Texture Analysis of CT Scan Images

Abstract

Medical imaging is though expensive because of capital costs, is easy to perform because of its noninvasive nature. It is clearly very important to extract the maximum possible information from any image obtained. However, image processing modes based on scan sections or radiographic views may not completely provide diagnostic information at an early stage, when it would be easier to control a disease, make a therapeutic decision, or perform surgery. This lack of timely information is, in part, because gray level differences in tissues are small compared to the accuracy with which the measurements may be carried out for a reasonable patient dose of X-rays. These limitations necessitate development of new analysis techniques that will improve diagnostic ability. One promising technique is texture analysis, which characterizes tissues to determine changes in functional characteristics of organs at the onset of disease. In this study, we have tried to analyze the texture of Computed Tomography (CT) images taken of abdomen and to find the values of various parameters of texture. In the present study, we quantitatively establish the use of texture for detection of abnormalities in CT images that are beyond human appreciation and otherwise difficult to determine by other classical methods of image processing. This study investigates whether the texture could be used to discriminate among the various tissue types in the abdomen CT scans and if so, what are the parameters which are useful for such an application. The present study focuses on contrast, homogeneity, energy, correlation, and entropy as parameters for texture.