打破连续性：面向结构性MRI重建的离散分布学习
Breaking the Continuum: Discrete Distribution Learning for Structural MRI Reconstruction
将MRI解剖结构的空间先验建模为潜空间中的离散分布，并用离散先验网络一次生成多个候选、再以双域评分和微扩散循环精修，为医学图像重建提供了可复用的“离散结构推理+连续细化”范式。
原文依据 DiCoS models an anatomy-aware discrete distribution and generates diverse reconstructions in one coarse-to-fine pass
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论MRI中的解剖结构具有强烈的空间先验，包括清晰的边界、较低的受试者间变异性和一致的拓扑结构。这些特性自然地在潜变量空间中诱导出聚类模式，而假设平滑流形分布的传统连续生成先验难以捕捉这种模式。为解决这一局限，我们提出DiCoS（离散-连续合成），一种将离散结构推理与连续细化相结合的生成式重建框架。DiCoS建模解剖感知的离散分布，并通过离散先验网络（DPN）在一次由粗到细的生成过程中产生多样化的重建结果。双域平衡评分（DBS）机制利用图像域保真度和k空间一致性自适应地评估候选结果。为进一步提升真实感，微扩散循环（MDC）执行高效的分数引导细化，在不破坏全局拓扑的情况下增强纹理真实感。在fastMRI膝关节和脑部数据集上的实验表明，DiCoS实现了最优的重建质量，具有更清晰的边界和更好的解剖一致性。除像素指标外，基于分割的评估进一步证实了更优的结构重叠和语义对齐，突显了DiCoS在解剖感知重建方面的优势。项目页面见 https://kincin.github.io/DiCoS/。
英文原文摘要 1428 字符
Anatomical structures in MRI exhibit strong spatial priors, including well-defined boundaries, low inter-subject variability, and consistent topology. These properties naturally induce clustered patterns in the latent space, which are difficult to capture using conventional continuous generative priors that assume smooth manifold distributions. To address this limitation, we propose DiCoS (Discrete-Continuous Synthesis), a generative reconstruction framework that integrates discrete structural reasoning with continuous refinement. DiCoS models an anatomy-aware discrete distribution and generates diverse reconstructions in one coarse-to-fine pass through a Discrete Prior Network (DPN). A Dual-domain Balanced Scoring (DBS) mechanism adaptively evaluates candidates using both image-domain fidelity and k-space consistency. To further enhance realism, Micro Diffusion Cycles (MDC) perform efficient score-guided refinement to enhance texture realism without disturbing global topology. Experiments on the fastMRI knee and brain datasets demonstrate that DiCoS achieves state-of-the-art reconstruction quality with sharper boundaries and improved anatomical consistency. Beyond pixel metrics, segmentation-based evaluations further confirm superior structural overlap and semantic alignment, highlighting DiCoS's advantages in anatomy-aware reconstruction. The project page is available at https://kincin.github.io/DiCoS/.