Parameter estimation in stochastic mammogram model by heuristic optimization techniques

S. Easter Selvan, C. Cecil Xavier, Nico Karssemeijer, Jean Sequeira, Rekha aley Cherian, Bharathi Y. Dhala

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

The appearance of disproportionately large amounts of high-density breast parenchyma in mammograms has been found to be a strong indicator of the risk of developing breast cancer. Hence, the breast density model is popular for risk estimation or for monitoring breast density change in prevention or intervention programs. However, the efficiency of such a stochastic model depends on the accuracy of estimation of the model's parameter set. We propose a new approach - heuristic optimization - to estimate more accurately the model parameter set as compared to the conventional and popular expectation-maximization (EM) algorithm. After initial segmentation of a given mammogram, the finite generalized Gaussian mixture (FGGM) model is constructed by computing the statistics associated with different image regions. The model parameter set thus obtained is estimated by particle swarm optimization (PSO) and evolutionary programming (EP) techniques, where the objective function to be minimized is the relative entropy between the image histogram and the estimated density distributions. When our heuristic approach was applied to different categories of mammograms from the Mini-MIAS database, it yielded lower floor of estimation error in 109 out of 112 cases (97.3%), and 101 out of 102 cases (99.0%), for the number of image regions being five and eight, respectively, with the added advantage of faster convergence rate, when compared to the EM approach. Besides, the estimated density model preserves the number of regions specified by the information-theoretic criteria in all the test cases, and the assessment of the segmentation results by radiologists is promising.

Original languageEnglish (US)
Pages (from-to)685-695
Number of pages11
JournalIEEE Transactions on Information Technology in Biomedicine
Volume10
Issue number4
DOIs
StatePublished - Oct 1 2006

Fingerprint

Stochastic models
Parameter estimation
Entropy
Databases
Breast Neoplasms
Efficiency
Evolutionary algorithms
Error analysis
Particle swarm optimization (PSO)
Heuristics
Breast Density
Statistics
Monitoring

All Science Journal Classification (ASJC) codes

  • Biotechnology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Selvan, S. Easter ; Xavier, C. Cecil ; Karssemeijer, Nico ; Sequeira, Jean ; Cherian, Rekha aley ; Dhala, Bharathi Y. / Parameter estimation in stochastic mammogram model by heuristic optimization techniques. In: IEEE Transactions on Information Technology in Biomedicine. 2006 ; Vol. 10, No. 4. pp. 685-695.
@article{e442481cf457446e93dcf2fe187675bc,
title = "Parameter estimation in stochastic mammogram model by heuristic optimization techniques",
abstract = "The appearance of disproportionately large amounts of high-density breast parenchyma in mammograms has been found to be a strong indicator of the risk of developing breast cancer. Hence, the breast density model is popular for risk estimation or for monitoring breast density change in prevention or intervention programs. However, the efficiency of such a stochastic model depends on the accuracy of estimation of the model's parameter set. We propose a new approach - heuristic optimization - to estimate more accurately the model parameter set as compared to the conventional and popular expectation-maximization (EM) algorithm. After initial segmentation of a given mammogram, the finite generalized Gaussian mixture (FGGM) model is constructed by computing the statistics associated with different image regions. The model parameter set thus obtained is estimated by particle swarm optimization (PSO) and evolutionary programming (EP) techniques, where the objective function to be minimized is the relative entropy between the image histogram and the estimated density distributions. When our heuristic approach was applied to different categories of mammograms from the Mini-MIAS database, it yielded lower floor of estimation error in 109 out of 112 cases (97.3{\%}), and 101 out of 102 cases (99.0{\%}), for the number of image regions being five and eight, respectively, with the added advantage of faster convergence rate, when compared to the EM approach. Besides, the estimated density model preserves the number of regions specified by the information-theoretic criteria in all the test cases, and the assessment of the segmentation results by radiologists is promising.",
author = "Selvan, {S. Easter} and Xavier, {C. Cecil} and Nico Karssemeijer and Jean Sequeira and Cherian, {Rekha aley} and Dhala, {Bharathi Y.}",
year = "2006",
month = "10",
day = "1",
doi = "10.1109/TITB.2006.874197",
language = "English (US)",
volume = "10",
pages = "685--695",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

Parameter estimation in stochastic mammogram model by heuristic optimization techniques. / Selvan, S. Easter; Xavier, C. Cecil; Karssemeijer, Nico; Sequeira, Jean; Cherian, Rekha aley; Dhala, Bharathi Y.

