A Hybrid Framework for Segmentation of MR Medical Images Using Adjusted Ant Colony Optimization

Author Name(s): Yogesh Sayajirao Bahendwar, Dr. Rajesh H. Talwekar
Author Email: bahendwar72@gmail.com

Abstract

In this paper a new framework is suggested for segmentation of medical images (MRI) using hybrid optimization technique. This frame work includes de-nosing as image enhancement technique using discrete wavelet transform and initial segmentation is obtained by Hidden Markov random field model along with Kmeans clustering to get Maximum a posterior values (thresholds). The optimal solution for these thresholds is achieved by incorporating a new concept of Adjusted Ant colony optimization. Finally a fine segmentation is obtained. The algorithm is tested for some of the medical images and for validation purpose various parameters like accuracy, sensitivity, dice, Jaccard, are obtained

Introduction

Medical image segmentation is often the first step in quantitative image analysis. The aim of segmentation is to identify the target anatomy or pathology and delineate the boundary of these structures of interest. Image segmentation plays a vital role in numerous medical applications (Ahemadet al. 2006).Medical image analysis is a wide concept that includes several processing and analysis methods applied to a number of different imaging modalities. This image analysis can be divided into different subjects such as: Image enhancement, segmentation, registration, quantification. Methods for performing segmentations vary widely, depending on the specific application, imaging modality, and other factors. For example, the segmentation of brain tissue has different requirements from the segmentation of the liver. General imaging artefacts such as noise, partial volume effects, and motion can also have significant consequences on the performance of segmentation algorithms. Furthermore, each imaging modality has its own idiosyncrasies with which to contend. There is currently no single segmentation method that yields acceptable results for every medical image. Methods do exist that are more general and can be applied to a variety of data. However, methods that are specialized to particular applications can often achieve better performance by taking into account prior knowledge. Selection of an appropriate approach to a segmentation problem can therefore be a difficult dilemma.

Conclusion

In this paper, the meta-heuristic image segmentation approach is presented. The approach used for segmentation is the Ant colony optimization. The improved accuracy rate according to the experimental results is due to better classification of natural brain structure. Experiments on MRI images show that the segmentation result of the proposed method has higher accuracy compared to existing algorithms.

687 total views, no views today

Download PDF File

About the author: admin