Texture Analysis of Ultrasonograms – a New Quality in Diagnostics of ThyroidalDisorders?

Overview

Ultrasonography is a generally accepted method for diagnosing both the diffuse and focal (nodal) lesions of thethyroid gland. The main limit of this method is the restricted ability of the human eye to analyse all informationincluded. Moreover, the proportion of subjectivity when evaluating the picture is greater than with other imagingmethods. Computer texture analysis in combination with automatic classification may prove a potent tool that couldenable – immediately after the standard examination – to assign the finding to a particular type of diffuse disorder,with an accuracy of up to 100 percent. From a variety of procedures, which we have tested until now, the best resultswere obtained with a combination of spatial, co-occurrence and systematically constructed features, selected bya method that is based on the magnitude of classification error. From several tested ways of classification the Bayes’sclassificator in combination with the criterion of majority was found to be the best approach.

Key words:
thyroid gland, autoimmune thyroiditis, ultrasonography, machine perception, texture analysis, co-occurrence,automatic classification.