In: IEEE Transactions on Information Technology in Biomedicine, Vol. 10, No. 4, 01.10.2006, p. 685-695.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Parameter estimation in stochastic mammogram model by heuristic optimization techniques

AU - Selvan, S. Easter

AU - Xavier, C. Cecil

AU - Karssemeijer, Nico

AU - Sequeira, Jean

AU - Cherian, Rekha aley

AU - Dhala, Bharathi Y.

PY - 2006/10/1

Y1 - 2006/10/1

N2 - The appearance of disproportionately large amounts of high-density breast parenchyma in mammograms has been found to be a strong indicator of the risk of developing breast cancer. Hence, the breast density model is popular for risk estimation or for monitoring breast density change in prevention or intervention programs. However, the efficiency of such a stochastic model depends on the accuracy of estimation of the model's parameter set. We propose a new approach - heuristic optimization - to estimate more accurately the model parameter set as compared to the conventional and popular expectation-maximization (EM) algorithm. After initial segmentation of a given mammogram, the finite generalized Gaussian mixture (FGGM) model is constructed by computing the statistics associated with different image regions. The model parameter set thus obtained is estimated by particle swarm optimization (PSO) and evolutionary programming (EP) techniques, where the objective function to be minimized is the relative entropy between the image histogram and the estimated density distributions. When our heuristic approach was applied to different categories of mammograms from the Mini-MIAS database, it yielded lower floor of estimation error in 109 out of 112 cases (97.3%), and 101 out of 102 cases (99.0%), for the number of image regions being five and eight, respectively, with the added advantage of faster convergence rate, when compared to the EM approach. Besides, the estimated density model preserves the number of regions specified by the information-theoretic criteria in all the test cases, and the assessment of the segmentation results by radiologists is promising.

AB - The appearance of disproportionately large amounts of high-density breast parenchyma in mammograms has been found to be a strong indicator of the risk of developing breast cancer. Hence, the breast density model is popular for risk estimation or for monitoring breast density change in prevention or intervention programs. However, the efficiency of such a stochastic model depends on the accuracy of estimation of the model's parameter set. We propose a new approach - heuristic optimization - to estimate more accurately the model parameter set as compared to the conventional and popular expectation-maximization (EM) algorithm. After initial segmentation of a given mammogram, the finite generalized Gaussian mixture (FGGM) model is constructed by computing the statistics associated with different image regions. The model parameter set thus obtained is estimated by particle swarm optimization (PSO) and evolutionary programming (EP) techniques, where the objective function to be minimized is the relative entropy between the image histogram and the estimated density distributions. When our heuristic approach was applied to different categories of mammograms from the Mini-MIAS database, it yielded lower floor of estimation error in 109 out of 112 cases (97.3%), and 101 out of 102 cases (99.0%), for the number of image regions being five and eight, respectively, with the added advantage of faster convergence rate, when compared to the EM approach. Besides, the estimated density model preserves the number of regions specified by the information-theoretic criteria in all the test cases, and the assessment of the segmentation results by radiologists is promising.

UR - http://www.scopus.com/inward/record.url?scp=33750200918&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750200918&partnerID=8YFLogxK

U2 - 10.1109/TITB.2006.874197

DO - 10.1109/TITB.2006.874197

M3 - Article

C2 - 17044402

AN - SCOPUS:33750200918

VL - 10

SP - 685

EP - 695

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 4

ER -