I
nte
rna
t
io
na
l
J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
9
,
No
.
2
,
A
p
r
il
201
9
,
p
p
.
9
9
2
~1
0
0
1
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v9
i
2
.
pp
992
-
1
0
0
1
992
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 nov
el appro
a
ch
t
o
j
o
intly a
dd
ress
loca
liz
a
tion
a
nd
cla
ss
ificatio
n
o
f
b
reas
t
ca
ncer
usin
g
bio
-
inspi
red ap
pro
a
ch
Su
s
h
m
a
S
.
J
.
1
, S
.
C
.
P
ra
s
a
nn
a
K
u
m
a
r
2
1
In
stru
m
e
n
tatio
n
T
e
c
h
n
o
lo
g
y
,
V
isv
e
sv
a
ra
y
a
Tec
h
n
o
lo
g
ica
l
Un
iv
e
rsity
,
Be
lg
a
v
i,
In
d
ia
2
De
p
a
rtme
n
t
o
f
In
stru
m
e
n
tatio
n
T
e
c
h
n
o
l
o
g
y
,
RV
CE
Ba
n
g
a
lo
re
,
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
19
,
2
0
1
8
R
ev
i
s
ed
Sep
14
,
2
0
1
8
A
cc
ep
ted
No
v
7
,
2
0
1
8
L
o
c
a
li
z
a
ti
o
n
o
f
th
e
c
a
n
c
e
ro
u
s
re
g
io
n
a
s
w
e
ll
a
s
c
las
sif
ic
a
ti
o
n
o
f
th
e
ty
p
e
o
f
th
e
c
a
n
c
e
r
is
h
ig
h
ly
in
ter
-
li
n
k
e
d
w
it
h
e
a
c
h
o
th
e
r.
Ho
w
e
v
e
r,
in
v
e
stig
a
ti
o
n
to
w
a
rd
s
e
x
isti
n
g
a
p
p
ro
a
c
h
e
s
d
e
p
icts
th
a
t
t
h
e
se
p
ro
b
lem
s
a
r
e
a
lwa
y
s
ii
n
d
iv
i
d
u
a
ll
y
so
lv
e
d
w
h
e
re
th
e
re
is
stil
l
a
b
ig
re
s
e
a
rc
h
g
a
p
f
o
r
a
g
e
n
e
ra
li
z
e
d
so
lu
ti
o
n
t
o
w
a
rd
s
a
d
d
re
ss
in
g
b
o
t
h
th
e
p
r
o
b
lem
s.
T
h
e
re
f
o
re
,
th
e
p
ro
p
o
se
d
m
a
n
u
sc
rip
t
p
re
se
n
ts
a
sim
p
le,
n
o
v
e
l,
a
n
d
les
s
-
it
e
ra
ti
v
e
c
o
m
p
u
tatio
n
a
l
m
o
d
e
l
th
a
t
jo
i
n
tl
y
a
d
d
re
ss
th
e
lo
c
a
li
z
a
ti
o
n
-
c
las
sif
ica
ti
o
n
p
ro
b
lem
s
ta
k
in
g
th
e
c
a
s
e
stu
d
y
o
f
e
a
rl
y
d
ia
g
n
o
sis
o
f
b
re
a
st
c
a
n
c
e
r.
T
h
e
p
ro
p
o
se
d
stu
d
y
h
a
rn
e
ss
e
s
th
e
p
o
ten
ti
a
l
o
f
sim
p
le
b
io
-
i
n
sp
ired
o
p
ti
m
iza
ti
o
n
tec
h
n
iq
u
e
i
n
o
r
d
e
r
t
o
o
b
tain
e
d
b
e
tt
e
r
lo
c
a
l
a
n
d
g
lo
b
a
l
b
e
st
o
u
tco
m
e
to
c
o
n
f
ir
m
th
e
a
c
c
u
ra
c
y
o
f
th
e
o
u
tco
m
e
.
T
h
e
stu
d
y
o
u
tco
m
e
o
f
th
e
p
ro
p
o
se
d
s
y
ste
m
e
x
h
ib
it
s
th
a
t
p
ro
p
o
se
d
s
y
ste
m
o
f
fe
rs
h
ig
h
e
r
a
c
c
u
ra
c
y
a
n
d
lo
w
e
r
re
sp
o
n
se
ti
m
e
in
c
o
n
tras
t
w
it
h
o
th
e
r
e
x
isti
n
g
c
la
ss
i
f
iers
th
a
t
a
re
f
r
e
q
e
n
tl
y
w
it
n
e
ss
e
d
in
e
x
isti
n
g
a
p
p
ro
a
c
h
e
s
o
f
c
las
si
f
ica
ti
o
n
in
m
e
d
ica
l
im
a
g
e
p
ro
c
e
ss
.
K
ey
w
o
r
d
s
:
B
io
-
in
s
p
ir
ed
B
r
ea
s
t
ca
n
ce
r
C
las
s
i
f
icatio
n
Dete
ctio
n
L
o
ca
lizatio
n
Op
ti
m
izatio
n
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Su
s
h
m
a
S J
,
I
n
s
tr
u
m
e
n
tatio
n
T
ec
h
n
o
lo
g
y
,
Vis
v
e
s
v
ar
a
y
a
T
ec
h
n
o
lo
g
ical
Un
i
v
er
s
it
y
,
B
elg
av
i,
I
n
d
ia
.
E
-
Ma
il: s
u
s
h
j
g
o
w
d
a@
g
m
ail.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
Dete
ctio
n
a
n
d
clas
s
i
f
icatio
n
p
r
o
b
lem
s
ar
e
h
i
g
h
l
y
co
n
n
ec
te
d
is
s
u
es
w
it
h
r
esp
ec
t
to
m
ed
i
ca
l
i
m
a
g
e
p
r
o
ce
s
s
in
g
[
1
]
.
Usu
all
y
t
h
i
s
p
r
o
b
lem
is
i
n
v
est
ig
ated
w
i
th
r
es
p
ec
t
to
a
s
p
ec
if
ic
ca
s
e
o
f
cli
n
i
ca
l
u
r
g
e
n
c
y
w
h
o
s
e
in
f
o
r
m
atio
n
is
u
s
u
all
y
ca
p
t
u
r
e
d
in
t
h
e
f
o
r
m
o
f
m
e
d
ical
i
m
ag
es
v
iz.
u
ltra
s
o
u
n
d
,
Ma
g
n
etic
R
eso
n
a
n
ce
I
m
ag
in
g
(
MRI)
,
x
-
r
a
y
,
co
m
p
u
ter
-
a
id
ed
d
iag
n
o
s
i
s
,
etc.
[
2
]
.
T
h
e
p
r
o
p
o
s
ed
s
tu
d
y
co
n
s
id
er
s
t
h
e
c
ase
o
f
d
ia
g
n
o
s
is
o
f
b
r
ea
s
t
ca
n
ce
r
w
h
er
e
th
e
i
n
p
u
t
is
u
s
u
al
l
y
o
b
tain
ed
f
r
o
m
m
a
m
m
o
g
r
a
m
s
.
U
s
u
all
y
,
s
u
c
h
f
o
r
m
s
o
f
m
a
m
m
o
g
r
a
m
in
p
u
t
s
co
u
ld
ex
h
ib
it
t
h
e
p
r
ese
n
ce
o
f
an
y
ab
n
o
r
m
alitie
s
if
i
t
is
v
i
s
ib
l
y
lar
g
er
in
s
ize.
Fro
m
th
e
m
ed
ical
i
m
a
g
e
p
r
o
ce
s
s
in
g
v
ie
w
p
o
i
n
t,
t
h
e
ca
p
t
u
r
ed
i
m
a
g
e
(
t
h
at
is
u
s
u
al
l
y
a
g
r
ay
-
s
ca
led
i
m
ag
e)
is
in
v
est
ig
at
ed
w
i
th
r
esp
ec
t
to
its
s
p
ec
i
f
ic
p
r
o
p
o
r
tio
n
o
f
co
n
tr
ast
to
d
is
p
la
y
a
p
r
ese
n
ce
o
f
an
y
lu
m
p
,
n
o
d
u
le,
o
r
tu
m
o
r
[
3
]
.
A
t
p
r
esen
t,
th
er
e
ar
e
g
o
o
d
n
u
m
b
er
s
o
f
wo
r
k
b
ein
g
ca
r
r
ied
o
u
t
to
w
ar
d
s
tu
d
ie
s
to
w
ar
d
s
f
ac
ilit
ati
n
g
th
e
lo
ca
lizatio
n
o
f
th
e
ca
n
ce
r
o
u
s
r
e
g
io
n
e.
g
.
[
4
]
-
[
6
]
,
h
o
w
ev
er
,
t
h
e
y
d
o
n
‟
t
r
elate
o
r
ad
d
r
ess
a
n
y
f
o
r
m
o
f
clas
s
if
ica
tio
n
p
r
o
b
le
m
t
h
at
i
s
n
ex
t
s
tag
e
o
f
t
h
e
d
iag
n
o
s
is
.
S
i
m
ilar
l
y
,
th
er
e
ar
e
also
s
tu
d
ie
s
ca
r
r
ied
o
u
t
to
w
ar
d
m
ed
ical
i
m
ag
e
cla
s
s
i
f
icatio
n
v
iz.
[
7
]
-
[
9
]
,
b
u
t
th
e
y
d
o
n
‟
t
in
i
tiate
w
ith
t
y
p
ical
lo
ca
lizatio
n
p
r
o
b
lem
s
a
n
d
h
en
ce
t
h
eir
o
w
n
w
a
y
to
s
o
l
v
e
s
u
c
h
class
i
f
icatio
n
p
r
o
b
le
m
s
.
Ho
w
e
v
er
,
t
h
er
e
ar
e
p
o
ten
tial
i
m
p
ed
im
en
ts
to
w
ar
d
s
t
h
e
r
esear
c
h
wo
r
k
ass
o
ciate
d
w
it
h
d
iag
n
o
s
i
s
an
d
class
if
icatio
n
p
r
o
b
lem
s
e.
g
.
i)
th
e
co
m
p
lete
i
m
a
g
e
is
ch
o
s
e
n
to
u
n
d
er
g
o
d
etec
tio
n
o
r
class
i
f
icatio
n
p
r
o
ce
s
s
w
h
ich
al
s
o
in
v
o
lv
e
s
s
o
m
e
s
u
r
p
lu
s
r
e
g
i
o
n
n
o
t r
eq
u
ir
ed
f
o
r
an
y
f
o
r
m
o
f
an
a
l
y
s
is
,
ii)
le
s
s
er
f
o
cu
s
o
n
p
r
ep
r
o
ce
s
s
in
g
m
ak
e
s
th
e
class
i
f
icat
io
n
p
r
o
ce
s
s
d
eg
r
ad
e
in
th
e
later
s
tag
e
af
ter
d
etec
tio
n
p
r
o
ce
s
s
,
iii)
ad
o
p
tio
n
o
f
iter
ativ
e
o
r
co
m
p
lex
m
ac
h
in
e
lear
n
i
n
g
-
b
ased
a
p
p
r
o
ac
h
th
at
o
f
f
er
s
g
o
o
d
p
r
ec
is
io
n
at
th
e
co
s
t
o
f
co
m
p
u
tatio
n
al
co
m
p
le
x
it
y
,
i
v
)
j
o
in
t
ad
d
r
ess
in
g
o
f
d
etec
tio
n
an
d
class
if
ica
tio
n
p
r
o
b
le
m
s
ar
e
less
v
is
u
alize
d
i
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
n
o
ve
l a
p
p
r
o
a
c
h
to
jo
in
tly
a
d
d
r
ess
lo
ca
liz
a
tio
n
a
n
d
cla
s
s
ifica
tio
n
o
f
b
r
ea
s
t c
a
n
ce
r
u
s
in
g
…
(
S
u
s
h
ma
S
.
J
.
)
993
ex
is
t
in
g
ap
p
r
o
ac
h
es,
etc.
I
t
w
a
s
also
f
o
u
n
d
th
at
s
e
g
m
e
n
tat
io
n
is
al
w
a
y
s
a
co
m
m
o
n
tech
n
iq
u
e
in
v
o
l
v
ed
in
b
o
th
t
h
e
p
r
o
ce
s
s
o
f
lo
ca
lizatio
n
an
d
class
i
f
icatio
n
o
f
ca
n
ce
r
.
A
p
ar
t
f
r
o
m
t
h
ese
en
t
ir
e
p
r
o
b
lem
s
,
th
e
s
it
u
atio
n
o
f
class
i
f
icatio
n
tu
r
n
s
m
o
s
t
ad
v
e
r
s
e
if
t
h
e
class
if
ica
tio
n
/
d
etec
tio
n
ar
e
s
u
p
p
o
s
ed
to
b
e
ca
r
r
ie
d
o
u
t
in
ea
r
l
y
s
ta
g
e
o
f
ca
n
ce
r
w
h
er
e
th
er
e
i
s
n
o
s
ig
n
i
f
ican
t d
ef
i
n
itio
n
o
f
ca
n
ce
r
o
u
s
r
eg
io
n
f
o
r
th
e
g
i
v
e
n
m
ed
ical
i
m
a
g
e.
A
t p
r
esen
t,
m
aj
o
r
ity
o
f
th
e
a
n
al
y
s
i
s
an
d
in
v
e
s
ti
g
atio
n
is
ca
r
r
ied
o
u
t
i
n
b
y
m
an
u
all
y
s
elec
tio
n
t
h
e
r
eg
io
n
b
ea
r
in
g
th
e
clin
ical
s
ig
n
i
f
ica
n
ce
e.
g
.
r
e
g
io
n
o
f
i
n
ter
est.
A
l
th
o
u
g
h
ad
o
p
tio
n
o
f
r
eg
i
o
n
o
f
i
n
ter
est
o
f
f
er
s
g
o
o
d
n
ar
r
o
w
d
o
w
n
o
f
t
h
e
i
n
v
esti
g
atio
n
to
w
ar
d
f
in
d
in
g
th
e
ca
n
ce
r
o
u
s
s
ite
b
u
t
th
er
e
is
n
o
d
en
y
i
n
g
t
h
e
f
ac
t
th
at
it
i
s
h
i
g
h
l
y
m
a
n
u
a
l
p
r
o
ce
s
s
an
d
i
s
j
u
s
ti
f
ied
f
o
r
o
n
l
y
t
h
o
s
e
i
m
a
g
e
s
t
h
at
r
eq
u
ir
es
s
p
ec
ial
atten
tio
n
f
r
o
m
t
h
e
p
h
y
s
ician
o
r
r
ad
io
lo
g
i
s
t.
