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.
15
,
No
.
4
,
A
u
g
u
s
t
20
25
,
p
p
.
4
3
3
2
~
4
3
4
0
I
SS
N:
2
0
8
8
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ec
e.
v
15
i
4
.
p
p
4
3
3
2
-
4
3
4
0
4332
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
An appro
a
ch f
o
r
predicti
ng
brain
t
u
m
o
r w
ith
m
a
chi
ne learning
techniqu
es
P
SRB
Sh
a
s
ha
n
k
1
,
L
.
Ana
nd
1
,
R.
P
it
cha
i
2
1
D
e
p
a
r
t
me
n
t
o
f
N
e
t
w
o
r
k
i
n
g
a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
s,
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
(
C
ET
)
,
S
R
M
I
n
st
i
t
u
t
e
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
K
a
t
t
a
n
k
u
l
a
t
h
u
r
,
T
a
mi
l
N
a
d
u
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
B
V
R
a
j
u
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
N
a
r
sap
u
r
,
M
e
d
a
k
,
T
e
l
a
n
g
a
n
a
,
I
n
d
i
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
2
0
,
2
0
2
4
R
ev
i
s
ed
Ma
r
2
9
,
2
0
2
5
A
cc
ep
ted
Ma
y
2
4
,
2
0
2
5
T
h
e
m
e
d
ica
l
in
d
u
stry
r
e
li
e
s
h
e
a
v
il
y
o
n
i
m
a
g
e
p
ro
c
e
ss
in
g
fo
r
tu
m
o
r
d
iag
n
o
sis.
M
e
d
ica
l
im
a
g
in
g
is
a
n
e
v
e
r
e
v
o
lv
in
g
a
n
d
i
n
tri
c
a
te
f
ield
.
Bra
i
n
tu
m
o
r
(BT
)
is e
x
tre
m
e
l
y
f
re
q
u
e
n
t
a
n
d
m
a
y
c
a
u
se
d
e
a
th
.
A
B
T
d
e
v
e
l
o
p
s w
h
e
n
b
ra
in
c
e
ll
s
d
iv
id
e
a
n
d
g
ro
w
o
u
t
o
f
c
o
n
tro
l.
T
h
e
p
ro
g
n
o
sis
f
o
r
p
e
o
p
l
e
w
it
h
B
T
c
a
n
b
e
g
re
a
tl
y
i
m
p
ro
v
e
d
a
n
d
th
e
su
rv
iv
a
l
ra
te c
a
n
b
e
in
c
re
a
se
d
if
th
e
tu
m
o
r
is
d
e
tec
ted
e
a
rl
y
.
A
sin
g
le
in
d
iv
i
d
u
a
l'
s
b
ra
in
m
a
g
n
e
ti
c
re
so
n
a
n
c
e
ima
g
in
g
(M
RI)
sc
a
n
c
o
m
p
rise
s
m
u
lt
ip
le
slice
s
th
ro
u
g
h
t
h
e
3
D
a
n
a
to
m
ica
l
p
e
rsp
e
c
ti
v
e
.
A
s
a
re
su
lt
,
e
x
trac
ti
n
g
tu
m
o
r
f
ro
m
M
RI
sc
a
n
s
is
a
d
if
f
icu
lt
a
n
d
ti
m
e
-
c
o
n
su
m
in
g
lab
o
rio
u
s
tas
k
.
Be
c
a
u
se
o
f
th
e
risk
s
a
ss
o
c
iate
d
w
it
h
b
io
p
sie
s,
a
n
M
RI
-
b
a
se
d
a
u
t
o
m
a
t
e
d
BT
c
a
teg
o
riza
ti
o
n
is
a
sa
f
e
r
a
lt
e
rn
a
ti
v
e
.
T
h
e
sc
ien
ti
f
ic
p
ro
f
e
ss
io
n
h
a
s
w
o
rk
e
d
ti
re
les
sly
f
ro
m
th
e
b
e
g
in
n
in
g
o
f
th
e
m
il
len
n
iu
m
to
d
e
v
e
lo
p
a
n
a
u
to
m
a
ti
c
BT
se
g
m
e
n
tatio
n
a
n
d
c
la
ss
if
ic
a
ti
o
n
s
y
ste
m
.
T
h
e
re
f
o
re
,
th
e
re
is
a
larg
e
b
o
d
y
o
f
w
o
rk
in
th
e
f
ield
d
e
d
ic
a
ted
to
th
e
stu
d
y
o
f
B
T
re
s
e
a
rc
h
th
ro
u
g
h
m
a
c
h
in
e
lea
rn
in
g
(M
L
)
tec
h
n
i
q
u
e
s.
T
h
e
re
v
i
e
w
p
a
p
e
r
su
m
m
a
rize
s
th
e
p
u
b
li
c
ly
a
c
c
e
ss
ib
le
b
e
n
c
h
m
a
rk
d
a
tas
e
ts
t
y
p
ica
ll
y
u
se
d
a
n
d
c
o
m
p
a
re
s
v
a
rio
u
s
p
r
o
c
e
ss
in
g
a
p
p
r
o
a
c
h
e
s,
f
e
a
tu
re
e
x
trac
ti
o
n
(F
E)
,
se
g
m
e
n
tatio
n
,
a
n
d
c
las
sif
ica
ti
o
n
a
lg
o
rit
h
m
s
f
o
r
BT
.
T
h
e
re
p
o
rt
a
ls
o
e
m
p
h
a
siz
e
s
th
e
c
h
a
ll
e
n
g
e
s
o
f
BT
d
e
tec
ti
o
n
.
Ou
r
h
o
p
e
is
t
h
a
t
th
is
s
u
rv
e
y
w
il
l
p
ro
v
id
e
re
se
a
rc
h
e
rs,
c
li
n
icia
n
s,
a
n
d
o
th
e
r
in
tere
ste
d
p
a
rti
e
s
w
il
l
g
a
in
a
n
in
-
d
e
p
th
u
n
d
e
rsta
n
d
in
g
o
f
BT
se
g
m
e
n
tatio
n
a
n
d
c
las
sif
ica
ti
o
n
u
sin
g
M
L
.
K
ey
w
o
r
d
s
:
B
r
ain
tu
m
o
r
clas
s
i
f
icatio
n
Ma
ch
i
n
e
lear
n
i
n
g
Ma
g
n
e
tic
r
eso
n
a
n
ce
i
m
ag
i
n
g
Me
d
ical
i
m
a
g
e
p
r
o
ce
s
s
in
g
T
u
m
o
r
s
e
g
m
en
ta
tio
n
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
L
.
A
n
a
n
d
Dep
ar
t
m
en
t o
f
Net
w
o
r
k
i
n
g
an
d
C
o
m
m
u
n
icatio
n
s
,
C
o
lle
g
e
o
f
E
n
g
i
n
ee
r
in
g
a
n
d
T
ec
h
n
o
lo
g
y
(
C
E
T
)
,
SR
M
I
n
s
tit
u
te
o
f
Scien
ce
a
n
d
T
ec
h
n
o
lo
g
y
C
h
e
n
n
ai,
I
n
d
ia
E
m
ail: a
n
an
d
.
l
@
s
r
m
is
t.e
d
u
.
in
1.
I
NT
RO
D
UCT
I
O
N
B
r
ain
tu
m
o
r
(
B
T
)
ar
e
m
ass
e
s
o
f
m
u
ta
ted
ce
lls
th
at
g
r
o
w
i
n
th
e
b
r
ain
'
s
ti
s
s
u
es.
B
T
ca
n
b
e
eith
er
b
en
ig
n
o
r
m
ali
g
n
a
n
t.
E
v
en
i
n
th
e
ab
s
en
ce
o
f
ad
d
itio
n
al
s
y
m
p
to
m
s
[
1
]
,
[
2
]
,
m
ali
g
n
an
t
B
T
s
ar
e
am
o
n
g
t
h
e
d
ea
d
lies
t
t
y
p
es
o
f
ca
n
ce
r
.
On
th
e
o
th
er
h
a
n
d
,
b
en
ig
n
B
T
s
ar
e
cu
r
ab
le
th
r
o
u
g
h
s
u
r
g
ical
r
e
m
o
v
al.
B
T
s
ca
n
b
e
class
i
f
ied
as
ei
th
er
p
r
i
m
ar
y
o
r
m
etas
tatic.
O
v
er
8
0
%
o
f
m
ali
g
n
a
n
t
B
T
s
in
ad
u
lts
ar
e
g
lio
m
as,
w
h
ic
h
o
r
ig
i
n
at
e
in
p
er
ig
lial
tis
s
u
e,
f
o
llo
w
ed
b
y
p
r
i
m
ar
y
ce
n
tr
al
n
er
v
o
u
s
s
y
s
te
m
(
C
N
S)
l
y
m
p
h
o
m
as.
A
cc
o
r
d
in
g
to
esti
m
ate
s
f
r
o
m
th
e
Glo
b
al
C
an
ce
r
Statis
tics
2
0
2
0
[
3
]
,
th
er
e
w
ill
b
e
ar
o
u
n
d
1
.
6
%
an
d
2
.
5
%
o
f
n
e
w
ca
s
es
an
d
d
ea
th
s
.
I
f
B
T
s
ar
e
f
o
u
n
d
at
a
n
ea
r
l
y
s
ta
g
e,
t
h
e
y
ca
n
b
e
e
f
f
ec
ti
v
el
y
tr
ea
ted
.
Ma
g
n
et
ic
r
eso
n
a
n
ce
i
m
ag
in
g
(
M
R
I
)
is
t
h
e
g
o
ld
s
tan
d
ar
d
b
ec
au
s
e
it
p
r
o
v
i
d
es
h
i
g
h
-
q
u
a
lit
y
i
m
ag
e
s
o
f
b
o
th
h
ea
lt
h
y
a
n
d
d
i
s
ea
s
e
d
t
is
s
u
es
i
n
a
s
h
o
r
t
am
o
u
n
t
o
f
t
im
e
[
4
]
.
S
l
i
ce
th
i
ck
n
es
s
,
im
a
g
e
q
u
a
li
ty
,
an
d
in
t
e
r
-
s
l
i
c
e
g
a
p
a
r
e
a
l
l
af
f
e
ct
e
d
b
y
th
e
m
ag
n
et
ic
f
ie
l
d
s
t
r
e
n
g
t
h
a
n
d
s
am
p
l
in
g
m
e
th
o
d
s
[
5
]
.
I
n
o
r
d
e
r
t
o
c
r
e
a
t
e
an
im
ag
e
,
th
e
s
c
an
n
e
r
'
s
b
u
i
l
t
-
in
r
a
d
i
o
an
t
en
n
a
m
u
s
t
f
i
r
s
t
t
ak
e
u
p
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
A
n
a
p
p
r
o
a
ch
f
o
r
p
r
ed
ictin
g
b
r
a
in
tu
mo
r
w
ith
ma
ch
in
e
lea
r
n
in
g
tech
n
iq
u
es (
P
S
R
B
S
h
a
s
h
a
n
k)
4333
s
in
u
s
o
i
d
al
s
ig
n
al
[
6
]
.
B
T
a
r
e
c
l
a
s
s
if
i
e
d
in
t
o
v
a
r
i
o
u
s
c
a
t
eg
o
r
i
es
f
r
o
m
s
l
o
w
g
r
o
w
in
g
t
o
t
h
e
m
o
s
t
d
an
g
e
r
o
u
s
tu
m
o
r
ty
p
es
[
7
]
,
[
8
]
.
T
h
e
s
a
m
p
le
M
R
I
f
r
o
m
ea
ch
ca
teg
o
r
y
o
f
B
T
is
g
iv
e
n
i
n
Fig
u
r
e
1
.
T
h
e
f
ir
s
t
r
o
w
r
ep
r
esen
t
s
t
h
e
g
lio
m
a
t
y
p
e,
th
e
s
ec
o
n
d
s
h
o
w
s
t
h
e
m
e
n
i
n
g
io
m
a,
th
e
t
h
ir
d
g
iv
es
t
h
e
p
itu
itar
y
,
an
d
t
h
e
f
o
u
r
th
r
o
w
i
s
an
ex
a
m
p
le
o
f
a
h
ea
lth
y
b
r
ain
.
T
h
e
au
to
m
atic
s
e
g
m
en
ta
tio
n
an
d
class
if
ica
tio
n
o
f
B
T
u
s
in
g
MRI
p
la
y
s
a
v
ital
r
o
l
e
in
t
h
e
f
ield
o
f
m
ed
ici
n
e.
T
h
e
s
u
r
v
e
y
ai
m
s
to
g
iv
e
a
d
et
ailed
d
escr
ip
tio
n
o
f
t
h
e
s
tep
s
in
v
o
l
v
ed
in
B
T
class
i
f
icatio
n
an
d
s
eg
m
e
n
tatio
n
.
T
h
e
s
u
r
v
e
y
’
s
f
ir
s
t
ch
ap
ter
g
iv
e
s
an
i
n
tr
o
d
u
ctio
n
to
B
T
a
n
d
its
t
y
p
es,
s
ec
o
n
d
ch
ap
ter
in
v
o
lv
es t
h
e
m
et
h
o
d
o
lo
g
y
o
f
B
T
id
en
tif
icatio
n
w
it
h
t
h
e
h
elp
o
f
a
f
lo
w
ch
ar
t
.
Fi
g
u
r
e
1
.
