INTERNATIONAL JOURNAL OF NEXT-GENERATION COMPUTING,
Journal Year:
2024,
Volume and Issue:
unknown
Published: Dec. 17, 2024
In
low-
and
middle-income
countries,
oral
cancer
is
becoming
more
common.
One
factor
delaying
the
discovery
of
in
rural
areas
a
lack
resources.
To
stop
disease
from
spreading,
it
essential
to
quickly
obtain
information
about
any
cancers.
Therefore,
carry
out
early
identification
before
spreads.
Primary
screening
maintained
this
study.
Furthermore,
deep
neural
network-based
automated
methods
were
used
produce
complex
patterns
address
challenging
issue
assessing
infection.
The
goal
work
develop
an
Android
application
that
uses
network
categorize
photos
into
four
groups:
erythroplakia,
leukoplakia,
ulcer,
normal
mouth.
Convolutional
networks
K-fold
validation
processes
are
study’s
methodology
create
customized
Deep
Oral
Augmented
Model
(DOAM).
Data
augmentation
techniques
including
shearing,
scaling,
rotation,
flipping
pre-process
images.
A
convolutional
then
extract
features
images
Optimal
configurations
max
pooling
layers,
dropout,
activation
functions
have
resulted
attainment
maximum
accuracies.
By
using
”ELU”
function
conjunction
with
RMSProp
as
optimizer,
model
achieves
96%
accuracy,
precision,
F1
score,
68%
testing
accuracy.
deployed
TensorFlow
Lite
application.
Current Oncology,
Journal Year:
2024,
Volume and Issue:
31(9), P. 5255 - 5290
Published: Sept. 6, 2024
Artificial
intelligence
(AI)
is
revolutionizing
head
and
neck
cancer
(HNC)
care
by
providing
innovative
tools
that
enhance
diagnostic
accuracy
personalize
treatment
strategies.
This
review
highlights
the
advancements
in
AI
technologies,
including
deep
learning
natural
language
processing,
their
applications
HNC.
The
integration
of
with
imaging
techniques,
genomics,
electronic
health
records
explored,
emphasizing
its
role
early
detection,
biomarker
discovery,
planning.
Despite
noticeable
progress,
challenges
such
as
data
quality,
algorithmic
bias,
need
for
interdisciplinary
collaboration
remain.
Emerging
innovations
like
explainable
AI,
AI-powered
robotics,
real-time
monitoring
systems
are
poised
to
further
advance
field.
Addressing
these
fostering
among
experts,
clinicians,
researchers
crucial
developing
equitable
effective
applications.
future
HNC
holds
significant
promise,
offering
potential
breakthroughs
diagnostics,
personalized
therapies,
improved
patient
outcomes.
Diagnostics,
Journal Year:
2025,
Volume and Issue:
15(3), P. 280 - 280
Published: Jan. 24, 2025
Background/Objectives:
Oral
cancer,
the
sixth
most
common
cancer
worldwide,
is
linked
to
smoke,
alcohol,
and
HPV.
This
scoping
analysis
summarized
early-onset
oral
diagnosis
applications
address
a
gap.
Methods:
A
review
identified,
selected,
synthesized
AI-based
diagnosis,
screening,
prognosis
literature.
The
verified
study
quality
relevance
using
frameworks
inclusion
criteria.
full
search
included
keywords,
MeSH
phrases,
Pubmed.
AI
were
tested
through
data
extraction
synthesis.
Results:
outperforms
traditional
analysis,
prediction
approaches.
Medical
pictures
can
be
used
diagnose
with
convolutional
neural
networks.
Smartphone
AI-enabled
telemedicine
make
screening
affordable
accessible
in
resource-constrained
areas.
methods
predict
risk
patient
data.
also
arrange
treatment
histopathology
images
heterogeneity,
restricted
longitudinal
research,
clinical
practice
inclusion,
ethical
legal
difficulties.
Future
potential
includes
uniform
standards,
long-term
investigations,
regulatory
frameworks,
healthcare
professional
training.
Conclusions:
may
transform
treatment.
It
develop
early
detection,
modelling,
imaging
phenotypic
change,
prognosis.
approaches
should
standardized,
longitudinally,
practical
issues
related
real-world
deployment
addressed.