I
t
is
d
u
e
to
p
r
ac
tical
im
p
le
m
e
n
tatio
n
o
f
r
eg
io
n
-
o
f
in
ter
e
s
t
f
o
r
d
iag
n
o
s
is
h
u
n
d
r
ed
s
o
f
m
ed
ical
i
m
ag
e
q
u
i
te
n
o
t
p
o
s
s
ib
le
in
r
ea
l
-
w
o
r
ld
s
ce
n
ar
i
o
an
d
th
is
p
r
o
b
lem
ca
n
b
e
o
n
l
y
s
o
lv
ed
if
t
h
e
s
y
s
te
m
is
ca
p
ab
le
o
f
id
en
tify
i
n
g
th
e
r
eg
io
n
o
f
t
h
e
i
m
a
g
e
ch
ar
ac
t
er
ized
b
y
ca
n
ce
r
.
Hen
ce
,
t
h
e
p
r
ac
tical
ap
p
licatio
n
w
ill
al
w
a
y
s
d
e
m
an
d
an
au
to
m
at
ic
d
etec
tio
n
a
n
d
clas
s
i
f
icatio
n
p
r
o
ce
s
s
to
p
er
f
o
r
m
d
i
ag
n
o
s
is
o
f
b
r
ea
s
t
ca
n
ce
r
e
f
f
ici
en
tl
y
.
T
h
e
p
r
ac
tical
p
ar
am
eter
s
to
j
u
s
ti
f
y
s
u
c
h
p
er
f
o
r
m
a
n
ce
in
r
ea
l
ti
m
e
ar
e
al
w
a
y
s
th
e
r
esp
o
n
s
e
ti
m
e
an
d
ac
c
u
r
ac
y
.
T
h
e
p
r
o
p
o
s
ed
m
an
u
s
cr
ip
t
in
tr
o
d
u
ce
s
a
n
o
v
el
o
p
tim
iza
tio
n
tec
h
n
iq
u
e
t
h
at
h
ar
n
ess
e
s
th
e
p
o
ten
tial
o
f
b
io
-
i
n
s
p
ir
ed
alg
o
r
ith
m
.
T
h
e
co
n
tr
ib
u
tio
n
o
f
t
h
e
p
r
o
p
o
s
ed
s
tu
d
y
i
s
t
h
at
it
o
f
f
er
s
s
o
lu
tio
n
b
y
j
o
in
tl
y
ad
d
r
ess
i
n
g
th
e
p
r
o
b
le
m
s
o
f
d
et
ec
tio
n
an
d
clas
s
i
f
icatio
n
o
f
b
r
ea
s
t
ca
n
ce
r
.
T
h
e
s
tu
d
y
also
i
m
p
le
m
en
t
s
a
r
u
le
-
s
et
b
ased
a
p
p
r
o
ac
h
in
o
r
d
er
to
m
ak
e
a
u
s
er
-
f
r
ie
n
d
l
y
cla
s
s
if
ic
atio
n
o
f
t
h
e
b
r
ea
s
t
ca
n
ce
r
.
Se
ctio
n
1
.
1
d
is
cu
s
s
e
s
ab
o
u
t
th
e
ex
is
t
in
g
liter
at
u
r
es
w
h
er
e
d
if
f
er
e
n
t
tech
n
iq
u
e
s
ar
e
d
is
cu
s
s
ed
f
o
r
d
etec
tio
n
as
w
ell
as
clas
s
i
f
icatio
n
s
ch
e
m
es
u
s
ed
in
d
iag
n
o
s
is
o
f
ea
r
l
y
s
tag
e
o
f
b
r
ea
s
t
ca
n
ce
r
f
o
llo
w
ed
b
y
d
is
c
u
s
s
io
n
o
f
r
esea
r
ch
p
r
o
b
le
m
s
a
s
s
o
ciate
d
w
it
h
th
e
e
x
is
tin
g
s
y
s
te
m
in
Sec
tio
n
1
.
2
a
n
d
p
r
o
p
o
s
ed
s
o
lu
tio
n
in
1
.
3
.
Sectio
n
2
d
is
c
u
s
s
es
ab
o
u
t
al
g
o
r
ith
m
i
m
p
le
m
en
tatio
n
as
s
o
ciate
d
w
it
h
t
h
e
lo
ca
lizatio
n
an
d
cla
s
s
if
icatio
n
p
r
o
ce
s
s
f
o
llo
w
ed
b
y
d
is
cu
s
s
io
n
o
f
r
es
u
lt a
n
al
y
s
is
with
r
esp
ec
t to
v
is
u
al
an
d
co
m
p
ar
ativ
e
an
a
l
y
s
is
in
Sectio
n
3
u
s
i
n
g
s
tan
d
ar
d
p
er
f
o
r
m
a
n
ce
p
ar
a
m
eter
s
to
as
s
e
s
s
t
h
e
p
r
o
p
o
s
itio
n
.
Fin
all
y
,
t
h
e
co
n
cl
u
s
i
v
e
r
e
m
ar
k
s
ar
e
p
r
o
v
id
ed
in
Sectio
n
4
.
1
.
1
.
B
a
ck
g
ro
un
d
T
h
is
s
ec
tio
n
is
a
co
n
ti
n
u
at
i
o
n
o
f
o
u
r
p
r
io
r
r
ev
ie
w
w
o
r
k
to
w
ar
d
s
ap
p
r
o
ac
h
es
o
f
b
r
ea
s
t
ca
n
ce
r
d
etec
tio
n
[
1
0
]
.
B
ee
v
i
et
a
l.
[
1
1
]
h
av
e
p
r
esen
ted
a
class
i
f
ier
d
esig
n
u
s
i
n
g
d
ee
p
b
elief
n
et
wo
r
k
f
o
r
ass
is
ti
n
g
in
s
eg
e
m
e
n
tatio
n
an
d
clas
s
i
f
icati
o
n
o
f
a
t
y
p
ical
s
ta
g
e
o
f
m
ito
s
is
in
ca
n
ce
r
p
r
o
g
r
ess
s
ta
g
e
w
it
h
ap
p
r
o
x
i
m
atel
y
8
5
%
o
f
ac
cu
r
ac
y
p
er
f
o
r
m
an
ce
.
Si
m
ilar
ad
o
p
tio
n
o
f
ad
v
an
ce
d
m
ac
h
i
n
e
lear
n
in
g
w
a
s
w
it
n
e
s
s
ed
in
t
h
e
w
o
r
k
o
f
C
ar
n
eir
o
et
a
l.
[
1
2
]
w
h
o
h
a
v
e
u
s
ed
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
i
n
o
r
d
er
to
p
er
f
o
r
m
cla
s
s
i
f
i
ca
tio
n
alo
n
g
w
it
h
s
eg
m
e
n
tatio
n
o
f
lesi
o
n
s
o
n
b
r
ea
s
t
i
m
a
g
e.
C
la
s
s
i
f
icat
io
n
p
r
o
b
le
m
w
it
h
r
e
s
p
ec
t
to
m
as
s
is
a
ls
o
ad
d
r
ess
ed
in
th
e
w
o
r
k
o
f
C
h
o
k
r
i
a
n
d
Far
id
a
[
1
3
]
w
h
er
e
m
u
lt
i
-
la
y
er
p
er
ce
p
tr
o
n
is
u
tili
z
ed
.
Du
r
ai
s
a
m
y
a
n
d
E
m
p
er
u
m
al
[
1
4
]
h
av
e
u
s
ed
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
in
o
r
d
er
t
o
p
e
r
f
o
r
m
clas
s
if
ica
tio
n
f
o
r
a
g
iv
e
n
m
a
m
m
o
g
r
a
m
.
T
h
e
au
th
o
r
s
h
av
e
also
u
s
ed
co
n
v
o
l
u
tio
n
n
e
u
r
al
n
et
w
o
r
k
in
o
r
d
er
to
ca
r
r
y
o
u
t
lear
n
i
n
g
p
r
o
ce
s
s
.
E
l
m
o
u
f
id
i
et
a
l.
[
1
5
]
h
av
e
i
m
p
le
m
en
ted
a
m
u
ltip
le
-
i
n
s
ta
n
ce
lear
n
i
n
g
m
et
h
o
d
f
o
r
f
ac
il
itatin
g
s
e
g
m
e
n
tatio
n
f
r
o
m
p
ix
el
-
le
v
el
as
w
ell
a
s
class
i
f
icatio
n
f
r
o
m
i
m
a
g
e
-
le
v
e
l
u
s
in
g
r
eg
io
n
-
of
-
in
ter
e
s
t.
St
u
d
y
to
w
ar
d
s
cla
s
s
i
f
ier
d
esi
g
n
was
i
m
p
le
m
e
n
ted
b
y
Ma
n
i
v
an
n
a
n
et
a
l.
[
1
6
]
as
w
el
l
as
Me
r
ca
n
et
a
l.
[
1
7
]
u
s
in
g
l
ea
r
n
in
g
-
b
ased
m
et
h
o
d
o
v
er
m
u
ltip
le
i
n
s
ta
n
ce
s
i
n
o
r
d
er
to
p
er
f
o
r
m
clas
s
i
f
icatio
n
.
Niza
m
et
a
l.
[
1
8
]
h
av
e
ca
r
r
ied
o
u
t
s
p
ec
tr
al
m
eth
o
d
s
i
n
o
r
d
er
to
p
er
f
o
r
m
esti
m
atio
n
o
f
t
h
e
s
p
ac
in
g
f
r
o
m
th
e
i
m
ag
e
s
o
b
tain
ed
f
r
o
m
t
h
e
u
ltra
s
o
u
n
d
.
R
ab
id
as
et
a
l.
[
1
9
]
h
av
e
ca
r
r
ied
o
u
t
an
al
y
s
is
o
f
cla
s
s
i
f
icat
io
n
p
r
o
b
le
m
w
it
h
t
h
e
h
elp
o
f
R
ip
p
le
t
-
I
I
tr
an
s
f
o
r
m
atio
n
tech
n
iq
u
e
b
y
q
u
a
n
ti
f
y
i
n
g
t
h
e
tex
t
u
r
al
f
ea
t
u
r
es.
R
ei
s
et
a
l.
[
2
0
]
h
av
e
u
s
ed
r
eg
io
n
-
of
-
in
te
r
est
s
ch
e
m
e
as
w
ell
as
f
ea
tu
r
e
ex
tr
ac
tio
n
u
s
in
g
m
u
ltis
ca
le
-
b
ased
ap
p
r
o
ac
h
.
S
ah
a
an
d
C
h
a
k
r
ab
o
r
t
y
[
2
1
]
ad
d
r
ess
ed
th
e
clas
s
i
f
icatio
n
p
r
o
b
lem
u
s
i
n
g
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
alo
n
g
w
it
h
a
s
eg
m
en
tatio
n
b
ein
g
ca
r
r
ied
o
u
t
u
s
in
g
s
e
m
an
tics
.
Usa
g
e
o
f
f
i
s
h
er
v
ec
to
r
to
w
ar
d
s
f
ac
ilit
ati
n
g
clas
s
i
f
ica
tio
n
o
f
i
m
a
g
e
is
ca
r
r
ied
o
u
t
b
y
So
n
g
et
a
l.
[
2
2
]
.
Ho
w
e
v
er
,
th
e
p
r
o
ce
s
s
o
f
class
i
f
icatio
n
p
o
ten
t
ial
d
ep
en
d
s
u
p
o
n
h
o
w
s
tr
o
n
g
is
th
e
d
etetio
n
p
r
o
ce
s
s
.
T
h
er
e
ar
e
ce
r
tain
s
tu
d
ie
s
ca
r
r
ied
o
u
t
to
w
ar
d
s
d
etec
tio
n
s
f
o
r
en
s
u
r
i
n
g
b
etter
class
i
f
icatio
n
p
r
o
ce
s
s
.
Stra
ck
x
et
a
l.
[
2
3
]
h
av
e
i
n
tr
o
d
u
ce
d
a
h
ar
d
w
ar
e
-
b
ased
ap
p
r
o
ac
h
f
o
r
im
p
le
m
e
n
tati
n
g
a
u
n
iq
u
e
s
u
b
s
a
m
p
li
n
g
p
r
o
ce
s
s
f
o
r
f
ac
ilit
at
in
g
id
en
ti
f
icatio
n
o
f
b
r
ea
s
t
ca
n
ce
r
.
I
n
v
esti
g
atio
n
o
f
ca
n
ce
r
u
s
i
n
g
b
r
ea
s
t
p
h
an
to
m
s
u
s
i
n
g
m
icr
o
w
a
v
e
i
m
ag
er
y
w
a
s
ca
r
r
i
ed
o
u
t
b
y
W
a
n
g
et
a
l.
[
2
4
]
,
[
2
5
]
w
h
er
e
th
e
au
t
h
o
r
s
h
a
v
e
co
n
s
id
er
ed
ti
m
e
-
d
o
m
ain
a
n
al
y
s
i
s
.
Yi
n
e
t
a
l.
[
2
6
]
h
av
e
i
m
p
le
m
en
ted
a
co
r
r
elatio
n
-
b
ased
m
eth
o
d
f
o
r
en
h
a
n
ci
n
g
t
h
e
i
m
a
g
e
a
n
al
y
s
is
f
o
r
b
r
ea
s
t
ca
n
ce
r
d
etec
tio
n
.
Ho
s
s
ai
n
a
n
d
Mo
h
a
n
[
2
7
]
h
av
e
u
s
ed
an
a
n
al
y
tical
t
ec
h
n
iq
u
e
alo
n
g
w
it
h
co
n
s
id
er
atio
n
o
f
ti
m
e
-
d
o
m
ai
n
to
f
i
n
d
ef
f
icien
t
d
et
ec
tio
n
o
f
ca
n
ce
r
o
v
er
m
icr
o
w
a
v
e
i
m
a
g
i
n
g
.
J
alilv
a
n
d
et
a
l.
[
2
8
]
h
av
e
u
s
ed
s
p
ec
if
ic
d
esi
g
n
o
f
b
o
w
t
ie
an
te
n
n
a
i
n
o
r
d
er
to
p
er
f
o
r
m
d
etec
tio
n
o
f
t
h
e
b
r
ea
s
t
ca
n
ce
r
.
T
h
e
w
o
r
k
ca
r
r
ied
o
u
t
b
y
K
w
o
n
e
t
al
[
2
9
]
h
av
e
u
s
ed
Gau
s
s
ia
n
b
an
d
-
p
ass
f
ilter
in
g
i
n
o
r
d
er
to
p
er
f
o
r
m
d
etec
tio
n
o
f
ca
n
ce
r
u
s
in
g
t
h
r
ee
d
i
m
e
n
s
io
n
al
i
m
a
g
e.