B
T
t
y
p
es
T
h
e
th
ir
d
ch
ap
ter
co
n
ce
n
tr
ates
o
n
th
e
av
ailab
le
p
u
b
lic
B
T
d
atab
ase,
th
e
f
o
u
r
t
h
ch
ap
ter
d
is
cu
s
s
es
t
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
s
tep
s
in
v
o
l
v
ed
in
clea
n
i
n
g
t
h
e
b
r
ain
MRI,
th
e
f
i
f
t
h
ch
ap
ter
s
h
o
w
s
t
h
e
s
e
g
m
e
n
tat
io
n
m
e
th
o
d
s
an
d
its
t
y
p
e
s
,
th
e
s
i
x
t
h
ch
ap
t
er
d
ef
in
es
t
h
e
av
a
ilab
le
f
ea
t
u
r
es
ex
tr
ac
tio
n
tec
h
n
iq
u
es
b
ased
o
n
co
lo
r
,
an
d
s
h
ap
e,
ch
ap
ter
s
ev
e
n
cla
s
s
i
f
ies
th
e
ML
m
o
d
els
i
n
to
th
r
ee
ca
te
g
o
r
ies
an
d
p
r
esen
t
s
t
h
e
av
ai
lab
le
alg
o
r
ith
m
s
in
ea
c
h
ca
teg
o
r
y
,
ch
ap
ter
ei
g
h
t
d
elib
er
ates
th
e
c
h
alle
n
g
e
s
i
n
B
T
cla
s
s
i
f
ic
atio
n
an
d
s
e
g
m
en
tatio
n
,
f
i
n
all
y
ch
ap
ter
n
in
e
co
n
clu
d
es t
h
e
s
u
r
v
e
y
.
2.
M
E
T
H
O
D
T
h
e
r
e
s
e
a
r
ch
o
n
B
T
c
l
a
s
s
if
i
c
a
tio
n
an
d
s
eg
m
en
ta
t
i
o
n
in
v
o
lv
es
th
e
f
o
l
l
o
w
in
g
s
te
p
s
as
s
h
o
w
n
i
n
F
ig
u
r
e
2
:
a.
Data
co
llectio
n
: M
a
n
y
d
ata
co
r
r
esp
o
n
d
in
g
to
v
ar
io
u
s
B
T
ty
p
es a
r
e
av
ailab
le
f
o
r
o
p
en
ac
ce
s
s
.
b.
I
m
ag
e
p
r
o
ce
s
s
i
n
g
: Ra
w
M
R
I
i
m
ag
e
s
r
eq
u
ir
e
p
r
e
-
p
r
o
ce
s
s
in
g
f
o
r
o
p
tim
izin
g
M
L
m
o
d
el
p
er
f
o
r
m
a
n
ce
c.
Seg
m
en
tatio
n
: T
o
lo
ca
lize
th
e
tu
m
o
r
r
eg
io
n
f
r
o
m
th
e
M
R
I
b
r
ain
i
m
ag
e
s
,
s
eg
m
e
n
tatio
n
is
e
m
p
lo
y
ed
.
d.
F
ea
tu
r
e
ex
tr
ac
tio
n
:
T
o
r
etr
iev
e
th
e
i
m
p
o
r
tan
t
f
ea
t
u
r
es
f
r
o
m
t
h
e
MRI
an
d
r
ed
u
ce
th
e
d
i
m
e
n
s
io
n
o
f
th
e
in
p
u
t.
e.
C
las
s
i
f
icatio
n
: T
h
e
b
in
ar
y
,
a
s
w
ell
a
s
m
u
lt
ip
le
B
T
class
if
icat
io
n
,
is
m
ad
e
u
s
i
n
g
t
h
e
M
L
m
o
d
el.
Fig
u
r
e
2
.
B
T
s
eg
m
e
n
tatio
n
a
n
d
class
if
icatio
n
r
esear
c
h
f
lo
w
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.
15
,
No
.
4
,
A
u
g
u
s
t
20
25
:
4
3
3
2
-
4340
4334
2
.
1
.
Da
t
a
a
cquis
it
io
n
Mo
s
t
B
T
d
etec
tio
n
s
tu
d
ie
s
h
av
e
m
ad
e
u
s
e
o
f
m
ed
ical
i
m
ag
e
co
m
p
u
ti
n
g
a
n
d
co
m
p
u
ter
-
as
s
is
ted
in
ter
v
e
n
tio
n
(
MI
C
C
A
I
)
d
atas
et
co
llectio
n
s
to
ev
al
u
ate
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
eir
in
ten
d
e
d
ap
p
r
o
ac
h
es.
Su
ch
d
atasets
ar
e
w
ell
k
n
o
w
n
f
o
r
th
eir
s
ta
n
d
ar
d
izatio
n
an
d
cli
n
ical
r
elev
an
ce
,
w
h
ic
h
r
en
d
er
s
th
e
m
s
u
itab
le
f
o
r
b
en
ch
m
ar
k
i
n
g
m
ac
h
i
n
e
lear
n
i
n
g
m
o
d
els.
Ot
h
er
d
atasets
u
t
i
lized
in
th
e
s
e
s
t
u
d
ies
ar
e
d
is
cu
s
s
ed
in
T
ab
le
1
,
p
r
o
v
id
in
g
a
m
o
r
e
co
m
p
r
eh
e
n
s
i
v
e
o
v
er
v
ie
w
o
f
d
ata
d
iv
er
s
it
y
an
d
u
s
e
f
u
l
n
ess
.
T
ab
le
1
.
A
n
o
v
er
v
ie
w
o
f
o
p
en
l
y
ac
ce
s
s
ib
le
b
r
ain
t
u
m
o
r
MRI
d
atasets
f
o
r
s
e
g
m
en
ta
tio
n
a
n
d
class
i
f
icatio
n
D
a
t
a
se
t
C
r
o
p
R
e
f
e
r
e
n
c
e
B
r
a
T
S
2
0
2
1
8
0
0
0
M
R
I
[
9
]
B
r
a
T
S
2
0
2
0
2
6
4
0
M
R
I
[
1
0
]
B
r
a
T
S
2
0
1
9
3
3
5
M
R
I
[
1
1
]
B
r
a
T
S
2
0
1
8
3
5
1
M
R
I
[
1
2
]
B
r
a
T
S
2
0
1
7
2
8
5
M
R
I
w
i
t
h
BT
mas
k
s
[
1
3
]
B
r
a
T
S
2
0
1
6
4
6
5
M
R
I
[
1
4
]
B
r
a
T
S
2
0
1
5
2
7
4
M
R
I
[
1
5
]
B
r
a
T
S
2
0
1
4
2
1
6
M
R
I
[
1
6
]
B
r
a
T
S
2
0
1
3
3
0
M
R
I
,
5
0
s
i
mu
l
a
t
e
d
i
mag
e
s
[
1
7
]
B
r
a
T
S
2
0
1
2
3
0
M
R
I
,
5
0
s
i
mu
l
a
t
e
d
i
mag
e
s
[
1
8
]
R
a
d
i
o
p
e
d
i
a
1
2
1
M
R
I
[
1
9
]
T
C
I
A
3
9
2
9
M
R
I
[
2
0
]
CE
-
M
R
I
d
a
t
a
se
t
3
0
6
4
M
R
I
[
2
1
]
B
r
3
5
H
3
0
0
0
M
R
I
[
2
2
]
H
a
r
v
a
r
d
1
0
0
M
R
I
[
2
3
]
M
S
D
4
8
4
m
u
l
t
i
-
mo
d
a
l
M
R
I
[
2
4
]
B
r
a
i
n
M
R
I
i
mag
es
2
5
3
M
R
I
[
2
5
]
3.
I
M
AG
E
P
RO
CE
SS
I
NG
MRI
i
m
ag
e
co
n
ta
m
i
n
atio
n
ca
n
o
cc
u
r
,
p
ar
ticu
lar
l
y
w
i
th
o
ld
er
MRI
m
ac
h
i
n
es,
d
u
e
to
lo
w
-
f
r
eq
u
en
c
y
,
h
ig
h
l
y
s
m
o
o
th
b
ias
f
ield
s
i
g
n
al
s
.
T
h
e
r
a
w
g
r
e
y
i
m
a
g
e
p
ix
els
ar
e
n
o
t
u
s
ef
u
l
f
o
r
s
e
g
m
e
n
tat
io
n
,
f
ea
tu
r
e
ex
tr
ac
tio
n
,
o
r
clas
s
i
f
icatio
n
.
T
h
ese
m
et
h
o
d
s
ca
n
n
o
t
b
e
ap
p
li
ed
d
ir
ec
tly
to
d
a
m
ag
ed
M
R
I
i
m
a
g
es
w
it
h
o
u
t
u
n
d
er
g
o
i
n
g
p
r
e
-
p
r
o
ce
s
s
in
g
to
r
em
o
v
e
u
n
w
a
n
ted
in
f
o
r
m
ati
o
n
.
T
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
s
tep
s
in
v
o
l
v
ed
in
M
R
I
i
m
a
g
es a
r
e
d
etailed
:
a.
R
esize:
T
o
en
s
u
r
e
u
n
i
f
o
r
m
i
t
y
d
u
r
in
g
tr
ai
n
i
n
g
,
all
i
m
a
g
es
i
n
th
e
M
R
I
d
atasets
h
av
e
h
ad
th
eir
o
r
ig
in
a
l
w
id
t
h
,
h
ei
g
h
t,
an
d
d
i
m
e
n
s
io
n
s
r
ed
u
ce
d
to
×
p
ix
els.
A
lar
g
er
i
n
p
u
t
i
m
a
g
e
d
o
u
b
les
th
e
tr
ai
n
i
n
g
ti
m
e
f
o
r
th
e
ar
ch
itect
u
r
e
s
i
n
ce
t
h
e
ML
m
u
s
t le
ar
n
f
r
o
m
f
o
u
r
ti
m
es a
s
m
an
y
p
ix
e
ls
[
2
6
]
.
b.
Sk
u
ll
s
tr
ip
p
in
g
:
C
o
m
p
u
ter
-
a
s
s
is
ted
ap
p
r
o
ac
h
es
h
a
v
e
tr
o
u
b
le
d
etec
tin
g
b
r
ain
tis
s
u
e
in
s
tr
u
c
tu
r
al
M
R
I
s
d
u
e
to
th
e
p
r
esen
ce
o
f
th
e
s
k
u
ll,
w
h
ic
h
ca
n
b
e
p
ar
ticu
lar
l
y
p
r
o
b
le
m
atic
f
o
r
p
atien
t
s
w
ith
B
T
s
[
2
7
]
.
I
t
h
elp
s
s
tan
d
ar
d
ize
g
r
ad
i
n
g
b
y
d
o
in
g
a
w
a
y
w
it
h
ti
m
e
-
co
n
s
u
m
i
n
g
m
an
u
al
p
r
o
ce
s
s
in
g
ac
t
iv
i
ties
an
d
s
u
b
j
ec
tiv
e
h
u
m
a
n
ass
e
s
s
m
e
n
t,
b
o
th
o
f
w
h
ich
ca
n
g
et
in
t
h
e
w
a
y
o
f
an
al
y
zi
n
g
a
n
d
r
ep
licatin
g
lar
g
e
-
s
ca
le
in
v
e
s
ti
g
atio
n
s
[
2
8
]
.
T
h
ese
m
e
th
o
d
s
ca
n
b
e
b
r
o
k
en
d
o
w
n
i
n
t
o
f
o
u
r
b
r
o
ad
ca
teg
o
r
ies,
i
n
cl
u
d
in
g
th
o
s
e
th
a
t
f
o
cu
s
o
n
m
o
r
p
h
o
lo
g
y
,
in
ten
s
it
y
,
d
ef
o
r
m
ab
le
s
u
r
f
ac
e
s
,
an
d
atl
ases
[
2
9
]
.
c.
Gr
e
y
s
ca
le
c
o
n
v
er
s
i
o
n
:
T
h
e
am
o
u
n
t
o
f
li
g
h
t
r
ec
eiv
ed
b
y
ea
ch
p
ix
el
in
a
g
r
a
y
s
ca
le
i
m
a
g
e
is
r
ep
r
esen
ted
n
u
m
er
icall
y
an
d
s
to
r
ed
as
a
b
y
te
o
r
w
o
r
d
[
3
0
]
.
T
h
e
r
an
g
e
o
f
g
r
a
y
s
ca
le
v
alu
e
s
i
n
an
8
-
b
it
i
m
a
g
e
is
f
r
o
m
0
(
b
lack
)
to
2
5
5
(
co
m
p
letel
y
w
h
ite)
.
d.
No
is
e
r
e
m
o
v
al
:
A
p
p
l
y
i
n
g
a
h
i
g
h
p
as
s
f
ilter
to
an
i
m
a
g
e
h
a
s
b
ee
n
s
h
o
w
n
to
in
cr
ea
s
e
ac
cu
r
a
c
y
an
d
d
ec
r
ea
s
e
n
o
is
e
[
3
1
]
.
Me
d
ian
f
ilter
s
p
r
o
v
id
e
m
o
r
e
n
o
is
e
r
ed
u
ctio
n
th
a
n
s
i
m
ilar
l
y
s
ized
li
n
ea
r
s
m
o
o
th
in
g
f
ilter
s
f
o
r
s
o
m
e
k
in
d
s
o
f
r
an
d
o
m
n
o
is
e
wh
ile
b
lu
r
r
i
n
g
f
ar
less
.
e.
T
h
r
esh
o
ld
in
g
:
Usi
n
g
th
r
e
s
h
o
l
d
in
g
,
o
b
j
ec
ts
ca
n
b
e
ex
tr
ac
ted
f
r
o
m
t
h
eir
b
ac
k
g
r
o
u
n
d
s
a
t
a
ch
o
s
en
th
r
es
h
o
ld
v
alu
e
T
.
P
o
in
ts
th
at
r
ep
r
esen
t
o
b
j
ec
ts
in
th
e
i
m
a
g
e
h
a
v
e
co
o
r
d
in
ates
(
x
,
y
)
s
u
c
h
t
h
at
f
(
x
,
y
)
>T
,
w
h
ile
p
o
i
n
t
s
th
at
r
ep
r
esen
t
th
e
b
ac
k
d
r
o
p
d
o
n
o
t.
