Artificial Intelligence for Optical Coherence Tomography in Glaucoma
Translational Vision Science & Technology,
Год журнала:
2025,
Номер
14(1), С. 27 - 27
Опубликована: Янв. 24, 2025
Purpose:
The
integration
of
artificial
intelligence
(AI),
particularly
deep
learning
(DL),
with
optical
coherence
tomography
(OCT)
offers
significant
opportunities
in
the
diagnosis
and
management
glaucoma.
This
article
explores
application
various
DL
models
enhancing
OCT
capabilities
addresses
challenges
associated
their
clinical
implementation.
Methods:
A
review
articles
utilizing
was
conducted,
including
convolutional
neural
networks
(CNNs),
recurrent
(RNNs),
generative
adversarial
(GANs),
autoencoders,
large
language
(LLMs).
Key
developments
practical
applications
these
image
analysis
were
emphasized,
context
quality,
glaucoma
diagnosis,
monitoring
progression.
Results:
CNNs
excel
segmenting
retinal
layers
detecting
glaucomatous
damage,
whereas
RNNs
are
effective
analyzing
sequential
scans
for
disease
GANs
enhance
quality
data
augmentation,
autoencoders
facilitate
advanced
feature
extraction.
LLMs
show
promise
integrating
textual
visual
comprehensive
diagnostic
assessments.
Despite
advancements,
such
as
availability,
variability,
potential
biases,
need
extensive
validation
persist.
Conclusions:
reshaping
by
OCT's
capabilities.
However,
successful
translation
into
practice
requires
addressing
major
related
to
fairness,
model
ensure
accurate
reliable
patient
care.
Translational
Relevance:
bridges
gap
between
basic
research
care
demonstrating
how
AI,
models,
can
markedly
utility
monitoring,
prediction,
moving
toward
more
individualized,
personalized,
precise
treatment
strategies.
Язык: Английский
Performance of the Generative Artificial Intelligence Chatbot in Ophthalmic Registration and Clinical Diagnosis: a Cross-sectional Study (Preprint)
Journal of Medical Internet Research,
Год журнала:
2024,
Номер
26, С. e60226 - e60226
Опубликована: Окт. 15, 2024
Background
Artificial
intelligence
(AI)
chatbots
such
as
ChatGPT
are
expected
to
impact
vision
health
care
significantly.
Their
potential
optimize
the
consultation
process
and
diagnostic
capabilities
across
range
of
ophthalmic
subspecialties
have
yet
be
fully
explored.
Objective
This
study
aims
investigate
performance
AI
in
recommending
outpatient
registration
diagnosing
eye
diseases
within
clinical
case
profiles.
Methods
cross-sectional
used
cases
from
Chinese
Standardized
Resident
Training–Ophthalmology
(2nd
Edition).
For
each
case,
2
profiles
were
created:
patient
with
history
(Hx)
examination
(Hx+Ex).
These
served
independent
queries
for
GPT-3.5
GPT-4.0
(accessed
March
5
18,
2024).
Similarly,
3
residents
posed
same
a
questionnaire
format.
The
accuracy
subspecialty
was
primarily
evaluated
using
Hx
top-ranked
diagnosis
top
suggestions
(do-not-miss
diagnosis)
assessed
Hx+Ex
gold
standard
judgment
published,
official
diagnosis.
Characteristics
incorrect
diagnoses
by
also
analyzed.
Results
A
total
208
12
analyzed
(104
104
profiles).
profiles,
GPT-3.5,
GPT-4.0,
showed
comparable
(66/104,
63.5%;
81/104,
77.9%;
72/104,
69.2%,
respectively;
P=.07),
ocular
trauma,
retinal
diseases,
strabismus
amblyopia
achieving
accuracies.
both
demonstrated
higher
than
(62/104,
59.6%
63/104,
60.6%
vs
41/104,
39.4%;
P=.003
P=.001,
respectively).
Accuracy
do-not-miss
improved
(79/104,
76%
68/104,
65.4%
51/104,
49%;
P<.001
P=.02,
highest
accuracies
observed
glaucoma;
lens
diseases;
eyelid,
lacrimal,
orbital
diseases.
recorded
fewer
top-3
(25/42,
60%
53/63,
84%;
P=.005)
more
partially
correct
(21/42,
50%
7/63
11%;
P<.001)
while
had
completely
(27/63,
43%
7/42,
17%;
less
precise
(22/63,
35%
5/42,
12%;
P=.009).
