International Journal of Management & Entrepreneurship Research,
Год журнала:
2024,
Номер
6(1), С. 200 - 215
Опубликована: Янв. 25, 2024
In
the
rapidly
evolving
landscape
of
entrepreneurship,
integration
Artificial
Intelligence
(AI)
has
emerged
as
a
transformative
force,
reshaping
traditional
business
paradigms
and
offering
unprecedented
opportunities
for
success.
This
paper
provides
comprehensive
critical
review
AI-driven
strategies
employed
by
entrepreneurs
to
enhance
their
ventures.
The
encompasses
thorough
analysis
key
AI
applications,
impact
on
various
aspects
potential
benefits
challenges
associated
with
implementation.
first
section
explores
role
in
market
analysis,
highlighting
how
advanced
data
analytics
predictive
modelling
contribute
informed
decision-making
forecasting.
discussion
then
extends
innovations
product
development,
emphasizing
acceleration
ideation,
prototyping,
customization
through
machine
learning
algorithms.
Next,
scrutinizes
influence
customer
engagement
relationship
management.
It
delves
into
personalized
experiences
facilitated
chatbots,
recommendation
systems,
sentiment
while
also
addressing
ethical
considerations
surrounding
privacy
algorithmic
biases.
Entrepreneurial
operations
efficiency
gains
are
examined
subsequent
section,
AI's
supply
chain
management,
logistics,
resource
optimization.
underscores
increased
productivity
cost-effectiveness
implementation
AI-powered
automation
smart
systems.
Despite
myriad
advantages,
critically
examines
such
concerns,
job
displacement,
digital
divide.
emphasizes
need
balanced
approach
that
addresses
societal
adoption
fostering
inclusive
entrepreneurial
ecosystems.
conclusion,
this
not
only
overview
current
entrepreneurship
but
offers
insights
future
developments
challenges.
Entrepreneurs,
policymakers,
researchers
can
leverage
navigate
intersection
sustainable
ethically
sound
environment
success
era.
Keywords:
(AI),
Entrepreneurship,
Strategic
Implementation,
Innovation,
Market
Analysis,
Predictive
Modelling.
Bioengineering,
Год журнала:
2025,
Номер
12(3), С. 288 - 288
Опубликована: Март 13, 2025
The
integration
of
artificial
intelligence
(AI)
into
ultrasound
medicine
has
revolutionized
medical
imaging,
enhancing
diagnostic
accuracy
and
clinical
workflows.
This
review
focuses
on
the
applications,
challenges,
future
directions
AI
technologies,
particularly
machine
learning
(ML)
its
subset,
deep
(DL),
in
diagnostics.
By
leveraging
advanced
algorithms
such
as
convolutional
neural
networks
(CNNs),
significantly
improved
image
acquisition,
quality
assessment,
objective
disease
diagnosis.
AI-driven
solutions
now
facilitate
automated
analysis,
intelligent
assistance,
education,
enabling
precise
lesion
detection
across
various
organs
while
reducing
physician
workload.
AI’s
error
capabilities
further
enhance
accuracy.
Looking
ahead,
with
is
expected
to
deepen,
promoting
trends
standardization,
personalized
treatment,
healthcare,
underserved
areas.
Despite
potential,
comprehensive
assessments
ethical
implications
remain
limited,
necessitating
rigorous
evaluations
ensure
effectiveness
practice.
provides
a
systematic
evaluation
technologies
medicine,
highlighting
their
transformative
potential
improve
global
healthcare
outcomes.
Scientific Reports,
Год журнала:
2024,
Номер
14(1)
Опубликована: Март 9, 2024
Abstract
This
study
aimed
to
develop
a
deep
learning
model
assess
the
quality
of
fetal
echocardiography
and
perform
prospective
clinical
validation.
The
was
trained
on
data
from
18–22-week
anomaly
scan
conducted
in
seven
hospitals
2008
2018.
Prospective
validation
involved
100
patients
two
hospitals.
A
total
5363
images
2551
pregnancies
were
used
for
training
model's
segmentation
accuracy
depended
image
measured
by
score
(QS).
It
achieved
an
overall
average
0.91
(SD
0.09)
across
test
set,
with
having
above-average
QS
scoring
0.97
0.03).
