结合物理与深度生成先验求解标记 MRI 的非线性盲逆问题
Solving a Nonlinear Blind Inverse Problem for Tagged MRI with Physics and Deep Generative Priors
把 MR 成像物理前向模型与深度生成先验结合，在未知成像参数下盲估计高分辨率解剖图像并同时做 3D 微分同胚 Lagrangian 运动跟踪，这套「物理+生成先验」的盲非线性逆问题框架可迁移到其他带编码伪影的医学/科学成像复原与配准任务。
原文依据 the synergy of MR physics and generative priors enables us to blindly estimate the unknown forward imaging models
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论标记 MRI 能够以非侵入方式跟踪内部组织运动。它通过周期性标记对解剖结构进行调制来编码运动，这些标记会随组织一同形变。然而，解剖结构、标记与运动之间的纠缠给后处理带来了显著挑战。标记的存在与成像模糊会阻碍解剖结构分割等下游任务。由 T1 弛豫引起的标记衰减破坏了运动跟踪所依赖的亮度恒常性假设。数十年来，这些挑战一直被孤立地、次优地处理。与之不同，我们为标记 MRI 引入了一个盲非线性逆问题框架，首次统一了以下任务：解剖图像恢复、高分辨率 cine 图像合成以及运动估计。其核心在于 MR 物理与生成先验的协同作用，使我们能够盲估计未知的前向成像模型与高分辨率底层解剖结构，同时随时间跟踪三维微分同胚 Lagrangian 运动。在标记脑部 MRI 上的实验表明，我们的方法能够生成高分辨率解剖图像、cine 图像，并获得比专用方法更准确的运动。
英文原文摘要 1146 字符
Tagged MRI enables tracking internal tissue motion non-invasively. It encodes motion by modulating anatomy with periodic tags, which deforms along with tissue. However, the entanglement between anatomy, tags and motion poses significant challenges on post processing. Existence of tags and imaging blur hinders downstream tasks such as segmenting anatomy. Tag fading, due to T1-relaxation, disrupts brightness constancy assumption for motion tracking. For decades, these challenges are handled in isolation and sub-optimally. In contrast, we introduce a blind and nonlinear inverse framework for tagged MRI that, for the first time, unifies these tasks: anatomical image recovery, high-resolution cine image synthesis, and motion estimation. At its core, the synergy of MR physics and generative priors enables us to blindly estimate the unknown forward imaging models, high-resolution underlying anatomy, while simultaneously tracking 3D diffeomorphic Lagrangian motion over time. Experiments on tagged brain MRI demonstrate that our approach yields high-resolution anatomy images, cine images, and more accurate motion than specialized methods.