A
d
o
p
tio
n
o
f
S
-
tr
an
s
f
o
r
m
s
is
r
ep
o
r
ted
to
u
p
g
r
ad
e
th
e
class
i
f
icat
io
n
p
r
o
ce
s
s
as
d
is
c
u
s
s
ed
b
y
B
eu
r
a
et
a
l
.
[
3
0
]
.
T
h
e
au
th
o
r
s
h
av
e
al
s
o
i
m
p
le
m
e
n
ted
A
d
aB
o
o
s
t
alg
o
r
ith
m
alo
n
g
w
it
h
r
an
d
o
m
f
o
r
est
to
en
h
a
n
ce
th
e
cla
s
s
i
f
icatio
n
p
r
o
ce
s
s
.
T
h
e
n
ex
t
s
ec
tio
n
d
is
c
u
s
s
es
ab
o
u
t
th
e
r
esear
ch
p
r
o
b
lem
s
ass
o
ciate
d
w
ith
e
x
is
ti
n
g
tech
n
iq
u
es.
Sak
t
h
i
et
a
l.
[
3
1
]
T
h
e
Un
it
C
o
m
m
it
m
e
n
t
(
UC
)
is
s
u
e
h
as
b
ee
n
p
r
ep
ar
ed
b
y
in
co
r
p
o
r
ates
w
i
n
d
en
er
g
y
g
e
n
er
ato
r
s
alo
n
g
w
it
h
th
er
m
a
l p
o
w
er
m
et
h
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.
9
,
No
.
2
,
A
p
r
il 2
0
1
9
:
9
9
2
-
1
0
0
1
994
Ha
m
ai
n
e
et
a
l.
[
3
2
]
d
e
m
o
n
s
tr
ates
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
p
r
ec
is
el
y
d
if
f
er
e
n
tiate
s
ta
n
d
ar
d
b
r
ain
i
m
a
g
es
f
r
o
m
th
e
ir
r
eg
u
lar
o
n
e
s
a
n
d
b
en
ig
n
lesi
o
n
s
f
r
o
m
m
ali
g
n
a
n
t
tu
m
o
r
s
.
Si
m
ilar
l
y
B
an
g
ar
e
et
a
l.
[
3
3
]
illu
s
tr
ated
an
d
u
s
ed
to
lo
o
k
f
o
r
th
e
tar
g
e
t
ed
s
ig
n
i
f
ica
n
ce
alo
n
g
w
it
h
r
e
v
ea
lin
g
t
h
e
b
es
t
-
f
o
cu
s
ed
g
r
ap
h
ic
lo
ca
tio
n
b
y
w
a
y
o
f
aliasi
n
g
s
ea
r
ch
tec
h
n
iq
u
e
i
n
clu
d
ed
w
it
h
n
o
v
el
“
Ne
u
r
o
en
d
o
s
co
p
y
A
d
ap
ter
Mo
d
u
le
(
NAM
)
”
m
eth
o
d
.
1
.
2
.
T
he
p
ro
ble
m
T
h
e
s
ig
n
i
f
ica
n
t r
esear
c
h
p
r
o
b
l
e
m
s
ar
e
as
f
o
llo
w
s
:
1)
E
x
is
ti
n
g
ap
p
r
o
ac
h
es
d
o
es
n
‟
t
o
f
f
er
eq
u
al
e
m
p
h
a
s
is
o
n
j
o
in
tl
y
ad
d
r
ess
i
n
g
t
h
e
p
r
o
b
le
m
s
o
f
d
etec
tio
n
a
n
d
class
i
f
icatio
n
o
f
b
r
ea
s
t c
an
ce
r
.
2)
T
h
er
e
ar
e
less
b
en
ch
m
ar
k
ed
m
o
d
el
to
p
r
o
v
e
ef
f
icie
n
c
y
o
f
class
i
f
icatio
n
ap
p
r
o
ac
h
w
ith
r
esp
ec
t
to
s
i
m
p
li
s
tic
a
n
d
co
s
t e
f
f
ec
ti
v
e
co
m
p
u
tatio
n
al
m
o
d
eli
n
g
.
3)
A
d
o
p
tio
n
o
f
all
e
x
is
t
in
g
m
a
ch
in
e
lear
n
i
n
g
o
f
f
er
i
n
cr
ea
s
e
p
r
ec
is
io
n
b
u
t
at
th
e
co
s
t
o
f
r
eso
u
r
ce
an
d
tr
ain
i
n
g
d
ep
en
d
en
c
ies t
h
er
eb
y
m
i
n
i
m
izi
n
g
t
h
e
p
r
ac
tical
u
ti
lit
y
.
4)
Ma
j
o
r
ity
o
f
t
h
e
ex
i
s
ti
n
g
m
e
ch
an
i
s
m
h
a
s
m
a
n
u
al
s
elec
tio
n
o
f
o
b
s
er
v
atio
n
ar
ea
an
d
t
h
er
e
ar
e
less
in
v
o
l
u
n
tar
y
tec
h
n
iq
u
es to
s
u
p
p
o
r
t th
is
p
h
en
o
m
en
o
n
.
T
h
er
ef
o
r
e,
th
e
p
r
o
b
lem
s
tate
m
en
t o
f
t
h
e
p
r
o
p
o
s
ed
s
tu
d
y
ca
n
b
e
s
tated
as
“Deve
lo
p
in
g
a
co
s
t e
ffective
co
mp
u
ta
tio
n
a
l
mo
d
elin
g
fo
r
jo
in
tly
a
d
d
r
ess
in
g
th
e
lo
ca
liz
a
tio
n
a
n
d
cla
s
s
ifica
tio
n
p
r
o
b
lems
a
s
s
o
cia
ted
w
ith
b
r
ea
s
t c
a
n
ce
r
d
ia
g
n
o
s
is
is
s
til
l
a
n
o
p
en
ch
a
llen
g
e”
.
T
h
e
n
ex
t
s
ec
tio
n
o
u
tl
in
e
s
s
o
lu
tio
n
to
th
is
is
s
u
e.
1
.
3
.
P
r
o
po
s
ed
s
o
lutio
n
T
h
e
p
r
o
p
o
s
ed
w
o
r
k
is
a
co
n
ti
n
u
atio
n
o
f
o
u
r
p
r
io
r
i
m
p
le
m
e
n
t
atio
n
[
3
4
]
an
d
[
3
5
]
.
I
n
t
h
e
p
r
esen
t
w
o
r
k
,
an
i
n
te
g
r
ated
f
r
a
m
e
w
o
r
k
is
m
o
d
eled
t
h
at
is
m
ea
n
t
f
o
r
ad
d
r
ess
in
g
t
h
e
j
o
in
t
p
r
o
b
lem
s
ass
o
ciate
d
w
it
h
lo
ca
lizatio
n
as
w
ell
as
cla
s
s
i
f
i
ca
tio
n
in
b
r
ea
s
t
ca
n
ce
r
.
T
h
e
im
p
le
m
e
n
tat
io
n
o
f
t
h
e
p
r
o
p
o
s
e
d
s
y
s
te
m
is
ca
r
r
ied
ou
t c
o
n
s
id
er
in
g
a
n
al
y
tical
r
ese
ar
ch
m
et
h
o
d
o
lo
g
y
.
T
h
e
s
ch
e
m
atic
f
lo
w
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
a
s
f
o
llo
w
s
:
L
o
c
a
l
i
z
a
t
i
o
n
P
r
o
b
l
e
m
C
l
a
s
s
i
f
i
c
a
t
i
o
n
P
r
o
b
l
e
m
A
u
t
o
-
s
e
g
m
e
n
t
a
t
i
o
n
M
u
l
t
i
-
l
a
y
e
r
e
n
h
a
n
c
e
m
e
n
t
P
e
r
f
o
r
m
L
o
c
a
l
i
z
a
t
i
o
n
T
h
r
e
s
h
o
l
d
i
n
g
O
b
j
e
c
t
i
v
e
F
u
n
c
t
i
o
n
(
B
i
o
-
I
n
s
p
i
r
e
d
)
E
l
i
m
i
n
a
t
i
o
n
S
u
r
p
l
u
s
R
e
g
i
o
n
N
o
r
m
a
l
i
z
a
t
i
o
n
P
e
c
t
o
r
a
l
M
u
s
c
l
e
A
p
p
l
y
D
W
T
B
i
o
-
i
n
s
p
i
r
e
d
o
p
t
i
m
i
z
a
t
i
o
n
A
p
p
l
y
R
u
l
e
-
S
e
t
P
e
r
f
o
r
m
B
i
n
a
r
y
C
l
a
s
s
i
f
i
c
a
t
i
o
n
Fig
u
r
e
1
.
Sch
e
m
atic
f
lo
w
o
f
p
r
o
p
o
s
ed
s
y
s
te
m
Fig
u
r
e
1
h
ig
h
li
g
h
ts
th
a
t
p
r
o
p
o
s
ed
s
y
s
te
m
f
ir
s
t
ad
d
r
ess
t
h
e
lo
ca
lizatio
n
p
r
o
b
le
m
a
n
d
th
e
n
t
h
e
class
i
f
icatio
n
p
r
o
b
lem
.
I
n
o
r
d
er
to
a
d
d
r
ess
lo
ca
lizatio
n
p
r
o
ce
s
s
,
a
m
u
lti
-
la
y
er
e
n
h
a
n
ce
m
en
t
is
b
eig
n
ca
r
r
ied
o
u
t
w
it
h
a
n
aid
o
f
t
h
r
es
h
o
ld
in
g
a
n
d
u
s
in
g
b
io
-
in
s
p
ir
ed
b
ased
i
m
p
licatio
n
o
f
o
b
j
ec
tiv
e
f
u
n
ctio
n
.
T
h
e
class
if
icatio
n
p
r
o
b
le
m
is
s
o
r
ted
b
y
p
er
f
o
r
m
in
g
eli
m
i
n
atio
n
o
f
th
e
s
u
r
p
lu
s
r
e
g
io
n
f
o
llo
w
ed
b
y
n
o
r
m
aliza
t
io
n
an
d
r
e
m
o
v
al
o
f
th
e
p
ec
to
r
al
m
u
s
cle.
T
h
e
o
u
tco
m
e
is
f
u
r
th
er
s
u
b
j
ec
ted
t
o
d
is
cr
ete
w
a
v
elet
tr
an
s
f
o
r
m
atio
n
in
o
r
d
er
to
ex
t
r
ac
t
d
ec
o
m
p
o
s
ed
w
av
ele
ts
as
th
e
f
ea
tu
r
e.
T
h
e
p
r
o
ce
s
s
is
t
h
an
s
u
b
j
ec
ted
to
th
e
b
io
-
in
s
p
ir
ed
b
ased
o
p
ti
m
izati
o
n
p
r
in
cip
le
th
at
r
es
u
lt
s
i
n
b
e
tter
s
elec
tio
n
o
f
r
eg
io
n
s
w
it
h
m
o
s
t
p
r
o
b
ab
ilit
y
o
f
f
ea
t
u
r
es
b
ea
r
in
g
ca
n
ce
r
o
u
s
r
e
g
io
n
.
T
h
e
in
f
er
en
ci
n
g
o
f
t
h
e
o
u
tco
m
e
is
ca
r
r
ied
o
u
t
b
y
ap
p
ly
in
g
r
u
le
-
s
et
t
h
at
s
ig
n
i
f
ica
n
t
as
s
is
t
s
in
p
er
f
o
r
m
i
n
g
b
i
n
ar
y
cla
s
s
i
f
icatio
n
p
r
o
ce
s
s
.
T
h
er
ef
o
r
e,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
o
f
f
er
s
a
p
r
o
g
r
ess
iv
e
m
ec
h
a
n
is
m
to
ad
d
r
ess
b
o
th
t
h
e
p
r
o
b
le
m
s
in
o
r
d
er
to
o
f
f
er
b
etter
class
if
ic
atio
n
p
er
f
o
r
m
a
n
c
e.
T
h
e
o
u
tco
m
es
ar
e
m
ad
e
w
ith
r
esp
ec
t
to
b
in
ar
ized
class
i
f
ic
atio
n
in
th
e
f
o
r
m
o
f
m
ali
g
n
a
n
t
(
ab
n
o
r
m
al)
a
n
d
b
en
ig
n
(
n
o
r
m
al)
s
tate
o
f
b
r
ea
s
t
ca
n
ce
r
.
T
h
e
n
ex
t sectio
n
o
u
tli
n
es a
l
g
o
r
ith
m
i
m
p
le
m
e
n
tat
io
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
n
o
ve
l a
p
p
r
o
a
c
h
to
jo
in
tly
a
d
d
r
ess
lo
ca
liz
a
tio
n
a
n
d
cla
s
s
ifica
tio
n
o
f
b
r
ea
s
t c
a
n
ce
r
u
s
in
g
…
(
S
u
s
h
ma
S
.
J
.
)
995
2.
AL
G
O
RI
T
H
M
I
M
P
L
E
M
E
NT
A
T
I
O
N
T
h
e
p
r
im
ar
y
f
u
n
ctio
n
o
f
t
h
e
c
o
r
e
alg
o
r
ith
m
is
to
e
n
s
u
r
e
an
ef
f
ec
ti
v
e
d
etec
tio
n
f
o
l
lo
w
ed
b
y
class
i
f
icatio
n
o
f
t
h
e
b
r
ea
s
t
c
an
ce
r
f
r
o
m
t
h
e
ca
p
tu
r
ed
m
e
d
ical
i
m
a
g
e.
T
h
e
p
r
o
p
o
s
ed
a
lg
o
r
ith
m
u
s
es
b
io
-
in
s
p
ir
ed
alg
o
r
it
h
m
ic
ap
p
r
o
ac
h
f
o
r
d
esig
n
in
g
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
.
T
h
e
co
m
p
lete
o
p
er
atio
n
o
f
th
e
a
lg
o
r
it
h
m
is
d
is
cu
s
s
ed
w
it
h
r
esp
ec
t
to
alg
o
r
ith
m
d
esi
g
n
f
o
r
lo
ca
lizin
g
t
h
e
ar
ea
o
f
b
r
ea
s
t
ca
n
ce
r
an
d
alg
o
r
ith
m
f
o
r
b
in
ar
ized
class
i
f
icatio
n
o
f
th
e
b
r
ea
s
t c
an
ce
r
as f
o
llo
w
i
n
g
:
2
.
1
.
