Search

In this paper a problem of inter-rater agreement is discussed in the case of human observers who judge how similar pairs of images are. In such a case significant differences in judgment appear among the group of people. We have observed that for some pairs of images all values of similarity ratings are assigned by various people with approximately the same probability. To investigate this phenomenon in a more thorough mannerwe performed experiments in which inter-rater coefficients were used to measure the level of agreement for each given pair of images and for each pair of human judges. The results obtained in the experiments suggest that the variation of the level of agreement is considerable among pairs of images as well as among pairs of people. We suggest that this effect should be taken into account in design of computer systems using image similarity as a criterion.

The subject of the paper is the evaluation of a brain atrophy depending on computed tomography (CT) images. There are two computer aided methods under investigation. The first one is a semi-automatic volumetric method, the second is a fully automatic one and depends on the fractal dimension. Results of the experiment with 68 patients show that both methods are able to estimate the brain atrophy very similarly to the evaluation made by expert radiologist with the coefficient of correlation in the range of 0.7-0.9. The great advantage of the automatic method comparing to volumetric method is generating results in a very short time, that counts in ordinary clinical practice and could be used to experiment with huge patient groups.