Co
m
pu
t
er
Science
a
nd
I
nfo
r
m
a
t
io
n T
ec
hn
o
lo
g
ies
Vo
l.
7
,
No
.
3
,
No
v
em
b
er
20
26
,
p
p
.
304
~
313
I
SS
N:
2722
-
3
2
2
1
,
DOI
:
1
0
.
1
1
5
9
1
/csi
t
.
v
7
i
3
.
p
3
0
4
-
3
1
3
304
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
p
r
ime.
co
m/in
d
ex
.
p
h
p
/csi
t
H
ema
tolo
g
ica
l pr
o
filing o
f
ma
la
ria
-
induced
anem
ia
using
deep
lea
rning
Va
nro
s
e
P
a
na
s
he
Ny
a
m
a
ng
o
do
,
Welling
t
o
n M
a
k
o
nd
o
,
Sim
ba
i Zi
nd
o
v
e
H
a
r
a
r
e
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
H
a
r
a
r
e
,
Z
i
m
b
a
b
w
e
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
May
16
,
2
0
2
6
R
ev
is
ed
J
u
n
11
,
2
0
2
6
Acc
ep
ted
J
u
l
13
,
2
0
2
6
Ho
we
v
e
r,
m
a
laria
-
in
d
u
c
e
d
a
n
e
m
ia
(
M
IA
)
sti
ll
p
e
rsists
t
o
b
e
o
n
e
o
f
t
h
e
g
lo
b
a
l
h
e
a
lt
h
c
h
a
ll
e
n
g
e
s
with
m
a
n
y
c
a
se
s
o
f
il
ln
e
ss
a
n
d
fa
talit
ies
m
a
in
ly
i
n
p
re
g
n
a
n
t
wo
m
e
n
a
n
d
c
h
il
d
re
n
.
Dia
g
n
o
sis
o
f
m
a
laria
a
n
d
a
ss
o
c
iate
d
h
e
m
a
to
lo
g
ic
d
ise
a
se
s
su
c
h
a
s
a
n
e
m
ia
is
trad
it
i
o
n
a
ll
y
c
a
rried
o
u
t
t
h
ro
u
g
h
e
x
a
m
in
a
t
io
n
o
f
b
l
o
o
d
sm
e
a
r.
H
o
we
v
e
r,
su
c
h
tec
h
n
iq
u
e
s
re
q
u
ire
e
x
p
e
rti
se
,
tak
e
lo
n
g
p
e
rio
d
s,
a
n
d
t
h
e
re
a
re
h
ig
h
c
h
a
n
c
e
s
o
f
in
ter
-
o
b
se
rv
e
r
v
a
riab
il
it
y
.
He
re
,
a
n
a
u
to
m
a
ti
c
sy
ste
m
b
a
se
d
o
n
d
e
e
p
lea
rn
i
n
g
f
o
r
d
e
t
e
c
ti
o
n
o
f
P
las
m
o
d
iu
m
p
a
ra
site
a
n
d
e
stim
a
ti
o
n
o
f
a
n
e
m
ia
is
i
n
tr
o
d
u
c
e
d
.
Th
e
p
ro
p
o
se
d
sy
ste
m
u
se
s
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
two
rk
(CNN
)
b
ra
n
c
h
f
o
r
ima
g
e
a
n
a
ly
sis
a
n
d
m
u
lt
i
-
lay
e
r
p
e
rc
e
p
tro
n
(M
L
P
)
b
ra
n
c
h
fo
r
a
n
a
ly
z
in
g
c
li
n
ica
l
d
a
t
a
,
th
e
re
b
y
u
sin
g
t
h
e
ir
c
o
m
b
in
a
ti
o
n
i
n
m
u
lt
i
-
lab
e
l
c
las
sifica
ti
o
n
.
T
h
e
a
d
v
a
n
ta
g
e
o
f
su
c
h
tec
h
n
iq
u
e
is
t
h
e
c
a
p
a
b
il
it
y
o
f
t
h
e
m
o
d
e
l
t
o
d
iag
n
o
se
c
o
m
p
lex
h
e
m
a
to
lo
g
ica
l
sig
n
s
a
n
d
g
i
v
e
p
ro
b
a
b
il
ist
ic
sc
o
r
e
s.
Th
is
sy
ste
m
wa
s
fo
u
n
d
to
b
e
a
c
c
u
ra
te,
p
re
c
ise
a
n
d
re
li
a
b
le.
K
ey
w
o
r
d
s
:
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
Dee
p
lear
n
in
g
Hem
ato
lo
g
ical
p
r
o
f
ilin
g
Ma
lar
ia
-
in
d
u
ce
d
a
n
em
ia
Me
d
ical
im
ag
e
class
if
icatio
n
Mu
lti
-
lay
er
p
er
ce
p
tr
o
n
Mu
ltimo
d
al
f
u
s
io
n
Po
in
t
-
of
-
ca
r
e
d
iag
n
o
s
tics
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
:
W
ellin
g
to
n
Ma
k
o
n
d
o
Har
ar
e
I
n
s
titu
te
o
f
T
ec
h
n
o
l
o
g
y
Har
ar
e,
Z
im
b
ab
we
E
m
ail:
wm
ak
o
n
d
o
@
h
it.a
c.
zw
1.
I
NT
RO
D
UCT
I
O
N
Ma
lar
ia
is
a
p
o
ten
tially
f
atal
i
n
f
ec
tio
u
s
d
is
ea
s
e.
I
n
2
0
2
3
,
th
e
r
e
wer
e
an
esti
m
ated
2
6
3
m
illi
o
n
m
alar
ia
ca
s
es
an
d
5
9
7
,
0
0
0
d
ea
t
h
s
g
lo
b
ally
,
with
9
5
%
o
f
d
ea
th
s
o
cc
u
r
r
in
g
in
th
e
W
o
r
ld
Hea
lth
Or
g
an
izatio
n
(
W
HO
)
Af
r
ican
R
eg
io
n
[
1
]
.
Ma
lar
ia
ca
n
p
r
o
g
r
ess
to
an
ae
m
ia
if
n
o
t
tr
ea
ted
ea
r
ly
.
Ma
lar
ia
-
in
d
u
ce
d
an
em
ia
(
MI
A)
ar
is
e
s
wh
en
Plas
m
o
d
iu
m
p
ar
asit
es
r
u
p
tu
r
e
r
ed
b
lo
o
d
c
ells
(
R
B
C
)
,
tr
ig
g
er
in
g
a
f
all
i
n
h
em
o
g
lo
b
in
t
h
at
is
p
ar
ticu
lar
ly
life
-
th
r
ea
ten
in
g
in
ch
ild
r
en
u
n
d
e
r
f
iv
e
a
n
d
p
r
eg
n
an
t w
o
m
en
[
1
]
.
MI
A
co
n
tr
ib
u
tes
s
u
b
s
tan
tially
to
th
e
h
ig
h
p
r
ev
alen
ce
o
f
s
e
v
er
e
an
e
m
ia
ca
s
es
am
o
n
g
c
h
i
ld
r
en
less
th
an
f
iv
e
y
ea
r
s
o
ld
in
en
d
e
m
ic
ar
ea
s
[
2
]
.
E
v
e
n
th
o
u
g
h
it
is
clea
r
th
at
Plas
m
o
d
iu
m
ca
u
s
es
an
em
ia
th
r
o
u
g
h
th
e
s
cien
tific
ca
u
s
al
r
elatio
n
s
h
ip
b
etwe
en
th
em
,
th
eir
d
iag
n
o
s
es
o
cc
u
r
s
ep
ar
ately
b
y
r
ely
in
g
o
n
lab
o
r
ato
r
y
test
s
th
at
u
s
e
s
ep
ar
ate
p
iece
s
o
f
eq
u
ip
m
en
t
an
d
h
av
e
d
i
f
f
er
en
t r
ef
e
r
r
al
ch
ain
s
[
3
]
.
Mo
s
t
o
f
th
e
a
u
t
o
m
ated
d
iag
n
o
s
tic
s
o
lu
tio
n
s
in
th
e
c
o
n
tem
p
o
r
ar
y
liter
atu
r
e
co
n
tin
u
e
th
is
tr
en
d
,
f
o
cu
s
in
g
th
eir
ef
f
o
r
ts
o
n
eith
e
r
d
etec
tin
g
p
ar
asit
es
f
r
o
m
m
icr
o
s
co
p
y
im
ag
es
[
4
]
o
r
id
en
tif
y
in
g
a
n
em
ia
u
s
in
g
b
l
o
o
d
p
ar
am
eter
s
[
5
]
.
Su
ch
f
r
ag
m
en
tatio
n
b
ec
o
m
es
a
s
ig
n
if
ican
t
ch
allen
g
e,
esp
ec
i
ally
in
r
eso
u
r
ce
-
co
n
s
tr
ain
e
d
r
e
g
io
n
s
wh
er
e
p
atien
ts
m
ay
b
e
u
n
ab
le
to
f
u
lf
ill
th
e
f
o
llo
w
-
u
p
s
[
6
]
.
I
n
o
r
d
er
to
o
v
er
co
m
e
th
is
c
h
allen
g
e,
th
is
r
e
s
ea
r
ch
f
o
c
u
s
es
o
n
d
ev
elo
p
in
g
m
u
lt
i
-
m
o
d
al
d
ee
p
lear
n
in
g
f
r
am
ewo
r
k
th
at
will
b
e
ab
le
t
o
p
e
r
f
o
r
m
b
o
th
class
if
icatio
n
o
f
ac
tiv
e
m
alar
ia
an
d
an
em
ia
ca
u
s
ed
b
y
th
e
d
is
ea
s
e
in
a
s
in
g
le
s
tep
.
Qu
ick
an
d
ac
cu
r
ate
d
iag
n
o
s
is
is
cr
u
cial
f
o
r
p
r
o
p
e
r
tr
ea
tm
e
n
t.
As
it
s
tan
d
s
,
m
alar
ia
a
n
d
o
th
er
b
lo
o
d
d
is
o
r
d
er
s
,
in
clu
d
in
g
an
em
ia,
ar
e
u
s
u
ally
d
etec
ted
b
y
m
a
n
u
ally
ex
am
in
in
g
Giem
s
a
-
s
tain
ed
p
er
ip
h
er
al
b
lo
o
d
s
m
ea
r
s
u
n
d
er
a
lig
h
t
m
icr
o
s
co
p
e.
T
h
is
m
eth
o
d
wo
r
k
s
,
b
u
t h
a
s
q
u
ite
a
f
ew
d
is
ad
v
a
n
tag
es;
it
is
tim
e
co
n
s
u
m
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
Hem
a
to
lo
g
ica
l p
r
o
fili
n
g
o
f m
a
la
r
ia
-
in
d
u
ce
d
a
n
emia
u
s
in
g
d
e
ep
lea
r
n
in
g
(
V
a
n
r
o
s
e
P
a
n
a
s
h
e
N
ya
ma
n
g
o
d
o
)
305
an
d
r
e
q
u
ir
es
s
k
illed
p
ar
asit
o
lo
g
is
ts
wh
o
ar
e
o
f
ten
n
o
t
r
ea
d
il
y
av
ailab
le
in
r
e
g
io
n
s
wh
er
e
m
alar
ia
is
co
m
m
o
n
,
b
etter
y
et
in
Af
r
ica.
As
a
r
esu
lt,
th
er
e
is
a
s
tr
o
n
g
n
ee
d
f
o
r
a
u
to
m
ated
s
y
s
tem
s
to
s
u
p
p
o
r
t
b
lo
o
d
a
n
aly
s
is
[
7
]
.
T
h
e
m
ain
d
if
f
er
en
ce
in
th
is
s
y
s
tem
co
m
p
a
r
ed
to
p
r
ev
io
u
s
ly
d
ev
elo
p
ed
m
u
ltimo
d
al
d
ia
g
n
o
s
tic
f
r
am
ewo
r
k
s
is
n
o
t
in
u
s
in
g
m
u
ltip
le
m
o
d
al
ities
b
u
t
in
th
e
ty
p
e
o
f
in
ter
d
ep
en
d
en
ce
b
etwe
en
th
e
c
lass
if
icatio
n
task
s
.
I
n
p
r
ev
io
u
s
m
u
ltimo
d
al
s
y
s
tem
s
in
m
e
d
ical
ar
tific
ial
in
telli
g
en
ce
(
AI
)
,
m
o
d
ality
f
u
s
io
n
te
ch
n
iq
u
es
h
av
e
b
ee
n
u
s
ed
to
en
h
an
ce
d
etec
tio
n
o
f
a
s
in
g
le
p
ath
o
lo
g
ic
co
n
d
itio
n
b
y
in
co
r
p
o
r
atin
g
v
ar
io
u
s
in
f
o
r
m
atio
n
s
o
u
r
ce
s
.
Fo
r
in
s
tan
ce
,
o
n
e
co
u
l
d
c
o
m
b
in
e
g
en
o
m
ic
a
n
d
im
a
g
e
f
ea
tu
r
es
to
d
etec
t
a
s
p
ec
if
ic
ca
n
ce
r
s
u
b
ty
p
e.
I
n
th
e
s
u
g
g
ested
ap
p
r
o
ac
h
,
th
er
e
a
r
e
n
o
two
is
o
lated
d
is
ea
s
es
th
at
ar
e
class
i
f
ied
in
d
ep
e
n
d
en
tly
.
On
th
e
c
o
n
tr
ar
y
,
an
em
ia
is
v
iewe
d
as
th
e
s
ec
o
n
d
ar
y
r
esu
lt
o
f
th
e
d
estru
ctio
n
o
f
RBC
b
y
Plas
m
o
d
iu
m
.
T
h
is
ca
u
s
ativ
e
lin
k
m
ak
es
th
e
cu
r
r
en
t
wo
r
k
s
tan
d
o
u
t
an
d
b
e
co
m
e
u
n
iq
u
e,
wh
ich
m
ea
n
s
th
at
it
is
th
e
p
r
im
ar
y
in
n
o
v
atio
n
o
f
th
e
p
r
o
ject
th
at
en
a
b
les
an
aly
zin
g
b
o
th
a
ca
u
s
ativ
e
f
ac
to
r
an
d
a
h
em
ato
lo
g
ic
al
ef
f
ec
t
at
o
n
ce
.
T
h
at
is
wh
y
t
h
e
ar
ch
itectu
r
e
h
as
b
ee
n
d
e
v
elo
p
e
d
in
s
u
ch
a
wa
y
th
at
th
e
two
task
s
wo
u
ld
b
e
p
r
o
ce
s
s
ed
s
im
u
ltan
e
o
u
s
ly
,
i
.
e.
,
b
o
th
v
is
u
al
an
d
h
em
ato
lo
g
ical
m
a
n
if
estatio
n
s
o
f
er
y
t
h
r
o
cy
te
d
am
ag
e
b
y
p
ar
a
s
ites
wo
u
ld
b
e
en
co
d
e
d
in
p
ar
allel.
Dee
p
lear
n
in
g
h
as
s
h
o
wn
g
r
ea
t
ca
p
ab
ilit
y
,
esp
ec
ially
with
m
ed
ical
im
ag
es.
I
t
ca
n
also
b
e
m
o
d
if
ied
to
u
s
e
n
o
t o
n
ly
m
ed
ical
im
ag
es b
u
t a
ls
o
tab
u
lar
clin
ical
d
ata
s
im
u
ltan
eo
u
s
ly
.
R
ec
en
t stu
d
ies
h
av
e
cr
ea
ted
m
o
d
els
th
at
f
o
cu
s
o
n
s
in
g
le
in
d
ep
en
d
en
t
task
s
lik
e
d
etec
tin
g
m
alar
i
a
[
5
]
o
r
id
e
n
tify
in
g
an
em
ia
[
6
]
.
