Contrast-enhanced Cardiac MRI Generation Using Contrast-free Cardiac Cine MRI

Motivation: Generating late gadolinium enhancement (LGE) images from contrast-free cardiac magnetic resonance (CMR) images is crucial for patients with severe renal failure or contrast agent allergies. Goal(s): This study aims to develop a method that can generate LGE images from cine images based on diffusion models. Approach: We introduced a novel multi-task diffusion model that generates LGE images from contrast-free cine images and evaluate the probability of enhancement presence in LGE images based on cine images. Results: In external validation, Cine2LGE generates LGE images with good consistency compared to actual LGE images, exhibiting fewer artifacts and improved contrast. Impact: We demonstrate the potential of diffusion models in generating LGE using contrast-free cine images. The proposed method is expected to provide a valuable alternative for patients who cannot obtain LGE images due to contraindications.