Context-dependent classification of medical images in the absence of complete class definitions

A method is developed to automatically classify multispectral medical images using context-dependent methods. The model is built with the knowledge that clusters of tissue features will overlap in feature space. The goal is to correctly classify pixels in these overlapping regions. The model also allows for the possibility that there may be no match for a particular pixel. Initialization of the likelihood of a pixel belonging to a tissue class can take advantage of a priori class distributions if such knowledge exists. Otherwise, the model can resort to modeling each class with a Gaussian distribution. These likelihoods can then be iteratively updated using the relaxation labeling algorithm. Once the model converges, iterations cease and each pixel is classified using the maximum likelihood for all classes.<>