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
.
3
0
3
~
3
1
2
I
SS
N:
2252
-
8
8
1
4
,
DOI
:
1
0
.
1
1
5
9
1
/ijaas
.
v
1
5
.
i
1
.
pp
303
-
3
1
2
303
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
a
s
.
ia
esco
r
e.
co
m
H
y
brid d
eep l
ea
rning
and ensem
bl
e learning
appro
a
ch f
o
r high
-
a
ccuracy
t
hy
ro
id
disea
se cla
ss
ificat
io
n
Sh
uriy
a
B
a
lu
s
a
m
y
1
,
B
a
la
j
is
ha
nm
ug
a
m Viv
eka
na
dh
a
n
2
,
P
ra
t
him
a
M
a
bel J
o
hn
3
,
Su
s
h
m
a
Su
nil
B
ho
s
le
4
1
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
,
U
n
i
t
e
d
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
C
o
i
m
b
a
t
o
r
e
,
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
,
H
i
n
d
u
s
t
a
n
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
C
o
i
m
b
a
t
o
r
e
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
D
a
y
a
n
a
n
d
a
S
a
g
a
r
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
4
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
S
h
r
i
J
a
g
d
i
sh
p
r
a
sa
d
J
h
a
b
a
r
mal
Ti
b
r
e
w
a
l
a
U
n
i
v
e
r
si
t
y
,
J
h
u
n
j
h
u
n
u
,
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
Sep
4
,
2
0
2
5
R
ev
is
ed
Dec
2
7
,
2
0
2
5
Acc
ep
ted
J
an
1
,
2
0
2
6
Th
y
r
o
id
d
ise
a
se
is
a
c
o
m
m
o
n
e
n
d
o
c
rin
e
d
is
o
rd
e
r
a
ffe
c
ti
n
g
t
h
e
th
y
r
o
id
g
lan
d
,
a
sm
a
ll
b
u
tt
e
rfly
-
sh
a
p
e
d
o
rg
a
n
a
t
th
e
b
a
se
o
f
th
e
n
e
c
k
.
Ac
c
o
rd
in
g
t
o
th
e
Wo
rld
He
a
lt
h
O
r
g
a
n
iza
ti
o
n
(W
H
O),
n
e
a
rly
o
n
e
b
il
li
o
n
p
e
o
p
le
wo
r
ld
wid
e
a
re
a
ffe
c
ted
b
y
th
y
ro
i
d
-
re
late
d
c
o
n
d
it
io
n
s.
C
o
n
v
e
n
ti
o
n
a
l
d
ia
g
n
o
stic
m
e
th
o
d
s
,
su
c
h
a
s
th
y
ro
id
sc
a
n
s
a
n
d
f
u
n
c
ti
o
n
tes
ts,
a
re
o
ften
c
o
stly
,
ti
m
e
-
c
o
n
su
m
i
n
g
,
a
n
d
c
o
m
p
lex
fo
r
c
li
n
icia
n
s
to
i
n
t
e
rp
re
t.
To
o
v
e
rc
o
m
e
th
e
se
li
m
it
a
ti
o
n
s,
t
h
is
stu
d
y
in
t
ro
d
u
c
e
s
a
n
o
v
e
l
tem
p
o
r
a
l
c
o
n
d
i
ti
o
n
a
l
-
M
a
rk
o
v
ra
n
d
o
m
f
ield
(
TC
-
M
RF
)
fra
m
e
wo
rk
fo
r
e
a
rly
d
e
te
c
ti
o
n
a
n
d
c
las
sifica
ti
o
n
o
f
t
h
y
r
o
i
d
d
ise
a
se
.
Th
e
m
u
lt
i
-
m
o
d
a
li
ty
ima
g
e
s
c
o
m
p
u
ted
t
o
m
o
g
ra
p
h
y
(CT),
m
a
g
n
e
ti
c
re
so
n
a
n
c
e
ima
g
in
g
(
M
RI),
a
n
d
u
lt
ra
so
u
n
d
(US)
a
re
c
o
ll
e
c
ted
fr
o
m
th
e
Im
a
g
e
Ne
t
d
a
tab
a
se
a
n
d
p
re
p
r
o
c
e
ss
e
d
u
sin
g
c
o
n
tras
t
stre
tch
in
g
a
d
a
p
ti
v
e
G
a
u
ss
ian
sta
r
(CS
AG
S
)
fil
ter
to
imp
r
o
v
e
ima
g
e
c
larity
.
T
h
e
e
n
h
a
n
c
e
d
ima
g
e
s
a
re
th
e
n
p
ro
c
e
ss
e
d
o
v
e
r
a
c
o
n
v
o
lu
t
io
n
a
l
n
e
u
ra
l
n
e
two
r
k
(CNN
)
f
o
r
fe
a
tu
re
e
x
trac
ti
o
n
.
Th
e
se
fe
a
tu
re
s
a
re
c
la
ss
ifi
e
d
u
sin
g
a
ra
n
d
o
m
f
o
re
st
(RF
)
m
o
d
e
l
t
o
d
e
term
in
e
wh
e
th
e
r
th
e
th
y
ro
i
d
c
o
n
d
it
io
n
is
n
o
rm
a
l
o
r
a
b
n
o
rm
a
l.
T
h
e
p
r
o
p
o
se
d
TC
-
M
RF
a
c
h
iev
e
s
a
c
las
sifica
ti
o
n
a
c
c
u
ra
c
y
o
f
9
8
.
2
7
%
a
n
d
F
1
-
sc
o
re
o
f
9
6
.
0
5
%
.
Th
e
TC
-
M
RF
e
n
h
a
n
c
e
s
th
e
to
t
a
l
a
c
c
u
ra
c
y
ra
n
g
e
o
f
6
.
3
0
%
,
4
.
1
1
%
,
a
n
d
5
.
3
6
%
b
e
tt
e
r
th
a
n
n
a
i
v
e
Ba
y
e
s,
m
u
l
ti
lay
e
r
p
e
rc
e
p
tro
n
(M
LP
)
,
a
n
d
d
e
c
isi
o
n
tree
,
re
sp
e
c
ti
v
e
ly
.
K
ey
w
o
r
d
s
:
Ad
ap
tiv
e
Gau
s
s
ian
s
tar
f
ilter
C
o
n
tr
ast s
tr
etch
in
g
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
R
an
d
o
m
f
o
r
est
T
h
y
r
o
i
d
d
is
ea
s
e
W
o
r
ld
Hea
lth
O
r
g
an
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
:
Su
s
h
m
a
Su
n
il B
h
o
s
le
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics an
d
C
o
m
m
u
n
icatio
n
E
n
g
in
ee
r
i
n
g
Sh
r
i Jag
d
is
h
p
r
asad
J
h
ab
ar
m
al
T
ib
r
ewa
la
Un
iv
er
s
ity
Vid
y
an
ag
ar
i,
J
h
u
n
jh
u
n
u
,
R
aja
s
th
an
,
I
n
d
ia
E
m
ail:
s
u
s
h
m
a4
4
b
@
o
u
tlo
o
k
.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
y
r
o
i
d
d
is
o
r
d
e
r
s
,
in
clu
d
in
g
h
y
p
o
th
y
r
o
i
d
is
m
an
d
h
y
p
er
t
h
y
r
o
id
is
m
,
ar
e
am
o
n
g
t
h
e
m
o
s
t
co
m
m
o
n
en
d
o
cr
in
e
ab
n
o
r
m
alities
wo
r
ld
wid
e,
s
ec
o
n
d
o
n
ly
t
o
d
iab
ete
s
[
1
]
.
T
h
e
t
h
y
r
o
id
g
lan
d
is
ess
en
tial
f
o
r
r
e
g
u
latin
g
b
lo
o
d
p
r
ess
u
r
e,
h
ea
r
t
r
ate,
m
etab
o
lis
m
,
an
d
b
o
d
y
tem
p
er
atu
r
e
b
ec
au
s
e
it
p
r
o
d
u
ce
s
h
o
r
m
o
n
es
s
u
ch
as
th
y
r
o
x
i
n
e
(
T
4
)
an
d
tr
iio
d
o
th
y
r
o
n
in
e
(
T
3
)
[
2
]
.
Dy
s
f
u
n
ctio
n
in
th
e
th
y
r
o
id
o
r
r
elate
d
o
r
g
an
s
s
u
ch
as
th
e
p
itu
itar
y
an
d
h
y
p
o
th
alam
u
s
ca
n
d
is
r
u
p
t
h
o
r
m
o
n
al
b
alan
c
e,
lead
in
g
to
s
er
io
u
s
h
ea
lth
co
m
p
licatio
n
s
[
3
]
.
Hy
p
o
th
y
r
o
id
is
m
ca
n
r
esu
lt
in
f
atig
u
e
,
weig
h
t
g
ain
,
d
e
p
r
ess
io
n
,
an
d
c
o
g
n
itiv
e
im
p
air
m
en
t,
wh
er
ea
s
h
y
p
er
th
y
r
o
i
d
is
m
m
ay
ca
u
s
e
an
x
iety
,
weig
h
t
lo
s
s
,
p
alp
itatio
n
s
,
an
d
ca
r
d
io
v
ascu
lar
is
s
u
es
[
4
]
.
E
ar
ly
an
d
ac
cu
r
ate
d
iag
n
o
s
is
o
f
th
ese
c
o
n
d
itio
n
s
is
cr
u
cial
to
p
r
ev
e
n
t
co
m
p
licatio
n
s
an
d
en
s
u
r
e
e
f
f
ec
tiv
e
tr
ea
tm
en
t,
h
ig
h
lig
h
tin
g
th
e
n
ee
d
f
o
r
im
p
r
o
v
ed
d
ia
g
n
o
s
tic
ap
p
r
o
ac
h
es
[
5
]
.
T
r
a
d
itio
n
al
d
iag
n
o
s
tic
m
eth
o
d
s
,
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
:
303
-
3
1
2
304
in
clu
d
in
g
la
b
o
r
ato
r
y
b
lo
o
d
te
s
ts
an
d
im
ag
in
g
tec
h
n
iq
u
es
s
u
ch
as
u
ltra
s
o
u
n
d
(
US)
,
co
m
p
u
ted
to
m
o
g
r
a
p
h
y
(
CT
)
,
an
d
m
a
g
n
etic
r
eso
n
a
n
ce
im
ag
in
g
(
MRI
)
,
ar
e
wid
ely
u
s
ed
to
d
etec
t th
y
r
o
id
a
b
n
o
r
m
ali
ties
[
6
]
.
B
lo
o
d
test
s
a
s
s
es
s
h
o
r
m
o
n
e
lev
els
to
d
eter
m
in
e
th
y
r
o
i
d
f
u
n
ctio
n
,
wh
ile
im
ag
in
g
p
r
o
v
i
d
es
in
s
ig
h
ts
in
to
s
tr
u
ctu
r
al
an
o
m
alies
[
7
]
.
Ho
wev
er
,
t
h
e
s
e
m
eth
o
d
s
ar
e
o
f
ten
d
ep
en
d
en
t
o
n
h
u
m
an
ex
p
er
tis
e
an
d
in
ter
p
r
etatio
n
,
wh
ich
ca
n
r
esu
lt
in
in
co
n
s
is
ten
t
o
u
tco
m
es
an
d
in
cr
ea
s
ed
d
iag
n
o
s
tic
er
r
o
r
s
[
8
]
.
R
ec
en
t
d
ev
elo
p
m
en
ts
in
d
ee
p
lear
n
in
g
(
DL
)
[
9
]
an
d
m
ac
h
in
e
lear
n
in
g
(
ML
)
[
1
0
]
h
av
e
d
e
m
o
n
s
tr
ated
p
r
o
m
is
e
in
tack
lin
g
th
ese
is
s
u
es
b
y
f
ac
ilit
atin
g
au
to
m
ated
,
d
ata
-
d
r
iv
en
in
ter
p
r
etatio
n
o
f
m
ed
ical
i
m
ag
er
y
an
d
p
atien
t
d
ata
[
1
1
]
.
Alg
o
r
ith
m
s
s
u
ch
as
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SVM)
,
r
an
d
o
m
f
o
r
ests
(
R
F),
an
d
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NN)
[
1
2
]
c
an
ex
tr
ac
t
p
atter
n
s
f
r
o
m
co
m
p
lex
d
atasets
,
o
f
f
er
in
g
h
i
g
h
er
a
cc
u
r
ac
y
,
ef
f
icien
cy
,
an
d
o
b
jectiv
ity
c
o
m
p
ar
e
d
to
tr
ad
itio
n
al
m
eth
o
d
s
[
1
3
]
.
