Deep learning autofluorescence-harmonic microscopy  

作　　者：Binglin Shen Shaowen Liu Yanping Li Ying Pan Yuan Lu Rui Hu Junle Qu Liwei Liu 

机构地区：[1]Key Laboratory of Optoelectronic Devices and Systems of Guangdong Province and Ministry of Education,College of Physics and Optoelectronic Engineering,Shenzhen University,518060 Shenzhen,China [2]Shenzhen Meitu.Innovation Technology LTD,518060 Shenzhen,China. [3]China-Japan Union Hospital of Jilin University,130033 Changchun,China [4]The Sixth People's Hospital of Shenzhen,518052 Shenzhen,China

出　　处：《Light(Science & Applications)》2022年第4期697-710,共14页光（科学与应用)（英文版）

基　　金：the National Natural Science Foundation of China(61935012/62175163/61961136005/61835009/62127819);Shenzhen Key Projeas(JCYJ20200109105404067);Shenzhen International Cooperation Project(GJHZ20190822095420249)for financial support。

摘　　要：Laser scanning microscopy has inherent tradeoffs between imaging speed,field of view(FOV),and spatial resolution due to the limitations of sophisticated mechanical and optical setups,and deep learning networks have emerged to overcome these limitations without changing the system.Here,we demonstrate deep learning autofluorescence-harmonic microscopy(DLAM)based on self-alignment attention-guided residual-in-residual dense generative adversarial networks to close the gap between speed,FOV;and quality.Using the framework,we demonstrate label-free large-field multimodal imaging of clinicopathological tissues with enhanced spatial resolution and running time advantages.Statistical quality assessments show that the attention-guided residual dense conneaions minimize the persistent noise,distortions,and scanning fringes that degrade the autofluorescence-harmonic images and avoid reconstruction artifaas in the output images.With the advantages of high contrast,high fidelity,and high speed in image reconstruction,DLAM can act as a powerful tool for the noninvasive evaluation of diseases,neural activity,and embryogenesis.

关 键 词：NETWORKS DEEP HARMONIC 

分 类 号：TH742[机械工程—光学工程]