Alg
o
rit
h
m
de
s
ig
n f
o
r
lo
ca
lizing
t
he
a
re
a
o
f
brea
s
t
ca
ncer
T
h
is
alg
o
r
it
h
m
is
r
esp
o
n
s
ib
le
f
o
r
lo
ca
lizin
g
t
h
e
e
x
ac
t
p
o
s
itio
n
o
f
th
e
ca
n
ce
r
i
n
t
h
e
b
r
ea
s
t
c
an
ce
r
f
o
r
a
g
iv
e
n
m
ed
ical
i
m
ag
e.
A
p
p
l
y
in
g
th
e
m
et
h
o
d
o
f
s
i
m
p
le
b
io
-
i
n
s
p
ir
ed
tech
n
iq
u
e,
th
e
al
g
o
r
ith
m
ta
k
es
t
h
e
in
p
u
t
o
f
I
(
in
p
u
t
i
m
a
g
e)
an
d
y
ield
t
h
e
o
u
tco
m
e
o
f
I
l
o
c
(
Ou
tp
u
t
i
m
ag
e)
w
i
th
id
e
n
ti
f
icatio
n
o
f
th
e
ca
n
ce
r
o
u
s
r
eg
io
n
.
T
h
e
s
tep
s
o
f
th
e
al
g
o
r
ith
m
ar
e
as f
o
llo
w
i
n
g
:
A
l
g
o
r
ith
m
f
o
r
L
o
ca
lizi
n
g
t
h
e
A
r
ea
o
f
B
r
ea
s
t Ca
n
ce
r
I
n
p
u
t: I
(
I
n
p
u
t I
m
ag
e)
Ou
tp
u
t: I
loc
(
Ou
tp
u
t I
m
a
g
e)
Star
t
1.
in
it I
2.
I
seg
f
1
(
T
h
(
I
)
)
3.
I
prim
f
2
(I
se
g
)
4.
I
sec
f
3
(I
pri
m
)
5.
I
ter
f
4
(I
sec
)
6.
I
op
f
5
(I
ter
)
E
n
d
T
h
e
d
escr
ip
tio
n
o
f
th
e
alg
o
r
it
h
m
i
s
as
f
o
llo
w
s
:
Af
ter
tak
i
n
g
th
e
i
n
p
u
t
o
f
m
ed
ical
i
m
ag
e
(
L
in
e
-
1
)
,
it
is
s
u
b
j
ec
ted
to
d
if
f
er
en
t
ex
p
licit
f
u
n
ctio
n
s
to
ca
r
r
y
o
u
t
d
if
f
er
e
n
t
p
r
o
ce
s
s
in
g
.
T
h
e
alg
o
r
ith
m
i
n
tr
o
d
u
ce
s
a
f
u
n
ctio
n
f
1
(
x
)
t
h
at
i
s
ess
e
n
tiall
y
m
ea
n
t
f
o
r
ca
r
r
y
i
n
g
o
u
t
i
n
v
o
l
u
n
tar
y
s
e
g
m
en
taio
n
p
r
o
ce
s
s
(
L
in
e
-
2
)
.
T
h
is
f
u
n
ct
io
n
i
m
p
le
m
en
t
s
a
c
u
t
-
o
f
f
o
p
er
ato
r
T
h
o
v
er
th
e
in
p
u
t
i
m
ag
e
I
f
o
llo
w
ed
b
y
o
b
tain
i
n
g
b
i
n
ar
ized
i
m
a
g
e
in
o
r
d
er
to
co
n
s
tr
u
ct
a
s
u
itab
l
e
m
as
k
.
T
h
e
alg
o
r
ith
m
t
h
a
n
o
n
s
tr
ict
s
t
h
e
h
i
g
h
est
p
o
s
s
ib
le
m
as
k
a
n
d
co
n
ti
n
u
e
lab
elin
g
it
f
o
llo
w
ed
b
y
t
h
e
co
n
ca
ten
a
tio
n
o
f
all
t
h
e
ar
ea
.
T
h
is
o
p
er
atio
n
lead
s
to
th
e
m
a
x
i
m
u
m
v
alu
e
o
f
t
h
e
co
n
ca
ten
ated
ar
ea
o
f
th
e
m
as
k
.
T
h
e
s
eg
m
e
n
tatio
n
i
s
ca
r
r
ied
o
u
t
o
v
er
o
r
ig
in
al
i
m
a
g
e
as
w
el
l
o
n
m
as
k
ed
i
m
a
g
e
en
s
u
r
in
g
t
h
at
o
n
l
y
o
n
e
s
p
ec
if
icatio
n
o
f
m
as
k
is
co
n
s
id
e
r
ed
.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
also
p
er
f
o
r
m
s
a
s
i
m
p
li
f
ied
o
p
er
atio
n
u
s
in
g
a
n
o
th
er
f
u
n
ctio
n
f
2
(
x
)
t
h
at
ta
k
es
in
t
h
e
i
n
p
u
t
o
f
s
e
g
m
e
n
ted
i
m
ag
e.
T
h
e
al
g
o
r
ith
m
f
ir
s
t
p
er
f
o
r
m
s
lo
ca
l
co
n
tr
ast
m
o
d
if
icatio
n
co
n
s
id
er
i
n
g
in
p
u
t
ar
g
u
m
e
n
ts
o
f
p
r
o
ce
s
s
ed
i
m
a
g
e
an
d
w
ei
g
h
t
f
ac
to
r
.
(
B
y
p
r
o
ce
s
s
ed
i
m
ag
e,
it
w
ill
m
ea
n
ap
p
l
y
in
g
u
n
s
i
g
n
ed
i
n
te
g
er
o
f
8
b
i
ts
o
n
in
p
u
t i
m
ag
e
f
o
ll
o
w
ed
b
y
alter
i
n
g
th
e
p
r
ec
is
io
n
to
d
o
u
b
le)
.
T
h
e
o
b
ta
in
ed
i
m
a
g
e
f
r
o
m
t
h
e
lo
ca
l
co
n
tr
ast
m
o
d
if
icat
io
n
is
t
h
en
s
u
b
j
ec
ted
to
th
e
en
tr
o
p
y
f
o
r
m
u
latio
n
f
o
llo
w
ed
b
y
ap
p
ly
in
g
s
o
b
el
o
p
er
ato
r
to
o
b
t
ain
p
r
o
m
i
n
e
n
t
ed
g
e
s
.
An
o
b
j
ec
tiv
e
f
u
n
ctio
n
is
d
ef
in
ed
as:
MN
E
E
.
)).
l
o
g
(
l
o
g
(
(
1
)
I
n
th
e
ab
o
v
e
ex
p
r
es
s
io
n
(
1
)
,
an
e
m
p
ir
ical
ex
r
e
s
s
io
n
o
f
o
b
j
ec
tiv
e
f
u
n
ctio
n
α
is
co
n
s
tr
u
cted
th
a
t
co
n
s
id
er
s
t
h
e
ed
g
e
co
m
p
o
n
en
t
s
E
o
b
tain
ed
f
r
o
m
s
u
m
m
a
tio
n
o
f
all
t
h
e
ed
g
e
s
u
s
i
n
g
s
o
b
el
o
p
er
ato
r
o
f
th
e
ar
ea
o
b
tain
ed
af
ter
lo
ca
l
co
n
tr
ast
m
o
d
i
f
icat
io
n
.
A
p
p
l
y
in
g
a
s
i
m
p
le
b
io
-
in
s
p
ir
ed
ap
p
r
o
ac
h
,
if
α
>
g
b
est,
th
a
n
t
h
e
o
r
ig
in
al
v
al
u
e
o
f
α
i
s
co
n
s
id
er
ed
as
th
e
g
b
est
o
r
else
a
p
r
o
b
ab
ilit
y
v
al
u
e
[
0
.
1
-
1
]
is
ass
ig
n
ed
to
t
h
e
p
b
est.
T
h
e
n
ex
t
s
tep
o
f
t
h
e
al
g
o
r
ith
m
i
s
to
ap
p
l
y
t
h
e
s
ec
o
n
d
ar
y
e
n
h
a
n
ce
m
en
t
u
s
i
n
g
f
u
n
c
tio
n
f
3
(
x
)
th
at
i
s
d
ev
elo
p
ed
o
n
th
e
b
asis
o
f
t
h
r
esh
o
ld
o
p
tim
izatio
n
(
L
i
n
e
-
4
)
.
T
h
e
alg
o
r
ith
m
co
m
p
u
te
s
th
e
p
r
o
b
ab
ilit
y
as
w
el
l
as
h
i
s
to
g
r
a
m
f
o
r
th
e
ac
t
u
al
i
n
p
u
t
i
m
ag
e
f
o
l
lo
w
ed
b
y
i
n
it
ializatio
n
o
f
m
e
an
an
d
w
e
ig
h
t
f
ac
to
r
.
C
o
m
p
u
t
atio
n
o
f
v
ar
ian
ce
is
ca
r
r
ied
o
u
t
an
d
o
n
l
y
th
e
v
a
r
ian
ce
m
atc
h
i
n
g
w
it
h
th
r
es
h
o
ld
is
co
n
s
id
er
ed
f
o
r
th
e
f
u
r
th
er
co
m
p
u
tatio
n
.
T
h
is
s
u
m
m
atio
n
o
f
m
a
x
i
m
u
m
v
al
u
e
o
f
t
h
is
n
e
w
v
ar
ia
n
c
e
is
u
s
ed
f
o
r
o
b
tain
i
n
g
t
h
e
n
e
w
t
h
r
es
h
o
ld
v
alu
e
.
T
h
e
o
u
tco
m
e
is
t
h
e
n
s
u
b
j
ec
ted
to
th
e
ter
tiar
y
e
n
h
a
n
ce
m
en
t
u
s
i
n
g
a
f
u
n
ctio
n
f
4
(
x
)
.
I
n
t
h
i
s
ca
s
e,
t
h
e
o
u
tco
m
e
i
m
a
g
e
I
s
ec
is
s
u
b
j
ec
ted
to
b
i
n
ar
izatio
n
f
o
llo
w
ed
b
y
c
h
ec
k
i
n
g
t
h
e
s
i
tu
at
io
n
w
h
en
t
h
e
v
a
l
u
e
o
f
t
h
e
b
in
ar
ized
i
m
a
g
e
i
s
m
o
r
e
t
h
a
n
1
0
,
w
h
ich
is
o
n
l
y
t
h
e
ca
s
e
o
f
eit
h
er
l
u
m
p
o
r
n
o
d
u
le
i
n
t
h
e
b
r
ea
s
t
tis
s
u
e.
T
h
e
f
i
n
al
f
u
n
ct
io
n
f
5
(
x
)
i
s
ap
p
lied
to
en
s
u
r
e
th
a
t
th
e
r
eg
io
n
i
n
f
ec
ted
w
i
th
ca
n
ce
r
is
id
en
tifie
d
(
L
i
n
e
-
4
a
n
d
L
in
e
-
5
)
.
A
s
li
g
h
t
a
m
o
u
n
t
o
f
r
ec
u
r
s
iv
e
f
u
n
c
tio
n
i
s
d
esi
g
n
ed
to
ap
p
l
y
p
r
o
b
ab
ilit
y
to
ascer
tai
n
t
h
at
th
er
e
i
s
a
r
e
g
u
lar
u
p
d
ate
o
f
th
e
th
r
es
h
o
ld
p
ar
a
m
eter
i
n
o
r
d
er
to
en
s
u
r
e
a
b
etter
f
o
r
o
f
id
en
t
if
icatio
n
p
r
o
ce
s
s
o
f
th
e
r
eg
io
n
d
etec
ted
w
it
h
t
h
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.
9
,
No
.
2
,
A
p
r
il 2
0
1
9
:
9
9
2
-
1
0
0
1
996
ca
n
ce
r
.
An
o
th
er
i
n
ter
esti
n
g
f
a
ct
o
f
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
i
s
th
at
it
o
f
f
er
s
a
s
i
g
n
if
ica
n
t
i
n
s
ig
h
t
s
o
f
th
e
h
ig
h
er
co
n
tr
asti
v
e
r
eg
io
n
to
b
e
n
o
r
m
al
tis
s
u
e
o
r
ca
n
ce
r
-
in
f
lic
ted
tis
s
u
e
i
n
o
r
d
er
to
en
s
u
r
e
t
h
at
a
s
i
m
p
le
an
d
ac
c
u
r
ac
y
id
en
ti
f
icatio
n
o
f
ca
r
r
ied
o
u
t u
s
in
g
b
io
-
in
s
p
ir
ed
ap
p
r
o
ac
h
.
2
.
2
.
Alg
o
rit
h
m
f
o
r
bin
a
rize
d
cla
s
s
if
ica
t
io
n o
f
t
he
brea
s
t
c
a
ncer
T
h
e
p
r
io
r
alg
o
r
ith
m
co
n
tr
ib
u
te
s
in
ca
r
r
y
i
n
g
o
u
t
lo
ca
lizat
io
n
o
f
th
e
r
e
g
io
n
i
n
f
ec
ted
w
ith
b
r
e
ast
ca
n
ce
r
w
h
ile
th
is
a
lg
o
r
it
h
m
as
s
is
t
to
ca
r
r
y
o
u
t
a
s
i
m
p
le
clas
s
i
f
icati
o
n
tec
h
n
iq
u
e
b
y
e
v
o
lv
i
n
g
u
p
w
it
h
a
s
i
m
p
le
an
d
n
o
v
el
b
io
-
i
n
s
p
ir
ed
ap
p
r
o
ac
h
.
T
h
is
alg
o
r
it
h
m
i
s
es
s
en
tial
f
o
r
i
m
p
le
m
en
tin
g
a
n
o
v
el
b
io
-
i
n
s
p
r
ed
ap
p
r
o
ac
h
f
o
r
ca
r
r
y
i
n
g
o
u
t
id
e
n
ti
f
icatio
n
f
o
l
lo
w
ed
b
y
b
in
ar
ized
cla
s
s
i
f
icat
io
n
o
f
t
h
e
o
u
tco
m
e.
T
h
e
alg
o
r
ith
m
tak
e
s
i
n
th
e
in
p
u
t
o
f
i
n
p
u
t
i
m
ag
e
th
a
t
a
f
ter
p
r
o
ce
s
s
in
g
r
e
s
u
l
ts
in
C
C
(
C
e
n
ter
o
f
cl
u
s
ter
)
a
n
d
I
o
u
t
(
clas
s
if
icatio
n
o
u
tco
m
e)
.
