Journal of Personalized Medicine,
Journal Year:
2020,
Volume and Issue:
10(4), P. 211 - 211
Published: Nov. 6, 2020
Mammography
plays
an
important
role
in
screening
breast
cancer
among
females,
and
artificial
intelligence
has
enabled
the
automated
detection
of
diseases
on
medical
images.
This
study
aimed
to
develop
a
deep
learning
model
detecting
digital
mammograms
various
densities
evaluate
performance
compared
previous
studies.
From
1501
subjects
who
underwent
mammography
between
February
2007
May
2015,
craniocaudal
mediolateral
view
were
included
concatenated
for
each
breast,
ultimately
producing
3002
merged
Two
convolutional
neural
networks
trained
detect
any
malignant
lesion
The
performances
tested
using
301
images
from
284
meta-analysis
including
12
mean
area
under
receiver-operating
characteristic
curve
(AUC)
mammogram
was
0.952
±
0.005
by
DenseNet-169
0.954
0.020
EfficientNet-B5,
respectively.
malignancy
decreased
as
density
increased
(density
A,
AUC
=
0.984
vs.
D,
0.902
DenseNet-169).
When
patients’
age
used
covariate
detection,
showed
little
change
(mean
AUC,
0.953
0.005).
sensitivity
specificity
(87
88%,
respectively)
surpassed
values
(81
82%,
obtained
meta-analysis.
Deep
would
work
efficiently
densities,
which
could
be
maximized
breasts
with
lower
parenchyma
density.
npj Digital Medicine,
Journal Year:
2021,
Volume and Issue:
4(1)
Published: Jan. 8, 2021
Abstract
A
decade
of
unprecedented
progress
in
artificial
intelligence
(AI)
has
demonstrated
the
potential
for
many
fields—including
medicine—to
benefit
from
insights
that
AI
techniques
can
extract
data.
Here
we
survey
recent
development
modern
computer
vision
techniques—powered
by
deep
learning—for
medical
applications,
focusing
on
imaging,
video,
and
clinical
deployment.
We
start
briefly
summarizing
a
convolutional
neural
networks,
including
tasks
they
enable,
context
healthcare.
Next,
discuss
several
example
imaging
applications
stand
to
benefit—including
cardiology,
pathology,
dermatology,
ophthalmology–and
propose
new
avenues
continued
work.
then
expand
into
general
highlighting
ways
which
workflows
integrate
enhance
care.
Finally,
challenges
hurdles
required
real-world
deployment
these
technologies.
Water Science & Technology,
Journal Year:
2020,
Volume and Issue:
82(12), P. 2635 - 2670
Published: Aug. 5, 2020
Abstract
The
global
volume
of
digital
data
is
expected
to
reach
175
zettabytes
by
2025.
volume,
variety
and
velocity
water-related
are
increasing
due
large-scale
sensor
networks
increased
attention
topics
such
as
disaster
response,
water
resources
management,
climate
change.
Combined
with
the
growing
availability
computational
popularity
deep
learning,
these
transformed
into
actionable
practical
knowledge,
revolutionizing
industry.
In
this
article,
a
systematic
review
literature
conducted
identify
existing
research
that
incorporates
learning
methods
in
sector,
regard
monitoring,
governance
communication
resources.
study
provides
comprehensive
state-of-the-art
approaches
used
industry
for
generation,
prediction,
enhancement,
classification
tasks,
serves
guide
how
utilize
available
future
challenges.
Key
issues
challenges
application
techniques
domain
discussed,
including
ethics
technologies
decision-making
management
governance.
Finally,
we
provide
recommendations
directions
models
hydrology
Artificial Intelligence Review,
Journal Year:
2022,
Volume and Issue:
55(6), P. 4755 - 4808
Published: Jan. 18, 2022
Human
activity
recognition
(HAR)
has
multifaceted
applications
due
to
its
worldly
usage
of
acquisition
devices
such
as
smartphones,
video
cameras,
and
ability
capture
human
data.
While
electronic
their
are
steadily
growing,
the
advances
in
Artificial
intelligence
(AI)
have
revolutionized
extract
deep
hidden
information
for
accurate
detection
interpretation.
This
yields
a
better
understanding
rapidly
growing
devices,
AI,
applications,
three
pillars
HAR
under
one
roof.
There
many
review
articles
published
on
general
characteristics
HAR,
few
compared
all
at
same
time,
explored
impact
evolving
AI
architecture.
