Deep learning autofluorescence-harmonic microscopy
作者机构：Key Laboratory of Optoelectronic Devices and Systems of Guangdong Province and Ministry of EducationCollege of Physics and Optoelectronic EngineeringShenzhen University518060 ShenzhenChina Shenzhen Meitu.Innovation Technology LTD518060 ShenzhenChina. China-Japan Union Hospital of Jilin University130033 ChangchunChina The Sixth People's Hospital of Shenzhen518052 ShenzhenChina
出 版 物：《Light(Science & Applications)》 (光（科学与应用)（英文版）)
年 卷 期：2022年第11卷第4期
页 面：697-710页
核心收录：
学科分类：0710[理学-生物学] 08[工学] 0803[工学-光学工程] 0812[工学-计算机科学与技术（可授工学、理学学位）]
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 ***,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 *** the framework,we demonstrate label-free large-field multimodal imaging of clinicopathological tissues with enhanced spatial resolution and running time *** 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 *** 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.
维普期刊数据库