Medical image texture segmentation using multifractal analysis

Abstract

Medical image segmentation is a technique using to mean manually, fully or semi-automatically delineating the boundaries of tissue regions or an object. This paper presents a robust segmentation approach for medical image texture using multifractal analysis. The goal is to segment the images with respect to their characteristics such as bone and tissue types. In clinical situations where large numbers of data sets must be segmented, traditional methods may be tedious and biased. For these reasons, we used an automatic image segmentation algorithm, which eliminates the problem the classical method presents and expedites the process. In this paper, we present an algorithm to reliably segment medical images by using multifractal analysis. The result shows that the proposed method is able to analyze a broad range of medical images.