In
our
proposed
review,
detailed
narration
is
presented
covering
period
from
2011
2021.
Further,
presents
recommendations
an
improved
design,
reliability,
stability.
Five
major
findings
were:
(1)
constitutes
applications;
(2)
dominated
healthcare
industry;
(3)
Hybrid
models
infancy
stage
needs
considerable
work
providing
stable
reliable
design.
these
trained
need
solid
prediction,
high
accuracy,
generalization,
finally,
meeting
objectives
without
bias;
(4)
little
was
observed
abnormality
during
actions;
(5)
almost
no
been
done
forecasting
actions.
We
conclude
that:
(a)
industry
will
evolve
terms
type
AI.
(b)
provide
powerful
impetus
future.
IEEE Internet of Things Journal,
Journal Year:
2021,
Volume and Issue:
8(14), P. 11016 - 11040
Published: Feb. 9, 2021
Recent
advances
in
the
Internet
of
Things
(IoT)
are
giving
rise
to
a
proliferation
interconnected
devices,
allowing
use
various
smart
applications.
The
enormous
number
IoT
devices
generates
large
volume
data
that
requires
further
intelligent
analysis
and
processing
methods
such
as
deep
learning
(DL).
Notably,
DL
algorithms,
when
applied
Industrial
(IIoT),
can
provide
new
applications,
assembling,
manufacturing,
efficient
networking,
accident
detection
prevention.
Motivated
by
these
numerous
this
article,
we
present
key
potentials
IIoT.
First,
review
techniques,
including
convolutional
neural
networks,
autoencoders,
recurrent
well
their
different
industries.
We
then
outline
variety
cases
for
IIoT
systems,
metering,
agriculture.
delineate
several
research
challenges
with
effective
design
appropriate
implementation
DL-IIoT.
Finally,
future
directions
inspire
motivate
area.
Healthcare,
Journal Year:
2022,
Volume and Issue:
10(12), P. 2493 - 2493
Published: Dec. 9, 2022
:
The
price
of
medical
treatment
continues
to
rise
due
(i)
an
increasing
population;
(ii)
aging
human
growth;
(iii)
disease
prevalence;
(iv)
a
in
the
frequency
patients
that
utilize
health
care
services;
and
(v)
increase
price.
British Journal of Ophthalmology,
Journal Year:
2020,
Volume and Issue:
105(2), P. 158 - 168
Published: June 12, 2020
With
the
advancement
of
computational
power,
refinement
learning
algorithms
and
architectures,
availability
big
data,
artificial
intelligence
(AI)
technology,
particularly
with
machine
deep
learning,
is
paving
way
for
‘intelligent’
healthcare
systems.
AI-related
research
in
ophthalmology
previously
focused
on
screening
diagnosis
posterior
segment
diseases,
diabetic
retinopathy,
age-related
macular
degeneration
glaucoma.
There
now
emerging
evidence
demonstrating
application
AI
to
management
a
variety
anterior
conditions.
In
this
review,
we
provide
an
overview
applications
addressing
keratoconus,
infectious
keratitis,
refractive
surgery,
corneal
transplant,
adult
paediatric
cataracts,
angle-closure
glaucoma
iris
tumour,
highlight
important
clinical
considerations
adoption
technologies,
potential
integration
telemedicine
future
directions.
Neurology and Therapy,
Journal Year:
2019,
Volume and Issue:
8(2), P. 351 - 365
Published: Aug. 21, 2019
Deciphering
the
massive
volume
of
complex
electronic
data
that
has
been
compiled
by
hospital
systems
over
past
decades
potential
to
revolutionize
modern
medicine,
as
well
present
significant
challenges.
Deep
learning
is
uniquely
suited
address
these
challenges,
and
recent
advances
in
techniques
hardware
have
poised
field
medical
machine
for
transformational
growth.
The
clinical
neurosciences
are
particularly
positioned
benefit
from
given
subtle
presentation
symptoms
typical
neurologic
disease.
Here
we
review
various
domains
which
deep
algorithms
already
provided
impetus
change-areas
such
image
analysis
improved
diagnosis
Alzheimer's
disease
early
detection
acute
events;
segmentation
quantitative
evaluation
neuroanatomy
vasculature;
connectome
mapping
Alzheimer's,
autism
spectrum
disorder,
attention
deficit
hyperactivity
disorder;
mining
microscopic
electroencephalogram
signals
granular
genetic
signatures.
We
additionally
note
important
challenges
integration
tools
setting
discuss
barriers
tackling
currently
exist.
