EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improving Precision in Extended-Range Three-Dimensional Single-Molecule Localization with Physics-Guided Deep Learning

Xiang Zhou, Yuma Ito, Makio Tokunaga

Photonics · 03.07.2026 · 13 (7) · 649

DOI: 10.3390/photonics13070649 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Photonics, online erschienen am 03.07.2026. Verfasst von Xiang Zhou und 2 weiteren Autor:innen. Die Arbeit nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Education, Culture, Sports, Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Extended-range three-dimensional (3D) single-molecule localization microscopy (SMLM) and single-particle tracking (SPT) require precise emitter localization across cellular-scale axial distances. However, long-rangeengineered point-spread functions (PSFs) spread photons over wider camera footprints, lowering the signal-to-noise ratio (SNR) and localization precision. We numerically evaluated a physics-guided deep learning workflow for 3D localization over a 10.0 µm axial range using simulated electron-multiplying charge-coupled device (EMCCD) images. The workflow combines an analytical secondary-astigmatism phase mask, frequency-domain cross-filtering, a cross-filtering generative adversarial network (CFGAN), and coarse-to-fine fitting. The optical model and engineered PSF provide physical signal priors, cross-filtering preserves directional Fourier-domain energy, and CFGAN suppresses residual structured noise before model-based localization. In low-SNR simulations, lateral, axial, and radial root-mean-squared localization errors (RMSEs) decreased from 54.11, 96.12, and 112.79 nm without denoising to 31.14, 39.06, and 50.12 nm after CFGAN denoising—close to Cramér–Rao lower-bound (CRLB) references of 34.39, 38.94, and 51.95 nm. High-SNR RMSE values were 8.78, 12.00, and 14.96 nm, comparable to CRLB references of 10.36, 11.71, and 15.64 nm. These simulations suggest that physics-guided restoration can improve extended-range 3D SMLM precision, while experimental validation remains necessary.

Förderung

  • Ministry of Education, Culture, Sports, Science and Technology

Zitieren

APA

Zhou, X., Ito, Y., & Tokunaga, M. (2026). Improving Precision in Extended-Range Three-Dimensional Single-Molecule Localization with Physics-Guided Deep Learning. Photonics, 13(7), 649. https://doi.org/10.3390/photonics13070649

Vancouver

Zhou X, Ito Y, Tokunaga M. Improving Precision in Extended-Range Three-Dimensional Single-Molecule Localization with Physics-Guided Deep Learning. Photonics. 2026;13(7):649. doi:10.3390/photonics13070649

BibTeX
@article{Zhou2026,
  author = {Zhou, Xiang and Ito, Yuma and Tokunaga, Makio},
  title = {Improving Precision in Extended-Range Three-Dimensional Single-Molecule Localization with Physics-Guided Deep Learning},
  journal = {Photonics},
  year = {2026},
  volume = {13},
  number = {7},
  pages = {649},
  doi = {10.3390/photonics13070649}
}
Kostenlos starten →