I
nte
rna
t
io
na
l J
o
urna
l o
f
Adv
a
nces in Applie
d Science
s
(
I
J
AAS)
Vo
l.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
,
p
p
.
1
3
3
~
1
4
1
I
SS
N:
2252
-
8
8
1
4
,
DOI
:
1
0
.
1
1
5
9
1
/ijaas
.
v
1
5
.
i
1
.
pp
133
-
1
4
1
133
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
a
s
.
ia
esco
r
e.
co
m
An ensembl
e
-
ba
s
ed appro
a
ch f
o
r
b
reas
t
ca
ncer
iden
t
ificatio
n
using
ma
mm
o
g
ra
phy
Na
v
ee
n Ana
nd
a
K
um
a
r
J
o
s
e
ph
Anna
ia
h
1
,
Na
k
k
a
T
hirup
a
t
hi Ra
o
2
,
B
a
la
k
esa
v
a
Reddy
P
a
rv
a
t
ha
la
3
,
B
a
na
na
O
m
ka
r
L
a
k
s
hm
i J
a
g
a
n
4
,
B
o
da
pa
t
i V
enk
a
t
a
Ra
j
a
nn
a
5
1
S
e
n
i
o
r
D
a
t
a
E
n
g
i
n
e
e
r
,
T
-
M
o
b
i
l
e
,
T
e
x
a
s,
U
n
i
t
e
d
S
t
a
t
e
s
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
,
V
i
g
n
a
n
’
s I
n
st
i
t
u
t
e
o
f
I
n
f
o
r
ma
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
V
i
sa
k
h
a
p
a
t
n
a
m,
I
n
d
i
a
3
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
(
C
y
b
e
r
S
e
c
u
r
i
t
y
a
n
d
D
a
t
a
S
c
i
e
n
c
e
)
a
n
d
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
D
a
t
a
S
c
i
e
n
c
e
,
V
N
R
V
i
g
n
a
n
a
J
y
o
t
h
i
I
n
st
i
t
u
t
e
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
H
y
d
e
r
a
b
a
d
,
I
n
d
i
a
4
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
s E
n
g
i
n
e
e
r
i
n
g
,
V
i
g
n
a
n
’
s
I
n
st
i
t
u
t
e
o
f
I
n
f
o
r
mat
i
o
n
T
e
c
h
n
o
l
o
g
y
,
V
i
sa
k
h
a
p
a
t
n
a
m,
I
n
d
i
a
5
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
s E
n
g
i
n
e
e
r
i
n
g
,
M
LR
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
H
y
d
e
r
a
b
a
d
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ap
r
2
6
,
2
0
2
5
R
ev
is
ed
No
v
2
1
,
2
0
2
5
Acc
ep
ted
J
an
1
,
2
0
2
6
Bre
a
st
c
a
n
c
e
r
is
a
m
o
n
g
t
h
e
m
o
st
c
o
m
m
o
n
c
a
n
c
e
rs
in
wo
m
e
n
w
o
rld
wi
d
e
;
ti
m
e
ly
d
e
tec
ti
o
n
is
v
it
a
ll
y
imp
o
rt
a
n
t
fo
r
imp
r
o
v
in
g
c
h
a
n
c
e
s
o
f
su
r
v
iv
a
l.
Th
e
p
re
se
n
t
stu
d
y
e
x
a
m
in
e
s
a
n
in
n
o
v
a
ti
v
e
m
a
c
h
in
e
lea
rn
i
n
g
tec
h
n
i
q
u
e
fo
r
t
h
e
d
iag
n
o
sis
o
f
b
re
a
st
c
a
n
c
e
r
u
si
n
g
th
e
b
re
a
st
c
a
n
c
e
r
Wi
sc
o
n
sin
(
d
iag
n
o
stic
)
d
a
tas
e
t
fro
m
Ka
g
g
le
.
Th
e
d
a
tas
e
t
in
c
l
u
d
e
s
5
6
9
i
n
sta
n
c
e
s,
a
n
d
e
a
c
h
i
n
sta
n
c
e
h
a
s
3
0
a
tt
r
ib
u
tes
d
e
riv
e
d
fro
m
d
i
g
it
ize
d
fi
n
e
n
e
e
d
le
a
sp
irati
o
n
(F
N
A)
ima
g
e
s
o
f
m
a
ss
e
s
fo
u
n
d
i
n
th
e
b
re
a
st.
We
will
p
re
se
n
t
a
n
e
n
se
m
b
le
d
e
e
p
lea
rn
i
n
g
(DL)
m
o
d
e
l
f
u
sin
g
a
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
two
r
k
(
CNN
)
a
n
d
LRAlex
Ne
t
a
rc
h
it
e
c
tu
re
s
to
in
c
re
a
se
th
e
a
c
c
u
ra
c
y
a
n
d
ro
b
u
stn
e
ss
o
f
t
h
is
ty
p
e
o
f
c
a
n
c
e
r
d
iag
n
o
sis.
CNN
m
o
d
e
ls
a
re
we
ll
-
k
n
o
wn
fo
r
t
h
e
ir
p
o
we
r
to
c
a
p
t
u
re
sp
a
ti
a
l
h
iera
rc
h
ies
in
ima
g
e
d
a
ta,
a
n
d
L
RAle
x
Ne
t
is
a
sp
e
c
ialize
d
d
e
e
p
CNN
th
a
t
e
x
c
e
ls
a
t
ima
g
e
c
las
sifica
ti
o
n
d
u
e
to
it
s
d
e
p
th
a
n
d
p
a
ra
m
e
ter
o
p
ti
m
i
z
a
ti
o
n
.
In
th
is
wo
r
k
,
we
u
se
t
h
e
a
b
i
li
ty
t
o
e
x
trac
t
fe
a
tu
re
s
o
f
CNN
s
a
lo
n
g
with
th
e
su
p
e
rio
r
c
las
sifica
ti
o
n
p
e
rfo
rm
a
n
c
e
o
f
LRAlex
Ne
t
to
d
ist
in
g
u
is
h
b
e
twe
e
n
b
e
n
ig
n
a
n
d
m
a
li
g
n
a
n
t
c
a
n
c
e
rs.
T
h
e
m
o
d
e
l
will
b
e
train
e
d
a
nd
v
a
l
id
a
ted
o
n
th
e
c
u
ra
ted
b
re
a
st
ima
g
in
g
su
b
se
t
o
f
th
e
d
ig
it
a
l
d
a
ta
b
a
se
fo
r
sc
re
e
n
in
g
m
a
m
m
o
g
ra
p
h
y
(
CBI
S
-
DD
S
M
)
d
a
tas
e
t
,
a
n
d
p
e
rf
o
rm
a
n
c
e
will
b
e
e
v
a
lu
a
ted
u
sin
g
se
n
siti
v
it
y
,
a
c
c
u
ra
c
y
,
sp
e
c
i
ficity
,
a
n
d
t
h
e
a
re
a
u
n
d
e
r
th
e
c
u
r
v
e
(AU
C)
fo
r
t
h
e
re
c
e
iv
e
r
o
p
e
ra
ti
n
g
c
h
a
ra
c
teristic.
Th
e
re
su
l
ts
sh
o
w
t
h
a
t
t
h
e
e
n
se
m
b
le
CNN
-
LRAlex
Ne
t
m
o
d
e
l
a
c
h
iev
e
d
su
p
e
ri
o
r
a
c
c
u
ra
c
y
f
o
r
b
re
a
st
c
a
n
c
e
r
p
re
d
ictio
n
wh
e
n
c
o
m
p
a
re
d
to
trad
it
io
n
a
l
m
a
c
h
in
e
lea
rn
i
n
g
m
e
th
o
d
s.
K
ey
w
o
r
d
s
:
B
r
ea
s
t c
an
ce
r
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
Fin
e
n
ee
d
le
asp
ir
atio
n
Kag
g
le
Par
am
eter
o
p
tim
izatio
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
:
Nak
k
a
T
h
ir
u
p
ath
i Rao
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
,
Vig
n
an
’
s
I
n
s
titu
te
o
f
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
Du
v
v
ad
a,
Vis
ak
h
a
p
atn
am
,
A
n
d
h
r
a
Pra
d
esh
5
3
0
0
4
6
,
I
n
d
ia
E
m
ail:
n
ak
k
ath
ir
u
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
B
r
ea
s
t
ca
n
ce
r
is
am
o
n
g
th
e
m
o
s
t
co
m
m
o
n
ca
n
ce
r
s
in
wo
m
en
ar
o
u
n
d
th
e
wo
r
ld
.
I
t
is
ess
en
tial
to
d
etec
t
an
d
tr
ea
tm
en
t
o
f
b
r
ea
s
t
ca
n
ce
r
at
ea
r
ly
is
cr
u
cial
to
in
cr
ea
s
in
g
s
u
r
v
iv
al
with
b
r
ea
s
t
ca
n
ce
r
an
d
d
ec
r
ea
s
in
g
th
e
b
u
r
d
en
o
f
d
i
s
ea
s
e.
T
r
ad
itio
n
al
s
cr
ee
n
in
g
m
o
d
alities
,
s
u
ch
as
m
am
m
o
g
r
ap
h
y
,
u
ltra
s
o
u
n
d
,
m
ag
n
etic
r
eso
n
an
ce
im
ag
in
g
(
MRI)
,
an
d
b
io
p
s
y
,
ar
e
s
till
u
s
ef
u
l
in
th
e
id
en
tific
atio
n
o
f
m
alig
n
an
t
tis
s
u
es,
b
u
t
ea
ch
o
f
th
ese
im
ag
in
g
s
tu
d
ies
h
a
s
lim
itatio
n
s
r
eg
ar
d
in
g
th
eir
s
en
s
itiv
ity
,
s
p
ec
if
icity
,
a
n
d
o
v
er
all
ac
cu
r
ac
y
[
1
]
–
[
3
]
.
Fo
r
e
x
am
p
le,
m
am
m
o
g
r
ap
h
y
m
ay
m
is
s
m
alig
n
an
t
tu
m
o
r
s
o
r
y
ield
a
f
alse
p
o
s
itiv
e
th
at
r
esu
lt
s
in
a
n
u
n
n
ec
ess
ar
y
in
ter
v
e
n
tio
n
.
Mo
r
eo
v
er
,
th
e
in
te
r
p
r
etatio
n
o
f
im
ag
in
g
s
tu
d
ies
r
eq
u
ir
es
a
tr
a
in
ed
s
p
ec
ialis
t,
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
c
h
2
0
2
6
:
133
-
1
4
1
134
o
f
ten
v
er
y
s
lo
w,
is
s
u
b
jectiv
e,
an
d
is
o
p
en
to
h
u
m
an
er
r
o
r
.
D
ee
p
lear
n
in
g
(
DL
)
,
a
ty
p
e
o
f
ar
tific
ial
in
tellig
en
ce
(
AI
),
h
as
d
em
o
n
s
tr
ated
t
o
b
e
a
v
alid
an
d
r
eliab
le
to
o
l
f
o
r
i
m
p
licatin
g
an
d
id
en
tif
y
in
g
b
r
ea
s
t
ca
n
ce
r
.
Usi
n
g
lar
g
e
d
atasets
,
DL
alg
o
r
ith
m
s
ca
n
id
en
tif
y
p
atter
n
s
an
d
f
ea
tu
r
es
th
at
m
ay
n
o
t
b
e
p
r
o
m
in
en
t
wh
en
v
iewe
d
b
y
a
h
u
m
an
o
b
s
er
v
er
t
o
im
p
r
o
v
e
d
etec
tio
n
ac
cu
r
ac
y
wh
ile
d
ec
r
e
asin
g
th
e
tim
e
r
eq
u
ir
ed
f
o
r
d
i
ag
n
o
s
is
.
As
a
r
esu
lt
,
DL
ap
p
r
o
a
ch
es
ar
e
e
n
ter
in
g
th
e
b
r
ea
s
t
ca
n
ce
r
d
etec
tio
n
s
y
s
tem
s
p
ac
e
to
ass
is
t
in
th
e
ad
v
a
n
ce
m
en
t
o
f
im
p
r
o
v
em
e
n
ts
an
d
,
i
n
s
o
m
e
c
ases
,
ex
ce
ed
in
g
tr
ad
itio
n
al
ap
p
r
o
ac
h
es.
I
f
b
r
ea
s
t
ca
n
ce
r
is
i
d
en
tifie
d
at
ea
r
lier
tim
es a
n
d
s
tag
es,
th
e
b
r
ea
s
t c
a
n
ce
r
s
u
r
v
iv
al
r
ates a
n
d
tr
ea
tm
e
n
t p
r
io
r
to
ca
n
ce
r
m
etastas
is
[
4
]
.
DL
alg
o
r
ith
m
s
tr
ain
ed
o
n
la
r
g
e
d
atasets
o
f
m
am
m
o
g
r
am
s
an
d
o
th
er
im
a
g
in
g
m
o
d
ali
ties
h
av
e
g
r
ea
t
p
r
o
m
is
e
f
o
r
r
eso
lv
in
g
th
ese
ch
allen
g
es,
lo
wer
in
g
f
alse
-
p
o
s
itiv
e
r
ates,
an
d
i
m
p
r
o
v
i
n
g
d
iag
n
o
s
tic
ac
cu
r
ac
y
[
5
]
–
[
8
]
.
