Medical Image Segmentation using Multifractal Analysis

S. Ezekiel (USA)


Multifractal analysis, medical images, sum measure,segmentation.


In this paper, we present a multifractal analysis-based method for automatic segmentation of medical images. Segmentation is a tool that has been widely used in medical image processing and computer vision for a variety of reasons. The goal is to segment the images with respect to their characteristics such as bone and tissue types; e.g. gray matter (GM), white matter (WM), etc. Traditionally segmentation is based on a histogram or manual decomposition. This method is one of the most difficult tasks of the machine analysis of images, especially when they are medical images. 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. Then we can present the images to the doctor that is easy to analyze and to diagnose. The result shows that the proposed method is superior to the traditional method and it has the capability to analyze a broad range of medical images. Moreover, since this method is simple, efficient, and has real-time response, it is more suitable for virtual surgical environment.

Important Links:

Go Back