Fluo-Fluo translation based on deep learning  

作　　者：Zhengfen Jiang Boyi Li Tho N.H.T.Tran Jiehui Jiang Xin Liu Dean Ta 姜正芬;李博艺;陈诗;蒋皆恢;刘欣;他得安(School of Communication&Information Engineering,Shanghai University,Shanghai 200A44,China;Academy for Engineering&Technology,Fudan University,Shanghai 200433,China;State Key Laboratory of Medical Neurobiology,Fudan University,Shanghai 200433,China;Center for Biomedical Engineering,Fudan University,Shanghai 200433,China)

机构地区：[1]School of Communication&Information Engineering,Shanghai University,Shanghai 200A44,China [2]Academy for Engineering&Technology,Fudan University,Shanghai 200433,China [3]State Key Laboratory of Medical Neurobiology,Fudan University,Shanghai 200433,China [4]Center for Biomedical Engineering,Fudan University,Shanghai 200433,China

出　　处：《Chinese Optics Letters》2022年第3期82-88,共7页中国光学快报（英文版）

基　　金：This work was supported in part by the National Natural Science Foundation of China(Nos.61871263,12034005,and 11827808);the Natural Science Foundation of Shanghai(Nos.21ZR1405200 and 20S31901300).

摘　　要：Fluorescence microscopy technology uses fluorescent dyes to provide highly specific visualization of cell components,which plays an important role in understanding the subcellular structure.However,fluorescence microscopy has some limitations such as the risk of non-specific cross labeling in multi-labeled fluorescent staining and limited number of fluo-rescence labels due to spectral overlap.This paper proposes a deep learning-based fluorescence to fluorescence[Flu0-Fluo]translation method,which uses a conditional generative adversarial network to predict a fluorescence image from another fluorescence image and further realizes the multi-label fluorescent staining.The cell types used include human motor neurons,human breast cancer cells,rat cortical neurons,and rat cardiomyocytes.The effectiveness of the method is verified by successfully generating virtual fluorescence images highly similar to the true fluorescence images.This study shows that a deep neural network can implement Fluo-Fluo translation and describe the localization relationship between subcellular structures labeled with different fluorescent markers.The proposed Fluo-Fluo method can avoid non-specific cross labeling in multi-label fluorescence staining and is free from spectral overlaps.In theory,an unlimited number of fluorescence images can be predicted from a single fluorescence image to characterize cells.

关 键 词：deep learning conditional generative adversarial network fluorescence image image translation 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程] R318[医药卫生—生物医学工程]