Fo
r
b
r
ea
s
t
c
an
ce
r
d
ia
g
n
o
s
is
,
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NN
s
)
ar
e
g
en
er
ally
tr
ain
ed
o
n
lar
g
e
d
atasets
o
f
m
am
m
o
g
r
a
m
s
,
MRIs,
o
r
u
ltra
s
o
u
n
d
im
ag
es.
T
h
e
e
n
s
em
b
le
C
NN
-
L
R
Alex
Net
m
o
d
el
is
d
ev
elo
p
e
d
to
b
e
u
s
er
-
f
r
ien
d
l
y
an
d
r
o
b
u
s
t
f
o
r
r
ea
l
-
life
p
r
a
ctice
an
d
tr
ain
ed
o
n
th
e
c
u
r
a
ted
b
r
ea
s
t
im
ag
in
g
s
u
b
s
et
o
f
th
e
d
ig
ital d
atab
ase
f
o
r
s
cr
ee
n
in
g
m
am
m
o
g
r
a
p
h
y
(
C
B
I
S
-
DD
SM
)
can
ce
r
d
ataset
f
r
o
m
Kag
g
le
,
wh
ich
was c
r
ea
ted
u
s
in
g
d
ig
itized
f
in
e
n
ee
d
le
asp
ir
atio
n
(
FNA
)
f
ea
tu
r
es th
at
ar
e
wid
ely
u
s
ed
in
cli
n
ical
p
r
ac
tice.
T
h
e
co
n
tr
i
b
u
tio
n
s
f
r
o
m
th
e
c
u
r
r
en
t p
r
o
p
o
s
ed
wo
r
k
in
t
h
e
ar
ti
cle
ar
e:
i)
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
co
m
b
in
es
im
p
r
o
v
e
m
en
ts
in
ad
v
an
ce
d
f
ea
tu
r
e
e
x
tr
ac
tio
n
(
C
NN)
an
d
class
if
icatio
n
(
L
R
Alex
Net)
,
with
an
em
p
h
asis
o
n
b
in
ar
y
d
is
tin
ctio
n
(
b
en
ig
n
/m
alig
n
a
n
t)
,
wh
ich
is
i
m
p
o
r
tan
t
f
o
r
clin
ical
d
ec
is
io
n
-
m
ak
in
g
ac
r
o
s
s
d
if
f
er
en
t ty
p
es o
f
tis
s
u
e
an
d
s
am
p
le
co
llectio
n
s
.
ii)
T
h
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
p
er
f
o
r
m
s
v
er
y
well,
ac
h
iev
in
g
an
ac
c
u
r
ac
y
o
f
9
6
.
4
%
u
s
in
g
a
r
elativ
ely
s
tan
d
ar
d
ized
d
ataset,
an
d
s
h
o
ws
p
r
o
m
is
e
f
o
r
u
s
e
in
m
o
r
e
s
itu
atio
n
s
with
less
d
ep
en
d
e
n
ce
o
n
lar
g
e,
an
n
o
tated
im
a
g
e
d
atasets
.
iii)
Data
p
r
ep
r
o
ce
s
s
in
g
,
au
g
m
e
n
tatio
n
,
an
d
h
y
p
er
p
ar
a
m
eter
o
p
tim
izatio
n
en
s
u
r
e
th
e
m
o
d
e
l
is
r
e
s
ilien
t
ag
ain
s
t o
v
er
f
itti
n
g
a
n
d
p
o
ten
ti
ally
ad
ap
tab
le
to
d
if
f
er
e
n
t p
o
p
u
latio
n
im
ag
in
g
s
ce
n
ar
io
s
.
iv
)
T
h
e
m
o
d
el
ad
v
a
n
ce
s
p
r
ac
tic
al
ap
p
licatio
n
an
d
ea
r
l
y
s
cr
ee
n
in
g
in
less
-
r
eso
u
r
ce
d
s
ettin
g
s
to
m
ak
e
au
to
m
ated
b
r
ea
s
t c
an
ce
r
d
etec
tio
n
m
o
r
e
ac
ce
s
s
ib
le
an
d
r
elia
b
le
th
an
s
p
ec
if
ic
DL
m
o
d
els.
T
h
e
b
r
e
ast
ca
n
ce
r
im
ag
es
with
ca
n
ce
r
o
u
s
tis
s
u
es
h
ig
h
lig
h
ted
in
r
ed
a
re
s
h
o
wn
in
Fig
u
r
e
1
.
T
h
e
m
ain
r
ea
s
o
n
f
o
r
co
n
d
u
ctin
g
th
e
cu
r
r
en
t
m
o
d
el
ex
p
er
im
en
tatio
n
is
th
e
u
r
g
en
t
n
ee
d
to
f
in
d
a
b
etter
id
en
tific
atio
n
m
o
d
el
f
o
r
b
r
ea
s
t
ca
n
ce
r
s
eg
m
en
tatio
n
an
d
class
if
icatio
n
.
A
d
is
ea
s
e
th
at
h
as
a
h
u
g
e
ef
f
ec
t
o
n
th
e
h
ea
lth
an
d
f
in
an
cial
s
tab
ilit
y
o
f
m
an
y
wo
m
en
ar
o
u
n
d
th
e
wo
r
ld
.
E
v
e
n
th
o
u
g
h
m
ed
ical
tech
n
o
lo
g
y
h
as
b
ec
o
m
e
m
o
r
e
ad
v
an
ce
d
,
it
is
s
t
ill
v
er
y
im
p
o
r
tan
t
to
id
en
tify
p
atien
ts
at
an
ea
r
ly
ag
e
o
r
s
tag
e
to
im
p
r
o
v
e
th
eir
ch
an
ce
s
o
f
s
u
r
v
iv
al
an
d
th
e
way
th
ey
ar
e
tr
ea
ted
.
Sti
ll,
th
e
ex
is
t
in
g
m
eth
o
d
s
o
f
d
iag
n
o
s
in
g
b
r
ea
s
t
ca
n
ce
r
o
f
ten
ar
en
'
t
v
er
y
ac
cu
r
ate
o
r
e
f
f
ec
tiv
e,
wh
ic
h
ca
n
lead
to
m
is
s
ed
o
r
late
d
iag
n
o
s
es
[
9
]
–
[
1
1
]
.
Fig
u
r
e
1
.
B
r
ea
s
t c
an
ce
r
im
a
g
e
s
with
ca
n
ce
r
o
u
s
tis
s
u
es h
ig
h
lig
h
ted
in
r
ed
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
R
esear
ch
o
n
b
r
ea
s
t
ca
n
ce
r
d
etec
tio
n
is
p
ar
ticu
lar
ly
r
elev
an
t
s
in
ce
it
i
s
th
e
m
o
s
t
co
m
m
o
n
ly
d
iag
n
o
s
ed
n
eo
p
lasi
a
wo
r
ld
wid
e
,
esp
ec
i
ally
in
wo
m
en
.
E
ar
ly
d
etec
tio
n
g
r
ea
tly
in
cr
ea
s
es
th
e
ef
f
icac
y
o
f
tr
ea
tm
en
t
o
u
tco
m
es
an
d
s
u
r
v
iv
al
r
ates,
th
u
s
ju
s
tify
in
g
th
e
n
ec
ess
ity
f
o
r
m
o
r
e
a
d
v
an
ce
d
s
cr
ee
n
in
g
m
eth
o
d
s
[
1
2
]
,
[
1
3
]
.
C
NNs
h
av
e
p
r
o
v
en
to
b
e
v
e
r
y
ef
f
ec
tiv
e
in
d
etec
tin
g
p
atter
n
s
in
m
a
m
m
o
g
r
ap
h
y
,
h
is
to
p
a
th
o
lo
g
y
,
an
d
FNA
im
ag
es
[
1
4
]
,
[
1
5
]
.
R
esear
ch
u
tili
zin
g
C
NN
d
esig
n
s
lik
e
R
esNet,
V
GGNe
t,
an
d
L
R
Alex
Net
h
as
s
h
o
wn
en
h
an
ce
d
d
iag
n
o
s
tic
p
r
ec
is
io
n
in
b
r
ea
s
t
ca
n
ce
r
d
etec
tio
n
.
No
twith
s
tan
d
in
g
th
e
p
r
o
g
r
ess
in
DL
m
eth
o
d
o
lo
g
ies,
o
b
s
tacle
s
p
er
s
is
t
in
g
u
a
r
an
te
ein
g
th
at
m
o
d
els
a
r
e
g
en
er
alize
d
ac
r
o
s
s
v
ar
ie
d
p
o
p
u
latio
n
s
an
d
im
ag
in
g
ap
p
ar
atu
s
[
1
6
]
.
Fu
r
th
er
m
o
r
e,
th
e
in
ter
p
r
etab
ilit
y
an
d
tr
u
s
two
r
th
in
ess
o
f
AI
-
d
r
iv
e
n
d
i
ag
n
o
s
tic
to
o
ls
ar
e
b
ec
o
m
in
g
s
ig
n
if
ican
t
ch
allen
g
es,
n
ec
ess
itatin
g
ad
d
itio
n
al
s
tu
d
y
t
o
g
u
ar
an
tee
th
at
m
o
d
els
ar
e
tr
an
s
p
ar
e
n
t
an
d
d
ep
en
d
a
b
le
in
clin
ical
en
v
ir
o
n
m
en
ts
[
1
7
]
.
T
ab
le
1
p
r
o
v
id
e
s
d
etails
o
f
ea
r
lier
wo
r
k
s
an
d
th
eir
d
etails
f
r
o
m
2
0
2
0
t
o
2
0
2
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
A
n
en
s
emb
le
-
b
a
s
ed
a
p
p
r
o
a
ch
fo
r
b
r
ea
s
t c
a
n
ce
r
id
en
tifi
ca
tio
n
…
(
N
a
ve
en
A
n
a
n
d
a
K
u
ma
r
Jo
s
ep
h
A
n
n
a
ia
h
)
135
T
ab
le
1
.
E
ar
lier
liter
atu
r
e
o
n
t
en
cu
r
r
e
n
t
to
p
ics
o
f
th
e
wo
r
k
A
u
t
h
o
r
s
M
e
t
h
o
d
o
l
o
g
y
D
a
t
a
s
e
t
(
samp
l
e
s
i
z
e
)
M
a
j
o
r
c
o
n
t
r
i
b
u
t
i
o
n
Li
mi
t
a
t
i
o
n
s
o
f
t
h
e
w
o
r
k
El
-
N
a
b
a
w
y
e
t
a
l
.
[
4
]
F
e
a
t
u
r
e
f
u
si
o
n
o
f
c
l
i
n
i
c
a
l
,
g
e
n
o
mi
c
,
a
n
d
h
i
s
t
o
p
a
t
h
o
l
o
g
i
c
a
l
d
a
t
a
w
i
t
h
DL
M
ETA
B
R
I
C
I
mp
r
o
v
e
d
s
u
b
t
y
p
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
b
y
i
n
t
e
g
r
a
t
i
n
g
mu
l
t
i
-
so
u
r
c
e
d
a
t
a
F
u
si
o
n
c
o
m
p
l
e
x
i
t
y
,
r
e
q
u
i
r
e
m
e
n
t
o
f
d
i
v
e
r
s
e
d
a
t
a
se
t
s
A
g
g
a
r
w
a
l
e
t
a
l
.
[
2
]
M
e
t
a
-
a
n
a
l
y
s
i
s
o
f
D
L
mo
d
e
l
s
i
n
m
e
d
i
c
a
l
i
ma
g
i
n
g
V
a
r
i
o
u
s
p
u
b
l
i
c
d
a
t
a
se
t
s
Est
a
b
l
i
s
h
e
d
a
p
o
o
l
e
d
a
c
c
u
r
a
c
y
b
e
n
c
h
m
a
r
k
f
o
r
D
L
a
p
p
r
o
a
c
h
e
s
H
e
t
e
r
o
g
e
n
e
i
t
y
i
n
d
a
t
a
s
e
t
q
u
a
l
i
t
y
,
l
i
mi
t
e
d
c
o
n
c
l
u
s
i
o
n
st
r
e
n
g
t
h
N
a
ssi
f
e
t
a
l
.
[
5
]
S
y
st
e
ma
t
i
c
r
e
v
i
e
w
o
f
A
I
mo
d
e
l
s
f
o
r
d
i
a
g
n
o
si
s
V
a
r
i
o
u
s (
n
o
t
sp
e
c
i
f
i
e
d
)
O
u
t
l
i
n
e
d
t
h
e
st
r
e
n
g
t
h
s
o
f
A
I
met
h
o
d
s f
o
r
b
r
e
a
s
t
c
a
n
c
e
r
d
i
a
g
n
o
si
s
C
o
m
p
a
r
i
so
n
a
c
r
o
ss
mo
d
e
l
s
/
st
u
d
i
e
s
i
s
c
h
a
l
l
e
n
g
i
n
g
A
h
ma
d
e
t
a
l
.
