ISIBC: An intelligent system for identification of breast cancer

This paper presents an intelligent system for the identification of breast cancer (ISIBC) based on image processing techniques and neural classifier. Recently, many researchers have developed image classification systems for classifying breast tumors using different image processing and classification techniques. The challenge is the extraction of the real features that distinguish the benign and malignant tumors. In this paper, the extraction of the shape and texture characteristics of the images has been considered for classification of breast cancer images. The texture features are extracted using GLCM algorithm, while the shape features are extracted directly from the images. In the paper, the asymmetry, roundness, intensity levels are determined as shape characteristics of the images. Mean, standard deviation, entropy and uniformity are determined as the texture features of the images. These two features allow distinguishing the two types of breast tumors. After feature extraction process neural networks are used for classification of the images. Different image processing techniques are used in order to detect tumor and extract the region of interest from the mammogram. The following data processing operations have been done for the extraction of tumors: thresholding, filtering, adjustments, canny edge detection, and some morphological operations. The used breast images are obtained from a public database available on the internet that contains mammography images (DDSM). The experimental results show a great identification rate of 92%.