Nev
er
th
eless
,
cu
r
r
en
t
m
o
d
els
o
f
ten
f
o
cu
s
eith
er
o
n
f
ea
tu
r
e
ex
tr
ac
tio
n
o
r
class
if
icatio
n
alo
n
e
an
d
m
ay
f
ail
to
in
t
eg
r
ate
b
o
th
o
p
tim
ally
,
lim
itin
g
th
eir
p
er
f
o
r
m
an
ce
in
r
ea
l
-
wo
r
ld
clin
ical
s
ce
n
ar
i
o
s
[
1
4
]
.
T
o
a
d
d
r
ess
th
ese
ch
allen
g
es,
th
is
s
tu
d
y
p
r
o
p
o
s
es
a
n
o
v
el
tem
p
o
r
al
co
n
d
itio
n
al
-
Ma
r
k
o
v
r
an
d
o
m
f
ield
(
TC
-
M
RF
)
f
o
r
th
y
r
o
id
d
is
o
r
d
er
d
etec
tio
n
.
T
h
e
k
ey
c
o
n
tr
ib
u
tio
n
s
o
f
th
is
r
esear
ch
ar
e
m
u
lti
-
m
o
d
ality
i
m
ag
es
wer
e
o
b
tain
ed
f
r
o
m
t
h
e
I
m
ag
eNe
t
d
ataset.
I
m
ag
e
Net
is
a
lar
g
e
-
s
ca
le
an
n
o
tated
d
atab
ase
th
at
p
r
o
v
i
d
es
h
ig
h
-
q
u
ality
,
f
u
ll
-
r
eso
lu
ti
o
n
im
ag
es
ac
r
o
s
s
d
iv
er
s
e
ca
t
eg
o
r
ies.
Usi
n
g
th
is
d
ataset
en
s
u
r
es
v
a
r
iab
ilit
y
an
d
r
ich
n
ess
in
in
p
u
t
s
am
p
les,
th
er
eb
y
en
h
a
n
cin
g
th
e
g
en
e
r
aliza
tio
n
ab
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
T
C
-
MRF
f
r
am
ewo
r
k
.
T
h
e
m
u
lti
-
m
o
d
ality
im
ag
es
ar
e
p
r
e
p
r
o
ce
s
s
ed
b
y
C
SAGS
f
ilter
to
e
n
h
an
ce
th
e
im
ag
e
q
u
ality
an
d
r
ed
u
ce
th
e
n
o
is
e
ar
tifa
cts.
I
n
o
r
d
er
to
ex
tr
ac
t
m
u
lti
-
lev
el
d
is
cr
im
in
ativ
e
f
ea
tu
r
es
f
r
o
m
lo
w
-
lev
el
tex
tu
r
e
an
d
e
d
g
e
p
atter
n
s
to
h
ig
h
-
lev
el
s
em
an
tic
r
ep
r
esen
tatio
n
s
o
f
th
y
r
o
id
ab
n
o
r
m
alities
,
th
e
d
en
o
is
ed
im
ag
es
ar
e
f
e
d
in
to
a
C
NN.
B
a
s
ed
o
n
th
e
ex
tr
ac
te
d
f
ea
tu
r
es
,
th
e
R
F
class
if
ies
t
h
y
r
o
id
d
is
ea
s
e
in
to
f
o
u
r
class
es
:
n
o
r
m
al,
h
y
p
o
t
h
y
r
o
id
is
m
,
h
y
p
er
t
h
y
r
o
id
is
m
,
an
d
th
y
r
o
id
n
o
d
u
les.
I
n
c
o
m
p
ar
is
o
n
to
s
in
g
l
e
class
if
ier
s
,
it
im
p
r
o
v
es
ac
cu
r
ac
y
,
r
o
b
u
s
tn
ess
,
an
d
g
en
e
r
aliza
tio
n
b
y
c
o
n
s
tr
u
ctin
g
s
ev
e
r
a
l
d
ec
is
io
n
tr
ee
s
an
d
co
m
b
in
in
g
th
eir
o
u
tp
u
ts
b
y
m
ajo
r
ity
v
o
ti
n
g
.
T
h
e
ef
f
icien
cy
o
f
th
e
p
r
o
p
o
s
ed
T
C
-
MRF
m
o
d
el
was
ev
alu
ated
b
ased
o
n
th
e
cr
iter
ia
,
in
clu
d
es
F1
-
s
co
r
e,
p
r
ec
is
io
n
,
r
ec
all,
s
p
e
cif
icity
,
an
d
ac
c
u
r
ac
y
.
T
h
is
s
tr
u
ctu
r
e
o
f
th
e
p
ap
er
is
o
r
g
an
ized
as
f
o
llo
ws:
s
ec
tio
n
2
ex
p
lain
s
th
e
liter
atu
r
e
s
u
r
v
ey
in
d
etail.
Sectio
n
3
ex
p
lain
s
th
e
p
r
o
p
o
s
ed
T
C
-
MRF
m
eth
o
d
.
Sectio
n
4
ex
p
lain
s
th
e
r
esu
lt
s
an
d
d
i
s
cu
s
s
io
n
.
Sectio
n
5
ex
p
lain
s
th
e
co
n
cl
u
s
io
n
an
d
f
u
tu
r
e
wo
r
k
.
2.
L
I
T
E
R
AT
U
RE
SU
RVE
Y
I
n
r
ec
en
t
y
ea
r
s
,
s
ev
er
al
r
esear
ch
er
s
h
av
e
p
r
o
p
o
s
ed
d
iv
er
s
e
f
r
am
ewo
r
k
s
aim
ed
at
en
h
an
cin
g
th
e
p
r
ec
is
io
n
o
f
th
y
r
o
id
d
is
ea
s
e
class
if
icatio
n
in
p
atien
ts
.
T
h
is
s
ec
tio
n
p
r
o
v
id
es
a
co
n
cise
an
aly
s
is
o
f
s
o
m
e
o
f
th
ese
ap
p
r
o
ac
h
es.
i)
T
o
p
s
ir
et
a
l
.
[
1
5
]
s
u
g
g
ested
a
s
o
p
h
is
ticated
ML
m
et
h
o
d
th
at
co
m
b
in
es
Ko
l
m
o
g
o
r
o
v
-
Ar
n
o
ld
n
etwo
r
k
s
(
KANs)
f
o
r
class
if
icatio
n
w
ith
g
en
er
ativ
e
ad
v
er
s
ar
ial
n
e
two
r
k
s
f
o
r
d
ata
au
g
m
en
tatio
n
.
Mu
ltil
ay
er
p
er
ce
p
tr
o
n
s
(
ML
P),
lo
g
is
tic
r
eg
r
ess
io
n
(
L
R
)
,
R
F,
SVM,
a
n
d
KANs
wer
e
am
o
n
g
th
e
M
L
m
o
d
els
th
at
wer
e
tr
ain
ed
an
d
ass
ess
ed
.
I
n
p
ar
ticu
lar
,
t
h
e
KAN
m
o
d
el
o
u
t
p
er
f
o
r
m
ed
C
NN
ap
p
licatio
n
s
with
an
AC
o
f
9
8
.
6
8
% a
n
d
an
R
F F1
-
s
co
r
e
o
f
9
8
.
0
0
%.
ii)
Sh
ar
m
a
et
a
l.
[
1
6
]
s
u
g
g
ested
t
h
at
a
p
r
e
-
tr
ain
ed
m
o
d
el
lik
e
Mix
er
-
ML
P,
DeiT
,
an
d
Swin
T
r
an
s
f
o
r
m
e
r
is
u
tili
ze
d
f
o
r
f
ea
t
u
r
e
ex
tr
ac
tio
n
.
T
o
s
o
lv
e
p
r
o
b
lem
s
with
class
im
b
alan
ce
,
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
co
m
b
in
es
an
en
s
em
b
le
m
o
d
e
l
with
s
tr
a
tifie
d
o
v
er
-
s
am
p
lin
g
.
T
h
e
o
p
t
im
al
v
alu
es
ar
e
9
2
.
8
3
%,
8
7
.
7
6
%,
9
7
.
6
6
%,
8
8
.
8
9
%,
0
.
9
5
5
1
,
an
d
0
.
9
3
5
7
f
o
r
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all
,
s
p
ec
if
icity
,
F1
-
s
co
r
e,
an
d
R
OC
-
AUC
s
co
r
e.
iii)
Xian
g
et
a
l
.
[
1
7
]
s
u
g
g
ested
a
m
u
lti
-
atten
tio
n
g
u
id
ed
UNe
t
(
MA
UNe
t)
f
o
r
s
eg
m
en
tin
g
th
y
r
o
id
n
o
d
u
les.
I
t
u
s
es
a
m
u
lti
-
s
ca
le
cr
o
s
s
atten
tio
n
(
MSC
A)
m
o
d
u
le
f
o
r
th
e
in
itial
v
is
u
al
f
ea
tu
r
e
ex
tr
ac
ti
o
n
s
tep
.
T
h
e
m
o
d
el
is
tr
ain
e
d
u
t
ilizin
g
th
e
f
ed
er
al
lear
n
i
n
g
a
p
p
r
o
ac
h
t
o
p
r
o
tect
p
r
iv
ac
y
.
T
h
e
m
o
d
el
Dice
s
co
r
es
o
n
th
e
th
r
ee
ce
n
ter
d
atasets
ar
e
0
.
9
0
8
,
0
.
9
1
2
,
an
d
0
.
8
8
7
,
r
esp
ec
tiv
el
y
,
b
ased
o
n
th
e
e
x
p
er
im
e
n
tal
f
in
d
in
g
s
.
iv
)
R
az
a
et
al
.
[
1
8
]
s
u
g
g
ested
a
n
ar
tific
ial
in
tellig
en
ce
-
b
ased
m
eth
o
d
f
o
r
th
y
r
o
id
d
is
ea
s
e
ea
r
ly
d
etec
tio
n
.
I
n
o
r
d
er
to
d
iag
n
o
s
e
th
y
r
o
id
d
is
ea
s
e
an
d
ad
d
r
ess
is
s
u
es
with
cl
ass
im
b
alan
ce
,
th
is
s
tu
d
y
u
s
ed
a
f
in
e
-
tu
n
e
d
lig
h
t
g
r
ad
ie
n
t
b
o
o
s
ter
m
ac
h
in
e
tech
n
iq
u
e
an
d
th
e
n
o
m
in
al
co
n
tin
u
o
u
s
s
y
n
th
etic
m
in
o
r
ity
o
v
er
s
am
p
lin
g
s
tr
ateg
y
f
o
r
d
ata
b
ala
n
cin
g
.
I
n
co
m
p
ar
is
o
n
t
o
th
e
s
tate
-
of
-
th
e
-
ar
t
tech
n
o
l
o
g
y
,
th
e
p
r
o
p
o
s
ed
s
y
n
th
etic
m
in
o
r
ity
o
v
er
-
s
am
p
lin
g
tech
n
iq
u
e
-
n
o
m
in
al
an
d
c
o
n
tin
u
o
u
s
-
lig
h
t
g
r
a
d
ien
t
b
o
o
s
tin
g
m
ac
h
i
n
e
(
SMOT
E
-
NC
-
L
GB
M
)
m
eth
o
d
o
lo
g
y
ac
h
iev
ed
h
ig
h
ac
cu
r
ac
y
p
er
f
o
r
m
a
n
ce
r
atin
g
s
o
f
0
.
9
6
.
v)
Ud
d
in
et
a
l.
[
1
9
]
s
u
g
g
ested
a
h
y
b
r
id
f
ea
t
u
r
e
s
elec
tio
n
tec
h
n
iq
u
e
f
o
r
t
h
y
r
o
i
d
d
is
ea
s
e
p
r
e
d
ictio
n
th
at
is
b
ased
o
n
en
s
em
b
le
ML
.
T
o
c
h
o
o
s
e
th
e
b
est
th
y
r
o
id
p
r
ed
ic
tio
n
o
u
tco
m
e
,
we
u
s
ed
f
iv
e
ML
m
o
d
els
in
ad
d
itio
n
to
th
e
E
n
s
em
b
le
ML
class
if
ier
.
Us
in
g
th
e
ex
tr
em
e
g
r
ad
ie
n
t
b
o
o
s
tin
g
(
XGBo
o
s
t
)
an
d
SelectKBe
s
t
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
,
th
e
e
n
s
em
b
le
ML
class
if
ier
ac
h
iev
es
th
e
b
est
r
esu
lts
o
n
h
ar
d
v
o
tin
g
o
n
R
F a
n
d
DT
with
1
0
0
%
r
ec
all
an
d
9
9
.
7
1
%
ac
cu
r
ac
y
.
v
i)
Ak
ter
an
d
M
u
s
taf
a
[
2
0
]
s
u
g
g
e
s
ted
a
m
eth
o
d
f
o
r
f
ea
tu
r
e
s
ig
n
if
ican
ce
an
aly
s
is
an
d
m
o
d
el
e
x
p
lan
atio
n
th
a
t
h
as
b
ee
n
in
v
esti
g
ated
b
o
th
lo
ca
lly
an
d
g
lo
b
ally
u
tili
zin
g
ex
p
lain
ab
le
ar
tific
ial
in
tellig
en
ce
(
XAI
)
to
o
ls
.
