Histogram analysis of the human brain MR images based on the S-function membership and Shannon's entropy function

Abstract

The analysis of medical images for the purpose of computer-aided diagnosis and therapy planning includes segmentation as a preliminary stage for the visualization or quantification. In this paper, we present the first step in our fuzzy segmentation system that is capable of segmenting magnetic resonance (MR) images of a human brain. The histogram analysis based on the S-function membership and the Shannon's entropy function provides finding exact segmentation points. In the final stage, pixel classification is performed using the rule-based fuzzy logic inference. When the segmentation is complete, attributes of these classes may be determined (e.g., volumes), or the classes may be visualized as spatial objects. In contrast to other segmentation methods, like thresholding and region-based algorithms, our methods proceeds automatically and allow more exact delineation of the anatomical structures.