4.7 Article

Deep learning-based single-shot structured illumination microscopy

期刊

OPTICS AND LASERS IN ENGINEERING
卷 155, 期 -, 页码 -

出版社

ELSEVIER SCI LTD
DOI: 10.1016/j.optlaseng.2022.107066

关键词

Structured illumination microscopy; Super-resolution; Deep learning

类别

资金

  1. National Natural Science Foundation of China (NSFC) [62075140, 61805086, 61727814, 61875059, 62175041]
  2. Science, Technology and Innovation Commission of Shen-zhen Municipality [20201026165007001]
  3. Guangdong Basic and Applied Basic Research Foundation [2021A1515110664]
  4. Start-Up Fund-ing of Guangdong Polytechnic Normal University [2022SDKYA008]

向作者/读者索取更多资源

This research presents a deep learning-based method for structured illumination microscopy (SIM) that can reconstruct super-resolution (SR) images using only one frame of structured illumination image. Generative adversative networks (GANs) and deformation of U-Net (DU-Net) are utilized for the task. Experimental and simulation results demonstrate the ability to reconstruct SR images from a single frame of structured illumination image, significantly reducing phototoxicity and photobleaching.
We report a deep learning-based structured illumination microscopy (SIM) method, which can reconstruct a super-resolution (SR) image using only one frame structured illumination image. Generative adversative networks (GANs) and deformation of U-Net (DU-Net) are employed to perform the task. GANs are trained to generate other structured illumination images by feeding a single structured illumination image, and DU-Net is trained to reconstruct the super-resolution image. The results of experiments and simulations demonstrate that the SR image could be reconstructed from one frame structured illumination image. Importantly, it can greatly reduce phototoxicity and photobleaching.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据