Mammography is acknowledged as the single most effective method of screening for breast cancer. We have used statistical feature extraction method by using a sliding window analysis, for detecting circumscribed masses in mammograms. This procedure is implemented by taking into account the multi-scale statistical properties of the breast tissue, and succeeds in finding the exact tumor position by performing the mammograph analysis using first few moments of each window. We have demonstrated that fast implementation in both feature extraction and the neural classification module can be achieved. The MIAS database, was used for the evaluation of the proposed circumscribed mass, giving reliable detection accuracy in both position and mass size.