Cine Cardiac MR Super-resolution using a Fast Diffusion Model with Motion Guided Temporal Consistency Enforcement

Motivation: Cine cardiac MRI (CMR) requires multiple breath-holds to cover the left ventricle. Acquiring images of small matrix size effectively reduces acquisition time but causes a loss of spatial details. Goal(s): To accelerate cine CMR acquisition while maintaining high image quality and temporal consistency based on diffusion model. Approach: A diffusion model with fast inter-frame motion-guided sampling is constructed to achieve super-resolution of cine CMR while suppressing potential inter-frame variations of generated dynamic images. Results: The proposed method outperforms both the state-of-the-art GAN-based super-resolution method, ESRGAN, and the cutting-edge fast diffusion super-resolution model, ResShift for recovering high-frequency details in cine CMR. Impact: The proposed method yielding good-quality cine cardiac MR image series from low-resolution images enables accelerated cine cardiac MR acquisition, and could be potentially applied to achieve high spatial-temporal real-time cardiac MRI.