Contextual and Non-Contextual Features Extraction and a Selection Method for Microcalcifications Detection

Author

Vega-Corona, Antonio ; Sanchez-Garcia, M. ; González-Romo, Mario ; Quintanilla-Dominguez, Joel ; Barron-Adame, J.M.

Author_Institution

Univ. de Guanajuato, Guanajuato

fYear

2006

fDate

24-26 July 2006

Firstpage

1

Lastpage

6

Abstract

In this paper a method to extract and build patterns to model microcalcifications from digitized mammography is presented. The proposed method consist in a combination of two steps, in the first one, a feature extraction method is applied using multiscale wavelet image processing, and is combined with a Self Organizing Neural Network to solve the segmentation image problem. In the second one, a feature selection method is considered applying a Generalized Regression Neural Networks (GRNN) in order to obtain an optimal and a short input vector for classifier design proposes. Optimal results were obtained and compared with others.

Keywords

feature extraction; generalisation (artificial intelligence); image segmentation; mammography; medical image processing; self-organising feature maps; digitized mammography; feature extraction; feature selection method; generalized regression neural network; image segmentation; microcalcification detection; multiscale wavelet image processing; self organizing neural network; Artificial neural networks; Breast cancer; Coronary arteriosclerosis; Feature extraction; Image analysis; Image segmentation; Neural networks; Organizing; Spatial databases; Wavelet transforms;

fLanguage

English

Publisher

ieee

Conference_Titel

Automation Congress, 2006. WAC '06. World

Conference_Location

Budapest

Print_ISBN

1-889335-33-9

Type

conf

DOI

10.1109/WAC.2006.375924

Filename

4259840