Breast Cancer Targets and Therapy,
Journal Year:
2025,
Volume and Issue:
Volume 17, P. 187 - 200
Published: Feb. 1, 2025
Accurate
identification
of
the
molecular
subtypes
breast
cancer
is
essential
for
effective
treatment
selection
and
prognosis
prediction.
This
study
aimed
to
evaluate
diagnostic
performance
a
radiomics
model,
which
integrates
mammography
dynamic
contrast-enhanced
magnetic
resonance
imaging
(DCE-MRI)
in
predicting
cancer.
We
retrospectively
included
462
female
patients
with
pathologically
confirmed
cancer,
including
53
cases
triple-negative,
94
HER2
overexpression,
95
luminal
A,
215
B
Radiomics
analysis
was
performed
using
FAE
software,
wherein
radiomic
features
were
examined
about
hormone
receptor
status.
The
model
evaluated
area
under
receiver
operating
characteristic
curve
(AUC)
accuracy.
In
multivariate
analysis,
only
independent
predictive
factors
subtypes.
that
incorporates
multimodal
fusion
from
DCE-MRI
images
exhibited
superior
overall
compared
either
modality
independently.
AUC
values
(or
accuracies)
six
pairings
as
follows:
0.648
(0.627)
A
vs
B,
0.819
(0.793)
0.725
(0.696)
triple-negative
subtype,
0.644
(0.560)
0.625
(0.636)
0.598
(0.500)
subtype
overexpression.
radionics
utilizing
combined
showed
high
distinguishing
It
significance
accurately
predict
determine
strategy
by
classification.
European journal of medical research,
Journal Year:
2025,
Volume and Issue:
30(1)
Published: Feb. 25, 2025
To
quantitatively
assess
the
differences
in
parameters
of
dynamic
contrast-enhanced
MRI
(DCE–MRI)
HER2-zero,
HER2-low,
or
HER2-positive
tumors,
and
to
build
optimal
model
for
early
prediction
HER2-low
breast
cancer
(BC).
Clinical
DCE–MRI
data
from
220
BC
patients
receiving
neoadjuvant
chemotherapy
(NACT)
were
retrospectively
analyzed.
Quantitative
semi-quantitative
compared
groups
before
after
NACT.
Empirical
models
developed
predict
using
logistic
regression
analysis
receiver
operating
characteristic
(ROC)
analysis.
Patients
have
a
lower
pCR
rate
with
HER2-zero
(17.9%
vs.
10.4%
29.5%,
p
<
0.001),
predominantly
HR
(hormone
receptor)
negative
group
(22.2%
7.7%
40.5%,
0.001).
Before
NACT,
exhibited
higher
Kep,
Ktrans,
Washin,
TME
intratumoral
perfusion
characteristics,
Kep
peritumoral
region
patients.
Notably,
changes
(Kep)
(Ktrans,
Washin)
more
pronounced
group.
The
ROC
curves
(AUC)
pre-NACT
intratumoral,
peritumoral,
combined
0.675(95%
CI
0.600–0.750),
0.661(95%
0.585–0.738),
0.731(95%
0.660–0.802).
pre-and-post-NACT
further
improved
predictive
performance
accordingly,
AUCs
0.764
(95%
0.637–0.865),
0.795
0.711–0.878),
0.850
0.774–0.926).
study
revealed
heterogeneity
between
different
HER2
statuses
identified
best
imaging
as
non-invasive
tool
BC,
which
can
help
pre-treatment
clinical
decision-making.
Radiation Oncology,
Journal Year:
2025,
Volume and Issue:
20(1)
Published: Feb. 28, 2025
The
study
aimed
to
create
a
radiomics
model
based
on
breast
intra-
and
peri-tumoral
regions
in
dynamic
contrast-enhanced
(DCE)
MRI
distinguish
benign
from
malignant
lesions
of
Breast
Imaging
Reporting
Data
System
(BI-RADS)
4.
