The purpose of this study was to evaluate the feasibility of spectral mammography using a dual-energy method to non-invasively distinguish between type I (calcium oxalate) and type II (calcium hydroxyapatite) microcalcifications. These two types of microcalcifications are difficult to differentiate owing to their similar linear attenuation coefficients. To improve the detection efficiency regarding microcalcifications, a photon-counting detector with energy discrimination capability was used, and the microcalcifications were classified using the optimal dual-energy spectrum. Two energy bins were used to obtain dual-energy images. In this study, a photon-counting spectral mammography system was simulated using Geant4 Application for Tomographic Emission (GATE) simulation tools. A cadmium zinc telluride detector with a high quantum efficiency was used in this study. The effects of classification on the density and thickness of the breast phantom were investigated. Microcalcifications of various sizes, ranging from 130 to 550 μm, were embedded in the phantom. For statistical analysis, the microcalcifications were classified as calcium hydroxyapatite or calcium oxalate based on a score calculation using the dual-energy images. According to the results, the measured contrast-to-noise ratio (CNR) of the calcium hydroxyapatite was higher than that of calcium oxalate in a single-energy image. The calcium hydroxyapatite had a higher attenuation coefficient and slightly higher contrast compared with calcium oxalate. In addition, the microcalcifications were classified into the optimal energy bin in the dual-energy images. This classification showed better performance with a high energy of 50 kVp and an energy threshold of 30 keV. This study demonstrated that using the dual-energy method could improve classification performance because the microcalcifications are affected by the density and thickness of the breast phantom. These results indicate that the classification accuracy was improved when the difference between the low-energy image and high-energy image was used. The dual-energy method can reduce the frequency of the need for biopsies and discriminate between different types of microcalcifications in mammography. These results can improve the efficiency of early breast cancer diagnosis.