Международный журнал научной педиатрии,
Journal Year:
2024,
Volume and Issue:
3(9), P. 723 - 729
Published: Dec. 13, 2024
В
статье
представлен
всесторонний
обзор
патогенеза
и
клинических
проявлений
нарушений
зубного
развития,
которые
представляют
собой
значительные
проблемы
в
современной
стоматологии.
Рассматриваются
механизмы,
приводящие
к
этим
нарушениям,
с
акцентом
на
генетические,
экологические
инфекционные
факторы,
нарушают
нормальное
развитие
зубов.
Обсуждаются
различные
состояния,
такие
как
гипоплазия
эмали,
дентиновая
дисплазия,
несовершенный
амелогенез
тауродонтизм,
их
этиологические
корни
влияние
здоровье
полости
рта.
Клинические
проявления
этих
варьируются
от
эстетических
дефектов
до
функциональных
проблем
осложнений,
таких
повышенная
подвижность
зубов
частые
инфекции.
анализируются
методы
диагностики,
включая
рентгенографию,
компьютерную
томографию
генетическое
тестирование,
способствуют
раннему
выявлению
патологических
изменений.
Ранняя
диагностика
является
ключевой
для
эффективного
управления
предотвращения
дальнейших
осложнений.
также
стратегии
лечения
подходы
управлению
этими
состояниями,
реставрационные
процедуры,
ортодонтическое
лечение
хирургическое
вмешательство.
Подчеркивается
важность
раннего
вмешательства
улучшения
исходов
прогрессирующих
повреждений.
Статья
завершает
рекомендациями
по
оптимизации
клинической
практики
разработке
более
эффективных
стратегий
профилактики
развития.
Интеграция
современных
исследований
данных
направлена
улучшение
понимания
управление
сложными
состояниями.
Journal of Clinical Medicine,
Journal Year:
2023,
Volume and Issue:
12(23), P. 7378 - 7378
Published: Nov. 28, 2023
The
concept
of
machines
learning
and
acting
like
humans
is
what
meant
by
the
phrase
“artificial
intelligence”
(AI).
Several
branches
dentistry
are
increasingly
relying
on
artificial
intelligence
(AI)
tools.
literature
usually
focuses
AI
models.
These
models
have
been
used
to
detect
diagnose
a
wide
range
conditions,
including,
but
not
limited
to,
dental
caries,
vertical
root
fractures,
apical
lesions,
diseases
salivary
glands,
maxillary
sinusitis,
maxillofacial
cysts,
cervical
lymph
node
metastasis,
osteoporosis,
cancerous
alveolar
bone
loss,
need
for
orthodontic
extractions
or
treatments,
cephalometric
analysis,
age
gender
determination,
more.
primary
contemporary
applications
in
field
undergraduate
teaching
research.
Before
these
methods
can
be
everyday
dentistry,
however,
underlying
technology
user
interfaces
refined.
Diagnostics,
Journal Year:
2025,
Volume and Issue:
15(2), P. 231 - 231
Published: Jan. 20, 2025
Background:
Oral
diseases
such
as
caries,
gingivitis,
and
periodontitis
are
highly
prevalent
worldwide
often
arise
from
plaque.
This
study
focuses
on
detecting
three
plaque
stages—new,
mature,
over-mature—using
state-of-the-art
YOLO
architectures
to
enhance
early
intervention
reduce
reliance
manual
visual
assessments.
Methods:
We
compiled
a
dataset
of
531
RGB
images
177
individuals,
captured
via
multiple
mobile
devices.
Each
sample
was
treated
with
disclosing
gel
highlight
types,
then
preprocessed
for
lighting
color
normalization.
YOLOv9,
YOLOv10,
YOLOv11,
in
various
scales,
were
trained
detect
categories,
their
performance
evaluated
using
precision,
recall,
mean
Average
Precision
(mAP@50).
Results:
Among
the
tested
models,
YOLOv11m
achieved
highest
mAP@50
(0.713),
displaying
superior
detection
over-mature
Across
all
variants,
older
generally
easier
than
newer
plaque,
which
can
blend
gingival
tissue.
Applying
O’Leary
index
indicated
that
over
half
population
exhibited
severe
levels.
Conclusions:
Our
findings
demonstrate
feasibility
automated
advanced
models
varied
imaging
conditions.
approach
offers
potential
optimize
clinical
workflows,
support
diagnoses,
mitigate
oral
health
burdens
low-resource
communities.
Diagnostics,
Journal Year:
2025,
Volume and Issue:
15(6), P. 653 - 653
Published: March 7, 2025
Background/Objectives:
Accurate
localization
of
fractured
endodontic
instruments
(FEIs)
in
periapical
radiographs
(PAs)
remains
a
significant
challenge.
This
study
aimed
to
evaluate
the
performance
YOLOv8
and
Mask
R-CNN
detecting
FEIs
root
canal
treatments
(RCTs)
compare
their
diagnostic
capabilities
with
those
experienced
endodontists.
Methods:
A
data
set
1050
annotated
PAs
was
used.
models
were
trained
evaluated
for
FEI
RCT
detection.
Metrics
including
accuracy,
intersection
over
union
(IoU),
mean
average
precision
at
0.5
IoU
(mAP50),
inference
time
analyzed.
Observer
agreement
assessed
using
inter-class
correlation
(ICC),
comparisons
made
between
AI
predictions
human
annotations.
Results:
achieved
an
accuracy
97.40%,
mAP50
98.9%,
14.6
ms,
outperforming
speed
mAP50.
demonstrated
98.21%,
95%,
88.7
excelling
detailed
segmentation
tasks.
