Digital Diagnostics,
Journal Year:
2025,
Volume and Issue:
unknown
Published: Feb. 28, 2025
Radiomics
is
a
method
to
extract
large
number
of
quantitative
features
from
digital
medical
image.
Since
its
first
applications
in
oncology
nearly
decade
ago,
radiomics
has
developed
towards
non-oncological
diseases,
particular,
diseases
the
musculoskeletal
system
(MSK)
and
connective
tissue.
This
article
aims
review
current
achievements
for
diagnosing
MSK
diseases.
study
includes
37
original
research
papers
published
English
between
2020
2023.
The
most
commonly
used
imaging
modalities
were
magnetic
resonance
computed
tomography,
rarely
approach
ultrasound.
vast
majority
studies
under
manual
region
interest
segmentation.
have
different
classification
models
based
on
clinical,
radiomics,
deep
features,
but
combined
clinical-radiomics
prevail.
Localizations
considered
included
mostly
spine
big
joints.
prevalence
multiple
source
input
(predominantly
clinical-radiomics)
compared
with
single
(clinical
only,
only)
diagnosis
can
be
explained
by
higher
performance
produced
probably
bigger
independent
information
sources.
Development
seems
promising
automatic
segmentation
requires
serious
efforts
creating
image
databases
model
training.
might
especially
useful
early
that
lead
pathological
changes
soft
tissues
cannot
seen
naked
eye.
Cancers,
Journal Year:
2023,
Volume and Issue:
15(17), P. 4344 - 4344
Published: Aug. 30, 2023
Lung
cancer
has
one
of
the
worst
morbidity
and
fatality
rates
any
malignant
tumour.
Most
lung
cancers
are
discovered
in
middle
late
stages
disease,
when
treatment
choices
limited,
patients’
survival
rate
is
low.
The
aim
screening
identification
malignancies
early
stage
more
options
for
effective
treatments
available,
to
improve
outcomes.
desire
efficacy
efficiency
clinical
care
continues
drive
multiple
innovations
into
practice
better
patient
management,
this
context,
artificial
intelligence
(AI)
plays
a
key
role.
AI
may
have
role
each
process
workflow.
First,
acquisition
low-dose
computed
tomography
programs,
AI-based
reconstruction
allows
further
dose
reduction,
while
still
maintaining
an
optimal
image
quality.
can
help
personalization
programs
through
risk
stratification
based
on
collection
analysis
huge
amount
imaging
data.
A
computer-aided
detection
(CAD)
system
provides
automatic
potential
nodules
with
high
sensitivity,
working
as
concurrent
or
second
reader
reducing
time
needed
interpretation.
Once
nodule
been
detected,
it
should
be
characterized
benign
malignant.
Two
approaches
available
perform
task:
first
represented
by
segmentation
consequent
assessment
lesion
size,
volume,
densitometric
features;
consists
first,
followed
radiomic
features
extraction
characterize
whole
abnormalities
providing
so-called
“virtual
biopsy”.
This
narrative
review
aims
provide
overview
all
possible
applications
screening.
Cancers,
Journal Year:
2024,
Volume and Issue:
16(5), P. 998 - 998
Published: Feb. 29, 2024
The
Frontline
and
Relapsed
Rhabdomyosarcoma
(FaR-RMS)
clinical
trial
is
an
overarching,
multinational
study
for
children
adults
with
rhabdomyosarcoma
(RMS).
trial,
developed
by
the
European
Soft
Tissue
Sarcoma
Study
Group
(EpSSG),
incorporates
multiple
different
research
questions
within
a
multistage
design
focus
on
(i)
novel
regimens
poor
prognostic
subgroups,
(ii)
optimal
duration
of
maintenance
chemotherapy,
(iii)
use
radiotherapy
local
control
widespread
metastatic
disease.
Additional
sub-studies
focusing
biological
risk
stratification,
imaging
modalities,
including
[
Cancers,
Journal Year:
2024,
Volume and Issue:
16(13), P. 2448 - 2448
Published: July 3, 2024
Cancer
is
one
of
the
leading
causes
death,
making
timely
diagnosis
and
prognosis
very
important.
Utilization
AI
(artificial
intelligence)
enables
providers
to
organize
process
patient
data
in
a
way
that
can
lead
better
overall
outcomes.
This
review
paper
aims
look
at
varying
uses
for
clinical
utility.
PubMed
EBSCO
databases
were
utilized
finding
publications
from
1
January
2020
22
December
2023.