Conclusions
intermediate
registration.
While
underperformed,
approached
numerically
surpassed
differential
show
promise
facilitating
However,
their
integration
into
decision-making
requires
validation.
Язык: Английский
A gene-based predictive model for lymph node metastasis in cervical cancer: superior performance over imaging techniques
Journal of Translational Medicine,
Год журнала:
2025,
Номер
23(1)
Опубликована: Апрель 3, 2025
Abstract
Objective
Lymph
node
metastasis
(LNM)
critically
impacts
the
prognosis
and
treatment
decisions
of
cervical
cancer
patients.
The
accuracy
sensitivity
current
imaging
techniques,
such
as
CT
MRI,
are
limited
in
assessing
lymph
status.
This
study
aims
to
develop
a
more
accurate
efficient
method
for
predicting
LNM.
Methods
Three
independent
cohorts
were
merged
divided
into
training
internal
validation
groups,
with
our
cohort
those
from
other
centers
serving
external
validation.
A
predictive
model
LNM
was
established
using
LASSO
regression
multivariate
logistic
regression.
diagnostic
performance
compared
that
CT/MRI
terms
accuracy,
sensitivity,
specificity,
AUC.
Results
Using
RNA-seq
data,
four
genes
(MAPT,
EPB41L1,
ACSL5,
PRPF4B)
identified
through
regression,
constructed
calculate
risk
score.
Compared
CT/MRI,
demonstrated
higher
efficiency,
an
0.840
0.804,
CT/MRI’s
0.713
0.587.
corrected
81%
misdiagnoses
by
demonstrating
significant
improvements
sensitivity.
Conclusion
developed
this
study,
based
on
gene
expression
significantly
improves
preoperative
assessment
cancer.
traditional
shows
superior
accuracy.
provides
robust
foundation
developing
precise
tools,
paving
way
future
clinical
applications
individualized
planning.
Язык: Английский
Progress in Artificial Intelligence-Assisted Fundus Photography Screening Technology for Glaucoma
Advances in Clinical Medicine,
Год журнала:
2025,
Номер
15(04), С. 967 - 973
Опубликована: Янв. 1, 2025
Язык: Английский
Artificial intelligence technology in ophthalmology public health: current applications and future directions
Frontiers in Cell and Developmental Biology,
Год журнала:
2025,
Номер
13
Опубликована: Апрель 17, 2025
Global
eye
health
has
become
a
critical
public
challenge,
with
the
prevalence
of
blindness
and
visual
impairment
expected
to
rise
significantly
in
coming
decades.
Traditional
ophthalmic
systems
face
numerous
obstacles,
including
uneven
distribution
medical
resources,
insufficient
training
for
primary
healthcare
workers,
limited
awareness
health.
Addressing
these
challenges
requires
urgent,
innovative
solutions.
Artificial
intelligence
(AI)
demonstrated
substantial
potential
enhancing
across
various
domains.
AI
offers
significant
improvements
data
management,
disease
screening
monitoring,
risk
prediction
early
warning
systems,
resource
allocation,
education
patient
management.
These
advancements
substantially
improve
quality
efficiency
healthcare,
particularly
preventing
treating
prevalent
conditions
such
as
cataracts,
diabetic
retinopathy,
glaucoma,
myopia.
Additionally,
telemedicine
mobile
applications
have
expanded
access
services
enhanced
capabilities
providers.
However,
there
are
integrating
into
Key
issues
include
interoperability
electronic
records
(EHR),
security
privacy,
bias,
algorithm
transparency,
ethical
regulatory
frameworks.
Heterogeneous
formats
lack
standardized
metadata
hinder
seamless
integration,
while
privacy
risks
necessitate
advanced
techniques
anonymization.
Data
biases,
stemming
from
racial
or
geographic
disparities,
"black
box"
nature
models,
limit
reliability
clinical
trust.
Ethical
issues,
ensuring
accountability
AI-driven
decisions
balancing
innovation
safety,
further
complicate
implementation.
The
future
lies
overcoming
barriers
fully
harness
AI,
that
technology
translate
tangible
benefits
patients
worldwide.
Язык: Английский
Advancements in artificial intelligence for the diagnosis and management of anterior segment diseases
Current Opinion in Ophthalmology,
Год журнала:
2025,
Номер
unknown
Опубликована: Апрель 22, 2025
Purpose
of
review
The
integration
artificial
intelligence
(AI)
in
the
diagnosis
and
management
anterior
segment
diseases
has
rapidly
expanded,
demonstrating
significant
potential
to
revolutionize
clinical
practice.