A
total
516
patients
Hospital
1
were
assigned
the
training
cohort.
Then,
146
52
enrolled
2
3,
respectively,
as
internal
external
test
Seven
classification
models
built,
using
features
extracted
regions.
Diagnostic
performance
was
evaluated
by
receiver
operating
characteristics
(ROC)
analysis
compared
DeLong
test.
Subgroup
performed
after
stratifying
all
enhancement
pattern
subdivision
BI-RADS
Comb2
model,
built
with
mm
intra-tumoral
region,
demonstrated
best
AUCs
0.828
0.844
cohort,
respectively.
robust
both
mass
non-mass
(NME)
lesions.
At
three
exploratory
cutoff
values
ROC
curve,
identified
9.1%
(sensitivity
C1
≥
98%),
27.3%
C2
95%)
36.4%
C3
90%)
Applying
cohort
showed
potential
lower
number
unnecessary
biopsies
An
MRI-based
region
combined
reduce
false-positive
diagnoses
may
avoid
low
underestimate
risk.
Insights into Imaging,
Journal Year:
2025,
Volume and Issue:
16(1)
Published: March 7, 2025
Recent
advances
in
human
epidermal
growth
factor
receptor
2
(HER2)-targeted
therapies
have
opened
up
new
therapeutic
options
for
HER2-low
cancers.
This
study
aimed
to
establish
an
ultrasound-based
radiomics
model
identify
three
different
HER2
states
noninvasively.
Between
May
2018
and
December
2023,
a
total
of
1257
invasive
breast
cancer
patients
were
enrolled
from
hospitals.
The
status
was
divided
into
classes:
positive,
low,
zero.
Four
peritumoral
regions
interest
(ROI)
auto-generated
by
dilating
the
manually
segmented
intratumoral
ROI
thicknesses
5
mm,
10
15
20
mm.
After
image
preprocessing,
4720
features
extracted
each
every
patient.
least
absolute
shrinkage
selection
operator
LightBoost
algorithm
utilized
construct
single-
multi-region
signatures
(RS).
A
clinical-radiomics
combined
developed
integrating
discriminative
clinical-sonographic
factors
with
optimal
RS.
data
stitching
strategy
used
build
patient-level
models.
Shapley
additive
explanations
(SHAP)
approach
explain
contribution
internal
prediction.
RS
constructed
12
tumor
9
peritumoral-15mm
features.
Age,
size,
seven
qualitative
ultrasound
retained
In
training,
validation,
test
cohorts,
showed
best
discrimination
ability
macro-AUCs
0.988
(95%
CI:
0.983-0.992),
0.915
0.851-0.965),
0.862
0.820-0.899),
respectively.
built
robust
interpretable
evaluate
classes
based
on
images.
Ultrasound-based
method
can
noninvasively
HER2,
which
may
guide
treatment
decisions
implementation
personalized
HER2-targeted
patients.
Determination
affect
cancer.
discriminate
statuses.
Our
assist
providing
recommendations
novel
therapies.
Frontiers in Oncology,
Journal Year:
2025,
Volume and Issue:
15
Published: March 11, 2025
Purpose
A
model
for
preoperative
prediction
of
molecular
subtypes
breast
cancer
using
tumor
and
peritumor
radiomics
features
from
multiple
magnetic
resonance
imaging
(mMRI)
sequences,
combined
with
semantic
features.
Materials
methods
total
254
female
patients
pathogically
confirmed
were
enrolled
in
this
study.
Preoperative
mMRI,
including
T2-weighted
(T2WI),
diffusion-weighted
(DWI),
dynamic
contrast-enhanced
MRI
(DCE)
covered
the
entire
breast.
To
analyze
different
identify
independent
predictive
risk
factors.
Thirty-three
binary
classification
models
established
based
on
radiomic
sequences
peritumoral
ranges.
The
best
was
selected
by
comparing
performance
above
models.