Articles
collected
using
key
search
terms
such
as
“artificial
intelligence”
“machine
learning.”
Included
collection
studies
application
determining
cancer
multi-omics
data,
radiomics,
pathomics,
laboratory
data.
The
resulting
89
categorized
into
eight
sections
based
on
type
then
further
subdivided
two
subsections
focusing
prognosis,
respectively.
Eight
integrated
more
than
form
omics,
namely
genomics,
transcriptomics,
epigenomics,
proteomics.
Incorporating
alongside
omics
represents
significant
advancement.
Given
considerable
potential
this
domain,
ongoing
prospective
are
essential
enhance
algorithm
interpretability
ensure
safe
integration.
Diagnostics,
Journal Year:
2023,
Volume and Issue:
13(5), P. 857 - 857
Published: Feb. 23, 2023
Stroke
is
a
leading
cause
of
disability
and
mortality,
resulting
in
substantial
socio-economic
burden
for
healthcare
systems.
With
advances
artificial
intelligence,
visual
image
information
can
be
processed
into
numerous
quantitative
features
an
objective,
repeatable
high-throughput
fashion,
process
known
as
radiomics
analysis
(RA).
Recently,
investigators
have
attempted
to
apply
RA
stroke
neuroimaging
the
hope
promoting
personalized
precision
medicine.
This
review
aimed
evaluate
role
adjuvant
tool
prognosis
after
stroke.
We
conducted
systematic
following
PRISMA
guidelines,
searching
PubMed
Embase
using
keywords:
‘magnetic
resonance
imaging
(MRI)’,
‘radiomics’,
‘stroke’.
The
PROBAST
was
used
assess
risk
bias.
Radiomics
quality
score
(RQS)
also
applied
methodological
studies.
Of
150
abstracts
returned
by
electronic
literature
research,
6
studies
fulfilled
inclusion
criteria.
Five
evaluated
predictive
value
different
models
(PMs).
In
all
studies,
combined
PMs
consisting
clinical
achieved
best
performance
compared
based
only
on
or
features,
results
varying
from
area
under
ROC
curve
(AUC)
0.80
(95%
CI,
0.75–0.86)
AUC
0.92
0.87–0.97).
median
RQS
included
15,
reflecting
moderate
quality.
Assessing
bias
PROBAST,
potential
high
participants
selection
identified.
Our
findings
suggest
that
integrating
both
advanced
variables
seem
better
predict
patients’
outcome
group
(favorable
outcome:
modified
Rankin
scale
(mRS)
≤
2
unfavorable
mRS
>
2)
at
three
six
months
Although
studies’
are
significant
research
field,
these
should
validated
multiple
settings
order
help
clinicians
provide
individual
patients
with
optimal
tailor-made
treatment.
Nutrients,
Journal Year:
2024,
Volume and Issue:
16(12), P. 1806 - 1806
Published: June 8, 2024
(1)
Background:
The
aim
was
to
validate
an
AI-based
system
compared
the
classic
method
of
reading
ultrasound
images
rectus
femur
(RF)
muscle
in
a
real
cohort
patients
with
disease-related
malnutrition.
(2)
Methods:
One
hundred
adult
DRM
aged
18
85
years
were
enrolled.
risk
assessed
by
Global
Leadership
Initiative
on
Malnutrition
(GLIM).
variation,
reproducibility,
and
reliability
measurements
for
RF
subcutaneous
fat
thickness
(SFT),
(MT),
cross-sectional
area
(CSA),
measured
conventionally
incorporated
tools
portable
imaging
device
(method
A)
automated
quantification
B).
(3)
Results:
Measurements
obtained
using
A
(i.e.,
conventionally)
B
raw
analyzed
AI),
showed
similar
values
no
significant
differences
absolute
coefficients
58.39–57.68%
SFT,
30.50–28.36%
MT,
36.50–36.91%
CSA,
respectively.
Intraclass
Correlation
Coefficient
(ICC)
consistency
analysis
between
methods
correlations
0.912
95%
CI
[0.872–0.940]
0.960
[0.941–0.973]
0.995
[0.993–0.997]
CSA;
Bland–Altman
Analysis
shows
that
spread
points
is
quite
uniform
around
bias
lines
evidence
strong
any
variable.
(4)
Conclusions:
study
demonstrated
this
new
automatic
based
machine
learning
AI
architecture
parameters
femoris
conventional
measurement.
Clinical Oncology,
Journal Year:
2024,
Volume and Issue:
36(8), P. e269 - e281
Published: March 15, 2024
Radiomics
is
a
promising
tool
for
the
development
of
quantitative
biomarkers
to
support
clinical
decision-making.
