A Systematic Review of Diffusion Microstructure Imaging (DMI): Current and Future Applications in Neurology Research
Brain Disorders,
Journal Year:
2025,
Volume and Issue:
unknown, P. 100238 - 100238
Published: May 1, 2025
Language: Английский
Quantitative Physiologic MRI Combined with Feature Engineering for Developing Machine Learning-Based Prediction Models to Distinguish Glioblastomas from Single Brain Metastases
Diagnostics,
Journal Year:
2024,
Volume and Issue:
15(1), P. 38 - 38
Published: Dec. 27, 2024
Background:
The
accurate
and
early
distinction
of
glioblastomas
(GBMs)
from
single
brain
metastases
(BMs)
provides
a
window
opportunity
for
reframing
treatment
strategies
enabling
optimal
timely
therapeutic
interventions.
We
sought
to
leverage
physiologically
sensitive
parameters
derived
diffusion
tensor
imaging
(DTI)
dynamic
susceptibility
contrast
(DSC)–perfusion-weighted
(PWI)
along
with
machine
learning-based
methods
distinguish
GBMs
BMs.
Methods:
Patients
histopathology-confirmed
(n
=
62)
BMs
26)
exhibiting
contrast-enhancing
regions
(CERs)
underwent
3T
anatomical
imaging,
DTI
DSC-PWI
prior
treatment.
Median
values
mean
diffusivity
(MD),
fractional
anisotropy,
linear,
planar
spheric
anisotropic
coefficients,
relative
cerebral
blood
volume
(rCBV)
maximum
rCBV
were
measured
CERs
immediate
peritumor
regions.
Data
normalization
scaling
performed.
In
the
next
step,
most
relevant
features
extracted
(non-interacting
features),
which
subsequently
used
generate
set
new,
innovative,
high-order
(interacting
features)
using
feature
engineering
method.
Finally,
10
learning
classifiers
employed
in
distinguishing
Cross-validation
receiver
operating
characteristic
(ROC)
curve
analyses
performed
determine
diagnostic
performance.
Results:
A
random
forest
classifier
ANOVA
F-value
selection
algorithm
both
interacting
non-interacting
provided
best
performance
an
area
under
ROC
92.67%,
classification
accuracy
87.8%,
sensitivity
73.64%
specificity
97.5%.
Conclusions:
based
approach
involving
combined
use
physiological
MRI
shows
promise
differentiate
between
high
accuracy.
Language: Английский
Editorial for “Differentiation Between High‐Grade Glioma and Brain Metastasis Using Cerebral Perfusion‐Related Parameters (Cerebral Blood Volume and Cerebral Blood Flow): A Systematic Review and Meta‐Analysis of Perfusion‐weighted MRI Techniques”
Journal of Magnetic Resonance Imaging,
Journal Year:
2024,
Volume and Issue:
unknown
Published: July 6, 2024
Language: Английский