Attention to the Electroretinogram: Gated Multilayer Perceptron for ASD Classification
IEEE Access,
Год журнала:
2024,
Номер
12, С. 52352 - 52362
Опубликована: Янв. 1, 2024
The
electroretinogram
(ERG)
is
a
clinical
test
that
records
the
retina's
electrical
response
to
brief
flash
of
light
as
waveform
signal.
Analysis
ERG
signal
offers
promising
non-invasive
method
for
studying
different
neurodevelopmental
and
neurodegenerative
disorders.
Autism
Spectrum
Disorder
(ASD)
condition
characterized
by
poor
communication,
reduced
reciprocal
social
interaction,
restricted
and/or
repetitive
stereotyped
behaviors
should
be
detected
early
possible
ensure
timely
appropriate
intervention
support
individual
their
family.
In
this
study,
we
applied
gated
Multilayer
Perceptron
(gMLP)
light-adapted
classification
an
effective
alternative
Transformers.
first
reported
application
model
ASD
which
consisted
basic
multilayer
perceptrons,
with
fewer
parameters
than
We
compared
performance
time-series
models
on
ASD-Control
dataset
found
superiority
gMLP
in
accuracy
was
best
at
89.7%
supports
use
based
recordings
involving
case-control
comparisons.
Язык: Английский
Generating Synthetic Light‐Adapted Electroretinogram Waveforms Using Artificial Intelligence to Improve Classification of Retinal Conditions in Under‐Represented Populations
Journal of Ophthalmology,
Год журнала:
2024,
Номер
2024(1)
Опубликована: Янв. 1, 2024
Visual
electrophysiology
is
often
used
clinically
to
determine
the
functional
changes
associated
with
retinal
or
neurological
conditions.
The
full‐field
flash
electroretinogram
(ERG)
assesses
global
contribution
of
outer
and
inner
layers
initiated
by
rods
cone
pathways
depending
on
state
adaptation.
Within
clinical
centers,
reference
normative
data
are
compare
cases
that
may
be
rare
underpowered
within
a
specific
demographic.
To
bolster
either
dataset
case
dataset,
application
synthetic
ERG
waveforms
offer
benefits
disease
classification
case‐control
studies.
In
this
study
as
proof
concept,
artificial
intelligence
(AI)
generate
signals
using
generative
adversarial
networks
deployed
upscale
male
participants
an
ISCEV
containing
68
participants,
from
right
left
eye.
Random
forest
classifiers
further
improved
for
sex
group
balanced
accuracy
0.72–0.83
added
waveforms.
This
first
demonstrate
generation
improve
machine
learning
modelling
Язык: Английский
Remodeling the light-adapted electroretinogram using a bayesian statistical approach
BMC Research Notes,
Год журнала:
2025,
Номер
18(1)
Опубликована: Янв. 23, 2025
Язык: Английский
Exploring autism via the retina: Comparative insights in children with autism spectrum disorder and typical development
Autism Research,
Год журнала:
2024,
Номер
17(8), С. 1520 - 1533
Опубликована: Июль 29, 2024
Abstract
Autism
spectrum
disorder
(ASD)
is
a
widely
recognized
neurodevelopmental
disorder,
yet
the
identification
of
reliable
imaging
biomarkers
for
its
early
diagnosis
remains
challenge.
Considering
specific
manifestations
ASD
in
eyes
and
interconnectivity
between
brain
eyes,
this
study
investigates
through
lens
retinal
analysis.
We
specifically
examined
differences
macular
region
retina
using
optical
coherence
tomography
(OCT)/optical
angiography
(OCTA)
images
children
diagnosed
with
those
typical
development
(TD).
Our
findings
present
potential
novel
characteristics
ASD:
thickness
ellipsoid
zone
(EZ)
cone
photoreceptors
was
significantly
increased
ASD;
large‐caliber
arteriovenous
inner
reduced
these
changes
EZ
were
more
significant
left
eye
than
right
eye.
These
observations
photoreceptor
alterations,
vascular
function
changes,
lateralization
phenomena
warrant
further
investigation,
we
hope
that
work
can
advance
interdisciplinary
understanding
ASD.
Язык: Английский
Spectral Analysis of Light-Adapted Electroretinograms in Neurodevelopmental Disorders: Classification with Machine Learning
Bioengineering,
Год журнала:
2024,
Номер
12(1), С. 15 - 15
Опубликована: Дек. 28, 2024
Electroretinograms
(ERGs)
show
differences
between
typically
developing
populations
and
those
with
a
diagnosis
of
autism
spectrum
disorder
(ASD)
or
attention
deficit/hyperactivity
(ADHD).
In
series
ERGs
collected
in
ASD
(n
=
77),
ADHD
43),
+
21),
control
137)
groups,
this
analysis
explores
the
use
machine
learning
feature
selection
techniques
to
improve
classification
these
clinically
defined
groups.
Standard
time
domain
signal
features
were
evaluated
different
models.
For
classification,
balanced
accuracy
(BA)
0.87
was
achieved
for
male
participants.
ADHD,
BA
0.84
female
When
three-group
model
(ASD,
control)
lower,
at
0.70,
fell
further
0.53
when
all
groups
included
control).
The
findings
support
role
ERG
establishing
broad
two-group
but
model's
performance
depends
upon
sex
is
limited
multiple
classes
are
modeling.
Язык: Английский