Automatic Segmentation and Identification of Abnormal Breast Region in Mammogram Images Based on Statistical Features

Abstract

Breast cancer is one of the most common malignant diseases among women;
Mammography is at present one of the available method for early detection of
abnormalities which is related to breast cancer. There are different lesions that are
breast cancer characteristic such as masses and calcifications which can be detected
trough this technique. This paper proposes a computer aided diagnostic system for
the extraction of features like masses and calcifications lesions in mammograms for
early detection of breast cancer. The proposed technique is based on a two-step
procedure: (a) unsupervised segmentation method includes two stages performed
using the minimum distance (MD) criterion, (b) feature extraction based on Gray
level Co-occurrence matrices GLCM for the identification of masses and
calcifications lesions. The method suggested for the detection of abnormal lesions
from mammogram image segmentation and analysis was tested over several images
taken from National Center for Early Detection of cancer in Baghdad.