Algorithms,
Journal Year:
2024,
Volume and Issue:
17(7), P. 309 - 309
Published: July 12, 2024
Cervical
cancer
ranks
among
the
leading
causes
of
mortality
in
women
worldwide,
underscoring
critical
need
for
early
detection
to
ensure
patient
survival.
While
Pap
smear
test
is
widely
used,
its
effectiveness
hampered
by
inherent
subjectivity
cytological
analysis,
impacting
sensitivity
and
specificity.
This
study
introduces
an
innovative
methodology
detecting
tracking
precursor
cervical
cells
using
SIFT
descriptors
video
sequences
captured
with
mobile
devices.
More
than
one
hundred
digital
images
were
analyzed
from
Papanicolaou
smears
provided
State
Public
Health
Laboratory
Michoacán,
Mexico,
along
over
1800
unique
examples
cells.
enabled
real-time
correspondence
cells,
yielding
results
demonstrating
98.34%
accuracy,
98.3%
precision,
98.2%
recovery
rate,
F-measure
98.05%.
These
methods
meticulously
optimized
showcasing
significant
potential
enhance
accuracy
efficiency
detection.
Multimedia Tools and Applications,
Journal Year:
2024,
Volume and Issue:
83(30), P. 75343 - 75367
Published: Feb. 16, 2024
Abstract
Cervical
cancer
is
a
prevalent
disease
affecting
the
cervix
cells
in
women
and
one
of
leading
causes
mortality
for
globally.
The
Pap
smear
test
determines
risk
cervical
by
detecting
abnormal
cells.
Early
detection
diagnosis
this
can
effectively
increase
patient’s
survival
rate.
advent
artificial
intelligence
facilitates
development
automated
computer-assisted
diagnostic
systems,
which
are
widely
used
to
enhance
screening.
This
study
emphasizes
segmentation
classification
various
cell
types.
An
intuitive
but
effective
technique
segment
nucleus
cytoplasm
from
histopathological
images.
Additionally,
handcrafted
features
include
different
properties
generated
distinct
area.
Two
feature
rankings
techniques
conducted
evaluate
study’s
significant
set.
Feature
analysis
identifies
critical
pathological
then
divides
them
into
30,
40,
50
sets
features.
Furthermore,
graph
dataset
constructed
using
strongest
correlated
features,
prioritizes
relationship
between
robust
convolution
network
(GCN)
introduced
efficiently
predict
proposed
model
obtains
sublime
accuracy
99.11%
40-feature
set
SipakMed
dataset.
outperforms
existing
study,
performing
both
simultaneously,
conducting
an
in-depth
analysis,
attaining
maximum
efficiently,
ensuring
interpretability
model.
To
validate
model’s
outcome,
we
tested
it
on
Herlev
highlighted
its
robustness
98.18%.
results
methodology
demonstrate
dependability
effectively,
early
stages
upholding
significance
lives
women.
Meta-Radiology,
Journal Year:
2023,
Volume and Issue:
1(3), P. 100045 - 100045
Published: Nov. 1, 2023
The
emergence
of
artificial
general
intelligence
(AGI)
is
transforming
radiation
oncology.
As
prominent
vanguards
AGI,
large
language
models
(LLMs)
such
as
GPT-4
and
PaLM
2
can
process
extensive
texts
vision
(LVMs)
the
Segment
Anything
Model
(SAM)
imaging
data
to
enhance
efficiency
precision
therapy.
This
paper
explores
full-spectrum
applications
AGI
across
oncology
including
initial
consultation,
simulation,
treatment
planning,
delivery,
verification,
patient
follow-up.
fusion
with
LLMs
also
creates
powerful
multimodal
that
elucidate
nuanced
clinical
patterns.
Together,
promises
catalyze
a
shift
towards
data-driven,
personalized
However,
these
should
complement
human
expertise
care.
provides
an
overview
how
transform
elevate
standard
care
in
oncology,
key
insight
being
AGI's
ability
exploit
at
scale.
Cureus,
Journal Year:
2025,
Volume and Issue:
unknown
Published: Feb. 4, 2025
Cervical
cancer
remains
one
of
the
leading
causes
mortality
among
women
worldwide,
and
its
early
detection
is
crucial
to
improve
survival
rates.
While
a
Pap
smear
widely
used
as
diagnostic
tool,
it
has
limitations
in
sensitivity
specificity
due
inherent
subjectivity
cytological
analysis.
This
study
proposes
methodology
for
cervical
cell
segmentation
extraction
based
on
Laplacian
Gaussian
(LoG)
algorithm,
which
enables
generation
regions
interest
detect
segment
cells
precisely
cytology
samples.
Over
2,000
digital
images
slides
were
analyzed,
derived
from
500
provided
by
State
Public
Health
Laboratory
Michoacán,
México.
The
dataset
results
demonstrated
an
accuracy
96.5%,
recall
rate
99.2%,
F-measure
97.8%.