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
Hyb
r
id
d
ee
p
lea
r
n
in
g
a
n
d
en
s
emb
le
lea
r
n
in
g
a
p
p
r
o
a
ch
fo
r
h
ig
h
-
a
cc
u
r
a
cy
…
(
S
h
u
r
iya
B
a
lu
s
a
my
)
305
L
astl
y
,
th
e
d
o
m
ain
ex
p
er
ts
c
o
n
f
ir
m
th
e
XAI
r
esu
lts
.
Acc
o
r
d
in
g
to
ex
p
er
im
en
tal
d
ata,
o
u
r
s
u
g
g
ested
m
ec
h
an
is
m
m
ay
ac
c
u
r
ately
ex
p
l
ain
th
e
m
o
d
els an
d
is
u
s
ef
u
l
in
d
etec
tin
g
th
y
r
o
id
illn
ess
.
v
ii)
Kesav
u
lu
an
d
Kan
n
ad
asan
[
2
1
]
p
r
o
p
o
s
ed
a
b
etter
b
io
-
in
s
p
ir
ed
m
eth
o
d
f
o
r
th
y
r
o
i
d
p
r
ed
icti
o
n
u
s
in
g
ML
.
I
n
o
r
d
e
r
to
in
cr
ea
s
e
th
e
ac
cu
r
a
cy
o
f
th
y
r
o
id
d
is
ea
s
e
p
r
ed
ictio
n
,
th
is
wo
r
k
ex
p
lo
r
es
th
e
u
s
e
o
f
s
ev
er
al
ML
an
d
DL
tech
n
iq
u
es,
in
clu
d
in
g
R
F,
d
ec
is
io
n
tr
ee
,
SVM,
an
d
KNN.
T
h
e
R
F
with
p
ar
ticle
s
n
ak
e
s
war
m
o
p
tim
izatio
n
(
PSSO
)
m
o
d
el
ac
h
iev
ed
9
8
.
7
%
ac
cu
r
ac
y
,
9
8
.
4
7
%
F1
-
s
co
r
e
,
9
8
.
5
1
%
p
r
e
cisi
o
n
,
9
8
.
7
%
r
ec
all
,
an
d
9
8
%
s
p
ec
if
icity
.
v
iii)
B
an
er
jee
et
a
l.
[
2
2
]
p
r
o
p
o
s
ed
a
h
y
b
r
id
DL
s
tr
ateg
y
th
at
c
o
m
b
in
es
s
tatis
tical
v
alid
atio
n
with
d
ee
p
f
ea
tu
r
e
atten
tio
n
to
im
p
r
o
v
e
th
y
r
o
id
US
s
eg
m
en
tatio
n
.
T
AT
HA
is
a
n
o
v
el
DL
ar
c
h
itectu
r
e
th
at
t
h
e
r
esear
ch
er
s
cr
ea
ted
b
y
th
e
g
o
al
o
f
in
cr
ea
s
in
g
th
e
ac
cu
r
ac
y
o
f
th
y
r
o
id
U
S
im
ag
e
s
eg
m
en
tatio
n
.
T
h
e
r
esu
lts
v
alid
ate
th
at
T
AT
HA
is
n
o
w
a
v
ital
to
o
l
f
o
r
t
h
y
r
o
id
im
ag
in
g
an
d
clin
ical
ap
p
licatio
n
s
f
o
r
r
ese
ar
ch
er
s
an
d
p
h
y
s
ician
s
.
B
ased
o
n
th
e
r
e
v
iewe
d
liter
atu
r
e,
v
a
r
io
u
s
DL
an
d
ML
a
p
p
r
o
ac
h
es
h
av
e
b
ee
n
d
ev
elo
p
ed
f
o
r
th
y
r
o
i
d
d
is
ea
s
e
clas
s
if
icatio
n
.
Ho
wev
er
,
th
ese
m
eth
o
d
s
s
till
f
ac
e
s
ev
er
al
lim
itatio
n
s
,
s
u
ch
as
h
ig
h
co
m
p
u
tatio
n
al
co
m
p
lex
ity
,
d
ep
e
n
d
en
c
y
o
n
s
y
n
t
h
etic
d
ata
a
u
g
m
en
tatio
n
th
at
m
ay
n
o
t
f
u
lly
r
ep
r
esen
t
r
ea
l
-
wo
r
ld
ca
s
es,
p
er
s
is
ten
t
class
im
b
alan
ce
is
s
u
es
d
esp
ite
o
v
e
r
s
am
p
lin
g
s
tr
ateg
ies,
r
estricte
d
g
en
e
r
aliza
b
ilit
y
d
u
e
to
lim
ited
o
r
s
in
g
le
-
ce
n
ter
d
atasets
,
an
d
ch
allen
g
es
in
clin
ical
in
teg
r
atio
n
ca
u
s
ed
b
y
a
lack
o
f
in
ter
p
r
e
tab
ilit
y
.
T
o
ad
d
r
ess
th
ese
s
h
o
r
tco
m
in
g
s
,
th
e
T
C
-
MRF
m
o
d
el
is
p
r
o
p
o
s
ed
as
a
m
o
r
e
ef
f
ec
ti
v
e
an
d
r
eliab
le
s
o
lu
tio
n
f
o
r
t
h
y
r
o
id
d
is
ea
s
e
class
if
icatio
n
.
3.
P
RO
P
O
SE
D
M
E
T
H
O
D
I
n
th
is
s
ec
tio
n
,
th
e
T
C
-
MRF
m
o
d
el
is
u
tili
ze
d
to
class
if
y
th
y
r
o
id
d
is
ea
s
e.
Fig
u
r
e
1
d
i
s
p
lay
s
th
e
g
en
er
al
s
tr
u
ct
u
r
e
o
f
th
is
p
r
o
p
o
s
ed
T
C
-
MRF
m
o
d
el.
T
h
e
m
o
d
el
e
n
ab
les
ef
f
ec
tiv
e
class
if
icatio
n
th
r
o
u
g
h
its
in
teg
r
ated
f
r
a
m
ewo
r
k
.
Fig
u
r
e
1
.
Pro
p
o
s
ed
T
C
-
MRF
m
o
d
el
3
.
1
.
Da
t
a
s
et
des
cr
iptio
n
I
m
ag
es
ar
e
r
ep
r
esen
ted
b
y
t
h
e
I
m
ag
eNe
t
o
n
to
l
o
g
y
b
ased
o
n
t
h
e
W
o
r
d
Net
m
o
d
el.
T
h
e
g
o
al
o
f
I
m
ag
eNe
t is to
ad
d
5
0
0
-
1
,
0
0
0
h
ig
h
-
q
u
ality
,
f
u
ll
-
r
eso
lu
tio
n
im
ag
es o
n
av
er
ag
e
to
ea
ch
o
f
t
h
e
8
0
,
0
0
0
s
u
b
s
ets o
f
W
o
r
d
N
et.
T
h
is
will
r
esu
lt
i
n
m
illi
o
n
s
o
f
an
n
o
tated
im
a
g
es
ar
r
an
g
ed
in
W
o
r
d
Net
s
em
an
tic
h
ier
a
r
ch
y
.
Gath
er
in
g
p
atien
t
im
ag
es
f
o
r
ev
er
y
s
u
b
s
et
is
th
e
in
itial
s
t
ep
in
I
m
ag
eNe
t.
E
v
e
n
tu
ally
,
I
m
ag
eNe
t
p
r
o
v
id
e
s
500
-
1
,
0
0
0
clea
n
im
a
g
es.
C
o
n
s
eq
u
en
tly
,
it
g
ath
er
s
a
b
ig
co
lle
ctio
n
o
f
p
atien
t im
ag
es.
3
.
2
.
Da
t
a
pre
-
pro
ce
s
s
ing
Me
d
ical
im
ag
es
ar
e
im
p
r
o
v
ed
b
y
p
r
e
-
p
r
o
ce
s
s
in
g
b
y
lo
wer
in
g
n
o
is
e
an
d
ad
ju
s
tin
g
h
ig
h
l
ig
h
tin
g
.
A
s
tr
aig
h
tf
o
r
war
d
m
eth
o
d
f
o
r
en
h
an
cin
g
im
ag
es
is
ca
lled
co
n
tr
ast
s
tr
etch
in
g
,
wh
ich
in
cr
ea
s
es
an
im
ag
e’
s
co
n
tr
ast
b
y
wid
en
in
g
its
r
an
g
e
o
f
in
ten
s
ity
v
alu
es.
T
h
is
is
p
ar
ticu
lar
ly
u
s
ef
u
l
f
o
r
im
a
g
es
with
lo
w
co
n
tr
ast,
wh
ich
ca
n
r
esu
lt
f
r
o
m
p
o
o
r
illu
m
in
atio
n
o
r
o
th
e
r
ac
q
u
is
itio
n
p
r
o
b
lem
s
.
I
t
in
d
icate
s
th
e
i
m
ag
e’
s
lo
west
an
d
m
ax
im
u
m
in
te
n
s
ity
v
alu
es.
M
ath
em
atica
lly
,
f
o
r
p
ix
el
in
ten
s
i
ty
I
as in
(
1
)
.
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
:
303
-
3
1
2
306
=
−
−
×
(
−
−
−
)
+
−
(
1
)
T
h
e
ter
m
ad
ap
tiv
e
Gau
s
s
ian
s
tar
f
ilter
c
o
m
b
in
e
th
e
c
o
n
ce
p
ts
o
f
ad
ap
tiv
e
f
ilter
in
g
,
Gau
s
s
ian
f
ilter
in
g
,
an
d
s
tar
f
ilter
in
g
.
T
h
is
f
ilter
ad
a
p
tiv
ely
ap
p
lies
Gau
s
s
ian
s
m
o
o
th
in
g
t
o
en
h
a
n
ce
s
tar
-
lik
e
f
ea
tu
r
es in
an
im
ag
e.
3
.
3
.
F
e
a
t
ure
ex
t
r
a
ct
io
n
C
NN
[
2
3
]
is
u
s
ed
to
ex
tr
ac
t
th
e
f
ea
tu
r
e
o
f
th
e
im
ag
e.
C
NN,
with
its
ca
p
ac
ity
to
a
u
t
o
m
atica
lly
an
aly
ze
an
d
e
x
tr
ac
t
co
m
p
licated
in
f
o
r
m
atio
n
f
r
o
m
m
e
d
ical
im
ag
es
,
f
o
r
id
e
n
tify
in
g
th
y
r
o
id
d
is
ea
s
e.
I
n
th
e
C
NN
ar
ch
itectu
r
e,
a
co
n
v
o
l
u
tio
n
lay
er
is
a
b
asic
elem
en
t
th
at
u
s
u
ally
co
m
b
in
es
lin
ea
r
an
d
n
o
n
lin
ea
r
o
p
er
atio
n
s
.
I
n
th
is
ap
p
licatio
n
,
a
co
llectio
n
o
f
t
h
y
r
o
i
d
im
ag
es
,
s
u
ch
as
US
,
C
T
,
o
r
M
R
I
im
ag
es
,
th
at
h
ad
lab
elled
with
p
ar
tic
u
lar
th
y
r
o
i
d
d
is
ea
s
es
,
is
u
s
ed
to
tr
ai
n
C
NNs.
T
h
e
n
etwo
r
k
ar
c
h
itectu
r
e
t
y
p
ically
in
clu
d
es
a
lar
g
e
n
u
m
b
er
o
f
co
n
v
o
lu
tio
n
al
lay
er
s
to
ca
p
tu
r
e
s
p
atial
h
ier
ar
ch
ies
in
th
e
d
ata,
p
o
o
lin
g
lay
er
s
to
r
ed
u
ce
d
im
en
s
io
n
ality
wh
ile
p
r
eser
v
i
n
g
cr
u
cial
in
f
o
r
m
atio
n
,
a
n
d
f
u
lly
co
n
n
ec
ted
lay
er
s
to
p
r
o
d
u
c
e
f
in
al
p
r
e
d
ictio
n
s
,
as
s
h
o
wn
in
Fig
u
r
e
2
.
I
n
th
e
t
r
ain
in
g
p
h
ase,
th
e
C
NN
p
ick
s
u
p
o
n
ch
a
r
ac
ter
is
tics
an
d
p
atter
n
s
th
at
p
o
in
ts
th
e
v
ar
io
u
s
th
y
r
o
id
d
is
ea
s
es,
s
u
ch
as
n
o
d
u
les,
h
y
p
o
th
y
r
o
i
d
is
m
,
an
d
h
y
p
er
th
y
r
o
id
is
m
.
