Cancer Communications,
Journal Year:
2020,
Volume and Issue:
40(4), P. 154 - 166
Published: April 1, 2020
Abstract
The
development
of
digital
pathology
and
progression
state‐of‐the‐art
algorithms
for
computer
vision
have
led
to
increasing
interest
in
the
use
artificial
intelligence
(AI),
especially
deep
learning
(DL)‐based
AI,
tumor
pathology.
DL‐based
been
developed
conduct
all
kinds
work
involved
pathology,
including
diagnosis,
subtyping,
grading,
staging,
prognostic
prediction,
as
well
identification
pathological
features,
biomarkers
genetic
changes.
applications
AI
not
only
contribute
improve
diagnostic
accuracy
objectivity
but
also
reduce
workload
pathologists
subsequently
enable
them
spend
additional
time
on
high‐level
decision‐making
tasks.
In
addition,
is
useful
meet
requirements
precision
oncology.
However,
there
are
still
some
challenges
relating
implementation
issues
algorithm
validation
interpretability,
computing
systems,
unbelieving
attitude
pathologists,
clinicians
patients,
regulators
reimbursements.
Herein,
we
present
an
overview
how
AI‐based
approaches
could
be
integrated
into
workflow
discuss
perspectives
Advances in Anatomic Pathology,
Journal Year:
2017,
Volume and Issue:
24(6), P. 311 - 335
Published: Aug. 2, 2017
Assessment
of
the
immune
response
to
tumors
is
growing
in
importance
as
prognostic
implications
this
are
increasingly
recognized,
and
immunotherapies
evaluated
implemented
different
tumor
types.
However,
many
approaches
can
be
used
assess
describe
response,
which
limits
efforts
at
implementation
a
routine
clinical
biomarker.
In
part
1
review,
we
have
proposed
standardized
methodology
tumor-infiltrating
lymphocytes
(TILs)
solid
tumors,
based
on
International
Immuno-Oncology
Biomarkers
Working
Group
guidelines
for
invasive
breast
carcinoma.
2
discuss
available
evidence
predictive
value
TILs
common
including
carcinomas
lung,
gastrointestinal
tract,
genitourinary
system,
gynecologic
head
neck,
well
primary
brain
mesothelioma
melanoma.
The
particularities
emphases
TIL
assessment
types
discussed.
propose
adapted
may
standard
against
other
compared.
Standardization
will
help
clinicians,
researchers
pathologists
conclusively
evaluate
utility
simple
biomarker
current
era
immunotherapy.
Journal of Clinical Oncology,
Journal Year:
2019,
Volume and Issue:
37(7), P. 559 - 569
Published: Jan. 16, 2019
Purpose
The
aim
of
the
current
study
was
to
conduct
a
pooled
analysis
studies
that
have
investigated
prognostic
value
tumor-infiltrating
lymphocytes
(TILs)
in
early-stage
triple
negative
breast
cancer
(TNBC).
Methods
Participating
had
evaluated
percentage
infiltration
stromally
located
TILs
(sTILs)
were
quantified
same
manner
patient
diagnostic
samples
TNBC
treated
with
anthracycline-based
chemotherapy
or
without
taxanes.
Cox
proportional
hazards
regression
models
stratified
by
trial
used
for
invasive
disease-free
survival
(iDFS;
primary
end
point),
distant
(D-DFS),
and
overall
(OS),
fitting
sTILs
as
continuous
variable
adjusted
clinicopathologic
factors.
Results
We
collected
individual
data
from
2,148
patients
nine
studies.
Average
age
50
years
(range,
22
85
years),
33%
node
negative.
average
23%
(standard
deviation,
20%),
77%
1%
more
sTILs.
significantly
lower
older
(
P
=
.001),
larger
tumor
size
.01),
nodal
involvement
.02),
histologic
grade
.001).
A
total
736
iDFS
548
D-DFS
events
533
deaths
observed.
In
multivariable
model,
added
significant
independent
information
all
points
(likelihood
ratio
χ
2
,
48.9
iDFS;
<
.001;
55.8
D-DFS;
48.5
OS;
Each
10%
increment
corresponded
an
hazard
0.87
(95%
CI,
0.83
0.91)
iDFS,
0.79
0.88)
D-DFS,
0.84
0.89)
OS.
node-negative
≥
30%,
3-year
92%
89%
98%),
97%
95%
99%),
OS
99%
100%).
Conclusion
This
confirms
strong
role
excellent
high
after
adjuvant
supports
integration
model
TNBC.
can
be
found
at
www.tilsinbreastcancer.org
.
