Localizing Axial Dense Emitters Based on Single-Helix Point Spread Function and Deep Learning
Open Access
- 8 October 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Photonics Journal
- Vol. 16 (6) , 1-6
Abstract
The point-by point 3D scanning strategy adopted in Stimulated Emission Depletion Microscopy (STED) is time-consuming. The 3D scanning can be replaced with a 2D scanning in the non-diffracting Bessel-Bessel STED (BB-STED). In order to extract the excited emitters' axial information in BB-STED, we propose to encode axial information by using a detection optical path with single-helix PSF, and then predict the depths of the emitters with deep learning. Simulation demonstrated that, for dense emitters in a depth range of 4 μm, an axial precision of ∼35 nm can be achieved. Our method also works for experimental data, and an axial precision of ∼63 nm can be achieved.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62475168, 11774242, 62175166, 61335001)
- National Key Research and Development Program of China (2022YFF0712500)
- Shenzhen Science and Technology Planning (JCYJ20210324094200001, JCYJ20200109105411133)
- Shenzhen Key Laboratory of Photonics and Biophotonics (ZDSYS20210623092006020)
This publication has 19 references indexed in Scilit:
- DeepSTORM3D: dense 3D localization microscopy and PSF design by deep learningNature Methods, 2020
- Deep learning enables structured illumination microscopy with low light levels and enhanced speedNature Communications, 2020
- Lightsheet localization microscopy enables fast, large-scale, and three-dimensional super-resolution imagingCommunications Biology, 2019
- Super-resolution fight club: assessment of 2D and 3D single-molecule localization microscopy softwareNature Methods, 2019
- Deep learning massively accelerates super-resolution localization microscopyNature Biotechnology, 2018
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Super‐resolution deep imaging with hollow Bessel beam STED microscopyLaser & Photonics Reviews, 2015
- DAOSTORM: an algorithm for high- density super-resolution microscopyNature Methods, 2011
- Three-dimensional, single-molecule fluorescence imaging beyond the diffraction limit by using a double-helix point spread functionProceedings of the National Academy of Sciences, 2009