Artificial Intelligence for Neuroimaging in Pediatric Cancer
Cancers,
Год журнала:
2025,
Номер
17(4), С. 622 - 622
Опубликована: Фев. 12, 2025
Background/Objectives:
Artificial
intelligence
(AI)
is
transforming
neuroimaging
by
enhancing
diagnostic
precision
and
treatment
planning.
However,
its
applications
in
pediatric
cancer
remain
limited.
This
review
assesses
the
current
state,
potential
applications,
challenges
of
AI
for
cancer,
emphasizing
unique
needs
population.
Methods:
A
comprehensive
literature
was
conducted,
focusing
on
AI’s
impact
through
accelerated
image
acquisition,
reduced
radiation,
improved
tumor
detection.
Key
methods
include
convolutional
neural
networks
segmentation,
radiomics
characterization,
several
tools
functional
imaging.
Challenges
such
as
limited
datasets,
developmental
variability,
ethical
concerns,
need
explainable
models
were
analyzed.
Results:
has
shown
significant
to
improve
imaging
quality,
reduce
scan
times,
enhance
accuracy
neuroimaging,
resulting
segmentation
outcome
prediction
treatment.
progress
hindered
scarcity
issues
with
data
sharing,
implications
applying
vulnerable
populations.
Conclusions:
To
overcome
limitations,
future
research
should
focus
building
robust
fostering
multi-institutional
collaborations
developing
interpretable
that
align
clinical
practice
standards.
These
efforts
are
essential
harnessing
full
improving
outcomes
children
cancer.
Язык: Английский
Multi-Modality Fusion and Tumor Sub-Component Relationship Ensemble Network for Brain Tumor Segmentation
Bioengineering,
Год журнала:
2025,
Номер
12(2), С. 159 - 159
Опубликована: Фев. 6, 2025
Deep
learning
technology
has
been
widely
used
in
brain
tumor
segmentation
with
multi-modality
magnetic
resonance
imaging,
helping
doctors
achieve
faster
and
more
accurate
diagnoses.
Previous
studies
have
demonstrated
that
the
weighted
fusion
method
effectively
extracts
modality
importance,
laying
a
solid
foundation
for
imaging
segmentation.
However,
challenge
of
fusing
features
single-modality
remains
unresolved,
which
motivated
us
to
explore
an
effective
solution.
We
propose
feature
recalibration
network
Specifically,
we
designed
dual
module
achieves
calibration
by
integrating
complementary
specific
single
modality.
Experimental
results
on
BraTS
2018
dataset
showed
proposed
outperformed
existing
multi-modal
methods
across
multiple
evaluation
metrics,
spatial
significantly
improving
results,
including
Dice
score
increases
1.7%,
0.5%,
1.6%
enhanced
core,
whole
tumor,
core
regions,
respectively.
Язык: Английский
SARS CoV-2 in tumor tissue in glioblastoma patients – preliminary study
Current Issues in Pharmacy and Medical Sciences,
Год журнала:
2024,
Номер
37(4), С. 216 - 220
Опубликована: Ноя. 28, 2024
Abstract
SARS-CoV-2
infection
often
causes
neurological
disorders.
Experimental
studies
on
an
animal
model
have
shown
that
is
able
to
cross
the
blood-brain
barrier.
Researchers
also
discovered
can
infect
glial
cells.
Gliomas
are
most
common
type
of
brain
tumor.
Oncological
patients
at
high
risk
infections,
including
SARS-CoV-2.
Moreover,
their
weakened
immunity
level
antibodies
after
or
vaccination
be
lower
than
in
healthy
population.
Therefore,
aim
our
study
was
evaluate
occurrence
RNA
tumor
tissue
collected
during
surgery.
We
tested
anti-SARS-CoV-2
these
patients.
The
obtained
results
indicate
tropism
virus
–
glioblastoma.
anti-SARS
higher
with
detected
tumour
tissue.
Язык: Английский