[
1
]
C
u
s
t
o
mi
z
e
d
A
l
e
x
N
e
t
a
n
d
S
V
M
a
p
p
l
i
e
d
t
o
mammo
g
r
a
p
h
y
D
D
S
M
(
n
o
t
sp
e
c
i
f
i
e
d
)
D
e
mo
n
st
r
a
t
e
d
e
f
f
e
c
t
i
v
e
n
e
ss
o
f
c
o
m
b
i
n
i
n
g
C
N
N
a
n
d
S
V
M
Li
mi
t
e
d
g
e
n
e
r
a
l
i
z
a
t
i
o
n
,
d
a
t
a
se
t
-
sp
e
c
i
f
i
c
o
p
t
i
m
i
z
a
t
i
o
n
Lu
o
e
t
a
l
.
[
8
]
R
e
v
i
e
w
o
f
C
N
N
,
e
n
s
e
mb
l
e
l
e
a
r
n
i
n
g
,
a
n
d
a
t
t
e
n
t
i
o
n
m
e
c
h
a
n
i
sms
M
u
l
t
i
p
l
e
mammo
g
r
a
p
h
y
d
a
t
a
se
t
s
H
i
g
h
l
i
g
h
t
e
d
D
L
m
o
d
e
l
s
o
u
t
p
e
r
f
o
r
me
d
c
o
n
v
e
n
t
i
o
n
a
l
a
p
p
r
o
a
c
h
e
s
D
L
n
e
e
d
s l
a
r
g
e
,
d
i
v
e
r
se
d
a
t
a
,
i
ss
u
e
s
w
i
t
h
i
n
t
e
r
p
r
e
t
a
b
i
l
i
t
y
,
a
n
d
c
l
i
n
i
c
a
l
u
p
t
a
k
e
Zh
a
n
g
e
t
a
l
.
[
9
]
A
d
v
a
n
c
e
d
D
L
mo
d
e
l
s
f
o
r
l
y
m
p
h
n
o
d
e
met
a
s
t
a
s
i
s
R
o
u
t
i
n
e
f
u
l
l
-
b
r
e
a
s
t
mammo
g
r
a
ms,
samp
l
e
si
z
e
En
a
b
l
e
d
l
y
m
p
h
n
o
d
e
met
a
s
t
a
s
i
s
p
r
e
d
i
c
t
i
o
n
f
r
o
m ma
m
mo
g
r
a
ms
La
c
k
s m
u
l
t
i
-
c
e
n
t
e
r
v
a
l
i
d
a
t
i
o
n
,
e
x
a
c
t
d
a
t
a
se
t
si
z
e
n
o
t
r
e
p
o
r
t
e
d
V
i
j
a
y
a
l
a
k
s
h
mi
e
t
a
l
.
[
7
]
H
y
b
r
i
d
mo
d
e
l
w
i
t
h
sh
e
a
r
l
e
t
t
r
a
n
sf
o
r
m,
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
,
b
i
d
i
r
e
c
t
i
o
n
a
l
l
o
n
g
sh
o
r
t
-
t
e
r
m
mem
o
r
y
(
B
i
LST
M
)
-
C
N
N
M
a
mm
o
g
r
a
p
h
i
c
I
mag
e
A
n
a
l
y
si
s
S
o
c
i
e
t
y
(
M
I
A
S
)
,
~
3
2
0
i
ma
g
e
s
A
c
h
i
e
v
e
d
9
7
.
1
4
%
a
c
c
u
r
a
c
y
,
c
o
m
b
i
n
i
n
g
h
a
n
d
c
r
a
f
t
e
d
a
n
d
D
L
f
e
a
t
u
r
e
s f
o
r
d
i
a
g
n
o
si
s
R
e
l
i
a
n
t
o
n
s
i
n
g
l
e
d
a
t
a
set
,
g
e
n
e
r
a
l
i
z
a
b
i
l
i
t
y
l
i
mi
t
e
d
R
a
b
a
h
e
t
a
l
.
[
1
0
]
C
N
N
-
b
a
s
e
d
mu
l
t
i
m
o
d
a
l
D
L
c
o
m
b
i
n
i
n
g
mammo
g
r
a
p
h
y
i
m
a
g
e
s
+
me
t
a
d
a
t
a
C
h
i
n
e
se
mammo
g
r
a
p
h
y
d
a
t
a
b
a
se
(
C
M
M
D
)
:
4
,
0
5
6
i
ma
g
e
s
,
1
,
7
7
5
p
a
t
i
e
n
t
s
O
u
t
p
e
r
f
o
r
m
e
d
i
m
a
g
e
-
o
n
l
y
m
o
d
e
l
s
,
a
r
e
a
u
n
d
e
r
t
h
e
c
u
r
v
e
(
A
U
C
)
8
8
.
8
7
%
f
o
r
mu
l
t
i
c
l
a
ss
l
e
s
i
o
n
su
b
t
y
p
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
D
a
t
a
s
e
t
f
o
c
u
se
d
o
n
C
h
i
n
e
se
c
o
h
o
r
t
ma
y
n
o
t
f
u
l
l
y
g
e
n
e
r
a
l
i
z
e
M
e
l
e
k
e
t
a
l
.
[
1
2
]
1
1
D
L
m
o
d
e
l
s
(
D
e
n
seNe
t
,
R
e
sN
e
t
,
V
G
G
,
e
n
s
e
m
b
l
e
s
,
C
N
N
s)
1
0
,
0
0
0
h
i
s
t
o
p
a
t
h
i
ma
g
e
s (
6
1
7
2
I
D
C
)
D
e
n
seN
e
t
2
0
1
:
8
9
.
4
%
a
c
c
u
r
a
c
y
,
9
5
.
8
%
A
U
C
f
o
r
b
e
n
i
g
n
/
ma
l
i
g
n
a
n
t
c
l
a
ss
i
f
i
c
a
t
i
o
n
D
a
t
a
i
m
b
a
l
a
n
c
e
,
d
e
p
e
n
d
e
n
c
e
o
n
h
i
g
h
-
q
u
a
l
i
t
y
i
ma
g
e
s
2
.
1
.
Resea
rc
h
g
a
p
a
nd
pro
po
s
ed
m
o
del
Fro
m
th
e
ab
o
v
e
,
ea
r
lier
e
x
is
tin
g
wo
r
k
s
o
n
m
am
m
o
g
r
a
m
an
aly
s
is
,
th
e
f
o
llo
win
g
g
ap
s
ar
e
id
en
tifie
d
f
o
r
t
h
e
cu
r
r
en
t
wo
r
k
.
Prio
r
s
tu
d
ies
d
em
o
n
s
tr
ate
t
h
e
s
tr
o
n
g
ac
cu
r
ac
y
of
tr
an
s
f
er
lear
n
in
g
,
b
u
t
m
an
y
ar
e
lim
ited
b
y
s
p
ec
ialized
d
atasets
(
e.
g
.
,
MI
AS
an
d
h
is
to
p
ath
o
lo
g
y
im
ag
es)
an
d
lack
b
r
o
ad
g
e
n
er
ali
za
b
ilit
y
to
d
iv
er
s
e,
r
ea
l
-
wo
r
ld
clin
ical
f
ea
tu
r
e
id
en
tific
atio
n
.
Mo
s
t
p
u
b
lis
h
ed
p
r
ev
io
u
s
wo
r
k
s
r
ep
o
r
t
p
er
f
o
r
m
an
ce
u
s
in
g
s
in
g
le
-
m
o
d
ality
d
ata
o
r
f
o
c
u
s
o
n
s
p
ec
if
ic
im
ag
in
g
ty
p
es
(
e.
g
.
,
m
am
m
o
g
r
a
p
h
y
a
n
d
h
is
to
p
ath
o
lo
g
y
)
,
r
ath
er
th
an
in
teg
r
atin
g
m
u
lti
-
s
o
u
r
ce
f
ea
t
u
r
e
ex
tr
ac
tio
n
f
o
r
e
n
h
an
ce
d
class
if
icatio
n
r
o
b
u
s
tn
ess
.
Sev
er
al
h
ig
h
-
ac
c
u
r
ac
y
p
r
ev
io
u
s
e
x
is
tin
g
m
o
d
els
d
e
p
en
d
o
n
v
er
y
lar
g
e
an
d
an
n
o
tated
d
atasets
,
wh
ich
ar
e
n
o
t
alwa
y
s
ac
ce
s
s
ib
le,
esp
ec
ially
in
r
eso
u
r
ce
-
co
n
s
tr
ain
ed
o
r
u
n
d
er
p
r
iv
ileg
e
d
h
ea
lth
ca
r
e
co
n
tex
ts
.
Fig
u
r
e
2
illu
s
tr
a
tes
th
e
ar
ch
itectu
r
e
o
f
th
e
p
r
o
p
o
s
ed
e
n
s
em
b
le
m
o
d
el
an
d
em
p
h
asizes
its
i
m
p
o
r
tan
ce
f
o
r
a
r
an
g
e
o
f
c
o
m
p
u
ter
v
is
io
n
a
n
d
m
ed
ical
r
esear
ch
ap
p
licatio
n
s
.
T
h
e
e
n
s
em
b
le
m
o
d
el'
s
tr
ain
in
g
an
d
test
in
g
en
tail
th
e
u
s
e
o
f
d
atasets
an
d
v
alid
atio
n
p
r
o
ce
d
u
r
es
with
th
e
g
o
al
o
f
cr
ea
tin
g
a
r
esil
ien
t
b
r
ea
s
t
ca
n
ce
r
d
etec
tio
n
m
o
d
el
.
B
y
em
p
lo
y
in
g
t
h
e
e
n
s
em
b
le
m
o
d
el
,
wh
ich
is
th
e
in
teg
r
atio
n
o
f
t
h
e
L
R
Alex
Net
m
o
d
el
in
to
b
asic
C
NN
m
o
d
el
as
th
e
ce
n
tr
al
ar
ch
itectu
r
e,
alo
n
g
with
th
e
L
ea
k
y
R
eL
U
ac
tiv
atio
n
f
u
n
ctio
n
an
d
Ad
am
o
p
tim
izer
,
th
e
cu
r
r
en
t
s
tu
d
y
ac
h
iev
es
an
ac
cu
r
ac
y
o
f
9
6
.
4
%
[
1
8
]
,
[
1
9
]
.
2
.
2
.
No
v
elt
y
o
f
t
he
pro
po
s
ed
wo
rk
T
h
e
n
o
v
elty
o
f
th
e
cu
r
r
en
t
ar
ticle
lies
in
its
in
n
o
v
ativ
e
in
teg
r
atio
n
o
f
ad
v
an
ce
d
DL
s
tr
ateg
ies
,
s
p
ec
if
ically
,
th
e
co
m
b
i
n
atio
n
o
f
a
cu
s
to
m
ized
C
NN
with
a
n
L
R
Alex
Net
ar
ch
itectu
r
e
to
cr
ea
te
an
en
s
em
b
le
m
o
d
el
th
at
ex
ce
ls
in
th
e
ch
all
en
g
in
g
task
o
f
b
r
ea
s
t
ca
n
ce
r
i
d
en
tific
atio
n
u
s
in
g
FNA
d
iag
n
o
s
tic
f
ea
tu
r
es.
T
h
e
s
u
g
g
ested
m
eth
o
d
ef
f
ec
tiv
el
y
m
er
g
es
th
e
s
p
atial
f
ea
tu
r
e
ex
tr
ac
tio
n
ca
p
ab
ilit
ies
ass
o
ciate
d
with
C
NN
s
an
d
th
e
ef
f
icien
t,
p
ar
am
eter
-
e
f
f
ec
tiv
e
class
if
icatio
n
p
r
esen
ted
b
y
a
r
ef
in
ed
m
eth
o
d
o
f
Alex
Net.
W
ith
n
o
r
m
aliza
tio
n
an
d
a
s
tan
d
ar
d
ized
r
ed
u
ctio
n
p
r
o
ce
s
s
as
well
as
in
cr
em
e
n
tal
d
ata
au
g
m
en
tatio
n
s
,
th
e
m
o
d
el
s
h
o
ws
s
tr
o
n
g
ef
f
ec
tiv
en
ess
o
n
a
s
m
all,
p
u
b
licly
ac
ce
s
s
ib
le
d
ataset
(
C
B
I
S
-
DDSM
d
ataset)
an
d
with
o
u
t
ac
ce
s
s
to
lar
g
e
m
ed
ical
im
ag
in
g
d
atasets
.
