Emerging Trends in Deep Learning for Early Alzheimer's Disease Diagnosis and Classification: A Comprehensive Review
S. Gokul Amuthan,
No information about this author
Naveen Kumar
No information about this author
International Journal of Computational and Experimental Science and Engineering,
Journal Year:
2025,
Volume and Issue:
11(1)
Published: Jan. 4, 2025
Alzheimer's
Disease
(AD),
a
progressive
neurodegenerative
disorder,
manifests
as
cognitive
decline
and
memory
loss,
significantly
impacting
individuals'
lives
healthcare
systems
globally.
Early
diagnosis
intervention
are
crucial
for
improving
patient
outcomes
managing
the
disease
effectively.
Recent
advancements
in
deep
learning
(DL)
have
shown
substantial
promise
medical
image
classification
early
AD
diagnosis.
This
survey
evaluates
state-of-the-art
DL
techniques,
including
hybrid
models,
Recurrent
Neural
Networks
(RNNs),
Convolutional
(CNNs),
applied
across
imaging
modalities
such
computed
tomography
(CT),
positron
emission
(PET),
magnetic
resonance
(MRI).
It
emphasizes
their
performance,
accuracy,
computational
efficiency
while
addressing
critical
challenges
like
need
large
annotated
datasets,
overfitting,
model
interpretability.
Furthermore,
explores
how
could
revolutionize
identifies
future
research
directions
to
bridge
existing
gaps,
aiming
improve
detection
personalized
diagnostic
approaches
individuals
with
AD.
Language: Английский
Exploring the role of Convolutional Neural Networks (CNN) in dental radiography segmentation: A comprehensive Systematic Literature Review
Engineering Applications of Artificial Intelligence,
Journal Year:
2024,
Volume and Issue:
133, P. 108510 - 108510
Published: May 11, 2024
Language: Английский
Advanced Implementation of Convolutional Neural Networks for Alzheimer's Diseases Diagnosis
SN Computer Science,
Journal Year:
2025,
Volume and Issue:
6(4)
Published: March 28, 2025
Language: Английский
Enhancing multi-class neurodegenerative disease classification using deep learning and explainable local interpretable model-agnostic explanations
Frontiers in Medicine,
Journal Year:
2025,
Volume and Issue:
12
Published: April 1, 2025
Alzheimer's
disease
(AD)
and
Parkinson's
(PD)
are
two
of
the
most
prevalent
neurodegenerative
disorders,
necessitating
accurate
diagnostic
approaches
for
early
detection
effective
management.
This
study
introduces
deep
learning
architectures,
Residual-based
Attention
Convolutional
Neural
Network
(RbACNN)
Inverted
(IRbACNN),
designed
to
enhance
medical
image
classification
AD
PD
diagnosis.
By
integrating
self-attention
mechanisms,
these
models
improve
feature
extraction,
interpretability,
address
limitations
traditional
methods.
Additionally,
explainable
AI
(XAI)
techniques
incorporated
provide
model
transparency
clinical
trust
in
automated
diagnoses.
Preprocessing
steps
such
as
histogram
equalization
batch
creation
applied
optimize
quality
balance
dataset.
The
proposed
achieved
an
outstanding
accuracy
99.92%.
results
demonstrate
that
combination
with
XAI,
facilitate
precise
diagnosis,
thereby
contributing
reducing
global
burden
diseases.
Language: Английский
From Handwriting Analysis to Alzheimer’s Disease Prediction: An Experimental Comparison of Classifier Combination Methods
Lecture notes in computer science,
Journal Year:
2024,
Volume and Issue:
unknown, P. 334 - 351
Published: Jan. 1, 2024
Language: Английский
Alzheimer’s Disease and Mild Cognitive Impairment Detection Using sMRI With Efficient Receptive Field and Enhanced Multi-Axis Attention Fusion
IEEE Access,
Journal Year:
2024,
Volume and Issue:
12, P. 100848 - 100861
Published: Jan. 1, 2024
Deep
neural
networks
have
shown
promising
results
in
the
analysis
of
structural
magnetic
resonance
imaging
(sMRI)
data
for
diagnosis
dementia,
particularly
Alzheimer's
disease
(AD).
Different
regions
brain
diverse
structures
that
are
linked
to
specific
functions,
which
could
account
variability
disease-related
changes
observed
sMRI
scans
these
areas.
Understanding
overall
characteristics
is
important
since
current
popular
convolutional
(CNN)
deep
learning
do
not
consider
interconnection
voxels.
Vision
transformers
effectiveness
identifying
long-distance
connections
brain,
has
led
their
success
applications
such
as
detection.
However,
image
noise
and
limited
scalability
self-attention
mechanisms
relation
size
hindered
widespread
use
advanced
analysis.
To
enhance
information
retention
reduce
network
complexity,
this
study
presents
a
novel
adaptable
efficient
receptive
field
feature
extraction
network.
Moreover,
an
attention
mechanism
with
both
local
grid
block
dilated
global
module
been
incorporated
highlight
AD.
Next,
more
improved
hierarchical
inverted
residual
feed
forward
place
multi-layer
perceptron
suggested
characterization
features
through
integration
from
lower
higher
layers.
Finally,
average
pooling
$1\times
1$
convolution
used
dimensionality,
non-linearity,
allow
channel
interactions
maps
before
being
input
into
classification
head.
The
achieved
high
performance
various
scenarios,
accuracies
97.29%
AD
vs.
HC
94.79%
MCI
using
ADNI
experimental
datasets.
Language: Английский
Deep Learning Model to Evaluate Alzheimer's disease Through Multi-View Clustering
Sneha Nimbare,
No information about this author
Priyanka Paygude,
No information about this author
Amol Dhumane
No information about this author
et al.
International Research Journal of Multidisciplinary Technovation,
Journal Year:
2024,
Volume and Issue:
unknown, P. 33 - 46
Published: Dec. 30, 2024
Early
diagnosis
of
Alzheimer's
disease
(AD)
plays
a
crucial
role
in
the
development
and
effectiveness
interventions,
neuroimaging
stands
out
as
an
up-and-coming
field
for
initial
identification
disease.
Earlier
models
utilized
various
methods
to
analyze
images
disease,
such
deep
learning
or
unsupervised
matrix
factorization
processes.
Neither
these
techniques
alone
can
produce
satisfactory
results
while
clustering
multi-view
photos
This
motivates
our
research
create
model
obtaining
most
important
factors
from
MRI
classifying
brain
into
different
stages.
To
achieve
optimal
clustering,
proposed
integrates
technique
(Channel
Boost-Convolution
Neural
Network)
with
inverse
method,
forming
ensemble
approach.
The
experiment
analyzes
several
evaluate
implemented
performance
RMSE,
which
are
about
2.32
better
than
compared
models.
show
that
combining
Inverse
image
works
well,
Transformers
further
improve
learning.
Language: Английский