Analysis of Malignant Neoplastic Using Image Processing Techniques

Breast Cancer is the second most frequently diagnosed cancer, leading to cancer death worldwide. Early detection of breast cancer saves lives. Mammograms play an important tool in early detection of breast cancer. Cancer that originates from the breast tissue is called as Breast Cancer. Cancer originating from the inner lining of milk ducts is called as Ductal Carcinomas (70%). Cancer originating from the lobules which are the glands that produce milk is called as Lobular Carcinomas (15%). Breast Cancer occurs in humans and other mammals. Every 74 seconds, somewhere in the world, someone dies from breast cancer, in which the majority is woman. Approximately 425,000 women around the world died from the disease in 2010. At this rate, 10.6 million women will die from breast cancer during the next 25 years. It is 100 times more common in women than in men. Mammography is a specific type of imaging that uses a low dose X-Ray system to examine breast cancers. Mammography exam is called Mammogram. In our proposed project, Image processing techniques are used in accurate and timely detection of Breast Cancer in high resolution medical images. Collected images from the database are segmented using Marker-Controlled Watershed segmentation method. The segmented image is then enhanced and the features are extracted using Gabor filter. Another methodology of Circular Hough Transform is used to obtain 3-Dimensional image of the Cancer. KeywordBreast Cancer, Carcinomas, Mammogram, Marker–Controlled Watershed Segmentation, Gabor filter, Circular Hough Transform.