Breast cancer classification from histological images with multiple features and random subspace classifier ensemble

Yungang Zhang; Bailing Zhang; Wenjin Lu

doi:10.1063/1.3596623

Breast cancer classification from histological images with multiple features and random subspace classifier ensemble

Yungang Zhang^*, Bailing Zhang, Wenjin Lu

^*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

12 Citations (Scopus)

Abstract

Histological image is important for diagnosis of breast cancer. In this paper, we present a novel automatic breaset cancer classification scheme based on histological images. The image features are extracted using the Curvelet Transform, statistics of Gray Level Co-occurence Matrix (GLCM) and Completed Local Binary Patterns (CLBP), respectively. The three different features are combined together and used for classification. A classifier ensemble approach, called Random Subspace Ensemble (RSE), are used to select and aggregate a set of base neural network classifiers for classification. The proposed multiple features and random subspace ensemble offer the classification rate 95.22% on a publically available breast cancer image dataset, which compares favorably with the previously published result 93.4%.

Original language	English
Title of host publication	2011 International Symposium on Computational Models for Life Sciences, CMLS-11
Pages	19-28
Number of pages	10
DOIs	https://doi.org/10.1063/1.3596623
Publication status	Published - 2011
Event	2011 International Symposium on Computational Models for Life Sciences, CMLS-11 - Toyama City, Japan Duration: 11 Oct 2011 → 13 Oct 2011

Publication series

Name	AIP Conference Proceedings
Volume	1371
ISSN (Print)	0094-243X
ISSN (Electronic)	1551-7616

Conference

Conference	2011 International Symposium on Computational Models for Life Sciences, CMLS-11
Country/Territory	Japan
City	Toyama City
Period	11/10/11 → 13/10/11

Keywords

Breast cancer classification
Curvelet transform
Histological images
Multilayer perceptron
Random subspace ensemble
Texture features

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1063/1.3596623

Cite this

@inproceedings{d43c64b84d68455f9291a1b4bba82ed3,

title = "Breast cancer classification from histological images with multiple features and random subspace classifier ensemble",

abstract = "Histological image is important for diagnosis of breast cancer. In this paper, we present a novel automatic breaset cancer classification scheme based on histological images. The image features are extracted using the Curvelet Transform, statistics of Gray Level Co-occurence Matrix (GLCM) and Completed Local Binary Patterns (CLBP), respectively. The three different features are combined together and used for classification. A classifier ensemble approach, called Random Subspace Ensemble (RSE), are used to select and aggregate a set of base neural network classifiers for classification. The proposed multiple features and random subspace ensemble offer the classification rate 95.22% on a publically available breast cancer image dataset, which compares favorably with the previously published result 93.4%.",

keywords = "Breast cancer classification, Curvelet transform, Histological images, Multilayer perceptron, Random subspace ensemble, Texture features",

author = "Yungang Zhang and Bailing Zhang and Wenjin Lu",

year = "2011",

doi = "10.1063/1.3596623",

language = "English",

isbn = "9780735409316",

series = "AIP Conference Proceedings",

pages = "19--28",

booktitle = "2011 International Symposium on Computational Models for Life Sciences, CMLS-11",

note = "2011 International Symposium on Computational Models for Life Sciences, CMLS-11 ; Conference date: 11-10-2011 Through 13-10-2011",

}

Zhang, Y, Zhang, B & Lu, W 2011, Breast cancer classification from histological images with multiple features and random subspace classifier ensemble. in 2011 International Symposium on Computational Models for Life Sciences, CMLS-11. AIP Conference Proceedings, vol. 1371, pp. 19-28, 2011 International Symposium on Computational Models for Life Sciences, CMLS-11, Toyama City, Japan, 11/10/11. https://doi.org/10.1063/1.3596623

Breast cancer classification from histological images with multiple features and random subspace classifier ensemble. / Zhang, Yungang; Zhang, Bailing; Lu, Wenjin.
2011 International Symposium on Computational Models for Life Sciences, CMLS-11. 2011. p. 19-28 (AIP Conference Proceedings; Vol. 1371).

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

TY - GEN

T1 - Breast cancer classification from histological images with multiple features and random subspace classifier ensemble

AU - Zhang, Yungang

AU - Zhang, Bailing

AU - Lu, Wenjin

PY - 2011

Y1 - 2011

N2 - Histological image is important for diagnosis of breast cancer. In this paper, we present a novel automatic breaset cancer classification scheme based on histological images. The image features are extracted using the Curvelet Transform, statistics of Gray Level Co-occurence Matrix (GLCM) and Completed Local Binary Patterns (CLBP), respectively. The three different features are combined together and used for classification. A classifier ensemble approach, called Random Subspace Ensemble (RSE), are used to select and aggregate a set of base neural network classifiers for classification. The proposed multiple features and random subspace ensemble offer the classification rate 95.22% on a publically available breast cancer image dataset, which compares favorably with the previously published result 93.4%.

AB - Histological image is important for diagnosis of breast cancer. In this paper, we present a novel automatic breaset cancer classification scheme based on histological images. The image features are extracted using the Curvelet Transform, statistics of Gray Level Co-occurence Matrix (GLCM) and Completed Local Binary Patterns (CLBP), respectively. The three different features are combined together and used for classification. A classifier ensemble approach, called Random Subspace Ensemble (RSE), are used to select and aggregate a set of base neural network classifiers for classification. The proposed multiple features and random subspace ensemble offer the classification rate 95.22% on a publically available breast cancer image dataset, which compares favorably with the previously published result 93.4%.

KW - Breast cancer classification

KW - Curvelet transform

KW - Histological images

KW - Multilayer perceptron

KW - Random subspace ensemble

KW - Texture features

UR - http://www.scopus.com/inward/record.url?scp=79960107073&partnerID=8YFLogxK

U2 - 10.1063/1.3596623

DO - 10.1063/1.3596623

M3 - Conference Proceeding

AN - SCOPUS:79960107073

SN - 9780735409316

T3 - AIP Conference Proceedings

SP - 19

EP - 28

BT - 2011 International Symposium on Computational Models for Life Sciences, CMLS-11

T2 - 2011 International Symposium on Computational Models for Life Sciences, CMLS-11

Y2 - 11 October 2011 through 13 October 2011

ER -

Breast cancer classification from histological images with multiple features and random subspace classifier ensemble

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Cite this