Hershey, Pennsylvania
New York, New YorkBeijing, China
Automatic MRI Brain Image Segmentation Using Gravitational Search-Based Clustering Technique

Automatic MRI Brain Image Segmentation Using Gravitational Search-Based Clustering Technique

Vijay Kumar (JCDM College of Engineering, India), Jitender Kumar Chhabra (National Institute of Technology, India), and Dinesh Kumar (GJUS&T, India)
Copyright: © 2017 |Pages: 16
DOI: 10.4018/978-1-5225-0571-6.ch005
OnDemand:
(Individual Chapters)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Image segmentation plays an important role in medical imaging applications. In this chapter, an automatic MRI brain image segmentation framework using gravitational search based clustering technique has been proposed. This framework consists of two stage segmentation procedure. First, non-brain tissues are removed from the brain tissues using modified skull-stripping algorithm. Thereafter, the automatic gravitational search based clustering technique is used to extract the brain tissues from the skull stripped image. The proposed algorithm has been applied on four simulated T1-weighted MRI brain images. Experimental results reveal that proposed algorithm outperforms the existing techniques in terms of the structure similarity measure.
Chapter Preview
Top

Background

In this section, we first define the terminology that will be used and brief description of recently developed segmentation methods.

Definitions

Image segmentation is an important process for medical image analysis. It is defined as the process of subdividing the image into constituent regions. These regions have two main properties: 1.) homogeneity within a region, 2.) heterogeneity between the regions. The mathematical formulation of segmentation is defined as follows (Raut et al., 2009):

Let 978-1-5225-0571-6.ch005.m01be the set of all image pixels. By applying segmentation on978-1-5225-0571-6.ch005.m02, it is partitioned into 978-1-5225-0571-6.ch005.m03different non-overlapping regions 978-1-5225-0571-6.ch005.m04such that:

978-1-5225-0571-6.ch005.m05
(1)

The main goal of segmentation is to change the representation of an image into something that is more meaningful and easier to analyze (Shapiro & Stockman, 2001). Image segmentation is often treated as pattern recognition problem since it requires classification of pixels (Li et al., 2005). The role of segmentation in medical imaging is to study anatomical structure of brain, identify the brain tissues, measure the growth of tumor and help in radiation dose calculation.

Complete Chapter List

Search this Book:
Reset