Abstract: Breast cancer is one of the major causes of death and the most common type of cancer among women worldwide. Breast cancer risk increases with age. Women within the age of 15-54 have more risk of breast cancer. Treatment is more efficient when detected early, as the evolution into a more severe stage is avoided. Screening mammography has been recommended as the most effective method for early detection of breast cancer. Computed aided detection intends to provide assistance to the mammography detection, reducing breast cancer misdiagnosis, and consequently allowing better treatment and prognosis. Several research works have tried to develop computer aided diagnosis tools. They could help radiologists interpret mammograms and could be useful for an accurate diagnosis. The purpose of this study is to introduce a new method based on the combination of neural networks and fuzzy logic in order for better detection and prognosis of breast cancer in mammography images. Results show that the proposed method is better than previous works and can facilitate the doctor to detect breast cancer in early stages of diagnosis process.