I
f
T
is
a
f
u
n
ctio
n
o
f
X
an
d
Y,
w
e
s
a
y
t
h
at
w
e
ar
e
en
g
a
g
in
g
i
n
d
y
n
a
m
i
c
o
r
ad
ap
tiv
e
th
r
esh
o
ld
in
g
[
3
2
]
.
f.
Mo
r
p
h
o
lo
g
ical
f
u
n
ctio
n
s
:
Mo
r
p
h
o
l
o
g
y
is
a
m
eth
o
d
f
o
r
s
t
u
d
y
in
g
s
h
ap
es
a
n
d
s
tr
u
ct
u
r
es
i
n
i
m
a
g
es
[
3
3
]
.
I
n
m
at
h
e
m
a
tical
m
o
r
p
h
o
lo
g
y
,
t
h
e
r
e
ar
e
f
o
u
r
p
r
im
ar
y
p
r
o
ce
d
u
r
es
:
er
o
s
io
n
,
d
ilatio
n
,
clo
s
in
g
,
an
d
o
p
en
in
g
.
T
h
e
ter
m
"
d
ilatio
n
"
r
ef
er
s
to
th
e
lar
g
es
t p
o
s
s
ib
le
v
al
u
e
w
it
h
i
n
th
e
w
i
n
d
o
w
.
I
n
v
er
ted
d
ilatio
n
i
s
er
o
s
io
n
.
Dilatio
n
a
n
d
er
o
s
io
n
cr
ea
te
b
o
th
th
e
o
p
en
i
n
g
an
d
clo
s
in
g
p
ar
am
eter
s
.
D
u
r
in
g
t
h
e
o
p
en
in
g
p
r
o
ce
s
s
,
t
h
e
i
m
a
g
e
w
il
l b
e
r
ed
u
ce
d
in
s
i
ze
b
ef
o
r
e
b
ein
g
m
a
g
n
i
f
ied
.
g.
Au
g
m
e
n
tatio
n
:
A
t
th
is
p
o
in
t,
d
ata
au
g
m
en
ta
tio
n
is
e
m
p
lo
y
e
d
to
im
p
r
o
v
e
th
e
q
u
a
n
tit
y
o
f
d
ata
ac
ce
s
s
ib
le
b
y
ch
an
g
i
n
g
t
h
e
o
r
ig
i
n
al
i
m
a
g
e,
as M
L
n
ee
d
s
a
s
i
g
n
if
ican
t a
m
o
u
n
t o
f
d
ata
to
tr
ain
[
3
4
]
,
[
3
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:
2088
-
8708
A
n
a
p
p
r
o
a
ch
f
o
r
p
r
ed
ictin
g
b
r
a
in
tu
mo
r
w
ith
ma
ch
in
e
lea
r
n
in
g
tech
n
iq
u
es (
P
S
R
B
S
h
a
s
h
a
n
k)
4335
3
.
1
.
I
m
a
g
e
s
eg
m
e
nta
t
io
n
T
h
e
tu
m
o
r
s
tr
u
ct
u
r
e
o
r
r
eg
io
n
o
f
in
ter
e
s
t
m
u
s
t
b
e
ac
cu
r
atel
y
d
elin
ea
ted
o
r
s
e
g
m
en
ted
i
n
th
e
i
m
ag
e
s
f
o
r
p
r
ec
is
e
q
u
an
ti
tati
v
e
an
al
y
s
is
o
f
r
e
g
io
n
al
p
h
y
s
io
lo
g
y
.
W
o
n
g
[
3
6
]
ar
g
u
es
t
h
at
s
e
g
m
en
tatio
n
s
er
v
e
s
t
h
r
ee
m
ai
n
p
u
r
p
o
s
es:
a
)
allo
w
in
g
q
u
an
ti
f
icat
io
n
,
b
)
s
h
r
in
k
i
n
g
t
h
e
d
ataset
s
o
t
h
at
q
u
a
n
tita
ti
v
e
a
n
al
y
s
is
ca
n
b
e
f
o
cu
s
ed
o
n
t
h
e
ex
tr
ac
tio
n
o
f
in
ter
ested
r
eg
io
n
s
,
a
n
d
c
)
estab
lis
h
in
g
s
tr
u
ct
u
r
al
c
o
n
n
ec
tio
n
s
f
o
r
th
e
p
h
y
s
io
lo
g
ical
d
ata
in
s
id
e
th
e
r
eg
io
n
s
.
Var
io
u
s
au
t
h
o
r
s
[
3
7
]
–
[
3
9
]
class
if
y
s
eg
m
e
n
tatio
n
tech
n
iq
u
es
i
n
to
f
o
u
r
b
r
o
ad
ca
teg
o
r
ies;
th
o
s
e
ca
teg
o
r
ies ar
e
ex
p
lain
ed
in
d
etail
b
el
o
w
.
a.
T
h
r
esh
o
ld
:
T
h
e
th
r
esh
o
ld
is
a
b
asic
y
e
t
ef
f
ec
ti
v
e
m
et
h
o
d
o
f
r
eg
io
n
s
eg
m
e
n
tatio
n
b
ec
au
s
e
ele
m
en
ts
o
f
a
n
i
m
a
g
e
ca
n
b
e
q
u
ick
l
y
r
ec
o
g
n
i
ze
d
b
y
co
m
p
ar
in
g
th
eir
i
n
ten
s
ities
w
it
h
th
e
t
h
r
es
h
o
ld
s
[
4
0
]
.
Ho
w
e
v
er
,
lo
ca
l
th
r
es
h
o
ld
is
es
s
en
t
ial
f
o
r
s
eg
m
en
tatio
n
if
th
e
i
m
a
g
e
h
as
m
o
r
e
th
a
n
t
w
o
t
y
p
es
o
f
r
eg
io
n
s
t
h
at
co
r
r
esp
o
n
d
to
d
is
tin
ct
o
b
j
ec
ts
.
E
ith
er
a
s
in
g
le
th
r
es
h
o
ld
o
r
a
co
m
b
i
n
atio
n
o
f
t
h
r
es
h
o
ld
s
ca
n
b
e
u
s
ed
to
p
ar
titi
o
n
th
e
i
m
a
g
e.
W
h
ile
M
R
I
p
r
o
v
id
es
a
w
ea
l
th
o
f
i
n
f
o
r
m
atio
n
,
lo
ca
l
o
r
g
lo
b
al
th
r
es
h
o
ld
-
b
ase
d
s
eg
m
en
ta
tio
n
alg
o
r
ith
m
s
ar
e
t
y
p
i
ca
ll
y
e
m
p
lo
y
ed
as a
j
u
m
p
in
g
-
o
f
f
p
o
in
t
f
o
r
th
e
s
e
g
m
en
ta
tio
n
p
r
o
ce
s
s
.
b.
P
ix
el
c
lass
i
f
icatio
n
:
P
ix
el
clas
s
if
ica
tio
n
is
an
o
t
h
er
m
et
h
o
d
u
s
ed
f
o
r
s
eg
m
e
n
tatio
n
.
E
ac
h
i
m
ag
e
p
ix
el
h
as
it
s
o
w
n
s
et
o
f
c
h
ar
ac
ter
is
tic
s
th
a
t
ca
n
b
e
ex
p
r
ess
ed
in
f
ea
t
u
r
e
s
p
ac
e.
T
h
e
p
ix
el
'
s
lo
ca
l
te
x
t
u
r
e,
co
lo
r
,
an
d
g
r
a
y
s
ca
le
v
al
u
e
ar
e
all
ex
a
m
p
les
o
f
s
u
c
h
attr
ib
u
tes.
1
D
f
ea
t
u
r
e
s
p
ac
e
s
eg
m
e
n
tat
io
n
is
p
o
s
s
ib
le
in
s
in
g
le
-
ch
an
n
el
(
o
r
s
in
g
le
-
f
r
a
m
e)
i
m
a
g
es
[
4
1
]
,
an
d
g
r
e
y
-
lev
el
a
n
al
y
s
is
is
co
m
m
o
n
l
y
u
s
ed
f
o
r
p
ix
el
ca
teg
o
r
izatio
n
.
Fo
r
im
a
g
es
w
it
h
s
e
v
er
al
ch
an
n
els
(
f
r
a
m
es)
o
r
m
o
d
alitie
s
(
s
p
ec
tr
u
m
s
)
,
s
e
g
m
en
tat
io
n
ca
n
b
e
p
er
f
o
r
m
ed
in
a
m
u
ltid
i
m
en
s
io
n
al
f
ea
t
u
r
e
s
p
ac
e.
Du
e
to
t
h
e
li
m
ita
tio
n
s
o
f
s
u
p
er
v
is
ed
an
d
u
n
s
u
p
er
v
is
ed
al
g
o
r
ith
m
s
u
s
ed
i
n
p
ix
el
class
i
f
icat
io
n
alg
o
r
it
h
m
s
,
B
T
s
eg
m
en
tatio
n
is
d
if
f
ic
u
lt.
B
y
p
u
tti
n
g
th
i
n
g
s
w
it
h
s
i
m
ilar
p
r
o
p
er
ties
to
g
eth
er
a
n
d
th
o
s
e
w
it
h
d
if
f
er
i
n
g
f
ea
t
u
r
es a
p
ar
t,
w
e
e
n
g
a
g
e
i
n
th
e
p
r
o
ce
s
s
o
f
cl
u
s
ter
in
g
.
An
ac
ce
p
tab
le
d
is
t
a
n
ce
m
ea
s
u
r
e
is
u
tili
ze
d
to
es
ti
m
ate
t
h
e
lev
el
o
f
s
i
m
ilar
it
y
.
Si
m
i
lar
it
y
ca
n
b
e
ea
s
il
y
q
u
an
ti
f
ied
b
y
ca
lc
u
lati
n
g
t
h
e
d
is
tan
ce
b
et
w
ee
n
t
w
o
f
ea
t
u
r
e
s
p
ac
e
v
ec
to
r
s
,
r
ep
r
esen
ted
b
y
.
Dis
ta
n
ce
(
,
)
=
√
∑
(
−
)
2
=
1
(
1
)
w
h
er
e
X
i
=
(
X
i
1
,
…
.
X
i
n
)
an
d
X
j
=
(
X
j
1
,
…
.
X
j
n
)
d
en
o
te
th
e
t
w
o
f
ea
t
u
r
e
v
ec
to
r
s
.
T
h
e
a
f
o
r
em
e
n
tio
n
ed
m
ea
s
u
r
e
is
id
en
tical
to
Ma
h
alan
o
b
is
an
d
E
u
c
lid
ea
n
d
is
ta
n
ce
if
p
=
1
an
d
p
=
2
.
An
o
th
er
f
r
eq
u
en
t
s
i
m
ilar
it
y
cr
iter
io
n
i
s
t
h
e
n
o
r
m
alize
d
in
n
er
p
r
o
d
u
ct,
d
ef
i
n
ed
as.
w
h
er
e
T
→
Ve
c
tor
s
R
e
s
pon
s
e
.
T
h
is
m
etr
ic
g
i
v
es
d
etail
s
ab
o
u
t
th
e
co
s
in
e
r
elatio
n
s
h
ip
b
et
w
e
en
f
ea
t
u
r
e
s
p
ac
e
v
ec
to
r
s
X
i
an
d
X
j
.
Sev
er
al
clu
s
ter
i
n
g
ap
p
r
o
ac
h
es
h
a
v
e
b
ee
n
p
r
o
p
o
s
ed
.
Su
ch
e
s
s
e
n
tial
tech
n
iq
u
e
s
in
c
lu
d
e
f
u
zz
y
C
-
m
ea
n
s
(
F
C
M)
,
k
-
m
ea
n
s
,
a
n
d
s
tatis
tical
ap
p
r
o
ac
h
es s
u
c
h
as M
ar
k
o
v
r
an
d
o
m
f
ield
s
(
MR
F).
c.
R
eg
io
n
-
b
a
s
ed
:
B
y
co
m
b
i
n
i
n
g
n
ei
g
h
b
o
r
in
g
p
i
x
els
w
it
h
h
o
m
o
g
e
n
eo
u
s
f
ea
tu
r
e
s
a
cc
o
r
d
in
g
to
a
p
r
ed
eter
m
i
n
ed
s
i
m
i
lar
it
y
cr
ite
r
io
n
,
r
eg
io
n
-
b
ased
s
e
g
m
en
ta
ti
o
n
ap
p
r
o
ac
h
es
an
al
y
ze
th
e
i
m
ag
e
p
i
x
els
to
cr
ea
te
s
ep
ar
ate
ar
ea
s
[
4
2
]
.
T
h
e
f
o
llo
w
in
g
i
s
a
h
ig
h
-
le
v
el
o
u
tlin
e
o
f
t
h
ese
tec
h
n
iq
u
es
:
L
et
b
e
an
i
m
ag
e
th
at
h
as
b
ee
n
d
iv
id
ed
in
to
r
eg
io
n
s
,
w
it
h
r
ep
r
esen
tin
g
ea
ch
ar
ea
an
d
=
1
,
2
,
…
.
No
tw
o
ar
ea
s
an
d
f
o
r
≠
s
h
o
u
ld
o
v
er
lap
in
o
r
d
er
f
o
r
th
e
r
esu
ltin
g
i
m
a
g
e
to
b
e
an
ac
cu
r
ate
r
ep
r
esen
tatio
n
o
f
th
e
o
r
ig
in
al.
T
h
e
r
eg
io
n
s
s
h
o
u
ld
h
av
e
th
e
c
h
ar
ac
ter
is
tic
s
lis
ted
b
elo
w
.
⋃
=
=
1
(
2
)
∩
=
0
∀
,
=
1
,
2
,
…
.
