近日，清华大学教授戴琼海及其研究小组提出了物理驱动的自监督学习，用于光场显微镜的快速高分辨率鲁棒3D重建。该研究于2025年5月12日发表于国际一流学术期刊《自然—方法学》杂志上。

在这里，课题组人员提出了一个物理驱动的自监督重建网络（SeReNet），用于未扫描LFM和扫描LFM (sLFM)，以毫秒级的处理速度实现近衍射限制的分辨率。SeReNet利用先验四维信息，不仅比现有的深度学习方法实现更好的泛化，特别是在强噪声、光学像差和样本运动等具有挑战性的条件下，而且比迭代层析成像的处理速度提高了700倍。轴向性能可以进一步增强，通过微调作为一个可选的附加与折衷的泛化。

该研究团队通过成像活细胞、斑马鱼胚胎和幼虫、秀丽隐杆线虫和小鼠来证明这些优势。配备了SeReNet， sLFM现在可以连续进行为期一天的高速3D亚细胞成像，具有超过30万卷的大规模细胞间动力学，如免疫反应和神经活动，从而导致广泛的实际生物学应用。

据悉，光场显微镜（LFM）及其变体具有显著先进的活体高速三维成像技术。然而，由于现有重建方法在处理速度、保真度和泛化方面的权衡，它们的实际应用仍然有限。

附：英文原文

Title: Physics-driven self-supervised learning for fast high-resolution robust 3D reconstruction of light-field microscopy

Author: Lu, Zhi, Jin, Manchang, Chen, Shuai, Wang, Xiaoge, Sun, Feihao, Zhang, Qi, Zhao, Zhifeng, Wu, Jiamin, Yang, Jingyu, Dai, Qionghai

Issue&Volume: 2025-05-12

Abstract: Light-field microscopy (LFM) and its variants have significantly advanced intravital high-speed 3D imaging. However, their practical applications remain limited due to trade-offs among processing speed, fidelity, and generalization in existing reconstruction methods. Here we propose a physics-driven self-supervised reconstruction network (SeReNet) for unscanned LFM and scanning LFM (sLFM) to achieve near-diffraction-limited resolution at millisecond-level processing speed. SeReNet leverages 4D information priors to not only achieve better generalization than existing deep-learning methods, especially under challenging conditions such as strong noise, optical aberration, and sample motion, but also improve processing speed by 700 times over iterative tomography. Axial performance can be further enhanced via fine-tuning as an optional add-on with compromised generalization. We demonstrate these advantages by imaging living cells, zebrafish embryos and larvae, Caenorhabditis elegans, and mice. Equipped with SeReNet, sLFM now enables continuous day-long high-speed 3D subcellular imaging with over 300,000 volumes of large-scale intercellular dynamics, such as immune responses and neural activities, leading to widespread practical biological applications.

DOI: 10.1038/s41592-025-02698-z

Source: https://www.nature.com/articles/s41592-025-02698-z