ULTRASONOGRAM ANALYSIS OF CHRONIC AUTOIMMUNE THYROIDITIS USING NON-HEURISTIC TEXTURE FEATURES

摘要

Chronic autoimmune thyroiditis is a common disease of thyroid gland. The paper describes a novel method of modeling texture features and reports results of sonographic image analysis and distinguishing between normal tissue and the chronic inflammation process in thyroid gland by means of texture analysis. Reconstruction analysis is used to find appropriate separations of pixels, which have the strong relationship with patient diagnosis. The Bayes classifier combined with majority voting is used for the classification. The highest achieved classification success rate, evaluated on 85 subjects, was 89%. There is possibility to use this texture analysis method in clinical diagnostic process.