Tsallis Entropy Extraction for Mammographic Region Classification
Breast cancer is the second disease responsible for women’s death in the world. To reduce the number of cases, screening mammography is used to detect this disease. To improve exam accuracy results, computer-aided systems (CAD) have been developed to analyze the mammography and provide statistics based on image features extracted. This paper presents a novel approach for a computer-aided detection system (CADe) based on Tsallis entropy extraction from quantized gray level co-occurrence matrix (GLCM) from mass images. A comparison study is presented based on a feature extraction scheme using weigthed Haralick features. The best result accuracy rate was 91.3% from Tsallis entropy based on GLCM matrix using 24 feature measures.
KeywordsTsallis entropy Mammography Classification SVM Haralick features
- 1.Globocan Cancer Fact Sheets: Breast Cancer. http://globocan.iarc.fr/Default.aspx. Accessed 03 July 2015
- 3.Mavroforakis, M., Georgiou, H., Cavouras, D., Dimitropoulos, N., Theodoridis, S.: Mammographic mass classification using textural features and descriptive diagnostic data. In: 2002 14th International Conference on Digital Signal Processing, DSP 2002, vol. 1, pp. 461–464 (2002)Google Scholar
- 4.Martins, L., Junior, G.B., Silva, A.C., de Paiva, A.C., Gattass, M.: Detection of masses in digital mammograms using k-means and support vector machine. ELCVIA: Electron. Lett. Comput. Vis. Image Anal. 8(2), 39–50 (2009)Google Scholar
- 8.Heath, M., Bowyer, K., Kopans, D., Kegelmeyer, P., Moore, R., Chang, K., Munishkumaran, S.: Current status of the digital database for screening mammography. In: Karssemeijer, N., Thijssen, M., Hendriks, J., van Erning, L. (eds.) Digital Mammography, vol. 13, pp. 457–460. Springer, Heidelberg (1998)CrossRefGoogle Scholar
- 10.Mata, B., Meenaksh, M.: A novel approach for automatic detection of abnormalities in mammograms. In: 2011 IEEE Recent Advances in Intelligent Computational Systems (RAICS), pp. 831–836 (2011)Google Scholar