I
n
th
is
s
en
s
e,
ac
cu
r
ate
n
o
v
elty
is
two
-
f
o
ld
:
it
p
r
o
v
id
es
a
c
o
n
tr
ib
u
tio
n
to
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
c
h
2
0
2
6
:
133
-
1
4
1
136
f
o
r
ef
r
o
n
t
o
f
th
e
tech
n
o
lo
g
y
v
i
a
a
th
o
r
o
u
g
h
ly
v
alid
ated
en
s
e
m
b
le
n
etwo
r
k
s
tr
u
ctu
r
e
in
r
el
atio
n
to
cy
to
lo
g
ical
b
r
ea
s
t
ca
n
ce
r
s
cr
ee
n
in
g
,
an
d
it
ad
d
s
to
th
e
co
n
g
lo
m
er
ati
o
n
o
f
c
o
n
s
id
er
atio
n
s
to
war
d
s
th
e
tr
an
s
latio
n
o
f
tech
n
o
lo
g
y
in
to
t
h
e
p
r
ac
tical
p
ar
t o
f
p
a
r
am
ed
ical
r
o
u
tin
e
wo
r
k
.
Fig
u
r
e
2
.
T
h
e
ar
ch
itectu
r
e
o
f
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
3.
M
E
T
H
O
D
T
h
e
s
tu
d
y
em
p
lo
y
s
th
e
C
B
I
S
-
DDSM
au
g
m
en
ted
d
ataset,
wh
ich
co
n
tain
s
5
6
9
o
b
s
er
v
atio
n
s
an
d
3
0
n
u
m
er
ical
f
ea
tu
r
es
ex
tr
ac
t
ed
f
r
o
m
d
ig
itally
s
ca
n
n
ed
im
ag
es
o
f
b
r
ea
s
t
tis
s
u
e.
T
h
e
d
a
taset
is
r
an
d
o
m
ly
d
iv
id
ed
in
t
o
tr
ain
in
g
an
d
test
s
ets
at
an
8
0
:2
0
r
ati
o
f
o
r
r
ig
o
r
o
u
s
m
o
d
el
v
alid
atio
n
.
T
o
o
v
er
co
m
e
u
n
d
er
-
s
am
p
lin
g
an
d
en
h
an
ce
g
e
n
e
r
aliza
b
ilit
y
,
d
if
f
er
en
t
au
g
m
e
n
tatio
n
tech
n
iq
u
es,
in
clu
d
in
g
s
m
all
g
eo
m
etr
ic
tr
an
s
f
o
r
m
atio
n
s
an
d
r
an
d
o
m
p
er
tu
r
b
atio
n
s
,
ar
e
u
s
ed
with
th
e
tr
ain
in
g
d
atab
ase
to
m
im
ic
v
a
r
iab
ilit
y
in
clin
ical
p
r
ac
tice.
T
h
e
f
o
u
n
d
atio
n
o
f
t
h
e
m
o
d
el
ar
ch
itectu
r
e
is
a
DL
en
s
em
b
le
o
f
C
NN
an
d
L
R
Alex
Net
m
o
d
u
les.
T
h
e
C
NN
lay
er
s
ex
tr
ac
t
r
ich
f
ea
tu
r
es
an
d
p
r
o
v
id
e
a
s
eq
u
e
n
ce
o
f
co
n
v
o
lu
tio
n
a
n
d
m
ax
-
p
o
o
lin
g
lay
er
s
t
o
ca
p
t
u
r
e
s
p
atial
an
d
s
tr
u
ct
u
r
al
f
e
atu
r
es
in
th
e
im
ag
es,
w
h
ile
L
R
Alex
Net
in
cr
ea
s
es
d
ep
th
a
n
d
allo
ws
e
f
f
icien
t
p
ar
am
eter
izatio
n
f
o
r
h
ig
h
-
lev
el
class
if
icatio
n
.
Af
ter
g
o
i
n
g
th
r
o
u
g
h
s
ev
er
al
co
n
v
o
l
u
tio
n
,
ac
tiv
atio
n
,
an
d
p
o
o
lin
g
lay
e
r
s
,
th
e
f
ea
tu
r
es
ar
e
p
r
o
ce
s
s
ed
th
r
o
u
g
h
f
u
lly
co
n
n
ec
ted
lay
er
s
in
to
a
f
in
al
b
in
a
r
y
o
u
tp
u
t
(
b
en
ig
n
o
r
m
alig
n
an
t)
.
Mo
d
el
t
r
ain
in
g
i
s
co
n
d
u
cte
d
u
s
in
g
th
e
A
d
am
o
p
tim
izer
with
b
in
a
r
y
c
r
o
s
s
-
en
tr
o
p
y
lo
s
s
,
an
d
r
eg
u
lar
izatio
n
tec
h
n
iq
u
es a
r
e
im
p
lem
en
ted
as n
ee
d
ed
to
p
r
ev
en
t o
v
er
f
itti
n
g
.
3
.
1
.
Da
t
a
s
et
,
re
s
o
urce
s
,
a
nd
da
t
a
no
rma
liza
t
io
n
T
h
e
d
ataset
co
m
p
r
is
es
(
C
B
I
S
-
DDSM)
ch
ar
ac
ter
is
tics
d
er
iv
ed
f
r
o
m
d
ig
itized
p
ictu
r
es
o
f
b
r
ea
s
t
m
ass
es,
p
r
o
v
id
in
g
d
ata
f
o
r
th
e
class
if
icatio
n
o
f
tu
m
o
r
s
as
m
alig
n
an
t
o
r
b
en
ig
n
.
T
h
e
s
tu
d
y
u
s
ed
a
d
ataset
co
n
s
is
tin
g
o
f
5
6
9
s
am
p
les.
W
e
class
if
y
th
e
s
am
p
les,
o
b
tain
ed
f
r
o
m
r
ep
u
tab
le
m
ed
ical
s
o
u
r
ce
s
an
d
lib
r
ar
ies,
in
to
two
s
ep
ar
ate
c
ateg
o
r
ies:
b
en
ig
n
an
d
m
alig
n
an
t.
T
h
ey
illu
s
tr
ate
n
u
m
er
o
u
s
clin
ical
s
tates
p
er
tin
en
t
to
b
r
ea
s
t
ca
n
ce
r
id
en
tific
atio
n
.
T
h
eir
v
ar
iatio
n
s
in
tex
tu
r
e,
s
h
a
p
e
,
an
d
in
te
n
s
ity
o
f
tis
s
u
e
illu
s
tr
ate
th
e
s
p
ec
tr
u
m
o
f
b
r
ea
s
t
co
n
d
itio
n
s
e
n
co
u
n
ter
ed
in
clin
ical
e
n
v
ir
o
n
m
en
ts
[
2
0
]
,
[
2
1
]
.
I
n
th
e
c
u
r
r
e
n
t
wo
r
k
,
d
ata
n
o
r
m
aliza
tio
n
is
a
k
ey
s
tep
in
th
e
p
r
e
p
r
o
ce
s
s
in
g
wo
r
k
f
lo
w
to
f
o
r
m
co
n
s
is
te
n
cy
in
all
f
ea
tu
r
e
v
alu
es
o
b
tai
n
ed
f
r
o
m
th
e
b
r
ea
s
t
ca
n
ce
r
d
iag
n
o
s
tic
d
ataset
.
T
h
e
p
r
o
ce
s
s
o
f
d
ata
n
o
r
m
aliza
ti
o
n
r
em
o
v
es
th
e
ef
f
ec
t
o
f
d
if
f
er
en
t
v
alu
e
r
an
g
es
an
d
/o
r
d
eg
r
ee
s
o
f
in
te
n
s
ity
b
etwe
en
in
d
iv
id
u
al
s
am
p
les
f
o
r
ea
ch
f
ea
tu
r
e,
th
er
eb
y
av
o
id
i
n
g
th
e
in
f
lu
en
ce
o
f
d
is
tin
g
u
is
h
in
g
ch
ar
ac
te
r
is
tics
o
f
an
in
d
iv
id
u
al
s
am
p
le
o
v
er
in
f
lu
en
ce
s
ettin
g
s
in
th
e
t
r
ain
in
g
.
3
.
2
.
Da
t
a
a
ug
m
ent
a
t
io
n a
nd
hy
perpa
ra
m
et
er
t
un
ing
T
o
b
o
o
s
t
th
e
r
o
b
u
s
tn
ess
o
f
th
e
class
if
icat
io
n
m
o
d
el
an
d
ad
d
r
ess
p
o
ten
tial
lim
itatio
n
s
o
f
a
m
o
d
er
ate
d
ataset
s
ize,
d
ata
au
g
m
en
tatio
n
tech
n
iq
u
es
ar
e
in
co
r
p
o
r
ated
d
u
r
in
g
tr
ain
i
n
g
.
Au
g
m
en
tin
g
t
h
e
d
ataset
in
v
o
lv
es
g
en
er
atin
g
ad
d
itio
n
al,
s
y
n
th
e
tically
v
ar
ied
e
x
am
p
les
f
r
o
m
th
e
o
r
ig
in
al
f
ea
tu
r
es.
C
o
m
m
o
n
ly
em
p
lo
y
ed
au
g
m
en
tatio
n
s
tr
ateg
ies
in
clu
d
e
s
lig
h
t
r
o
tatio
n
,
f
lip
p
in
g
,
s
ca
lin
g
,
an
d
in
tr
o
d
u
ci
n
g
m
in
o
r
r
a
n
d
o
m
p
e
r
tu
r
b
atio
n
s
to
th
e
d
ata,
wh
ich
r
ef
lect
r
ea
lis
tic
v
ar
iab
ilit
y
s
ee
n
in
h
is
to
p
ath
o
lo
g
ical
im
ag
in
g
.
T
h
e
b
r
ea
s
t
ca
n
ce
r
d
etec
tio
n
m
o
d
el
h
a
d
b
ee
n
tr
ain
ed
u
s
in
g
a
s
izab
le
d
ataset
o
f
b
r
ea
s
t
s
am
p
les
(
x
_
tr
ain
)
a
n
d
th
ei
r
c
o
r
r
esp
o
n
d
in
g
la
b
els
(
y
_
tr
ain
)
.
T
h
e
tr
ai
n
in
g
a
p
p
r
o
a
ch
en
ab
led
iter
ativ
e
ad
ju
s
tm
e
n
ts
to
th
e
m
o
d
el
p
ar
am
eter
s
u
s
in
g
a
b
atch
s
ize
o
f
3
2
a
n
d
1
0
0
e
p
o
ch
s
.
Fu
r
th
er
m
o
r
e,
a
twen
ty
p
e
r
ce
n
t
v
alid
atio
n
s
p
lit
was
u
s
ed
d
u
r
in
g
tr
ain
in
g
to
tr
ac
k
th
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
o
n
u
n
k
n
o
wn
d
ata,
th
er
e
b
y
p
r
o
p
er
ly
v
alid
atin
g
its
g
en
er
aliza
tio
n
ca
p
ab
ilit
ies.
T
h
e
lear
n
in
g
r
ate
0
.
0
2
is
an
ess
en
tial
h
y
p
er
p
ar
am
eter
th
at
d
eter
m
in
es
th
e
n
u
m
b
er
o
f
p
ar
a
m
eter
u
p
d
ates
d
u
r
in
g
o
p
tim
izatio
n
[
2
2
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
A
n
en
s
emb
le
-
b
a
s
ed
a
p
p
r
o
a
ch
fo
r
b
r
ea
s
t c
a
n
ce
r
id
en
tifi
ca
tio
n
…
(
N
a
ve
en
A
n
a
n
d
a
K
u
ma
r
Jo
s
ep
h
A
n
n
a
ia
h
)
137
3
.
3
.
Wo
r
k
f
lo
w
o
f
t
he
pro
po
s
ed
m
o
del
T
h
e
p
r
o
p
o
s
ed
b
r
ea
s
t
ca
n
ce
r
d
etec
tio
n
tech
n
iq
u
e
s
tar
ts
b
y
lo
ad
in
g
a
n
d
p
r
e
p
r
o
ce
s
s
in
g
th
e
d
ataset.
T
h
e
tar
g
et
lab
els,
d
iag
n
o
s
is
,
ar
e
en
co
d
ed
s
u
ch
t
h
at
b
en
ig
n
(
B
)
is
0
an
d
m
alig
n
an
t
(
M)
is
1
.
T
h
e
d
ataset
is
s
p
lit
in
to
a
tr
ain
in
g
s
et
an
d
test
s
et
in
a
n
8
0
:2
0
r
atio
u
s
in
g
tr
ain
_
test
_
s
p
lit
with
a
r
an
d
o
m
s
ee
d
f
o
r
r
ep
r
o
d
u
cib
ilit
y
.
T
h
e
f
ea
tu
r
es
ar
e
s
tan
d
ar
d
ized
b
y
u
s
in
g
a
s
tan
d
ar
d
s
ca
lar
in
o
r
d
er
to
b
e
o
n
a
s
im
ilar
s
ca
le.
T
h
is
p
ar
t
will
h
elp
en
s
u
r
e
th
at
th
e
m
o
d
el
f
o
c
u
s
es
o
n
r
eg
i
o
n
s
o
f
i
n
ter
est
in
th
e
i
m
ag
es,
wh
ich
ar
e
n
ec
ess
ar
y
f
o
r
ac
cu
r
ate
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
class
if
icatio
n
[
2
3
]
–
[
2
5
]
.
