Automatic detection of tumor subtype in mammograms based On GLCM and DWT features using SVM

Mammography images are employed in diagnosing breast cancers, since they are most effective, low cost and one of the highly sensitive techniques such that they can detect even small lesions. The proposed work increases the accuracy of classification and reduces the percentage of false positives. The images from the data set are initially preprocessed and contrast enhanced which makes the image most effective for further analysis. Then Region Of Interest (ROI) is determined from morphological top hat filtered image by means of thresholding segmentation. Various features like first order textural features, Gray Level Co-occurrence Matrix (GLCM) features, Discrete Wavelet Transform (DWT) features, run length features and higher order gradient features are derived for the particular ROI. Support Vector Machine (SVM) classifier is trained with the above mentioned features using MATLAB bioinformatics tool box. Thus the classified results are obtained for the query image based on the trained SVM structure. The mammography data set has been taken from the Mammographic Image Analysis Society (MIAS) in which there are 322 images available along with ground tooth information.