,
w
e
p
la
n
to
an
al
y
ze
t
h
e
s
e
g
m
e
n
ted
m
as
s
to
ex
tr
ac
t
m
o
r
e
d
escr
ip
tiv
e
an
d
in
f
o
r
m
a
tiv
e
i
n
f
o
r
m
atio
n
th
at
ca
n
b
e
u
s
ed
to
i
n
ter
p
r
eted
th
e
m
a
m
m
ar
y
m
as
s
.
RE
F
E
R
E
NC
E
S
[1
]
S
.
Bu
se
m
a
n
,
J.
M
o
u
c
h
a
w
a
r,
N.
C
a
lo
n
g
e
,
a
n
d
T
.
By
e
rs,
“
M
a
m
m
o
g
ra
p
h
y
S
c
re
e
n
in
g
M
a
tt
e
rs
f
o
r
y
o
u
n
g
w
o
m
e
n
w
it
h
Bre
a
st
Ca
rc
in
o
m
a
:
Ev
id
e
n
c
e
o
f
D
o
w
n
sta
g
in
g
a
m
o
n
g
4
2
-
49
-
y
e
a
r
-
o
ld
w
o
m
e
n
w
it
h
a
Histo
ry
o
f
P
re
v
io
u
s
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
N
ew A
p
p
r
o
a
ch
to
th
e
Dete
ct
io
n
o
f Ma
mmo
g
r
a
m
B
o
u
n
d
a
r
y
(
Mo
h
a
mme
d
R
mili
)
3593
M
a
m
m
o
g
ra
p
h
y
S
c
re
e
n
in
g
”
,
Ca
n
c
e
r
,
v
o
l.
9
7
,
n
o
.
2
,
p
p
.
3
5
2
-
3
5
8
,
2
0
0
3
.
[2
]
C.
Ho
,
D.
Ha
il
e
y
,
R.
Warb
u
rto
n
,
J.
H.
M
a
c
G
re
g
o
r,
E.
D.
P
isa
n
o
,
a
n
d
J.
Jo
y
c
e
,
“
L
a
m
a
m
m
o
g
r
a
p
h
ie
n
u
m
é
riq
u
e
c
o
m
p
a
ra
ti
v
e
m
e
n
t
à
l
a
m
a
m
m
o
g
r
a
p
h
ie
su
r
f
il
m
a
v
e
c
é
c
ra
n
:
é
v
a
lu
a
ti
o
n
te
c
h
n
iq
u
e
,
c
li
n
iq
u
e
e
t
é
c
o
n
o
m
iq
u
e
”
,
Ra
p
p
.
o
ff
.
C
a
n
.
Co
o
rd
.
l’év
a
lu
a
ti
o
n
d
e
s
T
e
c
h
n
o
l
.
l
a
sa
n
té
,
2
0
0
2
.
[3
]
G
.
X
u
,
K.
L
i,
A
n
d
G
.
F
e
n
g
,
“
Co
m
p
a
riso
n
o
f
T
h
re
e
I
m
a
g
in
g
M
e
th
o
d
s
i
n
t
h
e
Early
Dia
g
n
o
sis
o
f
th
e
Bre
a
st
Ca
n
c
e
r
[
J
]
”
,
J
.
C
a
p
.
M
e
d
.
Un
iv.
,
v
o
l.
3
,
p
.
1
1
,
2
0
0
9
.
[4
]
O.
Ch
e
n
g
,
D.
H
u
i,
a
n
d
W
.
G
u
a
n
g
z
h
i,
“
S
e
g
m
e
n
tatio
n
o
f
M
a
ss
e
s in
M
a
m
m
o
g
ra
m
s
”
,
Beiji
n
g
Bi
o
me
d
.
En
g
.
,
2
0
0
7
.
[5
]
M
.
L
.
G
ig
e
r,
“
Co
m
p
u
t
er
-
a
id
e
d
Di
a
g
n
o
sis in
Ra
d
i
o
l
o
g
y
”
,
El
se
v
ier
,
2
0
0
2
.
[6
]
K.
Ke
rli
k
o
w
s
k
e
e
t
a
l
.
,
“
P
e
r
f
o
rm
a
n
c
e
o
f
S
c
re
e
n
in
g
M
a
m
m
o
g
ra
p
h
y
a
m
o
n
g
w
o
m
e
n
w
it
h
a
n
d
w
it
h
o
u
t
a
f
irst
-
d
e
g
re
e
re
lativ
e
w
it
h
B
re
a
st c
a
n
c
e
r"
,
An
n
.
