Author's Name:	Dr.N. Venkatesa Mohan & Dr.Valliappan Raman
Subject Area:	Health Science
Subject	Medicine and Dentistry
Section	Research Paper

Mammography, Region Growing, Haralic Textures and Classification

Breast cancer is the most common cancer among women in the western world and in Asia, other than skin cancer. It is the second leading cause of cancer death in women, after lung cancer. Screening mammography (x-ray of the breast), is currently the most effective tool for early detection of breast cancer. Rational and Objective: Detection of suspicious abnormalities (masses) within mammogram is a repetitive and fatiguing task. For every thousand cases analyzed by a radiologist, only 3 to 4 are cancerous and the rest could be overlooked. Therefore the main objective of this paper is to develop a CAD system to identify regions of interest and segment the tumors in digital mammograms. The segmented image is then analyzed for estimating tumor and the results are compared against previously known diagnosis of the radiologist Materials and Methods: A fully automated Computer aided Detection (CAD) system is developed with main focus is to suppress noise, to enhance contrast between region of interest and background by enhanced segmentation, to extract and select mass\microcalcification features, detect and classify features of mammographic mass lesions and yet accurately detect the presence of breast cancer. Conclusion: This paper shows the matlab prototype implementation and experimental results of various stages in detection and segmentation of the tumor. The overall segmentation accuracy obtained is 95%. This proposed method appears to be of high clinical significance since mass detection plays an important role in diagnosis of breast cancer.