C
o
n
v
o
l
u
tio
n
lay
er
s
em
p
lo
y
f
ilter
s
to
ex
tr
ac
t
lo
ca
l
f
ea
tu
r
es
f
r
o
m
im
ag
es,
in
clu
d
in
g
ed
g
es,
tex
tu
r
es,
an
d
o
th
er
p
atter
n
s
.
Ma
p
s
ar
e
p
ar
am
eter
ized
b
y
th
e
n
u
m
b
er
o
f
co
n
v
o
lu
tio
n
al
lay
er
s
.
An
i
m
ag
e
is
class
if
ied
u
s
in
g
a
C
NN
b
ased
o
n
f
ea
tu
r
es
ex
tr
ac
ted
f
r
o
m
r
aw
p
ix
el
d
ata
u
s
in
g
f
ilter
s
.
ML
clas
s
if
ier
s
s
u
ch
as
R
F
ar
e
u
s
ed
to
en
h
an
ce
t
h
e
p
er
f
o
r
m
an
ce
o
f
th
is
f
ea
tu
r
e
ex
tr
ac
tio
n
p
r
o
ce
s
s
.
Fig
u
r
e
2
.
Stru
ctu
r
e
o
f
C
NN
3
.
4
.
Cla
s
s
if
ica
t
io
n
R
F
[
2
4
]
co
m
b
in
es
s
ev
er
al
d
ec
is
io
n
tr
ee
s
to
p
r
o
d
u
ce
m
o
r
e
ac
cu
r
ate
p
r
ed
ictio
n
s
.
T
h
y
r
o
id
illn
ess
d
etec
tio
n
with
ML
wo
r
k
s
well
with
R
F.
I
t
is
p
o
s
s
ib
le
to
tr
ain
R
F
with
f
ea
tu
r
es
th
a
t
ar
e
r
et
r
iev
ed
f
r
o
m
im
a
g
es,
lik
e
s
h
ap
e
d
escr
ip
to
r
s
,
tex
tu
r
e
attr
ib
u
tes,
an
d
co
lo
r
h
is
to
g
r
am
s
.
A
th
y
r
o
id
d
is
ea
s
e
d
etec
tio
n
p
r
o
ce
s
s
b
eg
in
s
with
th
e
co
llectio
n
an
d
p
r
e
p
r
o
ce
s
s
in
g
o
f
r
elev
a
n
t
d
ata,
i
n
c
lu
d
in
g
th
y
r
o
id
h
o
r
m
o
n
e
lev
el
s
an
d
US
f
ea
tu
r
es.
T
h
is
d
ata
is
th
en
s
ep
ar
ated
in
to
tr
ain
in
g
an
d
test
in
g
s
ets
in
o
r
d
er
to
b
u
ild
an
d
ev
alu
ate
th
e
R
F
m
o
d
el
.
Du
r
in
g
tr
ain
in
g
,
th
e
m
o
d
el
lear
n
s
to
c
lass
if
y
th
y
r
o
id
co
n
d
itio
n
s
b
y
an
aly
zin
g
v
a
r
io
u
s
f
ea
tu
r
es,
wi
th
h
y
p
er
p
ar
am
eter
s
s
u
ch
as
th
e
q
u
an
tity
an
d
d
e
p
th
o
f
tr
ee
s
b
ein
g
o
p
tim
ized
.
Af
ter
tr
ain
in
g
,
th
e
p
er
f
o
r
m
an
ce
is
ev
alu
ated
to
u
n
d
er
s
tan
d
its
im
p
ac
t
o
n
p
r
ed
ictio
n
s
.
R
F
o
f
f
er
s
b
en
ef
its
s
u
c
h
as
h
ig
h
ac
cu
r
ac
y
an
d
r
o
b
u
s
tn
ess
ag
ain
s
t
n
o
is
y
d
ata,
th
o
u
g
h
th
ey
ca
n
b
e
c
o
m
p
u
tatio
n
ally
d
em
an
d
i
n
g
a
n
d
co
m
p
lex
to
in
ter
p
r
et.
Fin
al
p
r
ed
ict
io
n
̂
is
d
eter
m
in
ed
b
y
m
ajo
r
ity
as in
(
2
)
.
̂
=
(
1
′
…
)
(
2
)
T
h
e
av
er
ag
e
o
f
th
e
p
r
e
d
ictio
n
s
p
r
o
d
u
ce
d
b
y
ea
c
h
in
d
iv
id
u
al
tr
ee
is
th
e
f
in
al
p
r
ed
ictio
n
in
r
e
g
r
ess
io
n
.
T
h
e
e
q
u
atio
n
is
g
iv
en
i
n
(
3
)
.
̂
=
1
∑
=
1
(
3
)
W
h
er
e
is
th
e
p
r
ed
ictio
n
m
a
d
e
b
y
th
e
t
-
t
h
tr
ee
.
T
r
ep
r
esen
ts
th
e
f
o
r
est'
s
to
tal
tr
ee
co
u
n
t.
T
h
e
m
ajo
r
ity
v
o
te
d
eter
m
in
es
th
e
f
in
al
a
n
ticip
ated
class
lab
el,
̂
.
T
o
ad
d
r
ess
th
e
ch
allen
g
es
o
u
tlin
ed
in
th
e
I
n
tr
o
d
u
ctio
n
,
t
h
e
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
em
p
lo
y
s
ad
v
an
ce
d
p
r
e
-
p
r
o
ce
s
s
in
g
with
Gau
s
s
ian
–
m
ed
ian
f
ilter
in
g
,
o
p
tim
ized
f
ea
tu
r
e
ex
tr
ac
tio
n
u
s
in
g
I
n
ce
p
tio
n
R
esNet,
an
d
class
if
icatio
n
th
r
o
u
g
h
a
n
in
ter
p
r
etab
le
g
e
n
er
ali
ze
d
ad
d
itiv
e
n
eu
r
al
n
etwo
r
k
.
T
h
ese
co
m
p
o
n
e
n
ts
im
p
r
o
v
e
d
ata
q
u
ality
,
ca
p
t
u
r
e
d
is
cr
im
in
ativ
e
f
ea
tu
r
es,
an
d
en
s
u
r
e
r
o
b
u
s
t,
tr
an
s
p
ar
en
t d
ec
is
io
n
-
m
ak
in
g
,
as d
em
o
n
s
tr
ated
b
y
s
u
p
er
io
r
a
cc
u
r
ac
y
an
d
r
eliab
i
lity
in
d
is
ea
s
e
p
r
ed
ictio
n
.
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
Hyb
r
id
d
ee
p
lea
r
n
in
g
a
n
d
en
s
emb
le
lea
r
n
in
g
a
p
p
r
o
a
ch
fo
r
h
ig
h
-
a
cc
u
r
a
cy
…
(
S
h
u
r
iya
B
a
lu
s
a
my
)
307
4.
RE
SU
L
T
S
T
h
e
p
r
o
p
o
s
ed
T
C
-
MRF
is
ev
a
lu
ated
u
s
in
g
th
e
g
ath
er
e
d
d
ata
s
ets
in
o
r
d
er
to
d
eter
m
in
e
its
s
p
ec
if
icity
,
p
r
ec
is
io
n
,
r
ec
all,
ac
cu
r
ac
y
,
an
d
F1
-
s
co
r
e
,
am
o
n
g
o
th
e
r
m
etr
ics.
Per
f
o
r
m
an
ce
o
f
T
C
-
M
R
F
an
d
th
e
o
v
er
all
ac
cu
r
ac
y
r
ate
,
wh
ich
is
s
p
ec
if
ically
d
ef
in
ed
a
n
d
ass
ess
ed
,
ar
e
in
clu
d
ed
i
n
th
e
b
e
n
ch
m
ar
k
.
Fig
u
r
e
3
s
h
o
ws
th
e
o
u
tco
m
e
o
f
th
e
p
r
o
p
o
s
ed
T
C
-
MRF
with
a
s
am
p
le
o
f
th
r
ee
d
if
f
er
e
n
t
im
ag
in
g
m
o
d
ality
s
u
ch
as
C
T
,
MRI
,
a
n
d
US
,
f
o
r
id
en
tify
i
n
g
t
h
e
th
y
r
o
id
class
if
icatio
n
.
Fro
m
th
e
co
llected
I
m
a
g
eNe
t
d
ataset,
th
e
m
ed
ical
im
a
g
e
is
p
r
ep
r
o
ce
s
s
ed
b
y
co
n
tr
ast
s
tr
etch
in
g
,
ad
a
p
t
ed
to
elim
in
ate
th
e
u
n
wa
n
ted
d
is
t
o
r
tio
n
s
.
T
h
e
p
r
ep
r
o
ce
s
s
ed
im
ag
es
ar
e
th
en
s
en
t
th
r
o
u
g
h
a
C
NN.
C
lass
if
icat
io
n
r
esu
lts
f
r
o
m
th
e
C
NN
m
ig
h
t b
e
f
u
r
t
h
er
r
ef
in
e
d
o
r
co
m
p
lem
en
ted
b
y
u
s
in
g
a
n
R
F c
lass
if
ier
.
T
h
e
o
u
tp
u
t im
ag
es a
r
e
ca
p
tu
r
ed
an
d
u
s
ed
as in
p
u
t f
o
r
T
C
-
MRF
to
class
i
f
y
th
e
th
y
r
o
i
d
d
is
ea
s
e.
Fig
u
r
e
3
.
E
x
p
er
im
e
n
tal
r
esu
lt o
f
T
C
-
MRF
m
o
d
el
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
:
303
-
3
1
2
308
4
.
1
.
P
er
f
o
r
m
a
nce
a
na
l
y
s
is
T
h
e
p
r
o
p
o
s
ed
T
C
-
MRF
m
o
d
el
ef
f
icien
c
y
ca
n
b
e
e
v
alu
a
ted
u
tili
zin
g
th
e
ev
alu
atio
n
m
etr
ics
o
f
F1
-
s
co
r
e
,
p
r
ec
is
io
n
,
s
p
ec
if
icity
,
ac
cu
r
ac
y
,
an
d
r
ec
all
o
f
T
C
-
MRF
.
=
+
(
4
)
=
+
(
5
)
=
+
(
6
)
=
+
.
(
7
)
1
−
=
2
(
∗
+
)
(
8
)
W
h
er
e
an
d
r
ep
r
esen
ts
th
e
ac
t
u
al
p
o
s
itiv
es
as
well
as
n
eg
ativ
es
o
f
o
n
e
o
f
th
e
im
ag
es.
Neg
ativ
es
an
d
f
alse
p
o
s
itiv
es
f
o
r
th
e
s
am
p
le
im
ag
es
ar
e
in
d
icate
d
b
y
an
d
.
T
h
e
p
er
f
o
r
m
an
ce
o
u
tc
o
m
e
o
b
tain
ed
b
y
th
e
p
r
o
p
o
s
ed
T
C
-
MRF
f
o
r
ca
teg
o
r
izin
g
s
ev
er
al
th
y
r
o
i
d
d
is
ea
s
e
d
etec
tio
n
class
es
,
i.e
.
,
h
y
p
o
th
y
r
o
id
is
m
,
h
y
p
er
th
y
r
o
i
d
is
m
,
th
y
r
o
id
n
o
d
u
les
,
an
d
n
o
r
m
al
ar
e
ex
p
o
s
ed
in
T
a
b
le
1
.
Pro
p
o
s
ed
T
C
-
MRF
ac
h
iev
es
9
5
.
1
9
%
r
ec
all
,
9
6
.
6
7
%
s
p
ec
if
icity
,
9
5
.
8
7
%
p
r
ec
is
io
n
,
a
n
d
9
6
.
0
5
% F1
-
s
co
r
e
, r
esp
ec
tiv
ely
.
Fig
u
r
e
4
illu
s
tr
ates
th
e
o
v
er
a
ll
p
er
f
o
r
m
a
n
ce
o
f
th
e
T
C
‑
M
R
F
m
o
d
el
d
u
r
in
g
tr
ain
i
n
g
an
d
test
in
g
,
p
r
esen
ted
th
r
o
u
g
h
th
e
ac
cu
r
ac
y
an
d
lo
s
s
cu
r
v
es
p
lo
tted
ag
ai
n
s
t
th
e
n
u
m
b
er
o
f
e
p
o
ch
s
.
Fig
u
r
e
4
(
a)
s
h
o
ws
th
e
ac
cu
r
ac
y
o
f
th
e
test
in
g
an
d
tr
a
in
in
g
,
wh
ich
also
d
is
p
lay
s
th
e
ep
o
ch
s
o
n
t
h
e
x
-
an
d
y
-
a
x
es.
B
ased
o
n
ac
cu
r
ac
y
o
f
its
test
in
g
an
d
tr
ain
in
g
cu
r
v
es,
T
C
-
MRF
's
ac
cu
r
ac
y
lev
el
is
9
8
.
2
7
%.