T
h
e
s
tep
s
o
f
th
e
al
g
o
r
ith
m
ar
e
as f
o
llo
w
s
:
A
l
g
o
r
ith
m
f
o
r
B
in
ar
iz
ed
C
lass
if
icatio
n
o
f
t
h
e
B
r
ea
s
t Can
ce
r
I
n
p
u
t: I
(
in
p
u
t i
m
a
g
e)
Ou
tp
u
t: C
C
(
C
e
n
ter
o
f
clu
s
ter
)
,
I
out
(
class
if
icat
io
n
o
u
tco
m
e)
Star
t
1.
I
f
6
(I)
2.
I
f
8
(
p
r
ec
(
f
7
(I)))
3.
I
f
j
>c
.
m
a
x
I
4.
(s
1
, s
2
)
=(
s
1
, s
2
)
+(
j
.
h
(
id
x
)
,
h
(
id
x
)
)
5.
E
n
d
6.
Fo
r
k
=1
:n
7.
[p
1
, p
2
]
[
R
w
(
id
x
1
)
,
R
w
(
~id
x
1
)]
8.
Fo
r
l=x
i
T
9.
id
x
=id
x
+1
10.
I
f
l>T
11.
(s
1p
, s
2p
)
=(
s
1p
, s
2p
)
+(
l.h
(
id
x
)
,
h
(
id
x
)
)
12.
E
n
d
13.
I
f
l<T
&
&
l>(
T
-
c
1
.
m
a
x
I
)
14.
s
1b
, s
2b
)
=(
s
1b
, s
2b
)
+(
j
.
h
(
id
x
)
,
h
(
i
d
x
)
)
15.
E
n
d
16.
E
n
d
17.
I
op
(x
win
-
1
0
:x
w
in
+1
0
,
1
:Ay
)
=I
se
g
18.
I
f
Fit
<P
best
19.
[
SIp
ar
t P
best
]
C
C
&
P
best
=Fit
20.
E
ls
e
21.
s
to
r
e
p
r
io
r
v
alu
e
o
f
SIp
ar
t
22.
I
f
P
b
est<Gb
est
23.
G
best
C
C
=P
best
C
C
,
G
bes
t
=P
best,
24.
C
C
=
SIp
ar
t(
g
best
id
,
id
v
ec
(
g
best
i
d
)
)
25.
I
out
b
in
(
C
C
,
„
Ma
li
g
n
a
n
t
‟
,
„
B
en
ig
n
‟
)
;
E
n
d
T
h
e
s
tep
s
o
f
th
e
al
g
o
r
ith
m
ar
e
as
f
o
llo
w
s
:
T
h
e
alg
o
r
it
h
m
u
s
e
s
a
f
u
n
ct
io
n
f
6
(
x
)
t
h
at
is
m
ea
n
t
f
o
r
ass
es
s
i
n
g
t
h
e
lef
t
a
n
d
r
ig
h
t
o
r
ien
tatio
n
o
f
an
i
m
ag
e
f
o
llo
w
e
d
b
y
co
r
r
ec
tin
g
t
h
e
o
r
ien
tatio
n
f
o
r
en
h
an
ci
n
g
th
e
class
i
f
icatio
n
p
r
o
ce
s
s
(
L
i
n
e
-
1
)
.
T
h
e
n
ex
t
s
tep
o
f
th
e
al
g
o
r
ith
m
is
to
ca
r
r
y
o
u
t
s
e
g
m
en
ta
tio
n
to
en
s
u
r
e
th
at
n
o
u
n
w
an
ted
r
eg
io
n
is
s
elec
ted
f
o
r
n
ex
t
p
r
o
ce
s
s
o
f
a
n
al
y
s
i
s
(
L
in
e
-
2
)
.
Fo
r
th
is
p
u
r
p
o
s
e,
t
h
e
s
e
g
m
e
n
tatio
n
is
ca
r
r
ied
o
u
t
b
y
o
b
tain
i
n
g
th
e
b
i
n
ar
y
i
m
a
g
e
u
s
i
n
g
t
w
o
d
if
f
er
e
n
t
ex
p
licit
f
u
n
c
tio
n
f
7
(
x
)
a
n
d
f
8
(
x
)
.
T
h
e
n
ex
t
p
ar
t
o
f
th
e
al
g
o
r
ith
m
i
s
all
ab
o
u
t
ap
p
ly
i
n
g
a
b
io
-
in
s
p
ir
ed
alg
o
r
ith
m
in
o
r
d
er
to
r
em
o
v
e
th
e
u
n
w
a
n
ted
tis
s
u
e
t
h
at
cr
ea
tes
an
i
m
p
ed
i
m
e
n
t
to
w
ar
d
s
id
en
ti
f
y
in
g
ca
n
ce
r
o
u
s
r
e
g
i
o
n
(
L
i
n
e
-
3
to
L
i
n
e
-
2
4
)
.
T
h
e
alg
o
r
ith
m
o
b
tain
s
h
is
to
g
r
a
m
h
,
i
n
d
ex
id
x
,
in
o
r
d
er
to
o
b
tain
w
i
n
d
o
w
s
s
1
a
n
d
s
2
.
T
h
e
alg
o
r
ith
m
p
er
f
o
r
m
s
d
u
al
class
i
f
icat
io
n
o
f
th
e
r
eg
io
n
v
iz.
p
1
an
d
p
2
f
o
llo
w
ed
b
y
co
m
p
u
tatio
n
o
f
th
e
th
r
esh
o
ld
v
a
lu
e
T
th
at
is
e
q
u
iv
ale
n
t
to
s
1
/s
2
.
T
h
e
alg
o
r
ith
m
f
u
r
t
h
er
co
m
p
u
t
es
u
p
d
ated
th
r
esh
o
ld
f
o
llo
w
ed
b
y
ev
al
u
a
ti
n
g
f
it
n
es
s
v
al
u
e
f
it
w
it
h
r
esp
ec
t
to
th
e
p
b
est
v
al
u
e.
L
i
k
e
w
i
s
e,
t
h
e
s
i
m
ilar
ch
ec
k
i
s
ca
r
r
ied
o
u
t
to
w
ar
d
s
ass
e
s
s
i
n
g
t
h
e
co
m
p
ar
ativ
e
v
alu
e
o
f
p
b
est
w
i
th
r
esp
ec
t
to
g
b
est.
T
h
is
p
r
o
ce
s
s
is
r
es
u
m
ed
b
y
co
m
p
u
ti
n
g
ce
n
t
er
o
f
cl
u
s
ter
t
h
at
is
co
n
s
id
er
ed
to
b
e
th
e
r
eg
io
n
o
f
b
est
o
u
tco
m
e
f
o
r
th
e
g
i
v
en
f
r
a
m
e
o
f
a
n
i
m
a
g
e.
T
h
e
p
r
i
m
e
ag
e
n
d
a
b
eh
in
d
d
esi
g
n
i
n
g
t
h
e
o
p
ti
m
izat
io
n
tech
n
iq
u
e
i
s
to
f
il
ter
o
u
t
b
o
th
p
b
est
an
d
g
b
est
f
r
o
m
t
h
e
g
iv
en
p
r
o
b
lem
s
p
ac
e,
w
h
er
e
t
h
e
f
it
n
es
s
f
u
n
ctio
n
i
s
co
n
s
is
ten
tl
y
u
p
d
ated
if
t
h
er
e
is
an
y
f
o
r
m
o
f
c
h
an
g
e
i
n
t
h
e
d
i
m
e
n
s
io
n
o
f
t
h
e
p
r
o
b
lem
s
p
ac
e.
Fo
r
th
is
p
u
r
p
o
s
e,
if
t
h
er
e
is
an
y
f
o
r
m
o
f
s
li
g
h
t
est
d
ev
iat
io
n
f
o
r
th
e
i
m
ag
e
s
d
en
s
it
y
(
t
h
at
o
cc
u
r
s
in
d
if
f
er
e
n
t
i
m
a
g
e
s
a
m
p
les),
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
o
ve
l a
p
p
r
o
a
c
h
to
jo
in
tly
a
d
d
r
ess
lo
ca
liz
a
tio
n
a
n
d
cla
s
s
ifica
tio
n
o
f
b
r
ea
s
t c
a
n
ce
r
u
s
in
g
…
(
S
u
s
h
ma
S
.
J
.
)
997
it
ca
n
ea
s
i
l
y
id
e
n
tit
y
t
h
e
lo
ca
ti
o
n
.
Ho
w
e
v
er
,
th
e
s
ig
n
i
f
ica
n
t
b
en
ef
it
is
t
h
at
it
c
h
ec
k
s
f
o
r
th
e
co
m
p
lete
r
e
g
io
n
i
n
o
r
d
er
to
av
o
id
f
alse
p
o
s
iti
v
e
w
h
ile
m
a
k
i
n
g
d
ec
is
io
n
.
Fi
n
all
y
,
f
u
zz
y
in
f
er
en
ce
s
y
s
te
m
is
u
tili
ze
d
in
o
r
d
er
to
f
u
r
t
h
er
ascer
tai
n
th
e
clas
s
i
f
ic
atio
n
o
u
tco
m
e
f
o
r
s
tati
n
g
w
h
eth
er
it
is
m
a
lig
n
a
n
t
o
r
b
en
ig
n
s
tate
o
f
e
h
b
r
ea
s
t
ca
n
ce
r
.
T
h
e
n
ex
t sectio
n
d
is
c
u
s
s
es a
b
o
u
t t
h
e
o
u
tco
m
es o
b
tai
n
ed
.
3.
RE
SU
L
T
ANAL
YSI
S
Fro
m
t
h
e
d
is
c
u
s
s
io
n
o
f
alg
o
r
ith
m
i
m
p
le
m
en
tat
io
n
,
it
ca
n
b
e
s
ee
n
t
h
at
p
r
o
p
o
s
ed
s
y
s
te
m
p
er
f
o
r
m
s
lo
ca
lizatio
n
as
w
e
ll
as
class
i
f
icatio
n
o
f
th
e
b
r
ea
s
t
ca
n
ce
r
f
r
o
m
th
e
m
ed
ical
d
ataset
e.
g
.
DDSM
[
3
6
]
an
d
MI
A
S
[
3
7
]
.
Hen
ce
,
th
e
a
n
al
y
s
i
s
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
ca
r
r
ied
o
u
t
in
t
w
o
d
is
cr
e
te
w
a
y
v
iz.
v
i
s
u
al
ass
es
s
m
en
t a
n
d
n
u
m
er
ical
ass
ess
m
en
t.
Fo
llo
w
in
g
ar
e
th
e
d
is
cu
s
s
io
n
o
f
t
h
e
o
u
tco
m
es.
(
a)
I
n
p
u
t
i
m
a
g
e
(
b
)
A
u
to
s
e
g
m
e
n
ted
i
m
ag
e
(
c)
Prim
ar
y
en
c
(
d
)
Seco
n
d
ar
y
en
c
(
e)
T
er
tiar
y
en
h
(
f
)
L
o
ca
lized
r
eg
io
n
Fig
u
r
e
2
.
Vis
u
al
o
u
tco
m
e
s
o
f
l
o
ca
lizatio
n
o
f
b
r
ea
s
t c
an
ce
r
Fig
u
r
e
2
h
ig
h
li
g
h
ts
t
h
e
v
is
u
al
o
u
tco
m
es
to
s
h
o
w
th
e
s
ta
g
es
o
f
p
r
o
ce
s
s
in
g
in
v
o
lv
ed
i
n
id
en
ti
f
icatio
n
o
f
th
e
b
r
ea
s
t
ca
n
ce
r
.
A
clo
s
er
lo
o
k
in
to
t
h
e
o
u
tco
m
e
s
h
o
w
s
t
h
at
a
f
ter
p
er
f
o
r
m
i
n
g
in
v
o
l
u
n
ta
r
y
s
e
g
m
e
n
tat
io
n
o
f
th
e
i
n
p
u
t
i
m
a
g
e,
t
h
er
e
ar
e
th
r
ee
s
ta
g
es
o
f
b
io
-
in
s
p
ir
ed
i
m
a
g
e
e
n
h
a
n
ce
m
en
t
i.e
.
p
r
i
m
ar
y
,
s
ec
o
n
d
ar
y
,
an
d
ter
tiar
y
e
n
h
an
ce
m
e
n
t
Fi
g
u
r
e
2
(
c)
to
Fig
u
r
e
2
(
e)
.
I
t
ev
i
d
en
tl
y
s
h
o
w
s
t
h
at
ea
c
h
p
r
o
g
r
ess
r
en
d
er
ed
b
y
t
h
e
co
n
s
ec
u
tiv
e
p
r
o
ce
s
s
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
e
n
tail
s
th
e
i
n
c
r
ea
s
e
o
f
th
e
lo
ca
l
co
n
tr
ast
alo
n
g
w
i
th
r
e
m
o
v
al
o
f
th
e
u
n
w
an
ted
r
eg
io
n
s
.
T
h
e
co
m
p
lete
p
r
o
ce
s
s
i
n
g
ti
m
e
in
o
r
d
er
to
y
ield
th
i
s
o
u
tco
m
e
is
ap
p
r
o
x
i
m
ate
y
0
.
2
6
6
5
7
s
ec
o
n
d
s
in
w
i
n
d
o
w
s
.
Si
m
ilar
l
y
,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
a
ls
o
t
esti
f
ies
t
h
e
v
i
s
u
a
l
o
u
tco
m
e
s
o
f
th
e
cla
s
s
i
f
icatio
n
p
r
o
ce
s
s
as
h
i
g
h
lig
h
ted
i
n
T
ab
l
e
1
.
T
h
e
v
is
u
al
o
u
tco
m
e
s
h
o
ws
th
at
i
n
p
u
t
f
o
r
b
o
th
n
o
r
m
al
an
d
ab
n
o
r
m
al
i
m
a
g
e
s
ar
e
in
itiall
y
as
s
es
s
ed
f
o
r
an
y
f
o
r
m
o
f
u
n
w
a
n
ted
s
p
ac
es
th
at
is
n
o
t
at
all
co
n
s
id
er
ed
in
th
e
a
n
al
y
s
i
s
.
Hen
ce
,
af
ter
r
e
m
o
v
i
n
g
all
t
h
e
u
n
w
an
ted
r
eg
io
n
s
,
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
p
er
f
o
r
m
s
n
o
r
m
aliza
tio
n
o
f
t
h
e
i
m
a
g
es.
A
clo
s
er
lo
o
k
in
to
th
is
p
r
o
ce
s
s
o
f
n
o
r
m
aliza
tio
n
w
il
l
s
h
o
w
th
at
p
r
o
p
o
s
ed
s
y
s
te
m
p
er
f
o
r
m
s
n
o
r
m
aliza
tio
n
i
n
q
u
ite
a
d
if
f
er
en
t
m
a
n
n
er
f
o
r
b
o
th
n
o
r
m
al
a
n
d
ab
n
o
r
m
al
i
m
ag
es.
