Applied Sciences,
Год журнала:
2024,
Номер
14(23), С. 11016 - 11016
Опубликована: Ноя. 27, 2024
Micro-computed
tomography
(micro-CT)
is
an
invaluable
tool
for
the
evaluation
of
dental
implant
success,
whereby
assessment
bone
microstructure
conducted.
This
review
examines
role
micro-CT
in
evaluating
implants.
A
current
literature
reveals
that
enables
accurate
measurement
volume,
trabecular
morphology,
and
connectivity
density,
all
which
play
a
crucial
stability.
The
high-resolution
three-dimensional
visualization
capabilities
are
also
beneficial
analysis
osseointegration
augmentation
biomaterials.
Despite
existence
challenges
such
as
imaging
artifacts
limitations
vivo
applications,
advancements
sub-micron
resolution
artificial
intelligence
integration
offer
promise
improving
diagnostic
capabilities.
Micro-CT
provides
valuable
insights
into
microarchitecture
dynamics,
have
potential
to
enhance
pre-operative
planning
clinical
outcomes
implantology.
Future
research
should
prioritize
standardization
protocols
exploration
direct
applications
this
technology.
Scientific Reports,
Год журнала:
2024,
Номер
14(1)
Опубликована: Июнь 16, 2024
Abstract
Recent
studies
have
shown
that
dental
implants
high
long-term
survival
rates,
indicating
their
effectiveness
compared
to
other
treatments.
However,
there
is
still
a
concern
regarding
treatment
failure.
Deep
learning
methods,
specifically
U-Net
models,
been
effectively
applied
analyze
medical
and
images.
This
study
aims
utilize
models
segment
bone
in
regions
where
teeth
are
missing
cone-beam
computerized
tomography
(CBCT)
scans
predict
the
positions
of
implants.
The
proposed
were
CBCT
dataset
Taibah
University
Dental
Hospital
(TUDH)
patients
between
2018
2023.
They
evaluated
using
different
performance
metrics
validated
by
domain
expert.
experimental
results
demonstrated
outstanding
terms
dice,
precision,
recall
for
segmentation
(0.93,
0.94,
0.93,
respectively)
with
low
volume
error
(0.01).
offer
promising
automated
implant
planning
implantologists.
Scientific Reports,
Год журнала:
2024,
Номер
14(1)
Опубликована: Июнь 1, 2024
Abstract
Most
artificial
intelligence
(AI)
studies
have
attempted
to
identify
dental
implant
systems
(DISs)
while
excluding
low-quality
and
distorted
radiographs,
limiting
their
actual
clinical
use.
This
study
aimed
evaluate
the
effectiveness
of
an
AI
model,
trained
on
a
large
multi-center
dataset,
in
identifying
different
types
DIS
radiographs.
Based
fine-tuned
pre-trained
ResNet-50
algorithm,
156,965
panoramic
periapical
radiological
images
were
used
as
training
validation
datasets,
530
four
(including
those
not
perpendicular
axis
fixture,
radiation
overexposure,
cut
off
apex
containing
foreign
bodies)
test
datasets.
Moreover,
accuracy
performance
classification
was
compared
using
five
periodontists.
evaluation
model
achieved
accuracy,
precision,
recall,
F1
score
metrics
95.05%,
95.91%,
92.49%,
94.17%,
respectively.
However,
periodontists
performed
nine
DISs
based
achieving
mean
overall
37.2
±
29.0%.
Within
limitations
this
study,
demonstrated
superior
from
or
outperforming
professionals
tasks.
for
application
AI,
extensive
standardization
research
radiographic
is
essential.
In
recent
years,
artificial
intelligence
(AI)
has
made
remarkable
advancements
and
achieved
significant
accomplishments
across
the
entire
field
of
dentistry.
Notably,
efforts
to
apply
AI
in
prosthodontics
are
continually
progressing.
This
scoping
review
aims
present
applications
performance
dental
crown
prostheses
related
topics.
We
conducted
a
literature
search
PubMed,
Scopus,
Web
Science,
Google
Scholar,
IEEE
Xplore
databases
from
January
2010
2024.
The
included
articles
addressed
application
various
aspects
treatment,
including
fabrication,
assessment,
prognosis.
initial
electronic
yielded
393
records,
which
were
reduced
315
after
eliminating
duplicate
references.
inclusion
criteria
led
analysis
12
eligible
publications
qualitative
review.
AI-based
this
detection
finish
line,
evaluation
color
matching,
preparation,
designed
by
AI,
identification
an
intraoral
photo,
prediction
debonding
probability.
potential
increase
efficiency
processes
such
as
fabricating
evaluating
crowns,
with
high
level
accuracy
reported
most
analyzed
studies.
However,
number
studies
focused
on
designing
crowns
using
software,
these
had
small
patients
did
not
always
their
algorithms.
Standardized
protocols
for
reporting
needed
evidence
effectiveness.
Clinical Implant Dentistry and Related Research,
Год журнала:
2025,
Номер
27(1)
Опубликована: Янв. 23, 2025
ABSTRACT
Objectives
This
study
aimed
to
develop
an
artificial
intelligence
(AI)‐based
deep
learning
model
for
the
detection
and
numbering
of
dental
implants
in
panoramic
radiographs.
The
novelty
this
lies
its
ability
both
detect
number
implants,
offering
improvements
clinical
decision
support
implantology.
Materials
Methods
A
retrospective
dataset
32
585
radiographs,
collected
from
patients
at
Sivas
Cumhuriyet
University
between
2014
2024,
was
utilized.
Two
deep‐learning
models
were
trained
using
YOLOv8
algorithm.
first
classified
regions
jaw
teeth
identify
implant
regions,
while
second
performed
segmentation.
