Real-time denoising enables high-sensitivity fluorescence time-lapse imaging beyond the shot-noise limit

作     者：Li, Xinyang Li, Yixin Zhou, Yiliang Wu, Jiamin Zhao, Zhifeng Fan, Jiaqi Deng, Fei Wu, Zhaofa Xiao, Guihua He, Jing Zhang, Yuanlong Zhang, Guoxun Hu, Xiaowan Chen, Xingye Zhang, Yi Qiao, Hui Xie, Hao Li, Yulong Wang, Haoqian Fang, Lu Dai, Qionghai 

作者机构：Tsinghua Univ Dept Automat Beijing Peoples R China Tsinghua Univ Tsinghua Shenzhen Int Grad Sch Shenzhen Peoples R China Tsinghua Univ Inst Brain & Cognit Sci Beijing Peoples R China Hangzhou Zhuoxi Inst Brain & Intelligence Hangzhou Peoples R China Fudan Univ Sch Informat & Technol Shanghai Peoples R China Tsinghua Univ Beijing Key Lab Multidimens & Multiscale Computat Beijing Peoples R China Tsinghua Univ IDG McGovern Inst Brain Res Beijing Peoples R China Tsinghua Univ Dept Elect Engn Beijing Peoples R China Peking Univ Sch Life Sci State Key Lab Membrane Biol Beijing Peoples R China PKU IDG McGovern Inst Brain Res Beijing Peoples R China 

出 版 物：《NATURE BIOTECHNOLOGY》 (自然生物技术)

年 卷 期：2023年第41卷第2期

页      面：282-+页

核心收录：

学科分类：0710[理学-生物学] 071010[理学-生物化学与分子生物学] 07[理学] 0836[工学-生物工程] 

基　　金：National Natural Science Foundation of China [62088102, 62071272, 61831014, 62125106] National Key Research and Development Program of China [2020AA0105500] Shenzhen Science and Technology Project [CJGJZD20200617102601004, ZDYBH201900000002] Beijing Laboratory of Brain and Cognitive Intelligence, Beijing Municipal Education Commission Beijing Key Laboratory of Multi-dimension & Multi-scale Computational Photography 

主　　题：Fluorescence imaging Image processing Microscopy Software 

摘      要：DeepCAD-RT denoises fluorescence time-lapse images in real time. A fundamental challenge in fluorescence microscopy is the photon shot noise arising from the inevitable stochasticity of photon detection. Noise increases measurement uncertainty and limits imaging resolution, speed and sensitivity. To achieve high-sensitivity fluorescence imaging beyond the shot-noise limit, we present DeepCAD-RT, a self-supervised deep learning method for real-time noise suppression. Based on our previous framework DeepCAD, we reduced the number of network parameters by 94%, memory consumption by 27-fold and processing time by a factor of 20, allowing real-time processing on a two-photon microscope. A high imaging signal-to-noise ratio can be acquired with tenfold fewer photons than in standard imaging approaches. We demonstrate the utility of DeepCAD-RT in a series of photon-limited experiments, including in vivo calcium imaging of mice, zebrafish larva and fruit flies, recording of three-dimensional (3D) migration of neutrophils after acute brain injury and imaging of 3D dynamics of cortical ATP release. DeepCAD-RT will facilitate the morphological and functional interrogation of biological dynamics with a minimal photon budget.