Edge detection in medical images using a genetic algorithm

Markus Gudmundsson, Essam A. El-Kwae, Mansur R. Kabuka

Research output: Contribution to journalArticle

82 Citations (Scopus)

Abstract

An algorithm is developed that detects well-localized, unfragmented, thin edges in medical images based on optimization of edge configurations using a genetic algorithm (GA). Several enhancements were added to improve the perfomance of the algorithm over a traditional GA. The edge map is split into connected subregions to reduce the solution space and simplify the problem. The edge-map is then optimized in parallel using incorporated genetic operators that perform transforms on edge structures. Adaptation is used to control operator probabilities based on their participation. The GA was compared to the simulated annealing (SA) approach using ideal and actual medical images from different modalities including magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound. Quantitative comparisons were provided based on the Pratt figure of merit and on the cost-function minimization. The detected edges were thin, continuous, and well localized. Most of the basic edge features were detected. Results for different medical image modalities are promising and encourage further investigation to improve the accuracy and experiment with different cost functions and genetic operators.

Original languageEnglish
Pages (from-to)469-474
Number of pages6
JournalIEEE Transactions on Medical Imaging
Volume17
Issue number3
StatePublished - Dec 1 1998

Fingerprint

Edge detection
Genetic algorithms
Cost functions
Mathematical operators
Magnetic resonance
Simulated annealing
Tomography
Costs and Cost Analysis
Ultrasonics
Imaging techniques
Magnetic Resonance Imaging
Experiments

Keywords

  • Edge detection
  • Genetic algorithms
  • Medical images
  • Optimization

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging
  • Radiological and Ultrasound Technology
  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Computational Theory and Mathematics

Cite this

Edge detection in medical images using a genetic algorithm. / Gudmundsson, Markus; El-Kwae, Essam A.; Kabuka, Mansur R.

In: IEEE Transactions on Medical Imaging, Vol. 17, No. 3, 01.12.1998, p. 469-474.

Research output: Contribution to journalArticle

Gudmundsson, Markus ; El-Kwae, Essam A. ; Kabuka, Mansur R. / Edge detection in medical images using a genetic algorithm. In: IEEE Transactions on Medical Imaging. 1998 ; Vol. 17, No. 3. pp. 469-474.
@article{ab295b9f19834a7c952fde10a2152975,
title = "Edge detection in medical images using a genetic algorithm",
abstract = "An algorithm is developed that detects well-localized, unfragmented, thin edges in medical images based on optimization of edge configurations using a genetic algorithm (GA). Several enhancements were added to improve the perfomance of the algorithm over a traditional GA. The edge map is split into connected subregions to reduce the solution space and simplify the problem. The edge-map is then optimized in parallel using incorporated genetic operators that perform transforms on edge structures. Adaptation is used to control operator probabilities based on their participation. The GA was compared to the simulated annealing (SA) approach using ideal and actual medical images from different modalities including magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound. Quantitative comparisons were provided based on the Pratt figure of merit and on the cost-function minimization. The detected edges were thin, continuous, and well localized. Most of the basic edge features were detected. Results for different medical image modalities are promising and encourage further investigation to improve the accuracy and experiment with different cost functions and genetic operators.",
keywords = "Edge detection, Genetic algorithms, Medical images, Optimization",
author = "Markus Gudmundsson and El-Kwae, {Essam A.} and Kabuka, {Mansur R.}",
year = "1998",
month = "12",
day = "1",
language = "English",
volume = "17",
pages = "469--474",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Edge detection in medical images using a genetic algorithm

AU - Gudmundsson, Markus

AU - El-Kwae, Essam A.

AU - Kabuka, Mansur R.

PY - 1998/12/1

Y1 - 1998/12/1

N2 - An algorithm is developed that detects well-localized, unfragmented, thin edges in medical images based on optimization of edge configurations using a genetic algorithm (GA). Several enhancements were added to improve the perfomance of the algorithm over a traditional GA. The edge map is split into connected subregions to reduce the solution space and simplify the problem. The edge-map is then optimized in parallel using incorporated genetic operators that perform transforms on edge structures. Adaptation is used to control operator probabilities based on their participation. The GA was compared to the simulated annealing (SA) approach using ideal and actual medical images from different modalities including magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound. Quantitative comparisons were provided based on the Pratt figure of merit and on the cost-function minimization. The detected edges were thin, continuous, and well localized. Most of the basic edge features were detected. Results for different medical image modalities are promising and encourage further investigation to improve the accuracy and experiment with different cost functions and genetic operators.

AB - An algorithm is developed that detects well-localized, unfragmented, thin edges in medical images based on optimization of edge configurations using a genetic algorithm (GA). Several enhancements were added to improve the perfomance of the algorithm over a traditional GA. The edge map is split into connected subregions to reduce the solution space and simplify the problem. The edge-map is then optimized in parallel using incorporated genetic operators that perform transforms on edge structures. Adaptation is used to control operator probabilities based on their participation. The GA was compared to the simulated annealing (SA) approach using ideal and actual medical images from different modalities including magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound. Quantitative comparisons were provided based on the Pratt figure of merit and on the cost-function minimization. The detected edges were thin, continuous, and well localized. Most of the basic edge features were detected. Results for different medical image modalities are promising and encourage further investigation to improve the accuracy and experiment with different cost functions and genetic operators.

KW - Edge detection

KW - Genetic algorithms

KW - Medical images

KW - Optimization

UR - http://www.scopus.com/inward/record.url?scp=0032081261&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032081261&partnerID=8YFLogxK

M3 - Article

C2 - 9735910

AN - SCOPUS:0032081261

VL - 17

SP - 469

EP - 474

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 3

ER -