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

• Tipo: Artigo em Revista Científica Internacional
• Data: 2005

Autores

Cardoso, JS (Autor) FCUP; da Costa, JFP (Autor) FCUP; Cardoso, MJ (Autor) Outra

Revista

Título: Neural Networks

Vol. 18 Nº 5

Páginas: 808-817

ISSN: 0893-6080

Editora: Elsevier

Indexação

ISI Web of Knowledge - 44 Citações

Scopus - 49 Citações

Classificação Científica

FOS: Ciências exactas e naturais > Ciências da computação e da informação

CORDIS: Ciências Tecnológicas > Engenharia > Engenharia biomédica

Outras Informações

ID Authenticus: 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.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 10