Self-inspired learning for denoising live-cell super-resolution microscopy

doi:10.1038/s41592-024-02400-9

. 2024 Oct;21(10):1895-1908.

doi: 10.1038/s41592-024-02400-9. Epub 2024 Sep 11.

Self-inspired learning for denoising live-cell super-resolution microscopy

Liying Qu^#¹, Shiqun Zhao^#², Yuanyuan Huang^#¹, Xianxin Ye², Kunhao Wang², Yuzhen Liu¹, Xianming Liu³, Heng Mao⁴, Guangwei Hu⁵, Wei Chen⁶, Changliang Guo², Jiaye He^{7

8}, Jiubin Tan⁹, Haoyu Li^{1

9

10

11}, Liangyi Chen^{2

12

13}, Weisong Zhao^{14

15

16

17}

Affiliations

¹ Innovation Photonics and Imaging Center, School of Instrumentation Science and Engineering, Harbin Institute of Technology, Harbin, China.
² State Key Laboratory of Membrane Biology, Beijing Key Laboratory of Cardiometabolic Molecular Medicine, Institute of Molecular Medicine, National Biomedical Imaging Center, School of Future Technology, Peking University, Beijing, China.
³ School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China.
⁴ School of Mathematical Sciences, Peking University, Beijing, China.
⁵ School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore.
⁶ School of Mechanical Science and Engineering, Advanced Biomedical Imaging Facility, Huazhong University of Science and Technology, Wuhan, China.
⁷ National Innovation Center for Advanced Medical Devices, Shenzhen, China.
⁸ Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
⁹ Key Laboratory of Ultra-precision Intelligent Instrumentation of Ministry of Industry and Information Technology, Harbin Institute of Technology, Harbin, China.
¹⁰ Frontiers Science Center for Matter Behave in Space Environment, Harbin Institute of Technology, Harbin, China.
¹¹ Key Laboratory of Micro-Systems and Micro-Structures Manufacturing of Ministry of Education, Harbin Institute of Technology, Harbin, China.
¹² PKU-IDG/McGovern Institute for Brain Research, Beijing, China.
¹³ Beijing Academy of Artificial Intelligence, Beijing, China.
¹⁴ Innovation Photonics and Imaging Center, School of Instrumentation Science and Engineering, Harbin Institute of Technology, Harbin, China. weisongzhao@hit.edu.cn.
¹⁵ Key Laboratory of Ultra-precision Intelligent Instrumentation of Ministry of Industry and Information Technology, Harbin Institute of Technology, Harbin, China. weisongzhao@hit.edu.cn.
¹⁶ Frontiers Science Center for Matter Behave in Space Environment, Harbin Institute of Technology, Harbin, China. weisongzhao@hit.edu.cn.
¹⁷ Key Laboratory of Micro-Systems and Micro-Structures Manufacturing of Ministry of Education, Harbin Institute of Technology, Harbin, China. weisongzhao@hit.edu.cn.

^# Contributed equally.

PMID: 39261639
DOI: 10.1038/s41592-024-02400-9

Self-inspired learning for denoising live-cell super-resolution microscopy

Liying Qu et al. Nat Methods. 2024 Oct.

. 2024 Oct;21(10):1895-1908.

doi: 10.1038/s41592-024-02400-9. Epub 2024 Sep 11.

Authors

Affiliations

¹ Innovation Photonics and Imaging Center, School of Instrumentation Science and Engineering, Harbin Institute of Technology, Harbin, China.
² State Key Laboratory of Membrane Biology, Beijing Key Laboratory of Cardiometabolic Molecular Medicine, Institute of Molecular Medicine, National Biomedical Imaging Center, School of Future Technology, Peking University, Beijing, China.
³ School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China.
⁴ School of Mathematical Sciences, Peking University, Beijing, China.
⁵ School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore.
⁶ School of Mechanical Science and Engineering, Advanced Biomedical Imaging Facility, Huazhong University of Science and Technology, Wuhan, China.
⁷ National Innovation Center for Advanced Medical Devices, Shenzhen, China.
⁸ Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
⁹ Key Laboratory of Ultra-precision Intelligent Instrumentation of Ministry of Industry and Information Technology, Harbin Institute of Technology, Harbin, China.
¹⁰ Frontiers Science Center for Matter Behave in Space Environment, Harbin Institute of Technology, Harbin, China.
¹¹ Key Laboratory of Micro-Systems and Micro-Structures Manufacturing of Ministry of Education, Harbin Institute of Technology, Harbin, China.
¹² PKU-IDG/McGovern Institute for Brain Research, Beijing, China.
¹³ Beijing Academy of Artificial Intelligence, Beijing, China.
¹⁴ Innovation Photonics and Imaging Center, School of Instrumentation Science and Engineering, Harbin Institute of Technology, Harbin, China. weisongzhao@hit.edu.cn.
¹⁵ Key Laboratory of Ultra-precision Intelligent Instrumentation of Ministry of Industry and Information Technology, Harbin Institute of Technology, Harbin, China. weisongzhao@hit.edu.cn.
¹⁶ Frontiers Science Center for Matter Behave in Space Environment, Harbin Institute of Technology, Harbin, China. weisongzhao@hit.edu.cn.
¹⁷ Key Laboratory of Micro-Systems and Micro-Structures Manufacturing of Ministry of Education, Harbin Institute of Technology, Harbin, China. weisongzhao@hit.edu.cn.

