Detection of Microcalcification Clusters in Mammograms Using a Difference of Optimized Gaussian Filters

摘要: Since microcalcification clusters are primary indicators of malignant types breast cancer, its detection is important to prevent and treat the disease. This paper proposes a method for in mammograms using sequential Difference Gaussian filters (DoG). In first stage, fifteen DoG applied sequentially extract potential regions, later, these regions classified following features: absolute contrast, standard deviation gray level moment contour sequence (asymmetry coefficient). Once microcalcifications detected, two approaches clustering compared. one, several detected each mammogram. other, all considered single cluster. We demonstrate that diagnosis based on mammogram more efficient than considering cluster including image.