arXiv (Cornell University),
Год журнала:
2022,
Номер
unknown
Опубликована: Янв. 1, 2022
Assessing
the
critical
view
of
safety
in
laparoscopic
cholecystectomy
requires
accurate
identification
and
localization
key
anatomical
structures,
reasoning
about
their
geometric
relationships
to
one
another,
determining
quality
exposure.
Prior
works
have
approached
this
task
by
including
semantic
segmentation
as
an
intermediate
step,
using
predicted
masks
then
predict
CVS.
While
these
methods
are
effective,
they
rely
on
extremely
expensive
ground-truth
annotations
tend
fail
when
is
incorrect,
limiting
generalization.
In
work,
we
propose
a
method
for
CVS
prediction
wherein
first
represent
surgical
image
disentangled
latent
scene
graph,
process
representation
graph
neural
network.
Our
representations
explicitly
encode
information
-
object
location,
class
information,
relations
improve
anatomy-driven
reasoning,
well
visual
features
retain
differentiability
thereby
provide
robustness
errors.
Finally,
address
annotation
cost,
train
our
only
bounding
box
annotations,
incorporating
auxiliary
reconstruction
objective
learn
fine-grained
boundaries.
We
show
that
not
outperforms
several
baseline
trained
with
but
also
scales
effectively
masks,
maintaining
state-of-the-art
performance.
Artificial Intelligence in Gastroenterology,
Год журнала:
2023,
Номер
4(3), С. 64 - 71
Опубликована: Дек. 7, 2023
BACKGROUND
Colorectal
cancer
is
a
major
public
health
problem,
with
1.9
million
new
cases
and
953000
deaths
worldwide
in
2020.
Total
mesorectal
excision
(TME)
the
standard
of
care
for
treatment
rectal
crucial
to
prevent
local
recurrence,
but
it
technically
challenging
surgery.
The
use
artificial
intelligence
(AI)
could
help
improve
performance
safety
TME
AIM
To
review
literature
on
AI
machine
learning
surgery
potential
future
developments.
METHODS
Online
scientific
databases
were
searched
articles
between
2020
2023.
RESULTS
search
yielded
876
results,
only
13
studies
selected
review.
specifically
rapidly
evolving
field.
There
are
number
different
algorithms
that
have
been
developed
TME,
including
instrument
detection,
anatomical
structure
identification,
image-guided
navigation
systems.
CONCLUSION
has
revolutionize
by
providing
real-time
surgical
guidance,
preventing
complications,
improving
training.
However,
further
research
needed
fully
understand
benefits
risks
arXiv (Cornell University),
Год журнала:
2022,
Номер
unknown
Опубликована: Янв. 1, 2022
Assessing
the
critical
view
of
safety
in
laparoscopic
cholecystectomy
requires
accurate
identification
and
localization
key
anatomical
structures,
reasoning
about
their
geometric
relationships
to
one
another,
determining
quality
exposure.
Prior
works
have
approached
this
task
by
including
semantic
segmentation
as
an
intermediate
step,
using
predicted
masks
then
predict
CVS.
While
these
methods
are
effective,
they
rely
on
extremely
expensive
ground-truth
annotations
tend
fail
when
is
incorrect,
limiting
generalization.
In
work,
we
propose
a
method
for
CVS
prediction
wherein
first
represent
surgical
image
disentangled
latent
scene
graph,
process
representation
graph
neural
network.
Our
representations
explicitly
encode
information
-
object
location,
class
information,
relations
improve
anatomy-driven
reasoning,
well
visual
features
retain
differentiability
thereby
provide
robustness
errors.
Finally,
address
annotation
cost,
train
our
only
bounding
box
annotations,
incorporating
auxiliary
reconstruction
objective
learn
fine-grained
boundaries.
We
show
that
not
outperforms
several
baseline
trained
with
but
also
scales
effectively
masks,
maintaining
state-of-the-art
performance.
