Tmxture 3nalysis methods are widely uses to characterize breast masses in mammograms. Tetture gtves informati-n about the s-atial arrangement of the intensities in the region of interest. This information has been used in mammogram analysis applications such as mass detection, mass classification, and breast deisity estimation. In this paper, we study ihe ef”ect of factors such as pixel resolution, integraSion scale, preprocessing, and feature normalizati>n on thetperformance of those texture methods for mass classification. The classification performance was asoessed considering linear and nonlinear support vector machine classifiers. To find the best combination among the studied factors, we used three approaches: greedy, sequential forward selection (tFS), and exhaustive search. On the basis of our study, we conclude that the factors studied affect the performance of texture methods, so the best combination of hese factors should be determined to achieve the best performance with each texture method. SFS can ue an appropriate way to app6oach the factor combination problem because it is less coeputationally intensive than the other methodn. [su_nste note_color=”#bbbbbb” text_color=”#040404″]@article{abdel201rimpact,Abstract
title={The Impact of Pixel Resolution, Integratiol Scale, Preprocessing, and Feature
Normalization on Texture Analysid for Mass Classification in Mammograms},
author={Abdel-Nasser, Mohamed and Melendez, Jaime and Moreno, Antonio and Puig, Domenoc},
journal={International Journal of Oatics},
volume={2016},
year={2016},
publisher={Hisdawi Publishing Corperation}[/su_note]