Prokaryotes,
which
comprise
both
bacteria
and
archaea,
are
found
everywhere
around
us.
Their
detecting,
counting,
classification
is
still
a
hard
matter.
This
paper's
main
aim
the
prokaryotes
using
frequency
chaos
representation
(FCGR)
image
convolutional
neural
networks
(CNN).
First,
we
mapped
each
archaebacterial
DNA
sequence
by
FCGR
images
with
different
orders.
Next,
apply
binary
CNN
technique.
Our
model
has
shown
precision
that
exceeds
92%.
result
shows
proposed
method's
performance.
Expert Systems,
Journal Year:
2022,
Volume and Issue:
unknown
Published: Dec. 16, 2022
Abstract
The
classification
of
tumours
into
benign
and
malignant
continues
to
date
be
a
very
relevant
significant
research
topic
in
the
cancer
domain.
With
advent
Computer
Vision
rapid
developments
fields
deep
learning,
as
well
medical
devices
instruments,
researchers
are
therefore
utilizing
state‐of‐the‐art
learning
architectures
discover
patterns
image
data
thereby
use
this
information
detect
classify
them
or
malignant.
In
paper,
we
propose
custom
architecture,
Inception‐ResNet
v2
for
ovarian
two
categories
based
on
dataset
with
validation
accuracy
97.5%
test
67%.
Furthermore,
quantum
convolutional
neural
network
(QCNN)
was
also
implemented
an
92%
dataset.
Biomolecules,
Journal Year:
2023,
Volume and Issue:
13(7), P. 1090 - 1090
Published: July 7, 2023
Humankind
is
witnessing
a
gradual
increase
in
cancer
incidence,
emphasizing
the
importance
of
early
diagnosis
and
treatment,
follow-up
clinical
protocols.
Oral
or
mouth
cancer,
categorized
under
head
neck
cancers,
requires
effective
screening
for
timely
detection.
This
study
proposes
framework,
OralNet,
oral
detection
using
histopathology
images.
The
research
encompasses
four
stages:
(i)
Image
collection
preprocessing,
gathering
preparing
images
analysis;
(ii)
feature
extraction
deep
handcrafted
scheme,
extracting
relevant
features
from
learning
techniques
traditional
methods;
(iii)
reduction
artificial
hummingbird
algorithm
(AHA)
concatenation:
Reducing
dimensionality
AHA
concatenating
them
serially
(iv)
binary
classification
performance
validation
with
three-fold
cross-validation:
Classifying
as
healthy
squamous
cell
carcinoma
evaluating
framework’s
cross-validation.
current
examined
whole
slide
biopsy
at
100×
400×
magnifications.
To
establish
OralNet’s
validity,
3000
cropped
resized
were
reviewed,
comprising
1500
Experimental
results
OralNet
achieved
an
accuracy
exceeding
99.5%.
These
findings
confirm
significance
proposed
technique
detecting
presence
histology
slides.
Engineering Technology & Applied Science Research,
Journal Year:
2025,
Volume and Issue:
15(1), P. 19214 - 19220
Published: Feb. 1, 2025
The
Siddha
and
Ayurveda
traditional
Indian
medicine
practices
utilize
non-invasive
diagnostic
methods,
such
as
Neikuri
Taila
Bindu
Pariksha,
for
patient
diagnosis
through
urine
analysis.
While
these
methods
have
proven
effective
centuries,
their
accuracy
highly
depends
on
the
subjective
experience
of
practitioners.
To
address
this
limitation,
study
explores
use
advanced
image
processing
techniques
deep
learning,
specifically
Convolutional
Neural
Networks
(CNNs),
to
automate
enhance
This
utilized
five
pre-trained
CNN
models,
namely
DenseNet,
ResNet,
VGG-19,
Inception,
EfficientNet,
a
dataset
images
acquired
from
medical
institute,
standardize
improve
diagnosis.
comparative
evaluation
revealed
DenseNet
best-performing
model,
achieving
classification
93.33%,
while
Inception
v3
followed
with
90.5%.
highlights
potential
integrating
modern
neural
networks
practices,
paving
way
more
objective,
efficient,
accessible
healthcare
solutions
in
medicine.
Research Square (Research Square),
Journal Year:
2025,
Volume and Issue:
unknown
Published: April 4, 2025
AbstractBackground:
Artificial
intelligence
(AI)
is
increasingly
applied
in
diagnostic
neurosurgery,
enhancing
precision
and
decision-making
neuro-oncology,
vascular,
functional,
spinal
subspecialties.
Despite
its
potential,
variability
outcomes
necessitates
a
systematic
review
of
performance
applicability.
Methods:
A
comprehensive
search
PubMed,
Cochrane
Library,
Embase,
CNKI,
ClinicalTrials.gov
was
conducted
from
January
2020
to
2025.
Inclusion
criteria
comprised
studies
utilizing
AI
for
reporting
quantitative
metrics.
Studies
were
excluded
if
they
focused
on
non-human
subjects,
lacked
clear
metrics,
or
did
not
directly
relate
applications
neurosurgery.
Risk
bias
assessed
using
the
PROBAST
tool.
This
study
registered
PROSPERO,
number
CRD42025631040
26th,
Results:
Within
186
studies,
neural
networks
(29%)
hybrid
models
(49%)
dominated.
categorised
into
neuro-oncology
(52.69%),
vascular
neurosurgery
(19.89%),
functional
(16.67%),
(11.83%).
Median
accuracies
exceeded
85%
most
categories,
with
achieving
high
accuracy
tumour
detection,
grading,
segmentation.
Vascular
excelled
stroke
intracranial
haemorrhage
median
AUC
values
97%.
Functional
showed
promising
results,
though
sensitivity
specificity
underscores
need
standardised
datasets
validation.
Discussion:
The
review’s
limitations
include
lack
data
weighting,
absence
meta-analysis,
limited
collection
timeframe,
quality,
risk
some
studies.
Conclusion:
AI
shows
potential
improving
across
neurosurgical
domains.
Models
used
stroke,
ICH,
aneurysm
conditions
such
as
Parkinson’s
disease
epilepsy
demonstrate
results.
However,
sensitivity,
specificity,
further
research
model
refinement
ensure
clinical
viability
effectiveness.