Recent
findings
AI
technologies,
including
machine
learning
deep
models,
are
increasingly
applied
detection
a
variety
conditions,
such
as
corneal
diseases,
refractive
surgery,
cataract,
conjunctival
disorders
(e.g.,
pterygium),
trachoma,
dry
eye
disease.
By
analyzing
large-scale
imaging
data
information,
enhances
diagnostic
accuracy,
predicts
treatment
outcomes,
supports
personalized
patient
care.
Summary
As
models
continue
evolve,
particularly
with
use
large
generative
techniques,
they
will
further
refine
planning.
While
challenges
remain,
issues
related
diversity
model
interpretability,
AI's
into
ophthalmology
promises
improve
healthcare
making
it
cornerstone
data-driven
medical
continued
development
application
undoubtedly
transform
future
ophthalmology,
leading
more
efficient,
accurate,
individualized
Язык: Английский
Electrochemical immunosensing for rapid glaucoma disease diagnosis through simultaneous determination of SPP1 and GAS6 proteins in ocular fluids
Talanta,
Год журнала:
2025,
Номер
unknown, С. 128438 - 128438
Опубликована: Июнь 1, 2025
Язык: Английский
A comparative study of GPT-4o and human ophthalmologists in glaucoma diagnosis
Scientific Reports,
Год журнала:
2024,
Номер
14(1)
Опубликована: Дек. 5, 2024
Artificial
intelligence
(AI),
particularly
large
language
models
like
GPT-4o,
holds
promise
for
enhancing
diagnostic
accuracy
in
healthcare.
This
study
evaluates
the
performance
of
GPT-4o
compared
to
human
ophthalmologists
glaucoma
cases.
A
prospective,
observational
was
conducted
at
a
tertiary
care
ophthalmology
center.
Twenty-six
cases,
including
both
primary
and
secondary
types,
were
selected
from
publicly
available
databases
institutional
records.
The
cases
analyzed
by
three
with
varying
levels
experience.
completeness
differential
diagnoses
assessed
using
10-point
6-point
Likert
scales,
respectively.
Statistical
analyses
performed
nonparametric
methods,
Kruskal–Wallis
Mann–Whitney
U
tests.
significantly
less
accurate
diagnosis
ophthalmologists.
Specifically,
achieved
mean
score
5.500
(p
<
0.001)
Doctor
C,
who
had
highest
8.038
0.001).
Completeness
scores
3.077
also
lower
than
B,
lowest
3.615
among
However,
diagnosis,
(7.577)
showed
comparable
(7.615)
C
(7.673)
0.0001)
while
achieving
(4.096),
outperforming
(3.846),
(2.923),
B
(2.808)
0.0001).
AI,
is
currently
not
an
acceptable
standalone
method
diagnosing
due
its
clinicians.
These
findings
suggest
that
could
serve
as
valuable
adjunct
clinical
practice,
complex
but
should
replace
expertise,
especially
initial
diagnoses.
Future
improvements
AI
enhance
their
utility
ophthalmology.
Язык: Английский
Artificial intelligence and glaucoma: a lucid and comprehensive review
Frontiers in Medicine,
Год журнала:
2024,
Номер
11
Опубликована: Дек. 16, 2024
Glaucoma
is
a
pathologically
irreversible
eye
illness
in
the
realm
of
ophthalmic
diseases.
Because
it
difficult
to
detect
concealed
and
non-obvious
progressive
changes,
clinical
diagnosis
treatment
glaucoma
extremely
challenging.
At
same
time,
screening
monitoring
for
disease
progression
are
crucial.
Artificial
intelligence
technology
has
advanced
rapidly
all
fields,
particularly
medicine,
thanks
ongoing
in-depth
study
algorithm
extension.
Simultaneously,
research
applications
machine
learning
deep
field
fast
evolving.
intelligence,
with
its
numerous
advantages,
will
raise
accuracy
efficiency
new
heights,
as
well
significantly
cut
cost
majority
patients.
This
review
summarizes
relevant
artificial
glaucoma,
reflects
deeply
on
limitations
difficulties
current
application
presents
promising
prospects
expectations
other
diseases
such
glaucoma.
Язык: Английский