用真实显微图像训练先验，提升低光下荧光显微成像的细节恢复
Improving Richardson--Lucy Deconvolution with Diffusion Priors for Fluorescence Microscopy
- 用扩散模型从真实显微图像学习先验梯度
- 在低光条件下显著减少噪声放大，保留微弱结构
- 适合处理低信噪比的生物样本成像
Richardson--Lucy (RL) 去卷积通过在泊松成像模型下估计最可能产生观测光子计数的荧光信号，来提升荧光显微图像的分辨率。然而，在低光子计数条件下，去卷积问题仍为不适定问题，微弱生物结构易被散粒噪声掩盖，先验对重建结果影响显著。传统 RL 在早期迭代中可恢复结构，但会放大噪声并导致不稳定；而如总变差（TV）等正则化方法虽能抑制伪影，却会造成过度平滑。本文提出一种新框架：利用无条件得分引导的扩散模型在大规模显微图像数据集上学习先验，并将其梯度引入逆问题求解过程。在每一步迭代中，学习到的先验引导 RL 向合理的样品结构收敛，同时保持与观测光子计数的泊松一致性。在多种生物样本和细胞形态上，该方法有效抑制了 RL 的噪声放大，同时在低光条件下更好地保留了微弱结构。
原文摘要 · Abstract (English)
Richardson--Lucy (RL) deconvolution improves fluorescence microscopy images by recovering details lost to diffraction. It estimates the fluorescence signal most likely to have produced the measured photon counts under a Poisson imaging model. However, deconvolution remains ill-posed, especially at low photon counts, when weak biological structures become difficult to distinguish from shot noise and the prior strongly influences the reconstruction. RL recovers structure in early iterations but can amplify noise and become unstable, while regularizers such as total variation (TV) reduce these artifacts at the cost of oversmoothing. Instead, we learn a prior from real fluorescence microscopy images and use its gradient within an inverse-problem framework. The prior is estimated using an unconditional score-based diffusion model trained on a large microscopy dataset. At each step, the learned prior guides RL toward plausible specimen structures, while RL enforces Poisson consistency with the measured counts. Across diverse biological samples and cellular morphologies, the framework reduces RL noise amplification while better preserving weak structures at low photon counts.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。