Skip to main content
SpringerLink
Log in

Combining a deep neural network with physical properties for super-resolution live imaging

  • Research Briefing
  • Published:

From Nature Biotechnology

View current issue Submit your manuscript

We integrated the pre-characterized physical model of super-resolution (SR) microscopy into a deep neural network to guide the denoising of raw images for high-quality SR image reconstruction. This approach enabled us to investigate a wide variety of fragile and rapidly evolving bioprocesses at ultrahigh spatiotemporal resolution over extended imaging times.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1: Comparison of rDL SIM with state-of-the-art SIM methods.

References

  1. Rahaman, N. et al. On the spectral bias of neural networks. Proc. 36th Int. Conf. Machine Learning, PMLR 97, 5301–5310 (2019). This paper reveals the spectral bias of DNNs.

    Google Scholar 

  2. Kendall, A. & Gal, Y. What uncertainties do we need in Bayesian deep learning for computer vision? Adv. Neural Inf. Process. Syst. 30, 5574–5584 (2017). This paper reports the model uncertainty of DL algorithms.

    Google Scholar 

  3. Guo, Y. et al. Visualizing intracellular organelle and cytoskeletal interactions at nanoscale resolution on millisecond timescales. Cell 175, 1430–1442 (2018). This paper reports grazing incidence SIM optimized for 2D-SIM live-cell imaging. On this basis, we developed the Multi-SIM reported in this work.

    Article  CAS  PubMed  Google Scholar 

  4. Chen, B. C. et al. Lattice light-sheet microscopy: imaging molecules to embryos at high spatiotemporal resolution. Science 346, 1257998 (2014). This paper reports creating a confined, structured light sheet to achieve high resolution, high speed, 3D live imaging while decreasing phototoxicity.

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This is a summary of: Qiao, C. et al. Rationalized deep learning super-resolution microscopy for sustained live imaging of rapid subcellular processes. Nat. Biotechnol. https://doi.org/10.1038/s41587-022-01471-3 (2022)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Combining a deep neural network with physical properties for super-resolution live imaging. Nat Biotechnol 41, 328–329 (2023). https://doi.org/10.1038/s41587-022-01508-7

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41587-022-01508-7

  • Springer Nature America, Inc.

This article is cited by

Search

Navigation