Advanced Enhancement Techniques for Breast Cancer Classification in Mammographic Images

Background: Breast cancer is one of the most significant health problems in world. Early diagnosis breast very important for treatment. Image enhancement techniques have been used to improve captured images quick and accurate diagnosis. These include median filtering, edge enhancement, dilation, erosion, contrast-limited adaptive histogram equalization. Although these many studies, their results not reached optimum values based on image properties methods feature extraction classification. Methods: In this study, were implemented guarantee best enhancement. They applied 319 collected from Mammographic Analysis Society (MIAS) database. The Gabor filter local binary pattern as together with support vector machine (SVM), linear discriminant analysis (LDA), nearest neighbor (KNN) classifiers. Results: experimental work indicates that by merging features pattern, 97.8%, 100%, 94.6% normal/abnormal 85.1%, 88.7%, 81.9% benign/malignant using SVM, LDA, KNN classifiers, respectively. Conclusion: obtained combining two tested strategies LDA a classifier.