Multi-class classification of ovarian tumors

In this work, we developed classifiers to distinguish between four ovarian tumor types using Bayesian least squares support vector machines (LS-SVMs) and kernel logistic regression. Input selection using rank-one updates for LS-SVMs performed better than automatic relevance determination. Evaluation on an independent test set showed good performance of the classifiers to distinguish between all groups, even though borderline and metastatic tumors were expected to be hard to identify.

• Type: Conference
• Year: 2008
• Where: ESANN
• Authors: Ben Van Calster, Dirk Timmerman, Antonia C. Testa, Lil Valentin, Sabine Van Huffel
• Keywords: Automatic Relevance Determination, ESANN 2008, Neural Networks, Ovarian Tumor Types, Squares Support Vector