Digital Mammogram Segmentation based on Fisher Information Measure

Zaher A. Abo-Eleneen, Gamil Abdel-Azim, and Mawaheb K. El Sousow


Segmentation image, Mammography images, Breast cancer, Fisher information measure


Mammogram segmentation is one of the important and critical tasks in automatic mammogram image analysis, with the goal of finding abnormality presented in the mammogram. The main purpose of mammogram segmentation is detecting the suspicious regions. In this paper, we are proposed the delectation of the suspicious regions on digital mammograms based on the Fisher information measure. The proposed method is applied for several different kinds of test images (fatty, fatty-glandular and dense glandular) of mini-MIAS database (Mammogram Image Analysis Society database (UK)) to demonstrate their effectiveness and usefulness. The proposed method is compared with a different segmentation based information theoretical methods. The experimental results on mammography images showed the effectiveness in the detection of suspicious regions. In order to objectively assess the proposed method, the uniformity measure, is used for performance evaluation. This study can be a part of developing a computer-aided decision (CAD) system for early detection of breast cancer.

Important Links:

Go Back