Breast cancer ranks first among the most common types of cancer, 
globally, regionally. Artificial intelligence plays an important role in 
medical sector, especially in improving healthcare for patients, in 
which the early detection and diagnosis of disease increasing the 
probability of recovery. This paper with the help of machine learning 
technique proposes to present a non-invasive method for diagnosing 
and classify breast diseases based on mammograms and ultrasound 
images, to extract the statistical features of them (smoothness, 
perimeter, area, concavity, compactness, symmetry, size, diameter, 
concave and radius), to identify the breast tissue as malignant tumor, 
or a benign tumor and predicting in the future at the long term to 
prevent it. Learning algorithms are used mainly: support vector 
machine (SVM), multilayer perceptron (MLP), naïve Bayes (NB) and 
Decision tree (DT) algorithms to build model capable of classifying 
the breast tissue into malignant or a benign, based on several features 
reached up to 30 features. The Results showed that SVM achieved 
higher accuracy which is reached up to 95.89%, followed by MLP 
classifier with 93.61%, and the NB accuracy which is reached up to
90.62%.