F
u
r
th
er
t
h
e
p
r
o
ce
s
s
o
f
f
ea
tu
r
e
ex
tr
ac
tio
n
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
2
,
A
p
r
il 2
0
1
9
:
9
9
2
-
1
0
0
1
998
ca
r
r
ied
o
u
t
w
it
h
a
n
aid
o
f
d
ec
o
m
p
o
s
ed
w
a
v
elets
o
b
tai
n
e
d
b
y
ap
p
l
y
i
n
g
d
is
cr
ete
w
a
v
e
let
tr
an
s
f
o
r
m
at
io
n
s
.
Fu
r
t
h
er
ap
p
l
y
i
n
g
th
e
n
o
v
el
b
io
-
i
n
s
p
ir
ed
alg
o
r
it
h
m
,
t
h
e
ac
t
u
al
r
eg
io
n
o
f
b
r
ea
s
t
ca
n
ce
r
i
s
f
i
n
a
ll
y
lo
ca
lized
a
n
d
i
s
n
o
w
r
ea
d
y
f
o
r
cla
s
s
i
f
icatio
n
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
a
p
p
lies
r
u
le
-
s
et
b
ased
ap
p
r
o
ac
h
es
u
s
in
g
b
in
ar
y
class
i
f
icatio
n
p
r
o
ce
s
s
,
w
h
er
e
t
h
e
f
in
al
l
y
lo
ca
lized
r
eg
io
n
i
s
d
ec
lar
ed
as
b
en
ig
n
o
r
m
ali
g
n
an
t
s
ta
g
e
o
f
ca
n
ce
r
af
ter
o
b
s
er
v
in
g
t
h
e
n
o
r
m
al
o
r
ab
n
o
r
m
al
s
ta
g
es o
f
ca
n
ce
r
.
T
ab
le
1
.
Vis
u
al
Ou
tco
m
e
o
f
C
lass
i
f
icatio
n
N
o
r
mal
A
b
n
o
r
mal
I
n
p
u
t
R
e
mo
v
a
l
o
f
u
n
w
a
n
t
e
d
r
e
g
i
o
n
N
o
r
mal
i
z
e
I
mag
e
2d
-
D
W
T
A
f
t
e
r
a
p
p
l
y
i
n
g
b
i
o
-
i
n
s
p
i
r
e
d
C
l
a
ssi
f
i
c
a
t
i
o
n
O
u
t
c
o
me
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
o
ve
l a
p
p
r
o
a
c
h
to
jo
in
tly
a
d
d
r
ess
lo
ca
liz
a
tio
n
a
n
d
cla
s
s
ifica
tio
n
o
f
b
r
ea
s
t c
a
n
ce
r
u
s
in
g
…
(
S
u
s
h
ma
S
.
J
.
)
999
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
a
ls
o
p
er
f
o
r
m
s
co
m
p
ar
ati
v
e
a
n
al
y
s
is
to
e
v
alu
a
te
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
class
i
f
icatio
o
n
T
h
e
o
u
tco
m
e
o
f
F
ig
u
r
e
3
s
h
o
w
s
t
h
at
m
ea
n
a
n
d
s
ta
n
d
ar
d
d
ev
iatio
n
o
f
p
r
o
p
o
s
ed
s
y
s
te
m
as
w
ell
as
ex
is
ti
n
g
cla
s
s
i
f
ier
s
e.
g
.
S
u
p
p
o
r
t
Vec
to
r
Ma
ch
i
n
e
(
SV
M)
,
K
-
Nea
r
est
Nei
g
h
b
o
r
(
K
NN)
,
an
d
A
r
ti
f
icial
Neu
r
al
Net
w
o
r
k
(
ANN)
.
Si
m
ilar
l
y
,
p
r
o
p
o
s
ed
s
y
s
te
m
al
s
o
o
f
f
er
s
r
ed
u
ce
d
s
k
e
w
n
e
s
s
a
n
d
k
u
r
to
s
is
v
al
u
e
i
n
Fig
u
r
e
4
.
T
h
e
class
if
ica
tio
n
ac
cu
r
ac
y
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
i
s
s
i
g
n
i
f
ican
tl
y
h
i
g
h
co
m
p
ar
ed
to
ex
i
s
ti
n
g
class
i
f
ier
s
(
i
n
F
ig
u
r
e
5
)
.
A
p
a
r
t
f
r
o
m
t
h
i
s
,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
also
o
f
f
er
s
f
a
s
ter
co
m
p
u
tatio
n
a
l
p
r
o
ce
s
s
in
g
ti
m
e
to
s
h
o
w
th
at
i
t
is
co
s
t
-
ef
f
ec
iv
e
ap
p
r
o
ac
h
to
ad
d
r
ess
th
e
j
o
in
t
lo
ca
lizatio
n
an
d
class
if
ic
atio
n
o
f
t
h
e
b
r
ea
s
t
ca
n
ce
r
w
ith
a
g
o
o
d
b
alan
ce
b
et
w
ee
n
ac
cu
r
ac
y
an
d
f
aster
r
esp
o
n
s
e
ti
m
e
in
Fig
u
r
e
6
.
Fig
u
r
e
3
.
C
o
m
p
ar
ativ
e
a
n
al
y
s
i
s
o
f
m
ea
n
an
d
d
ev
iatio
n
Fig
u
r
e
4
.
C
o
m
p
ar
ativ
e
a
n
al
y
s
i
s
o
f
s
k
e
w
n
e
s
s
&
k
u
r
to
s
is
Fig
u
r
e
5
.
C
o
m
p
ar
ativ
e
a
n
al
y
s
i
s
o
f
ac
cu
r
ac
y
Fig
u
r
e
6
.
C
o
m
p
ar
ativ
e
a
n
al
y
s
i
s
o
f
r
esp
o
n
s
e
ti
m
e
4.
CO
NCLU
SI
O
N
T
h
e
p
r
o
p
o
s
ed
r
esear
ch
w
o
r
k
o
f
f
er
s
a
n
i
n
s
i
g
h
t
t
h
at
it
i
s
f
ea
s
ib
le
to
p
r
esen
t
a
s
o
lu
t
io
n
to
w
a
r
d
s
j
o
in
tly
ad
d
r
ess
in
g
t
h
e
p
r
o
b
le
m
s
a
s
s
o
ciate
d
w
ith
d
etec
tio
n
an
d
cla
s
s
if
ica
tio
n
p
r
o
b
le
m
s
as
s
o
ciate
d
w
it
h
ea
r
l
y
s
ta
g
e
o
f
d
etec
tio
n
o
f
b
r
ea
s
t
ca
n
ce
r
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
in
itiall
y
ad
d
r
ess
es
lo
ca
lizatio
n
p
r
o
b
lem
s
b
y
u
s
in
g
a
n
o
v
el
m
u
lti
-
la
y
er
en
h
a
n
ce
m
e
n
t
u
s
i
n
g
n
o
v
el
th
r
e
s
h
o
ld
-
b
a
s
ed
ap
p
r
o
ac
h
alo
n
g
w
i
th
s
i
m
p
le
b
io
-
in
s
p
ir
ed
o
p
ti
m
izatio
n
th
at
allo
w
s
its
o
b
j
ec
tiv
e
f
n
cto
n
to
o
f
f
er
h
ig
h
y
ac
c
u
r
ate
o
u
tc
o
m
e
o
f
lo
ca
lized
r
eg
io
n
au
t
o
m
atica
ll
y
.
T
h
e
s
ec
o
n
d
p
ar
t
o
f
th
e
i
m
p
le
m
e
n
tatio
n
d
is
cu
s
s
es
ab
o
u
t
a
n
o
v
el
clas
s
i
f
ica
tio
n
ap
p
r
o
ac
h
th
at
o
f
f
er
s
s
i
g
n
i
f
ica
n
t
n
o
v
elt
y
o
v
er
eli
m
i
n
atio
n
o
f
u
n
w
an
ted
r
eg
i
o
n
s
th
at
h
in
d
er
s
t
h
e
class
i
f
ic
atio
n
o
f
th
e
b
r
ea
ts
ca
n
ce
r
.
An
o
v
el
b
io
-
i
n
s
p
ir
ed
alg
o
r
ith
m
i
s
i
m
p
le
m
e
n
ted
to
en
s
u
r
e
th
at
i
t
o
b
tain
s
b
o
th
lo
ca
l
an
d
g
lo
b
al
o
u
tco
m
e
f
o
r
en
s
u
r
in
g
h
i
g
h
l
y
co
r
r
ec
t
class
i
f
icatio
n
p
r
o
ce
s
s
.
T
h
e
o
u
tco
m
e
is
f
i
n
all
y
u
ti
lizi
n
g
r
u
le
-
s
et
s
y
s
te
m
in
o
r
d
er
to
p
er
f
o
r
m
u
s
er
-
f
r
ien
d
l
y
in
f
er
en
ce
o
f
t
h
e
cr
itcalit
y
o
f
ca
n
ce
r
in
t
h
e
f
o
r
m
o
f
b
en
i
g
n
a
n
d
m
ali
g
n
a
n
t s
tag
e.
RE
F
E
RE
NCES
[1
]
Kla
u
s
D
.
T
o
e
n
n
i
e
s
,
“
G
u
i
d
e
t
o
M
e
d
i
c
a
l
Im
a
g
e
A
n
a
ly
sis
:
M
e
t
h
o
d
s
a
n
d
A
lg
o
ri
t
h
m
s
,
”
S
p
ri
n
g
e
r
,
2
0
1
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
2
,
A
p
r
il 2
0
1
9
:
9
9
2
-
1
0
0
1
1000
[2
]
P
a
u
l
o
M
a
z
z
o
n
c
in
i
d
e
A
z
e
v
e
d
o
-
M
a
rq
u
e
s,
A
ria
n
n
a
M
e
n
c
a
tt
i
n
i
,
M
a
rc
e
ll
o
S
a
lm
e
ri
,
Ra
n
g
a
ra
j
M
.
Ra
n
g
a
y
y
a
n
,
“
M
e
d
ica
l
Im
a
g
e
A
n
a
ly
sis
a
n
d
I
n
f
o
rm
a
ti
c
s
:
Co
m
p
u
ter
-
A
i
d
e
d
D
iag
n
o
s
is
a
n
d
T
h
e
r
a
p
y
,
”
C
RC
Pre
ss
,
2
0
1
8
.
[3
]
Qia
n
g
L
i,
R
o
b
e
r
t
M
.
Ni
s
h
ik
a
w
a
,
“
Co
m
p
u
ter
-
A
i
d
e
d
De
te
c
t
i
o
n
a
n
d
D
iag
n
o
sis
i
n
M
e
d
ica
l
Im
a
g
i
n
g
,
”
T
a
y
l
o
r &
Fra
n
c
is
,
2015
.
[4
]
F
.
A
.
Ca
r
d
il
l
o
,
F
.
M
a
s
u
ll
i
a
n
d
S
.
R
o
v
e
tt
a
,
“
A
u
t
o
m
a
ti
c
A
p
p
r
o
a
c
h
e
s
f
o
r
CE
-
M
RI
Ex
a
m
i
n
a
ti
o
n
o
f
th
e
B
re
a
s
t:
A
S
u
rv
e
y
,
”
2
0
1
7
I
EE
E
I
n
te
rn
a
t
io
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
te
rn
e
t
o
f
T
h
i
n
g
s
(
i
T
h
i
n
g
s)
a
n
d
I
E
EE
Gr
e
e
n
Co
mp
u
t
in
g
a
n
d
Co
mm
u
n
ic
a
ti
o
n
s
(
Gr
e
e
n
C
o
m
)
a
n
d
IE
EE
Cy
b
e
r
,
P
h
y
s
ic
a
l
a
n
d
S
o
c
i
a
l
C
o
m
p
u
ti
n
g
(
C
P
S
C
o
m
)
a
n
d
I
E
EE
S
ma
rt
D
a
t
a
(
S
m
a
rt
Da
t
a
)
,
Ex
e
te
r,
2
0
1
7
,
p
p
.
1
4
7
-
154.
[5
]
M
.
S
.
I
s
lam
,
N.
Ka
a
b
o
u
c
h
a
n
d
W
.
C.
H
u
,
“
A
s
u
rv
e
y
o
f
m
e
d
ica
l
im
a
g
in
g
tec
h
n
i
q
u
e
s
u
se
d
f
o
r
b
re
a
s
t
c
a
n
c
e
r
d
e
te
c
t
i
o
n
,
”
IE
EE
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
E
lec
tr
o
-
I
n
f
o
r
ma
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
EI
T
2
0
1
3
,
Ra
p
i
d
C
i
ty
,
S
D,
2
0
1
3
,
p
p
.
1
-
5.
[6
]
K.
G
a
y
a
th
ri
a
n
d
P
.
Ra
a
ja
n
,
“
A
s
u
rv
e
y
o
f
b
re
a
s
t
c
a
n
c
e
r
d
e
tec
t
i
o
n
b
a
se
d
o
n
im
a
g
e
se
g
m
e
n
ta
ti
o
n
te
c
h
n
i
q
u
e
s,”
2
0
1
6
In
ter
n
a
ti
o
n
a
l
C
o
n
fe
re
n
c
e
o
n
C
o
mp
u
ti
n
g
T
e
c
h
n
o
l
o
g
ies
a
n
d
I
n
tel
l
i
g
e
n
t
D
a
t
a
E
n
g
i
n
e
e
ri
n
g
(
IC
CT
ID
E
'1
6
)
,
K
o
v
il
p
a
tt
i
,
2
0
1
6
,
p
p
.
1
-
5.
[7
]
F
.
F
.
T
i
n
g
a
n
d
K
.
S
.
S
im
,
“
S
e
lf
-
re
g
u
l
a
te
d
m
u
lt
il
a
y
e
r
p
e
rc
e
p
t
r
o
n
n
e
u
ra
l
n
e
tw
o
rk
f
o
r
b
re
a
s
t
c
a
n
c
e
r
c
la
ss
if
ica
t
i
o
n
,
”
2
0
1
7
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
R
o
b
o
ti
c
s,
A
u
t
o
m
a
ti
o
n
a
n
d
S
c
ie
n
c
e
s
(
IC
ORA
S
)
,
M
e
lak
a
,
2
0
1
7
,
p
p
.
1
-
5.
[8
]
T
.
Am
a
ra
l,
S
.
M
c
Ke
n
n
a
,
K
.
R
o
b
e
rts
o
n
a
n
d
A
.