In
ter
n
.
M
e
d
.
,
v
o
l.
1
3
3
,
n
o
.
1
1
,
p
p
.
8
5
5
-
8
6
3
,
2
0
0
0
.
[7
]
R.
E.
Bird
,
T
.
W
.
W
a
ll
a
c
e
,
a
n
d
B.
C.
Ya
n
k
a
sk
a
s,
“
A
n
a
l
y
sis
o
f
c
a
n
c
e
rs
m
iss
e
d
a
t
sc
re
e
n
in
g
M
a
m
m
o
g
ra
p
h
y
”
,
Ra
d
i
o
lo
g
y
,
v
o
l
.
1
8
4
,
n
o
.
3
,
p
p
.
6
1
3
-
6
1
7
,
1
9
9
2
.
[8
]
C.
J.
V
y
b
o
rn
y
,
M
.
L
.
G
ig
e
r,
a
n
d
R.
M
.
Nis
h
ik
a
wa
,
“
Co
m
p
u
ter
-
Aid
e
d
De
t
e
c
ti
o
n
a
n
d
Dia
g
n
o
sis
o
f
Bre
a
st
c
a
n
c
e
r
”
,
Ra
d
i
o
l.
C
li
n
.
No
rt
h
Am.
,
v
o
l.
3
8
,
n
o
.
4
,
p
p
.
7
2
5
-
7
4
0
,
2
0
0
0
.
[9
]
K.
Do
i,
H.
M
a
c
M
a
h
o
n
,
S
.
Ka
tsu
r
a
g
a
wa
,
R.
M
.
Nish
ik
a
w
a
,
a
n
d
Y.
Jia
n
g
,
“
Co
m
p
u
ter
-
a
id
e
d
Dia
g
n
o
si
s
in
Ra
d
io
l
o
g
y
:
P
o
ten
ti
a
l
a
n
d
P
it
f
a
ll
s
”
,
Eu
r.
J
.
Ra
d
io
l
.
,
v
o
l.
3
1
,
n
o
.
2
,
p
p
.
9
7
-
1
0
9
,
1
9
9
9
.
[1
0
]
M
.
L
.
G
ig
e
r,
N.
Ka
rss
e
m
e
ij
e
r,
a
n
d
S
.
G
.
A
r
m
a
to
,
“
G
u
e
st
Ed
it
o
rial
Co
m
p
u
ter
-
a
id
e
d
D
iag
n
o
sis
in
M
e
d
ica
l
Im
a
g
in
g
”
,
IEE
E
T
ra
n
s.
M
e
d
.
Im
a
g
i
n
g
,
v
o
l.
2
0
,
n
o
.
1
2
,
p
p
.
1
2
0
5
-
1
2
0
8
,
2
0
0
1
.
[1
1
]
F
.
A
.
S
.
A
ls
a
ro
ri
a
n
d
R.
Ha
ss
a
n
p
o
u
r,
“
A
u
to
m
a
ti
c
D
e
tec
ti
o
n
o
f
Bre
a
st
c
a
n
c
e
r
in
M
a
m
m
o
g
r
a
m
I
m
a
g
e
s
”
,
J
.
Ad
v
.
T
e
c
h
n
o
l
.
E
n
g
.
Res
.
,
v
o
l.
2
,
n
o
.
6
,
p
p
.
1
9
6
-
2
0
1
,
2
0
1
6
.
[1
2
]
S
.
A
n
a
n
d
,
V
.
V
i
n
o
d
,
a
n
d
A
.
Ra
m
p
u
re
,
“
A
p
p
li
c
a
ti
o
n
o
f
F
u
z
z
y
c
-
m
e
a
n
s
a
n
d
Ne
u
ra
l
Ne
tw
o
rk
s
to
Ca
teg
o
rize
T
u
m
o
r
Aff
e
c
ted
Bre
a
st M
R
Im
a
g
e
s
”
,
In
t.
J
.
Ap
p
l.
E
n
g
.
Res
.
,
v
o
l.
1
0
,
n
o
.
6
4
,
p
.
2
0
1
5
,
2
0
1
5
.
[1
3
]
S
.
R.
S
h
a
re
e
f
,
“
Bre
a
st c
a
n
c
e
r
De
t
e
c
ti
o
n
b
a
se
d
o
n
W
a
ters
h
e
d
T
ra
n
sfo
rm
a
ti
o
n
”
,
v
o
l.
1
1
,
n
o
.
1
,
p
p
.
2
3
7
-
2
4
5
,
2
0
1
4
.
[1
4
]
T
.
