Technologies,
Год журнала:
2024,
Номер
12(10), С. 190 - 190
Опубликована: Окт. 3, 2024
The
precise
and
prompt
identification
of
skin
cancer
is
essential
for
efficient
treatment.
Variations
in
colour
within
lesions
are
critical
signs
malignancy;
however,
discrepancies
imaging
conditions
may
inhibit
the
efficacy
deep
learning
models.
Numerous
previous
investigations
have
neglected
this
problem,
frequently
depending
on
features
from
a
singular
layer
an
individual
model.
This
study
presents
new
hybrid
model
that
integrates
discrete
cosine
transform
(DCT)
with
multi-convolutional
neural
network
(CNN)
structures
to
improve
classification
cancer.
Initially,
DCT
applied
dermoscopic
images
enhance
correct
distortions
these
images.
After
that,
several
CNNs
trained
separately
Next,
obtained
two
layers
each
CNN.
proposed
consists
triple
feature
fusion.
initial
phase
involves
employing
wavelet
(DWT)
merge
multidimensional
attributes
first
CNN,
which
lowers
their
dimension
provides
time–frequency
representation.
In
addition,
second
concatenated.
Afterward,
subsequent
fusion
stage,
merged
first-layer
combined
second-layer
create
effective
vector.
Finally,
third
bi-layer
various
integrated.
Through
process
training
multiple
both
original
photos
DCT-enhanced
images,
retrieving
separate
layers,
incorporating
CNNs,
comprehensive
representation
generated.
Experimental
results
showed
96.40%
accuracy
after
trio-deep
shows
merging
can
diagnostic
accuracy.
outperforms
CNN
models
most
recent
studies,
thus
proving
its
superiority.
IEEE Access,
Год журнала:
2023,
Номер
11, С. 135175 - 135184
Опубликована: Янв. 1, 2023
Cervical
cancer
(CC)
is
the
fourth
most
popular
affecting
women
worldwide.
Mortality
and
incidence
rates
can
be
consistently
enhancing,
particularly
in
emerging
countries,
because
of
lack
screening
services,
awareness,
restricted
qualified
experts.
CC
has
screened
utilizing
human
papillomavirus
(HPV)
test,
Papanicolaou
(Pap)
histopathology
visual
inspection
after
application
acetic
acid
(VIA).
Intra-
Inter-observer
variability
take
place
manual
analysis
method,
resulting
misdiagnosis.
Previous
studies
have
exploited
either
deep
learning
(DL)
or
machine
(ML)
approaches,
preceding
one
could
not
efficient
as
it
needs
segmentation
attaining
hand-crafted
features
that
utilize
critical
stage.
Artificial
Intelligence
(AI)
based
computer-aided
diagnoses
(CAD)
methods
are
generally
explored
for
identifying
enhancing
standard
testing
method.
This
manuscript
offers
an
Improved
Bald
Eagle
Search
Optimization
with
Deep
Learning
Cancer
Detection
Classification
(IBESODL-CCDC)
algorithm.
The
drive
IBESODL-CCDC
algorithm
lies
automated
classification
detection
CC.
In
presented
technique,
a
contrast
enhancement
process
takes
to
enhance
image
qualities.
addition,
technique
utilizes
modified
LeNet
model
feature
extraction
model.
For
detection,
applies
attention-based
long
short-term
memory
(ALSTM)
network.
A
wide-ranging
experiment
was
applied
validate
greater
outcome
technique.
experimental
values
highlight
remarkable
performance
other
recent
systems.
The
conventional
method
of
categorizing
cervical
cancer
types
relies
heavily
on
the
expertise
pathologists,
which
is
associated
with
a
lower
degree
precision.
utilization
colposcopy
an
essential
element
in
prevention
cancer.
Colposcopy
has
been
crucial
component
reduction
frequency
and
humanity
rates
over
past
five
decades,
conjunction
precancer
screening
treatment.
rise
workload
resulted
reduced
diagnostic
efficiency
misdiagnosis
during
vision
screening.
convolutional
neural
network
(CNN)
model
medical
image
processing
demonstrated
its
superior
performance
type
within
realm
cavernous
learning.
present
study
puts
forth
two
architectures
based
deep
learning
for
identification
through
analysis
images.
models
employed
this
research
are
VGG19
(TL)
Ensemble
Network
(CYENET).
as
transfer
approach
implemented
CNN
architecture
purposes.
developed
novel
automatic
classification
cancers
from
model's
precision,
selectivity,
responsiveness
evaluated.
exhibited
accuracy
70.3%.
outcomes
moderately
satisfactory.
kappa
score
VGG-19
perfect
inferred
that
falls
moderate
category.
findings
experiment
indicate
CYENET
noteworthy
levels
sensitivity,
specificity,
scores,
specifically,
90.4%,
95.2%,
88%,
correspondingly.
exhibits
enhanced
90.1%,
surpassing
by
10%.
Technologies,
Год журнала:
2024,
Номер
12(10), С. 190 - 190
Опубликована: Окт. 3, 2024
The
precise
and
prompt
identification
of
skin
cancer
is
essential
for
efficient
treatment.
Variations
in
colour
within
lesions
are
critical
signs
malignancy;
however,
discrepancies
imaging
conditions
may
inhibit
the
efficacy
deep
learning
models.
Numerous
previous
investigations
have
neglected
this
problem,
frequently
depending
on
features
from
a
singular
layer
an
individual
model.
This
study
presents
new
hybrid
model
that
integrates
discrete
cosine
transform
(DCT)
with
multi-convolutional
neural
network
(CNN)
structures
to
improve
classification
cancer.
Initially,
DCT
applied
dermoscopic
images
enhance
correct
distortions
these
images.
After
that,
several
CNNs
trained
separately
Next,
obtained
two
layers
each
CNN.
proposed
consists
triple
feature
fusion.
initial
phase
involves
employing
wavelet
(DWT)
merge
multidimensional
attributes
first
CNN,
which
lowers
their
dimension
provides
time–frequency
representation.
In
addition,
second
concatenated.
Afterward,
subsequent
fusion
stage,
merged
first-layer
combined
second-layer
create
effective
vector.
Finally,
third
bi-layer
various
integrated.
Through
process
training
multiple
both
original
photos
DCT-enhanced
images,
retrieving
separate
layers,
incorporating
CNNs,
comprehensive
representation
generated.
Experimental
results
showed
96.40%
accuracy
after
trio-deep
shows
merging
can
diagnostic
accuracy.
outperforms
CNN
models
most
recent
studies,
thus
proving
its
superiority.
