A Comparison of Multiple Filtering Methods for Edge Detection of Breast Cancer Cells

Breast cancer is second most commonly diagnosed cancer worldwide. In order to find the cure, it is necessary to quickly diagnose the disease accurately and treat it based on the kind of symptoms appeared. Breast cancer has several classifications, which may help to determine the best treatment. The most important of these classifications are binary classification, either benign or malignant. If the cancer is in benign stage, less invasive and risk of treatments is used than for malignant stage. The main cause of breast cancer is when a single cell or group of cells escapes from the usual controls, that regulate cellular growth and begins to multiply and spread. This activity may result in a mass, tumor or neoplasm. The present paper implies the edge detection techniques for the cancer cell detection purpose. The present paper deals with observation of breast cancer classification through Image Processing using the various filters which are mainly gradient based Roberts and Sobel. Laplacian based edge detector which is Canny edge detector. The various aspects and the implementation of above mentioned filters has been put across in the present paper. The images and data sample have been taken from the Digital Database for Screening Mammography (DDSM) and American cancer society and an effort has been made for the detection of malignant cells responsible for cancer