During
192
images,
clinicians
rated
44.8%
9.8)
as
equal
quality,
18.69%
5.7)
favoring
auto-captured
36.51%
9.0)
preferring
manually
captured
ones.
Images
above
showed
better
agreement
segmentations
(
p
<
0.001)
medicine
experts.
Auto-capture
saved
additional
planes
beyond
protocol
requirements,
resulting
more
comprehensive
echocardiographies.
Low
had
adverse
effect
both
performance
clinician’s
feedback.
findings
highlight
importance
developing
evaluating
AI
models
based
‘noisy’
real-life
rather
than
pursuing
highest
possible
retrospective
academic-grade
data.
Abstract
During
the
process
of
labor,
intrapartum
transperineal
ultrasound
examination
serves
as
a
valuable
tool,
allowing
direct
observation
relative
positional
relationship
between
pubic
symphysis
and
fetal
head
(PSFH).
Accurate
assessment
descent
prediction
most
suitable
mode
delivery
heavily
rely
on
this
relationship.
However,
achieving
an
objective
quantitative
interpretation
images
necessitates
precise
PSFH
segmentation
(PSFHS),
task
that
is
both
time-consuming
demanding.
Integrating
potential
artificial
intelligence
(AI)
in
field
medical
image
segmentation,
development
evaluation
AI-based
models
significantly
access
to
comprehensive
meticulously
annotated
datasets.
Unfortunately,
publicly
accessible
datasets
tailored
for
PSFHS
are
notably
scarce.
Bridging
critical
gap,
we
introduce
dataset
comprising
1358
images,
at
pixel
level.
The
annotation
adhered
standardized
protocols
involved
collaboration
among
experts.
Remarkably,
stands
expansive
resource
date.
Frontiers in Pediatrics,
Год журнала:
2025,
Номер
13
Опубликована: Апрель 17, 2025
Artificial
Intelligence
is
revolutionizing
prenatal
diagnostics
by
enhancing
the
accuracy
and
efficiency
of
procedures.
This
review
explores
AI
machine
learning
(ML)
in
early
detection,
prediction,
assessment
neural
tube
defects
(NTDs)
through
ultrasound
imaging.
Recent
studies
highlight
effectiveness
techniques,
such
as
convolutional
networks
(CNNs)
support
vector
machines
(SVMs),
achieving
detection
rates
up
to
95%
across
various
datasets,
including
fetal
images,
genetic
data,
maternal
health
records.
SVM
models
have
demonstrated
71.50%
on
training
datasets
68.57%
testing
for
NTD
classification,
while
advanced
deep
(DL)
methods
report
patient-level
prediction
94.5%
an
area
under
receiver
operating
characteristic
curve
(AUROC)
99.3%.
integration
with
genomic
analysis
has
identified
key
biomarkers
associated
NTDs,
Growth
Associated
Protein
43
(GAP43)
Glial
Fibrillary
Acidic
(GFAP),
logistic
regression
86.67%
accuracy.
Current
AI-assisted
technologies
improved
diagnostic
accuracy,
yielding
sensitivity
specificity
88.9%
98.0%,
respectively,
compared
traditional
81.5%
92.2%
specificity.
systems
also
streamlined
workflows,
reducing
median
scan
times
from
19.7
min
11.4
min,
allowing
sonographers
prioritize
critical
patient
care.
Advancements
DL
algorithms,
Oct-U-Net
PAICS,
achieved
recall
precision
0.93
0.96,
identifying
abnormalities.
Moreover,
AI's
evolving
role
research
supports
personalized
prevention
strategies
enhances
public
awareness
AI-generated
messages.
In
conclusion,
significantly
improves
leading
greater
As
continues
advance,
it
potential
further
enhance
healthcare
raise
about
ultimately
contributing
better
outcomes.
Anesthesia & Analgesia,
Год журнала:
2023,
Номер
137(4), С. 830 - 840
Опубликована: Сен. 5, 2023
Machine
vision
describes
the
use
of
artificial
intelligence
to
interpret,
analyze,
and
derive
predictions
from
image
or
video
data.
vision–based
techniques
are
already
in
clinical
radiology,
ophthalmology,
dermatology,
where
some
applications
currently
equal
exceed
performance
specialty
physicians
areas
interpretation.
While
machine
anesthesia
has
many
potential
applications,
its
development
remains
infancy
our
specialty.
