Artificial intelligence for microscopy: what you should know

被引:69
作者
von Chamier, Lucas [1 ]
Laine, Romain F. [1 ,2 ,3 ]
Henriques, Ricardo [1 ,2 ,3 ,4 ]
机构
[1] UCL, MRC, Lab Mol Cell Biol, London, England
[2] UCL, Dept Cell & Dev Biol, London, England
[3] Francis Crick Inst, London, England
[4] UCL, Inst Phys Living Syst, London, England
基金
英国生物技术与生命科学研究理事会; 英国惠康基金; 英国医学研究理事会;
关键词
DEEP; CLASSIFICATION; LOCALIZATION; INFORMATION; IMAGES;
D O I
10.1042/BST20180391
中图分类号
Q5 [生物化学]; Q7 [分子生物学];
学科分类号
071010 ; 081704 ;
摘要
Artificial Intelligence based on Deep Learning (DL) is opening new horizons in biomedical research and promises to revolutionize the microscopy field. It is now transitioning from the hands of experts in computer sciences to biomedical researchers. Here, we introduce recent developments in DL applied to microscopy, in a manner accessible to non-experts. We give an overview of its concepts, capabilities and limitations, presenting applications in image segmentation, classification and restoration. We discuss how DL shows an outstanding potential to push the limits of microscopy, enhancing resolution, signal and information content in acquired data. Its pitfalls are discussed, along with the future directions expected in this field.
引用
收藏
页码:1029 / 1040
页数:12
相关论文
共 92 条
[1]   Automating multimodal microscopy with NanoJ-Fluidics [J].
Almada, Pedro ;
Pereira, Pedro M. ;
Cuiley, Sian ;
Caillol, Ghislaine ;
Boroni-Rueda, Fanny ;
Dix, Christina L. ;
Charras, Guillaume ;
Baum, Buzz ;
Laine, Romain F. ;
Leterrier, Christophe ;
Henriques, Ricardo .
NATURE COMMUNICATIONS, 2019, 10 (1)
[2]   Deep learning for computational biology [J].
Angermueller, Christof ;
Parnamaa, Tanel ;
Parts, Leopold ;
Stegle, Oliver .
MOLECULAR SYSTEMS BIOLOGY, 2016, 12 (07)
[3]  
[Anonymous], 2016, ARXIV PREPRINT ARXIV
[4]  
[Anonymous], 1974, Ph.D. Thesis
[5]  
[Anonymous], 2015, Nature, DOI [10.1038/nature14539, DOI 10.1038/NATURE14539]
[6]  
[Anonymous], 2019, ARXIV190111365
[7]  
[Anonymous], LEARNING LOGIC TR 47
[8]  
[Anonymous], 2015, PROC CVPR IEEE
[9]  
[Anonymous], ADV NEURAL INFORM PR
[10]  
[Anonymous], 2018, ARXIV180303453