In
order
to
improve
diagnostic
precision,
this
study
offers
an
original
framework
for
multimodal
health
image
fusion
that
makes
use
of
cloud-based
deep
learning.
A
descriptive
design
is
used
with
additional
information
gathering,
utilizing
approach
deductive
along
interpretivist
perspective.
The
convolutional
neural
network-based
suggested
model
assessed
in
terms
its
scalability,
effectiveness,
and
stored
the
cloud
computational
effectiveness.
When
results
are
compared
current
techniques,
they
demonstrate
higher
precision.
model's
possible
consequences
on
healthcare
highlighted
by
interpretation
clinical
utility.
Limitations
addressed
through
critical
analysis,
suggestions
include
enhancing
model,
investigating
edge
computing,
taking
ethical
issues
into
account.
Subsequent
efforts
ought
concentrate
refining
growing
dataset,
guaranteeing
interpretability.
VFAST Transactions on Software Engineering,
Journal Year:
2023,
Volume and Issue:
11(2), P. 80 - 93
Published: June 27, 2023
Lung
cancer
is
a
highly
lethal
disease
affecting
both
males
and
females
nowadays.
It
essential
to
identify
accurately
at
the
initial
stage
of
lung
cancer.
However,
diagnosing
remains
challenging
task
for
pathologists.
Among
various
techniques
available,
CT
Scan
plays
crucial
role
in
early
identification
treatment
For
classification
cancer,
lots
developing
are
used
medical
research
field.
Unfortunately,
these
achieve
less
accuracy
due
poor
learning
rate,
class
imbalance,
data
overfitting,
vanishing
gradient.
develop
an
accurate,
faster,
well-organized
system
To
address
issues,
efficient
framework
called
LCCNet
presented,
which
transfer
applied
pre-trained
Densely
Connected
Convolutional
Networks
(DenseNet-121)
CNN
model.
classify
The
most
common
augmentation
approaches
deal
with
large
dataset.
utilized
Scans
accurate
assess
performance,
model
utilizes
evaluation
metrics
such
as
accuracy,
F1-score,
precision,
recall
along
confusion
matrix
validate
efficiency
classification.
Furthermore,
this
study
also
compares
several
current
studies
proposed
terms
measures,
showing
that
attained
greatest
99%
when
compared
existing
fields
study.
best
our
knowledge,
methodology
performs
efficiently.
In
order
to
improve
diagnostic
precision,
this
study
offers
an
original
framework
for
multimodal
health
image
fusion
that
makes
use
of
cloud-based
deep
learning.
A
descriptive
design
is
used
with
additional
information
gathering,
utilizing
approach
deductive
along
interpretivist
perspective.
The
convolutional
neural
network-based
suggested
model
assessed
in
terms
its
scalability,
effectiveness,
and
stored
the
cloud
computational
effectiveness.
When
results
are
compared
current
techniques,
they
demonstrate
higher
precision.
model's
possible
consequences
on
healthcare
highlighted
by
interpretation
clinical
utility.
Limitations
addressed
through
critical
analysis,
suggestions
include
enhancing
model,
investigating
edge
computing,
taking
ethical
issues
into
account.
Subsequent
efforts
ought
concentrate
refining
growing
dataset,
guaranteeing
interpretability.
