Background and Objective: A mammogram is commonly used to detect breast cancer and details of glandular tissue. A mammography can represent the mass and localization of a lesion. But mammography cannot define the type of observed lesion. For accurate diagnosis, a biopsy is needed to confirm the initial examination. The variety of tissues (both lesion and normal tissue) represent as different image data in mammography. It may be possible to separate different tissues by using image data.The aim of this study was to determine the difference of statistical data in differing breast tissues as observed in mammography.
Methods: Eighty-nine mammography images with lesions of different types (mass or microcalcification) were obtained and studied from an online database: The Mini-MIAS International Congress Series 1069. The statistical data (skewness, kurtosis, standard deviation, integrated density, mean, and median) were measured. The mean difference of image data was analyzed by one-way ANOVA or Kruskal-Wallis tests for normal or non-normal distribution data, respectively.
Results: Results show that the integrated density and the kurtosis could separate the mass from microcalcifications. The mean could separate normal tissue from the lesions as well. Sensitivity of mass and microcalcifications were 87.5% and 88.89%, respectively. Specificity of normal tissue was 100%.
Conclusion: The difference of the image data could help to diagnosis different breast lesions.