.
(
3
)
P(
)
=
(
4
)
(
∪
)
=
≠
(
5
)
w
h
er
e,
(
)
is
lo
g
ica
l
p
r
ed
icate
.
T
h
e
m
o
s
t
p
o
p
u
lar
r
eg
io
n
-
b
as
ed
ap
p
r
o
ac
h
es
f
o
r
B
T
s
eg
m
e
n
tatio
n
ar
e
r
eg
io
n
g
r
o
w
t
h
an
d
w
ater
s
h
ed
s
eg
m
e
n
tat
io
n
.
d.
Mo
d
el
-
b
ased
:
B
est
p
r
ac
tices
f
o
r
u
s
in
g
2
D
MRI
d
ata
to
id
en
ti
f
y
th
e
b
o
u
n
d
ar
ies
o
f
a
B
T
h
av
e
b
ee
n
in
v
e
s
ti
g
ated
b
ef
o
r
e.
T
h
e
h
u
g
e
q
u
a
n
tit
y
o
f
d
atase
ts
a
n
d
th
e
co
m
p
lex
ities
a
n
d
v
a
r
iatio
n
s
o
f
th
e
m
o
r
p
h
o
lo
g
ical
s
h
ap
es
o
f
in
t
er
est
m
a
k
es
i
t
d
if
f
ic
u
lt
to
s
eg
m
e
n
t
ele
m
e
n
t
s
f
r
o
m
m
ed
i
ca
l
i
m
a
g
es
a
n
d
r
ec
o
n
s
tr
u
ct
a
n
ef
f
icie
n
t
g
eo
m
e
tr
ic
r
ep
r
esen
tatio
n
o
f
t
h
ese
ele
m
en
ts
[
4
3
]
.
3
.
2
.
F
e
a
t
ure
ex
t
ra
ct
io
n
(
F
E
)
FE
f
r
o
m
r
a
w
i
m
ag
e
s
is
n
ec
e
s
s
ar
y
to
f
ac
ilit
ate
d
ec
is
io
n
s
li
k
e
p
atter
n
id
en
ti
f
ica
tio
n
,
ca
te
g
o
r
izatio
n
,
an
d
r
ec
o
g
n
it
io
n
.
T
r
u
s
t
w
o
r
th
y
an
d
d
is
cr
i
m
in
ati
v
e
FE
is
al
w
a
y
s
a
cr
itica
l
s
ta
g
e
i
n
ef
f
ec
ti
v
el
y
co
m
p
leti
n
g
i
m
ag
e
r
ec
o
g
n
itio
n
an
d
co
m
p
u
ter
v
is
i
o
n
task
s
[
4
4
]
.
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.
15
,
No
.
4
,
A
u
g
u
s
t
20
25
:
4
3
3
2
-
4340
4336
a.
C
o
lo
r
f
ea
tu
r
es:
C
o
lo
r
is
th
e
m
o
s
t
o
b
v
io
u
s
an
d
i
m
p
o
r
tan
t
f
ea
t
u
r
e
f
o
r
h
u
m
a
n
s
w
h
en
s
e
ein
g
a
n
i
m
a
g
e
.
B
ec
au
s
e
th
e
h
u
m
a
n
v
i
s
u
a
l
s
y
s
te
m
ab
s
o
r
b
s
co
lo
r
in
f
o
r
m
at
i
o
n
f
aster
th
a
n
g
r
e
y
lev
e
ls
,
it
is
o
f
ten
th
e
f
ir
s
t
ca
n
d
id
ate
ev
al
u
ated
w
h
en
atte
m
p
tin
g
to
e
x
tr
ac
t
f
ea
t
u
r
es.
A
p
o
p
u
lar
tech
n
iq
u
e
f
o
r
v
i
s
u
al
iz
in
g
co
lo
r
d
ata
is
th
e
co
lo
r
h
is
to
g
r
a
m
[
4
5
]
.
T
h
e
f
o
llo
w
in
g
ar
e
th
e
ad
v
a
n
ta
g
es o
f
th
is
ap
p
r
o
ac
h
:
R
o
b
u
s
t
n
es
s
: T
h
e
co
lo
r
h
is
to
g
r
a
m
is
i
n
v
ar
ian
t
u
n
d
er
r
o
tatio
n
o
r
r
esizin
g
b
u
t
g
r
ad
u
all
y
alter
s
.
E
f
f
ec
tiv
e
n
es
s
: T
h
e
m
a
tc
h
i
n
g
i
m
ag
e
s
f
o
u
n
d
ar
e
ex
tr
e
m
el
y
r
el
ev
an
t to
t
h
e
q
u
er
y
i
m
a
g
e.
I
m
p
le
m
e
n
tatio
n
s
i
m
p
licit
y
: P
r
o
d
u
cin
g
a
co
lo
r
h
i
s
to
g
r
a
m
in
v
o
lv
es
p
r
o
ce
s
s
i
n
g
t
h
e
i
m
ag
e,
m
ap
p
in
g
co
lo
r
v
alu
e
s
,
an
d
co
lo
r
in
g
i
n
d
ex
in
g
co
m
p
o
n
e
n
t
s
.
L
o
w
m
em
o
r
y
:
T
h
e
c
o
l
o
r
h
i
s
t
o
g
r
am
w
il
l
b
e
s
u
b
s
t
an
t
i
al
ly
l
es
s
th
an
th
e
im
ag
e
if
th
e
c
o
l
o
r
s
a
r
e
q
u
an
t
if
i
e
d
.
b.
T
ex
tu
r
e
f
ea
tu
r
es
:
T
h
er
e
ar
e
n
u
m
er
o
u
s
tech
n
iq
u
e
s
f
o
r
ex
t
r
ac
tin
g
te
x
t
u
r
e
f
ea
tu
r
e
s
.
Me
th
o
d
o
lo
g
ies
ar
e
ca
teg
o
r
ized
as
s
tr
u
ct
u
r
al,
s
ta
t
is
tical,
m
o
d
el
-
b
ased
,
a
n
d
tr
a
n
s
f
o
r
m
-
b
ased
tec
h
n
iq
u
es,
ea
c
h
w
it
h
its
o
w
n
u
n
iq
u
e
s
et
o
f
ad
v
a
n
ta
g
es a
n
d
d
is
ad
v
an
ta
g
es
[
4
6
]
.
T
h
e
1
s
t,
2
n
d
,
an
d
h
i
g
h
er
-
o
r
d
er
s
tatis
t
ics
ar
e
all
ex
a
m
p
le
s
o
f
s
tati
s
tical
f
ea
tu
r
e
s
[
4
7
]
.
c.
Sh
ap
e
f
ea
t
u
r
es:
T
h
e
ce
n
ter
o
f
g
r
av
it
y
,
cir
cu
lar
it
y
r
atio
,
co
n
v
e
x
it
y
,
p
r
o
f
ile
s
,
d
ig
ital
b
en
d
in
g
en
er
g
y
,
r
ec
tan
g
u
lar
it
y
,
ellip
tic
v
ar
ia
n
c
e
,
Ax
is
o
f
lea
s
t
i
n
er
tia,
So
lid
it
y
,
E
u
ler
n
u
m
b
er
,
E
cc
en
tr
icit
y
,
an
d
Ho
le
ar
ea
r
atio
ar
e
all
p
ar
am
eter
s
o
f
s
h
a
p
es
[
4
8
]
.
3
.
3
.
C
la
s
s
if
ica
t
io
n m
o
de
l
T
h
e
f
ield
o
f
s
t
u
d
y
d
ed
icate
d
to
th
e
an
al
y
s
i
s
o
f
co
m
p
u
ter
alg
o
r
it
h
m
s
is
r
ap
id
l
y
e
x
p
an
d
in
g
.
Un
s
u
p
er
v
i
s
ed
an
d
s
e
m
i
-
s
u
p
er
v
is
ed
lear
n
in
g
ar
e
t
w
o
f
u
r
t
h
er
t
y
p
es
o
f
M
L
,
i
n
ad
d
itio
n
to
s
u
p
er
v
is
ed
lear
n
in
g
[
4
9
]
,
[
5
0
]
.
I
n
ML
,
th
e
s
u
p
er
v
i
s
ed
lear
n
in
g
tas
k
r
elies
o
n
t
h
e
lab
eled
tr
ain
in
g
d
ata
to
in
f
er
a
f
u
n
ctio
n
.
T
o
b
e
m
o
r
e
p
r
ec
is
e,
u
n
s
u
p
er
v
i
s
ed
lear
n
in
g
m
a
k
e
s
u
s
e
o
f
r
a
w
d
ata
w
it
h
o
u
t
an
y
h
u
m
a
n
lab
el
s
.
Se
m
i
-
S
u
p
er
v
i
s
ed
lear
n
in
g
co
m
b
i
n
es lab
eled
an
d
u
n
lab
eled
d
ata.
I
n
M
L
,
t
h
e
s
u
p
er
v
is
ed
lear
n
in
g
tas
k
r
elie
s
o
n
t
h
e
lab
eled
tr
ain
i
n
g
d
ata
to
in
f
er
a
f
u
n
ctio
n
.
B
o
th
a
n
in
p
u
t
(
P
)
an
d
an
o
u
tp
u
t
(
Q)
ar
e
r
eq
u
ir
ed
f
o
r
s
u
p
er
v
is
ed
lear
n
in
g
[
5
1
]
.
T
h
e
p
u
r
p
o
s
e
o
f
t
h
e
alg
o
r
ith
m
is
t
o
in
v
e
s
ti
g
ate
t
h
e
m
ap
p
in
g
f
u
n
c
tio
n
=
(
)
f
r
o
m
t
h
e
i
n
p
u
t
v
ar
iab
le
to
th
e
o
u
tp
u
t
v
ar
iab
le.
T
h
e
lear
n
in
g
m
et
h
o
d
ca
n
r
eliab
ly
g
e
n
er
ali
s
e
th
e
lab
els
o
f
class
es
f
o
r
w
h
ic
h
d
ata
is
lack
in
g
[
5
2
]
.
Dec
is
io
n
t
r
ee
s
(
DT
)
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
s
(
SV
M)
,
n
eu
r
al
n
et
w
o
r
k
s
(
NN)
,
li
n
ea
r
d
is
cr
i
m
i
n
a
n
t
an
a
l
y
s
is
(
L
DA
)
,
r
an
d
o
m
f
o
r
ests
(
R
F),
k
-
n
ea
r
e
s
t
n
eig
h
b
o
r
s
(
K
NN)
,
an
d
n
ai
v
e
B
a
y
e
s
(
NB
)
ar
e
s
o
m
e
o
f
t
h
e
s
u
p
er
v
is
ed
lear
n
in
g
tech
n
iq
u
es.
T
h
e
in
p
u
t
v
ar
iab
le
(
P
)
is
p
r
esen
t
in
u
n
s
u
p
er
v
is
ed
lear
n
i
n
g
,
b
u
t
th
er
e
is
n
o
co
r
r
esp
o
n
d
in
g
o
u
tp
u
t.
T
h
e
g
o
al
o
f
u
n
s
u
p
er
v
is
ed
lear
n
in
g
i
s
to
d
is
co
v
er
laten
t
p
atter
n
s
i
n
d
ata
th
at
h
a
v
e
n
o
t
b
ee
n
e
x
p
li
citl
y
lab
eled
[
5
3
]
.
K
-
Me
a
n
s
,
Hid
d
en
Ma
r
k
o
v
m
o
d
el,
FC
M,
Gau
s
s
ia
n
m
i
x
tu
r
e
m
o
d
el,
an
d
p
r
in
cip
al
co
m
p
o
n
en
t
a
n
al
y
s
is
(
P
C
A
)
ar
e
all
ex
a
m
p
les
o
f
u
n
s
u
p
er
v
i
s
ed
lear
n
in
g
m
et
h
o
d
s
T
h
e
r
ec
en
t
r
esear
ch
w
o
r
k
o
n
au
to
m
a
t
ic
B
T
cla
s
s
if
icatio
n
an
d
s
eg
m
e
n
tatio
n
u
s
in
g
M
L
is
d
etailed
in
T
ab
le
2
.
T
ab
le
2
.
R
ec
en
t
w
o
r
k
co
m
p
ar
i
s
o
n
o
f
P
D
class
i
f
icat
io
n
u
s
i
n
g
A
I
m
eth
o
d
R
e
f
Y
e
a
r
D
a
t
a
Pre
-
p
r
o
c
e
ss
S
e
g
me
n
t
a
t
i
o
n
FE
M
o
d
e
l
[
5
4
]
2
0
2
1
N
i
sh
t
a
r
H
o
sp
i
t
a
l
M
u
l
t
a
n
N
o
i
se
r
e
mo
v
a
l
,
S
h
a
r
p
e
n
i
n
g
,
H
i
st
o
g
r
a
m,
S
k
u
l
l
S
t
r
i
p
p
i
n
g
K
-
M
e
a
n
s,
W
a
t
e
r
sh
e
d
,
T
h
r
e
sh
o
l
d
L
o
c
a
l
b
i
n
a
r
y
p
a
t
t
e
r
n
,
H
i
st
o
g
r
a
m
o
f
o
r
i
e
n
t
e
d
g
r
a
d
i
e
n
ts
S
V
M
,
F
u
z
z
y
[
5
5
]
2
0
2
2
M
/
s
A
a
r
t
h
i
c
h
e
c
k
s,
I
n
d
i
a
.