Ho
wev
er
,
th
er
e
is
s
till
a
n
ee
d
f
o
r
s
y
s
tem
s
th
at
ta
ck
le
p
air
wis
e
d
etec
tio
n
in
th
is
p
ar
ticu
lar
ca
s
e,
m
alar
ia
-
in
d
u
c
ed
an
ae
m
ia,
wh
ile
u
s
in
g
d
if
f
er
en
t
ty
p
es
o
f
p
a
tie
n
t
d
ata.
T
h
is
p
r
o
ject
aim
s
to
f
ill
th
at
g
ap
b
y
d
ev
elo
p
i
n
g
a
d
ee
p
lear
n
in
g
m
o
d
el
th
at
co
m
b
in
es c
lin
ical
tab
u
lar
d
ata
an
d
b
l
o
o
d
s
m
ea
r
im
a
g
es to
esti
m
ate
th
e
ch
an
ce
s
an
em
ia
f
r
o
m
th
e
ex
is
ten
ce
o
f
m
alar
ia.
T
h
is
o
f
f
er
s
a
m
o
r
e
co
m
p
lete
b
lo
o
d
an
al
y
s
is
.
2.
RE
L
AT
E
D
WO
RK
W
h
er
ea
s
n
o
n
in
v
asiv
e
co
n
j
u
n
c
tiv
al
p
allo
r
im
ag
e
a
n
aly
s
is
was
s
tu
d
ied
f
o
r
s
cr
ee
n
i
n
g
a
n
em
i
a,
th
is
ar
ea
f
alls
o
u
ts
id
e
th
e
s
co
p
e
o
f
t
h
is
s
tu
d
y
th
at
s
p
ec
if
ically
tar
g
ets
th
e
d
iag
n
o
s
is
o
f
a
n
em
ia
d
u
e
to
m
alar
ia
in
f
ec
tio
n
,
wh
ich
n
ec
ess
itates th
e
u
s
e
o
f
b
lo
o
d
s
m
ea
r
im
ag
es in
co
n
ju
n
ctio
n
with
co
m
p
lete
b
lo
o
d
co
u
n
ts
(
C
B
C
s
)
.
2
.
1
.
Dee
p
lea
rning
f
o
r
m
a
l
a
ria
det
ec
t
io
n
Ma
ch
in
e
lear
n
i
n
g
h
as
b
ee
n
ap
p
lied
to
h
ae
m
ato
lo
g
ical
d
i
ag
n
o
s
tics
,
lead
in
g
to
th
e
u
s
e
o
f
d
ee
p
lear
n
in
g
ar
c
h
itectu
r
es.
Kass
im
et
a
l.
[
7
]
ex
am
in
e
d
au
to
m
ate
d
d
iag
n
o
s
tic
tech
n
iq
u
es
an
d
s
h
o
wed
th
at
m
ac
h
in
e
lear
n
in
g
a
n
d
d
ee
p
lear
n
in
g
h
av
e
b
ec
o
m
e
h
i
g
h
ly
ef
f
ec
tiv
e
in
id
en
tify
i
n
g
m
alar
ia
p
a
r
asit
es.
Fu
h
ad
et
a
l.
[
5
]
f
u
r
th
er
s
h
o
wed
th
at
cu
s
to
m
is
ed
co
n
v
o
lu
ti
o
n
al
n
eu
r
al
n
etw
o
r
k
s
(
C
NNs),
co
m
b
in
ed
w
ith
d
ata
au
g
m
e
n
tatio
n
,
s
ig
n
if
ican
tly
im
p
r
o
v
e
th
e
au
t
o
n
o
m
o
u
s
d
etec
tio
n
o
f
Plas
m
o
d
iu
m
p
ar
asit
es,
h
en
ce
r
e
d
u
cin
g
h
u
m
a
n
er
r
o
r
an
d
f
atig
u
e.
T
h
e
r
e
v
iew
p
o
in
te
d
o
u
t
th
at
t
h
e
m
o
d
els
ca
n
h
an
d
le
d
ata
f
aster
,
y
et
th
e
y
h
av
e
n
o
t
b
ee
n
a
b
le
to
g
en
er
alis
e
b
etwe
en
v
ar
io
u
s
clin
ical
d
atab
ases
an
d
s
tain
in
g
p
r
o
ce
d
u
r
es.
Ace
v
ed
o
et
a
l.
[
8
]
f
o
cu
s
ed
o
n
tr
a
n
s
f
er
lear
n
in
g
a
n
d
an
en
s
em
b
le
m
o
d
el
to
class
if
y
b
lo
o
d
ce
lls
an
d
th
u
s
m
i
n
im
is
e
th
e
n
u
m
b
er
o
f
f
alse
p
o
s
itiv
e
p
r
ed
ictio
n
s
.
B
ib
in
et
a
l
.
[
9
]
i
m
p
lem
en
ted
s
o
p
h
is
ticated
C
NNs
f
o
r
ce
llu
l
ar
im
ag
es
to
in
cr
ea
s
e
th
e
s
p
ee
d
o
f
th
e
m
alar
ia
d
iag
n
o
s
tic
p
r
o
ce
s
s
.
T
o
m
itig
ate
m
o
r
p
h
o
lo
g
ical
d
if
f
er
en
ce
s
in
t
h
e
clin
ical
s
ettin
g
,
R
aja
et
a
l.
[
1
0
]
p
r
o
p
o
s
ed
a
Swin
-
Siam
ese
h
y
b
r
id
m
o
d
el.
T
h
e
au
to
m
ate
d
d
etec
tio
n
o
f
m
alar
ia
h
as
s
ig
n
if
ican
tly
a
d
v
an
ce
d
.
T
r
an
s
f
e
r
lear
n
in
g
ap
p
r
o
ac
h
es
u
tili
zin
g
p
r
etr
ain
e
d
ar
ch
itect
u
r
es
s
u
ch
as
r
esid
u
al
n
etw
o
r
k
-
5
0
(
R
esNet
-
50
)
,
v
is
u
al
g
eo
m
etr
y
g
r
o
u
p
-
1
6
(
VGG
-
16
)
,
a
n
d
Den
s
eNe
t
h
av
e
f
u
r
t
h
er
d
em
o
n
s
tr
ated
th
e
v
alu
e
o
f
lev
er
ag
i
n
g
I
m
ag
e
Net
-
d
er
iv
ed
f
ea
t
u
r
e
r
ep
r
esen
tatio
n
s
f
o
r
m
alar
ia
c
lass
if
icatio
n
,
p
ar
ticu
lar
ly
in
d
ata
-
s
ca
r
ce
clin
ical
s
ettin
g
s
[
1
1
]
.
I
n
ad
d
itio
n
to
p
r
o
v
id
i
n
g
m
o
r
e
e
v
id
en
ce
o
f
t
h
e
u
s
ef
u
ln
ess
o
f
tr
an
s
f
er
lear
n
in
g
in
d
iag
n
o
s
in
g
m
alar
ia,
Ma
q
s
o
o
d
et
a
l.
[
1
2
]
s
h
o
wed
th
at
d
ee
p
C
NN
m
o
d
e
ls
tr
ain
ed
u
s
in
g
im
ag
es
o
f
th
in
b
lo
o
d
s
m
ea
r
s
wer
e
ca
p
ab
le
o
f
ac
cu
r
ate
p
ar
asit
e
d
etec
tio
n
e
v
en
wh
en
tr
ain
ed
u
n
d
er
r
estrictiv
e
a
n
n
o
tated
d
a
ta.
R
ec
en
tly
,
L
a
g
h
ar
i
et
a
l.
[
1
3
]
co
m
p
a
r
ed
eig
h
t
p
r
e
-
tr
ain
ed
C
NN
m
o
d
els,
n
a
m
ely
R
esNet
-
5
0
,
R
esNet
-
1
0
1
,
an
d
Xce
p
tio
n
am
o
n
g
o
th
er
s
,
to
class
if
y
ce
lls
in
to
m
alar
ia
p
ar
asit
es,
co
n
f
ir
m
in
g
th
e
s
u
p
er
io
r
ity
o
f
e
n
s
em
b
le
tr
an
s
f
er
lear
n
i
n
g
o
v
er
in
d
i
v
id
u
al
tr
an
s
f
er
lea
r
n
in
g
m
o
d
els
b
ased
o
n
p
r
ec
is
io
n
an
d
r
ec
all
b
alan
ce
.
Sil
k
a
et
a
l.
[
1
4
]
f
u
r
th
er
d
em
o
n
s
tr
ated
h
ig
h
ac
cu
r
ac
y
in
m
alar
ia
d
etec
tio
n
u
s
in
g
ad
v
a
n
ce
d
d
ee
p
co
n
v
o
lu
tio
n
al
ar
ch
itectu
r
es,
ac
h
iev
in
g
9
9
.
6
8
%
ac
cu
r
ac
y
o
n
s
tan
d
ar
d
b
en
ch
m
ar
k
d
atasets
.
2
.
2
.
Aut
o
m
a
t
ed
a
nem
ia
s
cr
e
ening
L
o
n
e
et
a
l.
[
6
]
cr
ea
ted
a
d
ee
p
lear
n
in
g
s
y
s
tem
u
s
in
g
C
NNs
to
ex
tr
ac
t
f
ea
tu
r
es
f
r
o
m
m
icr
o
s
co
p
ic
b
lo
o
d
s
m
ea
r
im
ag
es,
h
e
n
ce
s
u
cc
ess
f
u
lly
d
etec
tin
g
in
d
ic
ato
r
s
o
f
an
e
m
ia.
Gil
et
a
l.
[
2
]
s
im
i
lar
ly
u
tili
s
ed
d
ee
p
lear
n
in
g
C
NNs
to
class
if
y
th
e
s
ev
er
ity
o
f
RBC
d
ef
o
r
m
er
s
.
T
h
at
d
em
o
n
s
tr
ated
th
at
d
ee
p
lear
n
in
g
ca
n
b
e
a
r
eliab
le
alter
n
ativ
e
to
m
an
u
al
s
cr
ee
n
in
g
.
Sajith
et
a
l
.
[
1
5
]
in
co
r
p
o
r
ated
e
x
p
lain
ab
le
A
I
(
XAI
)
t
o
h
i
g
h
lig
h
t
th
e
s
p
ec
if
ic
f
ea
t
u
r
e
a
b
n
o
r
m
al
ities
in
ce
lls
r
esp
o
n
s
ib
le
f
o
r
an
em
ia
d
iag
n
o
s
is
u
s
in
g
C
NN.
Nav
y
a
et
a
l
.
[
1
6
]
en
g
ag
ed
d
ee
p
lear
n
in
g
.
I
n
ad
d
itio
n
to
th
e
u
s
e
o
f
b
lo
o
d
s
m
ea
r
s
,
Sh
ah
za
d
et
a
l.
[
1
7
]
d
ev
is
ed
an
in
g
en
i
o
u
s
m
o
d
el
o
f
a
th
r
ee
-
la
y
er
ed
d
ee
p
n
eu
r
al
n
etwo
r
k
wh
ic
h
co
u
ld
d
etec
t
an
d
class
if
y
th
e
g
r
ad
e
o
f
an
ae
m
ia
b
ased
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
3
,
No
v
em
b
er
20
26
:
3
0
4
-
313
306
p
er
ip
h
er
al
b
lo
o
d
s
m
ea
r
im
a
g
e
s
,
th
er
eb
y
v
alid
atin
g
th
e
ab
ilit
y
o
f
h
ier
ar
c
h
ically
d
esig
n
e
d
C
NNs
to
r
ec
o
g
n
ize
ev
en
m
in
u
te
d
if
f
er
en
ce
s
b
et
wee
n
th
e
v
ar
io
u
s
ty
p
es
o
f
a
n
ae
m
ia
in
ter
m
s
o
f
m
o
r
p
h
o
l
o
g
y
.
I
n
ad
d
itio
n
to
ex
p
lo
r
in
g
a
u
to
m
ated
m
eth
o
d
s
o
f
d
iag
n
o
s
in
g
an
ae
m
ia
th
r
o
u
g
h
n
o
n
-
in
v
asiv
e
tech
n
iq
u
es
o
th
er
th
an
b
l
o
o
d
test
s
,
Ma
n
n
in
o
et
a
l.
[
1
8
]
ap
p
lied
m
ac
h
in
e
lea
r
n
in
g
/
d
ee
p
lear
n
in
g
alg
o
r
i
th
m
s
f
o
r
co
n
ju
n
cti
v
al
im
ag
e
a
n
aly
s
is
.
Fu
r
th
er
m
o
r
e
,
R
am
za
n
et
a
l.
[
1
9
]
p
r
o
p
o
s
ed
an
in
n
o
v
ativ
e
ap
p
r
o
ac
h
b
ased
o
n
m
u
ltimo
d
al
in
te
g
r
atio
n
o
f
elec
tr
o
n
ic
h
ea
lth
r
ec
o
r
d
(
E
H
R
)
an
d
co
n
ju
n
ctiv
al
im
ag
es
f
o
r
an
em
ia
d
etec
tio
n
,
wh
ile
R
am
za
n
et
a
l.
[
2
0
]
p
r
o
v
id
e
d
ev
id
e
n
ce
f
o
r
th
e
e
f
f
i
ca
cy
o
f
in
te
g
r
ativ
e
m
ac
h
in
e
le
ar
n
in
g
with
atten
tio
n
.
2
.
3
.
M
ultim
o
da
l
f
us
io
n f
o
r
c
lin
ica
l dec
is
io
n su
pp
o
rt
R
esear
ch
h
as
b
ee
n
m
o
tiv
ated
b
y
d
iag
n
o
s
tic
lim
itatio
n
s
o
f
s
in
g
le
-
m
o
d
ality
s
y
s
tem
s
th
at
h
av
e
b
ee
n
u
s
ed
in
th
e
p
ast.
T
h
is
h
as
s
et
a
n
ew
p
a
t
h
to
lo
o
k
i
n
to
m
u
lti
-
m
o
d
al
f
u
s
io
n
a
p
p
r
o
ac
h
es
to
c
o
m
b
in
e
h
eter
o
g
en
e
o
u
s
d
ata
s
tr
ea
m
s
.
T
h
e
n
ec
ess
ity
o
f
m
u
ltip
lex
ed
d
is
ea
s
e
d
etec
tio
n
ar
ch
itectu
r
es
th
at
ar
e
ca
p
ab
le
o
f
ev
alu
atin
g
m
u
ltip
le
h
em
ato
lo
g
ical
co
n
d
itio
n
s
f
r
o
m
a
s
in
g
le
b
lo
o
d
s
p
ec
im
en
was
ex
p
lo
r
ed
b
y
R
ajar
am
an
et
a
l
.
[
4
]
th
o
u
g
h
it
was
r
estricte
d
to
v
is
u
al
d
ata
o
n
ly
.
T
eo
h
et
a
l.
[
3
]
r
e
v
iewe
d
m
u
ltimo
d
al
f
u
s
io
n
tech
n
iq
u
es
a
n
d
d
o
cu
m
en
ted
th
at
in
ter
m
ed
iate,
late
f
u
s
i
o
n
s
tr
ateg
ies
s
p
ec
if
ically
f
e
atu
r
e
co
n
ca
ten
atio
n
co
n
s
is
ten
tly
o
u
tp
er
f
o
r
m
e
ar
ly
f
u
s
io
n
f
o
r
b
o
th
s
tr
u
ct
u
r
ed
an
d
u
n
s
tr
u
ctu
r
ed
d
ata
ac
r
o
s
s
d
if
f
er
e
n
t
m
ed
ical
co
n
d
itio
n
s
.
T
h
is
f
in
d
in
g
is
also
s
u
p
p
o
r
ted
b
y
Stah
ls
ch
m
id
t
et
a
l.