T
h
e
s
am
p
les
ar
e
th
en
p
ass
ed
th
r
o
u
g
h
th
e
L
R
Alex
Net
ar
ch
itectu
r
e,
wh
ich
is
in
itialized
with
th
e
s
eg
m
en
ted
s
am
p
les.
I
n
o
th
er
wo
r
d
s
,
th
e
wo
r
k
f
lo
w
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
is
s
h
o
wn
in
Fig
u
r
e
3
.
Her
e,
we
ar
e
tr
ain
in
g
th
e
L
R
Alex
Net
m
o
d
el
u
s
in
g
s
am
p
les
an
d
th
eir
f
ea
tu
r
es
an
d
id
en
tify
in
g
wh
eth
er
t
h
e
p
atie
n
t
h
as
b
en
ig
n
o
r
m
alig
n
a
n
t.
T
o
p
er
f
o
r
m
th
is
,
th
e
Ad
am
o
p
tim
izer
ch
a
n
g
es
in
ter
n
al
weig
h
ts
to
d
ec
r
ea
s
e
er
r
o
r
s
an
d
ac
h
iev
e
co
r
r
ec
t c
lass
if
icatio
n
s
.
Fig
u
r
e
3
.
W
o
r
k
f
lo
w
o
f
th
e
p
r
o
p
o
s
ed
R
esNet1
0
1
m
o
d
el
4.
VIS
UA
L
I
Z
A
T
I
O
N
O
F
RE
S
UL
T
S AN
D
D
I
SCU
SS
I
O
N
S
T
h
e
p
e
r
f
o
r
m
an
ce
o
f
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
F
ig
u
r
e
2
,
s
h
o
wed
a
f
u
ll
p
ictu
r
e
o
f
th
e
m
o
d
el'
s
s
tr
u
ctu
r
e,
s
h
o
win
g
h
o
w
th
e
co
n
v
o
lu
tio
n
al
an
d
p
o
o
lin
g
lay
e
r
s
wer
e
a
r
r
an
g
ed
i
n
a
ce
r
tain
o
r
d
e
r
,
lead
i
n
g
to
d
en
s
e
lay
er
s
f
o
r
class
if
icatio
n
.
Fig
u
r
e
4
s
h
o
w
s
th
at
th
e
m
o
d
el
s
h
o
ws
g
o
o
d
p
e
r
f
o
r
m
an
ce
o
v
er
1
5
ep
o
ch
s
with
ex
ce
llen
t
d
etailin
g
o
n
th
e
tr
ain
in
g
d
ata
(
lo
w
tr
ain
in
g
lo
s
s
)
.
B
u
t
th
e
te
s
t
lo
s
s
f
lu
ctu
atio
n
s
s
u
g
g
est
it
m
ay
n
o
t
g
en
er
alize
well,
p
o
s
s
ib
ly
d
u
e
to
o
v
er
-
f
itti
n
g
.
4
.
1
.
E
x
perim
ent
a
l
s
et
up
us
ed
f
o
r
t
he
im
plem
ent
a
t
io
n
T
h
e
f
o
l
lo
wi
n
g
s
p
e
ci
f
ic
ati
o
n
u
n
its
ar
e
u
tili
ze
d
i
n
e
ac
h
e
x
p
e
r
i
m
e
n
t:
a
1
6
GB
R
AM
m
o
d
u
l
e,
2
.
8
0
GH
z
I
n
tel
(
R
)
C
o
r
e
(
T
M
)
i7
-
7
7
0
0
c
en
t
r
al
p
r
o
ce
s
s
o
r
u
n
i
t
,
a
n
d
NV
I
D
I
A
GT
X
1
0
5
0
T
i
g
r
a
p
h
i
cs
c
ar
d
s
t
h
at
w
er
e
u
s
e
d
f
o
r
th
e
ex
p
e
r
i
m
e
n
ts
.
F
o
r
t
h
is
i
n
v
esti
g
a
ti
o
n
,
th
e
P
y
t
h
o
n
p
r
o
g
r
a
m
m
in
g
la
n
g
u
a
g
e
is
u
ti
liz
ed
,
an
d
m
o
r
e
s
p
e
ci
f
ic
all
y
,
t
h
e
I
m
a
g
e
Dat
aGe
n
e
r
a
to
r
m
o
d
u
l
e
f
r
o
m
t
h
e
K
er
as
f
r
am
ew
o
r
k
is
u
til
iz
ed
t
o
c
o
m
p
i
le
s
ets
o
f
MR
I
p
ic
tu
r
es.
Fi
g
u
r
es
4
(
a)
an
d
4
(
b
)
s
h
o
w
t
h
e
l
o
s
s
o
f
t
h
e
m
o
d
el
w
ith
r
es
p
e
ct
t
o
b
o
th
tr
ai
n
i
n
g
a
n
d
tes
ti
n
g
f
o
r
ep
o
ch
s
lik
e
1
0
a
n
d
1
5
.
T
h
e
f
ig
u
r
es
i
n
d
icat
e
th
at
t
h
e
m
o
d
el
a
c
h
ie
v
ed
l
o
w
tr
ai
n
i
n
g
lo
s
s
,
b
u
t
t
h
e
tes
t
lo
s
s
f
l
u
ct
u
at
e
d
.
(
a)
(
b
)
Fig
u
r
e
4
.
T
r
ain
in
g
a
n
d
test
in
g
lo
s
s
o
f
th
e
m
o
d
el
o
v
er
1
5
e
p
o
c
h
s
of
(
a)
e
p
o
ch
1
0
a
n
d
(
b
)
e
p
o
ch
15
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
c
h
2
0
2
6
:
133
-
1
4
1
138
Fig
u
r
e
5
illu
s
tr
ates
th
e
R
OC
cu
r
v
e
d
is
p
lay
s
th
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
.
T
h
is
p
ictu
r
e
is
cr
u
cial
f
o
r
co
m
p
r
eh
e
n
d
in
g
th
e
m
o
d
el'
s
co
n
v
er
g
en
ce
a
n
d
p
er
f
o
r
m
an
c
e
p
atter
n
s
d
u
r
in
g
th
e
tr
ai
n
in
g
p
h
ase.
Fig
u
r
e
6
d
is
p
lay
s
th
e
co
n
f
u
s
io
n
m
atr
ix
,
wh
ich
p
r
o
v
i
d
es
a
co
m
p
r
eh
e
n
s
iv
e
ev
alu
atio
n
o
f
t
h
e
m
o
d
el'
s
p
r
ed
ictio
n
s
o
n
th
e
test
d
ataset.
6
8
n
u
m
b
e
r
r
ep
r
esen
ts
th
e
n
u
m
b
e
r
o
f
d
ata
p
o
in
t
s
th
at
wer
e
co
r
r
ec
tly
class
if
ied
as
b
en
ig
n
(
ac
tu
al
class
)
an
d
wer
e
also
p
r
ed
icted
as b
en
ig
n
b
y
th
e
m
o
d
el
(
p
r
ed
i
cted
class
)
.
T
h
e
co
m
p
ar
ativ
e
r
esu
lts
in
T
ab
le
2
h
ig
h
lig
h
t
th
e
r
em
ar
k
a
b
le
ad
v
an
ce
m
en
ts
s
ee
n
in
b
r
ea
s
t
ca
n
ce
r
d
etec
tio
n
u
s
in
g
m
ac
h
in
e
lear
n
in
g
an
d
DL
alg
o
r
ith
m
s
o
v
er
th
e
last
s
ev
er
al
y
ea
r
s
.
T
h
e
c
u
r
r
e
n
t
s
tu
d
y
'
s
p
r
o
p
o
s
ed
en
s
em
b
le
m
o
d
el
(
C
NN
-
L
R
Al
ex
Net)
ac
h
iev
es
an
F1
-
s
co
r
e
o
f
9
5
.
7
0
,
with
s
en
s
itiv
ity
an
d
s
p
ec
if
icity
v
alu
es
o
f
9
6
.
5
0
%
a
n
d
9
6
.
1
0
%,
r
esp
ec
t
iv
ely
,
an
d
an
o
v
er
all
a
cc
u
r
a
cy
o
f
9
6
.
4
%.
Fro
m
Fig
u
r
e
7
,
it
is
ev
id
en
t
th
at
en
s
em
b
le
an
d
h
y
b
r
id
m
o
d
els,
s
u
ch
as
th
e
p
r
o
p
o
s
ed
en
s
e
m
b
le
C
NN
-
L
R
Alex
Net
an
d
v
ar
io
u
s
C
NN
-
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
o
r
s
tack
in
g
ap
p
r
o
ac
h
es,
c
o
n
s
is
ten
tly
r
ea
ch
s
tr
o
n
g
r
esu
lts
ac
r
o
s
s
all
s
ix
m
etr
ics.
Fig
u
r
e
5
.
R
OC
cu
r
v
e
f
o
r
th
e
p
r
o
p
o
s
ed
m
o
d
el
Fig
u
r
e
6
.
C
o
n
f
u
s
io
n
m
atr
i
x
T
ab
le
2
.
C
o
m
p
a
r
is
o
n
o
f
d
if
f
e
r
en
t m
o
d
els with
th
eir
ac
c
u
r
ac
i
es
S
t
u
d
y
M
o
d
e
l
F1
-
sc
o
r
e
S
e
n
s
i
t
i
v
i
t
y
(
%)
S
p
e
c
i
f
i
c
i
t
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
AUC
A
c
c
u
r
a
c
y
(
%
)
N
a
si
r
e
t
a
l
.
[
1
5
]
C
N
N
9
1
.
1
4
9
2
.
3
1
9
5
.
6
0
9
0
.
0
0
9
4
.
6
2
9
4
.
6
2
M
a
p
a
r
i
e
t
a
l
.
[
1
6
]
Ea
r
l
y
DL
9
6
.
2
0
9
6
.
5
1
n
o
t
s
t
a
t
e
d
9
5
.
9
2
n
o
t
s
t
a
t
e
d
9
6
.
2
1
K
a
d
d
e
s
e
t
a
l
.
[
1
8
]
d
a
t
a
se
t
1
H
y
b
r
i
d
C
N
N
-
LST
M
9
9
.
1
7
9
9
.
1
7
9
9
.
1
7
9
9
.
1
7
9
9
.
5
9
5
.
3
4
K
a
d
d
e
s
e
t
a
l
.
[
1
8
]
d
a
t
a
se
t
2
H
y
b
r
i
d
C
N
N
-
LST
M
9
9
.
8
0
9
9
.
9
0
9
9
.
9
0
9
9
.
8
0
1
0
0
.
0
9
9
.
1
7
K
w
o
n
e
t
a
l
.
[
2
0
]
S
t
a
c
k
i
n
g
e
n
s
e
mb
l
e
1
0
0
.
0
1
0
0
.
0
9
9
.
9
1
0
0
.
0
1
0
0
.
0
8
9
.
4
Q
a
sr
a
w
i
e
t
a
l
.
[
2
1
]
H
y
b
r
i
d
e
n
sem
b
l
e
9
5
.
3
4
9
3
.
0
5
n
o
t
s
t
a
t
e
d
n
o
t
s
t
a
t
e
d
n
o
t
s
t
a
t
e
d
98
A
l
sh
a
y
e
j
i
a
n
d
Al
-
B
u
l
o
u
s
h
i
[
2
2
]
C
N
N
9
9
.
1
3
9
9
.
5
9
9
9
.
5
3
9
8
.
7
1
n
o
t
s
t
a
t
e
d
9
9
.
1
3
B
h
a
r
d
w
a
j
e
t
a
l
.
[
2
4
]
Tr
e
e
-
b
a
se
d
9
6
.
7
7
n
o
t
s
t
a
t
e
d
n
o
t
s
t
a
t
e
d
n
o
t
s
t
a
t
e
d
n
o
t
s
t
a
t
e
d
9
9
.
1
Te
o
h
e
t
a
l
.
[
2
5
]
DL
f
r
a
mew
o
r
k
9
7
.
3
5
n
o
t
s
t
a
t
e
d
n
o
t
s
t
a
t
e
d
9
8
.
7
9
n
o
t
s
t
a
t
e
d
86
P
r
o
p
o
se
d
m
o
d
e
l
En
se
mb
l
e
mo
d
e
l
9
5
.
7
0
9
6
.
5
0
9
6
.
1
0
9
3
.
2
5
9
7
.
8
0
9
6
.
4
Fig
u
r
e
7
.
C
o
m
p
a
r
is
o
n
g
r
ap
h
o
f
th
e
cu
r
r
en
t m
o
d
el
with
o
th
e
r
ex
is
tin
g
m
o
d
els
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
A
n
en
s
emb
le
-
b
a
s
ed
a
p
p
r
o
a
ch
fo
r
b
r
ea
s
t c
a
n
ce
r
id
en
tifi
ca
tio
n
…
(
N
a
ve
en
A
n
a
n
d
a
K
u
ma
r
Jo
s
ep
h
A
n
n
a
ia
h
)
139
4
.
2
.
