Mammogram Image Analysis for Breast Cancer Detection

Abstract

Breast cancer is the uncontrolled growth of cells in the breast region. It is the second leading cause of death in women today. A mammography is an X-ray of the breast tissue. Mammographic image classification can be achieved using Gabor wavelet. The main purpose of the proposed work is to develop a system which classifies mammographic images using Gabor wavelet feature. The images are taken from Mammographic Image Analysis Society (MIAS) database. The proposed system involves three major steps called Pre-processing, Feature Extraction and Classification. Pre-processing reduces noise and normalizes staining intensity. After preprocessing a noise free image goes to the Segmentation phase. Segmentation is the process of partitioning an image into semantically interpretable regions. In feature extraction stage every image is assigned a feature vector to recognize it. Gabor Wavelet is used for Feature Extraction. The extracted features are then dimensionally reduced by Principal Component Analysis (PCA) method to avoid excess computations. Then Support Vector Machine (SVM) classifier is used for classification. The experimental results obtained from the system developed in this research will prove to be beneficial for the automated classification of mammographic images. The proposed method can allow the radiologist to focus rapidly on the relevant parts of the mammogram and it can increase the effectiveness and efficiency of radiology clinics.