Performance analysis of mammogram CAD system using SVM and KNN classifier

A CAD system for diagnosing the mammograms is proposed in this work. The mammogram image is preprocessed using adaptive median filter and ROI is segmented using otsu's thresholding technique. Then the extracted GLCM features from ROI were given to the classifier. The classifiers such as SVM and KNN were used in this CAD system and the performance metrics were analyzed. The classification accuracy of SVM is 95.7% and sensitivity is 0.91 which is higher than KNN classifier. This demonstrates that the automated detection of breast cancer with greater accuracy and sensitivity in our CAD system is reliable as an aid to radiologists.