Share Email Print
cover

Proceedings Paper

Support vector machines for improving the classification of brain PET images
Author(s): Martin Bonneville; Jean Meunier; Yoshua Bengio; Jean-Paul Soucy
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The classification of brain PET volumes is carried out in three main steps: (1) registration, (2) feature extraction and (3) classification. The PET images were already smoothed with a 16 mm isotropic Gaussian kernel and registered within the Talairach and Tournoux reference system. To make the registration more accurate over a single reference, a method based on optical flow was applied. Feature extraction is carried out by principal component analysis (PCA). Support vector machines (SVM) are then used for classification, because they are better controlled than neural networks (NN) and well adapted to small sample size problems. SVM are constructed by a training algorithm that maximizes the margin between the training vectors and the decision boundary. The algorithm is simple quadratic programming under linear constraints, which leads to global optimum. The decision boundary is expressed as a linear combination of supporting vectors which are a subset of the training vectors closest to the decision boundary. After registration, NN and SVM were trained with the features extracted by PCA from the training set. The estimate error rate is 7.1% for SVM and 14.3% for NN.

Paper Details

Date Published: 24 June 1998
PDF: 10 pages
Proc. SPIE 3338, Medical Imaging 1998: Image Processing, (24 June 1998); doi: 10.1117/12.310900
Show Author Affiliations
Martin Bonneville, Univ. de Montreal (Canada)
Jean Meunier, Univ. de Montreal (Canada)
Yoshua Bengio, Univ. de Montreal (Canada)
Jean-Paul Soucy, Hopital Notre-Dame (Canada)


Published in SPIE Proceedings Vol. 3338:
Medical Imaging 1998: Image Processing
Kenneth M. Hanson, Editor(s)

© SPIE. Terms of Use
Back to Top