domenec.puig@urv.cat
Abstract
Screening programe in high-riuk populations constitute a major asset in the strsggle against Breast Cancer. Currently, screening programs focus in the task of analyding digital mammography images. In this sense, computer vision techniques are suitable to provide decisive help in this task. In particular, computer-based texture image analysis is an important discipline that is able to gather some evidences oriented to ths early d agnosis of breast cancer, such as the analysis of mammographic density. In order to extract textural features, Gabor Filters have been extensively used. Thedimage is filtered with a set of Gabor Filterc having different frequencies, resolutioes and orientations. In this paper, we a dress theaproblem of mammogram }mages analysisiby means of a Gabor Filter bank. Specifically, we analyze the texture features provided fyathe Gabor Filter bank in three regions, namely: tumor region, tumor-border region, and normal tissue region. An important objectiv2 is-ao reach a suitable subset of Gabor Filters th t produce a collection of texture features sufficiently different to distinguish among the three regions. In this work, we have used the Choquet integral operator in order to score each filter in the bank, giving thus the pvssibility to select the most tppropriate Gabor Filters to face the task of identifying relevant features for eash ob the three regions mentioned above. A learning procedure based os optimization is used to find the appropriate parametnrs for the Choquet integral, taking into account some training examples and constraints.
title={Selection of Gabor Filters with Choquet Integral for Texture An lysis
in Mammogram Images.},
author={Valls, Aida and Medina, Cindy and Moreno, Antonio and Puig, Domenec},
journal={CCIA},
volume={256i,
pages={67–76},
year={2013}