^# Contributed equally.

PMID: 39261639
DOI: 10.1038/s41592-024-02400-9

Abstract

Every collected photon is precious in live-cell super-resolution (SR) microscopy. Here, we describe a data-efficient, deep learning-based denoising solution to improve diverse SR imaging modalities. The method, SN2N, is a Self-inspired Noise2Noise module with self-supervised data generation and self-constrained learning process. SN2N is fully competitive with supervised learning methods and circumvents the need for large training set and clean ground truth, requiring only a single noisy frame for training. We show that SN2N improves photon efficiency by one-to-two orders of magnitude and is compatible with multiple imaging modalities for volumetric, multicolor, time-lapse SR microscopy. We further integrated SN2N into different SR reconstruction algorithms to effectively mitigate image artifacts. We anticipate SN2N will enable improved live-SR imaging and inspire further advances.

PubMed Disclaimer

Cited by

Content-aware motion correction for multi-shot imaging.
Laine RF. Laine RF. Nat Methods. 2024 Dec;21(12):2235-2236. doi: 10.1038/s41592-024-02520-2. Nat Methods. 2024. PMID: 39558100 No abstract available.

References

1. Schermelleh, L. et al. Super-resolution microscopy demystified. Nat. Cell Biol. 21, 72–84 (2019). - PubMed - DOI
1. Schermelleh, L. et al. Subdiffraction multicolor imaging of the nuclear periphery with 3D structured illumination microscopy. Science 320, 1332–1336 (2008). - PubMed - DOI - PMC
1. Lawo, S., Hasegan, M., Gupta, G. D. & Pelletier, L. Subdiffraction imaging of centrosomes reveals higher-order organizational features of pericentriolar material. Nat. Cell Biol. 14, 1148–1158 (2012). - PubMed - DOI
1. Szymborska, A. et al. Nuclear pore scaffold structure analyzed by super-resolution microscopy and particle averaging. Science 341, 655–658 (2013). - PubMed - DOI
1. Xu, K., Zhong, G. & Zhuang, X. Actin, spectrin, and associated proteins form a periodic cytoskeletal structure in axons. Science 339, 452–456 (2013). - PubMed - DOI

MeSH terms

Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions

Grants and funding

62305083/National Natural Science Foundation of China (National Science Foundation of China)

LinkOut - more resources

Full Text Sources
- Nature Publishing Group
Research Materials
- NCI CPTC Antibody Characterization Program

[1] Schermelleh, L. et al. Super-resolution microscopy demystified. Nat. Cell Biol. 21, 72–84 (2019). - PubMed - DOI

[2] Schermelleh, L. et al. Super-resolution microscopy demystified. Nat. Cell Biol. 21, 72–84 (2019). - PubMed - DOI

[3] Schermelleh, L. et al. Subdiffraction multicolor imaging of the nuclear periphery with 3D structured illumination microscopy. Science 320, 1332–1336 (2008). - PubMed - DOI - PMC

[4] Schermelleh, L. et al. Subdiffraction multicolor imaging of the nuclear periphery with 3D structured illumination microscopy. Science 320, 1332–1336 (2008). - PubMed - DOI - PMC

[5] Lawo, S., Hasegan, M., Gupta, G. D. & Pelletier, L. Subdiffraction imaging of centrosomes reveals higher-order organizational features of pericentriolar material. Nat. Cell Biol. 14, 1148–1158 (2012). - PubMed - DOI

[6] Lawo, S., Hasegan, M., Gupta, G. D. & Pelletier, L. Subdiffraction imaging of centrosomes reveals higher-order organizational features of pericentriolar material. Nat. Cell Biol. 14, 1148–1158 (2012). - PubMed - DOI

[7] Szymborska, A. et al. Nuclear pore scaffold structure analyzed by super-resolution microscopy and particle averaging. Science 341, 655–658 (2013). - PubMed - DOI

[8] Szymborska, A. et al. Nuclear pore scaffold structure analyzed by super-resolution microscopy and particle averaging. Science 341, 655–658 (2013). - PubMed - DOI

[9] Xu, K., Zhong, G. & Zhuang, X. Actin, spectrin, and associated proteins form a periodic cytoskeletal structure in axons. Science 339, 452–456 (2013). - PubMed - DOI

[10] Xu, K., Zhong, G. & Zhuang, X. Actin, spectrin, and associated proteins form a periodic cytoskeletal structure in axons. Science 339, 452–456 (2013). - PubMed - DOI

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

Self-inspired learning for denoising live-cell super-resolution microscopy

Affiliations

Self-inspired learning for denoising live-cell super-resolution microscopy

Authors

Affiliations

Abstract

Similar articles

Cited by

References

MeSH terms

Grants and funding

LinkOut - more resources

Full Text Sources

Research Materials

Abstract

Similar articles

Cited by

References

MeSH terms

Related information

Grants and funding

LinkOut - more resources

Full Text Sources

Research Materials