Clini
ca
l deplo
y
m
ent
a
n
d e
t
hica
l A
I
co
nte
x
t
s
T
h
e
s
ettin
g
o
f
clin
ical
d
ep
lo
y
m
en
t
an
d
eth
ical
AI
co
n
s
id
er
a
tio
n
s
is
cr
u
cial
to
f
u
lly
u
n
d
er
s
tan
d
th
eir
p
r
ac
tical
im
p
licatio
n
s
an
d
to
ef
f
ec
tiv
ely
ad
d
r
ess
th
e
s
er
io
u
s
b
ar
r
ier
s
h
in
d
er
in
g
th
e
wid
esp
r
ea
d
ad
o
p
tio
n
o
f
m
ac
h
in
e
lear
n
in
g
m
o
d
els
in
h
ea
lth
ca
r
e
s
ettin
g
s
.
W
ith
AI
-
d
r
iv
en
d
iag
n
o
s
tic
to
o
ls
,
s
u
ch
as
th
e
en
s
em
b
le
C
NN
-
L
R
A
lex
Net
m
o
d
el
p
r
esen
ted
in
th
is
s
tu
d
y
,
d
em
o
n
s
tr
atin
g
ev
er
-
im
p
r
o
v
in
g
ac
cu
r
ac
y
an
d
p
er
f
o
r
m
an
ce
f
o
r
b
r
ea
s
t
ca
n
ce
r
id
en
tific
atio
n
,
th
e
in
teg
r
atio
n
o
f
AI
in
to
d
aily
clin
ical
p
r
ac
tice
h
as
b
e
co
m
e
in
cr
ea
s
in
g
ly
tan
g
ib
le,
f
ea
s
ib
le,
an
d
h
ig
h
ly
r
elev
an
t
f
o
r
r
ea
l
-
wo
r
ld
m
ed
i
ca
l
wo
r
k
f
l
o
ws.
C
lin
ically
,
th
er
ef
o
r
e,
th
e
m
o
d
el
m
u
s
t
s
u
cc
ess
f
u
lly
tr
an
s
itio
n
f
r
o
m
its
cu
r
r
en
t
lab
o
r
ato
r
y
-
v
alid
ated
s
tatu
s
to
p
r
ac
tical
d
ep
lo
y
m
en
t,
wh
ile
d
em
o
n
s
tr
atin
g
r
o
b
u
s
t
g
e
n
er
al
izab
ilit
y
ac
r
o
s
s
d
iv
e
r
s
e
p
atie
n
t
p
o
p
u
latio
n
s
,
v
ar
io
u
s
im
a
g
in
g
d
ev
ices,
a
n
d
d
if
f
er
en
t
h
ea
lth
ca
r
e
en
v
ir
o
n
m
en
ts
.
5.
CO
NCLU
SI
O
N
T
h
e
cu
r
r
e
n
t
en
s
em
b
le
DL
m
o
d
el
ac
h
iev
es
ex
ce
llen
t
ac
cu
r
a
cy
an
d
b
ala
n
ce
d
p
e
r
f
o
r
m
an
ce
m
etr
ics
in
r
elatio
n
to
th
e
C
B
I
S
-
DDSM
ca
n
ce
r
d
ataset
.
V
ar
io
u
s
p
o
ten
tial
lim
itatio
n
s
ar
e
im
p
o
r
tan
t
to
co
n
s
id
er
wh
en
in
ter
p
r
etin
g
th
e
r
esu
lts
o
f
AI
m
o
d
els
in
th
e
cu
r
r
en
t
AI
to
o
ls
an
d
lar
g
e
lan
g
u
a
g
e
m
o
d
el
(
L
L
M)
-
en
ab
le
d
r
esear
ch
en
v
ir
o
n
m
en
t.
T
h
e
m
o
d
el'
s
ev
alu
atio
n
is
b
ased
o
n
a
r
elativ
ely
s
m
all
an
d
h
o
m
o
g
en
eo
u
s
d
ataset
th
at
m
ay
n
o
t
f
u
lly
r
e
p
r
esen
t
th
e
c
o
m
p
lex
ity
an
d
d
iv
er
s
ity
t
h
at
ar
is
es
in
clin
ical
p
r
ac
tice,
r
aisi
n
g
co
n
ce
r
n
s
a
b
o
u
t
g
en
er
aliza
b
ilit
y
a
n
d
r
o
b
u
s
tn
ess
b
ey
o
n
d
th
e
c
u
r
r
e
n
t
ev
al
u
atio
n
s
ettin
g
,
all
o
f
wh
ich
ar
e
co
m
m
o
n
an
d
ess
en
tial
asp
ec
t
s
o
f
ev
alu
atin
g
m
o
s
t
AI
m
o
d
els
in
m
ed
ical
im
ag
in
g
.
L
ik
e
m
an
y
AI
m
o
d
els,
th
e
in
t
er
p
r
etab
ilit
y
o
f
th
e
m
o
d
el'
s
p
ath
way
s
o
f
f
in
al
d
e
cisi
o
n
s
r
em
ain
s
lim
ited
,
co
m
m
o
n
ly
r
ef
er
r
ed
to
as
th
e
"
b
la
ck
b
o
x
"
is
s
u
e
,
an
d
co
u
ld
r
esu
lt
in
p
o
o
r
clin
ical
tr
u
s
t
an
d
/o
r
s
lo
w
u
p
tak
e
o
f
m
o
d
els
b
ased
o
n
th
e
s
tu
d
y
'
s
r
esu
lts
an
d
im
p
licatio
n
s
,
p
ar
ticu
lar
ly
wh
e
n
ex
p
lain
i
n
g
t
h
e
m
o
d
els'
r
esu
lts
to
clin
ician
s
o
r
p
atien
ts
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
p
ar
t
o
f
t
h
e
wo
r
k
ca
r
r
i
ed
o
u
t
i
n
th
e
c
u
r
r
e
n
t
ar
ticl
e
was
s
u
p
p
o
r
ted
b
y
th
e
p
r
o
ject
u
n
d
e
r
Dep
ar
tm
en
t
o
f
Scien
ce
a
n
d
T
ec
h
n
o
lo
g
y
-
Scien
ce
a
n
d
E
n
g
in
ee
r
in
g
R
esear
ch
B
o
ar
d
(
DST
-
SERB
)
ca
teg
o
r
y
o
f
em
p
o
wer
m
en
t
an
d
e
q
u
ity
(
E
ME
Q)
,
Go
v
e
r
n
m
en
t
o
f
I
n
d
ia
,
with
Fil
e
No
.
E
E
Q/2
0
2
3
/
0
0
0
0
5
3
.
T
h
e
a
u
th
o
r
s
ar
e
th
an
k
f
u
l t
o
th
e
DST
-
SERB
,
Go
v
er
n
m
e
n
t o
f
I
n
d
ia
,
f
o
r
s
u
p
p
o
r
tin
g
th
e
wo
r
k
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
e
au
th
o
r
s
co
n
f
ir
m
th
at
th
i
s
wo
r
k
was
co
n
d
u
cte
d
with
o
u
t
an
y
ex
te
r
n
al
f
i
n
an
cial
s
u
p
p
o
r
t.
No
f
u
n
d
in
g
was
r
ec
eiv
ed
f
r
o
m
a
n
y
p
u
b
lic,
co
m
m
er
cial,
o
r
n
o
t
-
f
o
r
-
p
r
o
f
it
f
u
n
d
in
g
ag
en
cies
f
o
r
th
e
p
r
ep
a
r
atio
n
,
ex
ec
u
tio
n
,
o
r
p
u
b
licatio
n
o
f
th
is
s
tu
d
y
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
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
Nav
ee
n
An
a
n
d
a
K
u
m
ar
J
o
s
ep
h
An
n
aiah
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Nak
k
a
T
h
ir
u
p
ath
i Rao
✓
✓
✓
✓
✓
✓
✓
B
alak
esav
a
R
ed
d
y
Par
v
ath
ala
✓
✓
✓
✓
✓
✓
✓
B
an
an
a
Om
k
ar
L
ak
s
h
m
i Jag
an
✓
✓
✓
✓
✓
✓
✓
B
o
d
ap
ati
Ven
k
ata
R
ajan
n
a
✓
✓
✓
✓
✓
✓
✓
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
s
i
s
I
:
I
n
v
e
s
t
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
s
i
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
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
c
h
2
0
2
6
:
133
-
1
4
1
140
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
s
tate
th
at
th
ey
h
av
e
n
o
k
n
o
wn
co
m
p
etin
g
f
in
an
cial
in
ter
ests
o
r
p
er
s
o
n
al
r
e
latio
n
s
h
ip
s
th
at
co
u
ld
h
av
e
ap
p
ea
r
ed
t
o
in
f
lu
en
ce
th
e
wo
r
k
r
e
p
o
r
te
d
in
t
h
is
p
ap
er
.
T
h
e
a
u
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
ter
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
au
th
o
r
s
co
n
f
ir
m
th
at
t
h
e
d
ata
s
u
p
p
o
r
tin
g
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
av
ailab
le
with
in
th
e
ar
ticle.
RE
F
E
R
E
NC
E
S
[
1
]
J.
A
h
ma
d
,
S
.
A
k
r
a
m,
A
.
J
a
f
f
a
r
,
M
.
R
a
sh
i
d
,
a
n
d
S
.
M
.
B
h
a
t
t
i
,
“
B
r
e
a
st
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
:
a
n
i
n
v
e
st
i
g
a
t
i
o
n
u
si
n
g
th
e
D
D
S
M
d
a
t
a
se
t
a
n
d
a
c
u
s
t
o
mi
z
e
d
A
l
e
x
N
e
t
a
n
d
s
u
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
,
”
I
E
EE
A
c
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
1
0
8
3
8
6
–
1
0
8
3
9
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
3
1
1
8
9
2
.
[
2
]
R
.
A
g
g
a
r
w
a
l
e
t
a
l
.
,
“
D
i
a
g
n
o
st
i
c
a
c
c
u
r
a
c
y
o
f
d
e
e
p
l
e
a
r
n
i
n
g
i
n
me
d
i
c
a
l
i
mag
i
n
g
:
a
s
y
st
e
mat
i
c
r
e
v
i
e
w
a
n
d
m
e
t
a
-
a
n
a
l
y
si
s
,
”
n
p
j
D
i
g
i
t
a
l
Me
d
i
c
i
n
e
,
v
o
l
.
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
7
4
6
-
0
2
1
-
0
0
4
3
8
-
z.
[
3
]
N
.
I
.
Y
a
ssi
n
,
S
.
O
mr
a
n
,
E.
M
.
H
o
u
b
y
,
a
n
d
H
.
A
l
l
a
m,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
b
r
e
a
st
c
a
n
c
e
r
c
o
mp
u
t
e
r
-
a
i
d
e
d
d
i
a
g
n
o
s
i
s
u
si
n
g
d
i
f
f
e
r
e
n
t
i
m
a
g
e
m
o
d
a
l
i
t
i
e
s
:
a
s
y
st
e
ma
t
i
c
r
e
v
i
e
w
,
”
C
o
m
p
u
t
e
r
Me
t
h
o
d
s
a
n
d
Pr
o
g
r
a
m
s
i
n
B
i
o
m
e
d
i
c
i
n
e
,
v
o
l
.
1
5
6
,
p
p
.
2
5
–
4
5
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
m
p
b
.
2
0
1
7
.
1
2
.
0
1
2
.
[
4
]
A
.
El
-
N
a
b
a
w
y
,
N
.
El
-
B
e
n
d
a
r
y
,
a
n
d
N
.
A
.
B
e
l
a
l
,
“
A
f
e
a
t
u
r
e
-
f
u
s
i
o
n
f
r
a
mew
o
r
k
o
f
c
l
i
n
i
c
a
l
,
g
e
n
o
m
i
c
s,
a
n
d
h
i
s
t
o
p
a
t
h
o
l
o
g
i
c
a
l
d
a
t
a
f
o
r
M
ETA
B
R
I
C
b
r
e
a
s
t
c
a
n
c
e
r
s
u
b
t
y
p
e
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
Ap
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
9
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
s
o
c
.
2
0
2
0
.
1
0
6
2
3
8
.
[
5
]
A
.
B
.
N
a
ssi
f
,
M
.
A
.
T
a
l
i
b
,
Q
.
N
a
s
i
r
,
Y
.
A
f
a
d
a
r
,
a
n
d
O
.
El
g
e
n
d
y
,
“
B
r
e
a
s
t
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
u
s
i
n
g
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
t
e
c
h
n
i
q
u
e
s
:
a
sy
st
e
ma
t
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
,
”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
M
e
d
i
c
i
n
e
,
v
o
l
.
1
2
7
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
r
t
me
d
.
2
0
2
2
.
1
0
2
2
7
6
.
[
6
]
H
.
Y
a
o
,
X
.
Z
h
a
n
g
,
X
.
Zh
o
u
,
a
n
d
S
.
L
i
u
,
“
P
a
r
a
l
l
e
l
s
t
r
u
c
t
u
r
e
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
u
s
i
n
g
C
N
N
a
n
d
R
N
N
w
i
t
h
a
n
a
t
t
e
n
t
i
o
n
f
o
r
b
r
e
a
s
t
c
a
n
c
e
r
h
i
st
o
l
o
g
y
i
m
a
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
C
a
n
c
e
r
s
,
v
o
l
.
