Improving the performance of machine learning classifiers for Breast Cancer diagnosis based on feature selection

Noel Perez; Miguel A. Guevara; Augusto Silva; Isabel Ramos; Joana Loureiro

doi:10.15439/2014F249

Improving the performance of machine learning classifiers for Breast Cancer diagnosis based on feature selection

Noel Perez
, Miguel A. Guevara
, Augusto Silva
, Isabel Ramos
, Joana Loureiro

University of Porto
University of Aveiro
Centro Hospitalar São João

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

26 Scopus citations

Abstract

This paper proposed a comprehensive algorithm for building machine learning classifiers for Breast Cancer diagnosis based on the suitable combination of feature selection methods that provide high performance over the Area Under receiver operating characteristic Curve (AUC). The new developed method allows both for exploring and ranking search spaces of image-based features, and selecting subsets of optimal features for feeding Machine Learning Classifiers (MLCs). The method was evaluated using six mammography-based datasets (containing calcifications and masses lesions) with different configurations extracted from two public Breast Cancer databases. According to the Wilcoxon Statistical Test, the proposed method demonstrated to provide competitive Breast Cancer classification schemes reducing the number of employed features for each experimental dataset.

Original language	English
Title of host publication	2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	209-217
Number of pages	9
ISBN (Electronic)	9788360810583
DOIs	https://doi.org/10.15439/2014F249
State	Published - 21 Oct 2014
Externally published	Yes
Event	2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014 - Warsaw, Poland Duration: 7 Sep 2014 → 10 Sep 2014

Publication series

Name	2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014

Conference

Conference	2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014
Country/Territory	Poland
City	Warsaw
Period	7/09/14 → 10/09/14

UN SDGs

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

SDG 3 Good Health and Well-being

Access to Document

10.15439/2014F249

Cite this

Perez, N., Guevara, M. A., Silva, A., Ramos, I., & Loureiro, J. (2014). Improving the performance of machine learning classifiers for Breast Cancer diagnosis based on feature selection. In 2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014 (pp. 209-217). Article 6933015 (2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.15439/2014F249

Perez, Noel ; Guevara, Miguel A. ; Silva, Augusto et al. / Improving the performance of machine learning classifiers for Breast Cancer diagnosis based on feature selection. 2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 209-217 (2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014).

@inproceedings{9680fde961fa42f692a713cd7130cc16,

title = "Improving the performance of machine learning classifiers for Breast Cancer diagnosis based on feature selection",

abstract = "This paper proposed a comprehensive algorithm for building machine learning classifiers for Breast Cancer diagnosis based on the suitable combination of feature selection methods that provide high performance over the Area Under receiver operating characteristic Curve (AUC). The new developed method allows both for exploring and ranking search spaces of image-based features, and selecting subsets of optimal features for feeding Machine Learning Classifiers (MLCs). The method was evaluated using six mammography-based datasets (containing calcifications and masses lesions) with different configurations extracted from two public Breast Cancer databases. According to the Wilcoxon Statistical Test, the proposed method demonstrated to provide competitive Breast Cancer classification schemes reducing the number of employed features for each experimental dataset.",

author = "Noel Perez and Guevara, \{Miguel A.\} and Augusto Silva and Isabel Ramos and Joana Loureiro",

note = "Publisher Copyright: {\textcopyright} 2014 Polish Information Processing Society.; 2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014 ; Conference date: 07-09-2014 Through 10-09-2014",

year = "2014",

month = oct,

day = "21",

doi = "10.15439/2014F249",

language = "Ingl{\'e}s",

series = "2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "209--217",

booktitle = "2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014",

}

Perez, N, Guevara, MA, Silva, A, Ramos, I & Loureiro, J 2014, Improving the performance of machine learning classifiers for Breast Cancer diagnosis based on feature selection. in 2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014., 6933015, 2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014, Institute of Electrical and Electronics Engineers Inc., pp. 209-217, 2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014, Warsaw, Poland, 7/09/14. https://doi.org/10.15439/2014F249

Improving the performance of machine learning classifiers for Breast Cancer diagnosis based on feature selection. / Perez, Noel; Guevara, Miguel A.; Silva, Augusto et al.
2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 209-217 6933015 (2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014).

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

TY - GEN

T1 - Improving the performance of machine learning classifiers for Breast Cancer diagnosis based on feature selection

AU - Perez, Noel

AU - Guevara, Miguel A.

AU - Silva, Augusto

AU - Ramos, Isabel

AU - Loureiro, Joana

PY - 2014/10/21

Y1 - 2014/10/21

N2 - This paper proposed a comprehensive algorithm for building machine learning classifiers for Breast Cancer diagnosis based on the suitable combination of feature selection methods that provide high performance over the Area Under receiver operating characteristic Curve (AUC). The new developed method allows both for exploring and ranking search spaces of image-based features, and selecting subsets of optimal features for feeding Machine Learning Classifiers (MLCs). The method was evaluated using six mammography-based datasets (containing calcifications and masses lesions) with different configurations extracted from two public Breast Cancer databases. According to the Wilcoxon Statistical Test, the proposed method demonstrated to provide competitive Breast Cancer classification schemes reducing the number of employed features for each experimental dataset.

AB - This paper proposed a comprehensive algorithm for building machine learning classifiers for Breast Cancer diagnosis based on the suitable combination of feature selection methods that provide high performance over the Area Under receiver operating characteristic Curve (AUC). The new developed method allows both for exploring and ranking search spaces of image-based features, and selecting subsets of optimal features for feeding Machine Learning Classifiers (MLCs). The method was evaluated using six mammography-based datasets (containing calcifications and masses lesions) with different configurations extracted from two public Breast Cancer databases. According to the Wilcoxon Statistical Test, the proposed method demonstrated to provide competitive Breast Cancer classification schemes reducing the number of employed features for each experimental dataset.

UR - https://www.scopus.com/pages/publications/84912103556

U2 - 10.15439/2014F249

DO - 10.15439/2014F249

M3 - Contribución a la conferencia

AN - SCOPUS:84912103556

T3 - 2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014

SP - 209

EP - 217

BT - 2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014

Y2 - 7 September 2014 through 10 September 2014

ER -

Perez N, Guevara MA, Silva A, Ramos I, Loureiro J. Improving the performance of machine learning classifiers for Breast Cancer diagnosis based on feature selection. In 2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 209-217. 6933015. (2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014). doi: 10.15439/2014F249

Improving the performance of machine learning classifiers for Breast Cancer diagnosis based on feature selection

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this