Rationalized deep learning super-resolution microscopy for sustained live imaging of rapid subcellular processes
Chang Qiao, Di Li, Yong Liu, Siwei Zhang, Kan Liu, Chong Liu, Yuting Guo, Tao Jiang, Chuyu Fang, Nan Li, Yunmin Zeng, Kangmin He, Xueliang Zhu, Jennifer Lippincott-Schwartz, Qionghai Dai & Dong Li
Abstract
The goal when imaging bioprocesses with optical microscopy is to acquire the most spatiotemporal information with the least invasiveness. Deep neural networks have substantially improved optical microscopy, including image super-resolution and restoration, but still have substantial potential for artifacts. In this study, we developed rationalized deep learning (rDL) for structured illumination microscopy and lattice light sheet microscopy (LLSM) by incorporating prior knowledge of illumination patterns and, thereby, rationally guiding the network to denoise raw images. Here we demonstrate that rDL structured illumination microscopy eliminates spectral bias-induced resolution degradation and reduces model uncertainty by five-fold, improving the super-resolution information by more than ten-fold over other computational approaches. Moreover, rDL applied to LLSM enables self-supervised training by using the spatial or temporal continuity of noisy data itself, yielding results similar to those of supervised methods. We demonstrate the utility of rDL by imaging the rapid kinetics of motile cilia, nucleolar protein condensation during light-sensitive mitosis and long-term interactions between membranous and membrane-less organelles.
附件下载：
Rationalized deep learning super-resolution microscopy for sustained live imaging of rapid subcellular processes, Nat Biotechnol, 6 Oct 2022
Nature Biotechnology, 6 October, 2022, DOI：https://doi.org/10.1038/s41587-022-01471-3
Rationalized deep learning super-resolution microscopy for sustained live imaging of rapid subcellular processes
Chang Qiao, Di Li, Yong Liu, Siwei Zhang, Kan Liu, Chong Liu, Yuting Guo, Tao Jiang, Chuyu Fang, Nan Li, Yunmin Zeng, Kangmin He, Xueliang Zhu, Jennifer Lippincott-Schwartz, Qionghai Dai & Dong Li
Abstract
The goal when imaging bioprocesses with optical microscopy is to acquire the most spatiotemporal information with the least invasiveness. Deep neural networks have substantially improved optical microscopy, including image super-resolution and restoration, but still have substantial potential for artifacts. In this study, we developed rationalized deep learning (rDL) for structured illumination microscopy and lattice light sheet microscopy (LLSM) by incorporating prior knowledge of illumination patterns and, thereby, rationally guiding the network to denoise raw images. Here we demonstrate that rDL structured illumination microscopy eliminates spectral bias-induced resolution degradation and reduces model uncertainty by five-fold, improving the super-resolution information by more than ten-fold over other computational approaches. Moreover, rDL applied to LLSM enables self-supervised training by using the spatial or temporal continuity of noisy data itself, yielding results similar to those of supervised methods. We demonstrate the utility of rDL by imaging the rapid kinetics of motile cilia, nucleolar protein condensation during light-sensitive mitosis and long-term interactions between membranous and membrane-less organelles.
文章链接：https://www.nature.com/articles/s41587-022-01471-3
相关报道：/kyjz/zxdt/202210/t20221008_6520367.html