.png){kind=icon}
Return
Deep learning-based single-shot structured illumination microscopy
.png){kind=icon}
PRE
AI
DOI：10.1016/j.optlaseng.2022.107066.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
Structured illumination microscopy
Super-resolution
Deep learning
Journal
IF:
3.7
Papers:
7.3K
Citations:
1.7W
Organization
View more organizations
Cited Papers
ShareSaveSub-diffraction-limit imaging by stochastic optical reconstruction microscopy (STORM).png)
NATURE METHODS
OAAI
NATURE METHODSIF32.1
OAAIShareSaveDeep learning massively accelerates super-resolution localization microscopyNATURE BIOTECHNOLOGYOAAI
NATURE BIOTECHNOLOGYIF41.7
OAAIShareSaveShareSave View more