Self-organizing map for cluster analysis of a breast cancer database

Mia K. Markey, Joseph Y. Lo, Georgia D. Tourassi, Carey E. Floyd

Research output: Contribution to journalArticlepeer-review

96 Scopus citations

Abstract

The purpose of this study was to identify and characterize clusters in a heterogeneous breast cancer computer-aided diagnosis database. Identification of subgroups within the database could help elucidate clinical trends and facilitate future model building. A self-organizing map (SOM) was used to identify clusters in a large (2258 cases), heterogeneous computer-aided diagnosis database based on mammographic findings (BI-RADS™) and patient age. The resulting clusters were then characterized by their prototypes determined using a constraint satisfaction neural network (CSNN). The clusters showed logical separation of clinical subtypes such as architectural distortions, masses, and calcifications. Moreover, the broad categories of masses and calcifications were stratified into several clusters (seven for masses and three for calcifications). The percent of the cases that were malignant was notably different among the clusters (ranging from 6 to 83%). A feed-forward back-propagation artificial neural network (BP-ANN) was used to identify likely benign lesions that may be candidates for follow up rather than biopsy. The performance of the BP-ANN varied considerably across the clusters identified by the SOM. In particular, a cluster (#6) of mass cases (6% malignant) was identified that accounted for 79% of the recommendations for follow up that would have been made by the BP-ANN. A classification rule based on the profile of cluster #6 performed comparably to the BP-ANN, providing approximately 25% specificity at 98% sensitivity. This performance was demonstrated to generalize to a large (2177) set of cases held-out for model validation.

Original languageEnglish
Pages (from-to)113-127
Number of pages15
JournalArtificial Intelligence in Medicine
Volume27
Issue number2
DOIs
StatePublished - Feb 2003
Externally publishedYes

Funding

This work was supported in part by Susan G. Komen Breast Cancer Foundation grant DISS0100400, US Army Medical Research and Materiel Command grants DAMD17-02-1-0373 and DAMD17-01-1-0516, and NIH/NCI R29 CA-75547. We would like to thank Brian Harrawood for scientific programming.

Keywords

  • Breast cancer
  • Cluster analysis
  • Computer-aided diagnosis
  • Self-organizing map

Fingerprint

Dive into the research topics of 'Self-organizing map for cluster analysis of a breast cancer database'. Together they form a unique fingerprint.

Cite this