An efficient CAD for detection of tumour in mammograms using SVM

Breast tumour is one of the prime cancer type in women. Early stage of diagnosis is very important in the treatment of the disease. Mammograms are mostly employed in the Computer Aided Detection (CAD) techniques because a mammogram can often detect tumour in early stage. We propose an efficient Gray Level Co-occurrence Matrix (GLCM) based SVM technique for classifying mammograms. In this paper, classification is done in single view mammograms after performing preprocessing, ROI segmentation, GLCM feature extraction and SVM classification. The proposed method was evaluated on two datasets: University of South Florida Digital Mammography (USFDM) and Mammogram Image Analysis Society (MIAS) database. Early diagnosis and high accuracy rate could be achieved by combining best methods at each stage of diagnosis. From experimental results, it was observed that, the proposed method using GLCM extracted features for classifying tumour and non tumour with SVM classifier could give accurate results.