Extracting Discriminative Information from Medical Images: A Multivariate Linear Approach

Statistical discrimination methods are suitable not only for classification but also for characterization of differences between a reference group of patterns and the population under investigation. In the last years, statistical methods have been proposed to classify and analyze morphological and anatomical structures of medical images. Most of these techniques work in high-dimensional spaces of particular features such as shapes or statistical parametric maps and have overcome the difficulty of dealing with the inherent high dimensionality of medical images by analyzing segmented structures individually or performing hypothesis tests on each feature separately. In this paper, we present a general multivariate linear framework to identify and analyze the most discriminating hyper-plane separating two populations. The goal is to analyze all the intensity features simultaneously rather than segmented versions of the data separately or feature-by-feature. The conceptual and mathematical simplicity of the approach, which pivotal step is spatial normalization, involves the same operations irrespective of the complexity of the experiment or nature of the data, giving multivariate results that are easy to interpret. To demonstrate its performance we present experimental results on artificially generated data set and real medical data