N
o
i
se
R
e
mo
v
a
l
F
C
M
G
r
e
y
-
l
e
v
e
l
r
u
n
-
l
e
n
g
t
h
mat
r
i
x
S
V
M
,
NN
[
5
6
]
2
0
1
5
CE
-
M
R
I
N
o
r
mal
i
z
a
t
i
o
n
-
G
L
C
M
S
V
M
,
K
N
N
,
NN
[
5
7
]
2
0
2
2
K
a
g
g
l
e
N
o
r
mal
i
z
a
t
i
o
n
-
D
i
scre
t
e
w
a
v
e
l
e
t
t
r
a
n
sf
o
r
ms
(
D
W
T
)
,
G
L
C
M
,
P
C
A
,
S
V
M
,
XG
B
o
o
st
,
L
R
,
RF
[
5
8
]
2
0
2
2
B
R
A
T
S
2
0
1
8
R
e
si
z
e
,
N
o
i
se
r
e
mo
v
a
l
,
N
o
r
mal
i
z
a
t
i
o
n
.
A
u
g
me
n
t
a
t
i
o
n
K
-
M
e
a
n
s
-
-
[
5
9
]
2
0
2
2
A
A
N
LI
B
,
H
a
r
v
a
r
d
.
O
A
S
I
S
N
o
i
se
r
e
mo
v
a
l
,
S
k
u
l
l
s
t
r
i
p
p
i
n
g
,
M
o
r
p
h
o
l
o
g
i
c
a
l
o
p
e
r
a
t
i
o
n
K
-
M
e
a
n
s
P
C
A
,
D
W
T
k
e
r
n
e
l
-
b
a
se
d
S
V
M
[
6
0
]
2
0
2
2
U
C
I
r
e
p
o
si
t
o
r
y
N
o
i
se
r
e
mo
v
a
l
O
p
t
i
mi
z
e
d
,
K
-
M
e
a
n
s
D
W
T
S
V
M
,
K
N
N
.
NN
[
6
1
]
2
0
2
3
B
R
A
T
S
2
0
1
4
,
B
T
D
2
0
N
o
t
me
n
t
i
o
n
e
d
S
o
c
i
a
l
s
p
i
d
e
r
o
p
t
i
m
i
z
a
t
i
o
n
S
i
n
g
u
l
a
r
V
a
l
u
e
D
e
c
o
mp
o
si
t
i
o
n
En
se
mb
l
e
M
L
[
6
2
]
2
0
2
3
F
i
g
sh
a
r
e
N
o
t
me
n
t
i
o
n
e
d
-
L
B
P
,
H
o
G
,
G
L
C
M
K
N
N
,
S
V
M
,
N
B
,
D
T
,
En
se
mb
l
e
ML
[
6
3
]
2
0
1
9
N
o
t
me
n
t
i
o
n
e
d
N
o
i
se
r
e
mo
v
a
l
,
M
o
r
p
h
o
l
o
g
i
c
a
l
o
p
e
r
a
t
i
o
n
C
-
me
a
n
s
-
NB
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:
2088
-
8708
A
n
a
p
p
r
o
a
ch
f
o
r
p
r
ed
ictin
g
b
r
a
in
tu
mo
r
w
ith
ma
ch
in
e
lea
r
n
in
g
tech
n
iq
u
es (
P
S
R
B
S
h
a
s
h
a
n
k)
4337
4.
CH
AL
L
E
N
G
E
S
T
h
is
s
u
r
v
e
y
ex
a
m
i
n
e
s
th
e
m
o
s
t
u
p
-
to
-
d
ate
r
esear
ch
o
n
B
T
d
etec
tio
n
m
eth
o
d
s
a
n
d
co
n
clu
d
es
th
e
ch
alle
n
g
e
s
in
au
to
m
atic
B
T
d
etec
tio
n
.
Du
e
to
th
eir
ten
tacl
es
an
d
s
ca
tter
ed
s
tr
u
ctu
r
es,
B
T
s
ar
e
n
o
to
r
io
u
s
l
y
ch
alle
n
g
i
n
g
to
ac
cu
r
atel
y
s
eg
m
en
t
[
6
4
]
.
T
h
e
p
r
o
ce
s
s
o
f
ch
o
o
s
in
g
t
h
e
b
est
f
ea
t
u
r
es
to
e
x
tr
ac
t
an
d
th
e
r
i
g
h
t
a
m
o
u
n
t
o
f
tr
ain
i
n
g
/te
s
ti
n
g
s
a
m
p
les
to
u
s
e
is
also
cr
u
cial
f
o
r
ac
cu
r
ate
class
i
f
icatio
n
[
6
5
]
.
T
h
e
ch
allen
g
es
o
f
B
T
d
etec
tio
n
ar
e
in
d
eter
m
in
ate
lo
ca
tio
n
,
m
o
r
p
h
o
lo
g
ical
co
m
p
le
x
it
y
,
p
o
o
r
co
n
tr
ast
,
an
d
an
n
o
tatio
n
b
ias
.
Du
r
in
g
th
e
tr
ain
in
g
p
h
ase
o
f
th
e
s
eg
m
en
tatio
n
m
et
h
o
d
,
th
e
an
n
o
tatio
n
b
iases
h
av
e
a
s
i
g
n
i
f
ica
n
t
ef
f
ec
t
o
n
th
e
r
es
u
lt
s
[
6
6
]
.
5.
CO
NCLU
SI
O
N
C
an
ce
r
d
iag
n
o
s
i
s
g
r
ap
p
les
w
ith
a
u
to
m
ated
B
T
s
eg
m
en
ta
ti
o
n
an
d
clas
s
i
f
icatio
n
.
De
v
elo
p
m
e
n
t
s
i
n
ML
,
w
i
th
th
e
s
u
p
p
o
r
t
o
f
p
u
b
licl
y
a
v
ailab
le
d
atase
ts
s
u
c
h
a
s
B
R
A
T
S,
h
a
v
e
en
h
a
n
ce
d
m
e
d
ical
i
m
a
g
i
n
g
.
T
h
e
p
r
esen
t
p
ap
er
is
a
r
ev
ie
w
o
f
tr
ad
itio
n
al
p
r
e
-
p
r
o
ce
s
s
in
g
,
s
e
g
m
e
n
tat
io
n
,
an
d
f
ea
tu
r
e
e
x
tr
a
ctio
n
m
e
th
o
d
s
a
n
d
n
o
v
el
M
L
-
b
ased
clas
s
i
f
icatio
n
ap
p
r
o
ac
h
es.
E
s
s
e
n
tial
p
r
e
-
p
r
o
ce
s
s
in
g
tas
k
s
ar
e
f
ilter
i
n
g
,
s
k
u
l
l
s
tr
ip
p
in
g
,
n
o
r
m
aliza
t
io
n
,
co
lo
r
tr
an
s
f
o
r
m
atio
n
,
a
n
d
m
o
r
p
h
o
lo
g
ica
l
tr
a
n
s
f
o
r
m
atio
n
s
.
T
h
e
o
v
er
v
ie
w
p
r
esen
ts
s
tate
-
of
-
t
h
e
-
ar
t
ap
p
r
o
ac
h
es,
ch
allen
g
es,
an
d
th
e
p
o
s
s
ib
ilit
y
o
f
M
L
in
t
r
an
s
f
o
r
m
i
n
g
B
T
d
iag
n
o
s
tic
s
to
ac
h
iev
e
i
m
p
r
o
v
ed
p
atien
t o
u
tco
m
es.
F
UNDIN
G
I
NF
O
RM
AT
I
O
N
No
Fu
n
d
i
n
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RIB
UT
I
O
NS ST
A
T
E
M
E
NT
T
h
is
jo
u
r
n
al
u
s
e
s
th
e
C
o
n
t
r
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
r
ed
i
T
)
to
r
ec
o
g
n
ize
in
d
i
v
id
u
al
au
t
h
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
t
h
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
lla
b
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
P
SR
B
Sh
as
h
an
k
L.
A
n
a
n
d
R
.
P
itch
ai
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
si
s
I
:
I
n
v
e
st
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
si
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
t
h
o
r
s
s
tate
n
o
co
n
f
lic
t o
f
i
n
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t th
e
f
i
n
d
i
n
g
s
o
f
t
h
is
s
tu
d
y
ar
e
av
ailab
le
o
n
r
eq
u
est
.
RE
F
E
R
E
NC
E
S
[
1
]
Y
.
Y
a
n
g
e
t
a
l
.
,
“
G
l
i
o
ma
g
r
a
d
i
n
g
o
n
c
o
n
v
e
n
t
i
o
n
a
l
M
R
i
mag
e
s:
A
d
e
e
p
l
e
a
r
n
i
n
g
st
u
d
y
w
i
t
h
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
,
”
Fr
o
n
t
i
e
rs
i
n
N
e
u
ro
s
c
i
e
n
c
e
,
v
o
l
.
1
2
,
p
.
8
0
4
,
N
o
v
.
2
0
1
8
,
d
o
i
:
1
0
.
3
3
8
9
/
f
n
i
n
s.
2
0
1
8
.
0
0
8
0
4
.
[
2
]
R
.
S
u
n
e
t
a
l
.
,
“
A
p
o
t
e
n
t
i
a
l
f
i
e
l
d
se
g
me
n
t
a
t
i
o
n
b
a
se
d
me
t
h
o
d
f
o
r
t
u
mo
r
seg
me
n
t
a
t
i
o
n
o
n
m
u
l
t
i
-
p
a
r
a
me
t
r
i
c
M
R
I
o
f
g
l
i
o
ma
c
a
n
c
e
r
p
a
t
i
e
n
t
s,”
BM
C
Me
d
i
c
a
l
I
m
a
g
i
n
g
,
v
o
l
.
1
9
,
n
o
.
1
,
p
.
4
8
,
D
e
c
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
8
6
/
s1
2
8
8
0
-
019
-
0
3
4
8
-
y.
[
3
]
H
.
S
u
n
g
e
t
a
l
.
,
“
G
l
o
b
a
l
c
a
n
c
e
r
st
a
t
i
st
i
c
s
2
0
2
0
:
G
L
O
B
O
C
A
N
e
s
t
i
m
a
t
e
s
o
f
i
n
c
i
d
e
n
c
e
a
n
d
m
o
r
t
a
l
i
t
y
W
o
r
l
d
w
i
d
e
f
o
r
3
6
c
a
n
c
e
r
s
i
n
1
8
5
c
o
u
n
t
r
i
e
s
,
”
C
A
:
A
C
a
n
c
e
r
J
o
u
r
n
a
l
f
o
r
C
l
i
n
i
c
i
a
n
s
,
v
o
l
.
7
1
,
n
o
.
3
,
p
p
.
2
0
9
–
2
4
9
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
3
3
2
2
/
c
a
a
c
.
2
1
6
6
0
.
[
4
]
H
.
K
a
sb
a
n
,
M
.
A
.
M
.
El
-
B
e
n
d
a
r
y
,
a
n
d
D
.
H
.
S
a
l
a
ma,
“
A
c
o
mp
a
r
a
t
i
v
e
st
u
d
y
o
f
me
d
i
c
a
l
i
m
a
g
i
n
g
t
e
c
h
n
i
q
u
e
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
,
v
o
l
.
4
,
n
o
.
2
,
p
p
.
3
7
–
5
8
,
2
0
1
5
.
[
5
]
K
.
A
.
R
a
j
a
se
k
a
r
a
n
a
n
d
C
.
C
.
G
o
u
n
d
e
r
,
“
A
d
v
a
n
c
e
d
b
r
a
i
n
t
u
mo
u
r
se
g
me
n
t
a
t
i
o
n
f
r
o
m
M
R
I
i
mag
e
s,”
i
n
H
i
g
h
-
R
e
so
l
u
t
i
o
n
N
e
u
ro
i
m
a
g
i
n
g
-
Ba
s
i
c
Ph
y
si
c
a
l
P
ri
n
c
i
p
l
e
s
a
n
d
C
l
i
n
i
c
a
l
A
p
p
l
i
c
a
t
i
o
n
s
,
I
n
T
e
c
h
,
2
0
1
8
.
[
6
]
W
.
D
.
F
o
l
t
z
a
n
d
D
.
A
.
Jaff
r
a
y
,
“
P
r
i
n
c
i
p
l
e
s
o
f
mag
n
e
t
i
c
r
e
so
n
a
n
c
e
i
m
a
g
i
n
g
,
”
Ra
d
i
a
t
i
o
n
Re
s
e
a
rc
h
,
v
o
l
.
1
7
7
,
n
o
.
4
,
p
p
.
3
3
1
–
3
4
8
,
A
p
r
.
2
0
1
2
,
d
o
i
:
1
0
.
1
6
6
7
/
R
R
2
6
2
0
.
1
.
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.
15
,
No
.
4
,
A
u
g
u
s
t
20
25
:
4
3
3
2
-
4340
4338
[
7
]
K
.
A
.
M
c
N
e
i
l
l
,
“
Ep
i
d
e
mi
o
l
o
g
y
o
f
b
r
a
i
n
t
u
mo
r
s,”
N
e
u
r
o
l
o
g
i
c
C
l
i
n
i
c
s
,
v
o
l
.
3
4
,
n
o
.
4
,
p
p
.
9
8
1
–
9
9
8
,
N
o
v
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
c
l
.
2
0
1
6
.
0
6
.
0
1
4
.
[
8
]
P
.
M
.
B
l
a
c
k
,
“
B
r
a
i
n
t
u
mo
r
s,
”
N
e
w
E
n
g
l
a
n
d
J
o
u
rn
a
l
o
f
Me
d
i
c
i
n
e
,
v
o
l
.
3
2
4
,
n
o
.
2
2
,
p
p
.
1
5
5
5
–
1
5
6
4
,
M
a
y
1
9
9
1
,
d
o
i
:
1
0
.
1
0
5
6
/
N
EJ
M
1
9
9
1
0
5
3
0
3
2
4
2
2
0
5
.
