Synthesis of Contrast-Enhanced Spectral Mammograms from Low-Energy Mammograms Using cGAN-Based Synthesis Network

Contrast-enhanced spectral mammography (CESM) is a valuable tool in the diagnosis and staging of primary breast cancer, for which it has an extremely high predictive value. However, the iodinated contrast media injected during CESM examination can cause adverse reactions, such as allergic reactions, and even cause contra-induced nephropathy. Therefore, iodinated contrast media cannot be used for some patients. To address this problem, we developed a cGAN-based Synthesis Network (cGSNT) that uses mammogram images to synthesize corresponding CESM images. Key points of this study are that cGSNT utilizes the cycle-consistent approach to reduce information loss when converting from high to low tissue contrast images, and the introduction of concatenation layers for dual-view information fusion. The experimental results on paired images of low-energy CESM (mammogram) and recombined CESM demonstrated that the synthetic image was very similar to the real CESM image, and the proposed cGSNT qualitatively and quantitatively outperforms typical non-learning and other popular deep learning methods.

Automated summary

CESM is a valuable tool in diagnosing and staging primary breast cancer, but the use of iodinated contrast media may lead to adverse reactions. To address this issue, a cGAN-based Synthesis Network was developed to synthesize CESM images using mammogram images. The introduction of cycle-consistent approach and concatenation layers in cGSNT yielded promising results in image synthesis.