Ensembled deep convolution neural network-based breast cancer classification with misclassification reduction algorithms

2020 ◽  
Vol 79 (25-26) ◽  
pp. 18447-18479 ◽  
Author(s):  
Ghulam Murtaza ◽  
Liyana Shuib ◽  
Ainuddin Wahid Abdul Wahab ◽  
Ghulam Mujtaba ◽  
Ghulam Raza
Keyword(s):  
Breast Cancer ◽  
Neural Network ◽  
Cancer Classification ◽  
Convolution Neural Network ◽  
Breast Cancer Classification ◽  
Deep Convolution Neural Network

scholarly journals Spectral–Spatial Features Integrated Convolution Neural Network for Breast Cancer Classification

Sensors ◽  
2020 ◽  
Vol 20 (17) ◽  
pp. 4747
Author(s):  
Hiren K Mewada ◽  
Amit V Patel ◽  
Mahmoud Hassaballah ◽  
Monagi H. Alkinani ◽  
Keyur Mahant
Keyword(s):  
Breast Cancer ◽  
Neural Network ◽  
Image Features ◽  
Cancer Classification ◽  
Convolution Neural Network ◽  
Limiting Factors ◽  
Automatic Process ◽  
Spectral Features ◽  
Breast Cancer Classification ◽  
Spatial Features

Cancer identification and classification from histopathological images of the breast depends greatly on experts, and computer-aided diagnosis can play an important role in disagreement of experts. This automatic process has increased the accuracy of the classification at a reduced cost. The advancement in Convolution Neural Network (CNN) structure has outperformed the traditional approaches in biomedical imaging applications. One of the limiting factors of CNN is it uses spatial image features only for classification. The spectral features from the transform domain have equivalent importance in the complex image classification algorithm. This paper proposes a new CNN structure to classify the histopathological cancer images based on integrating the spectral features obtained using a multi-resolution wavelet transform with the spatial features of CNN. In addition, batch normalization process is used after every layer in the convolution network to improve the poor convergence problem of CNN and the deep layers of CNN are trained with spectral–spatial features. The proposed structure is tested on malignant histology images of the breast for both binary and multi-class classification of tissue using the BreaKHis Dataset and the Breast Cancer Classification Challenge 2015 Datasest. Experimental results show that the combination of spectral–spatial features improves classification accuracy of the CNN network and requires less training parameters in comparison with the well known models (i.e., VGG16 and ALEXNET). The proposed structure achieves an average accuracy of 97.58% and 97.45% with 7.6 million training parameters on both datasets, respectively.

Neural network and multi-fractal dimension features for breast cancer classification from ultrasound images

2018 ◽  
Vol 70 ◽  
pp. 871-882 ◽  
Author(s):  
Mazin Abed Mohammed ◽  
Belal Al-Khateeb ◽  
Ahmed Noori Rashid ◽  
Dheyaa Ahmed Ibrahim ◽  
Mohd Khanapi Abd Ghani ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Neural Network ◽  
Fractal Dimension ◽  
Cancer Classification ◽  
Ultrasound Images ◽  
Breast Cancer Classification
Sign in / Sign up

Export Citation Format

Share Document