[
9
]
B
r
a
T
S
,
“
R
S
N
A
-
A
S
N
R
-
M
I
C
C
A
I
b
r
a
i
n
t
u
mo
r
se
g
me
n
t
a
t
i
o
n
(
B
r
a
T
S
)
c
h
a
l
l
e
n
g
e
2
0
2
1
,
”
2
0
2
1
.
h
t
t
p
s:
/
/
w
w
w
.
s
y
n
a
p
se
.
o
r
g
/
#
!
S
y
n
a
p
se
:
s
y
n
2
5
8
2
9
0
6
7
/
w
i
k
i
/
6
1
0
8
6
3
(
a
c
c
e
sse
d
J
a
n
.
2
6
,
2
0
2
4
)
.
[
1
0
]
B
r
a
T
S
,
“
M
u
l
t
i
mo
d
a
l
b
r
a
i
n
t
u
mo
r
se
g
me
n
t
a
t
i
o
n
c
h
a
l
l
e
n
g
e
2
0
2
0
:
D
a
t
a
2
0
2
0
,
”
2
0
2
0
.
h
t
t
p
s:
/
/
w
w
w
.
me
d
.
u
p
e
n
n
.
e
d
u
/
c
b
i
c
a
/
b
r
a
t
s2
0
2
0
/
d
a
t
a
.
h
t
ml
(
a
c
c
e
sse
d
Ja
n
.
2
6
,
2
0
2
4
)
.
[
1
1
]
B
r
a
T
S
,
“
M
u
l
t
i
mo
d
a
l
b
r
a
i
n
t
u
mo
r
se
g
me
n
t
a
t
i
o
n
c
h
a
l
l
e
n
g
e
2
0
1
9
:
D
a
t
a
2
0
1
9
,
”
2
0
1
9
.
h
t
t
p
s:
/
/
w
w
w
.
me
d
.
u
p
e
n
n
.
e
d
u
/
c
b
i
c
a
/
b
r
a
t
s2
0
1
9
/
d
a
t
a
.
h
t
ml
(
a
c
c
e
sse
d
Ja
n
.
2
6
,
2
0
2
4
)
.
[
1
2
]
B
r
a
T
S
,
“
M
u
l
t
i
mo
d
a
l
b
r
a
i
n
t
u
mo
r
se
g
me
n
t
a
t
i
o
n
c
h
a
l
l
e
n
g
e
2
0
1
8
:
D
a
t
a
2
0
1
8
,
”
2
0
1
8
.
h
t
t
p
s:
/
/
w
w
w
.
me
d
.
u
p
e
n
n
.
e
d
u
/
s
b
i
a
/
b
r
a
t
s2
0
1
8
.
h
t
ml
(
a
c
c
e
sse
d
J
a
n
.
2
6
,
2
0
2
4
)
.
[
1
3
]
B
r
a
T
S
,
“
M
u
l
t
i
mo
d
a
l
b
r
a
i
n
t
u
mo
r
se
g
me
n
t
a
t
i
o
n
c
h
a
l
l
e
n
g
e
2
0
1
7
:
D
a
t
a
2
0
1
7
,
”
2
0
1
7
.
h
t
t
p
s:
/
/
w
w
w
.
me
d
.
u
p
e
n
n
.
e
d
u
/
s
b
i
a
/
b
r
a
t
s2
0
1
7
/
d
a
t
a
.
h
t
ml
(
a
c
c
e
sse
d
Ja
n
.
2
6
,
2
0
2
4
)
.
[
1
4
]
B
r
a
T
S
,
“
B
r
a
T
S
2
0
1
6
,
”
2
0
1
6
.
h
t
t
p
s:
/
/
w
w
w
.
smir.c
h
/
B
R
A
T
S
/
S
t
a
r
t
2
0
1
6
(
a
c
c
e
sse
d
Jan
.
2
6
,
2
0
2
4
)
.
[
1
5
]
B
r
a
T
S
,
“
B
r
a
T
S
2
0
1
5
,
”
2
0
1
5
.
h
t
t
p
s:
/
/
w
w
w
.
smir.c
h
/
B
R
A
T
S
/
S
t
a
r
t
2
0
1
5
(
a
c
c
e
sse
d
Jan
.
2
6
,
2
0
2
4
)
.
[
1
6
]
B
r
a
T
S
,
“
M
I
C
C
A
I
-
B
R
A
T
S
2
0
1
4
,
”
2
0
1
4
.
h
t
t
p
s:
/
/
w
w
w
.
smir.c
h
/
B
R
A
T
S
/
S
t
a
r
t
2
0
1
4
(
a
c
c
e
sse
d
Ja
n
.
2
6
,
2
0
2
4
)
.
[
1
7
]
Q
TI
M
,
“
T
h
e
q
u
a
n
t
i
t
a
t
i
v
e
t
r
a
n
sl
a
t
i
o
n
a
l
i
mag
i
n
g
i
n
M
e
d
i
c
i
n
e
L
a
b
a
t
t
h
e
M
a
r
t
i
n
o
s
C
e
n
t
e
r
,
”
2
0
1
3
.
h
t
t
p
s:
/
/
w
w
w
.
smir.c
h
/
B
R
A
T
S
/
S
t
a
r
t
2
0
1
3
(
a
c
c
e
sse
d
Ja
n
.
2
6
,
2
0
2
4
)
.
[
1
8
]
B
r
a
T
S
,
“
M
u
l
t
i
mo
d
a
l
b
r
a
i
n
t
u
mo
r
se
g
me
n
t
a
t
i
o
n
,
”
M
I
C
C
A
I
2
0
1
2
,
2
0
1
2
.
h
t
t
p
s:
/
/
w
w
w
2
.
i
mm
.
d
t
u
.
d
k
/
p
r
o
j
e
c
t
s/
B
R
A
T
S
2
0
1
2
/
(
a
c
c
e
sse
d
Jan
.
2
6
,
2
0
2
4
)
.
[
1
9
]
R
a
d
i
o
p
a
e
d
i
a
,
“
B
r
a
i
n
t
u
mo
r
d
a
t
a
se
t
.
”
h
t
t
p
s:
/
/
r
a
d
i
o
p
a
e
d
i
a
.
o
r
g
/
(
a
c
c
e
sse
d
F
e
b
.
0
1
,
2
0
2
4
)
.
[
2
0
]
T
C
I
A
,
“
C
a
n
c
e
r
i
m
a
g
i
n
g
a
r
c
h
i
v
e
,
”
N
a
t
i
o
n
a
l
C
a
n
c
e
r
I
n
st
i
t
u
t
e
(
N
C
I
)
.
h
t
t
p
s
:
/
/
w
w
w
.
c
a
n
c
e
r
i
mag
i
n
g
a
r
c
h
i
v
e
.
n
e
t
/
(
a
c
c
e
sse
d
F
e
b
.
0
2
,
2
0
2
4
)
.
[
2
1
]
J
.
C
h
e
n
g
,
“
B
r
a
i
n
t
u
m
o
r
d
a
t
a
s
e
t
,
”
f
i
g
sh
a
r
e
,
2
0
1
7
.
h
t
t
p
s
:
/
/
d
o
i
.
o
r
g
/
1
0
.
6
0
8
4
/
m9
.
f
i
g
s
h
a
r
e
.
1
5
1
2
4
2
7
.
v
5
(
a
c
c
e
s
s
e
d
F
e
b
.
0
2
,
2
0
2
4
)
.
[
2
2
]
A
.
H
a
mad
a
,
“
B
r
3
5
H
b
r
a
i
n
t
u
mo
r
d
e
t
e
c
t
i
o
n
2
0
2
0
d
a
t
a
se
t
,
”
2
0
2
0
.
h
t
t
p
s:
/
/
i
e
e
e
-
d
a
t
a
p
o
r
t
.
o
r
g
/
d
o
c
u
me
n
t
s
/
b
r
3
5
h
-
b
r
a
i
n
-
t
u
mo
r
-
d
e
t
e
c
t
i
o
n
-
2
0
2
0
-
0
(
a
c
c
e
sse
d
J
u
n
.
1
3
,
2
0
2
5
)
.
[
2
3
]
D
.
S
u
m
me
r
s,
“
H
a
r
v
a
r
d
W
h
o
l
e
b
r
a
i
n
a
t
l
a
s:
w
w
w
.
m
e
d
.
h
a
r
v
a
r
d
.
e
d
u
/
A
A
N
LI
B
/
h
o
me
.
h
t
ml
,
”
J
o
u
r
n
a
l
o
f
N
e
u
ro
l
o
g
y
,
N
e
u
r
o
s
u
rg
e
ry
&
Psy
c
h
i
a
t
r
y
,
v
o
l
.
7
4
,
n
o
.
3
,
p
.
2
8
8
,
M
a
r
.
2
0
0
3
,
d
o
i
:
1
0
.
1
1
3
6
/
j
n
n
p
.
7
4
.
3
.
2
8
8
.
[
2
4
]
A
.
L
.
S
i
m
p
so
n
e
t
a
l
.
,
“
A
l
a
r
g
e
a
n
n
o
t
a
t
e
d
me
d
i
c
a
l
i
mag
e
d
a
t
a
se
t
f
o
r
t
h
e
d
e
v
e
l
o
p
me
n
t
a
n
d
e
v
a
l
u
a
t
i
o
n
o
f
se
g
m
e
n
t
a
t
i
o
n
a
l
g
o
r
i
t
h
ms,
”
a
rXi
v
:
1
9
0
2
.
0
9
0
6
3
,
2
0
1
9
,
d
o
i
:
1
0
.
4
8
5
5
0
/
a
r
X
i
v
.
1
9
0
2
.
0
9
0
6
3
.
[
2
5
]
N
.
C
h
a
k
r
a
b
a
r
t
y
,
“
B
r
a
i
n
M
R
I
i
mag
e
s
f
o
r
b
r
a
i
n
t
u
mo
r
d
e
t
e
c
t
i
o
n
,
”
k
a
g
g
l
e
.
c
o
m
.
h
t
t
p
s:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m/
d
a
t
a
se
t
s/
n
a
v
o
n
e
e
l
/
b
r
a
i
n
-
mr
i
-
i
mag
e
s
-
f
o
r
-
b
r
a
i
n
-
t
u
mo
r
-
d
e
t
e
c
t
i
o
n
(
a
c
c
e
sse
d
F
e
b
.
0
2
,
2
0
2
4
)
.
[
2
6
]
S
.
S
a
p
o
n
a
r
a
a
n
d
A
.
El
h
a
n
a
s
h
i
,
“
I
mp
a
c
t
o
f
i
mag
e
r
e
si
z
i
n
g
o
n
d
e
e
p
l
e
a
r
n
i
n
g
d
e
t
e
c
t
o
r
s
f
o
r
t
r
a
i
n
i
n
g
t
i
me
a
n
d
mo
d
e
l
p
e
r
f
o
r
man
c
e
,
”
L
e
c
t
u
re
N
o
t
e
s
i
n
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
8
6
6
L
N
EE,
p
p
.
1
0
–
1
7
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
030
-
9
5
4
9
8
-
7
_
2
.
[
2
7
]
L
.
P
e
i
e
t
a
l
.
,
“
A
g
e
n
e
r
a
l
sk
u
l
l
st
r
i
p
p
i
n
g
o
f
mu
l
t
i
p
a
r
a
me
t
r
i
c
b
r
a
i
n
M
R
I
s u
si
n
g
3
D
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
r
t
s
,
v
o
l
.
1
2
,
n
o
.
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
8
-
022
-
1
4
9
8
3
-
4.
[
2
8
]
J.
K
l
e
e
si
e
k
e
t
a
l
.
,
“
D
e
e
p
M
R
I
b
r
a
i
n
e
x
t
r
a
c
t
i
o
n
:
A
3
D
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
sk
u
l
l
st
r
i
p
p
i
n
g
,
”
N
e
u
r
o
I
m
a
g
e
,
v
o
l
.
1
2
9
,
p
p
.
4
6
0
–
4
6
9
,
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
r
o
i
mag
e
.
2
0
1
6
.
0
1
.
0
2
4
.
[
2
9
]
P
.
K
a
l
a
v
a
t
h
i
a
n
d
V
.
B
.
S
.
P
r
a
s
a
t
h
,
“
M
e
t
h
o
d
s
o
n
s
k
u
l
l
st
r
i
p
p
i
n
g
o
f
M
R
I
h
e
a
d
sca
n
i
mag
e
s
—
a
r
e
v
i
e
w
,
”
J
o
u
r
n
a
l
o
f
D
i
g
i
t
a
l
I
m
a
g
i
n
g
,
v
o
l
.
2
9
,
n
o
.
3
,
p
p
.
3
6
5
–
3
7
9
,
2
0
1
6
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
2
7
8
-
0
1
5
-
9
8
4
7
-
8.
[
3
0
]
Y
.
S
h
a
r
ma
a
n
d
Y
.
K
.
M
e
g
h
r
a
j
a
n
i
,
“
E
x
t
r
a
c
t
i
o
n
o
f
g
r
a
y
sca
l
e
b
r
a
i
n
t
u
mo
r
i
n
mag
n
e
t
i
c
r
e
so
n
a
n
c
e
i
mag
e
,
”
I
j
a
rc
c
e
,
p
p
.
8
5
4
2
–
8
5
4
4
,
2
0
1
4
,
d
o
i
:
1
0
.
1
7
1
4
8
/
i
j
a
r
c
c
e
.
2
0
1
4
.
3
1
1
4
2
.
[
3
1
]
H
.
M
.
A
l
i
,
“
M
R
I
me
d
i
c
a
l
i
m
a
g
e
d
e
n
o
i
si
n
g
b
y
f
u
n
d
a
me
n
t
a
l
f
i
l
t
e
r
s,”
H
i
g
h
-
Re
so
l
u
t
i
o
n
N
e
u
r
o
i
m
a
g
i
n
g
-
B
a
s
i
c
Ph
y
si
c
a
l
Pr
i
n
c
i
p
l
e
s
a
n
d
C
l
i
n
i
c
a
l
A
p
p
l
i
c
a
t
i
o
n
s
,
2
0
1
8
,
d
o
i
:
1
0
.