Early
research
for
focused
on
automated
recognition
anatomical
structures
during
ultrasound-guided
regional
line
insertion;
glottic
opening
vocal
cords
laryngoscopy;
prediction
difficult
airway
using
facial
images;
alerts
endobronchial
intubation
detected
chest
radiograph.
Current
measuring
distance
between
endotracheal
tube
tip
carina
have
demonstrated
noninferior
compared
board-certified
physicians.
The
uses
will
only
grow
with
advancement
underlying
algorithm
technical
developed
outside
medicine,
such
as
convolutional
neural
networks
transfer
learning.
This
article
summarizes
recently
published
works
interest,
provides
a
brief
overview
used
create
explains
frequently
terms,
discusses
challenges
encounter
we
embrace
advantages
that
this
technology
may
bring
future
practice
patient
care.
As
emerges
onto
stage,
it
is
critically
important
anesthesiologists
prepared
confidently
assess
which
these
devices
safe,
appropriate,
added
value
Journal of Ultrasound in Medicine,
Год журнала:
2024,
Номер
43(5), С. 881 - 897
Опубликована: Янв. 26, 2024
The
goal
of
this
work
was
to
develop
robust
techniques
for
the
processing
and
identification
SUA
using
artificial
intelligence
(AI)
image
classification
models.
Scientific Reports,
Год журнала:
2024,
Номер
14(1)
Опубликована: Июль 3, 2024
Abstract
Providing
adequate
counseling
on
mode
of
delivery
after
induction
labor
(IOL)
is
utmost
importance.
Various
AI
algorithms
have
been
developed
for
this
purpose,
but
rely
maternal–fetal
data,
not
including
ultrasound
(US)
imaging.
We
used
retrospectively
collected
clinical
data
from
808
subjects
submitted
to
IOL,
totaling
2024
US
images,
train
models
predict
vaginal
(VD)
and
cesarean
section
(CS)
outcomes
IOL.
The
best
overall
model
only
(F1-score:
0.736;
positive
predictive
value
(PPV):
0.734).
imaging
employed
fetal
head,
abdomen
femur
showing
limited
discriminative
results.
images
0.594;
PPV:
0.580).
Consequently,
we
constructed
ensemble
test
whether
could
enhance
the
model.
included
0.689;
0.693),
presenting
a
false
negative
interesting
trade-off.
accurately
predicted
CS
4
additional
cases,
despite
misclassifying
20
VD,
resulting
in
6.0%
decrease
average
accuracy
compared
Hence,
integrating
into
latter
can
be
new
development
assisting
counseling.
Quality in Sport,
Год журнала:
2025,
Номер
37, С. 57301 - 57301
Опубликована: Янв. 14, 2025
Introduction
and
objective:
Breast
cancer
is
the
most
diagnosed
second
leading
cause
of
deaths
in
women
globally,
with
rising
cases
mortality.
Early
detection
via
mammography,
ultrasound,
or
MRI
vital,
ultrasound
excelling
dense
breast
tissue
due
to
its
safety
accuracy.Review
methods:
A
literature
review
utilizing
databases
like
Scopus,
Google
Scholar,
PubMed,
keywords
such
as
"AI
use
radiology"
"BI-RADS
scale"
underscores
need
for
advancements
understanding
managing
graft
rejection.Brief
knowledge
status:
AI
develops
systems
that
simulate
human
intelligence,
imaging
by
detecting
patterns
providing
accurate
results.
Machine
learning
(ML)
deep
(DL)
drive
advances,
DL's
CNNs
image
analysis.
aids
BI-RADS
lesion
classification,
detection,
lymph
node
analysis,
treatment
response
prediction,
often
surpassing
radiologists.
Its
future
relies
on
real-world
validation,
improved
outcomes,
clinical
integration.Discussion:
The
integration
artificial
intelligence
(AI)
into
marks
a
transformative
leap
diagnostic
radiology,
enhancing
precision,
efficiency,
scalability.
Driven
machine
(DL),
excels
analyzing
complex
datasets.
However,
adoption
requires
addressing
key
considerations
nuanced
approach.Summary:
In
conclusion,
holds
immense
promise
imaging,
poised
redefine
field
through
enhanced
capabilities
utility.
Continued
validation
efforts
will
ensure
broader
acceptance
sustained
impact
medical
imaging.
