Galen Medical Journal,
Journal Year:
2023,
Volume and Issue:
12
Published: Dec. 16, 2023
Artificial
Intelligence
(AI)
is
rapidly
transforming
various
aspects
of
healthcare,
including
the
field
diagnostics
and
treatment
diseases.
This
review
article
aimed
to
provide
an
in-depth
analysis
impact
AI,
especially,
radiomics
in
diagnosis
neuro-oncology
Indeed,
it
a
multidimensional
task
that
requires
integration
clinical
assessment,
neuroimaging
techniques,
emerging
technologies
like
AI
radiomics.
The
advancements
these
fields
have
potential
revolutionize
accuracy,
efficiency,
personalized
approach
diagnosing
diseases,
leading
improved
patient
outcomes
enhanced
overall
neurologic
care.
However,
has
some
limitations,
ethical
challenges
should
be
addressed
via
future
research.
Acta Neurochirurgica,
Journal Year:
2024,
Volume and Issue:
166(1)
Published: May 7, 2024
Abstract
Purpose
Mapping
higher-order
cognitive
functions
during
awake
brain
surgery
is
important
for
preservation
which
related
to
postoperative
quality
of
life.
A
systematic
review
from
2018
about
neuropsychological
tests
used
craniotomy
made
clear
that
until
2017
language
was
most
often
monitored
and
the
other
domains
were
underexposed
(Ruis,
J
Clin
Exp
Neuropsychol
40(10):1081–1104,
218).
The
field
monitoring
however
developing
rapidly.
aim
current
therefore,
investigate
whether
there
a
change
in
towards
incorporation
new
more
complete
mapping
(higher-order)
functions.
Methods
We
replicated
search
study
PubMed
Embase
February
November
2023,
yielding
5130
potentially
relevant
articles.
artificial
machine
learning
tool
ASReview
screening
included
272
papers
gave
detailed
description
craniotomy.
Results
Comparable
previous
2018,
majority
studies
(90.4%)
reported
assessing
Nevertheless,
an
increasing
number
now
also
describe
visuospatial
functions,
social
cognition,
executive
Conclusions
Language
remains
extensively
tested
domain.
However,
broader
range
are
implemented
(new
developed)
received
attention.
rapid
development
reflected
this
review.
some
(e.g.,
memory),
still
need
can
be
surgery.
Journal of Neuroimaging,
Journal Year:
2025,
Volume and Issue:
35(1)
Published: Jan. 1, 2025
ABSTRACT
Background
and
Purpose
In
neurosurgery,
functional
MRI
is
crucial
for
preoperative
planning
to
obtain
the
cortical
cortex
map
of
language
areas.
This
preliminary
work
involved
analyzing
MRIs
20
oncological
patients.
Our
question
if
resting‐state
(rs‐fMRI)
can
replace
standard
task‐based
(tb‐fMRI)
in
routine
clinical
applications.
The
aim
this
challenge
determine
rs‐fMRI
as
effective
tb‐fMRI
develop
a
systematic
approach
extraction
map.
Methods
We
started
by
our
images
validated
correct
mapping
regions
using
an
independent
components
analysis
approach;
then,
we
used
connectivity
networks
compare
two
techniques.
Results
identified
align
with
established
medical
knowledge;
comparison
reveals
that
four
regions—Broca's
Wernicke's
areas
both
hemispheres—exhibit
activation
techniques;
furthermore,
highlighted
more
comprehensive
details
about
contrast
tb‐fMRI.
Conclusions
rs‐MRI
tb‐MRI
provide
similar
levels
efficacy
revealing
brain
when
lesion
lies
related
language;
thus,
techniques
be
utilized
goal.
Based
on
this,
developed
processing
pipeline
usage
applied
it
patient
outside
study.
Frontiers in Medicine,
Journal Year:
2024,
Volume and Issue:
11
Published: June 26, 2024
Introduction
In
the
evolving
healthcare
landscape,
we
aim
to
integrate
hyperspectral
imaging
into
Hybrid
Health
Care
Units
advance
diagnosis
of
medical
diseases
through
effective
fusion
cutting-edge
technology.
The
scarcity
data
limits
use
in
disease
classification.
Methods
Our
study
innovatively
integrates
characterize
tumor
tissues
across
diverse
body
locations,
employing
Sharpened
Cosine
Similarity
framework
for
classification
and
subsequent
recommendation.
efficiency
proposed
model
is
evaluated
using
Cohen's
kappa,
overall
accuracy,
f1-score
metrics.
Results
demonstrates
remarkable
efficiency,
with
kappa
91.76%,
an
accuracy
95.60%,
96%.
These
metrics
indicate
superior
performance
our
over
existing
state-of-the-art
methods,
even
limited
training
data.
Conclusion
This
marks
a
milestone
hybrid
informatics,
improving
personalized
care
advancing
recommendations.
Advances in medical diagnosis, treatment, and care (AMDTC) book series,
Journal Year:
2024,
Volume and Issue:
unknown, P. 120 - 140
Published: Jan. 5, 2024
Functional
magnetic
resonance
imaging
(fMRI),
with
its
unique
advantages
of
non-invasiveness,
relatively
balanced
spatial
and
temporal
resolution,
repeatability,
whole
brain
imaging,
has
brought
methodological
breakthroughs
to
neuroscience
neurological
clinical
practice.
By
measuring
blood
oxygen-dependent
signals,
fMRI
can
reveal
activity
in
task
execution,
sensory
stimulation,
emotional
regulation.
comparing
the
functional
between
patients
normal
controls,
detect
abnormal
regions
associated
mental
illness.
