Field-dependent deep learning enables high-throughput whole-cell 3D super-resolution imaging.
Shuang FuWei ShiTingdan LuoYingchuan HeLulu ZhouJie YangZhichao YangJiadong LiuXiaotian LiuZhiyong GuoChengyu YangChao LiuZhen-Li HuangJonas RiesMingjie ZhangPeng XiDayong JinYiming LiPublished in: Nature methods (2023)
Single-molecule localization microscopy in a typical wide-field setup has been widely used for investigating subcellular structures with super resolution; however, field-dependent aberrations restrict the field of view (FOV) to only tens of micrometers. Here, we present a deep-learning method for precise localization of spatially variant point emitters (FD-DeepLoc) over a large FOV covering the full chip of a modern sCMOS camera. Using a graphic processing unit-based vectorial point spread function (PSF) fitter, we can fast and accurately model the spatially variant PSF of a high numerical aperture objective in the entire FOV. Combined with deformable mirror-based optimal PSF engineering, we demonstrate high-accuracy three-dimensional single-molecule localization microscopy over a volume of ~180 × 180 × 5 μm 3 , allowing us to image mitochondria and nuclear pore complexes in entire cells in a single imaging cycle without hardware scanning; a 100-fold increase in throughput compared to the state of the art.
Keyphrases
- single molecule
- deep learning
- high resolution
- high throughput
- atomic force microscopy
- living cells
- convolutional neural network
- single cell
- induced apoptosis
- artificial intelligence
- high speed
- cell death
- machine learning
- cell cycle arrest
- oxidative stress
- circulating tumor cells
- bone marrow
- stem cells
- dna methylation
- endoplasmic reticulum stress
- mass spectrometry
- fluorescence imaging
- cell proliferation
- low cost
- electron microscopy