Microcalcification detection is an important part of early breast cancer detection. In this paper, we propose a microcalcification detection method in mammography CAD (computer-aided diagnosis) system. The proposed microcalcification detection includes two parts. One is adaptive mammogram enhancement algorithm using homomorphic filtering in wavelet. The filter parameters are determined by background characteristics. The other is multi-stage microcalcification detection method. To verify our algorithm, we performed experiments and measured free-response operation characteristics (FROC) curve. The results show that the proposed microcalcification detection method is more robust for fluctuating noisy environments.