Cancer Imaging,
Journal Year:
2024,
Volume and Issue:
24(1)
Published: Sept. 16, 2024
Abstract
Purpose
We
aimed
to
develop
and
externally
validate
a
CT-based
deep
learning
radiomics
model
for
predicting
overall
survival
(OS)
in
clear
cell
renal
carcinoma
(ccRCC)
patients,
investigate
the
association
of
with
tumor
heterogeneity
microenvironment.
Methods
The
clinicopathological
data
contrast-enhanced
CT
images
512
ccRCC
patients
from
three
institutions
were
collected.
A
total
3566
features
extracted
3D
regions
interest.
generated
score
(DLRS),
validated
this
using
an
external
cohort
TCIA.
Patients
divided
into
high
low-score
groups
by
DLRS.
Sequencing
corresponding
TCGA
used
reveal
differences
microenvironment
between
different
groups.
What’s
more,
univariate
multivariate
Cox
regression
identify
independent
risk
factors
poor
OS
after
operation.
combined
was
developed
incorporating
DLRS
features.
SHapley
Additive
exPlanation
method
interpretation
predictive
results.
Results
At
analysis,
identified
as
factor
OS.
genomic
landscape
investigated.
significantly
varied
both
In
test
cohort,
had
great
performance,
AUCs
(95%CI)
1,
3
5-year
0.879(0.868–0.931),
0.854(0.819–0.899)
0.831(0.813–0.868),
respectively.
There
significant
difference
time
stratified
model.
This
showed
discrimination
calibration,
outperforming
existing
prognostic
models
(all
p
values
<
0.05).
Conclusion
allowed
prediction
clinicopathologic
could
reflect
Cancers,
Journal Year:
2024,
Volume and Issue:
16(4), P. 810 - 810
Published: Feb. 16, 2024
This
comprehensive
review
critically
examines
the
transformative
impact
of
artificial
intelligence
(AI)
and
radiomics
in
diagnosis,
prognosis,
management
bladder,
kidney,
prostate
cancers.
These
cutting-edge
technologies
are
revolutionizing
landscape
cancer
care,
enhancing
both
precision
personalization
medical
treatments.
Our
provides
an
in-depth
analysis
latest
advancements
AI
radiomics,
with
a
specific
focus
on
their
roles
urological
oncology.
We
discuss
how
have
notably
improved
accuracy
diagnosis
staging
bladder
cancer,
especially
through
advanced
imaging
techniques
like
multiparametric
MRI
(mpMRI)
CT
scans.
tools
pivotal
assessing
muscle
invasiveness
pathological
grades,
critical
elements
formulating
treatment
plans.
In
realm
kidney
aid
distinguishing
between
renal
cell
carcinoma
(RCC)
subtypes
grades.
The
integration
radiogenomics
offers
view
disease
biology,
leading
to
tailored
therapeutic
approaches.
Prostate
also
seen
substantial
benefits
from
these
technologies.
AI-enhanced
has
significantly
tumor
detection
localization,
thereby
aiding
more
effective
planning.
addresses
challenges
integrating
into
clinical
practice,
such
as
need
for
standardization,
ensuring
data
quality,
overcoming
“black
box”
nature
AI.
emphasize
importance
multicentric
collaborations
extensive
studies
enhance
applicability
generalizability
diverse
settings.
conclusion,
represent
major
paradigm
shift
oncology,
offering
precise,
personalized,
patient-centric
approaches
care.
While
potential
improve
diagnostic
accuracy,
patient
outcomes,
our
understanding
biology
is
profound,
application
persist.
advocate
continued
research
development
underscoring
address
existing
limitations
fully
leverage
capabilities
field
Scientific Reports,
Journal Year:
2025,
Volume and Issue:
15(1)
Published: Jan. 21, 2025
Eosinophilic
solid
and
cystic
renal
cell
carcinoma
(ESC-RCC)
is
rare
often
misdiagnosed
as
clear
(ccRCC).
Therefore,
a
CT-based
scoring
system
was
developed
to
improve
differential
diagnosis.
Retrospectively,
25
ESC-RCC
176
ccRCC
cases,
were
collected.
The
two
groups
matched
on
1:2
basis
using
the
propensity-score-matching
(PSM)
method,
with
matching
factors
including
sex
age.
Finally,
50
cases
included
randomly
divided
into
training
cohort
(52
cases)
validation
(23
cases).
Logistic
regression
identified
significant
factors,
constructed
primary
model,
assigned
weights
for
model.
Diagnostic
performance
compared
receiver
operating
characteristic
curves,
dividing
points
three
intervals.
Multifactorial
logistic
independent
factors:
intra-tumour
necrosis
(3
points),
degree
of
corticomedullary
phase
(CMP)
enhancement
pseudocapsule
(2
points).
model's
area
under
curve
(AUC)
value
0.954
(95%
confidence
interval
[CI]:
0.857–0.993,
P
<
0.001),
85.7%
sensitivity
94.1%
specificity.
AUC
0.950
CI:
0.852–0.991,
77.1%
100%
specificity
at
cut-off
4
points.
cohort's
0.942
0.759–0.997,
0.001).
intervals
were:
≥0
2
points,
≥
≤
3
>
8
Higher
scores
correlated
increased
incidence
decreased
incidence.The
limitation
this
study
small
sample
size.
A
effectively
differentiates
from
ccRCC.
EClinicalMedicine,
Journal Year:
2024,
Volume and Issue:
75, P. 102775 - 102775
Published: Aug. 16, 2024
Radiology-based
prognostic
biomarkers
play
a
crucial
role
in
patient
counseling,
enhancing
surveillance,
and
designing
clinical
trials
effectively.
This
study
aims
to
assess
the
predictive
significance
of
preoperative
CT-based
tumor
contour
irregularity
determining
outcomes
among
patients
with
renal
cell
carcinoma
(RCC).
