Breast cancer is the most common type of cancer in women after lung cancer. It is the leading cause of cancer-related deaths and remains a global risk. Recognizing a malignant breast cancer at an early stage of the disease improves the patient's survival It significantly increases the chances and reduces the secondary effects of treatments. mammography To date, it has been the most useful tool for general population screening. But only mammography Accurate detection and diagnosis of a breast lesion based on clinical findings is difficult and largely depends on the radiologist's expertise; This leads to a large number of false positive results and additional investigations. It leads. Some machine learning models are bad for speeding up cancer diagnosis It has been proposed to predict risks of developing malignant or benign tumors. Recommended deep learning algorithms; distinction between normal and abnormal pathological tissues and It plays an active role in diagnosis by segmentation. Literature searches made result; In this study, ResNet50, VGG16, LeNet, AlexNet deep learning models were used. was used and the accuracy values ​​were compared and shown on the graph. made As a result of the evaluations, ResNet50 is the model with the highest accuracy rate and all The accuracy rates of the models vary depending on their architectural features. has been evaluated.