A Deep Learning with Metaheuristic Optimization-Driven Breast Cancer Segmentation and Classification Model using Mammogram Imaging
Engineering Technology & Applied Science Research,
Год журнала:
2025,
Номер
15(1), С. 20342 - 20347
Опубликована: Фев. 2, 2025
Cancer
is
the
second
leading
cause
of
death
globally,
with
Breast
(BC)
accounting
for
20%
new
diagnoses,
making
it
a
major
morbidity
and
mortality.
Mammography
effective
BC
detection,
but
lesion
interpretation
challenging,
prompting
development
Computer-Aided
Diagnosis
(CAD)
systems
to
assist
in
classification
detection.
Machine
Learning
(ML)
Deep
(DL)
models
are
widely
used
disease
diagnosis.
Therefore,
this
study
presents
an
Optimized
Graph
Convolutional
Recurrent
Neural
Network
based
Segmentation
Recognition
Classification
(OGCRNN-SBCRC)
technique.
In
preparation
phase,
images
masks
annotated
then
classified
as
benign
or
malignant.
To
achieve
this,
Wiener
Filter
(WF)-based
noise
removal
log
transform-based
contrast
enhancement
preprocessing.
The
OGCRNN-SBCRC
technique
utilizes
UNet++
method
segmentation
RMSProp
optimizer
parameter
tuning.
addition,
employs
ConvNeXtTiny
Convolution
(CNN)
approach
feature
extraction.
For
(GCRNN)
model
used.
Finally,
Aquila
Optimizer
(AO)
employed
hyperparameter
tuning
GCRNN
approach.
simulation
analysis
methodology,
using
image
dataset,
demonstrated
superior
performance
accuracy
99.65%,
surpassing
existing
models.
Язык: Английский
Integrating sparse graph convolution and capsule networks for superior breast cancer diagnosis
Evolving Systems,
Год журнала:
2025,
Номер
16(2)
Опубликована: Март 13, 2025
Язык: Английский
A convolution and transformer-based method with effective stain normalization for breast cancer detection from whole slide images
Biomedical Signal Processing and Control,
Год журнала:
2025,
Номер
110, С. 108138 - 108138
Опубликована: Май 26, 2025
Язык: Английский
Smart neural network and cognitive computing process for multi task nuclei detection segmentation and classification in breast cancer histopathology images
Scientific Reports,
Год журнала:
2025,
Номер
15(1)
Опубликована: Май 26, 2025
Abstract
The
detection,
segmentation,
and
differentiation
of
benign
malignant
nuclei
from
the
histopathology
images
is
a
challenging
task
for
early
diagnosis
breast
cancer.
Misinterpretation
True
Negative
(TN)
False
Positive
(FP)
can
generate
incorrect
results.
proposed
Cognitive
Computing
Process
(CCP)
detects
segments
using
Deep
U-Net
with
Spatial
Attention
Mechanisms
(SAM)
microns-per-pixel
measurements
to
accurately
locate
assess
density.
To
separate
malignant,
patches
are
introduced
leverage
model’s
learning
process.
Smart
Neural
Network
(SNN)
models
contain
Convolutional
(SCNN)
(DCNN)
reduce
Proposed
CCP
SNN
were
evaluated
BreakHis
dataset,
which
contains
5547
samples
at
various
magnifications
(40×,
100×,
200×,
400×).
These
processed
into
patches,
totaling
11,642,
9282,
9102,
9678
each
224
×
pixels.
model
outperformed
state-of-the-art
UNet,
Residual
UNet
(ResUNet),
Long
Short-Term
Memory
(CNN-LSTM)
Dice
coefficient
99.90%,
an
F1-score
99.04%,
precision
99.80%,
recall
99.76%.
process
began
rate
0.01
decay
0.8,
SCNN
achieved
false
negative
positive
rates
0.04
0.05
low-density
400×
40×
magnification,
respectively.
In
contrast,
recorded
0.02
0.01.
For
high-density
FN
FP
0.0
0.08,
while
DCNN
reported
0.09
0.0.
Networks
high
(77–99%),
(75–99%),
AUC
86–100%.
combination
improved
accuracy
over
existing
CNN
like
ResNet50,
VGG19,
DenseNet109,
DenseNet201,
VGG16.
An
ablation
study
showed
p-value
0.00003
based
on
AUC,
highlighting
potential
enhance
automated
cancer
support
clinical
decision-making.
Язык: Английский
Advanced Analytical Methods for Multi-Spectral Transmission Imaging Optimization: Enhancing Breast Tissue Heterogeneity Detection and Tumor Screening with Hybrid Image Processing and Deep Learning
Analytical Methods,
Год журнала:
2024,
Номер
unknown
Опубликована: Ноя. 15, 2024
This
paper
combines
SPM,
M_D-FA,
and
DLNM
to
improve
multi-spectral
image
quality
classify
heterogeneities.
Results
show
significant
accuracy
enhancements,
achieving
95.47%
with
VGG19
98.47%
ResNet101
in
breast
tumor
screening.
Язык: Английский