Motivation: While breast MRI is the most sensitive imaging tool for breast cancer detection, concerns about gadolinium retention and access issues limits its use. Goal(s): Our goal was to investigate the deep learning method to generate synthetic post-contrast breast MRI from non-contrast images for breast cancer detection Approach: Using an Extra-Dimensional U-NET with visual geometry group, we simulated T1-weighted post-contrast images from pre-contrast T1 weighted and diffusion weighted images. Results: Combined synthetic post-contrast and non-contrast MRI significantly enhanced breast cancer detection compared to each modality alone. Impact: With increased demand for non-contrast breast MRI due to gadolinium concerns, synthetic post-contrast MRI offers a promising alternative, enhancing breast cancer detection and making MRI more accessible.
Ha et al. (Tue,) studied this question.