T
h
e
l
o
s
s
cu
r
v
e
p
l
o
tted
ag
ain
s
t
ep
o
ch
s
is
s
h
o
wn
in
Fig
u
r
e
4
(
b
)
,
s
h
o
win
g
th
at
th
e
lo
s
s
r
ed
u
ce
s
w
ith
in
cr
ea
s
in
g
ep
o
ch
s
.
T
h
e
p
r
o
p
o
s
ed
p
r
o
ce
d
u
r
e
y
ield
s
an
ac
cu
r
ate
r
esu
lt
with
a
r
ea
s
o
n
ab
ly
lo
w
lo
s
s
o
f
1
.
7
3
%.
T
ested
an
d
tr
ain
e
d
,
T
C
-
MRF
ex
h
ib
it
s
g
o
o
d
p
er
f
o
r
m
an
ce
.
T
ab
le
1
.
Per
f
o
r
m
an
ce
ass
ess
m
en
t o
f
th
e
T
C
-
MRF
m
o
d
el
Ty
p
e
s
A
c
c
u
r
a
c
y
S
p
e
c
i
f
i
c
i
t
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
sc
o
r
e
N
o
r
mal
9
8
.
4
1
9
5
.
1
2
9
6
.
2
4
9
6
.
2
5
9
6
.
1
9
H
y
p
o
t
h
y
r
o
i
d
i
sm
9
9
.
2
3
9
4
.
2
7
9
6
.
1
2
9
5
.
4
8
9
5
.
4
8
H
y
p
e
r
t
h
y
r
o
i
d
i
sm
9
7
.
1
3
9
6
.
2
4
9
7
.
2
8
9
6
.
0
8
9
6
.
5
2
Th
y
r
o
i
d
nod
u
l
e
s
9
8
.
3
2
9
5
.
1
5
9
7
.
0
5
9
6
.
1
2
9
6
.
0
2
(
a)
(
b
)
Fig
u
r
e
4
.
T
r
ain
in
g
a
n
d
test
in
g
g
r
ap
h
o
f
th
e
T
C
-
MRF
m
o
d
el
of
(
a)
ac
c
u
r
ac
y
cu
r
v
e
an
d
(
b
)
l
o
s
s
cu
r
v
e
4
.
2
.
Co
m
pa
ra
t
iv
e
a
na
ly
s
is
T
h
e
ef
f
ec
tiv
en
ess
o
f
ML
n
et
wo
r
k
was
d
eter
m
in
ed
in
o
r
d
e
r
to
v
er
if
y
th
at
th
e
T
C
-
MRF
h
ad
a
h
ig
h
lev
el
o
f
ac
cu
r
ac
y
.
T
h
e
T
C
-
M
R
F
with
L
R
,
DT
,
an
d
NB
w
as
co
m
p
a
r
ed
a
n
d
ev
alu
ated
.
W
ith
9
8
.
2
7
%
ac
c
u
r
ac
y
r
ate,
th
e
T
C
-
MRF
o
u
tp
er
f
o
r
m
ed
th
e
tr
ad
itio
n
al
ML
n
etwo
r
k
s
.
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
Hyb
r
id
d
ee
p
lea
r
n
in
g
a
n
d
en
s
emb
le
lea
r
n
in
g
a
p
p
r
o
a
ch
fo
r
h
ig
h
-
a
cc
u
r
a
cy
…
(
S
h
u
r
iya
B
a
lu
s
a
my
)
309
T
ab
le
2
p
r
esen
ts
t
h
e
p
e
r
f
o
r
m
an
ce
co
m
p
ar
is
o
n
o
f
s
ev
er
al
s
tan
d
alo
n
e
m
o
d
els
u
s
in
g
m
etr
i
cs
s
u
ch
as
ac
cu
r
ac
y
,
s
p
ec
if
icity
,
p
r
ec
is
io
n
,
r
ec
all
,
a
n
d
F1
-
s
co
r
e
.
T
h
e
p
r
o
p
o
s
ed
T
C
-
MRF
o
u
tp
er
f
o
r
m
s
all
o
th
er
m
o
d
els,
ac
h
iev
in
g
th
e
h
ig
h
est
o
v
er
all
ac
cu
r
ac
y
o
f
9
8
.
2
7
%.
C
o
m
p
ar
ed
to
s
tan
d
alo
n
e
m
o
d
els,
T
C
-
MRF
im
p
r
o
v
es
ac
cu
r
ac
y
b
y
8
.
9
2
%,
7
.
1
9
%,
2
.
1
0
%,
5
.
0
0
%,
a
n
d
0
.
8
2
%
o
v
er
DT
,
NB
,
L
R
,
R
F,
an
d
C
NN,
r
esp
ec
tiv
ely
,
d
em
o
n
s
tr
atin
g
th
e
b
e
n
ef
it
o
f
co
m
b
in
i
n
g
C
NN
f
ea
tu
r
e
ex
tr
ac
tio
n
with
R
F
class
if
icati
o
n
.
Similar
h
y
b
r
i
d
C
NN
-
R
F
an
d
tr
an
s
f
er
-
lear
n
in
g
ap
p
r
o
ac
h
es
h
av
e
also
s
h
o
wn
im
p
r
o
v
e
d
d
iag
n
o
s
tic
ac
cu
r
a
cy
an
d
r
o
b
u
s
tn
ess
in
m
ed
ical
im
ag
in
g
,
v
alid
atin
g
t
h
e
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
a
n
d
r
el
iab
i
lity
o
f
th
e
T
C
-
MRF
.
T
ab
le
2
.
Per
f
o
r
m
an
ce
co
m
p
a
r
is
o
n
o
f
s
tan
d
alo
n
e
m
o
d
els an
d
th
e
p
r
o
p
o
s
ed
T
C
-
MRF
h
y
b
r
id
m
o
d
el
N
e
t
w
o
r
k
s
A
c
c
u
r
a
c
y
S
p
e
c
i
f
i
c
i
t
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
sc
o
r
e
D
T
[
2
5
]
8
9
.
5
3
8
8
.
7
5
8
6
.
2
5
8
5
.
3
0
8
5
.
7
0
N
B
[
2
6
]
9
1
.
2
6
8
9
.
2
6
8
7
.
5
7
8
4
.
6
3
8
6
.
5
3
LR
[
2
7
]
9
5
.
2
2
9
2
.
1
3
9
0
.
6
2
9
0
.
8
5
9
4
.
1
8
R
F
[
2
8
]
9
3
.
2
7
9
2
.
1
8
9
4
.
6
7
9
2
.
8
7
9
3
.
0
5
C
N
N
[
2
9
]
9
7
.
4
5
9
4
.
3
4
9
3
.
1
3
9
4
.
6
2
9
5
.
2
3
TC
-
M
R
F
(
o
u
r
s)
9
8
.
2
7
9
5
.
1
9
9
6
.
6
7
9
5
.
8
7
9
6
.
0
5
T
ab
le
3
s
h
o
ws
th
e
n
u
m
b
er
o
f
ex
p
er
im
en
tal
im
ag
es
tak
e
n
d
u
r
in
g
th
e
p
r
o
ce
s
s
o
f
test
in
g
v
ar
io
u
s
m
eth
o
d
s
to
d
eter
m
in
e
t
h
eir
ac
cu
r
ac
y
.
T
h
e
p
r
o
p
o
s
ed
T
C
-
MRF
im
p
r
o
v
es
th
e
o
v
er
all
ac
cu
r
ac
y
b
y
6
.
3
0
%,
4
.
1
1
%,
an
d
5
.
3
6
%,
b
etter
th
a
n
NB
,
ML
P,
an
d
DT
,
r
esp
ec
tiv
ely
.
C
o
m
p
ar
in
g
t
h
e
p
r
o
p
o
s
ed
n
etwo
r
k
to
t
h
e
ex
is
tin
g
tech
n
iq
u
e,
T
C
-
MRF
p
er
f
o
r
m
s
m
u
c
h
b
etter
th
an
th
e
o
th
er
m
eth
o
d
s
.
As
a
r
esu
lt,
th
e
p
r
o
p
o
s
ed
TC
-
MRF
o
f
f
er
s
h
ig
h
r
eliab
ilit
y
f
o
r
d
etec
tin
g
th
y
r
o
id
d
is
ea
s
e.
T
ab
le
3
.
C
o
m
p
a
r
ativ
e
an
aly
s
is
o
f
ex
is
tin
g
v
s
p
r
o
p
o
s
ed
T
C
-
MRF
m
o
d
el
A
u
t
h
o
r
s
M
e
t
h
o
d
s
A
c
c
u
r
a
c
y
(
%)
Mir
e
t
a
l
.
[
3
0
]
NB
9
2
.
0
7
P
a
l
.
e
t
a
l
.
[
3
1
]
M
LP
9
4
.
2
3
Y
a
d
a
v
a
n
d
P
a
l
[
3
2
]
DT
93
P
r
o
p
o
se
d
TC
-
M
R
F
9
8
.
2
7
Fig
u
r
e
5
s
h
o
ws
th
e
p
r
ac
tic
al
d
ep
lo
y
m
e
n
t
o
f
th
e
p
r
o
p
o
s
ed
T
C
-
MRF
m
o
d
el
with
in
a
clin
ical
wo
r
k
f
lo
w.
T
h
e
m
u
lti
-
m
o
d
ality
th
y
r
o
id
im
ag
es
f
r
o
m
p
atien
ts
ar
e
p
r
o
ce
s
s
ed
th
r
o
u
g
h
th
e
T
C
-
MRF
m
o
d
el
f
o
r
ac
cu
r
ate
d
is
ea
s
e
class
if
icatio
n
.
T
h
e
class
if
ied
r
esu
lts
ar
e
th
en
co
m
m
u
n
icate
d
t
o
h
o
s
p
ital
d
ia
g
n
o
s
tic
s
y
s
tem
s
to
ass
is
t
clin
ician
s
in
d
ec
is
io
n
-
m
ak
in
g
.
T
h
is
au
t
o
m
ated
p
r
o
ce
s
s
m
in
im
izes
h
u
m
an
er
r
o
r
,
r
ed
u
ce
s
d
iag
n
o
s
is
tim
e,
an
d
en
h
an
ce
s
r
eliab
ilit
y
.
Fig
u
r
e
5
.
R
ea
l
-
wo
r
ld
d
ep
lo
y
m
en
t o
f
T
C
-
MRF
in
clin
ical
wo
r
k
f
lo
w
5.
DIS
CU
SS
I
O
N
T
h
e
f
in
d
in
g
s
r
ev
ea
l
th
at
th
e
p
r
o
p
o
s
ed
T
C
-
MRF
m
o
d
el,
wh
ich
in
teg
r
ates
C
NN
-
b
as
ed
f
ea
tu
r
e
ex
tr
ac
tio
n
with
R
F
class
if
icat
io
n
,
ac
h
iev
es
an
ac
c
u
r
ac
y
o
f
9
8
.
2
7
%,
p
r
ec
is
io
n
o
f
9
6
.
6
7
%,
an
d
F1
-
s
co
r
e
o
f
9
6
.
0
5
%.
T
h
ese
r
esu
lts
d
em
o
n
s
tr
ate
its
s
u
p
er
io
r
ity
o
v
er
c
o
n
v
en
tio
n
al
m
o
d
els
s
u
ch
as
DT
,
NB
,
an
d
L
R
,
s
h
o
win
g
im
p
r
o
v
em
en
ts
o
f
u
p
to
8
%
in
ac
cu
r
ac
y
.
T
h
e
h
y
b
r
i
d
DL
en
s
em
b
le
ap
p
r
o
ac
h
e
f
f
ec
t
iv
ely
ca
p
tu
r
es
b
o
th
s
p
atial
an
d
co
n
tex
tu
al
f
ea
t
u
r
es
f
r
o
m
m
u
lti
m
o
d
al
i
m
ag
es,
en
s
u
r
in
g
r
o
b
u
s
t
an
d
r
eliab
l
e
th
y
r
o
id
d
is
ea
s
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
:
303
-
3
1
2
310
class
if
icatio
n
.
T
h
is
en
h
an
ce
d
p
er
f
o
r
m
an
ce
s
u
g
g
ests
s
tr
o
n
g
p
o
ten
tial
f
o
r
clin
ical
d
ec
is
io
n
s
u
p
p
o
r
t,
e
n
ab
lin
g
ea
r
ly
d
etec
tio
n
,
r
ed
u
cin
g
d
iag
n
o
s
tic
er
r
o
r
s
,
a
n
d
s
u
p
p
o
r
tin
g
r
ad
io
lo
g
is
ts
in
r
o
u
tin
e
d
ia
g
n
o
s
i
s
.