[
2
1
]
wh
o
c
o
n
d
u
cted
an
ex
ten
s
iv
e
s
u
r
v
ey
o
n
m
u
ltimo
d
al
d
ee
p
lear
n
i
n
g
f
o
r
b
io
m
ed
ical
d
ata
f
u
s
io
n
,
wh
ic
h
r
ev
ea
led
th
at
f
ea
t
u
r
e
co
n
ca
t
en
atio
n
ap
p
r
o
ac
h
es
wer
e
f
o
u
n
d
to
alwa
y
s
o
u
tp
er
f
o
r
m
ea
r
lier
an
d
later
f
u
s
io
n
a
p
p
r
o
ac
h
es
in
f
u
s
in
g
s
t
r
u
ctu
r
ed
d
ata
with
u
n
s
tr
u
ctu
r
ed
im
ag
es.
C
u
i
et
a
l
.
[
2
2
]
f
u
r
t
h
er
r
ei
n
f
o
r
ce
d
th
ese
f
in
d
in
g
s
ac
r
o
s
s
d
is
ea
s
e
d
iag
n
o
s
is
an
d
p
r
o
g
n
o
s
is
ap
p
licatio
n
s
.
T
h
er
e
ar
e
th
r
ee
p
r
im
ar
y
ty
p
e
s
o
f
m
u
ltimo
d
al
f
u
s
io
n
ap
p
r
o
ac
h
es
in
m
u
ltimo
d
al
lear
n
in
g
;
n
am
ely
,
ea
r
ly
f
u
s
io
n
(
co
n
ca
ten
atio
n
at
th
e
in
p
u
t
lev
el)
,
in
ter
m
e
d
iate
f
u
s
io
n
(
co
n
ca
te
n
atio
n
o
f
in
d
e
p
en
d
en
t
m
o
d
alities
at
th
e
f
ea
tu
r
e
lev
el)
,
an
d
late
f
u
s
io
n
(
co
m
b
i
n
atio
n
o
f
in
d
ep
e
n
d
en
tly
m
ad
e
d
ec
is
io
n
s
)
.
E
a
r
ly
f
u
s
io
n
d
estro
y
s
th
e
u
n
iq
u
e
s
tr
u
ctu
r
e
o
f
ea
ch
m
o
d
ality
b
ef
o
r
e
p
er
f
o
r
m
in
g
e
n
co
d
in
g
,
wh
ich
p
o
s
es
a
d
is
ad
v
an
tag
e
if
h
i
g
h
d
im
en
s
io
n
al
im
ag
e
v
ec
to
r
s
a
r
e
co
n
ca
ten
ated
with
lo
w
-
d
im
e
n
s
io
n
al
tab
u
lar
v
ec
to
r
s
.
T
h
o
u
g
h
late
f
u
s
io
n
d
o
es
n
o
t
co
m
p
r
o
m
is
e
m
o
d
ality
in
d
ep
en
d
en
ce
,
it
m
ak
es
th
e
class
if
ier
h
ea
d
u
n
a
b
le
to
lear
n
th
e
in
ter
d
ep
en
d
e
n
cies
b
etwe
en
th
e
m
o
d
alities
.
Featu
r
e
-
lev
el
co
n
ca
ten
atio
n
ap
p
r
o
ac
h
,
u
s
ed
in
th
is
p
a
p
er
,
is
th
e
b
est
tr
ad
e
-
o
f
f
b
etwe
en
th
e
two
s
in
ce
ea
ch
m
o
d
ality
is
s
ep
ar
ately
e
n
co
d
e
d
u
s
in
g
its
o
wn
s
p
ec
ialized
b
r
an
ch
(
C
NN
f
o
r
im
ag
e
an
d
m
u
lti
-
lay
er
p
er
ce
p
tr
o
n
(
ML
P)
f
o
r
tab
le)
b
ef
o
r
e
b
ein
g
co
n
ca
ten
ated
an
d
class
if
ied
b
y
th
e
s
h
ar
ed
h
ea
d
.
T
h
is
s
tr
ateg
y
ca
n
b
e
d
ir
ec
tly
r
elate
d
to
th
e
r
esu
lts
f
o
u
n
d
in
[
5
]
,
[
2
1
]
.
As
f
ar
as
a
n
in
f
o
r
m
atio
n
a
n
d
co
m
m
u
n
icatio
n
tech
n
o
lo
g
y
(
I
C
T
)
in
f
r
astru
ctu
r
e
f
o
r
im
p
le
m
en
tatio
n
g
o
es,
th
e
af
o
r
em
en
tio
n
ed
m
u
ltimo
d
al
ar
ch
itectu
r
e
wo
u
ld
b
e
s
u
itab
le
f
o
r
in
teg
r
atio
n
i
n
to
clo
u
d
lab
o
r
ato
r
y
in
f
o
r
m
atio
n
s
y
s
tem
s
.
T
h
e
lig
h
tweig
h
t
ML
P
s
u
b
n
etwo
r
k
wo
u
ld
an
al
y
ze
s
tr
u
ctu
r
ed
d
ata
f
r
o
m
C
B
C
test
r
esu
lts
av
ailab
le
th
r
o
u
g
h
E
HR
s
,
an
d
th
e
C
NN
im
ag
e
s
u
b
n
etwo
r
k
co
u
ld
p
r
o
ce
s
s
d
ig
itized
b
lo
o
d
s
m
ea
r
im
ag
es
o
b
tain
ed
u
s
in
g
in
ex
p
e
n
s
iv
e
m
icr
o
s
co
p
e
attac
h
m
e
n
ts
f
o
r
s
m
ar
tp
h
o
n
es.
Hen
ce
,
s
u
ch
a
n
ar
c
h
itectu
r
e
wo
u
l
d
b
e
co
m
p
atib
le
with
p
o
in
t
-
of
-
ca
r
e
(
POC
)
an
d
m
Hea
lth
d
ep
lo
y
m
en
t
s
tr
ateg
ie
s
,
wh
ich
wo
u
ld
b
e
r
elev
an
t
to
th
e
jo
u
r
n
al
’
s
f
o
cu
s
o
n
I
C
T
ap
p
lica
tio
n
s
an
d
d
is
tr
ib
u
ted
h
ea
lth
ca
r
e
s
y
s
tem
s
.
2
.
4
.
Da
t
a
s
ca
rc
it
y
,
g
ener
a
t
i
v
e
a
ug
m
ent
a
t
io
n,
a
nd
f
eder
a
t
ed
lea
rning
I
n
th
is
ca
s
e,
th
e
au
g
m
en
tatio
n
m
eth
o
d
ap
p
lied
in
v
o
lv
e
d
s
tan
d
ar
d
g
eo
m
etr
y
an
d
p
h
o
to
m
etr
y
m
an
ip
u
latio
n
s
s
u
c
h
as
h
o
r
izo
n
tal
f
lip
s
,
r
a
n
d
o
m
r
o
tatio
n
s
b
etwe
en
±
1
5
d
eg
r
ee
s
,
an
d
c
o
n
tr
ast
ad
ju
s
tm
en
t.
I
n
s
p
ite
o
f
th
e
f
ac
t
th
at,
ac
co
r
d
in
g
to
g
en
e
r
atio
n
au
g
m
en
tatio
n
with
g
en
er
ativ
e
ad
v
er
s
ar
ial
n
etwo
r
k
s
(
GANs)
,
s
u
ch
as
C
y
cleG
AN
an
d
c
o
n
d
itio
n
al
GA
N
m
o
d
els
tr
ain
e
d
o
n
b
lo
o
d
s
m
ea
r
im
ag
es,
p
r
o
v
es
e
f
f
icien
t
in
in
cr
ea
s
in
g
th
e
v
o
l
u
m
e
o
f
m
ed
ical
im
ag
es,
th
is
m
eth
o
d
was
n
o
t
ap
p
lied
in
th
e
cu
r
r
en
t
ex
p
er
im
en
t
b
ec
au
s
e
o
f
th
e
ex
tr
a
co
m
p
u
tatio
n
co
s
ts
n
ec
ess
ar
y
f
o
r
th
e
s
tab
le
tr
ain
in
g
o
f
GANs
o
n
a
s
m
all
d
ataset
s
o
u
r
ce
an
d
p
o
s
s
ib
le
ar
tifa
cts
th
at
d
o
n
o
t
c
o
r
r
esp
o
n
d
to
ac
tu
al
v
ar
iatio
n
s
.
GANs
-
b
ased
au
g
m
e
n
tatio
n
is
s
ee
n
as
a
p
r
io
r
ity
r
esear
ch
av
en
u
e
f
o
r
th
e
f
u
tu
r
e.
C
las
s
im
b
alan
ce
an
d
th
e
s
ca
r
ci
ty
o
f
an
n
o
tated
tr
ain
in
g
d
ata
a
r
e
a
co
n
s
tan
t c
h
allen
g
e
i
n
d
ee
p
lear
n
in
g
.
P
er
ez
et
a
l.
[
2
3
]
d
em
o
n
s
tr
ate
d
th
e
u
tili
ty
o
f
GAN
in
s
y
n
t
h
esizin
g
b
lo
o
d
s
m
ea
r
im
a
g
es
i
n
o
r
d
er
t
o
im
p
r
o
v
e
class
if
icatio
n
ac
cu
r
ac
y
f
o
r
a
n
em
ia
s
u
b
ty
p
es
th
at
ar
e
u
n
d
er
r
ep
r
esen
ted
.
T
h
er
e
ar
e
p
r
iv
ac
y
co
n
s
tr
ain
ts
th
at
h
in
d
er
cr
o
s
s
in
s
titu
tio
n
al
d
ata
s
h
ar
in
g
an
d
th
is
h
as
b
ee
n
m
itig
ated
b
y
f
e
d
er
ated
lear
n
in
g
(
FL)
.
R
esNet
-
5
0
/Den
s
eNe
t
f
r
am
ewo
r
k
f
o
r
d
is
tr
ib
u
ted
m
alar
ia
im
ag
e
d
et
ec
tio
n
ac
r
o
s
s
m
u
ltip
le
s
ites
was
im
p
lem
en
ted
b
y
Kar
ee
m
et
a
l.
[
2
4
]
.
I
t
ac
h
iev
e
d
9
0
%
ac
cu
r
ac
y
with
o
u
t
r
aw
d
ata
ex
ch
an
g
e
.
T
h
is
wo
r
k
h
ig
h
lig
h
ts
th
e
p
r
ac
tical
s
ca
lab
ilit
y
as
an
ex
ten
s
io
n
o
f
th
e
p
r
o
p
o
s
ed
m
u
ltimo
d
al
ar
c
h
i
tectu
r
e
f
o
r
f
ac
ilit
atio
n
ac
r
o
s
s
h
ea
lth
ca
r
e
n
etwo
r
k
s
in
th
e
r
eso
u
r
ce
-
lim
ited
en
d
e
m
ic
r
eg
io
n
s
.
Mo
r
eo
v
e
r
,
s
ca
lab
ilit
y
is
s
u
p
p
o
r
ted
f
u
r
th
er
b
y
th
e
f
i
n
d
in
g
s
o
f
R
am
o
s
-
B
r
iceñ
o
et
a
l.
[
2
5
]
wh
o
f
o
u
n
d
th
at
em
p
lo
y
in
g
d
i
f
f
er
en
tial
p
r
iv
ac
y
m
eth
o
d
s
with
in
FL
r
esu
lts
in
r
o
b
u
s
t
class
if
icatio
n
o
f
m
ed
ical
i
m
a
g
es
with
o
u
t
s
ac
r
if
icin
g
p
atien
t
co
n
f
id
e
n
tiality
an
in
s
ig
h
t
d
i
r
ec
tly
ap
p
licab
le
to
im
p
lem
en
tatio
n
ac
r
o
s
s
in
s
titu
t
io
n
s
f
o
r
th
e
p
r
o
p
o
s
ed
m
u
ltimo
d
al
f
r
a
m
ewo
r
k
in
m
ala
r
ia
-
en
d
em
ic
r
eg
io
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
Hem
a
to
lo
g
ica
l p
r
o
fili
n
g
o
f m
a
la
r
ia
-
in
d
u
ce
d
a
n
emia
u
s
in
g
d
e
ep
lea
r
n
in
g
(
V
a
n
r
o
s
e
P
a
n
a
s
h
e
N
ya
ma
n
g
o
d
o
)
307
3.
M
E
T
H
O
D
3
.
1
.
Da
t
a
s
et
d
escript
io
n
T
h
e
d
ataset
th
at
is
b
ein
g
u
s
ed
in
th
is
esteem
ed
r
esear
ch
co
n
tain
s
1
9
3
p
atien
ts
.
Data
s
et
was
s
o
u
r
ce
d
f
r
o
m
th
e
Natio
n
al
I
n
s
titu
tes
o
f
Hea
lth
(
NI
H
)
m
alar
ia
ce
ll
i
m
ag
e
r
ep
o
s
ito
r
y
,
wh
ich
co
n
tai
n
s
th
in
b
lo
o
d
s
m
ea
r
im
ag
es
f
r
o
m
clin
ical
co
llectio
n
s
.
T
h
e
lim
itatio
n
s
r
e
g
ar
d
in
g
th
e
u
s
e
o
f
th
e
NI
H
d
ataset,
o
n
wh
ich
th
is
s
tu
d
y
was
b
ased
,
s
h
o
u
ld
b
e
n
o
ted
as
well.
T
h
e
d
ata
in
th
e
NI
H
d
at
ab
ase
wer
e
in
itially
g
at
h
er
ed
f
o
r
m
alar
ia
-
e
n
d
em
ic
p
o
p
u
latio
n
s
in
So
u
t
h
ea
s
t
Asi
a
an
d
So
u
th
Am
e
r
ica
wh
e
r
e
b
o
t
h
Plas
m
o
d
iu
m
f
alcip
ar
u
m
an
d
Plas
m
o
d
iu
m
v
iv
ax
ar
e
en
d
em
ic.
T
h
e
u
s
e
o
f
th
e
NI
H
d
ataset
f
o
r
d
ev
elo
p
i
n
g
a
lg
o
r
ith
m
s
f
o
r
id
en
tif
y
in
g
p
ar
a
s
item
ia
in
Af
r
ican
p
o
p
u
latio
n
s
h
ig
h
l
y
en
d
em
ic
f
o
r
m
alar
ia
p
o
s
es
ce
r
tain
p
r
o
b
lem
s
as
th
e
r
e
ar
e
d
if
f
er
en
ce
s
in
s
tain
p
r
o
ce
d
u
r
es
an
d
p
ar
asit
e
s
tag
es
.
A
lth
o
u
g
h
it
is
r
elativ
ely
s
m
all
co
m
p
ar
ed
to
th
e
o
th
er
d
ee
p
lear
n
i
n
g
ex
p
er
im
en
ts
,
it
is
s
till
with
in
th
e
s
co
p
e
o
f
d
atasets
u
s
ed
f
o
r
s
im
ilar
s
tu
d
ies
o
n
s
p
ec
ial
im
ag
in
g
d
atab
ases
in
m
ed
icin
e
[
1
9
]
,
[
2
0
]
.
T
h
e
clin
ical
d
ata
co
m
p
r
is
ed
o
f
p
atien
t
d
em
o
g
r
a
p
h
ics
lik
e
wh
ite
b
lo
o
d
ce
ll
(
W
B
C
)
co
u
n
t
an
d
RBC
co
u
n
t.
I
n
o
r
d
er
to
av
o
id
o
v
er
f
itti
n
g
,
s
ev
er
al
m
eth
o
d
s
wer
e
im
p
lem
en
ted
:
ad
d
i
n
g
d
r
o
p
o
u
t
lay
er
s
with
a
d
r
o
p
-
o
u
t
o
f
0
.
