Deakin University
Browse

File(s) under permanent embargo

A global optimisation approach to classification in medical diagnosis and prognosis

conference contribution
posted on 2001-01-01, 00:00 authored by A Bagirov, A Rubinov, John YearwoodJohn Yearwood, A Strainieri
In this paper global optimisation-based techniques are studied in order to increase the accuracy of medical diagnosis and prognosis with FNA image data from the Wisconsin Diagnostic and Prognostic Breast Cancer databases. First we discuss the problem of determining the most informative features for the classification of cancerous cases in the databases under consideration. Then we apply a technique based on convex and global optimisation to breast cancer diagnosis. It allows the classification of benign cases and malignant ones and the subsequent diagnosis of patients with very high accuracy. The third application of this technique is a method that calculates centres of clusters to predict when breast cancer is likely to recur in patients for which cancer has been removed. The technique achieves higher accuracy with these databases than reported else-where in the literature.

History

Event

Annual Hawaii International Conference on System Sciences (34th : 2001 : Maui, Hawaii)

Pagination

1 - 9

Publisher

IEEE

Location

Maui, Hawaii

Place of publication

Piscataway, N.J.

Start date

2001-01-06

End date

2001-01-06

ISSN

1060-3425

Language

eng

Publication classification

EN.1 Other conference paper

Copyright notice

2001, IEEE

Title of proceedings

HAISS 2001 : Proceedings of the 34th Annual Hawaii International Conference on System Sciences

Usage metrics

    Research Publications

    Categories

    No categories selected

    Keywords

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC