International Journal of Scientific Research in Computer Science Engineering and Information Technology,
Год журнала:
2024,
Номер
10(6), С. 1258 - 1267
Опубликована: Дек. 5, 2024
Artificial
intelligence
is
revolutionizing
medical
imaging
and
diagnostics,
marking
a
transformative
era
in
healthcare
delivery.
This
comprehensive
article
explores
the
evolution
from
early
computer-aided
diagnosis
systems
to
sophisticated
deep-learning
architectures,
examining
their
impact
across
radiology,
pathology,
clinical
workflows.
The
covers
breakthrough
technologies,
including
vision
transformers,
multi-modal
integration,
explainable
AI
frameworks,
highlighting
contributions
improved
diagnostic
accuracy
efficiency.
encompasses
benefits
of
disease
detection,
workflow
optimization,
cost
reduction
while
addressing
crucial
challenges
regulatory
compliance,
ethical
considerations,
data
privacy.
Looking
ahead,
review
examines
emerging
trends
federated
learning,
infrastructure
requirements,
economic
implications
implementation
settings,
providing
insights
into
future
landscape
AI-driven
imaging.
International Journal of Scientific Research in Computer Science Engineering and Information Technology,
Год журнала:
2025,
Номер
11(1), С. 1007 - 1017
Опубликована: Янв. 20, 2025
This
technical
article
explores
the
evolution,
architecture,
and
implementation
challenges
of
multimodal
AI
systems,
which
represent
a
significant
advancement
in
artificial
intelligence.
The
how
these
systems
integrate
multiple
input
modalities
to
achieve
comprehensive
understanding
analysis
capabilities,
mirroring
human
cognitive
processes.
Through
detailed
system
architectures,
performance
metrics,
strategies,
we
investigate
current
state
across
various
applications,
from
virtual
assistants
healthcare
analytics.
covers
core
components,
data
synchronization
challenges,
resource
optimization
techniques,
future
directions
field,
providing
insights
into
both
theoretical
frameworks
practical
implementations.
Seminars in Nuclear Medicine,
Год журнала:
2025,
Номер
unknown
Опубликована: Фев. 1, 2025
Nuclear
medicine
has
continuously
evolved
since
its
beginnings,
constantly
improving
the
diagnosis
and
treatment
of
various
diseases.
The
integration
artificial
intelligence
(AI)
is
one
latest
revolutionizing
chapters,
promising
significant
advancements
in
diagnosis,
prognosis,
segmentation,
image
quality
enhancement,
theranostics.
Early
AI
applications
nuclear
focused
on
diagnostic
accuracy,
leveraging
machine
learning
algorithms
for
disease
classification
outcome
prediction.
Advances
deep
learning,
including
convolutional
more
recently
transformer-based
neural
networks,
have
further
enabled
precise
segmentation
as
well
low-dose
imaging,
patient-specific
dosimetry
personalized
treatment.
Generative
AI,
driven
by
large
language
models
diffusion
techniques,
now
allowing
process,
interpretation,
generation
complex
medical
images.
Despite
these
achievements,
challenges
such
data
scarcity,
heterogeneity,
ethical
concerns
remain
barriers
to
clinical
translation.
Addressing
issues
through
interdisciplinary
collaboration
will
pave
way
a
broader
adoption
medicine,
potentially
enhancing
patient
care
optimizing
therapeutic
outcomes.
Buildings,
Год журнала:
2024,
Номер
14(11), С. 3675 - 3675
Опубликована: Ноя. 19, 2024
The
accurate
prediction
of
dam
deformation
is
essential
for
ensuring
safe
and
efficient
operation
risk
management.
However,
the
nonlinear
relationships
between
time-varying
environmental
factors
pose
significant
challenges,
often
limiting
accuracy
conventional
deep
learning
models.
To
address
these
issues,
this
study
aimed
to
improve
predictive
interpretability
in
modeling
by
proposing
a
novel
LSTM
seq2seq
model
that
integrates
chaos-based
arithmetic
optimization
algorithm
(AOA)
an
attention
mechanism.
AOA
optimizes
model’s
learnable
parameters
utilizing
distribution
patterns
four
mathematical
operators,
further
enhanced
logistic
cubic
mappings,
avoid
local
optima.
mechanism,
placed
encoder
decoder
networks,
dynamically
quantifies
impact
influencing
on
deformation,
enabling
focus
most
relevant
information.
This
approach
was
applied
earth-rock
dam,
achieving
superior
performance
with
RMSE,
MAE,
MAPE
values
0.695
mm,
0.301
0.156%,
respectively,
outperforming
machine
weights
provide
insights
into
contributions
each
factor,
enhancing
interpretability.
holds
potential
real-time
monitoring
maintenance,
contributing
safety
resilience
infrastructure.