Be
rb
e
r,
A
.
A
lp
k
o
c
a
k
,
P
.
Ba
lci,
a
n
d
O.
Dic
le,
“
Bre
a
st
m
a
s
s
Co
n
to
u
r
S
e
g
m
e
n
tatio
n
A
lg
o
ri
th
m
in
Dig
it
a
l
M
a
m
m
o
g
ra
m
s
”
,
Co
mp
u
t.
M
e
th
o
d
s P
ro
g
ra
ms
B
io
me
d
.
,
v
o
l.
1
1
0
,
n
o
.
2
,
p
p
.
1
5
0
-
1
5
9
,
2
0
1
3
.
[1
5
]
V
.
V
e
d
a
n
a
ra
y
a
n
a
n
a
n
d
N.
M
.
N
a
n
d
h
i
th
a
,
“
A
d
v
a
n
c
e
d
I
m
a
g
e
S
e
g
m
e
n
tatio
n
T
e
c
h
n
iq
u
e
s
f
o
r
Ac
c
u
ra
te
Iso
latio
n
o
f
A
b
n
o
rm
a
li
t
y
to
En
h
a
n
c
e
Bre
a
st
c
a
n
c
e
r
D
e
te
c
ti
o
n
in
Dig
it
a
l
M
a
m
m
o
g
ra
p
h
s
”
,
Bi
o
me
d
.
Res
.
,
v
o
l.
2
8
,
n
o
.
6
,
p
p
.
2
7
5
3
-
2
7
5
7
,
2
0
1
7
.
[1
6
]
S
.
M
.
L
.
d
e
L
ima
,
A
.
G
.
d
a
S
il
v
a
-
F
il
h
o
,
a
n
d
W
.
P
.
d
o
s
S
a
n
t
o
s,
“
De
tec
ti
o
n
a
n
d
Clas
sif
ica
ti
o
n
o
f
M
a
ss
e
s
in
M
a
m
m
o
g
ra
p
h
ic
I
m
a
g
e
s
in
a
M
u
lt
i
-
k
e
rn
e
l
A
p
p
ro
a
c
h
”
,
Co
mp
u
t.
M
e
th
o
d
s
Pro
g
ra
ms
Bi
o
me
d
.
,
v
o
l.
1
3
4
,
p
p
.
1
1
-
2
9
,
2
0
1
6
.
[1
7
]
E.
Ch
a
g
h
a
ri
a
n
d
A
.
K
a
ri
m
i,
“
A
No
v
e
l
A
p
p
ro
a
c
h
f
o
r
T
u
m
o
r
De
t
e
c
ti
o
n
in
M
a
m
m
o
g
ra
p
h
y
I
m
a
g
e
s,”
T
EL
KOM
NIKA
(
T
e
l
e
c
o
mm
u
n
ica
ti
o
n
,
Co
m
p
u
t
in
g
,
El
e
c
tro
n
ics
a
n
d
Co
n
tro
l)
,
v
o
l.
1
2
,
n
o
.
8
,
p
p
.
6
2
1
1
-
6
2
1
6
,
2
0
1
4
.
[1
8
]
K.
T
a
i
f
i,
R.
A
h
d
id
,
M
.
F
a
k
ir,
a
n
d
S
.
S
a
f
i,
“
A
H
y
b
rid
th
e
No
n
su
b
sa
m
p
led
Co
n
to
u
rlet
T
ra
n
sf
o
r
m
a
n
d
Ho
m
o
m
o
rp
h
ic
F
il
terin
g
f
o
r
En
h
a
n
c
in
g
M
a
m
m
o
g
ra
m
s
”
,
v
o
l.
1
6
,
n
o
.
3
,
p
p
.
5
3
9
-
5
4
5
,
2
0
1
5
.
[1
9
]
M
.
M
u
sta
f
a
,
H.
Na
jw
a
O
m
a
r
Ra
s
h
id
,
N
.
Ru
l
Ha
sm
a
A
b
d
u
ll
a
h
,
R
.
S
a
m
a
d
,
a
n
d
D.
P
e
b
rian
ti
,
“
M
a
m
m
o
g
r
a
p
h
y
I
m
a
g
e
S
e
g
m
e
n
tatio
n
:
Ch
a
n
-
V
e
se
A
c
ti
v
e
Co
n
t
o
u
r
a
n
d
L
o
c
a
li
se
d
A
c
ti
v
e
Co
n
t
o
u
r
A
p
p
ro
a
c
h
”
,
I
n
d
o
n
e
s.
J
.
