The effect of region of interest size on textural parameters

Texture analysis provides quantitative information describing the properties of a digital image. The value of texture analysis has been tested in various medical applications, using mostly magnetic resonance images because of the amount of information the method is capable to provide. However, there exists no certain practice to define the region of interest (ROI) within the texture parameters are calculated. Many parameters seem to be dependent on the ROI size. We studied the effect of the ROI size with magnetic resonance head images from 64 healthy adults and artificial noise images. According to our results, ROI size has a significant effect on the computed value of several second-order texture features. We conclude that comparisons of different size ROIs will therefore lead to falsely optimistic classification between analyzed tissues.