5
a
f
ter
t
h
e
f
u
lly
c
o
n
n
ec
te
d
lay
er
s
,
u
s
in
g
d
ata
a
u
g
m
en
ta
tio
n
o
n
th
e
im
ag
es
p
ar
t
th
r
o
u
g
h
h
o
r
izo
n
tal
f
lip
,
r
o
tatio
n
s
,
an
d
ch
an
g
es
in
b
r
ig
h
tn
ess
,
an
d
im
p
lem
en
tin
g
e
ar
ly
s
to
p
p
in
g
ac
co
r
d
in
g
to
t
h
e
v
alid
atio
n
lo
s
s
.
A
7
0
%
-
1
5
%
-
1
5
%
s
p
lit
i
n
th
e
t
r
ain
,
v
alid
atio
n
,
an
d
test
d
atas
ets
was
co
n
d
u
cte
d
s
u
ch
th
at
n
o
n
e
o
f
th
e
p
atien
ts
’
d
ata
o
v
er
lap
b
etwe
en
th
e
s
p
lit
s
.
T
o
f
u
r
t
h
er
v
alid
ate
th
e
m
o
d
el
’
s
r
o
b
u
s
tn
ess
b
ey
o
n
d
a
s
in
g
le
t
r
ain
k
-
f
o
ld
cr
o
s
s
v
alid
atio
n
(
k
=5
)
h
ad
t
o
b
e
ap
p
lied
w
h
ile
tr
ain
in
g
.
Fiv
e
eq
u
al
f
o
ld
s
wer
e
p
ar
titi
o
n
e
d
am
o
n
g
th
e
1
9
3
p
atie
n
ts
to
p
r
ev
en
t
d
ata
leak
a
g
e.
T
h
is
en
s
u
r
ed
th
at
all
im
ag
es
b
elo
n
g
in
g
to
th
e
s
am
e
p
atien
t
wer
e
with
in
th
e
s
am
e
f
o
ld
.
T
ab
le
1
s
h
o
ws
th
at
th
e
1
9
3
p
atien
ts
wer
e
allo
ca
te
d
r
a
n
d
o
m
ly
ac
co
r
d
in
g
to
t
h
e
7
0
/1
5
/1
5
r
atio
.
T
h
is
m
ea
n
t
1
3
5
tr
a
in
in
g
p
atien
ts
(
6
7
5
im
ag
es),
2
9
v
alid
atio
n
p
atien
ts
(
1
4
5
im
ag
es)
,
an
d
2
9
test
p
atien
ts
(
1
4
5
im
a
g
es).
T
ab
le
1
.
Patien
t
-
s
tr
atif
ied
d
ata
s
et
p
ar
titi
o
n
in
g
f
o
r
tr
ain
in
g
,
v
a
lid
atio
n
,
an
d
in
d
ep
e
n
d
en
t te
s
ti
n
g
P
a
r
t
i
t
i
o
n
P
a
t
i
e
n
t
s (
n
)
I
mag
e
s (n
)
P
r
o
p
o
r
t
i
o
n
(
%)
Tr
a
i
n
i
n
g
1
3
5
6
7
5
70
V
a
l
i
d
a
t
i
o
n
29
1
4
5
15
Te
st
29
1
4
5
15
To
t
a
l
1
9
3
9
6
5
1
0
0
3
.
2
.
P
re
pro
ce
s
s
ing
p
ipelin
e
3
.
2
.
1
.
I
m
a
g
e
p
re
pro
ce
s
s
ing
T
h
e
r
aw
in
p
u
t
im
ag
es
wer
e
s
tan
d
ar
d
ized
t
o
1
2
8
x
1
2
8
r
e
s
o
lu
tio
n
in
o
r
d
er
t
o
s
atis
f
y
th
e
s
p
atial
r
eso
lu
tio
n
r
eq
u
ir
em
en
ts
o
f
th
e
co
n
v
o
l
u
tio
n
al
b
ac
k
b
o
n
e
wh
il
e
r
ed
u
cin
g
th
e
o
v
er
h
ea
d
.
T
o
m
itig
ate
o
v
er
f
itti
n
g
an
d
p
r
o
m
o
te
m
o
d
el
r
o
b
u
s
tn
ess
a
d
etailed
d
ata
au
g
m
e
n
tatio
n
s
u
ite
was
ap
p
lied
e
x
clu
s
iv
ely
to
th
e
tr
ain
in
g
d
ataset.
T
h
is
in
clu
d
ed
r
an
d
o
m
h
o
r
izo
n
tal
an
d
v
e
r
tical
f
li
p
p
in
g
(
p
=
0
.
5
)
,
b
o
u
n
d
ed
r
o
tatio
n
al
p
e
r
tu
r
b
atio
n
s
(
±
1
5
°),
c
o
lo
r
ad
j
u
s
tm
en
ts
af
f
ec
tin
g
b
r
ig
h
t
n
ess
(
±
2
0
%)
an
d
co
n
tr
ast
(
±
1
5
°),
an
d
a
d
d
iti
v
e
Gau
s
s
ian
n
o
is
e
(
σ
=0
.
0
1
)
.
T
h
ese
s
tr
ateg
ies
wer
e
s
elec
ted
b
ased
o
n
r
ec
o
m
m
en
d
atio
n
s
in
Fu
h
ad
et
a
l.
[
5
]
.
T
h
ey
s
im
u
lated
r
ea
lis
tic
in
ter
-
in
s
titu
tio
n
al
v
ar
iatio
n
in
a
s
tain
in
g
tech
n
iq
u
e
an
d
m
icr
o
s
co
p
e
illu
m
in
atio
n
.
All
p
ix
el
v
alu
es
wer
e
n
o
r
m
alis
ed
to
t
h
e
[
0
,
1
]
i
n
ter
v
al.
3
.
2
.
2
.
Clini
ca
l
m
et
a
da
t
a
pre
pro
ce
s
s
ing
Z
-
s
co
r
e
n
o
r
m
alis
atio
n
was
d
o
n
e
o
n
th
e
co
n
tin
u
o
u
s
f
ea
tu
r
es
to
en
s
u
r
e
s
tab
le
g
r
ad
ien
t
d
escen
t
co
n
v
er
g
en
ce
w
h
ile
p
r
e
v
en
ti
n
g
h
ig
h
m
ag
n
itu
d
e
f
ea
tu
r
es
f
r
o
m
d
o
m
in
atin
g
th
e
ML
P
lear
n
in
g
p
r
o
ce
s
s
.
C
ateg
o
r
ical
v
ar
iab
les
(
b
i
o
lo
g
i
ca
l
s
ex
,
s
y
m
p
to
m
class
if
icati
o
n
s
)
wer
e
e
n
co
d
e
d
u
s
in
g
o
n
e
-
h
o
t
r
e
p
r
esen
tatio
n
.
Miss
in
g
v
alu
es
p
r
esen
t
in
f
ew
er
th
an
3
%
o
f
r
ec
o
r
d
s
wer
e
im
p
u
ted
u
s
in
g
f
ea
tu
r
e
-
wis
e
m
ed
i
an
im
p
u
tatio
n
p
r
io
r
to
n
o
r
m
aliza
tio
n
.
3
.
3
.
M
o
del
a
rc
hite
ct
ure
Dee
p
lear
n
in
g
alg
o
r
ith
m
s
h
av
e
ad
v
an
ce
d
s
ig
n
if
ican
tly
i
n
te
r
m
s
o
f
th
eir
u
tili
ty
in
au
t
o
m
at
ic
an
aly
s
is
o
f
m
e
d
ical
im
ag
es,
with
C
NNs
n
o
w
r
eg
a
r
d
ed
as
th
e
f
u
n
d
am
en
tal
co
m
p
o
n
en
t
in
au
to
m
atin
g
d
ia
g
n
o
s
tic
p
r
o
ce
s
s
es
th
at
ar
e
in
v
o
lv
ed
in
f
ield
s
s
u
ch
as
o
n
co
lo
g
y
,
h
ae
m
ato
lo
g
y
,
an
d
in
f
ec
tio
n
d
i
ag
n
o
s
is
[
2
6
]
–
[
2
8
]
.
T
h
e
ab
ilit
y
o
f
C
NNs
to
au
to
m
atica
lly
d
er
iv
e
h
ie
r
ar
ch
al
f
e
atu
r
es
f
r
o
m
p
ix
el
im
ag
es,
wi
th
o
u
t
th
e
n
ee
d
f
o
r
m
an
u
al
f
ea
t
u
r
e
e
n
g
in
ee
r
in
g
,
i
s
o
n
e
o
f
t
h
e
ch
a
r
ac
ter
is
tics
th
at
m
ak
es
it
s
u
itab
le
f
o
r
th
e
task
o
f
d
iag
n
o
s
in
g
p
er
ip
h
er
al
b
lo
o
d
m
alar
ia
[
2
7
]
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
ar
ch
it
ec
tu
r
e
im
p
lem
en
ts
a
ca
s
ca
d
e
d
m
u
lti
-
task
n
e
u
r
al
n
etwo
r
k
co
m
p
r
is
in
g
two
p
ar
allel
en
co
d
in
g
b
r
a
n
ch
es
wh
o
s
e
f
ea
tu
r
e
r
ep
r
esen
tatio
n
s
ar
e
f
u
s
ed
p
r
io
r
t
o
a
p
r
im
ar
y
m
alar
ia
o
u
t
p
u
t,
wh
ich
is
th
en
ex
p
licitly
f
ed
in
to
th
e
d
ep
en
d
e
n
t
an
em
ia
b
r
an
c
h
as
an
ad
d
itio
n
al
co
n
d
itio
n
in
g
s
ig
n
al.
T
h
is
ca
s
ca
d
ed
d
esig
n
f
o
r
m
alis
es
th
e
b
io
lo
g
ical
ca
u
s
ality
b
etwe
en
p
ar
asit
em
ia
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
3
,
No
v
em
b
er
20
26
:
3
0
4
-
313
308
er
y
th
r
o
c
y
te
d
estru
ctio
n
:
th
e
C
NN
b
r
an
ch
ac
ce
p
ts
1
2
8
×
1
2
8
×
3
b
lo
o
d
s
m
ea
r
im
a
g
es
an
d
p
a
s
s
es
th
em
th
r
o
u
g
h
two
co
n
v
o
lu
t
io
n
al
b
lo
ck
s
(
3
2
f
ilter
s
,
th
en
6
4
f
ilter
s
,
ea
ch
3
×3
with
r
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
U
),
an
d
Ma
x
Po
o
l)
,
f
o
llo
we
d
b
y
a
Flat
ten
lay
er
an
d
a
De
n
s
e
-
6
4
p
r
o
jectio
n
y
ield
in
g
a
6
4
-
d
im
e
n
s
io
n
al
v
is
u
al
f
ea
tu
r
e
v
ec
to
r
.
T
h
e
ML
P
b
r
an
ch
en
c
o
d
es
th
r
ee
clin
ical
f
ea
tu
r
es
(
W
B
C
co
u
n
t,
in
f
ec
ted
R
B
C
c
o
u
n
t,
an
d
u
n
in
f
ec
ted
R
B
C
co
u
n
t)
th
r
o
u
g
h
two
d
en
s
e
lay
er
s
(
1
6
u
n
its
th
en
8
u
n
its
,
b
o
th
R
eL
U)
,
p
r
o
d
u
ci
n
g
an
8
-
d
im
en
s
io
n
al
clin
ical
f
ea
tu
r
e
v
ec
to
r
.
T
h
e
tw
o
v
ec
to
r
s
ar
e
c
o
n
ca
ten
ated
i
n
to
a
7
2
-
d
im
en
s
io
n
al
jo
i
n
t
r
ep
r
e
s
en
tatio
n
,
wh
ich
is
p
ass
ed
th
r
o
u
g
h
a
s
h
ar
ed
Den
s
e
-
6
4
lay
er
with
R
eL
U
ac
tiv
atio
n
an
d
Dr
o
p
o
u
t
(
0
.
3
)
b
ef
o
r
e
s
p
litt
in
g
in
to
th
e
p
r
im
ar
y
m
alar
ia
o
u
tp
u
t
h
ea
d
(
Den
s
e
1
,
s
ig
m
o
id
)
.
T
h
e
r
esu
ltin
g
m
alar
ia
p
r
o
b
ab
ilit
y
P(m
alar
ia)
is
th
en
co
n
ca
ten
ated
with
th
e
s
h
ar
e
d
r
ep
r
esen
tatio
n
to
f
o
r
m
a
6
5
-
d
im
e
n
s
io
n
al
ca
s
ca
d
e
in
p
u
t,
wh
ich
f
ee
d
s
th
e
d
ep
en
d
e
n
t
an
em
ia
b
r
a
n
ch
(
De
n
s
e
3
2
,
Den
s
e
1
,
s
ig
m
o
id
)
,
en
s
u
r
in
g
th
at
P(a
n
em
ia)
is
ex
p
li
citly
co
n
d
itio
n
ed
o
n
P(m
alar
ia)
.
T
h
e
o
v
er
all
a
r
ch
itectu
r
e
o
f
th
e
p
r
o
p
o
s
ed
ca
s
ca
d
ed
m
u
lti
-
task
d
ee
p
lear
n
i
n
g
f
r
am
ewo
r
k
is
illu
s
tr
ated
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
C
ascad
ed
m
u
lti
-
task
d
ee
p
lear
n
in
g
ar
c
h
itectu
r
e
f
o
r
co
n
cu
r
r
en
t m
alar
ia
a
n
d
m
alar
i
a
-
in
d
u
ce
d
an
ae
m
ia
class
if
icatio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
Hem
a
to
lo
g
ica
l p
r
o
fili
n
g
o
f m
a
la
r
ia
-
in
d
u
ce
d
a
n
emia
u
s
in
g
d
e
ep
lea
r
n
in
g
(
V
a
n
r
o
s
e
P
a
n
a
s
h
e
N
ya
ma
n
g
o
d
o
)
309
3
.
4
.
L
o
s
s
f
un
ct
io
n a
nd
o
ptim
iza
t
io
n
Hem
ato
lo
g
ical
p
r
o
f
ilin
g
o
f
MI
A
r
eq
u
ir
es
th
e
s
eq
u
en
tial
p
r
ed
ictio
n
o
f
t
wo
b
in
ar
y
co
n
d
iti
o
n
s
lin
k
ed
b
y
a
c
au
s
al
d
ep
e
n
d
en
c
y
.
Ma
l
ar
ia
is
p
r
ed
icted
f
ir
s
t
as
th
e
p
r
im
ar
y
task
;
its
s
ig
m
o
id
o
u
t
p
u
t
P(m
alar
ia)
is
th
en
co
n
ca
ten
ated
with
th
e
s
h
ar
ed
r
ep
r
esen
tatio
n
an
d
p
ass
ed
to
t
h
e
d
e
p
en
d
e
n
t
an
e
m
ia
b
r
an
ch
,
m
ak
in
g
th
e
a
n
em
ia
p
r
ed
ictio
n
e
x
p
licitly
co
n
d
itio
n
ed
o
n
p
a
r
asit
em
ia
s
tatu
s
.
B
o
th
o
u
t
p
u
t
n
o
d
es
ar
e
o
p
tim
iz
ed
u
s
in
g
t
h
e
b
in
a
r
y
cr
o
s
s
-
en
tr
o
p
y
(
B
C
E
)
lo
s
s
f
u
n
c
tio
n
,
ca
lcu
lated
in
d
ep
en
d
en
tly
f
o
r
ea
ch
lab
el
an
d
s
u
m
m
ed
:
=
−
1
[
∑
l
og
(
)
+
(
1
−
)
l
og
(
1
−
̂
)
]
̂
=
1
wh
er
e
y
ᵢ
is
th
e
g
r
o
u
n
d
tr
u
th
b
i
n
ar
y
lab
el
an
d
ŷ
ᵢ
is
th
e
m
o
d
el
’
s
p
r
ed
icted
p
r
o
b
ab
ilit
y
.
