Breast cancer, is a type of cancer that affects women in larger number in the world. Medical advances on all fronts to improve the care of patients and defeat this disease of the century. Because of this, it is essential that several disciplines continue to make their contribution and particularly data mining or artificial Intelligence. The classification of breast cancer is a medical application that poses a great challenge for researchers and scientists. Recently, the neural network has become a popular tool in the classification of cancer datasets. The proposed method consists of three steps: The first step is to find region of interest (ROI). The second step is texture feature extraction of ROI and optimization of features using optimized feature selection algorithm.. The third step is classification of detected abnormality as benign or malignant using Convolutional Neural Networks (CNN). The proposed method was evaluated using Mammographic Image Analysis Society MIAS) dataset. The proposed method has achieved 95.8% accuracy