This document summarizes a research paper that aims to classify breast lesions as benign or malignant using ultrasound and ultrasound elastography images. It presents a methodology for preprocessing images, extracting textural features using discrete wavelet transform and gray level co-occurrence matrix, performing feature reduction with principal component analysis, and classifying images using support vector machine and k-nearest neighbor classifiers. The methodology is applied to a dataset of ultrasound and elastography images and classifiers are evaluated based on accuracy, sensitivity, and specificity metrics derived from confusion matrices. The results show high performance for both classifiers on the elastography images and slightly better performance for the k-nearest neighbor classifier on the ultrasound images.