T
h
er
e
ar
e
s
ev
er
al
r
ea
s
o
n
s
wh
y
B
C
E
was
ch
o
s
en
in
s
tead
o
f
f
o
ca
l
lo
s
s
.
Fo
ca
l
lo
s
s
i
s
s
p
ec
if
ically
tailo
r
ed
to
war
d
s
h
an
d
lin
g
h
ig
h
l
y
im
b
alan
ce
d
class
es,
an
d
its
m
ain
id
ea
is
to
r
ed
u
ce
t
h
e
im
p
ac
t
o
f
co
r
r
ec
tly
class
if
ied
s
am
p
les f
r
o
m
th
e
m
ajo
r
ity
class
d
u
r
in
g
t
r
ain
in
g
.
Ho
wev
er
,
th
er
e
is
n
o
ex
tr
e
m
e
im
b
alan
ce
b
etwe
en
th
e
m
alar
ia
-
p
o
s
itiv
e
class
an
d
th
e
an
em
ia
-
p
o
s
itiv
e
class
in
th
is
d
ataset
(
as
co
n
f
ir
m
ed
wh
ile
s
tr
atif
y
in
g
th
e
d
ataset)
,
s
o
th
e
class
r
ewe
ig
h
tin
g
co
m
p
o
n
en
t
o
f
f
o
ca
l
l
o
s
s
is
less
u
s
ef
u
l.
Mo
r
e
o
v
er
,
B
C
E
p
r
esen
ts
a
s
im
p
ler
an
d
m
o
r
e
in
tu
itiv
e
g
r
ad
ien
t
lan
d
s
ca
p
e,
wh
ich
ca
n
b
e
v
er
y
b
en
ef
icial
s
in
ce
th
e
s
m
all
d
at
aset
o
f
1
9
3
p
atien
ts
d
o
es
n
o
t
t
o
ler
ate
an
in
cr
ea
s
e
in
th
e
s
en
s
itiv
ity
o
f
th
e
m
o
d
e
l
to
h
y
p
e
r
p
ar
am
eter
s
,
s
u
ch
as
th
e
g
am
m
a
p
ar
a
m
eter
f
o
r
f
o
ca
l
lo
s
s
.
T
h
e
Ad
a
m
o
p
tim
izer
was
u
tili
ze
d
f
o
r
its
ad
ap
tiv
e
lear
n
in
g
r
ate
p
r
o
p
e
r
ties
.
Sig
m
o
id
ac
tiv
atio
n
r
ath
er
th
an
s
o
f
tm
ax
is
ap
p
lied
to
ea
c
h
o
u
t
p
u
t
n
eu
r
o
n
i
n
d
ep
e
n
d
en
tly
,
p
er
m
i
ttin
g
co
-
o
cc
u
r
r
en
ce
o
f
p
o
s
itiv
e
p
r
ed
ictio
n
s
.
A
class
if
icatio
n
th
r
esh
o
ld
o
f
0
.
5
was
estab
lis
h
ed
;
p
r
o
b
a
b
ilit
ies>0
.
5
wer
e
class
if
ied
a
s
p
o
s
itiv
e
(
1
)
,
a
n
d
th
o
s
e<
0
.
5
as
n
eg
ativ
e
(
0
)
.
Mo
d
el
tr
ain
in
g
was
ca
r
r
ied
o
u
t
i
n
Py
th
o
n
3
.
1
0
u
s
in
g
T
e
n
s
o
r
Flo
w
2
.
1
3
/Ker
as
an
d
tr
ain
ed
o
n
VS Co
d
e
C
PU (
1
6
GB
R
AM
)
.
T
r
ain
in
g
was c
o
n
d
u
cted
f
o
r
u
p
t
o
1
0
0
ep
o
ch
s
with
an
ea
r
ly
s
to
p
p
in
g
ca
llb
ac
k
(
p
atien
ce
=1
5
ep
o
c
h
s
,
m
o
n
ito
r
e
d
o
n
v
alid
atio
n
lo
s
s
)
an
d
a
R
ed
u
ce
L
R
On
Plateau
s
ch
ed
u
ler
(
f
ac
to
r
=0
.
5
; p
atien
ce
=7
)
to
p
r
ev
en
t o
v
e
r
f
itti
n
g
an
d
o
p
tim
ize
co
n
v
er
g
en
ce
d
y
n
am
ics.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
4
.
1
.
Q
ua
ntit
a
t
iv
e
perf
o
rma
nce
m
et
rics
T
h
e
s
y
s
tem
ac
h
iev
e
d
a
9
6
.
1
%
r
ec
all
r
ate
f
o
r
m
alar
ia
d
et
ec
tio
n
.
Sp
ec
if
ically
in
r
elatio
n
to
MI
A
id
en
tific
atio
n
,
r
ec
all
is
th
e
k
ey
cr
iter
io
n
o
f
alg
o
r
ith
m
p
er
f
o
r
m
an
ce
i
n
th
e
m
alar
ia
d
etec
tio
n
m
o
d
u
le.
T
h
e
co
n
s
eq
u
en
ce
s
o
f
m
is
s
in
g
a
m
alar
ia
d
iag
n
o
s
is
g
o
b
ey
o
n
d
f
ailin
g
to
d
etec
t
th
e
d
is
ea
s
e
i
t
s
elf
,
s
in
ce
a
f
ailu
r
e
to
d
etec
t
m
alar
ia
m
ea
n
s
th
at
an
y
s
u
b
s
eq
u
e
n
t
an
em
ia
d
etec
tio
n
b
ec
o
m
es
am
b
ig
u
o
u
s
f
r
o
m
a
clin
ical
p
o
in
t
o
f
v
iew,
wh
er
e
o
n
e
ca
n
n
o
t
d
ete
r
m
in
e
wh
eth
er
th
e
an
em
ia
r
e
s
u
lts
f
r
o
m
r
ed
ce
ll
ly
s
is
ca
u
s
ed
b
y
Plas
m
o
d
i
u
m
.
T
h
u
s
,
it
is
ju
s
tifie
d
f
r
o
m
a
clin
ical
p
o
in
t
o
f
v
iew
to
d
esig
n
an
alg
o
r
ith
m
m
ax
im
izin
g
r
ec
a
ll
at
th
e
e
x
p
en
s
e
o
f
p
r
ec
is
io
n
(
9
4
.
8
%).
T
h
e
ar
ch
it
ec
tu
r
e
ac
h
iev
ed
a
n
an
em
ia
cl
ass
if
icatio
n
ac
cu
r
ac
y
o
f
9
3
.
2
%,
wh
ich
is
s
lig
h
tly
lo
wer
th
an
th
e
m
alar
ia
d
etec
tio
n
a
cc
u
r
ac
y
o
f
9
5
.
4
%.
T
h
is
p
e
r
f
o
r
m
a
n
ce
d
if
f
e
r
en
tial
is
clin
ically
ex
p
ec
ted
f
r
o
m
a
m
o
r
p
h
o
lo
g
ical
p
e
r
s
p
ec
tiv
e.
T
h
e
q
u
an
titativ
e
p
e
r
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
m
u
ltimo
d
al
c
lass
if
icatio
n
m
o
d
el
o
n
th
e
in
d
ep
en
d
en
t te
s
t set is s
u
m
m
ar
ized
in
T
ab
le
2
.
T
ab
le
2
.
Per
f
o
r
m
an
ce
m
etr
ics o
f
th
e
p
r
o
p
o
s
ed
m
u
ltimo
d
al
class
if
icatio
n
m
o
d
el
o
n
th
e
in
d
e
p
en
d
en
t te
s
t set
Ta
r
g
e
t
c
o
n
d
i
t
i
o
n
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
s
c
o
r
e
(
%)
M
a
l
a
r
i
a
9
5
.
4
9
4
.
8
9
6
.
1
9
5
.
4
A
n
e
m
i
a
9
3
.
2
9
2
.
5
9
3
.
8
9
3
.
1
M
a
c
r
o
-
a
v
e
r
a
g
e
9
4
.
3
9
3
.
6
9
4
.
9
9
4
.
2
Plas
m
o
d
iu
m
-
in
f
ec
ted
er
y
t
h
r
o
cy
tes
p
r
esen
t
d
is
tin
ct
in
tr
ac
e
llu
lar
s
tain
in
g
p
atter
n
s
th
at
ar
e
r
ea
d
ily
ca
p
tu
r
ed
b
y
th
e
im
ag
e
d
ata
b
r
an
ch
.
I
n
c
o
n
tr
ast,
th
e
RBC
m
o
r
p
h
o
lo
g
ical
ch
an
g
es
ass
o
ciate
d
with
an
em
ia
ar
e
co
m
p
ar
ativ
ely
s
u
b
tler
an
d
in
h
er
en
tly
m
o
r
e
v
a
r
iab
le,
m
a
k
in
g
th
em
h
a
r
d
er
to
d
is
tin
g
u
is
h
in
s
tan
d
ar
d
p
e
r
ip
h
er
al
b
lo
o
d
s
m
ea
r
im
ag
es.
T
o
d
eter
m
in
e
th
e
r
o
b
u
s
tn
ess
o
f
th
e
m
e
asu
r
es
cited
ab
o
v
e,
b
o
o
ts
tr
ap
co
n
f
id
en
ce
in
te
r
v
als
(
C
I
)
at
9
5
%
lev
el
wer
e
d
eter
m
in
ed
u
s
in
g
1
,
0
0
0
b
o
o
ts
tr
ap
r
esam
p
les
o
f
th
e
test
s
et.
CI
o
b
tain
ed
a
r
e
as:
m
alar
i
a
ac
cu
r
ac
y
is
9
5
.
4
%
(
C
I
9
3
.
1
%
-
9
7
.
6
%),
m
alar
ia
r
ec
all
is
9
6
.
1
%
(
C
I
9
4
.
0
%
-
9
8
.
1
%),
an
em
ia
ac
cu
r
ac
y
is
9
3
.
2
%
(
C
I
9
0
.
5
%
-
9
5
.
8
%),
an
d
m
ac
r
o
F1
-
s
co
r
e
is
9
4
.
2
%
(
C
I
9
1
.
8
%
-
9
6
.
5
%).
T
h
ese
in
ter
v
als
co
n
f
ir
m
th
at
th
e
r
ep
o
r
ted
p
er
f
o
r
m
an
ce
is
s
tatis
tically
s
tab
le
an
d
n
o
t
an
ar
ti
f
ac
t
o
f
a
f
av
o
r
ab
le
test
p
ar
tit
io
n
,
s
u
p
p
o
r
tin
g
th
e
r
eliab
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
f
r
a
m
ewo
r
k
ac
r
o
s
s
p
lau
s
ib
le
d
ata
v
ar
iatio
n
s
.
4
.
2
.
Co
m
pa
ra
t
iv
e
a
na
ly
s
is
T
o
co
n
te
x
tu
alize
p
r
o
p
o
s
ed
m
o
d
el
p
e
r
f
o
r
m
an
ce
,
T
ab
le
3
p
r
esen
ts
a
s
tr
u
ctu
r
ed
c
o
m
p
ar
is
o
n
with
clo
s
ely
r
elate
d
s
tate
-
of
-
th
e
-
ar
t
ap
p
r
o
ac
h
es
in
liter
atu
r
e,
s
elec
ted
b
ased
o
n
m
eth
o
d
o
l
o
g
i
ca
l
s
im
ilar
ity
an
d
r
ec
en
cy
(
2
0
2
2
–
2
0
2
5
)
.
As
ca
n
b
e
o
b
s
er
v
ed
f
r
o
m
T
ab
le
3
,
t
h
e
s
in
g
le
-
task
m
o
d
els
o
f
m
alar
ia
d
etec
tio
n
s
h
o
w
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
3
,
No
v
em
b
er
20
26
:
3
0
4
-
313
310
s
lig
h
tly
b
etter
p
er
f
o
r
m
an
ce
o
n
p
a
r
asit
e
id
en
tific
atio
n
o
n
ly
.
T
h
is
,
h
o
wev
er
,
ca
n
n
o
t
b
e
tak
en
as
a
f
air
co
m
p
ar
is
o
n
d
u
e
t
o
th
e
f
ac
t
th
a
t
th
e
s
in
g
le
-
task
m
o
d
el
is
n
o
t b
o
u
n
d
b
y
th
e
n
ee
d
f
o
r
class
if
icatio
n
in
ad
d
itio
n
to
th
e
task
a
n
d
h
en
ce
u
s
es
all
o
f
its
r
eso
u
r
ce
s
to
war
d
s
id
en
tify
in
g
p
ar
asi
tes
alo
n
e
.
O
n
th
e
o
th
e
r
h
an
d
,
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
s
o
lv
e
s
two
clin
ically
in
d
ep
en
d
en
t b
u
t c
au
s
ally
r
elate
d
p
r
o
b
lem
s
,
i
.
e.
,
p
ar
asit
em
ia
an
d
s
u
b
s
eq
u
en
t
d
ev
el
o
p
m
e
n
t
o
f
an
em
ia.
Fro
m
a
m
ed
ical
s
tan
d
p
o
i
n
t,
a
s
y
s
tem
ca
p
ab
le
o
f
d
etec
tin
g
b
o
th
p
ath
o
lo
g
ies in
o
n
e
g
o
will si
g
n
if
ican
tly
d
ec
r
ea
s
e
th
e
am
o
u
n
t
o
f
tim
e
s
p
en
t o
n
d
iag
n
o
s
tics
,
will sav
e
ef
f
o
r
ts
f
o
r
th
e
d
iag
n
o
s
is
o
f
s
ec
o
n
d
ar
y
p
at
h
o
lo
g
y
i
n
th
e
ca
s
e
o
f
p
o
s
itiv
e
m
alar
ia
d
iag
n
o
s
is
,
an
d
will
h
elp
clin
ician
s
o
b
tain
a
m
o
r
e
co
m
p
r
e
h
en
s
iv
e
u
n
d
e
r
s
tan
d
in
g
o
f
a
p
atien
t
’
s
h
ea
lth
co
n
d
itio
n
[
2
2
]
.
Su
ch
an
in
teg
r
ated
ap
p
r
o
ac
h
h
as
a
g
r
ea
t
ad
v
a
n
tag
e
esp
ec
ially
i
n
d
ev
elo
p
in
g
c
o
u
n
tr
ies
wh
er
e
th
er
e
ar
e
lim
itatio
n
s
with
r
e
g
ar
d
s
to
lab
o
r
ato
r
y
r
eso
u
r
ce
s
an
d
p
atien
t
f
o
llo
w
-
t
h
r
o
u
g
h
[
2
4
]
.
Hen
ce
,
th
e
9
4
.
3
%
m
ac
r
o
-
av
er
ag
e
ac
cu
r
ac
y
o
b
tain
ed
th
r
o
u
g
h
th
is
s
y
s
tem
ca
n
b
e
co
n
s
id
er
e
d
s
u
p
er
io
r
to
ex
is
tin
g
m
eth
o
d
s
wh
i
ch
p
er
f
o
r
m
th
eir
an
aly
s
is
u
s
in
g
a
s
m
aller
s
co
p
e
o
f
d
iag
n
o
s
is
.
T
h
is
o
b
s
er
v
atio
n
is
co
n
s
is
ten
t
with
r
ec
en
t
r
ev
iew
f
in
d
in
g
s
th
at
d
ee
p
lea
r
n
in
g
h
as
b
ec
o
m
e
in
cr
ea
s
in
g
ly
ef
f
ec
tiv
e
in
m
e
d
i
ca
l i
m
ag
e
an
aly
s
is
b
y
en
ab
lin
g
ac
cu
r
ate
an
d
r
eliab
le
d
iag
n
o
s
tic
d
ec
is
io
n
s
u
p
p
o
r
t
ac
r
o
s
s
v
ar
io
u
s
clin
ical
ap
p
lica
tio
n
s
[
2
9
]
.
