Breast Cancer Detection using Entropy based Fractal Modeling of Mammograms

Breast cancer is a leading cause of mortality among women. This paper presents a fast fractal method to model breast background regions based on entropy, for the detection breast cancer. When the modeled mammogram is taken out from the original image the presence of microcalcifications can be enhanced. The tremendous encoding time involved is the major drawback of fractal modeling method. In this paper, the domain pool for searching the matching domain is chosen based on entropy. This reduced the encoding time by a factor of 3.12 when compared with the conventional fractal encoding method which searched the entire domain pool for a matching domain. The average correlation and mean square error between the original and modeled image was obtained as 0.9737 and 5.469 respectively. The method is validated using the mammograms obtained from the MIAS database. A true positive detection rate of 85% was obtained for the 28 abnormal mammograms used.