T
h
o
m
p
s
o
n
,
“
Cla
ss
if
ica
t
i
o
n
o
f
b
re
a
s
t
-
t
iss
u
e
m
icr
o
a
rr
a
y
sp
o
t
s
u
s
i
n
g
c
o
l
o
u
r
a
n
d
l
o
c
a
l
i
n
v
a
ria
n
ts
,
”
2
0
0
8
5
t
h
IE
EE
I
n
ter
n
a
ti
o
n
a
l
S
y
m
p
o
s
iu
m o
n
B
i
o
me
d
ic
a
l
Im
a
g
i
n
g
:
Fr
o
m
Na
n
o
to
M
a
c
r
o
,
P
a
r
is
,
2
0
0
8
,
p
p
.
9
9
9
-
1
0
0
2
.
[9
]
S
h
a
h
n
a
z
,
J
.
H
o
ss
a
i
n
,
S
.
A
.
F
a
tt
a
h
,
S
.
G
h
o
sh
a
n
d
A
.
I
.
K
h
a
n
,
“
Ef
f
icie
n
t
a
p
p
r
o
a
c
h
e
s
f
o
r
a
c
c
u
ra
c
y
i
m
p
ro
v
e
m
e
n
t
o
f
b
re
a
st
c
a
n
c
e
r
c
la
ss
if
ic
a
t
i
o
n
u
s
i
n
g
w
isc
o
n
s
i
n
d
a
ta
b
a
se
,
”
2
0
1
7
I
EE
E
Re
g
i
o
n
1
0
H
u
m
a
n
i
t
a
ri
a
n
T
e
c
h
n
o
l
o
g
y
Co
n
f
e
re
n
c
e
(
R1
0
-
HT
C)
,
D
h
a
k
a
,
2
0
1
7
,
p
p
.
7
9
2
-
797.
[1
0
]
S
u
s
h
m
a
S
J
,
S
C
P
ra
s
a
n
n
a
K
u
m
a
r,
“
A
d
v
a
n
c
e
m
e
n
t
i
n
Re
se
a
rc
h
T
e
c
h
n
i
q
u
e
s
o
n
M
e
d
ica
l
Im
a
g
i
n
g
P
r
o
c
e
ss
i
n
g
f
o
r
B
re
a
s
t
Ca
n
c
e
r
De
tec
ti
o
n
”
,
I
n
ter
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
lec
tr
ic
a
l
a
n
d
C
o
m
p
u
t
e
r E
n
g
i
n
e
e
ri
n
g
(
IJ
E
CE
)
,
v
o
l.
6
,
n
o
.
2
,
A
p
r
i
l
2
0
1
6
,
p
p
.
7
1
7
-
724
.
[1
1
]
K.
S
.
B
e
e
v
i
,
M
.
S
.
N
a
i
r
a
n
d
G
.
R.
B
i
n
d
u
,
“
A
M
u
lt
i
-
Cla
ss
if
i
e
r
S
y
ste
m
f
o
r
A
u
t
o
m
a
t
ic
M
it
o
sis
De
te
c
ti
o
n
in
Bre
a
s
t
His
t
o
p
a
t
h
o
lo
g
y
Im
a
g
e
s
Us
in
g
De
e
p
Be
li
e
f
Ne
tw
o
rk
s
,
”
in
I
EE
E
J
o
u
r
n
a
l
o
f
T
r
a
n
s
l
a
t
i
o
n
a
l
E
n
g
i
n
e
e
r
i
n
g
i
n
He
a
l
t
h
a
n
d
M
e
d
i
c
i
n
e
,
v
o
l
.
5
,
p
p
.
1
-
1
1
,
2
0
1
7
.
[1
2
]
G
.
Ca
r
n
e
i
r
o
,
J
.
Na
sc
im
e
n
to
a
n
d
A
.
P
.
B
ra
d
ley
,
“
A
u
t
o
m
a
te
d
A
n
a
l
y
sis
o
f
Un
re
g
is
tere
d
M
u
l
ti
-
Vie
w
M
a
m
m
o
g
ra
m
s
W
it
h
De
e
p
L
e
a
r
n
i
n
g
,
”
in
I
EE
E
T
r
a
n
s
a
c
ti
o
n
s
o
n
M
e
d
ic
a
l
Im
a
g
i
n
g
,
v
o
l
.
3
6
,
n
o
.
1
1
,
p
p
.
2
3
5
5
-
2
3
6
5
,
N
o
v
.
2
0
1
7
.
[1
3
]
F
.
C
h
o
k
r
i
a
n
d
M
.
Ha
y
e
t
F
a
r
i
d
a
,
“
M
a
m
m
o
g
ra
p
h
ic
m
a
ss
c
las
sif
i
c
a
ti
o
n
a
c
c
o
r
d
i
n
g
t
o
B
i
-
RA
DS
l
e
x
ic
o
n
,
”
in
I
E
T
Co
mp
u
ter
Vi
s
i
o
n
,
v
o
l.
1
1
,
n
o
.
3
,
p
p
.
1
8
9
-
1
9
8
,
4
2
0
1
7
.
[1
4
]
S
.
D
u
r
a
isa
m
y
a
n
d
S
.
Em
p
e
r
u
m
a
l
,
“
Co
m
p
u
ter
-
a
i
d
e
d
m
a
m
m
o
g
ra
m
d
i
a
g
n
o
s
is
sy
ste
m
u
s
i
n
g
d
e
e
p
lea
r
n
i
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
f
u
l
ly
c
o
m
p
lex
-
v
a
l
u
e
d
re
lax
a
t
io
n
n
e
u
r
a
l
n
e
tw
o
rk
c
las
sif
ie
r,
”
in
I
E
T
C
o
m
p
u
te
r
Vi
s
i
o
n
,
v
o
l
.
1
1
,
n
o
.
8
,
p
p
.
6
5
6
-
6
6
2
,
1
2
2
0
1
7
.
[1
5
]
A
.
El
m
o
u
f
i
d
i
,
K
.
E
l
F
a
h
ss
i,
S
.
Ja
i
-
a
n
d
a
l
o
u
ss
i
,
A
.
S
e
k
k
a
k
i,
Q.
G
w
e
n
o
l
e
a
n
d
M
.
L
a
m
a
rd
,
“
A
n
o
m
a
ly
c
las
s
if
ica
ti
o
n
i
n
d
ig
i
tal
m
a
m
m
o
g
ra
p
h
y
b
a
se
d
o
n
m
u
lt
i
p
le
-
i
n
sta
n
c
e
le
a
r
n
in
g
,
”
in
I
E
T
Im
a
g
e
Pr
o
c
e
s
si
n
g
,
v
o
l.
1
2
,
n
o
.
3
,
p
p
.
3
2
0
-
3
2
8
,
3
2
0
1
8
.
[1
6
]
S
.
M
a
n
iv
a
n
n
a
n
,
C.
C
o
b
b
,
S
.
B
u
rg
e
ss
a
n
d
E
.
T
r
u
c
c
o
,
“
S
u
b
c
a
teg
o
ry
Clas
sif
ie
rs
f
o
r
M
u
lt
i
p
l
e
-
I
n
sta
n
c
e
L
e
a
rn
i
n
g
a
n
d
It
s
A
p
p
li
c
a
t
i
o
n
t
o
Re
t
in
a
l
N
e
rv
e
F
i
b
e
r
L
a
y
e
r
V
i
si
b
il
it
y
Cla
ss
if
ica
t
i
o
n
,
”
in
IE
EE
T
r
a
n
s
a
c
t
io
n
s
o
n
M
e
d
ic
a
l
Im
a
g
i
n
g
,
v
o
l
.
3
6
,
n
o
.
5
,
p
p
.
1
1
4
0
-
1
1
5
0
,
M
a
y
2
0
1
7
.
[1
7
]
M
e
rc
a
n
,
S
.
A
k
so
y
,
E
.
M
e
rc
a
n
,
L
.
G
.
S
h
a
p
i
r
o
,
D
.
L
.
W
e
a
v
e
r
a
n
d
J.
G
.
El
m
o
re
,
“
M
u
l
ti
-
I
n
s
ta
n
c
e
M
u
lt
i
-
L
a
b
e
l
L
e
a
r
n
i
n
g
f
o
r
M
u
l
t
i
-
C
las
s
C
las
sif
ica
t
io
n
o
f
W
h
o
l
e
S
l
i
d
e
Bre
a
st
Hi
st
o
p
a
t
h
o
l
o
g
y
Im
a
g
e
s,”
in
IE
EE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
M
e
d
ic
a
l
Im
a
g
i
n
g
,
v
o
l.
3
7
,
n
o
.
1
,
p
p
.
3
1
6
-
3
2
5
,
J
a
n
.
2
0
1
8
.
[1
8
]
N.
I.
Niz
a
m
,
S
.
K
.
A
lam
a
n
d
M
.
K.
Ha
sa
n
,
“
EE
M
D
D
o
m
a
in
A
R
S
p
e
c
t
ra
l
M
e
t
h
o
d
f
o
r
M
e
a
n
S
c
a
tt
e
re
r
S
p
a
c
i
n
g
Est
im
a
ti
o
n
o
f
B
re
a
s
t
T
u
m
o
rs
F
r
o
m
Ul
tras
o
u
n
d
Ba
c
k
sc
a
tt
e
re
d
R
F
Da
ta
,
”
in
I
EE
E
T
r
a
n
s
a
c
ti
o
n
s
o
n
U
lt
r
a
s
o
n
ic
s,
Fer
r
o
e
lec
tri
c
s,
a
n
d
Fre
q
u
e
n
c
y
C
o
n
t
r
o
l
,
v
o
l
.
6
4
,
n
o
.
1
0
,
p
p
.
1
4
8
7
-
1
5
0
0
,
O
c
t
.
2
0
1
7
.
[1
9
]
R.
Ra
b
i
d
a
s
,
J
.
C
h
a
k
ra
b
o
rty
a
n
d
A
.
M
i
d
y
a
,
“
A
n
a
ly
sis
o
f
2
D
si
n
g
u
la
ri
ti
e
s
f
o
r
m
a
m
m
o
g
ra
p
h
ic
m
a
ss
c
l
a
ss
if
i
c
a
t
io
n
,
”
in
IE
T
C
o
m
p
u
te
r
V
isi
o
n
,
v
o
l
.
1
1
,
n
o
.
1
,
p
p
.
2
2
-
3
2
,
2
2
0
1
7
.
[2
0
]
S
.
Re
i
s
e
t
a
l
.
,
“
A
u
t
o
m
a
te
d
C
las
s
if
ica
t
i
o
n
o
f
Bre
a
s
t
Ca
n
c
e
r
S
t
ro
m
a
M
a
t
u
ri
ty
f
ro
m
Hist
o
l
o
g
ica
l
Im
a
g
e
s,”
in
I
EE
E
T
r
a
n
s
a
c
ti
o
n
s
o
n
B
io
me
d
ic
a
l
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l.
6
4
,
n
o
.
1
0
,
p
p
.
2
3
4
4
-
2
3
5
2
,
Oc
t
.
2017.
[2
1
]
M
.
S
a
h
a
a
n
d
C
.
C
h
a
k
ra
b
o
rty
,
“
H
e
r2
Ne
t
:
A
De
e
p
F
ra
m
e
w
o
rk
f
o
r
S
e
m
a
n
ti
c
S
e
g
m
e
n
tat
i
o
n
a
n
d
Cla
ss
i
f
ica
ti
o
n
o
f
Ce
l
l
M
e
m
b
ra
n
e
s
a
n
d
N
u
c
l
e
i
i
n
Br
e
a
s
t
Ca
n
c
e
r
Ev
a
l
u
a
t
i
o
n
,
”
in
I
EE
E
T
r
a
n
s
a
c
ti
o
n
s
o
n
Im
a
g
e
Pr
o
c
e
ss
i
n
g
,
v
o
l
.
2
7
,
n
o
.
5
,
p
p
.
2
1
8
9
-
2
2
0
0
,
M
a
y
2
0
1
8
.
[2
2
]
Y.
S
o
n
g
,
Q.
L
i,
H
.
H
u
a
n
g
,
D
.
F
e
n
g
,
M
.
C
h
e
n
a
n
d
W
.
Ca
i
,
“
L
o
w
Dim
e
n
s
i
o
n
a
l
Re
p
re
se
n
tat
i
o
n
o
f
F
i
sh
e
r
V
e
c
t
o
rs
f
o
r
M
ic
r
o
sc
o
p
y
Im
a
g
e
Clas
sif
ica
t
io
n
,
”
in
I
EE
E
T
r
a
n
s
a
c
ti
o
n
s
o
n
M
e
d
i
c
a
l
Im
a
g
i
n
g
,
v
o
l.
3
6
,
n
o
.
8
,
p
p
.
1
6
3
6
-
1
6
4
9
,
A
u
g
.
2
0
1
7
.
[2
3
]
M
.
S
trac
k
x
,
E
.
D'
A
g
o
s
ti
n
o
,
P
.
L
e
r
o
u
x
a
n
d
P
.
Re
y
n
a
e
rt
,
“
D
ir
e
c
t
RF
S
u
b
sa
m
p
l
i
n
g
Re
c
e
iv
e
rs
E
n
a
b
li
n
g
Im
p
u
lse
-
Ba
s
e
d
UW
B
S
ig
n
a
l
s
f
o
r
B
re
a
s
t
Ca
n
c
e
r
De
tec
t
io
n
,
”
i
n
IE
EE
T
ra
n
sa
c
ti
o
n
s
o
n
Ci
rc
u
i
ts
a
n
d
S
y
ste
m
s
I
I:
Ex
p
re
ss
B
rief
s
,
v
o
l
.
6
2
,
n
o
.
2
,
p
p
.
1
4
4
-
1
4
8
,
F
e
b
.
2
0
1
5
.
[2
4
]
Z.
W
a
n
g
,
X.
X
i
a
o
,
H.
S
o
n
g
,
L
.
W
a
n
g
an
d
Q
.
L
i
,
“
De
v
e
l
o
p
m
e
n
t
o
f
A
n
a
to
m
ica
ll
y
Re
a
l
ist
ic
N
u
m
e
rica
l
Bre
a
st
P
h
a
n
t
o
m
s
Ba
se
d
o
n
T
1
-
a
n
d
T
2
-
W
e
ig
h
te
d
M
RIs
f
o
r
M
i
c
r
o
w
a
v
e
Bre
a
s
t
Ca
n
c
e
r
De
tec
ti
o
n
,
”
i
n
IE
E
E
A
n
te
n
n
a
s
a
n
d
W
ire
l
e
ss
P
ro
p
a
g
a
ti
o
n
L
e
t
ter
s
,
v
o
l
.