T
ab
le
3
.
C
o
m
p
a
r
is
o
n
s
u
m
m
ar
y
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
ag
ai
n
s
t r
elate
d
d
ee
p
lear
n
i
n
g
ap
p
r
o
a
ch
es f
o
r
m
alar
ia
an
d
an
em
ia
d
iag
n
o
s
is
S
t
u
d
y
M
e
t
h
o
d
Ta
sk
B
e
st
a
c
c
u
r
a
c
y
(
%)
M
o
d
a
l
i
t
y
S
i
l
k
a
e
t
a
l
.
[
1
4
]
C
u
s
t
o
m C
N
N
M
a
l
a
r
i
a
9
9
.
6
8
I
mag
e
R
a
m
o
s
-
B
r
i
c
e
ñ
o
e
t
a
l
.
[
2
5
]
S
p
e
c
i
e
s
-
I
D
C
N
N
M
a
l
a
r
i
a
9
7
.
1
I
mag
e
R
a
mz
a
n
e
t
a
l
.
[
1
9
]
R
e
si
d
u
a
l
c
o
n
v
o
l
u
t
i
o
n
a
l
b
l
o
c
k
a
t
t
e
n
t
i
o
n
m
o
d
u
l
e
(
R
C
B
A
M
)
+
r
a
n
d
o
m
f
o
r
e
st
(
R
F
)
f
u
s
i
o
n
A
n
e
m
i
a
9
5
.
0
M
u
l
t
i
m
o
d
a
l
R
a
mz
a
n
e
t
a
l
.
[
2
0
]
I
n
t
e
g
r
a
t
i
v
e
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
(
ML
)
+
a
t
t
e
n
t
i
o
n
A
n
e
m
i
a
9
4
.
3
Ta
b
u
l
a
r
K
a
r
e
e
m
e
t
a
l
.
[
2
4
]
F
e
d
e
r
a
t
e
d
R
e
sN
e
t
-
50
M
a
l
a
r
i
a
9
0
.
0
I
mag
e
(
F
L)
P
r
o
p
o
se
d
m
o
d
e
l
C
N
N
+
M
LP
f
u
s
i
o
n
M
I
A
(
m
u
l
t
i
-
l
a
b
e
l
)
9
4
.
3
M
u
l
t
i
m
o
d
a
l
4
.
3
.
Dis
cus
s
io
n
T
h
e
m
alar
ia
d
etec
tio
n
b
r
an
ch
r
ec
o
r
d
ed
a
r
ec
all
o
f
9
6
.
1
%
wh
ich
s
ee
m
ed
to
b
e
a
r
esu
lt
th
at
ca
r
r
ies
co
n
s
id
er
ab
le
clin
ical
weig
h
t.
I
n
r
eso
u
r
ce
lim
ited
en
v
ir
o
n
m
e
n
ts
,
a
f
alse
n
eg
ativ
e
o
u
tco
m
e
wh
er
eb
y
an
in
f
ec
ted
p
atien
t
is
in
co
r
r
ec
tly
clea
r
ed
r
is
k
s
d
elay
ed
tr
ea
tm
en
t
a
n
d
p
o
ten
tial
f
atality
.
Desig
n
in
g
th
e
s
y
s
tem
to
p
r
io
r
itize
r
ec
all
o
v
er
p
r
ec
is
io
n
in
th
is
b
r
an
ch
th
e
r
ef
o
r
e
r
ef
lects
a
clin
ically
d
ef
en
s
ib
le
d
ec
is
io
n
t
h
at
alig
n
s
with
th
e
p
u
b
lic
h
ea
lth
g
u
id
elin
es.
C
o
m
p
ar
in
g
m
o
d
est
p
e
r
f
o
r
m
an
ce
o
f
th
e
an
em
ia
b
r
an
c
h
r
elativ
e
to
m
alar
ia
s
h
o
ws
co
n
s
is
ten
t
f
in
d
in
g
s
r
ep
o
r
ted
t
h
e
b
r
o
ad
er
o
f
h
e
m
ato
lo
g
ical
im
ag
in
g
liter
atu
r
e.
T
h
e
m
o
r
p
h
o
lo
g
ical
m
ar
k
er
s
ass
o
ciate
d
with
an
em
ia
ar
e
in
h
er
en
tly
m
o
r
e
d
if
f
icu
lt
to
d
is
tin
g
u
is
h
in
b
lo
o
d
s
m
e
ar
im
ag
es
th
an
th
e
in
tr
ac
ellu
lar
s
tain
i
n
g
p
atter
n
s
m
ar
k
p
lasmo
d
iu
m
in
f
ec
ted
e
r
y
th
r
o
c
y
tes.
T
h
e
m
u
ltimo
d
al
d
esig
n
m
ir
r
o
r
s
th
e
wo
r
k
f
lo
w
o
f
a
n
ex
p
e
r
t
clin
ical
tech
n
ician
wh
o
in
teg
r
ates
v
i
s
u
al
m
icr
o
s
co
p
ic
f
in
d
in
g
s
with
lab
o
r
ato
r
y
r
esu
lts
an
d
p
atien
t
h
is
to
r
y
.
I
n
th
is
s
tu
d
y
with
o
n
ly
1
9
3
p
atien
ts
,
th
e
d
ataset
is
r
elativ
ely
s
m
all.
Al
th
o
u
g
h
we
ap
p
lied
s
tr
ict
s
tr
atif
icat
io
n
an
d
d
ata
au
g
m
en
tatio
n
to
r
e
d
u
ce
im
p
ac
t,
th
e
m
o
d
els
’
p
er
f
o
r
m
a
n
ce
m
ay
n
o
t
h
o
ld
u
p
ac
r
o
s
s
v
ar
ied
p
a
r
asit
e
s
tag
es,
p
o
p
u
lat
io
n
s
o
r
la
b
p
r
o
to
co
ls
.
I
n
f
u
tu
r
e
wo
r
k
,
th
e
m
o
s
t
im
p
o
r
tan
t
c
o
n
s
id
er
atio
n
w
o
u
ld
b
e
ac
q
u
ir
i
n
g
a
la
r
g
er
d
ata
s
et
f
o
r
b
etter
m
o
d
el
g
en
er
a
lis
atio
n
an
d
r
o
b
u
s
tn
ess
in
th
e
clin
ical
s
ettin
g
.
I
n
p
ar
ticu
lar
,
co
llectin
g
d
ata
f
r
o
m
m
u
ltip
le
s
ites
with
in
m
al
ar
ia
en
d
em
ic
r
e
g
io
n
s
,
esp
ec
ia
lly
in
Su
b
-
Sah
ar
a
n
Af
r
ica,
wo
u
ld
en
a
b
le
th
e
cr
ea
t
i
o
n
o
f
a
lar
g
e
r
,
m
o
r
e
r
ep
r
esen
tativ
e
d
ata
s
et
r
ef
lectin
g
b
o
th
th
e
wid
e
v
ar
iety
o
f
m
o
r
p
h
o
lo
g
ies
o
f
th
e
Plas
m
o
d
iu
m
in
f
ec
tio
n
life
cy
cle
,
wh
ic
h
co
u
ld
also
f
ac
ilit
ate
f
u
tu
r
e
FL
f
r
am
ewo
r
k
s
f
o
r
co
llab
o
r
ativ
e
m
e
d
ical
im
ag
e
a
n
aly
s
is
wh
ile
p
r
eser
v
in
g
d
ata
p
r
iv
ac
y
[
3
0]
.
Fo
r
d
ep
lo
y
m
en
t
with
in
I
C
T
s
y
s
tem
s
,
th
e
s
u
g
g
ested
m
o
d
el
wo
u
ld
b
e
f
ea
s
ib
le
f
o
r
POC
ap
p
licatio
n
s
with
in
a
m
o
b
ile
h
ea
lth
(
MI
A
Hea
lth
)
ap
p
licatio
n
.
T
h
e
in
p
u
t
clin
ical
d
ata
p
r
o
ce
s
s
ed
b
y
t
h
e
ML
P
b
r
an
ch
wo
u
ld
b
e
s
tan
d
ar
d
is
ed
an
d
c
o
llected
in
an
E
HR
,
wh
ich
co
u
ld
th
e
n
b
e
r
elay
ed
t
h
r
o
u
g
h
m
o
b
ile
n
etwo
r
k
s
at
lo
wer
b
an
d
wid
th
s
.
T
h
e
i
n
p
u
t
im
ag
e
s
f
ed
in
to
th
e
C
NN
b
r
an
ch
c
o
u
ld
co
n
s
is
t
o
f
b
lo
o
d
s
m
ea
r
p
ictu
r
es
tak
en
u
s
in
g
s
m
ar
tp
h
o
n
e
c
o
m
p
atib
le
attac
h
m
en
ts
to
d
ig
ital
m
icr
o
s
co
p
es
alr
ea
d
y
in
p
lace
in
s
o
m
e
m
alar
ia
en
d
em
ic
co
u
n
t
r
ies.
Dep
lo
y
m
en
t
o
f
th
e
m
o
d
el
u
s
in
g
cl
o
u
d
-
b
ased
i
n
f
er
en
ce
wo
u
ld
en
ab
le
th
e
m
o
d
el
to
b
e
h
o
s
ted
ce
n
tr
ally
an
d
h
av
e
a
d
ia
g
n
o
s
ti
c
s
er
v
ice
ex
p
o
s
ed
v
ia
a
n
ac
ce
s
s
ib
le
ap
p
licatio
n
p
r
o
g
r
am
m
i
n
g
in
ter
f
ac
e
(
API
)
,
allo
win
g
f
ac
ilit
ies with
o
u
t G
PU c
ap
ab
ilit
ies to
ac
ce
s
s
th
e
m
o
d
el.
5.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
d
em
o
n
s
tr
ates
th
at
m
alar
ia
p
ar
asit
em
ia
an
d
MI
A
ca
n
b
e
d
etec
ted
s
im
u
ltan
e
o
u
s
ly
an
d
ac
cu
r
ately
with
in
a
s
in
g
le,
co
m
p
u
tatio
n
ally
lig
h
tweig
h
t d
ee
p
lear
n
in
g
f
r
am
ewo
r
k
.
Ach
iev
in
g
a
m
ac
r
o
-
a
v
er
ag
e
F1
-
s
co
r
e
o
f
9
4
.
2
%
an
d
a
m
ala
r
ia
r
ec
all
o
f
9
6
.
1
%
o
n
an
in
d
e
p
en
d
en
t
test
s
et,
th
e
p
r
o
p
o
s
ed
C
NN
-
ML
P
f
u
s
io
n
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
Hem
a
to
lo
g
ica
l p
r
o
fili
n
g
o
f m
a
la
r
ia
-
in
d
u
ce
d
a
n
emia
u
s
in
g
d
e
ep
lea
r
n
in
g
(
V
a
n
r
o
s
e
P
a
n
a
s
h
e
N
ya
ma
n
g
o
d
o
)
311
m
o
d
el
clo
s
es
a
cr
itical
d
iag
n
o
s
tic
g
ap
in
r
eso
u
r
ce
-
co
n
s
tr
ain
ed
en
d
e
m
ic
s
ettin
g
s
:
th
e
n
ee
d
f
o
r
c
o
n
cu
r
r
en
t
,
o
b
jectiv
e
ass
ess
m
en
t
o
f
b
o
th
a
ca
u
s
ativ
e
in
f
ec
tio
n
an
d
its
p
r
im
ar
y
h
em
ato
l
o
g
ical
co
n
s
eq
u
en
ce
f
r
o
m
a
s
in
g
le
b
lo
o
d
s
p
ec
im
en
a
n
d
co
n
s
u
ltatio
n
.
B
y
en
co
d
i
n
g
th
e
ca
u
s
al
d
ep
en
d
en
c
y
b
etwe
en
p
a
r
asit
em
ia
an
d
er
y
th
r
o
cy
te
d
estru
ctio
n
d
ir
ec
tly
i
n
to
t
h
e
a
r
ch
itectu
r
e
r
at
h
er
t
h
an
tr
ea
tin
g
th
e
two
c
o
n
d
itio
n
s
as
in
d
ep
en
d
en
t
class
if
icatio
n
tar
g
ets
th
e
s
y
s
tem
p
r
o
d
u
ce
s
c
lin
ically
co
h
er
e
n
t
p
r
o
b
a
b
ilis
ti
c
o
u
tp
u
ts
th
at
m
ir
r
o
r
th
e
r
ea
s
o
n
in
g
o
f
an
ex
p
e
r
t
h
ae
m
ato
lo
g
is
t.
T
h
is
d
esig
n
p
r
i
n
cip
le
r
e
p
r
esen
ts
th
e
c
o
r
e
s
cien
tific
co
n
tr
i
b
u
tio
n
o
f
th
e
wo
r
k
an
d
d
is
tin
g
u
is
h
es
it f
r
o
m
p
r
io
r
m
u
ltimo
d
al
an
d
s
in
g
le
-
task
ap
p
r
o
ac
h
es in
th
e
liter
atu
r
e.
T
h
e
b
r
o
ad
er
im
p
ac
t
o
f
th
is
wo
r
k
lies
in
its
p
o
ten
tial
to
r
ed
u
c
e
d
iag
n
o
s
tic
d
elay
s
an
d
f
r
ag
m
en
tatio
n
in
m
alar
ia
-
en
d
em
ic
r
eg
io
n
s
o
f
S
u
b
-
Sah
ar
an
Af
r
ica,
w
h
er
e
co
-
o
cc
u
r
r
in
g
an
em
ia
s
ig
n
if
ican
tl
y
elev
ates
m
o
r
tality
r
is
k
in
ch
ild
r
en
u
n
d
er
f
iv
e
an
d
p
r
eg
n
an
t
wo
m
e
n
.
A
s
y
s
tem
ca
p
ab
le
o
f
p
r
o
d
u
ci
n
g
d
u
al
d
ia
g
n
o
s
tic
o
u
tp
u
ts
f
r
om
a
s
in
g
le
b
lo
o
d
s
m
ea
r
im
ag
e
an
d
th
r
ee
r
o
u
tin
e
h
ae
m
ato
l
o
g
ical
p
ar
am
eter
s
is
d
ir
ec
tly
co
m
p
atib
le
with
POC
d
ep
lo
y
m
e
n
t
v
ia
s
m
ar
tp
h
o
n
e
-
c
o
m
p
atib
le
m
icr
o
s
co
p
e
attac
h
m
en
ts
an
d
lo
w
-
b
a
n
d
wid
th
m
o
b
ile
h
ea
lth
p
latf
o
r
m
s
.
T
h
e
r
esear
ch
team
’
s
im
m
ed
i
ate
n
ex
t
s
tep
s
ar
e
as
:
f
ir
s
t
,
a
p
r
o
s
p
ec
tiv
e
m
u
lti
-
s
ite
d
ata
c
o
llectio
n
ca
m
p
aig
n
tar
g
etin
g
at
least
f
iv
e
clin
ic
al
f
ac
ilit
ies
ac
r
o
s
s
Z
im
b
ab
w
e
an
d
n
eig
h
b
o
u
r
in
g
en
d
e
m
ic
co
u
n
t
r
ies
will
b
e
co
n
d
u
cte
d
to
ass
em
b
le
a
d
ataset
o
f
n
o
f
ewe
r
th
a
n
1
,
0
0
0
p
a
tien
ts
,
s
p
an
n
in
g
th
e
f
u
ll
Plas
m
o
d
iu
m
f
alcip
a
r
u
m
in
f
ec
tio
n
life
cy
cle
an
d
en
c
o
m
p
ass
in
g
d
iv
er
s
e
s
tain
in
g
p
r
o
to
co
ls
an
d
m
icr
o
s
co
p
e
t
y
p
es.