Furthermore,
was
optimized
real-time
analysis,
allowing
efficient
their
morphological
variations.
not
only
significantly
improves
efficiency
but
also
high
potential
application
other
experiments
that
require
precise
despite
In
this
regard,
offers
adaptable
versatile
approach,
making
substantial
contribution
studies
establishing
itself
effective
process
extract
automatically
real
time.
Bioengineering,
Journal Year:
2025,
Volume and Issue:
12(2), P. 176 - 176
Published: Feb. 13, 2025
Artificial
Intelligence
(AI)
has
the
potential
to
revolutionize
cytopathology
by
enhancing
diagnostic
accuracy,
efficiency,
and
accessibility.
However,
implementation
of
AI
in
this
field
presents
significant
challenges
opportunities.
This
review
paper
explores
current
landscape
applications
cytopathology,
highlighting
critical
challenges,
including
data
quality
availability,
algorithm
development,
integration
standardization,
clinical
validation.
We
discuss
such
as
limitation
only
one
optical
section
z-stack
scanning,
complexities
associated
with
acquiring
high-quality
labeled
data,
intricacies
developing
robust
generalizable
models,
difficulties
integrating
tools
into
existing
laboratory
workflows.
The
also
identifies
substantial
opportunities
that
brings
cytopathology.
These
include
for
improved
accuracy
through
enhanced
detection
capabilities
consistent,
reproducible
results,
which
can
reduce
observer
variability.
AI-driven
automation
routine
tasks
significantly
increase
allowing
cytopathologists
focus
on
more
complex
analyses.
Furthermore,
serve
a
valuable
educational
tool,
augmenting
training
facilitating
global
health
initiatives
making
diagnostics
accessible
resource-limited
settings.
underscores
importance
addressing
these
harness
full
ultimately
improving
patient
care
outcomes.
Frontiers in Medical Technology,
Journal Year:
2025,
Volume and Issue:
7
Published: March 31, 2025
Cervical
cancer
remains
a
significant
health
challenge
around
the
globe,
with
particularly
high
prevalence
in
low-
and
middle-income
countries.
This
disease
is
preventable
curable
if
detected
early
stages,
making
regular
screening
critically
important.
cytology,
most
widely
used
method,
has
proven
highly
effective
reducing
cervical
incidence
mortality
income
However,
its
effectiveness
low-resource
settings
been
limited,
among
other
factors,
by
insufficient
diagnostic
infrastructure
shortage
of
trained
healthcare
personnel.
paper
introduces
development
low-cost
microscopy
platform
designed
to
address
these
limitations
enabling
automatic
reading
cytology
slides.
The
system
features
robotized
microscope
capable
slide
scanning,
autofocus,
digital
image
capture,
while
supporting
integration
artificial
intelligence
(AI)
algorithms.
All
at
production
cost
below
500
USD.
A
dataset
nearly
2,000
images,
captured
custom-built
covering
seven
distinct
cellular
types
relevant
cytologic
analysis,
was
created.
then
fine-tune
test
several
pre-trained
models
for
classifying
between
images
containing
normal
abnormal
cell
subtypes.
Most
tested
showed
good
performance
properly
cells,
sensitivities
above
90%.
Among
models,
MobileNet
demonstrated
highest
accuracy
detecting
types,
achieving
98.26%
97.95%,
specificities
88.91%
88.72%,
F-scores
96.42%
96.23%
on
validation
sets,
respectively.
results
indicate
that
might
be
suitable
model
real-world
deployment
platform,
offering
precision
efficiency
images.
presents
first
step
towards
promising
solution
improving
settings.
Research Square (Research Square),
Journal Year:
2025,
Volume and Issue:
unknown
Published: April 15, 2025
Abstract
Large
language
models
(LLMs)
and
large
vision-language
(LVLMs)
have
exhibited
near-human
levels
of
knowledge,
image
comprehension,
reasoning
abilities,
their
performance
has
undergone
evaluation
in
some
healthcare
domains.
However,
a
systematic
capabilities
cervical
cytology
screening
yet
to
be
conducted.
Here,
we
constructed
CCBench,
benchmark
dataset
dedicated
the
LLMs
LVLMs
screening,
developed
GPT-based
semi-automatic
pipeline
assess
six
(GPT-4,
Bard,
Claude-2.0,
LLaMa-2,
Qwen-Max,
ERNIE-Bot-4.0)
five
(GPT-4V,
Gemini,
LLaVA,
Qwen-VL,
ViLT)
on
this
dataset.
CCBench
comprises
773
question-answer
(QA)
pairs
420
visual-question-answer
(VQA)
triplets,
making
it
first
include
both
QA
VQA
data.
We
found
that
demonstrate
promising
accuracy
specialization
screening.
GPT-4
achieved
best
dataset,
with
an
70.5%
for
close-ended
questions
expert
score
7.1/10
open-ended
questions.
On
Gemini
highest
at
67.8%,
while
GPT-4V
attained
6.9/10
Besides,
revealed
varying
abilities
answering
across
different
topics
difficulty
levels.
remains
inferior
expertise
by
cytopathology
professionals,
risk
generating
misinformation
could
lead
potential
harm.
Therefore,
substantial
improvements
are
required
before
these
can
reliably
deployed
clinical
practice.
