Detection of Breast Cancer Based on Texture Analysis from Digital Mammograms
In this study, we propose a novel breast cancer detection algorithm based on texture properties of mass area. Proposed method extracts the midpoint of mass area by using AHE (Adaptive Histogram Equalization), and selects the ROI (Region of Interest) in the original image. L1-norm based smoothing filter is then employed to stabilize the mass area, and the form of the mass is determined. Additionally, we measured homogeneity and Ranklet using SVM (Support Vector Machine) to analyze texture properties of the selected mass area. As a result, we observed that the proposed method shows the more stable and outstanding performance for Korean women compared with the existing methods.
Keywordsmammogram breast cancer SVM (Support Vector Machine) Ranklet homogeneity
Unable to display preview. Download preview PDF.
- 1.Zhang, L., Ren, Y., Huang, C., Lin, F.: A novel automatic tumor detection for breast cancer ultrasound images. In: International Conference on Fuzzy Systems and Knowledge Discovery (FSKD), pp. 401–404 (2011)Google Scholar
- 2.Nadvoretskiy, V., Ermilov, S., Brecht, H.P., Su, R., Oraevsky, A.: Image processing and analysis in a dual-modality optoacoustic/ultrasonic system for breast cancer diagnosis. Photons Plus Ultrasound: Imaging and Sensing (2011)Google Scholar
- 6.Karssemeijer, N.: Detection of masses in mammograms. In: Image-Processing Techniques for Tumor Detection, pp. 187–212. Marcel Dekker, Inc., New York (2002)Google Scholar