Seco
n
d
,
th
e
au
g
m
en
tatio
n
p
ip
elin
e
will
b
e
ex
ten
d
e
d
to
i
n
co
r
p
o
r
ate
C
o
n
d
itio
n
al
GAN
-
b
ased
s
y
n
th
esis
o
f
u
n
d
er
-
r
ep
r
esen
ted
p
ar
asit
e
s
tag
es
an
d
an
em
ia
s
ev
er
ities
,
ad
d
r
ess
in
g
m
o
r
p
h
o
lo
g
ical
class
im
b
alan
ce
with
o
u
t
in
tr
o
d
u
cin
g
n
o
n
-
b
i
o
lo
g
ical
a
r
tef
ac
ts
.
T
h
ir
d
,
th
e
ar
c
h
itectu
r
e
will
b
e
ad
ap
ted
f
o
r
FL
d
ep
lo
y
m
e
n
t
u
s
in
g
a
d
if
f
er
e
n
tial
-
p
r
iv
ac
y
f
r
a
m
ewo
r
k
,
e
n
ab
lin
g
cr
o
s
s
-
in
s
titu
tio
n
al
m
o
d
el
tr
ain
in
g
with
o
u
t
r
aw
d
ata
ex
c
h
an
g
e
a
p
r
er
e
q
u
is
ite
f
o
r
eth
ical
m
u
l
ti
-
co
u
n
tr
y
co
llab
o
r
atio
n
.
Fo
u
r
th
,
an
ex
ter
n
al
clin
ical
v
alid
a
tio
n
s
tu
d
y
will
b
e
d
esig
n
ed
in
p
ar
tn
er
s
h
ip
with
t
h
e
Min
is
tr
y
o
f
Hea
lth
to
ass
es
s
th
e
m
o
d
el
’
s
r
ea
l
-
wo
r
l
d
d
iag
n
o
s
tic
p
er
f
o
r
m
an
c
e
an
d
clin
ician
ac
ce
p
tan
ce
u
n
d
e
r
f
ield
co
n
d
iti
o
n
s
,
p
r
io
r
to
i
n
teg
r
atio
n
in
to
a
n
e
x
is
tin
g
lab
o
r
ato
r
y
in
f
o
r
m
atio
n
s
y
s
tem
an
d
th
e
p
r
o
p
o
s
ed
M
I
AHe
alth
m
o
b
ile
ap
p
licatio
n
.
ACK
NO
WL
E
DG
M
E
N
T
S
W
e
wo
u
ld
lik
e
to
ex
p
r
ess
o
u
r
s
in
ce
r
e
g
r
atitu
d
e
to
o
u
r
s
u
p
er
v
is
o
r
s
f
o
r
th
eir
in
v
alu
a
b
le
g
u
i
d
an
ce
a
n
d
ad
v
ice.
W
e
also
e
x
ten
d
o
u
r
s
in
ce
r
e
ap
p
r
ec
iatio
n
to
o
u
r
p
ar
en
ts
C
asp
er
an
d
Patien
ce
Ny
am
an
g
o
d
o
f
o
r
th
eir
co
n
s
tan
t
s
u
p
p
o
r
t
a
n
d
t
o
o
u
r
f
r
i
en
d
,
R
u
k
u
d
zo
Sam
u
el
M
p
ala,
f
o
r
h
is
co
n
tin
u
ed
e
n
co
u
r
ag
em
en
t
th
r
o
u
g
h
o
u
t
t
h
is
r
esear
ch
.
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
Th
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
t
r
ib
u
to
r
R
o
les
T
a
x
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
i
d
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
Van
r
o
s
e
Pan
ash
e
Ny
am
an
g
o
d
o
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
W
ellin
g
to
n
Ma
k
o
n
d
o
✓
✓
✓
✓
Simb
ai
Z
in
d
o
v
e
✓
✓
✓
✓
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
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
3
,
No
v
em
b
er
20
26
:
3
0
4
-
313
312
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
i
n
g
s
o
f
th
is
s
tu
d
y
ar
e
av
ailab
le
f
r
o
m
th
e
NI
H
lib
r
ar
y
a
n
d
ar
e
ac
ce
s
s
ib
le
to
q
u
alif
ied
r
esear
ch
er
s
u
p
o
n
r
eq
u
est f
r
o
m
t
h
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
.
RE
F
E
R
E
NC
E
S
[
1
]
W
o
r
l
d
H
e
a
l
t
h
O
r
g
a
n
i
z
a
t
i
o
n
,
“
W
o
r
l
d
mal
a
r
i
a
r
e
p
o
r
t
2
0
2
4
:
a
d
d
r
e
ssi
n
g
i
n
e
q
u
i
t
y
i
n
t
h
e
g
l
o
b
a
l
ma
l
a
r
i
a
r
e
s
p
o
n
se
,
”
G
e
n
e
v
a
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
w
w
w
.
w
h
o
.
i
n
t
/
p
u
b
l
i
c
a
t
i
o
n
s/
i
/
i
t
e
m
/
9
7
8
9
2
4
0
1
0
4
4
4
0
[
2
]
T.
G
i
l
,
C
.
I
.
M
o
o
n
,
S
.
Le
e
,
a
n
d
O
.
L
e
e
,
“
A
u
t
o
ma
t
i
c
a
n
a
l
y
si
s
s
y
s
t
e
m
f
o
r
a
b
n
o
r
ma
l
r
e
d
b
l
o
o
d
c
e
l
l
s
i
n
p
e
r
i
p
h
e
r
a
l
b
l
o
o
d
sme
a
r
s,”
Mi
c
r
o
s
c
o
p
y
Re
s
e
a
r
c
h
a
n
d
T
e
c
h
n
i
q
u
e
,
v
o
l
.
8
5
,
n
o
.
1
1
,
p
p
.
3
6
2
3
–
3
6
3
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
2
/
j
e
mt
.
2
4
2
1
5
.
[
3
]
J.
R
.
T
e
o
h
,
J.
D
o
n
g
,
X
.
Z
u
o
,
K
.
W
.
L
a
i
,
K
.
H
a
si
k
i
n
,
a
n
d
X
.
W
u
,
“
A
d
v
a
n
c
i
n
g
h
e
a
l
t
h
c
a
r
e
t
h
r
o
u
g
h
mu
l
t
i
mo
d
a
l
d
a
t
a
f
u
si
o
n
:
a
c
o
m
p
r
e
h
e
n
si
v
e
r
e
v
i
e
w
o
f
t
e
c
h
n
i
q
u
e
s
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s,”
Pe
e
rJ
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
0
,
p
.
e
2
2
9
8
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
7
7
1
7
/
p
e
e
r
j
-
c
s
.
2
2
9
8
.
[
4
]
S
.
R
a
j
a
r
a
ma
n
e
t
a
l
.
,
“
P
r
e
-
t
r
a
i
n
e
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
a
s
f
e
a
t
u
r
e
e
x
t
r
a
c
t
o
r
s
t
o
w
a
r
d
i
mp
r
o
v
e
d
ma
l
a
r
i
a
p
a
r
a
s
i
t
e
d
e
t
e
c
t
i
o
n
i
n
t
h
i
n
b
l
o
o
d
sme
a
r
i
m
a
g
e
s,
”
P
e
e
rJ
,
v
o
l
.
6
,
p
.
e
4
5
6
8
,
A
p
r
.
2
0
1
8
,
d
o
i
:
1
0
.
7
7
1
7
/
p
e
e
r
j
.
4
5
6
8
.
[
5
]
K
.
M
.
F
.
F
u
h
a
d
,
J.
F
.
Tu
b
a
,
M
.
R
.
A
.
S
a
r
k
e
r
,
S
.
M
o
me
n
,
N
.
M
o
h
a
mm
e
d
,
a
n
d
T
.
R
a
h
ma
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
b
a
se
d
a
u
t
o
ma
t
i
c
m
a
l
a
r
i
a
p
a
r
a
s
i
t
e
d
e
t
e
c
t
i
o
n
f
r
o
m
b
l
o
o
d
sm
e
a
r
a
n
d
i
t
s
smar
t
p
h
o
n
e
b
a
se
d
a
p
p
l
i
c
a
t
i
o
n
,”
D
i
a
g
n
o
s
t
i
c
s
,
v
o
l
.
1
0
,
n
o
.
5
,
p
.
3
2
9
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
d
i
a
g
n
o
st
i
c
s
1
0
0
5
0
3
2
9
.
[
6
]
T
.
L
o
n
e
,
A
.
A
l
d
a
y
,
a
n
d
R
.
Z
a
k
e
r
z
a
d
e
h
,
“
N
u
meri
c
a
l
a
n
a
l
y
si
s
o
f
st
e
n
o
ses
se
v
e
r
i
t
y
a
n
d
a
o
r
t
i
c
w
a
l
l
mec
h
a
n
i
c
s
i
n
p
a
t
i
e
n
t
s
w
i
t
h
s
u
p
r
a
v
a
l
v
u
l
a
r
a
o
r
t
i
c
st
e
n
o
s
i
s,”
C
o
m
p
u
t
e
rs
i
n
B
i
o
l
o
g
y
a
n
d
Me
d
i
c
i
n
e
,
v
o
l
.
1
3
5
,
p
.
1
0
4
5
7
3
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
b
i
o
me
d
.
2
0
2
1
.
1
0
4
5
7
3
.
[
7
]
Y
.
M
.
K
a
ss
i
m
e
t
a
l
.
,
“
C
l
u
s
t
e
r
i
n
g
-
b
a
s
e
d
d
u
a
l
d
e
e
p
l
e
a
r
n
i
n
g
a
r
c
h
i
t
e
c
t
u
r
e
f
o
r
d
e
t
e
c
t
i
n
g
r
e
d
b
l
o
o
d
c
e
l
l
s i
n
ma
l
a
r
i
a
d
i
a
g
n
o
s
t
i
c
sm
e
a
r
s,
”
I
EEE
J
o
u
rn
a
l
o
f
Bi
o
m
e
d
i
c
a
l
a
n
d
H
e
a
l
t
h
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
2
5
,
n
o
.
5
,
p
p
.
1
7
3
5
–
1
7
4
6
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
JB
H
I
.
2
0
2
0
.
3
0
3
4
8
6
3
.
[
8
]
A
.
A
c
e
v
e
d
o
,
A
.
M
e
r
i
n
o
,
S
.
A
l
f
é
r
e
z
,
Á
.
M
o
l
i
n
a
,
L.
B
o
l
d
ú
,
a
n
d
J.
R
o
d
e
l
l
a
r
,
“
A
d
a
t
a
s
e
t
o
f
mi
c
r
o
s
c
o
p
i
c
p
e
r
i
p
h
e
r
a
l
b
l
o
o
d
c
e
l
l
i
ma
g
e
s
f
o
r
d
e
v
e
l
o
p
me
n
t
o
f
a
u
t
o
ma
t
i
c
r
e
c
o
g
n
i
t
i
o
n
sy
s
t
e
ms
,
”
D
a
t
a
i
n
Br
i
e
f
,
v
o
l
.
3
0
,
p.
1
0
5
4
7
4
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
i
b
.
2
0
2
0
.
1
0
5
4
7
4
.
[
9
]
D
.
B
i
b
i
n
,
M
.
S
.
N
a
i
r
,
a
n
d
P
.
P
u
n
i
t
h
a
,
“
M
a
l
a
r
i
a
p
a
r
a
si
t
e
d
e
t
e
c
t
i
o
n
f
r
o
m p
e
r
i
p
h
e
r
a
l
b
l
o
o
d
s
mea
r
i
ma
g
e
s u
si
n
g
d
e
e
p
b
e
l
i
e
f
n
e
t
w
o
r
k
s,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
5
,
p
p
.
9
0
9
9
–
9
1
0
8
,
2
0
1
7
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
7
.
2
7
0
5
6
4
2
.
[
1
0
]
N
.
K
.
R
a
j
a
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
d
r
i
v
e
n
sc
a
l
a
b
l
e
a
n
d
h
i
g
h
-
p
r
e
c
i
s
i
o
n
mal
a
r
i
a
d
e
t
e
c
t
i
o
n
f
r
o
m
m
i
c
r
o
sc
o
p
i
c
b
l
o
o
d
sme
a
r
i
ma
g
e
s
,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
6
,
n
o
.
8
,
p
p
.
6
8
5
–
6
9
7
,
2
0
2
5
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
2
5
.
0
1
6
0
8
6
8
.
[
1
1
]
T.
Jam
e
e
l
a
,
K
.
A
t
h
o
t
a
,
N
.
S
i
n
g
h
,
V
.
K
.
G
u
n
j
a
n
,
a
n
d
S
.
K
a
h
a
l
i
,
“
D
e
e
p
l
e
a
r
n
i
n
g
a
n
d
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
f
o
r
ma
l
a
r
i
a
d
e
t
e
c
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
,
v
o
l
.
2
0
2
2
,
n
o
.
1
,
p
p
.
1
–
1
4
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
2
2
2
1
7
2
8
.
[
1
2
]
A
.
M
a
q
s
o
o
d
,
M
.
S
.
F
a
r
i
d
,
M
.
H
.
K
h
a
n
,
a
n
d
M
.
G
r
z
e
g
o
r
z
e
k
,
“
D
e
e
p
mal
a
r
i
a
p
a
r
a
s
i
t
e
d
e
t
e
c
t
i
o
n
i
n
t
h
i
n
b
l
o
o
d
s
mea
r
m
i
c
r
o
sc
o
p
i
c
i
ma
g
e
s,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
1
,
n
o
.
5
,
p
.
2
2
8
4
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
1
0
5
2
2
8
4
.
[
1
3
]
A
.
A
.
La
g
h
a
r
i
,
W
.
M
u
h
a
mm
a
d
,
M
.
L.
M
e
mo
n
,
A
.
H
u
ss
a
i
n
,
a
n
d
A
.
K
u
mar,
“
M
a
l
a
r
i
a
p
a
r
a
s
i
t
e
c
e
l
l
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
w
i
t
h
st
a
t
e
-
of
-
t
h
e
-
a
r
t
C
N
N
a
r
c
h
i
t
e
c
t
u
r
e
s
,
”
B
i
o
l
o
g
y
,
v
o
l
.
1
4
,
n
o
.
1
2
,
p
.
1
7
9
2
,
D
e
c
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
b
i
o
l
o
g
y
1
4
1
2
1
7
9
2
.
[
1
4
]
W
.
S
i
l
k
a
,
M
.
W
i
e
c
z
o
r
e
k
,
J.
S
i
l
k
a
,
a
n
d
M
.
W
o
ź
n
i
a
k
,
“
M
a
l
a
r
i
a
d
e
t
e
c
t
i
o
n
u
si
n
g
a
d
v
a
n
c
e
d
d
e
e
p
l
e
a
r
n
i
n
g
a
r
c
h
i
t
e
c
t
u
r
e
,”
S
e
n
s
o
rs
,
v
o
l
.
2
3
,
n
o
.
3
,
p
.
1
5
0
1
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
3
0
3
1
5
0
1
.
[
1
5
]
S
.
S
a
j
i
t
h
e
t
a
l
.
,
“
A
n
e
mi
a
i
d
e
n
t
i
f
i
c
a
t
i
o
n
f
r
o
m
b
l
o
o
d
sme
a
r
i
ma
g
e
s
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
:
a
n
X
A
I
a
p
p
r
o
a
c
h
,
”
i
n
2
0
2
3
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
R
e
c
e
n
t
A
d
v
a
n
c
e
s
i
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
f
o
r
S
u
s
t
a
i
n
a
b
l
e
D
e
v
e
l
o
p
m
e
n
t
(
I
C
RAI
S
)
,
N
o
v
.
