Multiparametric MRI and artificial intelligence in predicting and monitoring treatment response in bladder cancer
Insights into Imaging,
Год журнала:
2025,
Номер
16(1)
Опубликована: Янв. 2, 2025
Abstract
Bladder
cancer
is
the
10th
most
common
and
13th
deadly
worldwide,
with
urothelial
carcinomas
being
type.
Distinguishing
between
non-muscle-invasive
bladder
(NMIBC)
muscle-invasive
(MIBC)
essential
due
to
significant
differences
in
management
prognosis.
MRI
may
play
an
important
diagnostic
role
this
setting.
The
Vesical
Imaging
Reporting
Data
System
(VI-RADS),
a
multiparametric
(mpMRI)-based
consensus
reporting
platform,
allows
for
standardized
preoperative
muscle
invasion
assessment
BCa
proven
accuracy.
However,
post-treatment
using
VI-RADS
challenging
because
of
anatomical
changes,
especially
interpretation
layer.
techniques
that
provide
tumor
tissue
physiological
information,
including
diffusion-weighted
(DW)-
dynamic
contrast-enhanced
(DCE)-MRI,
combined
derived
quantitative
imaging
biomarkers
(QIBs),
potentially
overcome
limitations
evaluation
when
predominantly
focusing
on
anatomic
changes
at
MRI,
particularly
therapy
response
Delta-radiomics,
which
encompasses
(Δ)
image
features
extracted
from
mpMRI
data,
has
potential
monitor
treatment
response.
In
comparison
current
Response
Evaluation
Criteria
Solid
Tumors
(RECIST),
QIBs
mpMRI-based
radiomics,
combination
artificial
intelligence
(AI)-based
analysis,
allow
earlier
identification
therapy-induced
changes.
This
review
provides
update
radiomics
discusses
future
applications
AI
management,
assessing
Critical
relevance
statement
Incorporating
biomarkers,
into
enhance
prognosis
prediction.
Key
Points
Quantitative
(QIBs)
can
outperform
RECIST
treatments.
improves
segmentation
enhances
feature
extraction
effectively.
Predictive
models
integrate
clinical
data
tools.
Multicenter
studies
strict
criteria
validate
clinically.
Consistent
need
reliable
validation
practice.
Graphical
Язык: Английский
Multiparametric MRI for Bladder Cancer: A Practical Approach to the Clinical Application of VI-RADS
Radiology,
Год журнала:
2025,
Номер
314(3)
Опубликована: Март 1, 2025
Multiparametric
MRI
using
the
Vesical
Imaging
Reporting
and
Data
System
scoring
system
is
a
powerful
diagnostic
tool
to
assess
bladder
cancer
but
requires
standardized
acquisition,
evaluation,
interpretation,
reporting
optimize
accuracy
reproducibility.
Язык: Английский
Predicting variant histology in bladder cancer: the role of multiparametric MRI and vesical imaging-reporting and data system (VI-RADS)
Abdominal Radiology,
Год журнала:
2025,
Номер
unknown
Опубликована: Март 18, 2025
Abstract
Objectives
(1)
To
evaluate
the
diagnostic
performance
of
VI-RADS
score
in
detecting
muscle
invasion
variant
urothelial
carcinomas
(VUC).
(2)
identify
spesific
MRI
features
that
may
serve
as
predicting
for
VUC.
Methods
Two
hundred
four
patients
who
underwent
TUR-B
and/or
radical
cystectomy
and
a
bladder
mpMRI
scan
within
three
months
prior
to
procedure
were
retrospectively
enrolled.
The
tumors
divided
into
two
histological
cohorts:
pure
carcinoma
(PUC)
Various
features,
including
largest
tumor
diameter,
long-to-short
axis
ratio,
morphology,
heterogeneous
signal
intensity
(SI),
presence
necrosis,
normalized
ADC
(ADC
n
)
value,
analyzed.
was
calculated
using
cut-off
point
≥
4
both
cohorts.
Univariate
logistic
regression
also
performed
predict
Inter-reader
agreement
assessed
with
weighted
kappa
coefficient.
Results
Our
study
identified
several
significantly
associated
VUC,
SI
on
T2-weighted
images
(OR:
3.055;
95%
CI:
1.312–7.112;
p
<
0.001),
dynamic
contrast
enhancement
2.935;
1.263–6.821;
necrosis
3.575;
1.798–7.107;
0.001).
