Formation of features for improving the quality of medical diagnosis based on discriminant analysis methods

A computer aided diagnosis system for ocular disease detection is considered. To improve the quality of diagnostics we propose an algorithm for the informative features formation, using methods of discriminant analysis. A method for obtaining an informative value estimate is described. A research confirming the efficiency of the feature-based classification of fundus images was conducted by means of classification by support vector machine. The algorithm possesses a sufficient level of universality and may be applied to increase the informative value of any feature set.