Modelling ordinal relations with SVMs: An application to objective aesthetic evaluation of breast cancer conservative treatment

• Type: Article in International Scientific Journal
• Date: 2005

Authors

Cardoso, JS (Author) FCUP; da Costa, JFP (Author) FCUP; Cardoso, MJ (Author) Other

Journal

Title: Neural Networks

Vol. 18 No. 5

Pages: 808-817

ISSN: 0893-6080

Publisher: Elsevier

Indexing

ISI Web of Knowledge - 44 Citations

Scopus - 49 Citations

Scientific classification

FOS: Natural sciences > Computer and information sciences

CORDIS: Technological sciences > Engineering > Biomedical enginnering

Other information

Authenticus ID: P-000-36F

DOI: 10.1016/j.neunet.2005.06.023

Abstract (EN): The cosmetic result is an important endpoint for breast cancer conservative treatment (BCCT), but the verification of this outcome remains without a standard. Objective assessment methods are preferred to overcome the drawbacks of subjective evaluation. In this paper a novel algorithm is proposed, based on support vector machines, for the classification of ordinal categorical data. This classifier is then applied as a new methodology for the objective assessment of the aesthetic result of BCCT. Based on the new classifier, a semi-objective score for quantification of the aesthetic results of BCCT was developed, allowing the discrimination of patients into four classes.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 10