Clustering breast cancer data by consensus of different validity indices

D. Soria; J. M. Garibaldi; F. Ambrogi; P. J G Lisboa; P. Boracchi; E. Biganzoli

doi:10.1049/cp:20080437

Clustering breast cancer data by consensus of different validity indices

D. Soria, J. M. Garibaldi, F. Ambrogi, P. J G Lisboa, P. Boracchi, E. Biganzoli

Fondazione IRCCS Istituto Nazionale dei Tumori

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

Abstract

Clustering algorithms will, in general, either partition a given data set into a pre-specified number of clusters or will produce a hierarchy of clusters. In this paper we analyse several different clustering techniques and apply them to a particular data set of breast cancer data. When we do not know a priori which is the best number of groups, we use a range of different validity indices to test the quality of clustering results and to determine the best number of clusters. While for the K-means method there is not absolute agreement among the indices as to which is the best number of clusters, for the PAM algorithm all the indices indicate 4 as the best cluster number.

Original language	English
Title of host publication	IET Conference Publications
Edition	540 CP
DOIs	https://doi.org/10.1049/cp:20080437
Publication status	Published - 2008
Event	4th IET International Conference on Advances in Medical, Signal and Information Processing, MEDSIP 2008 - Santa Margherita Ligure, Italy Duration: Jul 14 2008 → Jul 16 2008

Other

Other	4th IET International Conference on Advances in Medical, Signal and Information Processing, MEDSIP 2008
Country/Territory	Italy
City	Santa Margherita Ligure
Period	7/14/08 → 7/16/08

Keywords

Breast cancer
Clustering algorithms
Validity indices

ASJC Scopus subject areas

Electrical and Electronic Engineering

Access to Document

10.1049/cp:20080437

Cite this

Soria, D, Garibaldi, JM, Ambrogi, F, Lisboa, PJG, Boracchi, P & Biganzoli, E 2008, Clustering breast cancer data by consensus of different validity indices. in IET Conference Publications. 540 CP edn, 4th IET International Conference on Advances in Medical, Signal and Information Processing, MEDSIP 2008, Santa Margherita Ligure, Italy, 7/14/08. https://doi.org/10.1049/cp:20080437

@inproceedings{3bb738f9076344efaea328e702b1316c,

title = "Clustering breast cancer data by consensus of different validity indices",

abstract = "Clustering algorithms will, in general, either partition a given data set into a pre-specified number of clusters or will produce a hierarchy of clusters. In this paper we analyse several different clustering techniques and apply them to a particular data set of breast cancer data. When we do not know a priori which is the best number of groups, we use a range of different validity indices to test the quality of clustering results and to determine the best number of clusters. While for the K-means method there is not absolute agreement among the indices as to which is the best number of clusters, for the PAM algorithm all the indices indicate 4 as the best cluster number.",

keywords = "Breast cancer, Clustering algorithms, Validity indices",

author = "D. Soria and Garibaldi, {J. M.} and F. Ambrogi and Lisboa, {P. J G} and P. Boracchi and E. Biganzoli",

year = "2008",

doi = "10.1049/cp:20080437",

language = "English",

isbn = "9780863419348",

booktitle = "IET Conference Publications",

edition = "540 CP",

note = "4th IET International Conference on Advances in Medical, Signal and Information Processing, MEDSIP 2008 ; Conference date: 14-07-2008 Through 16-07-2008",

}

TY - GEN

T1 - Clustering breast cancer data by consensus of different validity indices

AU - Soria, D.

AU - Garibaldi, J. M.

AU - Ambrogi, F.

AU - Lisboa, P. J G

AU - Boracchi, P.

AU - Biganzoli, E.

PY - 2008

Y1 - 2008

N2 - Clustering algorithms will, in general, either partition a given data set into a pre-specified number of clusters or will produce a hierarchy of clusters. In this paper we analyse several different clustering techniques and apply them to a particular data set of breast cancer data. When we do not know a priori which is the best number of groups, we use a range of different validity indices to test the quality of clustering results and to determine the best number of clusters. While for the K-means method there is not absolute agreement among the indices as to which is the best number of clusters, for the PAM algorithm all the indices indicate 4 as the best cluster number.

AB - Clustering algorithms will, in general, either partition a given data set into a pre-specified number of clusters or will produce a hierarchy of clusters. In this paper we analyse several different clustering techniques and apply them to a particular data set of breast cancer data. When we do not know a priori which is the best number of groups, we use a range of different validity indices to test the quality of clustering results and to determine the best number of clusters. While for the K-means method there is not absolute agreement among the indices as to which is the best number of clusters, for the PAM algorithm all the indices indicate 4 as the best cluster number.

KW - Breast cancer

KW - Clustering algorithms

KW - Validity indices

UR - http://www.scopus.com/inward/record.url?scp=67549102287&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67549102287&partnerID=8YFLogxK

U2 - 10.1049/cp:20080437

DO - 10.1049/cp:20080437

M3 - Conference contribution

AN - SCOPUS:67549102287

SN - 9780863419348

BT - IET Conference Publications

T2 - 4th IET International Conference on Advances in Medical, Signal and Information Processing, MEDSIP 2008

Y2 - 14 July 2008 through 16 July 2008

ER -

Clustering breast cancer data by consensus of different validity indices

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this