Frontiers in Oral Health,
Journal Year:
2025,
Volume and Issue:
6
Published: March 10, 2025
Oral
cavity
cancer
is
associated
with
high
morbidity
and
mortality,
particularly
advanced
stage
diagnosis.
cancer,
typically
squamous
cell
carcinoma
(OSCC),
often
preceded
by
oral
potentially
malignant
disorders
(OPMDs),
which
comprise
eleven
variable
risks
for
transformation.
While
OPMDs
are
clinical
diagnoses,
conventional
exam
followed
biopsy
histopathological
analysis
the
gold
standard
diagnosis
of
OSCC.
There
vast
heterogeneity
in
presentation
OPMDs,
possible
visual
similarities
to
early-stage
OSCC
or
even
various
benign
mucosal
abnormalities.
The
diagnostic
challenge
OSCC/OPMDs
compounded
non-specialist
primary
care
setting.
has
been
significant
research
interest
technology
assist
OSCC/OPMDs.
Artificial
intelligence
(AI),
enables
machine
performance
human
tasks,
already
shown
promise
several
domains
medical
diagnostics.
Computer
vision,
field
AI
dedicated
data,
over
past
decade
applied
photographs
Various
methodological
concerns
limitations
may
be
encountered
literature
on
OSCC/OPMD
image
analysis.
This
narrative
review
delineates
current
landscape
photograph
navigates
limitations,
issues,
workflow
implications
this
field,
providing
context
future
considerations.
Scientific Reports,
Journal Year:
2025,
Volume and Issue:
15(1)
Published: Feb. 15, 2025
This
study
presents
a
robust
approach
for
continuous
food
recognition
essential
nutritional
research,
leveraging
advanced
computer
vision
techniques.
The
proposed
method
integrates
Mutually
Guided
Image
Filtering
(MuGIF)
to
enhance
dataset
quality
and
minimize
noise,
followed
by
feature
extraction
using
the
Visual
Geometry
Group
(VGG)
architecture
intricate
visual
analysis.
A
hybrid
transformer
model,
combining
Vision
Transformer
Swin
variants,
is
introduced
capitalize
on
their
complementary
strengths.
Hyperparameter
optimization
performed
Improved
Discrete
Bat
Algorithm
(IDBA),
resulting
in
highly
accurate
efficient
classification
system.
Experimental
results
highlight
superior
performance
of
achieving
accuracy
99.83%,
significantly
outperforming
existing
methods.
underscores
potential
architectures
preprocessing
techniques
advancing
systems,
offering
enhanced
efficiency
practical
applications
dietary
monitoring
personalized
nutrition
recommendations.
Frontiers in Oncology,
Journal Year:
2025,
Volume and Issue:
15
Published: Feb. 18, 2025
Deep
learning
(DL)
algorithms
generally
require
full
supervision
of
annotating
the
region
interest
(ROI),
a
process
that
is
both
labor-intensive
and
susceptible
to
bias.
We
aimed
develop
weakly
supervised
algorithm
differentiate
between
benign
malignant
breast
tumors
in
ultrasound
images
without
image
annotation.
developed
validated
models
using
two
publicly
available
datasets:
(BUSI)
GDPH&SYSUCC
datasets.
After
removing
poor
quality
images,
total
3049
were
included,
divided
into
classes:
(N
=
1320
images)
1729
images).
Weakly-supervised
DL
implemented
with
four
networks
(DenseNet121,
ResNet50,
EffientNetb0,
Vision
Transformer)
trained
2136
unannotated
images.
609
304
used
for
validation
test
sets,
respectively.
Diagnostic
performances
calculated
as
area
under
receiver
operating
characteristic
curve
(AUC).
Using
class
activation
map
interpret
prediction
results
algorithms.
The
DenseNet121
model,
utilizing
complete
inputs
ROI
annotations,
demonstrated
superior
diagnostic
performance
distinguishing
nodules
when
compared
EfficientNetb0,
Transformer
models.
achieved
highest
AUC,
values
0.94
on
set
0.93
set,
significantly
surpassing
other
across
datasets
(all
P
<
0.05).
model
this
study
feasibility
diagnosis
tumor
showed
good
capabilities
differential
diagnosis.
This
may
help
radiologists,
especially
novice
doctors,
improve
accuracy
ultrasound.