5
7
7
2
/
i
n
t
e
c
h
o
p
e
n
.
7
2
4
2
7
.
[
3
2
]
P
.
N
a
t
a
r
a
j
a
n
,
N
.
K
r
i
sh
n
a
n
,
N
.
S
.
K
e
n
k
r
e
,
S
.
N
a
n
c
y
,
a
n
d
B
.
P
.
S
i
n
g
h
,
“
T
u
mo
r
d
e
t
e
c
t
i
o
n
u
s
i
n
g
t
h
r
e
sh
o
l
d
o
p
e
r
a
t
i
o
n
i
n
M
R
I
b
r
a
i
n
i
mag
e
s,”
2
0
1
2
I
E
EE
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
C
o
m
p
u
t
i
n
g
Re
se
a
r
c
h
,
I
C
C
I
C
2
0
1
2
,
2
0
1
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
I
C
.
2
0
1
2
.
6
5
1
0
2
9
9
.
[
3
3
]
N
.
Jo
sh
i
a
n
d
S
.
Ja
i
n
,
“
A
r
o
b
u
st
a
p
p
r
o
a
c
h
f
o
r
a
p
p
l
i
c
a
t
i
o
n
o
f
mo
r
p
h
o
l
o
g
i
c
a
l
o
p
e
r
a
t
i
o
n
s
o
n
M
R
I
,
”
i
n
I
C
RI
T
O
2
0
2
0
-
I
E
EE
8
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Re
l
i
a
b
i
l
i
t
y
,
I
n
f
o
c
o
m
T
e
c
h
n
o
l
o
g
i
e
s
a
n
d
O
p
t
i
m
i
z
a
t
i
o
n
(
T
re
n
d
s
a
n
d
F
u
t
u
re
D
i
rec
t
i
o
n
s)
,
2
0
2
0
,
p
p
.
5
8
5
–
5
8
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
R
I
TO
4
8
8
7
7
.
2
0
2
0
.
9
1
9
8
0
1
1
.
[
3
4
]
P
.
C
h
l
a
p
,
H
.
M
i
n
,
N
.
V
a
n
d
e
n
b
e
r
g
,
J.
D
o
w
l
i
n
g
,
L
.
H
o
l
l
o
w
a
y
,
a
n
d
A
.
H
a
w
o
r
t
h
,
“
A
r
e
v
i
e
w
o
f
me
d
i
c
a
l
i
mag
e
d
a
t
a
a
u
g
me
n
t
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
f
o
r
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
l
i
c
a
t
i
o
n
s,
”
J
o
u
rn
a
l
o
f
Me
d
i
c
a
l
I
m
a
g
i
n
g
a
n
d
R
a
d
i
a
t
i
o
n
O
n
c
o
l
o
g
y
,
v
o
l
.
6
5
,
n
o
.
5
,
p
p
.
5
45
–
5
6
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
1
1
/
1
7
5
4
-
9
4
8
5
.
1
3
2
6
1
.
[
3
5
]
C
.
Z
h
a
n
g
,
W
.
T
a
v
a
n
a
p
o
n
g
,
J.
W
o
n
g
,
P
.
C
.
d
e
G
r
o
e
n
,
a
n
d
J.
H
.
O
h
,
“
R
e
a
l
d
a
t
a
a
u
g
me
n
t
a
t
i
o
n
f
o
r
me
d
i
c
a
l
i
m
a
g
e
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
L
e
c
t
u
re
N
o
t
e
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
i
n
c
l
u
d
i
n
g
s
u
b
ser
i
e
s
L
e
c
t
u
r
e
N
o
t
e
s
i
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
L
e
c
t
u
re
N
o
t
e
s
i
n
Bi
o
i
n
f
o
rm
a
t
i
c
s)
,
v
o
l
.
1
0
5
5
2
L
N
C
S
,
p
p
.
6
7
–
7
6
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
3
1
9
-
6
7
5
3
4
-
3
_
8
.
[
3
6
]
K.
-
P
.
W
o
n
g
,
“
M
e
d
i
c
a
l
i
mag
e
se
g
men
t
a
t
i
o
n
:
me
t
h
o
d
s
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s
i
n
f
u
n
c
t
i
o
n
a
l
i
mag
i
n
g
,
”
H
a
n
d
b
o
o
k
o
f
Bi
o
m
e
d
i
c
a
l
I
m
a
g
e
An
a
l
y
si
s
,
p
p
.
111
–
1
8
2
,
2
0
0
7
,
d
o
i
:
1
0
.
1
0
0
7
/
0
-
306
-
4
8
6
0
6
-
7
_
3
.
[
3
7
]
T
.
P
a
v
l
i
d
i
s,
“
A
d
v
a
n
c
e
d
se
g
me
n
t
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s,”
S
t
r
u
c
t
u
r
a
l
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
,
p
p
.
9
0
–
1
2
3
,
1
9
7
7
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
6
4
2
-
8
8
3
0
4
-
0
_
5
.
[
3
8
]
D
.
L
.
P
h
a
m,
C
.
X
u
,
a
n
d
J.
L
.
P
r
i
n
c
e
,
“
C
u
r
r
e
n
t
me
t
h
o
d
s
i
n
me
d
i
c
a
l
i
ma
g
e
se
g
me
n
t
a
t
i
o
n
,
”
An
n
u
a
l
Re
v
i
e
w
o
f
Bi
o
m
e
d
i
c
a
l
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
,
n
o
.
2
0
0
0
,
p
p
.
3
1
5
–
3
3
7
,
2
0
0
0
,
d
o
i
:
1
0
.
1
1
4
6
/
a
n
n
u
r
e
v
.
b
i
o
e
n
g
.
2
.
1
.
3
1
5
.
[
3
9
]
N
.
G
o
r
d
i
l
l
o
,
E.
M
o
n
t
se
n
y
,
a
n
d
P
.
S
o
b
r
e
v
i
l
l
a
,
“
S
t
a
t
e
o
f
t
h
e
a
r
t
su
r
v
e
y
o
n
M
R
I
b
r
a
i
n
t
u
mo
r
se
g
me
n
t
a
t
i
o
n
,
”
M
a
g
n
e
t
i
c
R
e
so
n
a
n
c
e
I
m
a
g
i
n
g
,
v
o
l
.
3
1
,
n
o
.
8
,
p
p
.
1
4
2
6
–
1
4
3
8
,
O
c
t
.
2
0
1
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
mr
i
.
2
0
1
3
.
0
5
.
0
0
2
.
[
4
0
]
S
.
S
.
A
l
-
a
mr
i
,
N
.
V
K
a
l
y
a
n
k
a
r
,
a
n
d
K
.
S
.
D
.
,
“
I
mag
e
seg
me
n
t
a
t
i
o
n
b
y
u
si
n
g
t
h
r
e
sh
o
l
d
t
e
c
h
n
i
q
u
e
s,”
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
,
n
o
.
5
,
p
p
.
8
3
–
8
6
,
2
0
1
0
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
a
r
x
i
v
.
o
r
g
/
a
b
s/
1
0
0
5
.
4
0
2
0
.
[
4
1
]
D
.
P
a
n
d
a
a
n
d
A
.
R
o
se
n
f
e
l
d
,
“
I
mag
e
s
e
g
me
n
t
a
t
i
o
n
b
y
p
i
x
e
l
c
l
a
ssi
f
i
c
a
t
i
o
n
i
n
(
g
r
a
y
l
e
v
e
l
,
e
d
g
e
v
a
l
u
e
)
sp
a
c
e
,
”
I
E
EE
T
ra
n
sa
c
t
i
o
n
s o
n
C
o
m
p
u
t
e
rs
,
v
o
l
.
C
–
2
7
,
n
o
.
9
,
p
p
.
8
7
5
–
8
7
9
,
1
9
7
8
,
d
o
i
:
1
0
.
1
1
0
9
/
T
C
.
1
9
7
8
.
1
6
7
5
2
0
8
.
[4
2]
L
.
L
a
l
a
o
u
i
a
n
d
T
.
M
o
h
a
m
a
d
i
,
“
A
c
o
mp
a
r
a
t
i
v
e
s
t
u
d
y
o
f
i
mag
e
r
e
g
i
o
n
-
b
a
s
e
d
se
g
me
n
t
a
t
i
o
n
a
l
g
o
r
i
t
h
m
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
4
,
n
o
.
6
,
2
0
1
3
,
d
o
i
:
1
0
.
1
4
5
6
9
/
i
j
a
c
sa
.
2
0
1
3
.
0
4
0
6
2
7
.
[
4
3
]
T
.
M
c
I
n
e
r
n
e
y
a
n
d
D
.
T
e
r
z
o
p
o
u
l
o
s,
D
e
f
o
rm
a
b
l
e
m
o
d
e
l
s.
H
a
n
d
b
o
o
k
o
f
m
e
d
i
c
a
l
i
m
a
g
i
n
g
p
r
o
c
e
ssi
n
g
a
n
d
a
n
a
l
y
si
s
.
N
e
w
Y
o
r
k
:
A
c
a
d
e
mi
c
,
2
0
0
0
.
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:
2088
-
8708
A
n
a
p
p
r
o
a
ch
f
o
r
p
r
ed
ictin
g
b
r
a
in
tu
mo
r
w
ith
ma
ch
in
e
lea
r
n
in
g
tech
n
iq
u
es (
P
S
R
B
S
h
a
s
h
a
n
k)
4339
[
4
4
]
I
.
G
u
y
o
n
a
n
d
A
.
El
i
sse
e
f
l
,
“
A
n
i
n
t
r
o
d
u
c
t
i
o
n
t
o
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
,
”
S
t
u
d
i
e
s
i
n
Fu
zz
i
n
e
ss
a
n
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
0
7
,
p
p
.
1
–
2
5
,
2
0
0
6
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
5
4
0
-
3
5
4
8
8
-
8
_
1
.
[
4
5
]
D
.
Z
h
a
n
g
,
“
C
o
l
o
r
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
,
”
i
n
F
u
n
d
a
m
e
n
t
a
l
s
o
f
I
m
a
g
e
D
a
t
a
Mi
n
i
n
g
.
T
e
x
t
s
i
n
C
o
m
p
u
t
e
r S
c
i
e
n
c
e
,
S
p
r
i
n
g
e
r
,
C
h
a
m,
2
0
2
1
,
p
p
.
5
9
–
9
9
.
[
4
6
]
R
.
B
a
l
a
,
“
S
u
r
v
e
y
o
n
t
e
x
t
u
r
e
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
me
t
h
o
d
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
n
g
i
n
e
e
r
i
n
g
S
c
i
e
n
c
e
a
n
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
7
,
n
o
.
4
,
p
p
.
1
0
3
7
5
–
1
0
3
7
7
,
2
0
1
7
.
[
4
7
]
W
.
K
.
M
u
t
l
a
g
,
S
.
K
.
A
l
i
,
Z
.
M
.
A
y
d
a
m,
a
n
d
B
.
H
.
T
a
h
e
r
,
“
F
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
me
t
h
o
d
s:
a
r
e
v
i
e
w
,
”
J
o
u
r
n
a
l
o
f
P
h
y
si
c
s:
C
o
n
f
e
re
n
c
e
S
e
r
i
e
s
,
v
o
l
.
1
5
9
1
,
n
o
.
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
1
5
9
1
/
1
/
0
1
2
0
2
8
.
[
4
8
]
M
.
Y
a
n
g
,
K
.
K
p
a
l
ma,
a
n
d
J.
R
o
n
si
n
,
“
A
su
r
v
e
y
o
f
sh
a
p
e
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s,”
Pa
t
t
e
rn
R
e
c
o
g
n
i
t
i
o
n
T
e
c
h
n
i
q
u
e
s,
T
e
c
h
n
o
l
o
g
y
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
p
p
.
4
3
–
9
0
,
2
0
0
8
.
[
4
9
]
M
.
G
.
P
e
c
h
t
,
“
P
r
o
g
n
o
st
i
c
s
a
n
d
h
e
a
l
t
h
m
a
n
a
g
e
me
n
t
o
f
e
l
e
c
t
r
o
n
i
c
s,
”
P
ro
g
n
o
st
i
c
s
a
n
d
H
e
a
l
t
h
M
a
n
a
g
e
m
e
n
t
o
f
E
l
e
c
t
r
o
n
i
c
s
,
p
p
.
1
–
3
1
5
,
2
0
0
8
,
d
o
i
:
1
0
.
1
0
0
2
/
9
7
8
0
4
7
0
3
8
5
8
4
5
.
[
5
0
]
N
.
T
h
o
mas
R
i
n
c
y
a
n
d
R
.
G
u
p
t
a
,
“
A
su
r
v
e
y
o
n
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
a
n
d
i
t
s
t
e
c
h
n
i
q
u
e
s,
”
i
n
2
0
2
0
I
E
EE
I
n
t
e
rn
a
t
i
o
n
a
l
S
t
u
d
e
n
t
s’
C
o
n
f
e
r
e
n
c
e
o
n
El
e
c
t
ri
c
a
l
,
El
e
c
t
r
o
n
i
c
s
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
S
C
E
EC
S
2
0
2
0
,
2
0
2
0
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
S
C
EEC
S
4
8
3
9
4
.
2
0
2
0
.
1
9
0
.
[
5
1
]
V
.
N
a
st
e
sk
i
,
“
A
n
o
v
e
r
v
i
e
w
o
f
t
h
e
su
p
e
r
v
i
se
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
me
t
h
o
d
s,
”
H
o
ri
z
o
n
s
.
B
,
v
o
l
.
4
,
p
p
.
