The
brain
tumor
(BT)
is
a
severe
condition
caused
by
abnormal
cell
growth.
If
left
untreated,
the
BT
may
result
in
variety
of
harsh
conditions,
including
death.
As
consequence
significance
automatic
detection,
several
schemes
have
been
developed
and
implemented
literature
to
accurately
assess
BT.
We
propose
method
for
segmenting
images
from
MRI
slices
this
study.
This
proposal
includes
number
phases,
including;
(i)
collecting
resizing
images,
(ii)
enhancing
image
using
selected
scheme,
(iii)
ResUnet,
(iv)
evaluating
validating
performance.
study
examines
MRi
with
or
without
skull
region,
results
are
evaluated
separately.
Based
on
these
outcomes,
it
concluded
that
proposed
ResUnet
together
CLAHE
provides
significant
improvement
over
other
methods
concerning
Jaccard
(>92%),
Dice
(>95
%
),
accuracy
(>98%).
Mathematics,
Journal Year:
2023,
Volume and Issue:
11(19), P. 4189 - 4189
Published: Oct. 7, 2023
Brain
tumor
segmentation
in
medical
imaging
is
a
critical
task
for
diagnosis
and
treatment
while
preserving
patient
data
privacy
security.
Traditional
centralized
approaches
often
encounter
obstacles
sharing
due
to
regulations
security
concerns,
hindering
the
development
of
advanced
AI-based
applications.
To
overcome
these
challenges,
this
study
proposes
utilization
federated
learning.
The
proposed
framework
enables
collaborative
learning
by
training
model
on
distributed
from
multiple
institutions
without
raw
data.
Leveraging
U-Net-based
architecture,
renowned
its
exceptional
performance
semantic
tasks,
emphasizes
scalability
approach
large-scale
deployment
experimental
results
showcase
remarkable
effectiveness
learning,
significantly
improving
specificity
0.96
dice
coefficient
0.89
with
increase
clients
50
100.
Furthermore,
outperforms
existing
convolutional
neural
network
(CNN)-
recurrent
(RNN)-based
methods,
achieving
higher
accuracy,
enhanced
performance,
increased
efficiency.
findings
research
contribute
advancing
field
image
upholding
Complexity,
Journal Year:
2022,
Volume and Issue:
2022(1)
Published: Jan. 1, 2022
The
most
predominant
kind
of
disease
that
is
normal
among
ladies
breast
cancer.
It
one
the
significant
reasons
ladies,
regardless
huge
endeavors
to
stay
away
from
it
through
screening
developers.
An
automatic
detection
system
for
helps
doctors
identify
and
provide
accurate
results,
thereby
minimizing
death
rate.
Computer‐aided
diagnosis
(CAD)
has
minimum
intervention
humans
produces
more
results
than
humans.
will
be
a
difficult
long
task
depends
on
expertise
pathologists.
Deep
learning
methods
proved
give
better
outcomes
when
correlated
with
ML
extricate
best
highlights
images.
main
objective
this
paper
propose
deep
technique
in
combination
convolution
neural
network
(CNN)
short‐term
memory
(LSTM)
random
forest
algorithm
diagnose
Here,
CNN
used
feature
extraction,
LSTM
extracted
detection.
experimental
show
proposed
accomplishes
100%
accuracy,
sensitivity
99%,
recall
an
F1‐score
98%
compared
other
traditional
models.
As
achieved
correct
can
help
investigate
cancer
easily.
Mathematics,
Journal Year:
2022,
Volume and Issue:
10(3), P. 467 - 467
Published: Jan. 31, 2022
The
COVID-19
pandemic
created
a
global
emergency
in
many
sectors.
spread
of
the
disease
can
be
subdued
through
timely
vaccination.
vaccination
process
various
countries
is
ongoing
and
slowing
down
due
to
multiple
factors.
Many
studies
on
European
USA
have
been
conducted
highlighted
public’s
concern
that
over-vaccination
results
rate.
Similarly,
we
analyzed
collection
data
from
gulf
countries’
citizens’
vaccine-related
discourse
shared
social
media
websites,
mainly
via
Twitter.
people’s
feedback
regarding
different
types
vaccines
needs
considered
increase
process.
In
this
paper,
concerns
Gulf
people
are
lessen
vaccine
hesitancy.
proposed
approach
emphasizes
region-specific
related
accurately
using
machine
learning
(ML)-based
methods.
collected
were
filtered
tokenized
analyze
sentiments
extracted
three
methods:
Ratio,
TextBlob,
VADER
sentiment-scored
classified
into
positive
negative
tweeted
LSTM
method.
Subsequently,
obtain
more
confidence
classification,
in-depth
features
given
four
ML
classifiers.
ratio,
sentiment
scores
separately
provided
had
best
classification
fine-KNN
Ensemble
boost
with
94.01%
accuracy.
Given
improved
accuracy,
scheme
robust
confident
classifying
determining
Twitter
discourse.
The American Journal of Sports Medicine,
Journal Year:
2023,
Volume and Issue:
51(2), P. 358 - 366
Published: Jan. 9, 2023
Background:
Medical
screening
using
ultrasonography
(US)
has
been
performed
on
young
baseball
players
for
early
detection
of
osteochondritis
dissecans
(OCD)
the
humeral
capitellum.
Deep
learning
(DL)
and
artificial
intelligence
(AI)
techniques
are
widely
adopted
in
medical
imaging
research
field.
Purpose/Hypothesis:
The
purpose
this
study
was
to
calculate
diagnostic
accuracy
DL
US
images
OCD.
We
hypothesized
that
would
improve
prediction
Study
Design:
Cohort
(Diagnosis);
Level
evidence,
2.
Methods:
A
total
40
elbows
(mean
age
patients,
12.1
years)
were
suspected
having
OCD
at
a
checkup
later
confirmed
by
radiographs
magnetic
resonance
included
study.
affected
used
as
group
contralateral
control
group.
From
videos,
100
per
elbow
captured
from
different
angles,
4000
prepared
both
groups.
Of
these,
80%
randomly
selected
models
training
data;
remaining
test
data.
Transfer
conducted
3
pretrained
models.
confusion
matrix
area
under
receiver
operating
characteristic
curve
(AUC)
evaluate
model,
visualization
areas
deemed
important
also
performed.
Furthermore,
regions
detected
an
automatic
image
recognition
model
based
DL.
Results:
Classification
performed;
best
score
0.87;
recall
1.00.
AUC
high
all
Visualization
features
showed
AI
predicted
presence
focusing
irregularity
or
discontinuity
surface
subchondral
bone.
In
task,
mean
average
precision
0.83.
Conclusion:
identified
with
accuracy.
correspond
clinicians
images.
object
model.
may
be
