Evaluation of Screening Mammograms by Local Structural Mixture Models

0382295 - ÚTIA 2013 RIV CZ eng C - Conference Paper (international conference)
Grim, Jiří - Lee, G. L.
Evaluation of Screening Mammograms by Local Structural Mixture Models.
Stochastic and Physical Monitoring Systems SPSM 2012. Praha: Czech Technical University in Prague, 2012, s. 51-61. ISBN 978-80-01-05130-6.
[Stochastic and Physical Monitoring Systems. Zlenice near Prague (CZ), 25.06.2012-30.06.2012]
R&D Projects: GA ČR GA102/08/0593
Grant - others:GA ČR(CZ) GAP403/12/1557
Institutional support: RVO:67985556
Keywords : Screening mammography * Texture information * Local statistical model * Log-likelihood image * Structural Gaussian mixture
Subject RIV: IN - Informatics, Computer Science
http://library.utia.cas.cz/separaty/2012/RO/grim-evaluation of screening mammograms by local structural mixture modelsr.pdf

We consider the recently proposed evaluation of screening mammograms by local statistical models. The model is defined as a joint probability density of inside grey levels of a suitably chosen search window. We approximate the model density by a mixture of Gaussian densities. Having estimated the mixture parameters we calculate at all window positions the corresponding log-likelihood values which can be displayed as grey levels at the respective window centers. The resulting log-likelihood image closely correlates with the original mammogram and emphasizes the structural details. In this paper we try to enhance the log-likelihood images by using structural mixture model capable of suppressing the influence of noisy variables.
Permanent Link: http://hdl.handle.net/11104/0212556