Clustering approach for the classificarion of SPECT images

We present a method to cluster the information contained in 3-dimensional brain images where each cluster incorporates a contiguous brain region with similar activation. The grey-level distribution of a brain image is approximated by a sum of Gaussian functions and the parameters of the Gaussian mixture are determined by a maximum likelihood criterion via the expectation maximization (EM) algorithm. Each cluster, therefore, is represented by a multivariate Gaussian function with a definite centre coordinate and a certain shape. This approach leads to a drastic compression of the information contained in the brain image and serves as a starting point for a variety of possible feature extraction methods for the diagnosis of brain diseases.