Geometric and dosimetric evaluation of a commercial AI auto‐contouring tool on multiple anatomical sites in CT scans
Journal of Applied Clinical Medical Physics,
Год журнала:
2025,
Номер
unknown
Опубликована: Март 17, 2025
Abstract
Current
radiotherapy
practices
rely
on
manual
contouring
of
CT
scans,
which
is
time‐consuming,
prone
to
variability,
and
requires
highly
trained
experts.
There
a
need
for
more
efficient
consistent
methods.
This
study
evaluated
the
performance
Varian
Ethos
AI
auto‐contouring
tool
assess
its
potential
integration
into
clinical
workflows.
retrospective
included
223
patients
with
treatment
sites
in
pelvis,
abdomen,
thorax,
head
neck
regions.
The
generated
auto‐contours
each
patients’
pre‐treatment
planning
CT,
45
unique
structures
were
across
cohort.
Multiple
measures
geometric
similarity
computed,
including
surface
Dice
Similarity
Coefficient
(sDSC)
mean
distance
agreement
(MDA).
Dosimetric
concordance
was
by
comparing
dose
maximum
2
cm
3
(D
cc
)
between
contours.
demonstrated
high
accuracy
well‐defined
like
bladder,
lungs,
femoral
heads.
Smaller
those
less
defined
boundaries,
such
as
optic
nerves
duodenum,
showed
lower
agreement.
Over
70%
sDSC
>
0.8,
74%
had
MDA
<
2.5
mm.
Geometric
generally
correlated
dosimetric
concordance,
however
differences
contour
definitions
did
result
some
exhibiting
deviations.
offers
promising
reliability
many
anatomical
structures,
supporting
use
Auto‐contouring
errors,
although
rare,
highlight
importance
ongoing
QA
expert
oversight.
Язык: Английский
Interobserver variation in organs at risk contouring in head and neck cancer according to the DAHANCA guidelines
Radiotherapy and Oncology,
Год журнала:
2024,
Номер
197, С. 110337 - 110337
Опубликована: Май 19, 2024
Язык: Английский
Cumulative rib fracture risk after stereotactic body radiotherapy in patients with localized non-small cell lung cancer
Radiotherapy and Oncology,
Год журнала:
2024,
Номер
200, С. 110481 - 110481
Опубликована: Авг. 17, 2024
Язык: Английский
Potential of E-Learning Interventions and Artificial Intelligence–Assisted Contouring Skills in Radiotherapy: The ELAISA Study
JCO Global Oncology,
Год журнала:
2024,
Номер
10
Опубликована: Авг. 1, 2024
PURPOSE
Most
research
on
artificial
intelligence–based
auto-contouring
as
template
(AI-assisted
contouring)
for
organs-at-risk
(OARs)
stem
from
high-income
countries.
The
effect
and
safety
are,
however,
likely
to
depend
local
factors.
This
study
aimed
investigate
the
effects
of
AI-assisted
contouring
teaching
time
contour
quality
among
radiation
oncologists
(ROs)
working
in
low-
middle-income
countries
(LMICs).
MATERIALS
AND
METHODS
Ninety-seven
ROs
were
randomly
assigned
either
manual
or
eight
OARs
two
head-and-neck
cancer
cases
with
an
in-between
session
guidelines.
Thereby,
(yes/no)
was
quantified.
Second,
completed
short-term
long-term
follow-up
all
using
AI
assistance.
Contour
quantified
Dice
Similarity
Coefficient
(DSC)
between
ROs'
contours
expert
consensus
contours.
Groups
compared
absolute
differences
medians
95%
CIs.
RESULTS
without
previous
increased
DSC
optic
nerve
(by
0.05
[0.01;
0.10]),
oral
cavity
(0.10
[0.06;
0.13]),
parotid
(0.07
[0.05;
0.12]),
spinal
cord
(0.04
0.06]),
mandible
(0.02
0.03]).
