
	Journal of Applied Sciences
	Year: 2012 \| Volume: 12 \| Issue: 6 \| Page No.: 587-592 DOI: 10.3923/jas.2012.587.592

Automatic Tissue Segmentation in Medical Images using Differential Evolution

K. Karteeka Pavan, V. Sesha Srinivas, A. SriKrishna and B. Eswara Reddy

Abstract: Segmentation of medical images is a challenging task and preprocessing step in medical diagnosis. Evolutionary algorithms such as Genetic Algorithms (GA) have been found to be effective in medical image segmentation. Almost all GAs are semiautomatic, requires either some parameters or domain knowledge such as number of segments, shape, texture etc. Differential Evolution (DE) is a simple and robust evolutionary algorithm and Automatic Clustering using Differential Evolution (ACDE) is a variant of DE. There is no study in medical image segmentation using ACDE. This study is made an attempt to extract the shape of the tissues in medical images automatically using ACDE. The performance of the ACDE algorithm in determining shape of breast cancer, lung tissues has been studied using different ultrasound images. The experimental results are compared with the regions identified by the radiologist and have demonstrated that the ACDE can extract shape of the tissues automatically (without domain knowledge) and helpful in operation surgery and radiology to cure diseases like breast cancer.

PDF Fulltext XML References Citation Report Citation

RELATED ARTICLES:

•	Multi-Objective Differential Evolution Algorithm for Solving Engineering Problems

•	A Modified Tabu Search Approach for the Clustering Problem

•	A New Differential Evolutionary Algorithm with Neighborhood Search

•	Segmentation of Satellite Imagery using RBF Neural Network and Genetic Algorithm

•	Strategies of Differential Evolution for Optimum Cropping Pattern

How to cite this article:

K. Karteeka Pavan, V. Sesha Srinivas, A. SriKrishna and B. Eswara Reddy, 2012. Automatic Tissue Segmentation in Medical Images using Differential Evolution. Journal of Applied Sciences, 12: 587-592.

DOI: 10.3923/jas.2012.587.592

URL: https://scialert.net/abstract/?doi=jas.2012.587.592

COMMENT ON THIS PAPER

Navigation


		Online First
		Current Issue
		Previous Issues
		Editorial Board
		Submit a Manuscript
		Guide to Authors
		Subscribe to E-alerts

Indexed In


		AGRIS
		ASCI-Database
		Asian Digital Library
		Google Scholar

Science Alert