Detection of masses in digital mammograms may helps in an early diagnosis of breast cancer. In this paper, we proposed method to detect high probability of mass areas based on texture feature analysis. Firstly, an automated segmentation of region of interests (ROIs) is done using 8-bit quantization technique. Then, Gray Level Co occurrence Matrices (GLCM) at four directions is constructed for each ROIs. This is due to the fact that the Gray Level Co occurrence Matrices (GLCM) may provide the texture-context information. The results prove that the Gray Level Co occurrence Matrices(GLCM) at 0°, 45°, 90° and 135° with a block size of 8×8 give significant texture information to identify between masses and non-masses tissues. © 2008 Springer-Verlag.
CITATION STYLE
Khuzi, A. M., Besar, R., & Zaki, W. M. D. W. (2008). Texture features selection for masses detection in digital mammogram. In IFMBE Proceedings (Vol. 21 IFMBE, pp. 629–632). Springer Verlag. https://doi.org/10.1007/978-3-540-69139-6_157
Mendeley helps you to discover research relevant for your work.