Current deep learning reconstruction for accelerated cardiac cine MRI suffers from spatial and temporal blurring. We aim to improve image sharpness and motion delineation for cine MRI under high undersampling rates. A spatiotemporal diffusion enhancement model conditional on an existing deep learning reconstruction along with a novel paired sampling strategy was developed. The diffusion model provided sharper tissue boundaries and clearer motion than the original reconstruction in experts evaluation on clinical data. The innovative paired sampling strategy substantially reduced artificial noises in the generative results.

翻译：当前深度学习加速心脏电影磁共振成像重建存在时空模糊问题。本研究旨在提高高欠采样率下电影MRI的图像锐度与运动描绘能力。本文开发了一种时空扩散增强模型，以现有深度学习重建结果为条件，并配合新型配对采样策略。临床数据专家评估表明，该扩散模型较原始重建方法能提供更锐利的组织边界与更清晰的运动影像。创新性配对采样策略显著降低了生成结果中的人工噪声。