1
1
,
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
c
a
n
c
e
r
s
1
1
1
2
1
9
0
1
.
[
7
]
S
.
V
i
j
a
y
a
l
a
k
s
h
mi
,
B
.
K
.
P
a
n
d
e
y
,
D
.
P
a
n
d
e
y
,
a
n
d
M
.
E.
Le
l
i
s
h
o
,
“
I
n
n
o
v
a
t
i
v
e
d
e
e
p
l
e
a
r
n
i
n
g
c
l
a
ssi
f
i
e
r
s
f
o
r
b
r
e
a
st
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
t
h
r
o
u
g
h
h
y
b
r
i
d
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,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
5
,
n
o
.
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
025
-
0
6
6
6
9
-
4.
[
8
]
L.
L
u
o
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
i
n
b
r
e
a
s
t
c
a
n
c
e
r
i
ma
g
i
n
g
:
a
d
e
c
a
d
e
o
f
p
r
o
g
r
e
s
s
a
n
d
f
u
t
u
r
e
d
i
r
e
c
t
i
o
n
s
,
”
I
EE
E
R
e
v
i
e
w
s
i
n
B
i
o
m
e
d
i
c
a
l
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
8
,
p
p
.
1
3
0
–
1
5
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
0
9
/
R
B
M
E
.
2
0
2
4
.
3
3
5
7
8
7
7
.
[
9
]
D
.
Z
h
a
n
g
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
o
n
r
o
u
t
i
n
e
f
u
l
l
-
b
r
e
a
s
t
m
a
mm
o
g
r
a
ms
e
n
h
a
n
c
e
s
l
y
m
p
h
n
o
d
e
me
t
a
s
t
a
s
i
s
p
r
e
d
i
c
t
i
o
n
i
n
e
a
r
l
y
b
r
e
a
s
t
c
a
n
c
e
r
,
”
n
p
j
D
i
g
i
t
a
l
M
e
d
i
c
i
n
e
,
v
o
l
.
8
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
7
4
6
-
0
2
5
-
0
1
8
3
1
-
8.
[
1
0
]
C
.
B
.
R
a
b
a
h
,
A
.
S
a
t
t
a
r
,
A
.
I
b
r
a
h
i
m,
a
n
d
A
.
S
e
r
a
g
,
“
A
mu
l
t
i
m
o
d
a
l
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
f
o
r
t
h
e
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
b
r
e
a
st
c
a
n
c
e
r
su
b
t
y
p
e
s,”
D
i
a
g
n
o
st
i
c
s
,
v
o
l
.
1
5
,
n
o
.
8
,
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
d
i
a
g
n
o
st
i
c
s
1
5
0
8
0
9
9
5
.
[
1
1
]
P
.
O
z
a
,
P
.
S
h
a
r
m
a
,
a
n
d
S
.
P
a
t
e
l
,
“
D
e
e
p
e
n
s
e
mb
l
e
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
-
b
a
se
d
f
r
a
mew
o
r
k
f
o
r
mam
mo
g
r
a
p
h
i
c
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
T
h
e
J
o
u
r
n
a
l
o
f
S
u
p
e
r
c
o
m
p
u
t
i
n
g
,
v
o
l
.
7
9
,
n
o
.
7
,
p
p
.
8
0
4
8
–
8
0
6
9
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
2
2
7
-
022
-
0
4
9
9
2
-
5.
[
1
2
]
A
.
M
e
l
e
k
,
S
.
F
a
k
h
r
y
,
a
n
d
T.
B
a
sh
a
,
“
S
p
a
t
i
o
t
e
m
p
o
r
a
l
m
a
mm
o
g
r
a
p
h
y
-
b
a
se
d
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
f
o
r
i
mp
r
o
v
e
d
b
r
e
a
s
t
c
a
n
c
e
r
r
i
sk
p
r
e
d
i
c
t
i
o
n
,
”
i
n
2
0
2
3
4
5
t
h
A
n
n
u
a
l
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
f
t
h
e
I
EEE
En
g
i
n
e
e
ri
n
g
i
n
Me
d
i
c
i
n
e
&
B
i
o
l
o
g
y
S
o
c
i
e
t
y
(
EM
BC
)
,
2
0
2
3
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
EM
B
C
4
0
7
8
7
.
2
0
2
3
.
1
0
3
4
0
6
0
2
.
[
1
3
]
A
.
R
o
v
sh
e
n
o
v
a
n
d
S
.
P
e
k
e
r
,
“
P
e
r
f
o
r
man
c
e
c
o
mp
a
r
i
s
o
n
o
f
d
i
f
f
e
r
e
n
t
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
e
a
r
l
y
p
r
e
d
i
c
t
i
o
n
o
f
b
r
e
a
s
t
c
a
n
c
e
r
u
si
n
g
w
i
s
c
o
n
s
i
n
b
r
e
a
s
t
c
a
n
c
e
r
d
a
t
a
set
,
”
i
n
2
0
2
2
3
r
d
I
n
t
e
rn
a
t
i
o
n
a
l
I
n
f
o
rm
a
t
i
c
s
a
n
d
S
o
f
t
w
a
re
E
n
g
i
n
e
e
ri
n
g
C
o
n
f
e
r
e
n
c
e
(
I
I
S
EC
)
,
2
0
2
2
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
I
S
EC
5
6
2
6
3
.
2
0
2
2
.
9
9
9
8
2
4
8
.
[
1
4
]
M
.
L
u
,
X
.
X
i
a
o
,
Y
.
P
a
n
g
,
G
.
L
i
u
,
a
n
d
H
.
Lu
,
“
R
e
sp
o
n
se
t
o
c
o
mm
e
n
t
s
o
n
‘
d
e
t
e
c
t
i
o
n
a
n
d
l
o
c
a
l
i
z
a
t
i
o
n
o
f
b
r
e
a
st
c
a
n
c
e
r
u
si
n
g
U
W
B
mi
c
r
o
w
a
v
e
t
e
c
h
n
o
l
o
g
y
a
n
d
C
N
N
-
LS
TM
f
r
a
mew
o
r
k
’
,”
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
M
i
c
r
o
w
a
v
e
T
h
e
o
r
y
a
n
d
T
e
c
h
n
i
q
u
e
s
,
v
o
l
.
7
1
,
n
o
.
1
0
,
p
.
4
6
1
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
TM
TT.
2
0
2
3
.
3
2
6
4
5
5
5
.
[
1
5
]
F
.
N
a
s
i
r
,
S
.
R
a
h
m
a
n
,
a
n
d
N
.
N
a
s
i
r
,
“
B
r
e
a
st
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
u
si
n
g
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:
a
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
a
p
p
r
o
a
c
h
,
”
C
u
re
u
s
,
v
o
l
.
1
7
,
n
o
.
5
,
2
0
2
5
,
d
o
i
:
1
0
.
7
7
5
9
/
c
u
r
e
u
s.
8
3
4
2
1
.
[
1
6
]
S
.
M
a
p
a
r
i
,
A
.
M
a
h
m
o
u
d
,
M
.
S
a
t
h
y
a
mo
o
r
t
h
y
,
S
.
P
,
S
.
S
a
i
n
i
,
a
n
d
N
.
A
.
A
w
a
d
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
e
a
r
l
y
d
e
t
e
c
t
i
o
n
o
f
b
r
e
a
st
c
a
n
c
e
r
:
i
m
p
r
o
v
i
n
g
a
c
c
u
r
a
c
y
a
n
d
e
f
f
i
c
i
e
n
c
y
i
n
d
i
a
g
n
o
s
i
s
f
o
r
e
n
h
a
n
c
e
d
p
a
t
i
e
n
t
o
u
t
c
o
m
e
s,”
i
n
2
0
2
4
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
m
u
n
i
c
a
t
i
o
n
,
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
s
a
n
d
E
n
g
i
n
e
e
r
i
n
g
(
I
C
3
S
E)
,
2
0
2
4
,
p
p
.
4
8
9
–
4
9
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
3
S
E6
2
0
0
2
.
2
0
2
4
.
1
0
5
9
3
3
9
6
.
[
1
7
]
H
.
S
o
n
g
e
t
a
l
.
,
“
D
e
t
e
c
t
a
b
i
l
i
t
y
o
f
b
r
e
a
s
t
t
u
m
o
r
s
i
n
e
x
c
i
s
e
d
b
r
e
a
s
t
t
i
ss
u
e
s
o
f
t
o
t
a
l
m
a
st
e
c
t
o
m
y
b
y
I
R
-
U
W
B
-
r
a
d
a
r
-
b
a
s
e
d
b
r
e
a
s
t
c
a
n
c
e
r
d
e
t
e
c
t
o
r
,
”
I
E
EE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
B
i
o
m
e
d
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
6
6
,
n
o
.
8
,
p
p
.
2
2
9
6
–
2
3
0
5
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
T
B
M
E.
2
0
1
8
.
2
8
8
7
0
8
3
.
[
1
8
]
M
.
K
a
d
d
e
s
e
t
a
l
.
,
“
B
r
e
a
s
t
c
a
n
c
e
r
c
l
a
ssi
f
i
c
a
t
i
o
n
b
a
se
d
o
n
h
y
b
r
i
d
C
N
N
w
i
t
h
LST
M
m
o
d
e
l
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
1
5
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
025
-
8
8
4
5
9
-
6.
[
1
9
]
X
.
F
e
n
g
e
t
a
l
.
,
“
A
c
c
u
r
a
t
e
p
r
e
d
i
c
t
i
o
n
o
f
n
e
o
a
d
j
u
v
a
n
t
c
h
e
m
o
t
h
e
r
a
p
y
p
a
t
h
o
l
o
g
i
c
a
l
c
o
m
p
l
e
t
e
r
e
m
i
ss
i
o
n
(
p
C
R
)
f
o
r
t
h
e
f
o
u
r
s
u
b
-
t
y
p
e
s
o
f
b
r
e
a
s
t
c
a
n
c
e
r
,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
7
,
p
p
.
1
3
4
6
9
7
–
1
3
4
7
0
6
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
4
1
5
4
3
.
[
2
0
]
H
.
K
w
o
n
,
J.
P
a
r
k
,
a
n
d
Y
.
L
e
e
,
“
S
t
a
c
k
i
n
g
e
n
s
e
mb
l
e
t
e
c
h
n
i
q
u
e
f
o
r
c
l
a
ssi
f
y
i
n
g
b
r
e
a
st
c
a
n
c
e
r
,
”
H
e
a
l
t
h
c
a
r
e
I
n
f
o
r
m
a
t
i
c
s
Re
s
e
a
r
c
h
,
v
o
l
.
2
5
,
n
o
.
4
,
p
p
.
2
8
3
–
2
8
8
,
2
0
1
9
,
d
o
i
:
1
0
.
4
2
5
8
/
h
i
r
.
2
0
1
9
.
2
5
.
4
.
2
8
3
.
[
2
1
]
R
.
Q
a
sr
a
w
i
e
t
a
l
.
,
“
H
y
b
r
i
d
e
n
s
e
m
b
l
e
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
f
o
r
a
d
v
a
n
c
i
n
g
b
r
e
a
s
t
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
i
n
c
l
i
n
i
c
a
l
a
p
p
l
i
c
a
t
i
o
n
s,
”
H
e
l
i
y
o
n
,
v
o
l
.
1
0
,
n
o
.
1
9
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
4
.
e
3
8
3
7
4
.
[
2
2
]
M
.
H
.
A
l
sh
a
y
e
j
i
a
n
d
J.
A
l
-
B
u
l
o
u
s
h
i
,
“
B
r
e
a
s
t
c
a
n
c
e
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
c
o
n
c
a
t
e
n
a
t
e
d
t
r
i
p
l
e
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 m
o
d
e
l
,
”
Bi
g
D
a
t
a
a
n
d
C
o
g
n
i
t
i
v
e
C
o
m
p
u
t
i
n
g
,
v
o
l
.
7
,
n
o
.
3
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
b
d
c
c
7
0
3
0
1
4
2
.
[
2
3
]
H
.
D
.
S
e
h
g
a
l
,
Y
.
P
r
a
t
a
p
,
a
n
d
S
.
K
a
b
r
a
,
“
D
e
t
e
c
t
i
o
n
o
f
b
r
e
a
st
c
a
n
c
e
r
ce
ll
-
M
D
A
-
MB
-
2
3
1
b
y
me
a
s
u
r
i
n
g
c
o
n
d
u
c
t
i
v
i
t
y
o
f
S
c
h
o
t
t
k
y
so
u
r
c
e
/
d
r
a
i
n
G
a
N
F
i
n
F
ET,
”
I
EEE
S
e
n
so
rs
J
o
u
r
n
a
l
,
v
o
l
.
2
2
,
n
o
.
6
,
p
p
.
6
1
0
8
–
6
1
1
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
EN
.
2
0
2
2
.
3
1
4
8
1
1
7
.
[
2
4
]
A
.
