Morphological classification of medical images using nonlinear support vector machines

The wavelet decomposition of a high-dimensional shape transformation posed in a mass-preserving framework is used as a morphological signature of a brain image. Population differences with complex spatial patterns are then determined by applying a nonlinear support vector machine pattern classification method to the morphological signatures. By considering measurements from the entire image, and not only from isolated anatomical structures, and by using a highly non-linear classifier, this method has achieved very high classification results in a variety of tests.