Additionally,
values
lower
VUC
cohort
(
=
0.003).
demonstrated
high
across
PUC
cohorts,
sensitivity
ranging
from
94.4
86.8%
(reader
1)
94.2–82.2%
2),
specificity
100
94.6%
100–94%
accuracy
96
90.6%
96–88.2%
2).
area
under
curve
(AUC)
ranged
between
0.972
0.838–0.781
No
significant
differences
observed
readers
or
cohorts
>
0.05),
inter-reader
scores
excellent
Conclusion
can
be
used
detect
regardless
reader
experience.
specific
such
SI,
potential
predictors
Graphical
Язык: Английский
A case of plasmacytoid urothelial carcinoma with characteristic radiological findings
Abdominal Radiology,
Год журнала:
2025,
Номер
unknown
Опубликована: Апрель 11, 2025
Язык: Английский
Stimuli-responsive smart nanomaterials for theranostics of urological cancers
Coordination Chemistry Reviews,
Год журнала:
2025,
Номер
539, С. 216745 - 216745
Опубликована: Май 1, 2025
Язык: Английский
Prediction of muscular-invasive bladder cancer using multi-view fusion self-distillation model based on 3D T2-Weighted images
Biomedical Engineering / Biomedizinische Technik,
Год журнала:
2024,
Номер
unknown
Опубликована: Ноя. 5, 2024
Abstract
Objectives
Accurate
preoperative
differentiation
between
non-muscle-invasive
bladder
cancer
(NMIBC)
and
muscle-invasive
(MIBC)
is
crucial
for
surgical
decision-making
in
(BCa)
patients.
MIBC
diagnosis
relies
on
the
Vesical
Imaging-Reporting
Data
System
(VI-RADS)
clinical
using
multi-parametric
MRI
(mp-MRI).
Given
absence
of
some
sequences
practice,
this
study
aims
to
optimize
existing
T2-weighted
imaging
(T2WI)
sequence
assess
accurately.
Methods
We
analyzed
T2WI
images
from
615
BCa
patients
developed
a
multi-view
fusion
self-distillation
(MVSD)
model
that
integrates
transverse
sagittal
views
classify
NMIBC.
This
3D
image
classification
method
leverages
z-axis
information
volume,
combining
adjacent
slices
comprehensive
features
extraction.
Multi-view
enhances
global
by
mutually
complementing
constraining
planes.
Self-distillation
allows
shallow
classifiers
learn
valuable
knowledge
deep
layers,
boosting
feature
extraction
capability
backbone
achieving
better
performance.
Results
Compared
performance
MVSD
with
classical
learning
methods
state-of-the-art
MRI-based
approaches,
proposed
achieves
highest
area
under
curve
(AUC)
0.927
accuracy
(Acc)
0.880,
respectively.
DeLong’s
test
shows
AUC
has
statistically
significant
differences
VGG16,
Densenet,
ResNet50,
residual
network.
Furthermore,
Acc
higher
than
two
urologists.
Conclusions
Our
performs
satisfactorily
distinguishing
NMIBC,
indicating
potential
facilitating
Язык: Английский
Use of Multiparametric and Biparametric Magnetic Resonance Imaging in Bladder Cancer Staging: Prospective Observational Study and Analysis of Radiologist Learning Curve
Journal of Clinical Medicine,
Год журнала:
2024,
Номер
13(22), С. 6955 - 6955
Опубликована: Ноя. 18, 2024
:
Nowadays,
thanks
to
the
introduction
of
VI-RADS
scoring
system,
mpMRI
has
shown
promising
results
in
pre-TURBT
assessment
muscular
invasiveness
BCa,
even
if
its
application
everyday
practice
is
still
limited.
This
might
be
due
a
lack
literature
about
learning
curve
radiologists
and
characteristics
exam.
With
aim
reduce
scan
time
patient
discomfort
while
maintaining
diagnostic
accuracy,
bpMRI
been
introduced
as
possible
alternative
this
group
patients.
study
reports
single-center
experience
using
system
differentiate
NMIBC
from
MIBC.
The
primary
assess
accuracy
system.
secondary
evaluate
an
experienced
radiologist.
Additionally,
we
perform
retrospective
same
patients
evaluating
only
DWIs
T2-weighted
images,
they
underwent
bpMRI,
compare
performance
bpMRI.
Язык: Английский