Application of Fractals to Detect Breast Cancer

Abstract

Breast cancer is one of the major causes of death among women. Small clusters of micro calcifications appearing as collection of white spots on mammograms show an early warning of breast cancer. Image segmentation is an important element of Digital Image processing that subdivides the image into discrete regions/objects, each identified by the property of homogeneity of pixels. X-ray mammography is used as diagnostic tool for diagnosis of breast cancer. Edge detection of micro calcification clusters in mammogram images is the main issue of early detection of breast cancer. Fractals are of rough or fragmented geometric shape that can be subdivided in parts, each of which is a reduced similar of the whole. Fractal dimension and Hurst exponent are used to locate the micro calcifications in the mammogram. The concept of fractal is associated with geometrical objects satisfying criteria such as self-similarity and fractal dimensionality. Present method of edge detection is superior compared to conventional Sobel method, in which detection of edges of the regions or objects in an image takes place by the Fudge factor. The paper presents the application of fractals for early detection of breast cancer.