Staff Members - Benha University
Towards Automatic Classification of Breast Cancer Histopathological Image
2018 13th International Conference on Computer Engineering and Systems (ICCES) • 2018
Publication Information
Authors
E. elelimy , A. A. Mohamed
Keywords
Breast Cancer; Classification; Computer-aided
Diagnosis; SVD; CLBP; Gabor filter; Wavelet Transform; SVM.
Journal
2018 13th International Conference on Computer Engineering and Systems (ICCES)
Publisher
IEEE
Volume
Not Available
Issue
Not Available
Pages
Not Available
publication.type
International
Paper Link
Open Link
Supplementary Materials
Not Available
Abstract
Today the treatment and diagnosis of diseases heavily rely on medical images. These images are produced in huge
amount, which causes a bottleneck in the process of investigation.
One of the most important diseases, which heavily rely on images,
is Breast Cancer. We introduce a classification system based on a
hybrid feature extractor that relies on Completed Local Binary
Pattern (CLBP), Singular Value Decomposition (SVD), Gabor
Filter, Wavelet Transform and Support Vector Machines
classifier (SVM). The purpose of this research is to increase the
level of classification automation of Breast Cancer (BC)
Histopathological image. The Experimental approach was used to
investigate the effect of the proposed algorithm which has shown
promising results. These results were benchmarked against a
standard dataset of BC Histopathological image
amount, which causes a bottleneck in the process of investigation.
One of the most important diseases, which heavily rely on images,
is Breast Cancer. We introduce a classification system based on a
hybrid feature extractor that relies on Completed Local Binary
Pattern (CLBP), Singular Value Decomposition (SVD), Gabor
Filter, Wavelet Transform and Support Vector Machines
classifier (SVM). The purpose of this research is to increase the
level of classification automation of Breast Cancer (BC)
Histopathological image. The Experimental approach was used to
investigate the effect of the proposed algorithm which has shown
promising results. These results were benchmarked against a
standard dataset of BC Histopathological image