[Detection of microcalcifications in digital mammograms based on dual-threshold]

Breast cancer is one of the main cancers leading to women mortality in the world. Since the causes are still obscure, the microcalcification clusters are the primary indicators of breast cancer, and the detection is of importance to the prevention and treatment of the disease. Microcalcifications appear in the small clusters of a few pixels and as spots which are slightly brighter than their backgrounds. It becomes a challenge to detect all the microcalcifications. This paper presents an approach for detecting microcalcifications in digital mammograms employing a dual-threshold method developed from LoG edge detection. Two thresholds are proposed in our method based on two additional criterions. Experimental results show that the proposed method can locate the microcalcifications exactly in mammogram as well as restrain the contours produced by the noises.