Adversarial Diffusion Probabilistic Models for Unpaired MRI Contrast Translation

Synthesis of missing contrasts in an MRI protocol via translation from acquired contrasts can reduce costs associated with prolonged exams. Current learning-based translation methods are predominantly based on generative adversarial networks (GAN) that implicitly characterize the distribution of the target contrast, with limits fidelity of synthesized images. Here we present SynDiff, a novel conditional adversarial diffusion model for computationally efficient, high-fidelity contrast translation. SynDiff enables training on unpaired datasets, thanks to its cycle-consistent architecture with coupled diffusion processes. Demonstrations on multi-contrast MRI datasets indicate the superiority of SynDiff against competing GAN and diffusion models.