Texture Features Selection for Masses Detection In Digital Mammogram

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.

[1]  N. Szekely,et al.  A hybrid system for detecting masses in mammographic images , 2004, Proceedings of the 21st IEEE Instrumentation and Measurement Technology Conference (IEEE Cat. No.04CH37510).

[2]  Sergios Theodoridis,et al.  Mammographic mass classification using textural features and descriptive diagnostic data , 2002, 2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628).

[3]  Rangaraj M. Rangayyan,et al.  Gradient and texture analysis for the classification of mammographic masses , 2000, IEEE Transactions on Medical Imaging.

[4]  Heng-Da Cheng,et al.  Approaches for automated detection and classification of masses in mammograms , 2006, Pattern Recognit..

[5]  F.E.Z. Abou-Chadi,et al.  Early detection of masses in digitized mammograms using texture features and neuro-fuzzy model , 2003, Proceedings of the Twentieth National Radio Science Conference (NRSC'2003) (IEEE Cat. No.03EX665).

[6]  Sameer Singh,et al.  Detection of masses in mammograms using texture features , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[7]  Rangaraj M. Rangayyan,et al.  Classification of tumors and masses in mammograms using neural networks with shape and texture features , 2003, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439).