T
h
e
m
o
d
el
co
u
ld
also
s
u
p
p
o
r
t
telem
ed
icin
e
b
y
en
ab
lin
g
r
em
o
te
d
iag
n
o
s
is
,
f
ac
ilit
at
in
g
ea
r
ly
s
cr
ee
n
in
g
,
an
d
in
teg
r
at
in
g
with
elec
tr
o
n
ic
h
ea
lth
r
ec
o
r
d
s
y
s
tem
s
f
o
r
s
tr
ea
m
lin
ed
r
ep
o
r
ti
n
g
a
n
d
clin
ical
d
ec
is
io
n
-
m
a
k
in
g
.
Fu
r
th
er
m
o
r
e,
ca
r
e
f
u
l
co
n
s
id
er
atio
n
o
f
eth
ical
im
p
li
ca
tio
n
s
,
d
ata
p
r
iv
ac
y
,
an
d
cli
n
ical
v
alid
atio
n
is
es
s
en
tial
t
o
en
s
u
r
e
u
n
b
iased
p
r
ed
ictio
n
s
,
p
r
o
tect
p
atien
t
d
at
a,
an
d
v
alid
ate
t
h
e
m
o
d
el
ac
r
o
s
s
d
iv
er
s
e
p
o
p
u
latio
n
s
.
I
n
co
r
p
o
r
atin
g
ex
p
lain
ab
le
AI
an
d
f
e
d
er
ated
lea
r
n
in
g
in
th
e
f
u
tu
r
e
ca
n
f
u
r
th
e
r
en
h
a
n
ce
in
ter
p
r
eta
b
ilit
y
,
p
r
iv
a
cy
,
an
d
s
ca
lab
ilit
y
f
o
r
telem
ed
icin
e
ap
p
licatio
n
s
.
6.
CO
NCLU
SI
O
N
I
n
th
is
r
esear
ch
,
th
e
TC
-
MRF
m
o
d
el
is
p
r
o
p
o
s
ed
f
o
r
class
if
y
in
g
th
y
r
o
id
d
is
ea
s
es.
T
h
e
in
p
u
t
im
ag
es
ar
e
g
ath
er
ed
f
r
o
m
th
e
I
m
ag
eNe
t
d
atasets
.
T
o
r
em
o
v
e
n
o
is
e
ar
tifa
cts
f
r
o
m
th
e
in
p
u
t
im
ag
es,
a
co
n
tr
ast
-
s
tr
etch
in
g
ad
ap
tiv
e
G
au
s
s
ian
s
tar
f
ilter
i
s
ap
p
lied
d
u
r
in
g
p
r
e
-
p
r
o
ce
s
s
in
g
.
T
o
ex
tr
ac
t
th
e
f
ea
tu
r
e,
th
e
p
r
ep
r
o
ce
s
s
ed
im
ag
e
is
f
ed
in
to
a
C
NN.
T
h
e
e
x
t
r
ac
ted
f
ea
tu
r
e
f
r
o
m
C
NN
is
u
s
ed
to
cl
ass
if
y
th
e
th
y
r
o
i
d
d
is
ea
s
e.
T
o
ev
alu
ate
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
p
ar
a
m
eter
s
,
s
u
ch
as
r
ec
all,
F1
-
s
co
r
e,
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
an
d
s
p
ec
if
icity
,
T
C
-
MRF
i
s
u
tili
z
ed
.
Pro
p
o
s
ed
R
F
in
cr
ea
s
es
th
e
o
v
er
all
ac
cu
r
ac
y
b
y
8
.
1
%,
7
.
1
5
%
,
an
d
2
.
1
%
o
f
d
ec
is
io
n
tr
ee
s
,
n
aiv
e
B
ay
es,
an
d
LR
.
As
a
r
esu
lt
o
f
e
x
p
e
r
im
en
ta
l
r
esu
lts
,
th
e
p
r
o
p
o
s
e
d
ap
p
r
o
ac
h
d
etec
ts
th
y
r
o
id
illn
ess
with
in
a
n
ac
c
u
r
ac
y
r
a
n
g
e
o
f
9
8
.
2
7
%.
T
h
e
p
r
o
p
o
s
ed
T
C
-
MRF
im
p
r
o
v
es
th
e
o
v
er
all
ac
c
u
r
ac
y
b
y
6
.
3
0
%,
4
.
1
1
%,
an
d
5
.
3
6
%,
b
etter
th
an
DT
,
NB
,
an
d
L
R
,
r
esp
ec
tiv
ely
.
I
n
th
e
f
u
tu
r
e
th
e
p
r
o
p
o
s
ed
T
C
-
MRF
in
cr
ea
s
e
its
ac
cu
r
ac
y
an
d
d
ete
ct
th
e
g
r
ad
es o
f
th
y
r
o
id
d
is
ea
s
e.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
w
o
u
ld
lik
e
to
ex
p
r
ess
h
is
h
ea
r
tf
elt
g
r
atitu
d
e
to
th
e
s
u
p
er
v
is
o
r
f
o
r
h
is
g
u
i
d
an
ce
an
d
u
n
wav
er
in
g
s
u
p
p
o
r
t d
u
r
in
g
t
h
is
r
esear
ch
f
o
r
h
is
g
u
id
an
ce
an
d
s
u
p
p
o
r
t.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
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
Sh
u
r
iy
a
B
alu
s
am
y
✓
✓
✓
✓
✓
✓
✓
✓
B
alajish
an
m
u
g
am
Viv
ek
an
ad
h
a
n
✓
✓
✓
✓
✓
✓
✓
✓
Pra
th
im
a
Ma
b
el
J
o
h
n
✓
✓
✓
✓
✓
✓
✓
✓
✓
Su
s
h
m
a
Su
n
il B
h
o
s
le
✓
✓
✓
✓
✓
✓
✓
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
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
t
h
o
r
s
d
ec
lar
e
th
at
th
e
y
h
av
e
n
o
k
n
o
wn
c
o
m
p
etin
g
f
in
an
cial
in
ter
ests
o
r
p
er
s
o
n
al
r
el
atio
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
.
I
NF
O
RM
E
D
CO
NS
E
N
T
I
ce
r
tify
th
at
I
h
a
v
e
ex
p
lain
e
d
th
e
n
atu
r
e
an
d
p
u
r
p
o
s
e
o
f
th
i
s
s
tu
d
y
to
th
e
ab
o
v
e
-
n
am
ed
i
n
d
iv
id
u
al,
an
d
I
h
av
e
d
is
cu
s
s
ed
th
e
p
o
te
n
tial
b
en
ef
its
o
f
th
is
s
tu
d
y
p
ar
ticip
atio
n
.
T
h
e
q
u
esti
o
n
s
th
e
i
n
d
iv
id
u
al
h
ad
ab
o
u
t
th
is
s
tu
d
y
h
av
e
b
ee
n
an
s
wer
ed
,
an
d
we
will a
lw
ay
s
b
e
av
aila
b
le
to
ad
d
r
ess
f
u
tu
r
e
q
u
esti
o
n
s
.
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
Hyb
r
id
d
ee
p
lea
r
n
in
g
a
n
d
en
s
emb
le
lea
r
n
in
g
a
p
p
r
o
a
ch
fo
r
h
ig
h
-
a
cc
u
r
a
cy
…
(
S
h
u
r
iya
B
a
lu
s
a
my
)
311
E
T
H
I
CAL AP
P
RO
V
AL
My
r
esear
ch
g
u
id
e
r
e
v
iewe
d
a
n
d
eth
ically
ap
p
r
o
v
ed
th
is
m
a
n
u
s
cr
ip
t f
o
r
p
u
b
li
ca
tio
n
in
th
is
jo
u
r
n
al.
DATA AV
AI
L
AB
I
L
I
T
Y
Data
s
h
ar
in
g
is
n
o
t
ap
p
licab
l
e
to
th
is
ar
ticle
as
n
o
d
ataset
s
wer
e
g
en
er
ate
d
o
r
an
aly
ze
d
d
u
r
in
g
th
e
cu
r
r
en
t stu
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
D.
-
M
.
Ti
l
i
c
i
e
t
a
l
.
,
“
Th
e
i
n
t
r
i
c
a
t
e
r
e
l
a
t
i
o
n
s
h
i
p
b
e
t
w
e
e
n
t
h
y
r
o
i
d
d
i
s
o
r
d
e
r
s
a
n
d
t
y
p
e
2
d
i
a
b
e
t
e
s
—
a
n
a
r
r
a
t
i
v
e
r
e
v
i
e
w
,
”
D
i
a
b
e
t
o
l
o
g
y
,
v
o
l
.
6
,
n
o
.
5
,
M
a
y
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
d
i
a
b
e
t
o
l
o
g
y
6
0
5
0
0
4
1
.
[
2
]
L.
S
a
b
a
t
i
n
o
a
n
d
C
.
V
a
ssa
l
l
e
,
“
T
h
y
r
o
i
d
h
o
r
mo
n
e
s
a
n
d
met
a
b
o
l
i
sm
r
e
g
u
l
a
t
i
o
n
:
w
h
i
c
h
r
o
l
e
o
n
b
r
o
w
n
a
d
i
p
o
s
e
t
i
ss
u
e
a
n
d
b
r
o
w
n
i
n
g
p
r
o
c
e
ss?
,
”
Bi
o
m
o
l
e
c
u
l
e
s
,
v
o
l
.
1
5
,
n
o
.
3
,
M
a
r
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
b
i
o
m1
5
0
3
0
3
6
1
.
[
3
]
U
d
i
,
“
S
l
e
e
p
,
n
e
u
r
o
e
n
d
o
c
r
i
n
e
d
i
s
o
r
d
e
r
s,
a
n
d
t
h
e
b
i
d
i
r
e
c
t
i
o
n
a
l
r
e
l
a
t
i
o
n
sh
i
p
b
e
t
w
e
e
n
t
h
e
h
y
p
o
t
h
a
l
a
mi
c
-
p
i
t
u
i
t
a
r
y
-
a
d
r
e
n
a
l
a
x
i
s
:
a
mi
n
i
-
r
e
v
i
e
w
,
”
J
o
u
rn
a
l
o
f
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
a
n
d
E
n
v
i
r
o
n
m
e
n
t
a
l
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
2
9
,
n
o
.
4
,
p
p
.
1
2
1
7
–
1
2
2
7
,
2
0
2
5
,
d
o
i
:
h
t
t
p
s:
/
/
d
o
i
.
o
r
g
/
1
0
.
4
3
1
4
/
j
a
sem
.
v
2
9
i
4
.
2
5
.
[
4
]
N
.
S
.
-
G
u
t
a
j
,
N
.
Za
w
a
l
n
a
,
P
.
G
u
t
,
a
n
d
M
.
R
u
c
h
a
ł
a
,
“
R
e
l
a
t
i
o
n
s
h
i
p
b
e
t
w
e
e
n
t
h
y
r
o
i
d
h
o
r
mo
n
e
s
a
n
d
c
e
n
t
r
a
l
n
e
r
v
o
u
s
s
y
s
t
e
m
met
a
b
o
l
i
sm
i
n
p
h
y
s
i
o
l
o
g
i
c
a
l
a
n
d
p
a
t
h
o
l
o
g
i
c
a
l
c
o
n
d
i
t
i
o
n
s,”
P
h
a
rm
a
c
o
l
o
g
i
c
a
l
R
e
p
o
r
t
s
,
v
o
l
.
7
4
,
n
o
.
5
,
p
p
.
8
4
7
–
8
5
8
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
3
4
4
0
-
02
2
-
0
0
3
7
7
-
w.
[
5
]
Y
.
A
b
d
u
l
R
a
h
e
e
m,
“
U
n
v
e
i
l
i
n
g
t
h
e
s
i
g
n
i
f
i
c
a
n
c
e
a
n
d
c
h
a
l
l
e
n
g
e
s
o
f
i
n
t
e
g
r
a
t
i
n
g
p
r
e
v
e
n
t
i
o
n
l
e
v
e
l
s
i
n
h
e
a
l
t
h
c
a
r
e
p
r
a
c
t
i
c
e
,
”
J
o
u
r
n
a
l
o
f
Pri
m
a
r
y
C
a
r
e
&
C
o
m
m
u
n
i
t
y
H
e
a
l
t
h
,
v
o
l
.
1
4
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
7
7
/
2
1
5
0
1
3
1
9
2
3
1
1
8
6
5
0
0
.
[
6
]
J.
H
u
a
n
g
a
n
d
J.
Z
h
a
o
,
“
Q
u
a
n
t
i
t
a
t
i
v
e
d
i
a
g
n
o
s
i
s
p
r
o
g
r
e
ss
o
f
u
l
t
r
a
so
u
n
d
i
ma
g
i
n
g
t
e
c
h
n
o
l
o
g
y
i
n
t
h
y
r
o
i
d
d
i
f
f
u
se
d
i
s
e
a
ses
,
”
D
i
a
g
n
o
s
t
i
c
s
,
v
o
l
.
1
3
,
n
o
.
