Detection of Unsupervised Ultrasound Liver Lesion Images Using Texture-Based Parameters

Texture can be defined as an entity consisting of mutually related pixels and group of pixels. This group of pixels is called texture primitives or texture elements (texels). As the texture is a quantitative measure of the arrangement of intensities in a region, the methods to characterize texture fall into two major categories: Statistical and Structural. Statistical methods characterize texture by the statistical distribution of the image intensity. Spatial distribution of gray values is one of the defining qualities of texture [1]. Texture is one of the important characteristics used in identifying objects or region of interest in an image. Texture is defined for our purposes as an attribute of a field having no components that appear enumerable [2]. With the advent of high-speed computers, it is becoming possible to perform mathematical or algorithmic processes on pictorial data from images. The Texture features are used for image characterization. Texture is a measurement of the variation of intensity of a surface, quantifying properties such as smoothness, coarseness and regularity. Numerous methods have been applied towards the analysis and characterization of ultrasound image texture within medical images including run-length, wavelet transform and two-dimensional co-occurrence matrices. By constructing co-occurrence matrices and extracting the few image texture parameters, classification of images is carried out. It is demonstrated that the proposed technique leads to the in-vivo differentiation of normal and lesion liver image using image texture parameters of ultrasound B-scan image.