cryoSENSE：压缩感知借助蛋白质冷冻电镜图像流形上的稀疏先验与生成先验实现高通量显微成像
cryoSENSE: Compressive Sensing Enables High-throughput Microscopy with Sparse and Generative Priors on the Protein Cryo-EM Image Manifold
把去噪扩散模型当作图像流形上的生成先验，用于从欠采样测量中重建图像；这种「稀疏先验 + 扩散生成先验」的混合重建思路可以直接迁移到其他欠采样成像任务（如快速 MRI、低剂量 CT、压缩超分辨），并且论文给出了在像素域与傅里叶域欠采样下两种先验各自的适用边界。
原文依据 cryo-EM images of proteins lie on low-dimensional manifolds that can be independently represented using sparse priors in predefined bases and generative priors captured by a denoising diffusion model
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论冷冻电子显微镜（cryo-EM）能够实现生物分子的原子级分辨率可视化；然而，现代直接探测器产生的数据量远超可用的存储与传输带宽，从而限制了实际吞吐量。我们提出 cryoSENSE，这是面向压缩冷冻电镜感知与采集的软硬件协同设计框架的计算实现。我们表明，蛋白质的冷冻电镜图像位于低维流形上，这些流形可以分别用预定义基下的稀疏先验以及由去噪扩散模型捕获的生成先验来独立表示。cryoSENSE 利用这些低维流形，从空间域与傅里叶域的欠采样测量中实现忠实的图像重建，同时保持下游的结构分辨率。在实验中，cryoSENSE 将采集吞吐量提升至多 2.5 倍，同时保持原有的三维分辨率，并在掩码测量数量与降采样程度之间提供可控的权衡。稀疏先验有利于从傅里叶域测量和中等压缩程度下实现忠实重建，而生成式扩散先验则能从像素域测量和更严重的欠采样中实现准确恢复。
英文原文摘要 1267 字符
Cryo-electron microscopy (cryo-EM) enables the atomic-resolution visualization of biomolecules; however, modern direct detectors generate data volumes that far exceed the available storage and transfer bandwidth, thereby constraining practical throughput. We introduce cryoSENSE, the computational realization of a hardware-software co-designed framework for compressive cryo-EM sensing and acquisition. We show that cryo-EM images of proteins lie on low-dimensional manifolds that can be independently represented using sparse priors in predefined bases and generative priors captured by a denoising diffusion model. cryoSENSE leverages these low-dimensional manifolds to enable faithful image reconstruction from spatial and Fourier-domain undersampled measurements while preserving downstream structural resolution. In experiments, cryoSENSE increases acquisition throughput by up to 2.5xwhile retaining the original 3D resolution, offering controllable trade-offs between the number of masked measurements and the level of downsampling. Sparse priors favor faithful reconstruction from Fourier-domain measurements and moderate compression, whereas generative diffusion priors achieve accurate recovery from pixel-domain measurements and more severe undersampling.