AUTOMATIC CONTEXT-SENSITIVE KARYOTYPING OF HUMAN-CHROMOSOMES BASED ONELLIPTICALLY SYMMETRICAL STATISTICAL DISTRIBUTIONS

We introduce a statistical model of a metaphase cell consisting of ind ependent chromosomes with elliptically symmetric feature vectors. From this model we derive the ML-classifier for classification in the 24 c hromosomal classes, taking into account the correct number of chromoso mes in each class. Experimental results show that error rates of the b est of these classifiers are less than 2% with respect to chromosomes if applied to the large Copenhagen data set Cpr. Simulation studies su ggest that there should be even more information contained in the feat ures of this data set.