4
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
d
i
a
g
n
o
s
t
i
c
s1
3
0
4
0
7
0
0
.
[
7
]
M
.
V
i
n
e
e
l
a
,
G
.
D
.
S
.
R
e
d
d
y
,
G
.
K
a
r
t
h
i
k
,
N
.
M
u
t
h
u
k
u
m
a
r
a
n
,
a
n
d
S
.
H
.
A
l
D
e
e
n
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
l
e
u
k
e
mi
a
w
h
i
t
e
b
l
o
o
d
c
e
l
l
c
a
n
c
e
r
,
”
i
n
2
0
2
4
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
v
e
n
t
i
v
e
C
o
m
p
u
t
a
t
i
o
n
T
e
c
h
n
o
l
o
g
i
e
s
(
I
C
I
C
T
)
,
A
p
r
.
2
0
2
4
,
p
p
.
1
2
3
3
–
1
2
3
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
C
T6
0
1
5
5
.
2
0
2
4
.
1
0
5
4
4
9
7
8
.
[
8
]
R
.
A
.
T
a
y
l
o
r
e
t
a
l
.
,
“
L
e
v
e
r
a
g
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
o
r
e
d
u
c
e
d
i
a
g
n
o
s
t
i
c
e
r
r
o
r
s
i
n
e
mer
g
e
n
c
y
m
e
d
i
c
i
n
e
:
C
h
a
l
l
e
n
g
e
s,
o
p
p
o
r
t
u
n
i
t
i
e
s,
a
n
d
f
u
t
u
r
e
d
i
r
e
c
t
i
o
n
s,”
Ac
a
d
e
m
i
c
Em
e
rg
e
n
c
y
Me
d
i
c
i
n
e
,
v
o
l
.
3
2
,
n
o
.
3
,
p
p
.
3
2
7
–
3
3
9
,
M
a
r
.
2
0
2
5
,
d
o
i
:
1
0
.
1
1
1
1
/
a
c
e
m.
1
5
0
6
6
.
[
9
]
R
.
Th
a
r
a
n
i
a
n
d
C
.
J
a
sp
h
i
n
,
“
G
a
st
r
i
c
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
v
i
a
d
e
e
p
l
e
a
r
n
i
n
g
i
n
i
m
a
g
e
p
r
o
c
e
ss
i
n
g
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
S
y
st
e
m
D
e
si
g
n
a
n
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
7
–
1
3
,
2
0
2
4
.
[
1
0
]
R
.
S
u
n
d
a
r
a
s
e
k
a
r
a
n
d
A
.
A
p
p
a
t
h
u
r
a
i
,
“
A
u
t
o
m
a
t
i
c
b
r
a
i
n
t
u
m
o
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
b
a
se
d
o
n
I
o
T
a
n
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
F
l
u
c
t
u
a
t
i
o
n
a
n
d
N
o
i
s
e
L
e
t
t
e
rs
,
v
o
l
.
2
1
,
n
o
.
0
3
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
4
2
/
S
0
2
1
9
4
7
7
5
2
2
5
0
0
3
0
4
.
[
1
1
]
A
.
V
.
S
u
p
r
a
ma
n
i
a
n
,
“
B
i
g
d
a
t
a
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
i
n
h
e
a
l
t
h
c
a
r
e
:
r
e
v
o
l
u
t
i
o
n
i
z
i
n
g
p
a
t
i
e
n
t
o
u
t
c
o
m
e
s
t
h
r
o
u
g
h
a
d
v
a
n
c
e
d
a
n
a
l
y
t
i
c
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
Re
se
a
rc
h
i
n
E
n
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
6
,
n
o
.
2
,
p
p
.
2
2
8
–
2
5
4
,
M
a
r
.
2
0
2
5
,
d
o
i
:
1
0
.
3
4
2
1
8
/
I
JA
R
ET
_
1
6
_
0
2
_
0
1
4
.
[
1
2
]
J.
B
.
M
a
d
a
v
a
r
a
p
u
,
“
C
A
B
-
I
D
S
:
I
o
T
-
b
a
s
e
d
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
u
s
i
n
g
b
a
c
t
e
r
i
a
f
o
r
a
g
i
n
g
o
p
t
i
mi
z
e
d
B
i
G
R
U
-
C
N
N
n
e
t
w
o
r
k
,
”
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
a
n
d
E
n
g
i
n
e
e
ri
n
g
O
p
t
i
m
i
za
t
i
o
n
,
v
o
l
.
1
,
n
o
.
2
,
p
p
.
6
3
–
6
8
,
2
0
2
3
.
[
1
3
]
M
.
C
.
G
u
e
r
r
e
r
o
,
J
.
S
.
P
a
r
a
d
a
,
a
n
d
H
.
E.
Es
p
i
t
i
a
,
“
E
EG
si
g
n
a
l
a
n
a
l
y
si
s
u
si
n
g
c
l
a
ss
i
f
i
c
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s:
Lo
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
,
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
s
u
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
s
,
a
n
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,
”
H
e
l
i
y
o
n
,
v
o
l
.
7
,
n
o
.
6
,
Ju
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
1
.
e
0
7
2
5
8
.
[
1
4
]
F
.
Li
u
a
n
d
D
.
P
a
n
a
g
i
o
t
a
k
o
s,
“
R
e
a
l
-
w
o
r
l
d
d
a
t
a
:
a
b
r
i
e
f
r
e
v
i
e
w
o
f
t
h
e
m
e
t
h
o
d
s
,
a
p
p
l
i
c
a
t
i
o
n
s,
c
h
a
l
l
e
n
g
e
s
a
n
d
o
p
p
o
r
t
u
n
i
t
i
e
s
,
”
B
MC
Me
d
i
c
a
l
R
e
se
a
rc
h
Me
t
h
o
d
o
l
o
g
y
,
v
o
l
.
2
2
,
n
o
.
1
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
2
8
7
4
-
0
2
2
-
0
1
7
6
8
-
6.
[
1
5
]
A
.
To
p
şi
r
,
F
.
G
ü
l
e
r
,
E.
Ç
e
t
i
n
,
M
.
F
.
B
u
r
a
k
,
a
n
d
M
.
A
ğ
r
a
z
,
“
T
h
y
r
o
i
d
d
i
se
a
se
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
g
e
n
e
r
a
t
i
v
e
a
d
v
e
r
sari
a
l
n
e
t
w
o
r
k
s
a
n
d
K
o
l
m
o
g
o
r
o
v
-
A
r
n
o
l
d
n
e
t
w
o
r
k
f
o
r
t
h
r
e
e
-
c
l
a
ss
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
B
MC
Me
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
a
n
d
D
e
c
i
s
i
o
n
Ma
k
i
n
g
,
v
o
l
.
2
5
,
n
o
.
1
,
Ju
l
.
2
0
2
5
,
d
o
i
:
1
0
.
1
1
8
6
/
s1
2
9
1
1
-
025
-
0
3
0
1
4
-
7.
[
1
6
]
R
.
S
h
a
r
ma
,
G
.
K
.
M
a
h
a
n
t
i
,
C
.
C
h
a
k
r
a
b
o
r
t
y
,
G
.
P
a
n
d
a
,
a
n
d
A
.
R
a
t
h
,
“
A
n
I
o
T
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
sm
a
r
t
h
e
a
l
t
h
c
a
r
e
f
r
a
mew
o
r
k
f
o
r
t
h
y
r
o
i
d
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
,
”
AC
M
T
r
a
n
s
a
c
t
i
o
n
s
o
n
I
n
t
e
r
n
e
t
T
e
c
h
n
o
l
o
g
y
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
4
5
/
3
6
3
7
0
6
2
.
[
1
7
]
Z.
X
i
a
n
g
e
t
a
l
.
,
“
F
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
v
i
a
m
u
l
t
i
-
a
t
t
e
n
t
i
o
n
g
u
i
d
e
d
U
N
e
t
f
o
r
t
h
y
r
o
i
d
n
o
d
u
l
e
se
g
m
e
n
t
a
t
i
o
n
o
f
u
l
t
r
a
so
u
n
d
i
m
a
g
e
s,
”
N
e
u
ra
l
N
e
t
w
o
rks
,
v
o
l
.
1
8
1
,
J
a
n
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
n
e
t
.
2
0
2
4
.
1
0
6
7
5
4
.
[
1
8
]
A
.
R
a
z
a
,
F
.
E
i
d
,
E.
C
.
M
o
n
t
e
r
o
,
I
.
D
.
N
o
y
a
,
a
n
d
I
.
A
sh
r
a
f
,
“
E
n
h
a
n
c
e
d
i
n
t
e
r
p
r
e
t
a
b
l
e
t
h
y
r
o
i
d
d
i
se
a
se
d
i
a
g
n
o
s
i
s
b
y
l
e
v
e
r
a
g
i
n
g
sy
n
t
h
e
t
i
c
o
v
e
r
sam
p
l
i
n
g
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
s,
”
BM
C
Me
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
a
n
d
D
e
c
i
si
o
n
M
a
k
i
n
g
,
v
o
l
.
2
4
,
n
o
.
1
,
N
o
v
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
8
6
/
s1
2
9
1
1
-
024
-
0
2
7
8
0
-
0.
[
1
9
]
K
.
M
.
M
.
U
d
d
i
n
,
A
.
A
l
M
a
mu
n
,
A
.
C
h
a
k
r
a
b
a
r
t
i
,
a
n
d
R
.
M
o
st
a
f
i
z
,
“
A
n
e
n
s
e
mb
l
e
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
se
d
a
p
p
r
o
a
c
h
t
o
p
r
e
d
i
c
t
t
h
y
r
o
i
d
d
i
se
a
se
u
s
i
n
g
h
y
b
r
i
d
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
,
”
Bi
o
m
e
d
i
c
a
l
A
n
a
l
y
si
s
,
v
o
l
.
1
,
n
o
.
3
,
p
p
.
2
2
9
–
2
3
9
,
S
e
p
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
i
o
a
n
a
.
2
0
2
4
.
0
8
.
0
0
1
.
[
2
0
]
S
.
A
k
t
e
r
a
n
d
H
.
A
.
M
u
s
t
a
f
a
,
“
A
n
a
l
y
s
i
s
a
n
d
i
n
t
e
r
p
r
e
t
a
b
i
l
i
t
y
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
s
t
o
c
l
a
ss
i
f
y
t
h
y
r
o
i
d
d
i
se
a
se,
”
PLO
S
O
N
E
,
v
o
l
.
1
9
,
n
o
.
5
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
3
0
0
6
7
0
.
[
2
1
]
D
.
K
e
s
a
v
u
l
u
a
n
d
R
.
K
a
n
n
a
d
a
sa
n
,
“
I
mp
r
o
v
e
d
b
i
o
-
i
n
sp
i
r
e
d
w
i
t
h
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
c
o
mp
u
t
i
n
g
a
p
p
r
o
a
c
h
f
o
r
t
h
y
r
o
i
d
p
r
e
d
i
c
t
i
o
n
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
5
,
n
o
.
1
,
J
u
l
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
8
-
0
2
5
-
0
3
2
9
9
-
8.
[
2
2
]
T.
B
a
n
e
r
j
e
e
,
D
.
P
.
S
i
n
g
h
,
D
.
S
w
a
i
n
,
S
.
M
a
h
a
j
a
n
,
S
.
K
a
d
r
y
,
a
n
d
J.
K
i
m,
“
A
n
o
v
e
l
h
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
c
o
m
b
i
n
i
n
g
d
e
e
p
f
e
a
t
u
r
e
a
t
t
e
n
t
i
o
n
a
n
d
s
t
a
t
i
s
t
i
c
a
l
v
a
l
i
d
a
t
i
o
n
f
o
r
e
n
h
a
n
c
e
d
t
h
y
r
o
i
d
u
l
t
r
a
s
o
u
n
d
se
g
m
e
n
t
a
t
i
o
n
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
5
,
n
o
.
1
,
Ju
l
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
8
-
025
-
1
2
6
0
2
-
6.
[
2
3
]
D
.
Y
a
n
g
,
T
.
Li
,
L.
Li
,
S
.
C
h
e
n
,
a
n
d
X
.
Li
,
“
M
u
l
t
i
-
m
o
d
a
l
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
-
b
a
se
d
t
h
y
r
o
i
d
c
y
t
o
l
o
g
y
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
n
d
d
i
a
g
n
o
si
s,
”
H
u
m
a
n
P
a
t
h
o
l
o
g
y
,
v
o
l
.
1
6
1
,
J
u
l
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
u
m
p
a
t
h
.
2
0
2
5
.
1
0
5
8
6
8
.
[
2
4
]
R
.
N
.
P
.
P
r
a
t
a
m
a
,
S
.
W
i
n
a
r
n
o
,
a
n
d
T.
N
.
O
.