It
has
been
shown
improve
prediction
response
treatment
and
outcome
in
different
settings,
particularly
field
radiation
oncology
by
optimising
dose
delivery
solutions
reducing
rate
radiation-induced
side
effects,
leading
fully
personalised
approach.Despite
results
offered
radiomics
at
each
these
stages,
standardised
methodologies,
reproducibility
interpretability
are
still
lacking,
limiting
potential
impact
tools.In
this
review,
we
briefly
describe
principles
most
relevant
applications
stage
cancer
management
framework
oncology.
Furthermore,
integration
into
decision
systems
analysed,
defining
challenges
offering
possible
translating
clinically
applicable
tool.
Frontiers in Pharmacology,
Journal Year:
2023,
Volume and Issue:
14
Published: Nov. 1, 2023
Radiomics
has
become
a
research
field
that
involves
the
process
of
converting
standard
nursing
images
into
quantitative
image
data,
which
can
be
combined
with
other
data
sources
and
subsequently
analyzed
using
traditional
biostatistics
or
artificial
intelligence
(Al)
methods.
Due
to
capture
biological
pathophysiological
information
by
radiomics
features,
these
features
have
been
proven
provide
fast
accurate
non-invasive
biomarkers
for
lung
cancer
risk
prediction,
diagnosis,
prognosis,
treatment
response
monitoring,
tumor
biology.
In
this
review,
emphasized
discussed
in
research,
including
advantages,
challenges,
drawbacks.
European Radiology Experimental,
Journal Year:
2023,
Volume and Issue:
7(1)
Published: Sept. 13, 2023
Abstract
High-grade
serous
ovarian
cancer
is
the
most
lethal
gynaecological
malignancy.
Detailed
molecular
studies
have
revealed
marked
intra-patient
heterogeneity
at
tumour
microenvironment
level,
likely
contributing
to
poor
prognosis.
Despite
large
quantities
of
clinical,
and
imaging
data
on
being
accumulated
worldwide
rise
high-throughput
computing,
frequently
remain
siloed
are
thus
inaccessible
for
integrated
analyses.
Only
a
minority
set
out
harness
artificial
intelligence
(AI)
integration
multiomics
developing
powerful
algorithms
that
capture
characteristics
multiple
scales
levels.
Clinical
data,
serum
markers,
were
used,
followed
by
genomics
transcriptomics.
The
current
literature
proves
integrative
approaches
outperform
models
based
single
types
indicates
can
be
used
longitudinal
tracking
in
space
potentially
over
time.
This
review
presents
an
overview
two
or
more
develop
AI-based
classifiers
prediction
models.
Relevance
statement
Integrative
using
classification,
prognostication,
predictive
tasks.
Key
points
•
cancer.
Current
types.
Around
60%
combination
with
clinical
data.
transcriptomics
was
infrequently
used.
Graphical
International Journal of Gynecological Cancer,
Journal Year:
2023,
Volume and Issue:
33(10), P. 1522 - 1541
Published: Sept. 15, 2023
Objective
Radiomics
is
the
process
of
extracting
quantitative
features
from
radiological
images,
and
represents
a
relatively
new
field
in
gynecological
cancers.
Cervical
cancer
has
been
most
studied
tumor
for
what
concerns
radiomics
analysis.
The
aim
this
study
was
to
report
on
clinical
applications
combined
and/or
compared
with
clinical-pathological
variables
patients
cervical
cancer.
Methods
A
systematic
review
literature
inception
February
2023
performed,
including
studies
analysing
predictive/prognostic
model,
which
or
model.
Results
total
57
334
(17.1%)
screened
met
inclusion
criteria.
majority
used
magnetic
resonance
imaging
(MRI),
but
positron
emission
tomography
(PET)/computed
(CT)
scan,
CT
ultrasound
scan
also
underwent
In
apparent
early-stage
disease,
(16/27,
59.3%)
analysed
role
signature
predicting
lymph
node
metastasis;
six
(22.2%)
investigated
prediction
detect
lymphovascular
space
involvement,
one
(3.7%)
depth
stromal
infiltration,
parametrial
infiltration.
Survival
evaluated
both
locally
advanced
settings.
No
focused
application
metastatic
recurrent
disease.
Conclusion
signatures
were
predictive
pathological
oncological
outcomes,
particularly
if
variables.
These
may
be
integrated
model
using
different
translational
characteristics,
tailor
personalize
treatment
each
patient