Performance
metrics
including
precision,
recall,
F1‐score
used
evaluate
model's
effectiveness.
Results
segmentation
achieved
a
precision
91.4%,
recall
90.5%,
93.1%.
For
implant‐numbering
task,
ranged
0.94
0.981,
0.895
0.956,
F1‐scores
0.917
0.966
across
various
regions.
analysis
revealed
that
most
frequently
located
maxillary
posterior
region.
Conclusions
AI
demonstrated
high
accuracy
detecting
technology
offers
potential
reduce
clinicians'
workload
improve
diagnostic
Further
validation
more
diverse
datasets
is
recommended
enhance
applicability.
Clinical
Relevance
could
revolutionize
classification,
providing
fast,
objective
analyses
decision‐making
practices.
Clinical and Experimental Dental Research,
Год журнала:
2025,
Номер
11(1)
Опубликована: Фев. 1, 2025
ABSTRACT
Objectives
There
is
currently
a
scarcity
of
data
on
the
frequency
and
bilateral
symmetry
position
other
characteristics
mental
foramen
(MF)
accessory
foramina
in
Yemen.
The
objective
this
study
was
to
analyze
characteristics,
as
well
MF,
sample
Yemeni
population.
Materials
Methods
A
retrospective
analysis
conducted
500
digital
panoramic
radiographs
(1000
sides).
examined
various
including
horizontal
vertical
positions,
shapes,
appearances,
presence
foramina.
Additionally,
explored
potential
associations
between
these
variables
such
subject's
gender,
sides,
symmetry.
Data
performed
using
SPSS,
statistical
significance
evaluated
chi‐square
tests;
p
value
set
at
0.05.
Results
MF
most
frequently
observed
first
second
lower
premolars
(63.2%).
predominantly
below
apices
(66.2%).
majority
MFs
had
round
shape
(46.3%).
In
72%
75.6%
cases,
there
continuous
descending
relationship
mandibular
canal,
respectively.
Accessory
present
3.8%
cases.
Gender
differences
were
significant
for
pattern
canal
right
side.
rates
features
included
positions
(87.4%),
(82.6%),
shapes
(80.4%).
Conclusion
commonly
situated
horizontally
vertically
teeth.
showed
with
canal.
instances,
symmetrical
both
sides.
International Journal of Oral and Maxillofacial Surgery,
Год журнала:
2025,
Номер
unknown
Опубликована: Май 1, 2025
The
aim
of
this
systematic
review
was
to
comprehensively
analyse
recent
studies
on
the
application
artificial
intelligence
(AI)
in
dental
implantology.
PRISMA
guidelines
were
followed.
Five
databases
accessed:
Scopus,
Web
Science,
MEDLINE/PubMed,
IEEE
Xplore,
and
JSTOR.
Documents
published
between
2018
October
15,
2024
relating
AI
implantology
considered.
Exclusions
encompassed
reviews,
opinion
articles,
books,
conference
references,
using
as
a
supplementary
method,
for
teaching
implant
dentistry,
fabrication,
prothesis,
or
design.
A
total
120
relevant
papers
included.
Risk
bias
assessed
PROBAST.
Findings
demonstrated
extensive
utilization
various
aspects
implantology:
guided
surgery,
diagnosis,
classification
oral
structures,
bone
classification,
restorations,
planning,
prognosis.
Deep
learning
algorithms
employed
89.2%
studies,
predominantly
utilizing
image
data
(72.0%
two-dimensional
images
28.0%
three-dimensional
images).
Publications
doubled
2022
compared
previous
year
have
remained
consistent
since.
Despite
growth,
field
remains
relatively
underdeveloped.
However,
with
advancements
technology
quality,
substantial
progress
is
anticipated
forthcoming
years.
Remarkably,
11
found
high
risk
bias.
Recent
advancements
in
Artificial
Intelligence
(AI)
have
transformed
the
healthcare
field,
particularly
through
chatbots
like
ChatGPT,
OpenEvidence,
and
MediSearch.
These
tools
analyze
complex
data
to
aid
clinical
decision-making,
enhancing
efficiency
diagnosis,
treatment
planning,
patient
management.
When
applied
"All-on-Four"
dental
implant
concept,
AI
facilitates
immediate
prosthetic
restorations
meets
demand
for
expert
guidance.
This
integration
boosts
long-term
success
of
surgical
outcomes
by
providing
real-time
support
improving
education
postoperative
satisfaction.
study
aimed
evaluate
effectiveness
three
AI-powered
chatbots-ChatGPT
4.0,
MediSearch-in
answering
frequently
asked
questions
regarding
All-on-Four
concept.
investigated
response
accuracy
common
queries
about
Using
alsoasked.com,
twenty
pertinent
questions-ten
patient-focused
ten
technical-were
identified.
Oral
maxillofacial
surgeons
evaluated
chatbot
responses
using
a
5-point
Likert
scale.
Statistical
analysis
was
performed
with
Kruskal-Wallis
test,
supplemented
pairwise
Mann-Whitney
U
tests
Bonferroni
correction,
assess
significance
differences
among
chatbots'
performances.
The
test
showed
statistically
significant
between
both
technical
(p
<
0.01).
Pairwise
comparisons
were
test.
While
found
each
questions,
no
difference
observed
ChatGPT
MediSearch
=
0.158).
comparing
same
it
that
better
0.001).
Advancements
technology
made
an
inevitable
influence
specialized
medical
fields
such
as
Oral,
Maxillofacial
Surgery.
Our
findings
indicate
these
can
provide
valuable
information
patients
undergoing
procedures
serve
resource
professionals.