B
h
a
r
d
w
a
j
,
H
.
B
h
a
r
d
w
a
j
,
A
.
S
a
k
a
l
l
e
,
Z.
U
d
d
i
n
,
M
.
S
a
k
a
l
l
e
,
a
n
d
W
.
I
b
r
a
h
i
m,
“
Tr
e
e
-
b
a
s
e
d
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
a
n
a
l
y
si
s
f
o
r
b
r
e
a
s
t
c
a
n
c
e
r
c
l
a
ss
i
f
i
c
a
t
i
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
N
e
u
r
o
sc
i
e
n
c
e
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
6
7
1
5
4
0
6
.
[
2
5
]
J.
R
.
Te
o
h
,
K
.
H
a
s
i
k
i
n
,
K
.
W
.
L
a
i
,
X
.
W
u
,
a
n
d
C
.
Li
,
“
E
n
h
a
n
c
i
n
g
e
a
r
l
y
b
r
e
a
st
c
a
n
c
e
r
d
i
a
g
n
o
s
i
s
t
h
r
o
u
g
h
a
u
t
o
ma
t
e
d
mi
c
r
o
c
a
l
c
i
f
i
c
a
t
i
o
n
d
e
t
e
c
t
i
o
n
u
si
n
g
a
n
o
p
t
i
m
i
z
e
d
e
n
sem
b
l
e
d
e
e
p
l
e
a
r
n
i
n
g
f
r
a
mew
o
r
k
,
”
P
e
e
r
J
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
0
,
2
0
2
4
,
d
o
i
:
1
0
.
7
7
1
7
/
p
e
e
r
j
-
c
s
.
2
0
8
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
A
n
en
s
emb
le
-
b
a
s
ed
a
p
p
r
o
a
ch
fo
r
b
r
ea
s
t c
a
n
ce
r
id
en
tifi
ca
tio
n
…
(
N
a
ve
en
A
n
a
n
d
a
K
u
ma
r
Jo
s
ep
h
A
n
n
a
ia
h
)
141
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Na
v
e
e
n
An
a
n
d
a
K
u
m
a
r
J
o
se
p
h
Ann
a
ia
h
sta
n
d
s
a
s
a
d
isti
n
g
u
ish
e
d
c
lo
u
d
d
a
ta
e
n
g
in
e
e
r
wit
h
o
v
e
r
f
o
u
r
y
e
a
rs
o
f
p
ro
f
o
u
n
d
e
x
p
e
rien
c
e
i
n
p
io
n
e
e
rin
g
,
e
v
a
l
u
a
ti
n
g
,
a
n
d
d
e
p
l
o
y
in
g
c
lo
u
d
-
b
a
se
d
tec
h
n
o
lo
g
ies
su
c
h
a
s
AWS
,
G
CP
,
a
n
d
Az
u
re
.
His
il
lu
stri
o
u
s
c
a
re
e
r
is
c
h
a
ra
c
teriz
e
d
b
y
a
n
u
n
wa
v
e
rin
g
p
u
rsu
it
o
f
in
n
o
v
a
ti
o
n
a
n
d
a
n
a
rd
e
n
t
fa
sc
in
a
ti
o
n
wit
h
e
m
e
rg
in
g
d
o
m
a
in
s
li
k
e
AI
a
n
d
M
L.
His
re
p
e
rto
ire
o
f
c
e
rti
fica
ti
o
n
s,
wit
h
AWS
sp
e
c
i
a
li
st,
G
CP
d
a
ta
e
n
g
in
e
e
r
,
a
n
d
si
x
si
g
m
a
g
re
e
n
b
e
lt
,
e
p
i
to
m
ize
s
h
is
ste
a
d
fa
st
c
o
m
m
it
m
e
n
t
to
p
ro
fe
ss
io
n
a
l
e
x
c
e
ll
e
n
c
e
.
Ac
a
d
e
m
ica
ll
y
,
h
e
h
o
l
d
s
a
m
a
ste
r
o
f
De
c
isio
n
An
a
ly
t
ics
fro
m
Vir
g
in
ia
Co
m
m
o
n
we
a
lt
h
U
n
iv
e
rsit
y
,
a
n
M
BA
in
Bu
si
n
e
ss
An
a
ly
t
ics
fro
m
Ch
rist
U
n
iv
e
rsit
y
,
a
n
d
a
Ba
c
h
e
lo
r
o
f
En
g
in
e
e
rin
g
in
E
lec
tri
c
a
l
a
n
d
El
e
c
tro
n
ics
En
g
in
e
e
ri
n
g
fro
m
An
n
a
Un
iv
e
rsit
y
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
a
v
e
e
n
jan
n
a
iah
@g
m
a
il
.
c
o
m
.
Na
k
k
a
T
h
irup
a
th
i
Ra
o
is
a
fu
ll
-
ti
m
e
p
ro
fe
ss
o
r
a
t
VIG
N
AN
’s
In
stit
u
te
o
f
In
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
,
I
n
d
ia
.
He
re
c
e
iv
e
d
h
is
P
h
.
D.
(Co
m
p
u
te
r
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
)
fro
m
An
d
h
ra
Un
iv
e
rsit
y
,
Visa
k
h
a
p
a
tn
a
m
,
In
d
ia
,
in
2
0
1
4
.
He
is
th
e
a
c
a
d
e
m
ic
e
d
it
o
r
o
f
P
LO
S
ON
E
In
tern
a
ti
o
n
a
l
J
o
u
r
n
a
ls
(in
d
e
x
e
d
b
y
S
c
o
p
u
s
,
S
CIE
,
a
n
d
We
b
o
f
S
c
ien
c
e
).
He
p
u
b
l
ish
e
d
9
8
S
c
o
p
u
s
-
i
n
d
e
x
e
d
p
a
p
e
rs
a
n
d
4
7
Web
o
f
S
c
ien
c
e
p
a
p
e
rs
so
fa
r.
H
is
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
so
ft
c
o
m
p
u
ti
n
g
,
m
a
th
e
m
a
ti
c
a
l
m
o
d
e
li
n
g
,
a
n
d
m
e
d
ica
l
ima
g
e
p
ro
c
e
ss
in
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
a
k
k
a
th
iru
@
g
m
a
il
.
c
o
m
or
n
a
k
k
a
th
i
ru
@v
ig
n
a
n
ii
t
.
e
d
u
.
in
.
Ba
la
k
e
sa
v
a
Re
d
d
y
Pa
r
v
a
th
a
l
a
w
o
rk
i
n
g
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
in
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
(Cy
b
e
r
S
e
c
u
r
it
y
a
n
d
Da
ta
S
c
ien
c
e
)
a
n
d
Artifi
c
ial
In
telli
g
e
n
c
e
a
n
d
Da
ta
S
c
ien
c
e
at
VN
R
Vig
n
a
n
a
Jy
o
th
i
In
stit
u
te
o
f
Tec
h
n
o
lo
g
y
.
He
g
ra
d
u
a
ted
i
n
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
In
f
o
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
a
t
JN
TU,
An
d
h
ra
P
ra
d
e
sh
,
In
d
ia.
He
se
c
u
re
d
a
m
a
ste
r
o
f
Tec
h
n
o
l
o
g
y
i
n
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
a
t
JN
TU,
Hy
d
e
ra
b
a
d
,
Tela
n
g
a
n
a
,
In
d
ia.
He
is
p
u
rs
u
in
g
a
P
h
.
D.
in
th
e
fiel
d
o
f
d
e
e
p
lea
rn
in
g
,
m
a
c
h
i
n
e
lea
rn
in
g
,
e
x
p
lain
a
b
le
AI,
a
n
d
n
a
tu
ra
l
la
n
g
u
a
g
e
p
ro
c
e
ss
in
g
a
t
S
R
M
I
n
stit
u
te
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
,
Ch
e
n
n
a
i,
In
d
ia.
He
h
a
s
b
e
e
n
i
n
t
h
e
tea
c
h
in
g
p
ro
fe
ss
i
o
n
fo
r
m
o
re
th
a
n
1
5
y
e
a
rs.
He
h
a
s
p
re
se
n
ted
a
n
u
m
b
e
r
o
f
p
a
p
e
rs
in
n
a
ti
o
n
a
l
a
n
d
in
tern
a
t
io
n
a
l
jo
u
r
n
a
ls,
c
o
n
fe
re
n
c
e
a
n
d
sy
m
p
o
siu
m
s
.
His
m
a
in
a
re
a
o
f
i
n
tere
st
in
c
lu
d
e
s
e
x
p
lai
n
a
b
le
AI,
d
e
e
p
lea
rn
in
g
,
a
n
d
n
a
tu
ra
l
lan
g
u
a
g
e
p
r
o
c
e
ss
in
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
a
lak
e
sa
v
a
re
d
d
y
p
@g
m
a
il
.
c
o
m
.
Ba
n
a
n
a
O
m
k
a
r
La
k
shm
i
J
a
g
a
n
p
re
se
n
t
wo
r
k
in
g
a
s
a
n
a
ss
o
c
iat
e
p
ro
fe
ss
o
r
in
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ie
n
c
e
a
n
d
En
g
i
n
e
e
rin
g
,
Vig
n
a
n
'
s
In
stit
u
te
o
f
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
(A),
Du
v
v
a
d
a
,
Visa
k
h
a
p
a
t
n
a
m
,
An
d
h
ra
P
ra
d
e
sh
,
In
d
ia.
He
re
c
e
iv
e
d
h
is
P
h
.
D.
d
e
g
re
e
fro
m
t
h
e
Ko
n
e
ru
Lak
sh
m
a
iah
Ed
u
c
a
ti
o
n
F
o
u
n
d
a
ti
o
n
(
De
e
m
e
d
to
b
e
U
n
iv
e
rsit
y
)
,
Va
d
d
e
sw
a
ra
m
,
G
u
n
tu
r,
A
n
d
h
ra
P
ra
d
e
sh
,
I
n
d
ia
,
in
2
0
1
6
.
He
p
u
b
li
sh
e
d
se
v
e
ra
l
p
a
p
e
rs
in
in
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls
in
t
h
e
field
s
o
f
sta
ti
stica
l
sig
n
a
l
p
ro
c
e
ss
in
g
,
b
i
o
m
e
d
ica
l
sig
n
a
l
p
ro
c
e
ss
in
g
,
a
n
d
ima
g
e
p
r
o
c
e
ss
in
g
tec
h
n
o
lo
g
ies
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
o
m
k
a
rjag
a
n
@y
a
h
o
o
.
c
o
m
.
Bo
d
a
p
a
ti
Ve
n
k
a
t
a
Ra
j
a
n
n
a
is
c
u
rre
n
tl
y
wo
rk
in
g
a
s
a
n
a
ss
o
c
ia
te
p
ro
fe
ss
o
r
i
n
t
h
e
De
p
a
rtme
n
t
o
f
E
lec
tri
c
a
l
a
n
d
El
e
c
tro
n
ics
E
n
g
i
n
e
e
rin
g
a
t
M
L
R
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
Hy
d
e
ra
b
a
d
,
In
d
ia.
He
re
c
e
iv
e
d
a
P
h
.
D.
in
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ics
E
n
g
i
n
e
e
rin
g
a
t
Ko
n
e
ru
Lak
sh
m
a
iah
Ed
u
c
a
ti
o
n
F
o
u
n
d
a
ti
o
n
,
G
u
n
tu
r,
In
d
ia,
i
n
2
0
2
1
.
His
c
u
rre
n
t
re
se
a
rc
h
in
c
l
u
d
e
s
,
d
y
n
a
m
ic
m
o
d
e
li
n
g
o
f
b
a
tt
e
ries
fo
r
re
n
e
wa
b
le
e
n
e
rg
y
sto
ra
g
e
,
b
a
tt
e
ry
m
a
n
a
g
e
m
e
n
t
sy
ste
m
s
(BM
S
)
f
o
r
e
lec
tri
c
v
e
h
icle
s
a
n
d
p
o
rtab
le
e
lec
tro
n
ics
a
p
p
li
c
a
ti
o
n
s,
re
n
e
wa
b
le
e
n
e
rg
y
s
o
u
rc
e
s
in
teg
ra
ti
o
n
wit
h
b
a
tt
e
ry
e
n
e
r
g
y
sto
ra
g
e
sy
ste
m
s
(BES
S
),
sm
a
rt
m
e
terin
g
a
n
d
sm
a
rt
g
rid
s,
m
icro
-
g
rid
s,
a
u
t
o
m
a
ti
c
m
e
ter
re
a
d
in
g
(AMR)
d
e
v
ice
s,
G
S
M
/G
P
RS
a
n
d
p
o
we
r
li
n
e
c
a
r
rier
(P
LC)
c
o
m
m
u
n
ica
ti
o
n
,
a
n
d
v
a
rio
u
s
m
o
d
u
lati
o
n
tec
h
n
i
q
u
e
s
s
u
c
h
a
s
QPS
K,
B
P
S
K,
A
S
K,
F
S
K,
OOK
,
a
n
d
G
M
S
K.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ra
jan
n
a
b
v
2
0
1
2
@
g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.