W
i
j
a
y
a
,
“
T
h
y
r
o
i
d
d
i
se
a
se
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
r
a
n
d
o
m
f
o
r
e
st
w
i
t
h
K
N
N
I
mp
u
t
e
r
f
o
r
mi
ssi
n
g
v
a
l
u
e
s,”
S
i
n
k
r
o
n
,
v
o
l
.
9
,
n
o
.
1
,
p
p
.
1
6
0
–
1
6
6
,
Ja
n
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
3
9
5
/
si
n
k
r
o
n
.
v
9
i
1
.
1
4
3
3
4
.
[
2
5
]
S
.
O
u
a
r
t
a
n
i
,
N
.
T
a
l
e
b
,
a
n
d
B
.
A
y
o
u
b
,
“
I
n
t
e
g
r
a
t
i
n
g
o
n
t
o
l
o
g
y
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
e
n
h
a
n
c
e
d
d
e
c
i
si
o
n
su
p
p
o
r
t
i
n
t
h
y
r
o
i
d
d
i
se
a
se
p
r
e
d
i
c
t
i
o
n
,
”
i
n
2
0
2
3
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
D
e
c
i
s
i
o
n
A
i
d
S
c
i
e
n
c
e
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
(
D
AS
A)
,
S
e
p
.
2
0
2
3
,
p
p
.
2
0
8
–
2
1
2
.
d
o
i
:
1
0
.
1
1
0
9
/
D
A
S
A
5
9
6
2
4
.
2
0
2
3
.
1
0
2
8
6
6
7
5
.
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
:
303
-
3
1
2
312
[
2
6
]
V
.
B
r
i
n
d
h
a
a
n
d
A
.
M
u
t
h
u
k
u
mar
a
v
e
l
,
“
Ef
f
i
c
a
c
y
o
f
t
h
e
d
e
c
i
si
o
n
t
r
e
e
a
s
a
n
a
l
t
e
r
n
a
t
i
v
e
t
o
t
h
e
n
a
ï
v
e
B
a
y
e
s
mo
d
e
l
f
o
r
t
h
e
p
r
e
d
i
c
t
i
o
n
o
f
t
h
y
r
o
i
d
d
i
sea
s
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
i
n
O
p
t
i
m
i
zi
n
g
P
a
t
i
e
n
t
O
u
t
c
o
m
e
s
T
h
r
o
u
g
h
Mu
l
t
i
-
S
o
u
r
c
e
D
a
t
a
A
n
a
l
y
s
i
s
i
n
H
e
a
l
t
h
c
a
re
,
I
G
I
G
l
o
b
a
l
,
2
0
2
5
,
p
p
.
1
3
3
–
1
4
8
.
d
o
i
:
1
0
.
4
0
1
8
/
9
7
9
-
8
-
3
6
9
3
-
9
4
2
0
-
5
.
c
h
0
0
9
.
[
2
7
]
S
.
R
.
D
a
r
a
w
s
h
e
h
,
A
.
S
.
A
l
-
S
h
a
a
r
,
F
.
A
.
H
a
z
i
e
me
h
,
a
n
d
M
.
T
.
A
l
sh
u
r
i
d
e
h
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
t
h
y
r
o
i
d
d
i
s
e
a
s
e
u
si
n
g
m
u
l
t
i
n
o
m
i
a
l
l
o
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
s
(
L
R
)
,
”
i
n
T
h
e
E
f
f
e
c
t
o
f
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
o
n
Bu
si
n
e
ss
a
n
d
Ma
r
k
e
t
i
n
g
I
n
t
e
l
l
i
g
e
n
c
e
S
y
st
e
m
s
,
2
0
2
3
,
p
p
.
6
4
5
–
6
5
9
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
1
-
1
2
3
8
2
-
5
_
3
4
.
[
2
8
]
S
.
R
.
J,
S
.
K
S
,
a
n
d
S
.
S
.
T
K
,
“
P
r
e
d
i
c
t
i
v
e
m
o
d
e
l
i
n
g
f
o
r
t
h
y
r
o
i
d
d
i
se
a
se
u
si
n
g
g
r
a
d
i
e
n
t
b
o
o
st
i
n
g
a
n
d
r
a
n
d
o
m
f
o
r
e
s
t
a
l
g
o
r
i
t
h
ms
,
”
i
n
2
0
2
4
2
n
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
,
C
o
m
m
u
n
i
c
a
t
i
o
n
,
P
o
w
e
r
a
n
d
Em
b
e
d
d
e
d
S
y
st
e
m
(
S
C
O
PES
)
,
D
e
c
.
2
0
2
4
,
p
p
.
1
–
6
.
d
o
i
:
1
0
.
1
1
0
9
/
S
C
O
P
ES6
4
4
6
7
.
2
0
2
4
.
1
0
9
9
0
4
5
4
.
[
2
9
]
P
.
T.
R
a
j
a
n
.
B
a
n
d
N
.
M
u
t
h
u
k
u
mar
a
n
,
“
O
p
t
i
mi
z
e
d
C
N
N
a
n
d
a
d
a
p
t
i
v
e
R
B
F
N
N
f
o
r
c
h
a
n
n
e
l
e
st
i
ma
t
i
o
n
a
n
d
h
y
b
r
i
d
p
r
e
c
o
d
i
n
g
a
p
p
r
o
a
c
h
e
s
f
o
r
mu
l
t
i
u
ser
m
i
l
l
i
m
e
t
e
r
w
a
v
e
mass
i
v
e
M
I
M
O
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
l
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
1
2
,
n
o
.
7
,
p
p
.
1
2
9
5
–
1
3
1
8
,
Ju
l
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
8
0
/
0
0
2
0
7
2
1
7
.
2
0
2
4
.
2
3
7
2
0
6
0
.
[
3
0
]
Y
.
I
.
M
i
r
,
S
.
M
i
t
t
a
l
,
a
n
d
M
.
S
h
u
j
a
,
“
A
n
i
n
si
g
h
t
o
f
t
h
y
r
o
i
d
d
i
s
e
a
se
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
d
a
t
a
m
i
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
S
S
R
N
El
e
c
t
ro
n
i
c
J
o
u
rn
a
l
,
v
o
l
.
9
,
n
o
.
2
,
p
p
.
2
8
6
8
–
2
8
7
4
,
2
0
2
0
,
d
o
i
:
1
0
.
2
1
3
9
/
ssr
n
.
3
5
5
4
2
2
6
.
[
3
1
]
M
.
P
a
l
,
S
.
P
a
r
i
j
a
,
a
n
d
G
.
P
a
n
d
a
,
“
E
n
h
a
n
c
e
d
p
r
e
d
i
c
t
i
o
n
o
f
t
h
y
r
o
i
d
d
i
sea
s
e
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
me
t
h
o
d
,
”
i
n
2
0
2
2
I
EEE
VL
S
I
D
e
v
i
c
e
C
i
r
c
u
i
t
a
n
d
S
y
s
t
e
m
(
VL
S
I
D
C
S
)
,
F
e
b
.
2
0
2
2
,
p
p
.
1
9
9
–
2
0
4
.
d
o
i
:
1
0
.
1
1
0
9
/
V
LSI
D
C
S
5
3
7
8
8
.
2
0
2
2
.
9
8
1
1
4
7
2
.
[
3
2
]
D
.
C
.
Y
a
d
a
v
a
n
d
S
.
P
a
l
,
“
P
r
e
d
i
c
t
i
o
n
o
f
t
h
y
r
o
i
d
d
i
s
e
a
se
u
si
n
g
d
e
c
i
si
o
n
t
r
e
e
e
n
s
e
mb
l
e
me
t
h
o
d
,
”
H
u
m
a
n
-
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
I
n
t
e
g
r
a
t
i
o
n
,
v
o
l
.
2
,
n
o
.
1
–
4
,
p
p
.
8
9
–
9
5
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s4
2
4
5
4
-
0
2
0
-
0
0
0
0
6
-
y.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
S
h
u
r
iy
a
B
a
lu
s
a
m
y
h
a
s
fo
u
rtee
n
y
e
a
rs
o
f
p
ro
fe
ss
io
n
a
l
e
x
p
e
rien
c
e
in
tea
c
h
in
g
,
st
u
d
e
n
t
m
a
n
a
g
e
m
e
n
t,
a
n
d
so
ft
c
o
m
p
u
ti
n
g
.
S
h
e
h
o
l
d
s
a
P
h
.
D
.
in
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
.
S
h
e
is
c
u
rre
n
tl
y
wo
r
k
in
g
with
E
n
g
i
n
e
e
rin
g
Co
ll
e
g
e
a
s
a
n
a
ss
o
c
iate
p
ro
fe
s
so
r
.
S
h
e
h
a
s
fift
e
e
n
p
u
b
li
c
a
ti
o
n
s
,
in
c
lu
d
in
g
in
n
a
ti
o
n
a
l
a
n
d
i
n
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sh
u
riy
a
sm
il
e
@g
m
a
il
.
c
o
m
.
Ba
la
jish
a
n
m
u
g
a
m
Viv
e
k
a
n
a
d
h
a
n
h
a
d
1
4
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
tea
c
h
i
n
g
.
A
d
o
c
to
ra
te
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
fro
m
A
n
n
a
U
n
iv
e
rsity
,
C
h
e
n
n
a
i.
Co
m
p
lete
d
B
.
E
CS
E
a
n
d
M
.
E
CS
E
fr
o
m
S
N
S
Co
l
leg
e
o
f
T
e
c
h
n
o
l
o
g
y
,
C
o
i
m
b
a
to
re
.
P
u
b
l
ish
e
d
m
o
re
t
h
a
n
1
0
re
p
u
ted
j
o
u
r
n
a
ls
with
1
0
p
a
ten
ts.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
a
lajish
a
n
m
u
g
a
m
.
c
se
@g
m
a
il
.
c
o
m
.
Pra
th
im
a
Ma
b
e
l
J
o
h
n
is
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
a
t
Da
y
a
n
a
n
d
a
S
a
g
a
r
C
o
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
,
Visv
e
sv
a
ra
y
a
Tec
h
n
o
lo
g
ica
l
Un
iv
e
rsit
y
(VTU),
Be
n
g
a
lu
ru
,
Ka
rn
a
tak
a
,
I
n
d
ia.
S
h
e
h
a
s
re
c
e
iv
e
d
h
e
r
P
h
.
D
.
fr
o
m
VTU,
Be
lag
a
v
i,
Ka
rn
a
tak
a
,
In
d
ia.
S
h
e
re
c
e
iv
e
d
h
e
r
Ba
c
h
e
l
o
r
o
f
En
g
i
n
e
e
rin
g
a
n
d
M
a
ste
r
o
f
Tec
h
n
o
lo
g
y
d
e
g
re
e
s
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
fro
m
VTU
,
Be
lag
a
v
i,
Ka
rn
a
tak
a
,
In
d
ia.
S
h
e
h
a
s
a
b
o
u
t
1
6
y
e
a
rs
o
f
e
x
p
e
rien
c
e
i
n
tea
c
h
in
g
a
n
d
th
e
in
d
u
str
y
.
He
r
a
re
a
s
o
f
in
tere
st
a
re
c
o
m
p
u
ter
n
e
two
rk
s,
S
DN
,
m
o
b
il
e
n
e
two
r
k
s,
n
e
two
r
k
se
c
u
ri
ty
,
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
P
ra
th
ima
m
a
b
e
l
-
ise
@d
a
y
a
n
a
n
d
a
sa
g
a
r.
e
d
u
.
S
u
shm
a
S
u
n
i
l
Bh
o
sle
is
a
re
se
a
r
c
h
sc
h
o
lar
in
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
En
g
i
n
e
e
rin
g
,
a
t
S
h
r
i
Ja
g
d
is
h
p
ra
sa
d
Jh
a
b
a
rm
a
l
Ti
b
re
wa
la
Un
iv
e
rsity
,
Vid
y
a
n
a
g
a
ri,
J
h
u
n
jh
u
n
u
,
Ra
jas
th
a
n
,
a
n
d
a
lso
w
o
rk
i
n
g
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
a
t
Nu
tan
M
a
h
a
ra
sh
tra
In
sti
tu
te
o
f
En
g
i
n
e
e
rin
g
a
n
d
Tec
h
n
o
l
o
g
y
,
Tale
g
a
o
n
Da
b
h
a
d
e
,
P
u
n
e
,
M
a
h
a
ra
sh
tra,
I
n
d
ia.
S
h
e
h
a
s
c
o
m
p
lete
d
M
.
E.
(E&TC
-
C
o
m
m
u
n
ica
ti
o
n
Ne
two
rk
s)
fro
m
S
a
v
i
tri
b
a
i
P
h
u
le
P
u
n
e
Un
iv
e
rsity
,
P
u
n
e
,
M
a
h
a
ra
sh
tra,
In
d
ia.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
su
sh
m
a
4
4
b
@
o
u
t
lo
o
k
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.