Surpassing the resolution limitation of structured illumination microscopy by an untrained neural network

Yu He; Yunhua Yao; Yilin He; Zhengqi Huang; Fan Luo; Chonglei Zhang; Dalong Qi; Tianqing Jia; Zhiyong Wang; Zhenrong Sun; Xiaocong Yuan; Shian Zhang

doi:10.1364/BOE.479621

Surpassing the resolution limitation of structured illumination microscopy by an untrained neural network

Biomed Opt Express. 2022 Dec 12;14(1):106-117. doi: 10.1364/BOE.479621. eCollection 2023 Jan 1.

Authors

Yu He^{1

2}, Yunhua Yao^{1

2}, Yilin He¹, Zhengqi Huang¹, Fan Luo³, Chonglei Zhang³, Dalong Qi¹, Tianqing Jia¹, Zhiyong Wang⁴, Zhenrong Sun¹, Xiaocong Yuan^{3

5}, Shian Zhang^{1

6

7}

Affiliations

¹ State Key Laboratory of Precision Spectroscopy, School of Physics and Electronic Science, East China Normal University, Shanghai 200062, China.
² Contributed equally.
³ Nanophotonics Research Center, Shenzhen Key Laboratory of Micro-Scale Optical Information Technology, Institute of Microscale Optoelectronics, Shenzhen University, Shenzhen 518060, China.
⁴ School of Mathematical Sciences, University of Electronic Science and Technology of China, Chengdu 611731, China.
⁵ xcyuan@szu.edu.cn.
⁶ Collaborative Innovation Center of Extreme Optics, Shanxi University, Taiyuan 030006, China.
⁷ Collaborative Innovation Center of Light Manipulations and Applications, Shandong Normal University, Jinan 250358, China.

Abstract

Structured illumination microscopy (SIM), as a flexible tool, has been widely applied to observing subcellular dynamics in live cells. It is noted, however, that SIM still encounters a problem with theoretical resolution limitation being only twice over wide-field microscopy, where imaging of finer biological structures and dynamics are significantly constrained. To surpass the resolution limitation of SIM, we developed an image postprocessing method to further improve the lateral resolution of SIM by an untrained neural network, i.e., deep resolution-enhanced SIM (DRE-SIM). DRE-SIM can further extend the spatial frequency components of SIM by employing the implicit priors based on the neural network without training datasets. The further super-resolution capability of DRE-SIM is verified by theoretical simulations as well as experimental measurements. Our experimental results show that DRE-SIM can achieve the resolution enhancement by a factor of about 1.4 compared with conventional SIM. Given the advantages of improving the lateral resolution while keeping the imaging speed, DRE-SIM will have a wide range of applications in biomedical imaging, especially when high-speed imaging mechanisms are integrated into the conventional SIM system.