Cargando…

Breast Cancer Detection with Reduced Feature Set

This paper explores feature reduction properties of independent component analysis (ICA) on breast cancer decision support system. Wisconsin diagnostic breast cancer (WDBC) dataset is reduced to one-dimensional feature vector computing an independent component (IC). The original data with 30 feature...

Descripción completa

Detalles Bibliográficos
Autores principales: Mert, Ahmet, Kılıç, Niyazi, Bilgili, Erdem, Akan, Aydin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi Publishing Corporation 2015
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4452509/
https://www.ncbi.nlm.nih.gov/pubmed/26078774
http://dx.doi.org/10.1155/2015/265138
_version_ 1782374310691733504
author Mert, Ahmet
Kılıç, Niyazi
Bilgili, Erdem
Akan, Aydin
author_facet Mert, Ahmet
Kılıç, Niyazi
Bilgili, Erdem
Akan, Aydin
author_sort Mert, Ahmet
collection PubMed
description This paper explores feature reduction properties of independent component analysis (ICA) on breast cancer decision support system. Wisconsin diagnostic breast cancer (WDBC) dataset is reduced to one-dimensional feature vector computing an independent component (IC). The original data with 30 features and reduced one feature (IC) are used to evaluate diagnostic accuracy of the classifiers such as k-nearest neighbor (k-NN), artificial neural network (ANN), radial basis function neural network (RBFNN), and support vector machine (SVM). The comparison of the proposed classification using the IC with original feature set is also tested on different validation (5/10-fold cross-validations) and partitioning (20%–40%) methods. These classifiers are evaluated how to effectively categorize tumors as benign and malignant in terms of specificity, sensitivity, accuracy, F-score, Youden's index, discriminant power, and the receiver operating characteristic (ROC) curve with its criterion values including area under curve (AUC) and 95% confidential interval (CI). This represents an improvement in diagnostic decision support system, while reducing computational complexity.
format Online
Article
Text
id pubmed-4452509
institution National Center for Biotechnology Information
language English
publishDate 2015
publisher Hindawi Publishing Corporation
record_format MEDLINE/PubMed
spelling pubmed-44525092015-06-15 Breast Cancer Detection with Reduced Feature Set Mert, Ahmet Kılıç, Niyazi Bilgili, Erdem Akan, Aydin Comput Math Methods Med Research Article This paper explores feature reduction properties of independent component analysis (ICA) on breast cancer decision support system. Wisconsin diagnostic breast cancer (WDBC) dataset is reduced to one-dimensional feature vector computing an independent component (IC). The original data with 30 features and reduced one feature (IC) are used to evaluate diagnostic accuracy of the classifiers such as k-nearest neighbor (k-NN), artificial neural network (ANN), radial basis function neural network (RBFNN), and support vector machine (SVM). The comparison of the proposed classification using the IC with original feature set is also tested on different validation (5/10-fold cross-validations) and partitioning (20%–40%) methods. These classifiers are evaluated how to effectively categorize tumors as benign and malignant in terms of specificity, sensitivity, accuracy, F-score, Youden's index, discriminant power, and the receiver operating characteristic (ROC) curve with its criterion values including area under curve (AUC) and 95% confidential interval (CI). This represents an improvement in diagnostic decision support system, while reducing computational complexity. Hindawi Publishing Corporation 2015 2015-05-19 /pmc/articles/PMC4452509/ /pubmed/26078774 http://dx.doi.org/10.1155/2015/265138 Text en Copyright © 2015 Ahmet Mert et al. https://creativecommons.org/licenses/by/3.0/ This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Mert, Ahmet
Kılıç, Niyazi
Bilgili, Erdem
Akan, Aydin
Breast Cancer Detection with Reduced Feature Set
title Breast Cancer Detection with Reduced Feature Set
title_full Breast Cancer Detection with Reduced Feature Set
title_fullStr Breast Cancer Detection with Reduced Feature Set
title_full_unstemmed Breast Cancer Detection with Reduced Feature Set
title_short Breast Cancer Detection with Reduced Feature Set
title_sort breast cancer detection with reduced feature set
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4452509/
https://www.ncbi.nlm.nih.gov/pubmed/26078774
http://dx.doi.org/10.1155/2015/265138
work_keys_str_mv AT mertahmet breastcancerdetectionwithreducedfeatureset
AT kılıcniyazi breastcancerdetectionwithreducedfeatureset
AT bilgilierdem breastcancerdetectionwithreducedfeatureset
AT akanaydin breastcancerdetectionwithreducedfeatureset