Detection of Microcalcification in Mammogram Images using Support Vector Machine based Classifier

Breast cancer is one of the most frequently occurring disease which leads even to death among women community. The appearance of micro-calcifications in mammograms is an early sign of breast cancer. To overcome the issue, automated micro-calcification detection techniques play a vital role in cancer diagnosis and treatment. In this paper we proposed Support Vector Machine (SVM) based classifier to detect the microcalcification at each location in the mammogram. The proposed method has been implemented in three stages a) pre-processing b) ROI extraction and c) feature extraction and classification. The proposed method was evaluated with Mammogram Image Analysis Society (MIAS) database. Experimental results show that, when compared to several other methods SVM shows 90% microcalcification detection in mammograms.