An Evaluation of Wavelet Features Subsets for Mammogram Classification
This paper is about an evaluation for a feature selection strategy for mammogram classification. An earlier solution to this problem is revisited, which constructed a supervised classifier for two problems in mammogram classification: tumor nature, and tumor geometric type. The approach works by transforming the data of the images in a wavelet basis and by using a minimum subset of representative features of these textures based in a specific threshold (λ T ). In this paper different wavelet bases, variation of the selection strategy for the coefficients, and different metrics are all evaluated with known labelled images. This is a suitable solution worth further exploration. For the experiments we have used samples of images labeled by physicians. Results shown are promising, and we describe possible lines for future directions.
KeywordsMahalanobis Distance Wavelet Basis Gabor Wavelet Representative Feature Tumor Nature
- 4.http://www.wiau.man.ac.uk/services/MIAS (Mammographic Image Analysis Society)
- 5.Jain, R., Kasturi, R., Schunck, B.: Machine Vision. McGraw Hill, USA (1995)Google Scholar
- 7.Qi, H., Kuruganti, P., Liu, Z.: Early detection of breast cancer using thermal texture maps. In: IEEE Symposium on Biomedical Imaging: Macro to Nano (2002)Google Scholar
- 8.Rangayyan, R.M., Ferrari, R.J., Desautels, J.E.L., Frère, A.F.: Directional analysis of images with Gabor wavelets. In: Proceedings of XIII Brazilian Symposium on Computer Graphics and Image Processing, SIBGRAPI, pp. 170–177 (2000)Google Scholar
- 9.Woods, K.S.: Automated image analysis techniques for digital mammography, Ph. D thesis, Dept C. Science and Engineering, University of South Florida, FL, USA (1994)Google Scholar