Contouring
decreased
brain
(–1.41
[–2.44;
–0.25]),
(–6.60
[–8.09;
–3.35]),
(–0.19
[–0.47;
–0.02]),
(–1.80
[–2.66;
–0.32]),
thyroid
(–1.03
[–2.18;
–0.05]).
Without
contouring,
(0.05
0.09])
[0.02;
0.07]),
(2.36
[–0.51;
5.14]),
(1.42
[–0.08;
4.14]),
(1.60
[–0.04;
2.22]).
CONCLUSION
suggested
that
is
safe
beneficial
LMICs.
Prospective
clinical
trials
should,
be
conducted
upon
implementation
confirm
effects.
Язык: Английский
Recent advances in the clinical applications of machine learning in proton therapy
medRxiv (Cold Spring Harbor Laboratory),
Год журнала:
2024,
Номер
unknown
Опубликована: Окт. 10, 2024
ABSTRACT
The
present
systematic
review
is
an
effort
to
explore
the
different
clinical
applications
and
current
implementations
of
machine/deep
learning
in
proton
therapy.
It
will
assist
as
a
reference
for
scientists,
researchers,
other
health
professionals
who
are
working
field
radiation
therapy
need
up-to-date
knowledge
regarding
recent
technological
advances.
This
utilized
Pubmed
Embase
search
identify
research
studies
interest
published
between
2019
2024.
literature
PubMed
pertinent
machine
time
period
2024
was
chosen
capture
most
signficant
An
initial
on
made
with
strategy
“‘proton
therapy’,
‘machine
learning’,
‘deep
learning’”,
filters
including
only
articles
from
2024,
returning
84
results.
Next,
“(“proton
therapy”)
AND
(“machine
learning”
OR
“deep
learning”)”
searched
Embase,
retrieving
546
When
filtered
articles,
250
results
were
retrieved
Embase.
Reviews,
editorials,
technical
notes,
any
language
than
English
excluded
broad
both
databases.
Filtering
by
title,
papers
based
two
inclusion
factors:
explicit
application
to,
or
mention
of,
therapy,
algorithm.
Assessing
abstract,
works
irrelevant
specific
aspects
workflow
scope
excluded.
Upon
assessing
evaluating
full
texts
quality,
that
lacked
clear
explanation
model
architecture.
If
multiple
same
architecture
applied
step
identified,
chronologically
advancement
included.
additional
5
met
all
criteria
identified
references
papers.
In
total,
38
relevant
have
been
summarized
incorporated
into
this
review.
first
comprehensively
cover
potential
areas
workflow.
Язык: Английский
Danish and Swedish national data collections for cancer – solutions for radiotherapy
Clinical Oncology,
Год журнала:
2024,
Номер
37, С. 103657 - 103657
Опубликована: Окт. 12, 2024
Язык: Английский
Think big–think BiGART. The 21st Acta Oncologica Symposium—BiGART 2023
Acta Oncologica,
Год журнала:
2023,
Номер
62(11), С. 1357 - 1359
Опубликована: Окт. 5, 2023
Acta
Oncologica
has
supported
Nordic
symposia
from
the
start
in
late
eighties
and
since
2006
they
have
a
biannual
Symposium
hosted
by
radiotherapy
research
environment
Aarhus,
Denmark.The
topics
included
stereotactic
body
(2006),
imageguided
(2008),
2010
BIGART
(biologyguided
adaptive
radiotherapy),
with
current
being
seventh
this
series
[1].The
BiGART
meeting
concept
is
unique
for
bridging
clinical
translational
radiation
oncology.Clinical
studies,
physics,
radiobiology
are
equally
important
parts
that
must
interact
integrate-and
just
what
aim
of
BiGART.BiGART
2023
21st
were
held
20th
to
June
2023,
attracting
more
than
170
participants
13
countries
(Figure
1),
which
125
presented
their
ongoing
research,
either
stage
or
during
poster
discussion
sessions-indicating
it
was
lively
very
interactive
as
usual.BiGART
only
multidisciplinary,
multimodality,
site
unspecific
oriented
oncology
serves
such
an
glue
community.
Язык: Английский