At
same
time,
sequence
extent
extracted
target
features,
score
calculated,
factors
predicted.
Finally,
a
nomogram
Triple-Negative
Breast
Cancer
(TNBC),
Hormone
Receptor
(HR)
positive
HER2
negative
(HR+/HER2−),
HER2+
staging
types
cancer.
Results
Tumor
length,
edge
enhancement,
edema
predicting
DCE
margin
6
mm.
AUC
optimal
sequence(DCE)
range
(6
mm)
0.910,
0.909,
0.845,
respectively.
Conclusion
predictors
intratumoral
scores
can
be
used
as
an
auxiliary
diagnostic
tool
subtype
Frontiers in Oncology,
Journal Year:
2025,
Volume and Issue:
15
Published: March 14, 2025
To
comprehensively
describe
MRI
characteristics
of
serous
endometrial
carcinoma
(SEC)
and
distinguish
SEC
from
endometrioid
(EEC).
We
retrospectively
recruited
62
patients
a
tertiary
center
with
pathologically
proven
cancers
(37
25
EEC)
as
the
training
set.
image
interpretation
was
blindly
interpreted
by
two
experienced
radiologists
consensus
reading.
Both
qualitative
quantitative
on
were
recorded
case
case.
Histological
findings
retrieved
hospital
information
system.
Fifty-four
samples
(27
27
external
treated
testing
The
had
no
statistical
difference
between
EEC
groups
in
more
often
invaded
deep
myometrium
than
(p
=
0.03).
signal
intensity
(SI)T2Ratio,
SIcontrastRatio,
LesionareaRatio,
VolumeareaRatio
group
1.35
±
0.36,
0.77
0.18,
0.25
0.24,
0.22
0.26,
respectively.
SIT2Ratio,
showed
statistically
significant
differences
<
0.05).
highest
discriminative
index
for
distinguishing
SIcontrastRatio
an
area
under
curve
(AUC)
0.7533
(95%
CI:
0.627-0.878).
A
predictive
nomogram
achieved
AUC
0.814
0.614-0.968),
sensitivity
1.0,
specificity
0.60
This
study
developed
validated
model
to
predict
based
clinical
features,
which
can
be
used
EEC.
BMC Cancer,
Journal Year:
2025,
Volume and Issue:
25(1)
Published: April 1, 2025
This
study
aimed
to
assess
the
predictive
value
of
radiomic
analysis
derived
from
primary
lesions
and
ipsilateral
axillary
suspicious
lymph
nodes
(SLN)
on
dynamic
contrast-enhanced
MRI
(DCE-MRI)
for
evaluating
response
neoadjuvant
therapy
(NAT)
in
early
high-risk
advanced
breast
cancer
(BC)
patients.
A
retrospective
was
conducted
222
BC
patients
(192
Center
I
30
II)
who
underwent
NAT.
Radiomic
features
were
extracted
lesion
(intra-
peritumoral
regions)
SLN
develop
signatures
(RS-primary,
RS-SLN).
An
integrated
signature
(RS-Com)
combined
both
regions.
Feature
selection
performed
using
correlation
analysis,
Mann-Whitney
U
test,
least
absolute
shrinkage
operator
(LASSO)
regression.
diagnostic
nomogram
constructed
by
integrating
RS-Com
with
key
clinical
factors.
Model
performance
evaluated
receiver
operating
characteristic
(ROC)
decision
curve
(DCA).
demonstrated
superior
compared
RS-primary
RS-SLN
alone.
The
DeLong
test
confirmed
that
SLNs
provide
supplementary
information
lesion.
Among
factors,
N
staging
HER2
status
significant
contributors.
nomogram,
RS-Com,
staging,
status,
achieved
highest
training
(AUC:
0.926),
validation
0.868),
0.839)
cohorts,
outperforming
models
offer
valuable
predicting
NAT
proposed
incorporating
radiomics
provides
a
robust
tool
individualized
treatment
planning.