2
0
2
3
,
p
p
.
1
4
7
–
1
5
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
R
A
I
S
5
9
6
8
4
.
2
0
2
3
.
1
0
3
6
7
0
7
8.
[
1
6
]
K.
T
.
N
a
v
y
a
,
K
.
P
r
a
s
a
d
,
a
n
d
B
.
M
.
K
.
S
i
n
g
h
,
“
A
n
a
l
y
si
s
o
f
r
e
d
b
l
o
o
d
c
e
l
l
s
f
r
o
m
p
e
r
i
p
h
e
r
a
l
b
l
o
o
d
sme
a
r
i
m
a
g
e
s
f
o
r
a
n
e
mi
a
d
e
t
e
c
t
i
o
n
:
a
me
t
h
o
d
o
l
o
g
i
c
a
l
r
e
v
i
e
w
,
”
Me
d
i
c
a
l
a
n
d
B
i
o
l
o
g
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
6
0
,
n
o
.
9
,
p
p
.
2
4
4
5
–
2
4
6
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
5
1
7
-
022
-
0
2
6
1
4
-
z.
[
1
7
]
M
.
S
h
a
h
z
a
d
e
t
a
l
.
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
a
n
e
mi
a
a
n
d
i
t
s
se
v
e
r
i
t
y
l
e
v
e
l
i
n
a
p
e
r
i
p
h
e
r
a
l
b
l
o
o
d
sm
e
a
r
u
s
i
n
g
3
-
t
i
e
r
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
2
,
n
o
.
1
0
,
p
.
5
0
3
0
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
2
1
0
5
0
3
0
.
[
1
8
]
R
.
G
.
M
a
n
n
i
n
o
e
t
a
l
.
,
“
S
m
a
r
t
p
h
o
n
e
a
p
p
f
o
r
n
o
n
-
i
n
v
a
s
i
v
e
d
e
t
e
c
t
i
o
n
o
f
a
n
e
mi
a
u
si
n
g
o
n
l
y
p
a
t
i
e
n
t
-
s
o
u
r
c
e
d
p
h
o
t
o
s
,
”
N
a
t
u
re
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
v
o
l
.
9
,
n
o
.
1
,
p.
4
9
2
4
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
4
6
7
-
0
1
8
-
0
7
2
6
2
-
2.
[
1
9
]
M
.
R
a
mz
a
n
,
M
.
U
.
S
a
e
e
d
,
a
n
d
G
.
A
l
i
,
“
En
h
a
n
c
i
n
g
a
n
e
mi
a
d
e
t
e
c
t
i
o
n
t
h
r
o
u
g
h
m
u
l
t
i
m
o
d
a
l
d
a
t
a
f
u
s
i
o
n
:
a
n
o
n
-
i
n
v
a
si
v
e
a
p
p
r
o
a
c
h
u
si
n
g
EH
R
s
a
n
d
c
o
n
j
u
n
c
t
i
v
a
i
m
a
g
e
s,
”
D
i
sc
o
v
e
r
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
4
,
n
o
.
1
,
p
p
.
1
–
19
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s4
4
1
6
3
-
024
-
0
0
1
9
6
-
3.
[
2
0
]
M
.
R
a
mz
a
n
,
J.
S
h
e
n
g
,
M
.
U
.
S
a
e
e
d
,
B
.
W
a
n
g
,
a
n
d
F
.
Z.
D
u
r
a
i
h
e
m
,
“
R
e
v
o
l
u
t
i
o
n
i
z
i
n
g
a
n
e
m
i
a
d
e
t
e
c
t
i
o
n
:
i
n
t
e
g
r
a
t
i
v
e
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
s
a
n
d
a
d
v
a
n
c
e
d
a
t
t
e
n
t
i
o
n
m
e
c
h
a
n
i
sms
,
”
Vi
s
u
a
l
C
o
m
p
u
t
i
n
g
f
o
r
I
n
d
u
st
r
y
,
B
i
o
m
e
d
i
c
i
n
e
,
a
n
d
Ar
t
,
v
o
l
.
7
,
n
o
.
1
,
p
p
.
1
–
13
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
2
4
9
2
-
0
2
4
-
0
0
1
6
9
-
4.
[
2
1
]
S
.
R
.
S
t
a
h
l
s
c
h
mi
d
t
,
B
.
U
l
f
e
n
b
o
r
g
,
a
n
d
J
.
S
y
n
n
e
r
g
r
e
n
,
“
M
u
l
t
i
m
o
d
a
l
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
b
i
o
m
e
d
i
c
a
l
d
a
t
a
f
u
si
o
n
:
a
r
e
v
i
e
w
,
”
B
ri
e
f
i
n
g
s
i
n
Bi
o
i
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
2
3
,
n
o
.
2
,
p
p
.
1
–
1
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
9
3
/
b
i
b
/
b
b
a
b
5
6
9
.
[
2
2
]
C
.
C
u
i
et
a
l
.
,
“
D
e
e
p
mu
l
t
i
mo
d
a
l
f
u
si
o
n
o
f
i
ma
g
e
a
n
d
n
o
n
-
i
m
a
g
e
d
a
t
a
i
n
d
i
sea
s
e
d
i
a
g
n
o
s
i
s
a
n
d
p
r
o
g
n
o
s
i
s:
a
r
e
v
i
e
w
,
”
Pr
o
g
ress
i
n
Bi
o
m
e
d
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
5
,
n
o
.
2
,
p.
0
2
2
0
0
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
8
8
/
2
5
1
6
-
1
0
9
1
/
a
c
c
2
f
e
.
[
2
3
]
N
.
P
e
r
e
z
,
M
.
C
u
a
d
r
o
s,
a
n
d
G
.
R
i
g
a
u
,
“
N
e
g
a
t
i
o
n
a
n
d
s
p
e
c
u
l
a
t
i
o
n
p
r
o
c
e
ssi
n
g
:
a
s
t
u
d
y
o
n
c
u
e
-
sc
o
p
e
l
a
b
e
l
l
i
n
g
a
n
d
a
ssert
i
o
n
c
l
a
ss
i
f
i
c
a
t
i
o
n
i
n
S
p
a
n
i
sh
c
l
i
n
i
c
a
l
t
e
x
t
,
”
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
Me
d
i
c
i
n
e
,
v
o
l
.
1
4
5
,
p
.
1
0
2
6
8
2
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
r
t
me
d
.
2
0
2
3
.
1
0
2
6
8
2
.
[
2
4
]
A
.
K
a
r
e
e
m
,
H
.
L
i
u
,
a
n
d
V
.
V
e
l
i
sa
v
l
j
e
v
i
c
,
“
A
p
r
i
v
a
c
y
-
p
r
e
ser
v
i
n
g
a
p
p
r
o
a
c
h
t
o
e
f
f
e
c
t
i
v
e
l
y
u
t
i
l
i
z
e
d
i
s
t
r
i
b
u
t
e
d
d
a
t
a
f
o
r
ma
l
a
r
i
a
i
m
a
g
e
d
e
t
e
c
t
i
o
n
,
”
Bi
o
e
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
1
,
n
o
.
4
,
p
.
3
4
0
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
b
i
o
e
n
g
i
n
e
e
r
i
n
g
1
1
0
4
0
3
4
0
.
[
2
5
]
D
.
A
.
R
a
mo
s
-
B
r
i
c
e
ñ
o
,
A
.
F
l
a
mm
i
a
-
D
’
A
l
e
o
,
G
.
F
e
r
n
á
n
d
e
z
-
L
ó
p
e
z
,
F
.
S
.
C
a
r
r
i
ó
n
-
N
e
s
si
,
a
n
d
D
.
A
.
F
o
r
e
r
o
-
P
e
ñ
a
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
m
a
l
a
r
i
a
p
a
r
a
si
t
e
d
e
t
e
c
t
i
o
n
:
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
f
o
r
a
c
c
u
r
a
t
e
sp
e
c
i
e
s
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
P
l
a
sm
o
d
i
u
m
f
a
l
c
i
p
a
r
u
m
a
n
d
P
l
a
s
mo
d
i
u
m
v
i
v
a
x
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
1
5
,
n
o
.
1
,
p
.
3
7
4
6
,
Ja
n
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
8
-
0
2
5
-
8
7
9
7
9
-
5.
[
2
6
]
X
.
Li
u
e
t
a
l
.
,
“
A
d
v
a
n
c
e
s
i
n
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
m
e
d
i
c
a
l
i
ma
g
e
a
n
a
l
y
si
s
,”
H
e
a
l
t
h
D
a
t
a
S
c
i
e
n
c
e
,
v
o
l
.
2
0
2
1
,
p
p
.
1
–
14
,
Ja
n
.
2
0
2
1
,
d
o
i
:
1
0
.
3
4
1
3
3
/
2
0
2
1
/
8
7
8
6
7
9
3.
[
2
7
]
M
.
Li
,
Y
.
J
i
a
n
g
,
Y
.
Zh
a
n
g
,
a
n
d
H
.
Z
h
u
,
“
M
e
d
i
c
a
l
i
ma
g
e
a
n
a
l
y
s
i
s
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
,
”
Fro
n
t
i
e
rs
i
n
P
u
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
1
1
,
p.
1
2
7
3
2
5
3
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
u
b
h
.
2
0
2
3
.
1
2
7
3
2
5
3
.
[
2
8
]
Y
.
Z
h
a
n
g
,
J
.
M
.
G
o
r
r
i
z
,
a
n
d
Z.
D
o
n
g
,
“
D
e
e
p
l
e
a
r
n
i
n
g
i
n
m
e
d
i
c
a
l
i
m
a
g
e
a
n
a
l
y
si
s
,
”
J
o
u
r
n
a
l
o
f
I
m
a
g
i
n
g
,
v
o
l
.
7
,
n
o
.
4
,
p
.
7
4
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
j
i
ma
g
i
n
g
7
0
4
0
0
7
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
Hem
a
to
lo
g
ica
l p
r
o
fili
n
g
o
f m
a
la
r
ia
-
in
d
u
ce
d
a
n
emia
u
s
in
g
d
e
ep
lea
r
n
in
g
(
V
a
n
r
o
s
e
P
a
n
a
s
h
e
N
ya
ma
n
g
o
d
o
)
313
[
2
9
]
S
.
S
u
g
a
n
y
a
d
e
v
i
,
V
.
S
e
e
t
h
a
l
a
k
s
h
mi
,
a
n
d
K
.
B
a
l
a
sam
y
,
“
A
r
e
v
i
e
w
o
n
d
e
e
p
l
e
a
r
n
i
n
g
i
n
me
d
i
c
a
l
i
ma
g
e
a
n
a
l
y
s
i
s,”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
M
u
l
t
i
m
e
d
i
a
I
n
f
o
rm
a
t
i
o
n
R
e
t
ri
e
v
a
l
,
v
o
l
.
1
1
,
n
o
.
1
,
p
p
.
1
9
–
3
8
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
3
7
3
5
-
0
2
1
-
0
0
2
1
8
-
1.
[
3
0
]
M
.
A
d
n
a
n
,
S
.
K
a
l
r
a
,
J
.
C
.
C
r
e
ssw
e
l
l
,
G
.
W
.
T
a
y
l
o
r
,
a
n
d
H
.
R
.
Ti
z
h
o
o
s
h
,
“
F
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
a
n
d
d
i
f
f
e
r
e
n
t
i
a
l
p
r
i
v
a
c
y
f
o
r
me
d
i
c
a
l
i
ma
g
e
a
n
a
l
y
s
i
s,”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
r
t
s
,
v
o
l
.
1
2
,
n
o
.
1
,
p
.
1
9
5
3
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
2
-
0
5
5
3
9
-
7.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Va
n
r
o
se
Pa
n
a
she
Ny
a
m
a
n
g
o
d
o
is
p
u
rs
u
in
g
a
M
a
ste
r
o
f
Tec
h
n
o
lo
g
y
d
e
g
re
e
a
t
th
e
Ha
ra
re
In
stit
u
te
o
f
Tec
h
n
o
lo
g
y
(HIT)
i
n
Ha
ra
re
,
Zi
m
b
a
b
we
.
He
r
re
se
a
r
c
h
in
tere
sts
c
e
n
ter
o
n
a
rti
ficia
l
i
n
telli
g
e
n
c
e
,
d
e
e
p
lea
rn
in
g
,
m
e
d
ica
l
ima
g
e
a
n
a
ly
sis,
d
a
ta
sc
ien
c
e
a
n
d
a
n
a
ly
ti
c
s
,
a
n
d
so
ftwa
re
d
e
v
e
lo
p
m
e
n
t.
I
n
a
d
d
it
i
o
n
,
s
h
e
b
ri
n
g
s
p
r
o
fe
ss
io
n
a
l
e
x
p
e
rien
c
e
in
we
b
d
e
v
e
lo
p
m
e
n
t
a
n
d
d
a
ta
sc
ien
c
e
Re
tri
e
v
a
l
-
Au
g
m
e
n
ted
G
e
n
e
ra
ti
o
n
(
RAG
)
sy
ste
m
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
v
a
n
ro
se
p
a
n
a
s
h
e
@g
m
a
il
.
c
o
m
.
We
ll
in
g
to
n
M
a
k
o
n
d
o
is
a
l
e
c
tu
re
r
in
t
h
e
De
p
a
rtme
n
t
o
f
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
a
t
Ha
ra
re
In
stit
u
te
o
f
Tec
h
n
o
lo
g
y
(HIT),
Ha
ra
re
,
Zi
m
b
a
b
we
.
Hi
s
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
a
rti
ficia
l
in
telli
g
e
n
c
e
,
m
a
c
h
in
e
lea
rn
in
g
,
a
rti
ficia
l
n
e
u
ra
l
n
e
t
wo
rk
s,
f
u
z
z
y
l
o
g
ic,
c
lo
u
d
c
o
m
p
u
ti
n
g
,
s
o
ftwa
re
tes
t
in
g
,
a
n
d
c
o
m
m
u
n
ica
ti
o
n
e
n
g
in
e
e
rin
g
.
He
h
a
s
a
u
th
o
re
d
n
u
m
e
ro
u
s
p
u
b
li
c
a
ti
o
n
s
in
in
telli
g
e
n
t
sy
ste
m
s,
m
e
d
ica
l
AI,
a
n
d
e
m
e
rg
in
g
in
fo
rm
a
ti
o
n
tec
h
n
o
lo
g
ies
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
wm
a
k
o
n
d
o
@
h
it
.
a
c
.
z
w
.
S
im
b
a
i
Zin
d
o
v
e
is
a
lec
tu
r
e
r
in
th
e
De
p
a
rtme
n
t
o
f
S
o
ftwa
re
En
g
i
n
e
e
rin
g
a
t
Ha
ra
re
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
(HIT),
Ha
ra
re
,
Zi
m
b
a
b
we
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
a
rti
ficia
l
in
telli
g
e
n
c
e
,
c
lo
u
d
c
o
m
p
u
ti
n
g
,
a
n
d
c
y
b
e
rse
c
u
rit
y
.
S
h
e
h
a
s
c
o
-
a
u
t
h
o
re
d
a
c
a
d
e
m
ic
p
u
b
li
c
a
ti
o
n
s
f
o
c
u
sin
g
o
n
n
a
t
u
r
a
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
,
p
re
d
ic
ti
v
e
fra
m
e
wo
rk
s,
a
rti
ficia
l
in
telli
g
e
n
c
e
,
a
n
d
o
p
ti
m
iza
ti
o
n
sy
s
tem
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sz
in
d
o
v
e
@h
i
t.
a
c
.
z
w
Evaluation Warning : The document was created with Spire.PDF for Python.