El
e
c
tr.
En
g
.
Co
mp
u
t
.
S
c
i
.
,
v
o
l.
5
,
n
o
.
3
,
p
.
5
7
7
,
2
0
1
7
.
[2
0
]
J.
S
u
c
k
li
n
g
e
t
a
l
.
,
“
T
h
e
M
a
m
m
o
g
ra
p
h
ic
Im
a
g
e
A
n
a
l
y
sis
S
o
c
iety
Dig
it
a
l
M
a
m
m
o
g
ra
m
D
a
tab
a
se
”
,
Exp
e
rt.
M
e
d
ica
,
In
t.
C
o
n
g
r.
S
e
r.
,
v
o
l.
1
0
6
9
,
p
p
.
3
7
5
-
3
7
8
,
1
9
9
4
.
[2
1
]
J.
P
ra
g
a
th
i,
“
S
e
g
m
e
n
tatio
n
M
e
th
o
d
f
o
r
ROI
De
tec
ti
o
n
in
M
a
m
m
o
g
r
a
p
h
ic
Im
a
g
e
s
u
sin
g
W
ien
e
r
F
il
te
r
a
n
d
Kitt
ler
’
s
M
e
th
o
d
”
,
v
o
l.
2
0
1
3
,
p
p
.
2
7
-
3
3
,
2
0
1
3
.
[2
2
]
A
.
Ro
jas
-
Do
m
ín
g
u
e
z
a
n
d
A
.
K.
Na
n
d
i,
“
De
v
e
lo
p
m
e
n
t
o
f
T
o
ler
a
n
t
F
e
a
t
u
re
s
f
o
r
Ch
a
ra
c
teriz
a
ti
o
n
o
f
M
a
ss
e
s
in
M
a
m
m
o
g
ra
m
s
”
,
Co
mp
u
t.
Bi
o
l.
M
e
d
.
,
v
o
l.
3
9
,
n
o
.
8
,
p
p
.
6
7
8
-
6
8
8
,
2
0
0
9
.
[2
3]
S
.
Xu
,
H.
L
iu
,
a
n
d
E.
S
o
n
g
,
“
M
a
rk
e
r
-
Co
n
tro
ll
e
d
W
a
ters
h
e
d
f
o
r
L
e
s
io
n
S
e
g
m
e
n
tatio
n
in
M
a
m
m
o
g
ra
m
s
"
,
p
p
.
7
5
4
-
7
6
3
,
2
0
1
1
.
[2
4
]
I.
K.
M
a
it
ra
,
S
.
Na
g
,
a
n
d
S
.
K.
B
a
n
d
y
o
p
a
d
h
y
a
y
,
“
A
u
to
m
a
ted
Dig
it
a
l
M
a
m
m
o
g
ra
m
S
e
g
m
e
n
tatio
n
f
o
r
De
ste
c
ti
o
n
o
f
A
b
n
o
rm
a
l
M
a
s
se
s
u
sin
g
Bi
n
a
ry
Ho
m
o
g
e
n
e
it
y
En
h
a
n
c
e
m
e
n
t
”
,
In
d
i
a
n
J
.
Co
m
p
u
t
.
S
c
i.
E
n
g
.
,
v
o
l.
2
,
n
o
.
3
,
p
p
.
4
1
6
-
4
2
7
,
2
0
1
1
.
[2
5
]
T
.
T
e
r
a
d
a
,
Y.
F
u
k
u
m
izu
,
H.
Ya
m
a
u
c
h
i,
H.
Ch
o
u
,
a
n
d
Y.
Ku
r
u
m
i,
“
De
tec
ti
n
g
M
a
ss
a
n
d
it
s
Re
g
io
n
in
M
a
m
m
o
g
ra
m
s
Us
in
g
M
e
a
n
S
h
i
f
t
S
e
g
m
e
n
tatio
n
a
n
d
Iris
F
il
ter
”
,
p
p
.
1
1
7
6
-
1
1
7
9
,
2
0
1
0
.
[2
6
]
A
.
R.
Do
m
í
n
g
u
e
z
a
n
d
A
.
K.
N
a
n
d
i,
“
T
o
w
a
rd
Bre
a
st c
a
n
c
e
r
Dia
g
n
o
sis b
a
se
d
o
n
A
u
to
m
a
ted
S
e
g
m
e
n
tatio
n
o
f
M
a
ss
e
s
in
M
a
m
m
o
g
ra
m
s
”
,
v
o
l.
4
2
,
p
p
.
1
1
3
8
-
1
1
4
8
,
2
0
0
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.