Intelligent decision support in pathomorphology.

ABSTRACT

This paper presents a novel approach to computer-supported diagnosing based on microscopic images of histological sections. A method of extraction of textural feature is presented, which is in a sense complementary to the texture-based segmentation. The textural feature is obtained by tracing the process of image segmentation. For classification, a n2-classifier oriented to multi-class problems has been used. The paper presents also an empirical verification of the proposed approach on 700 microscopic images representing 14 classes of CNS neuroepithelial tumours, in which case an encouraging accuracy of classification on the testing set (70.6%) has been obtained.