5
1
–
6
2
,
2
0
1
7
,
d
o
i
:
1
0
.
2
0
5
4
4
/
h
o
r
i
z
o
n
s.
b
.
0
4
.
1
.
1
7
.
p
0
5
.
[
5
2
]
H
.
B
h
a
v
sar
a
n
d
A
.
G
a
n
a
t
r
a
,
“
A
c
o
mp
a
r
a
t
i
v
e
st
u
d
y
o
f
t
r
a
i
n
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
su
p
e
r
v
i
se
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
S
o
f
t
C
o
m
p
u
t
i
n
g
a
n
d
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
,
n
o
.
4
,
p
p
.
7
4
–
8
1
,
2
0
1
2
.
[
5
3
]
P
.
S
i
n
g
h
,
“
U
n
su
p
e
r
v
i
se
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
L
e
a
rn
Py
S
p
a
r
k
,
p
p
.
1
6
1
–
1
8
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
1
-
4
8
4
2
-
4
9
6
1
-
1
_
7
.
[
5
4
]
H
.
H
a
b
i
b
,
A
.
M
e
h
mo
o
d
,
T
.
N
a
z
i
r
,
M
.
N
a
w
a
z
,
M
.
M
a
so
o
d
,
a
n
d
R
.
M
a
h
u
m,
“
B
r
a
i
n
t
u
mo
r
se
g
me
n
t
a
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
I
C
AEM
2
0
2
1
-
2
0
2
1
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ap
p
l
i
e
d
a
n
d
E
n
g
i
n
e
e
ri
n
g
M
a
t
h
e
m
a
t
i
c
s,
Pr
o
c
e
e
d
i
n
g
s
,
2
0
2
1
,
p
p
.
1
3
–
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
E
M
5
3
5
5
2
.
2
0
2
1
.
9
5
4
7
0
8
4
.
[
5
5
]
A
.
M
i
s
h
r
a
,
M
.
T
i
w
a
r
i
,
J.
M
i
s
h
r
a
,
a
n
d
B
.
T
.
H
u
n
g
,
“
B
r
a
i
n
t
u
mo
r
se
g
me
n
t
a
t
i
o
n
o
f
M
R
i
mag
e
s
u
si
n
g
S
V
M
a
n
d
f
u
z
z
y
c
l
a
ssi
f
i
e
r
i
n
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
Me
a
su
r
e
m
e
n
t
:
S
e
n
s
o
rs
,
p
p
.
8
1
–
1
1
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
99
-
1
9
4
9
-
9
_
5
.
[
5
6
]
N
.
C
h
a
v
a
n
,
B
.
D
.
Ja
d
h
a
v
,
a
n
d
P
.
M
.
P
a
t
i
l
,
“
D
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
b
r
a
i
n
t
u
mo
r
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
1
2
,
n
o
.
8
,
p
p
.
4
8
–
5
3
,
2
0
1
5
.
[
5
7
]
P
.
Jy
o
t
h
i
a
n
d
R
.
A
.
S
i
n
g
h
,
“
A
c
o
mp
a
r
i
so
n
s
t
u
d
y
o
f
v
a
r
i
o
u
s
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
s
f
o
r
c
l
a
ssi
f
y
i
n
g
t
u
mo
r
s
i
n
b
r
a
i
n
M
R
I
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
8
3
,
n
o
.
4
7
,
p
p
.
2
8
–
3
2
,
2
0
2
2
,
d
o
i
:
1
0
.
5
1
2
0
/
i
j
c
a
2
0
2
2
9
2
1
8
7
5
.
[
5
8
]
P
.
A
.
T
h
a
k
u
r
,
“
B
r
a
i
n
t
u
mo
r
se
g
me
n
t
a
t
i
o
n
u
si
n
g
k
-
me
a
n
s
c
l
u
st
e
r
i
n
g
a
l
g
o
r
i
t
h
m,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
f
o
r
Re
s
e
a
r
c
h
i
n
Ap
p
l
i
e
d
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
0
,
n
o
.
2
,
p
p
.
1
–
8
,
2
0
2
2
,
d
o
i
:
1
0
.
2
2
2
1
4
/
i
j
r
a
se
t
.
2
0
2
2
.
4
0
1
1
2
.
[
5
9
]
A
.
K
.
M
a
n
d
l
e
,
S
.
P
.
S
a
h
u
,
a
n
d
G
.
G
u
p
t
a
,
“
B
r
a
i
n
t
u
mo
r
se
g
me
n
t
a
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
i
n
M
R
I
u
si
n
g
c
l
u
st
e
r
i
n
g
a
n
d
K
e
r
n
e
l
-
b
a
se
d
S
V
M
,
”
Bi
o
m
e
d
i
c
a
l
a
n
d
P
h
a
rm
a
c
o
l
o
g
y
J
o
u
rn
a
l
,
v
o
l
.
1
5
,
n
o
.
2
,
p
p
.
6
9
9
–
7
1
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
3
0
0
5
/
b
p
j
/
2
4
0
9
.
[
6
0
]
P
.
K
a
u
s
h
i
k
a
n
d
R
.
R
a
t
a
n
,
“
B
r
a
i
n
t
u
m
o
r
se
g
me
n
t
a
t
i
o
n
&
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
o
p
t
i
mi
z
e
d
k
-
me
a
n
s
(
S
F
L
A
)
a
n
d
e
n
s
e
mb
l
e
l
e
a
r
n
i
n
g
,
”
J
o
u
rn
a
l
o
f
Ph
a
rm
a
c
e
u
t
i
c
a
l
N
e
g
a
t
i
v
e
Re
su
l
t
s
,
v
o
l
.
1
3
,
n
o
.
S
0
1
,
2
0
2
2
,
d
o
i
:
1
0
.
4
7
7
5
0
/
p
n
r
.
2
0
2
2
.
1
3
.
s
0
1
.
2
3
5
.
[
6
1
]
E.
G
h
a
f
o
u
r
i
a
n
,
F
.
S
a
ma
d
i
f
a
m
,
H
.
F
a
d
a
v
i
a
n
,
P
.
Je
r
f
i
C
a
n
a
t
a
l
a
y
,
A
.
R
.
T
a
j
a
l
l
y
,
a
n
d
S
.
C
h
a
n
n
u
msi
n
,
“
A
n
e
n
se
mb
l
e
mo
d
e
l
f
o
r
t
h
e
d
i
a
g
n
o
si
s o
f
b
r
a
i
n
t
u
mo
r
s t
h
r
o
u
g
h
M
R
I
s,”
D
i
a
g
n
o
s
t
i
c
s
,
v
o
l
.
1
3
,
n
o
.
3
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
d
i
a
g
n
o
st
i
c
s1
3
0
3
0
5
6
1
.
[
6
2
]
B
.
B
.
P
a
t
t
a
n
a
i
k
,
K
.
A
n
i
t
h
a
,
S
.
R
a
t
h
o
r
e
,
P
.
B
i
sw
a
s,
P
.
K
.
S
e
t
h
y
,
a
n
d
S
.
K
.
B
e
h
e
r
a
,
“
B
r
a
i
n
t
u
mo
r
mag
n
e
t
i
c
r
e
so
n
a
n
c
e
i
mag
e
s
c
l
a
ssi
f
i
c
a
t
i
o
n
b
a
se
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
p
a
r
a
d
i
g
ms,”
Ws
p
o
l
c
zes
n
a
O
n
k
o
l
o
g
i
a
,
v
o
l
.
2
6
,
n
o
.
4
,
p
p
.
2
6
8
–
2
7
4
,
2
0
2
2
,
d
o
i
:
1
0
.
5
1
1
4
/
w
o
.
2
0
2
3
.
1
2
4
6
1
2
.
[
6
3
]
G
.
K
a
u
r
a
n
d
A
.
O
b
e
r
o
i
,
“
N
a
i
v
e
B
a
y
e
s
c
l
a
ssi
f
i
e
r
f
o
r
b
r
a
i
n
t
u
mo
r
d
e
t
e
c
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
ri
c
a
l
,
El
e
c
t
r
o
n
i
c
s
a
n
d
D
a
t
a
C
o
m
m
u
n
i
c
a
t
i
o
n
,
v
o
l
.
7
,
n
o
.
1
0
,
2
0
1
9
.
[
6
4
]
M
.
I
r
sh
a
d
,
N
.
M
u
h
a
mm
a
d
,
M
.
S
h
a
r
i
f
,
a
n
d
M
.
Y
a
sme
e
n
,
“
A
u
t
o
mat
i
c
se
g
men
t
a
t
i
o
n
o
f
t
h
e
l
e
f
t
v
e
n
t
r
i
c
l
e
i
n
a
c
a
r
d
i
a
c
M
R
s
h
o
r
t
a
x
i
s
i
mag
e
u
s
i
n
g
b
l
i
n
d
mo
r
p
h
o
l
o
g
i
c
a
l
o
p
e
r
a
t
i
o
n
,
”
E
u
r
o
p
e
a
n
Ph
y
si
c
a
l
J
o
u
r
n
a
l
Pl
u
s
,
v
o
l
.
1
3
3
,
n
o
.
4
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
4
0
/
e
p
j
p
/
i
2
0
1
8
-
1
1
9
4
1
-
0.
[
6
5
]
J.
Ji
a
n
g
,
Y
.
W
u
,
M
.
H
u
a
n
g
,
W
.
Y
a
n
g
,
W
.
C
h
e
n
,
a
n
d
Q
.
F
e
n
g
,
“
3
D
b
r
a
i
n
t
u
mo
r
se
g
m
e
n
t
a
t
i
o
n
i
n
m
u
l
t
i
mo
d
a
l
M
R
i
mag
e
s
b
a
se
d
o
n
l
e
a
r
n
i
n
g
p
o
p
u
l
a
t
i
o
n
-
a
n
d
p
a
t
i
e
n
t
-
s
p
e
c
i
f
i
c
f
e
a
t
u
r
e
se
t
s,”
C
o
m
p
u
t
e
ri
ze
d
Me
d
i
c
a
l
I
m
a
g
i
n
g
a
n
d
G
r
a
p
h
i
c
s
,
v
o
l
.
3
7
,
n
o
.
7
–
8
,
p
p
.
5
1
2
–
5
2
1
,
2
0
1
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
me
d
i
mag
.
2
0
1
3
.
0
5
.
0
0
7
.
[
6
6
]
Z
.
L
i
u
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
b
a
se
d
b
r
a
i
n
t
u
mo
r
se
g
me
n
t
a
t
i
o
n
:
a
s
u
r
v
e
y
,
”
C
o
m
p
l
e
x
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
,
v
o
l
.
9
,
n
o
.
1
,
p
p
.
1
0
0
1
–
1
0
2
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
0
7
4
7
-
0
2
2
-
0
0
8
1
5
-
5.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
PS
RB
S
h
a
sh
a
n
k
re
se
a
rc
h
sc
h
o
lar
in
th
e
D
e
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
,
S
RM
In
stit
u
te
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
Ka
tt
a
n
k
u
lath
u
r,
Ch
e
n
n
a
i,
I
n
d
ia.
His
re
se
a
rc
h
in
tere
sts
in
c
l
u
d
e
th
e
a
p
p
li
c
a
ti
o
n
s
o
f
a
rti
f
icia
l
in
tell
ig
e
n
c
e
,
im
a
g
e
p
ro
c
e
ss
in
g
,
a
n
d
p
a
tt
e
rn
re
c
o
g
n
it
i
o
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sh
a
sh
a
n
k
m
o
u
li
3
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
4
,
A
u
g
u
s
t
20
25
:
4
3
3
2
-
4340
4340
L
.
An
a
n
d
a
ss
o
c
iate
p
r
o
f
e
ss
o
r
,
De
p
a
rtm
e
n
t
o
f
Ne
tw
o
rk
in
g
a
n
d
Co
m
m
u
n
ica
ti
o
n
s,
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
lo
g
y
,
S
RM
In
stit
u
te
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
Ka
tt
a
n
k
u
lath
u
r,
Ch
e
n
n
a
i,
In
d
ia,
h
is
re
se
a
rc
h
i
n
tere
sts
in
c
l
u
d
e
w
irele
ss
n
e
tw
o
rk
s,
b
ig
d
a
ta
a
n
a
ly
ti
c
s,
m
a
c
h
in
e
lea
rn
in
g
,
d
e
e
p
lea
rn
in
g
Io
T
,
De
v
Op
s,
b
ig
d
a
ta
in
Ha
d
o
o
p
a
n
d
sp
a
rk
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
n
a
n
d
l@sr
m
ist.
e
d
u
.
in
.
R
.
Pi
tc
h
a
i
a
ss
o
c
iate
p
ro
f
e
s
so
r
in
th
e
D
e
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
,
B
V
Ra
ju
I
n
stit
u
te
o
f
Tec
h
n
o
lo
g
y
,
Na
rs
a
p
u
r,
M
e
d
a
k
,
T
e
lan
g
a
n
a
,
In
d
ia
.
Re
c
e
iv
e
d
th
e
B.
T
e
c
h
a
n
d
M
.
T
e
c
h
d
e
g
re
e
s
i
n
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
in
e
e
ri
n
g
,
so
f
t
w
a
re
e
n
g
in
e
e
rin
g
in
2
0
0
5
a
n
d
2
0
0
8
r
e
sp
e
c
ti
v
e
ly
.
His
re
se
a
r
c
h
in
tere
sts
in
c
lu
d
e
so
f
t
w
a
re
e
n
g
in
e
e
rin
g
,
c
lo
u
d
c
o
m
p
u
ti
n
g
.
He
c
a
n
b
e
C
o
n
tac
ted
a
t
e
m
a
il
:
ra
m
a
sa
m
y
.
p
@b
v
rit
.
a
c
.
in
.
Evaluation Warning : The document was created with Spire.PDF for Python.