Proceedings of the Southwest State University Series IT Management Computer Science Computer Engineering Medical Equipment Engineering,
Journal Year:
2024,
Volume and Issue:
14(3), P. 104 - 120
Published: Nov. 15, 2024
The
purpose
of
the
research
is
to
analyze
efficiency
U-net
neural
network
architecture
in
decision
support
systems
for
glioma
diagnostics
and
segmentation
brain
areas
affected
by
it
on
MRI
images.
Methods.
To
conduct
experimental
studies,
a
training
dataset
was
generated
data
normalized.
A
software
implementation
U-Net
performed
using
Keras
framework
Python
programming
language.
model
trained.
Results.
series
experiments
were
conducted,
during
which
error
classification
matrices
obtained,
trained
"Tumor"
"No
tumor"
classes
assessed
metrics
such
as
Recall,
Precision
F1-measure,
quality
glioma-affected
test
set
assessed.
IoU
metric,
reflects
ratio
bounding
boxes
used
assess
accuracy
spatial
correspondence
predicted
segmented
highlighted
masks.
Based
results
testing
solving
problem
segmenting
glioma,
average
value
metric
0.812,
an
acceptable
result.
Conclusion.
showed
that
based
able
effectively
diagnose
presence
with
values
metrics,
indicates
possibility
this
medical
diagnostics,
well
its
However,
advisable
refine
reduce
number
false
negative
results,
critically
important
diagnostics.
Acta Neuropathologica,
Journal Year:
2025,
Volume and Issue:
149(1)
Published: March 26, 2025
Abstract
Spinal
ependymoma
and
myxopapillary
are
the
two
most
common
spinal
ependymal
tumor
types
that
feature
distinct
histological
characteristics,
genetic
alterations
DNA
methylation
profiles.
Their
distinction
may
be
difficult
in
individual
cases
molecular
diagnostic
assessment,
particular
methylome
profiling,
then
required
to
assign
correct
diagnosis.
Expression
of
homeobox
gene
HOXB13
at
mRNA
protein
levels
has
been
reported
as
a
frequent
finding
serve
marker
for
these
tumors.
Here,
we
evaluated
role
immunostaining
143
neoplasms,
comprising
54
histologically
classified
ependymomas,
46
various
other
types.
Immunohistochemical
results
were
compared
findings
obtained
by
bead
array-based
copy
number
well
next
generation
panel
sequencing-based
mutational
analysis.
Our
indicate
strong
nuclear
expression
reliable
molecularly
confirmed
ependymoma.
Moreover,
provide
evidence
differential
is
related
-associated
CpG
site
vs.
which
can
assessed
targeted
Taken
together,
immunohistochemistry
analysis
represent
useful
surrogate
approaches
substitute
profiling
routine
diagnostics
facilitate
precise
classification
In
particular,
immunoreactivity
novel
criterion
Frontiers in Aging Neuroscience,
Journal Year:
2025,
Volume and Issue:
17
Published: Feb. 13, 2025
Introduction
Alzheimer’s
disease
(AD)
and
glioblastoma
(GBM)
are
severe
neurological
disorders
that
pose
significant
global
healthcare
challenges.
Despite
extensive
research,
the
molecular
mechanisms,
particularly
those
involving
mitochondrial
dysfunction,
remain
poorly
understood.
A
major
limitation
in
current
studies
is
lack
of
cell-specific
markers
effectively
represent
dynamics
AD
GBM.
Methods
In
this
study,
we
analyzed
single-cell
transcriptomic
data
using
10
machine
learning
algorithms
to
identify
mitochondria-associated
markers.
We
validated
these
through
integration
gene
expression
methylation
across
diverse
cell
types.
Our
dataset
comprised
single-nucleus
RNA
sequencing
(snRNA-seq)
from
patients,
(scRNA-seq)
GBM
additional
DNA
ROSMAP,
ADNI,
TCGA,
CGGA
cohorts.
Results
analysis
identified
four
cross-disease
markers:
EFHD1,
SASH1,
FAM110B,
SLC25A18
.
These
showed
both
shared
unique
profiles
GBM,
suggesting
a
common
mechanism
contributing
diseases.
Additionally,
oligodendrocytes
their
interactions
with
astrocytes
were
implicated
progression,
APP
signaling
pathway.
Key
hub
genes,
such
as
HS6ST3
TUBB2B
,
different
cellular
subpopulations,
highlighting
co-expression
network
linked
function.
Brain Sciences,
Journal Year:
2025,
Volume and Issue:
15(3), P. 309 - 309
Published: March 14, 2025
Background
and
Objective:
The
discovery
of
novel
molecular
biomarkers
via
next-generation
sequencing
technologies
has
revolutionized
how
glioblastomas
(GBMs)
are
classified
nowadays.
This
resulted
in
more
precise
diagnostic,
prognostic,
therapeutic
approaches
to
address
this
malignancy.
present
work
examines
the
applications
single-cell
RNA
(scRNA-seq)
GBM,
focusing
on
its
potential
tumor
complexity
resistance
improve
patient
outcomes.
Methods:
A
scoping
review
original
studies
published
between
2009
2024
was
conducted
using
PUBMED
EMBASE
databases.
Studies
English
or
Spanish
related
analysis
GBM
were
included.
Key
Findings:
database
search
yielded
453
publications.
Themes
scRNA-seq
applied
for
diagnosis,
prognosis,
treatment,
understanding
cancer
biology
used
as
criteria
article
selection.
Of
24
that
included
review,
11
focused
microenvironment
cell
subpopulations
samples,
5
investigated
use
elucidate
biology,
3
examined
disease
prognosis
models,
translational
research
through
scRNA-seq,
2
addressed
treatment-related
problems
elucidated
by
scRNA-seq.
Conclusions:
explored
various
clinical
approaching
GBM.
findings
highlight
utility
technology
unraveling
complex
cellular
immune
landscapes
paving
way
improved
diagnosis
personalized
treatments.
cutting-edge
approach
might
strengthen
treatment
strategies
against
progression
recurrence,
setting
stage
multi-targeted
interventions
could
significantly
outcomes
patients
with
aggressive,
treatment-resistant
GBMs.