During
rehabilitation
stroke,
traumatic
injury,
neurodegenerative
diseases,
enables
evaluation
function
recovery
guides
personalized
training.
This
chapter
introduces
working
principle
summarizes
state
art,
providing
references
for
clinicians,
researchers
neuroscience,
biomedical
engineers.
This
chapter
explores
the
fundamentals
and
recent
advancements
of
diffusion-weighted
imaging
(DWI)
its
primary
application,
tractography.
Both
have
become
indispensable
in
research
arena
are
currently
being
integrated
into
clinical
world,
especially
for
neurosurgery.
These
technologies
provide
rapid,
vivo
mapping
white
matter
tracts,
greatly
assisting
surgeons
pre-surgical
planning
enabling
them
to
offer
patients
more
precise
prognostic
information,
thereby
enhancing
process
informed
decision-making.
Despite
nearly
three
decades
use
development
sophisticated
techniques,
adoption
contemporary
tractography
methods
settings
has
been
slow.
Here,
we
aim
a
comprehensive
understanding
DWI's
basic
principles,
shed
light
on
advanced
methodologies
that
surpass
traditional
diffusion
tensor
model,
discuss
integration
Our
objective
is
advocate
incorporation
newer
techniques
standard
practice.
Clinical Nuclear Medicine,
Journal Year:
2024,
Volume and Issue:
49(9), P. 822 - 829
Published: May 1, 2024
Purpose
18
F-FDG
PET
captures
the
relationship
between
glucose
metabolism
and
synaptic
activity,
allowing
for
modeling
brain
function
through
metabolic
connectivity.
We
investigated
tumor-induced
modifications
of
Patients
Methods
Forty-three
patients
with
left
hemispheric
tumors
PET/MRI
were
retrospectively
recruited.
included
37
healthy
controls
(HCs)
from
database
CERMEP-IDB-MRXFDG.
analyzed
whole
right
versus
hemispheres
connectivity
in
HC,
frontal
temporal
tumors,
active
radiation
necrosis,
high
Karnofsky
performance
score
(KPS
=
100)
low
KPS
<
70).
Results
compared
2-sided
t
test
(
P
0.05).
Twenty
high-grade
glioma,
4
low-grade
19
metastases
included.
The
patients’
whole-brain
network
displayed
lower
metrics
HC
0.001),
except
assortativity
betweenness
centrality
0.001).
showed
decreased
similarity,
0.01),
exception
0.002).
did
not
show
significant
differences.
Frontal
higher
0.001)
than
but
4.5
−7
).
distance
local
efficiency
rich
club
coefficient
0.0048),
clustering
0.00032),
0.008),
similarity
0.0027)
KPS.
tumor(s)
(14/43)
demonstrated
significantly
necroses.
Conclusions
Tumors
cause
reorganization
networks,
characterized
by
formation
new
connections
centrality.
retained
a
more
efficient,
centralized,
segregated
tumors.
Stronger
was
associated
American Journal of Neuroradiology,
Journal Year:
2024,
Volume and Issue:
45(10), P. 1552 - 1561
Published: May 7, 2024
ABSTRACT
BACKGROUND
AND
PURPOSE:
Resting-state
functional
MRI
(rs-fMRI)
can
be
used
to
estimate
connectivity
(FC)
between
different
brain
regions,
which
may
of
value
for
identifying
cognitive
impairment
in
patients
with
tumors.
Unfortunately,
neither
rs-fMRI
nor
neurocognitive
assessments
are
routinely
assessed
clinically,
mostly
due
limitations
exam
time
and
cost.
Since
DSC
perfusion
is
often
clinically
assess
tumor
vascularity
similarly
uses
a
gradient
echo-EPI
sequence
T2*sensitivity,
we
theorized
"pseudo-rs-fMRI"
signal
could
derived
from
simultaneously
quantify
FC
metrics,
these
metrics
MATERIALS
METHODS:
N=24
consecutive
gliomas
were
enrolled
prospective
study
that
included
MRI,
rs-fMRI,
assessment.
Voxel-wise
modeling
contrast
bolus
dynamics
during
acquisition
was
performed
then
subtracted
the
original
generate
residual
signal.
Following
pre-processing
pseudo-rs-fMRI,
full
truncated
version
(first
100
timepoints)
data,
default
mode,
motor,
language
network
maps
generated
atlas-based
ROIs.
Dice
scores
calculated
resting-state
pseudo-rs-fMRI
using
as
reference.
Seed-to-voxel
ROI-to-ROI
analyses
differences
cognitively
impaired
non-impaired
patients.
RESULTS:
group-level
patient-level
(mean±SD)
0.905/0.689±0.118
(group/patient),
0.973/0.730±0.124,
0.935/0.665±0.142,
respectively.
There
no
significant
difference
mode
(P=0.97)
or
networks
(P=0.30),
but
there
motor
(P=0.02).
A
multiple
logistic
regression
classifier
applied
identify
(Sensitivity=84.6%,
Specificity=63.6%,
ROC
AUC=0.7762±0.0954
(SE),
P=0.0221)
performance
not
significantly
than
predictions
(AUC=0.8881±0.0733
P=0.0013,
P=0.29
compared
pseudo-rs-fMRI).
CONCLUSIONS:
MRI-derived
data
perform
typical
decline
tumors
while
still
performing
analyses.
ABBREVIATIONS:
AUC
=
Area
under
curve;
BOLD
Blood
oxygenation
level
dependent;
Functional
connectivity;
MNI
Montreal
Neurological
Institute;
Receiver
operating
characteristic;
Rs-fMRI