Mass Detection in Mammograms Using Fractal Analysis

H. Sager, Kamal

	Mass Detection in Mammograms Using Fractal Analysis
Al-Mustansiriyah Journal of Science
Article 1, Volume 22, Issue 3, 2011, Pages 93-102
Author
Kamal H. Sager
Abstract
Mammography is considered to be the best available technique for early detection of breast cancer yet. The most common breast abnormalities that may indicate breast cancer are masses and calcifications. The challenge is to quickly and accurately overcome the development of breast cancer which affects more and more women through the world. Micro calcifications appear in a mammogram as fine, granular clusters, which are often difficult to identify in a raw mammogram. One of the major mammographic characteristics for mass classification is texture In this paper the use of functions for computing texture based on fractal analysis measures is prescribed. MDE (Mass Dimension Estimation) algorithm is employed. The developed algorithm consists of automatic extraction of the fractal dimension feature for the mammogram image, and using a classifier that automatically identifies the various abnormalities existed in the images according to their fractal dimension behavior. The algorithm evaluates the region properties of the mammogram image and thereby would classify the image into important segments based on the different fractal aspects within the image. Images from MIAS data base (Mammogram Image Analysis Society database (UK)) have been considered to conduct the proposed methods. The segmentation thus obtained is comparatively better than the other normal methods.

Statistics Article View: 63 PDF Download: 4