Deep MRI reconstruction is commonly performed with conditional models that de-alias undersampled acquisitions to recover images consistent with fully-sampled data. Since conditional models are trained with knowledge of the imaging operator, they can show poor generalization across variable operators. Unconditional models instead learn generative image priors decoupled from the imaging operator to improve reliability against domain shifts. Recent diffusion models are particularly promising given their high sample fidelity. Nevertheless, inference with a static image prior can perform suboptimally. Here we propose the first adaptive diffusion prior for MRI reconstruction, AdaDiff, to improve performance and reliability against domain shifts. AdaDiff leverages an efficient diffusion prior trained via adversarial mapping over large reverse diffusion steps. A two-phase reconstruction is executed following training: a rapid-diffusion phase that produces an initial reconstruction with the trained prior, and an adaptation phase that further refines the result by updating the prior to minimize reconstruction loss on acquired data. Demonstrations on multi-contrast brain MRI clearly indicate that AdaDiff outperforms competing conditional and unconditional methods under domain shifts, and achieves superior or on par within-domain performance.

翻译：深度磁共振重建通常采用条件模型进行,这些模型通常不以充分抽样数据为基准,为恢复图像而减少标本;由于对成像操作员进行知识培训,对成像操作员来说,有条件模型可以显示不同操作员的通用性差;不附带条件的模型可以学习与成像操作员分离的基因化图像前科,以提高对域变换的可靠性;鉴于最近的扩散模型具有较高的样本忠诚性,因此特别有希望;然而,先使用静态图像进行推导,可以产生亚光极性效果;在这里,我们提议在进行MRI重建之前首先进行适应性扩散,AdaDiff,以提高对域变换的性能和可靠性;AdaDiff利用以前通过对大反向扩散步骤进行对抗性绘图培训后的有效传播;在培训之后进行两个阶段的重建:一个快速扩散阶段,通过经过训练的先前的模拟进行初步重建,以及一个适应阶段,通过更新前期的结果,以尽量减少已获得数据的重建损失,从而进一步完善结果;关于多调式大脑MRI的演示清楚地表明AdaDiff在域变换的有条件和无条件方法之间相互竞争,并实现高级或内部业绩。