1
3
,
p
p
.
1
7
5
7
-
1
7
6
0
,
2
0
1
4
.
[2
5
]
X.
W
a
n
g
,
T
.
Q
i
n
,
R.
S
.
W
i
tt
e
a
n
d
H
.
Xi
n
,
“
C
o
m
p
u
tat
i
o
n
a
l
F
e
a
si
b
i
li
ty
S
t
u
d
y
o
f
C
o
n
t
ra
s
t
-
E
n
h
a
n
c
e
d
T
h
e
rm
o
a
c
o
u
s
t
ic
Im
a
g
in
g
f
o
r
Bre
a
st
Ca
n
c
e
r
De
t
e
c
ti
o
n
Us
in
g
Re
a
li
st
ic
N
u
m
e
ri
c
a
l
B
re
a
s
t
P
h
a
n
t
o
m
s,”
i
n
IE
EE
T
r
a
n
s
a
c
ti
o
n
s
o
n
M
icr
o
w
a
v
e
T
h
e
o
ry
a
n
d
T
e
c
h
n
i
q
u
e
s
,
v
o
l
.
6
3
,
n
o
.
5
,
p
p
.
1
4
8
9
-
1
5
0
1
,
M
a
y
2
0
1
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
A
n
o
ve
l a
p
p
r
o
a
c
h
to
jo
in
tly
a
d
d
r
ess
lo
ca
liz
a
tio
n
a
n
d
cla
s
s
ifica
tio
n
o
f
b
r
ea
s
t c
a
n
ce
r
u
s
in
g
…
(
S
u
s
h
ma
S
.
J
.
)
1001
[2
6
]
T
.
Yi
n
,
F
.
H
.
A
li
a
n
d
C
.
C
.
Re
y
e
s
-
A
ld
a
so
r
o
,
“
A
Ro
b
u
s
t
a
n
d
A
rti
f
a
c
t
Re
si
sta
n
t
A
lg
o
ri
t
h
m
o
f
Ultraw
i
d
e
b
a
n
d
Im
a
g
i
n
g
S
y
ste
m
f
o
r
Bre
a
s
t
Ca
n
c
e
r
De
t
e
c
ti
o
n
,
”
i
n
IE
E
E
T
r
a
n
s
a
c
t
io
n
s
o
n
B
i
o
me
d
ic
a
l
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
6
2
,
n
o
.
6
,
p
p
.
1
5
1
4
-
1
5
2
5
,
J
u
n
e
2
0
1
5
.
[2
7
]
M
.
D
.
H
o
s
sa
i
n
a
n
d
A
.
S
.
M
o
h
a
n
,
“
C
a
n
c
e
r
De
t
e
c
t
i
o
n
i
n
H
ig
h
ly
De
n
se
B
re
a
s
ts
Us
in
g
C
o
h
e
re
n
t
ly
F
o
c
u
se
d
T
im
e
-
Re
v
e
rsa
l
M
ic
r
o
w
a
v
e
Im
a
g
in
g
,
”
in
IE
EE
T
r
a
n
s
a
c
t
io
n
s
o
n
C
o
m
p
u
t
a
t
io
n
a
l
Im
a
g
i
n
g
,
v
o
l.
3
,
n
o
.
4
,
p
p
.
9
2
8
-
9
3
9
,
De
c
.
2
0
1
7
.
[2
8
]
M
.
Ja
l
il
v
a
n
d
,
X
.
L
i
,
L
.
Zw
ir
e
l
l
o
a
n
d
T
.
Zw
i
c
k
,
“
Ul
tra
w
i
d
e
b
a
n
d
c
o
m
p
a
c
t
n
e
a
r
-
f
iel
d
im
a
g
i
n
g
sy
st
e
m
fo
r
b
r
e
a
st
c
a
n
c
e
r
d
e
tec
t
i
o
n
,
”
in
I
ET
M
i
c
r
o
w
a
v
e
s
,
A
n
t
e
n
n
a
s &
Pr
o
p
a
g
a
t
io
n
,
v
o
l
.
9
,
n
o
.
1
0
,
p
p
.
1
0
0
9
-
1
0
1
4
,
7
1
6
2
0
1
5
.
[2
9
]
S
.
Kw
o
n
,
H.
L
e
e
a
n
d
S
.
L
e
e
,
“
Im
a
g
e
e
n
h
a
n
c
e
m
e
n
t
w
it
h
G
a
u
ss
i
a
n
f
il
ter
i
n
g
i
n
ti
m
e
-
d
o
m
a
i
n
m
icro
w
a
v
e
im
a
g
in
g
sy
st
e
m
f
o
r
b
re
a
s
t
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
,
”
in
E
lec
tr
o
n
ic
s
L
e
tt
e
rs
,
v
o
l.
5
2
,
n
o
.
5
,
p
p
.
3
4
2
-
3
4
4
,
3
3
2
0
1
6
.
[3
0
]
S
.
Be
u
ra
,
B
.
M
a
j
h
i
,
R
.
Da
s
h
a
n
d
S
.
R
o
y
,
“
C
las
s
if
ica
ti
o
n
o
f
m
a
m
m
o
g
ra
m
u
si
n
g
tw
o
-
d
im
e
n
s
i
o
n
a
l
d
isc
r
e
te
o
r
t
h
o
n
o
rm
a
l
S
-
tra
n
sf
o
rm
f
o
r
b
re
a
s
t
c
a
n
c
e
r
d
e
te
c
ti
o
n
,
”
in
He
a
lt
h
c
a
re
T
e
c
h
n
o
l
o
g
y
L
e
t
ter
s
,
v
o
l
.
2
,
n
o
.
2
,
p
p
.
4
6
-
5
1
,
4
2
0
1
5
.
[3
1
]
S
a
k
t
h
i,
S
.
S
iv
a
,
R.
K
.
S
a
n
t
h
i,
N
.
M
u
ra
li
Kr
is
h
n
a
n
,
S
.
G
a
n
e
sa
n
,
a
n
d
S
.
S
u
b
ra
m
a
n
ia
n
,
“
W
in
d
I
n
teg
ra
te
d
T
h
e
rm
a
l
U
n
i
t
Co
m
m
it
m
e
n
t
S
o
l
u
ti
o
n
Us
i
n
g
G
re
y
W
o
lf
Op
t
im
ize
r
,
”
I
n
ter
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
t
ric
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
(
IJ
EC
E)
7
,
n
o
.
5
(
2
0
1
7
)
:
2
3
0
9
-
2
3
2
0
.
[3
2
]
Ha
m
a
in
e
e
t
a
l
.
,
“D
e
m
o
n
st
ra
tes
t
h
e
p
r
o
p
o
se
d
m
e
t
h
o
d
p
re
c
ise
ly
d
if
f
e
re
n
t
iate
s
ta
n
d
a
r
d
b
ra
i
n
im
a
g
e
s
f
ro
m
th
e
i
rre
g
u
lar
o
n
e
s
a
n
d
b
e
n
ig
n
les
i
o
n
s
f
r
o
m
m
a
li
g
n
a
n
t
t
u
m
o
rs
”
.
[3
3
]
Ba
n
g
a
re
,
S
u
n
i
l
L
.
,
G
.
P
ra
d
e
e
p
in
i
,
a
n
d
S
h
r
is
h
a
il
a
p
p
a
T
a
ty
a
sa
h
e
b
P
a
ti
l
,
“
Ne
u
r
o
e
n
d
o
sc
o
p
y
Ad
a
p
ter
M
o
d
u
l
e
De
v
e
l
o
p
m
e
n
t
f
o
r
Be
tt
e
r
B
ra
i
n
T
u
m
o
r
Im
a
g
e
Vis
u
a
l
iza
ti
o
n
,
”
I
n
ter
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
lec
tri
c
a
l
a
n
d
C
o
m
p
u
ter
E
n
g
i
n
e
e
r
i
n
g
(
IJ
EC
E
)
7
,
n
o
.
6
(
2
0
1
7
)
:
3
6
4
3
-
3
6
5
4
.
[3
4
]
S
u
s
h
m
a
S
J
a
n
d
S
.
C
.
P
.
Ku
m
a
r
,
“
Im
a
g
e
En
h
a
n
c
e
m
e
n
t
u
s
i
n
g
Bi
o
-
in
s
p
i
re
d
A
lg
o
r
i
t
h
m
s
o
n
m
a
m
m
o
g
ra
m
f
o
r
c
a
n
c
e
r
d
e
tec
t
i
o
n
,
”
I
n
ter
n
a
t
i
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Eme
r
g
i
n
g
Re
se
a
rc
h
in
El
e
c
tr
o
n
ics
,
C
o
m
p
u
ter
S
c
ie
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
(
ICER
EC
T
)
,
M
a
n
d
y
a
,
2
0
1
5
,
p
p
.
1
1
-
16.
[3
5
]
S
.
J
.
S
u
s
h
m
a
,
S
.
C.
P
ra
sa
n
n
a
Ku
m
a
r,
“
M
u
lt
i
-
s
tag
e
O
p
ti
m
iza
ti
o
n
Ov
e
r
Ex
t
ra
c
t
e
d
F
e
a
t
u
re
f
o
r
De
tec
ti
o
n
a
n
d
C
las
sif
ica
t
io
n
o
f
B
re
a
s
t
Ca
n
c
e
r,
”
S
p
r
i
n
g
e
r
-
C
o
m
p
u
te
r
S
c
ie
n
c
e
O
n
-
l
i
n
e
C
o
n
fer
e
n
c
e
,
p
p
.
2
7
6
-
2
8
3
,
2
0
1
7
[3
6
]
“
DD
S
M
:
Dig
it
a
l
Da
ta
b
a
se
f
o
r
S
c
re
e
ri
n
g
M
a
m
m
o
g
ra
p
h
y
”
,
h
t
t
p
:/
/m
a
ra
t
h
o
n
.
c
se
e
.
u
s
f
.
e
d
u
/M
a
m
m
o
g
ra
p
h
y
/Da
ta
b
a
se
.
h
tm
l
,
Re
t
r
iev
e
d
o
n
1
9
th
A
p
r
il
2
0
1
8
[3
7
]
“
M
a
m
o
g
ra
p
h
ic
Im
a
g
e
A
n
a
ly
sis
H
o
m
e
p
a
g
e
”
,
h
t
t
p
:
//
w
w
w
.
m
a
m
m
o
im
a
g
e
.
o
rg
/
d
a
ta
b
a
se
s
/
,
Re
tr
iv
e
d
,
1
3
t
h
Ja
n
,
2
0
1
7
.
B
I
O
G
RA
P
H
I
E
S
O
F
AUT
H
O
R
S
S
u
sh
m
a
S
.
J
.
is
w
o
rk
in
g
a
s
A
s
so
c
iate
P
ro
f
e
ss
o
r,
De
p
a
rtm
e
n
t
o
f
ECE
,
G
S
S
S
I
n
stit
u
te
o
f
En
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
f
o
r
w
o
m
e
n
,
M
y
su
ru
.
S
h
e
h
a
s
g
o
t
1
4
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
S
h
e
h
a
s
o
b
tai
n
e
d
Ba
c
h
e
lo
r
o
f
En
g
in
e
e
rin
g
f
ro
m
M
a
n
g
lo
re
Un
iv
e
rsity
in
th
e
y
e
a
r
2
0
0
1
.
I
n
2
0
0
7
.
S
h
e
o
b
tain
e
d
M
a
ste
r
o
f
T
e
c
h
n
o
l
o
g
y
f
ro
m
V
isv
e
s
wa
ra
y
a
Tec
h
n
o
lo
g
ica
l
Un
iv
e
rsit
y
,
Be
lag
a
v
i.
Cu
rre
n
tl
y
p
u
rsu
in
g
P
h
.
D.
a
t
V
is
v
e
s
w
a
r
a
y
a
Tec
h
n
o
lo
g
ica
l
Un
iv
e
rsity
,
Be
l
a
g
a
v
i,
In
d
ia.
S
h
e
h
a
s
p
u
b
li
sh
e
d
1
3
p
a
p
e
rs
in
n
a
ti
o
n
a
l
c
o
n
f
e
re
n
c
e
s
7
in
in
tern
a
ti
o
n
a
l
c
o
n
f
e
r
e
n
c
e
a
n
d
4
in
in
tern
a
ti
o
n
a
l
jo
u
r
n
a
l.
He
r
a
re
a
o
f
in
tere
sts
in
c
lu
d
e
s
Im
a
g
e
P
ro
c
e
ss
in
g
,
Co
m
p
u
tatio
n
a
l
In
telli
g
e
n
c
e
a
n
d
Co
m
p
u
ter Ne
tw
o
rk
s.
Dr
Pra
s
a
n
n
a
K
u
m
a
r
S
.
C
.
is
wo
rk
in
g
a
s
P
ro
f
e
ss
o
r
a
n
d
He
a
d
,
De
p
a
rtme
n
t
o
f
In
stru
m
e
n
tatio
n
T
e
c
h
n
o
lo
g
y
,
RV
c
o
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
,
Ba
n
g
a
lo
re
.
He
h
a
s
g
o
t
1
8
y
e
a
rs
o
f
te
a
c
h
in
g
,
0
1
y
e
a
r
o
f
in
d
u
stry
a
n
d
1
0
y
e
a
rs
o
f
re
se
a
rc
h
e
x
p
e
rien
c
e
.
He
d
id
h
is
Ba
c
h
e
lo
r
o
f
En
g
in
e
e
rin
g
a
n
d
m
a
st
e
r
o
f
En
g
in
e
e
rin
g
f
ro
m
M
y
so
re
Un
iv
e
rsit
y
.
He
wa
s
a
w
a
rd
e
d
P
h
D
in
th
e
y
e
a
r
2
0
0
9
f
ro
m
Av
in
a
sh
li
n
g
h
a
m
Un
iv
e
r
sit
y
,
T
a
m
il
n
a
d
u
.
He
h
a
s
p
u
b
li
sh
e
d
o
v
e
r
1
4
p
a
p
e
rs
in
n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
c
o
n
f
e
re
n
c
e
s
a
n
d
a
r
o
u
n
d
2
4
p
a
p
e
rs
in
th
e
in
tern
a
ti
o
n
a
l
jo
u
r
n
a
ls.
He
h
a
s
r
e
c
e
i
v
e
d
a
c
a
d
e
m
ic e
x
c
e
ll
e
n
c
e
a
wa
rd
f
o
r
th
e
y
e
a
rs 2
0
0
8
a
n
d
2
0
0
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.