2021
DOI: 10.1007/978-3-030-86960-1_14
|View full text |Cite
|
Sign up to set email alerts
|

Breast Fine Needle Cytological Classification Using Deep Hybrid Architectures

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
4

Relationship

2
6

Authors

Journals

citations
Cited by 13 publications
(4 citation statements)
references
References 35 publications
0
4
0
Order By: Relevance
“…Intensity normalization (Kociołek et al , 2020) and Contrast Limited Adaptive Histogram Equalization (Yussof et al , 2013) were employed for preprocessing the BreakHis dataset. Similar procedures were used in Zerouaoui et al (2021) and Nakach et al (2022b), with the objective of removing noise, eliminating shadows and improving the contrast of images. As shown in Table I, almost 67 per cent of the histological images in the BreakHis dataset were malignant.…”
Section: Methodsmentioning
confidence: 99%
“…Intensity normalization (Kociołek et al , 2020) and Contrast Limited Adaptive Histogram Equalization (Yussof et al , 2013) were employed for preprocessing the BreakHis dataset. Similar procedures were used in Zerouaoui et al (2021) and Nakach et al (2022b), with the objective of removing noise, eliminating shadows and improving the contrast of images. As shown in Table I, almost 67 per cent of the histological images in the BreakHis dataset were malignant.…”
Section: Methodsmentioning
confidence: 99%
“…Another study presented a meta-analysis [10], which affirmed the potential of neural network algorithms in aiding FNAC cancer diagnosis. At the same time [11] explored twenty-eight hybrid architectures combining various deep learning techniques for feature extraction (DenseNet 201, Inception V3, Inception ReseNet V2, MobileNet V2, ResNet 50, VGG16, and VGG19) with classifiers (multilayer perceptron (MLP), support vector machine (SVM), decision tree (DT), and K-nearest neighbor (KNN)) to advance binary classification of breast cytological images. Unfortunately, the dataset is wrongly cited, and they worked with the same dataset as in [5].…”
Section: Earlier Workmentioning
confidence: 99%
“…This section presents the data preparation process applied on the histological BreakHis dataset, which consists of data acquisition, data preprocessing using intensity normalization and Contrast Limited Adaptive Histogram Equalization (CLAHE) and data augmentation. The same process for the data preparation is followed in the studies (Zerouaoui et al , 2021; Zerouaoui and Idri, 2022), and therefore it will be summarized in this subsection.…”
Section: Data Preparationmentioning
confidence: 99%
“…In order to compare the results of the study (El Alaoui et al , 2022), and to elevate the burdens of the previous related works, this paper develops and evaluates the performances of 24 deep hybrid heterogenous ensembles (DHHtEs) using DL models (DenseNet 201 (Huang et al , 2017), Inception V3, VGG16, VGG19, Inception-ResNet-V3, MobileNet V2 and ResNet 50) for FE and ML models (MLP, SVM, DT and KNN) for classification over the BreakHis histological images dataset. The choice of the members of base learners for the DHHtEs is based on the finding of the previous studies (Zerouaoui et al , 2021; Zerouaoui and Idri, 2022) which designed 28 hybrid architectures using seven DL techniques for FE including DenseNet 201, Inception V3, VGG16, VGG19, Inception-ResNet-V3, MobileNet V2 and ResNet 50 and four ML classifiers (MLP, SVM, DT and KNN). Results showed that for all the four MF values 40×, 100×, 200× and 400× of the BreakHis dataset, the hybrid architecture MLP for classification and DenseNet 201 for feature extraction (MDEN) constructed using DenseNet 201 for FE and MLP for classification outperformed the others.…”
Section: Introductionmentioning
confidence: 99%