Comparative
analysis
revealed
no
statistically
differences
Conclusions:
Both
high
reliability,
comparable
YOLOv8’s
rapid
detection
make
it
particularly
suitable
real-time
clinical
applications,
while
excels
precise
segmentation.
establishes
strong
foundation
integrating
into
dental
diagnostics,
offering
innovative
solutions
improve
outcomes.
Future
research
should
address
diversity
explore
multimodal
imaging
enhanced
capabilities.
BMC Medical Imaging,
Journal Year:
2024,
Volume and Issue:
24(1)
Published: July 11, 2024
Abstract
Objectives
In
the
interpretation
of
panoramic
radiographs
(PRs),
identification
and
numbering
teeth
is
an
important
part
correct
diagnosis.
This
study
evaluates
effectiveness
YOLO-v5
in
automatic
detection,
segmentation,
deciduous
permanent
mixed
dentition
pediatric
patients
based
on
PRs.
Methods
A
total
3854
PRs
were
labelled
for
using
CranioCatch
labeling
program.
The
dataset
was
divided
into
three
subsets:
training
(
n
=
3093,
80%
total),
validation
387,
10%
total)
test
385,
total).
An
artificial
intelligence
(AI)
algorithm
models
developed.
Results
sensitivity,
precision,
F-1
score,
mean
average
precision-0.5
(mAP-0.5)
values
0.99,
0.98
respectively,
to
detection.
mAP-0.5
0.98,
segmentation.
Conclusions
can
have
potential
detect
enable
accurate
segmentation
with
dentition.
Frontiers in Dental Medicine,
Journal Year:
2025,
Volume and Issue:
6
Published: May 20, 2025
Background
Third
molar
extraction,
a
common
dental
procedure,
often
involves
complications,
such
as
alveolar
nerve
injury.
Accurate
preoperative
assessment
of
the
extraction
difficulty
and
injury
risk
is
crucial
for
better
surgical
planning
patient
outcomes.
Recent
advancements
in
deep
learning
(DL)
have
shown
potential
to
enhance
predictive
accuracy
using
panoramic
radiographic
(PR)
images.
This
systematic
review
evaluated
reliability
DL
models
predicting
third
inferior
(IAN)
risk.
Methods
A
search
was
conducted
across
PubMed,
Scopus,
Web
Science,
Embase
until
September
2024,
focusing
on
studies
assessing
complexity
IAN
PR
The
inclusion
criteria
required
report
performance
metrics.
Study
selection,
data
quality
were
independently
performed
by
two
authors
PRISMA
QUADAS-2
guidelines.
Results
Six
involving
12,419
images
met
criteria.
demonstrated
high
(up
96%)
92.9%),
with
notable
sensitivity
97.5%)
specific
classifications,
horizontal
impactions.
Geographically,
three
originated
South
Korea
one
each
from
Turkey
Thailand,
limiting
generalizability.
Despite
accuracy,
demographic
sparsely
reported,
only
providing
sex
distribution.
Conclusion
show
promise
improving
extraction.
However,
further
validation
diverse
populations
integration
clinical
workflows
are
necessary
establish
its
real-world
utility,
limitations
limited
generalizability,
selection
bias
lack
long-term
follow
up
remain
challenges.
Journal of Oral Medicine and Oral Surgery,
Journal Year:
2025,
Volume and Issue:
31(1), P. 7 - 7
Published: Jan. 1, 2025
Introduction:
Mandibular
third
molars
(MTMs)
are
the
most
frequently
impacted
teeth,
making
their
detection
and
classification
essential
before
surgical
extraction.
This
study
aims
to
develop
assess
accuracy
of
a
deep
learning
model
for
detecting
classifying
mandibular
(IMTMs)
using
panoramic
radiographs
(PRs).
Materials
methods:
The
utilized
dataset
1100
PRs
with
1200
IMTMs
711
without
MTMs.
An
oral
radiologist
validated
annotations,
data
were
split
into
training,
validation,
testing
sets.
Sobel
Third
Molar
Detection
Model
(STMD),
built
on
VGG16
architecture,
identified
Detected
MTMs
located
YOLOv7
classified
per
Winter’s
via
ResNet50-based
prediction
model.
Results:
VGG16-based
achieved
93.51%,
precision
94.64,
recall
89.47,
an
F1
score
91.97.
attained
92.17%,
92.1,
92.17,
AUC
98.28.
These
findings
demonstrate
high
reliability
both
models.
Conclusion:
ResNet50
integrated
YOLOv7,
demonstrated
suggesting
that
automatic
can
be
significantly
improved
these
Computers in Biology and Medicine,
Journal Year:
2024,
Volume and Issue:
180, P. 108927 - 108927
Published: Aug. 2, 2024
Rare
genetic
diseases
are
difficult
to
diagnose
and
this
translates
in
patient's
diagnostic
odyssey!
This
is
particularly
true
for
more
than
900
rare
including
orodental
developmental
anomalies
such
as
missing
teeth.
However,
if
left
untreated,
their
symptoms
can
become
significant
disabling
the
patient.
Early
detection
rapid
management
therefore
essential
context.
The
i-Dent
project
aims
supply
a
pre-diagnostic
tool
detect
with
tooth
agenesis
of
varying
severity
pattern.
To
identify
teeth,
image
segmentation
models
(Mask
R-CNN,
U-Net)
have
been
trained
automatic
teeth
on
patients'
panoramic
dental
X-rays.
Teeth
enables
identification
which
present
or
within
mouth.
Furthermore,
age
assessment
conducted
verify
whether
absence
an
anomaly
characteristic
age.
Due
small
size
our
dataset,
we
developed
new
technique
based
eruption
rate.
Information
about
then
used
by
final
algorithm
probabilities
propose
pre-diagnosis
disease.
results
obtained
detecting
three
types
genes
(PAX9,
WNT10A
EDA)
system
very
promising,
providing
average
accuracy
72
%.