EUVIMEDEUVIMED entdecken
Crossref

Deep-learning-assisted scattering structured-illumination confocal microscopy for industrial super-resolution imaging

Peng Du, Meiting Wang, Xinran Li, Xiaomin Zheng, Ying Long, Ying Wu, Jingsha Shu, Xin Long, Zheng Shao, Yuye Wang, Junle Qu, Yonghong Shao

Optics Express · 01.06.2026 · 34 (11) · 20197

DOI: 10.1364/oe.600149 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Optics Express, online erschienen am 21.05.2026. Verfasst von Peng Du und 11 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Gefördert von: Project from National Key Research and Development Program of China, National Natural Science Foundation of China, Department of Science and Technology of Guangdong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Laser scanning confocal microscopy (LSCM) plays an essential role in industrial inspection, yet its performance is fundamentally limited by the “edge shadow effect” in reflection imaging and the Abbe diffraction limit. To address these challenges, we propose a deep learning-driven scattering laser scanning structural illumination microscope (DL-sLSSIM) for super-resolution inspection of semiconductor nanostructures. A polarization-compensated scattering confocal configuration is first established to suppress specular reflection background and enhance edge contrast in steep topographies. We further analyze the imaging mechanism of point-scanning structured illumination and show that morphology-dependent reflection–scattering modulation induces severe stripe distortion, which prevents conventional SIM reconstruction in industrial samples. To overcome this issue, a residual channel attention network (RCAN) is introduced to perform nonlinear demodulation of the distorted structured light patterns and accurately extract the high-frequency image information from the distorted fringes. Experiments on semiconductor wafers demonstrate that DL-sLSSIM achieves a lateral resolution improvement of approximately 1.8×, reaching 480 nm under low-magnification inspection conditions, while significantly improving the signal-to-noise ratio. The proposed method provides a promising route for high-fidelity, non-destructive super-resolution metrology in advanced semiconductor manufacturing.

Förderung

  • Project from National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Department of Science and Technology of Guangdong Province
  • Shenzhen Science and Technology R&D and Innovation Foundation
  • Shenzhen Key Laboratory of Photonics and Biophotonics
  • Medical-Engineering Interdisciplinary Research Foundation of Shenzhen University
  • Scientific Instrument Developing Project of Shenzhen University
  • Shenzhen University 2035 Program for Excellent Research

Zitieren

APA

Du, P., Wang, M., Li, X., Zheng, X., Long, Y., Wu, Y., Shu, J., Long, X., Shao, Z., Wang, Y., Qu, J., & Shao, Y. (2026). Deep-learning-assisted scattering structured-illumination confocal microscopy for industrial super-resolution imaging. Optics Express, 34(11), 20197. https://doi.org/10.1364/oe.600149

Vancouver

Du P, Wang M, Li X, Zheng X, Long Y, Wu Y, et al. Deep-learning-assisted scattering structured-illumination confocal microscopy for industrial super-resolution imaging. Optics Express. 2026;34(11):20197. doi:10.1364/oe.600149

BibTeX
@article{Du2026,
  author = {Du, Peng and Wang, Meiting and Li, Xinran and Zheng, Xiaomin and Long, Ying and Wu, Ying and Shu, Jingsha and Long, Xin and Shao, Zheng and Wang, Yuye and Qu, Junle and Shao, Yonghong},
  title = {Deep-learning-assisted scattering structured-illumination confocal microscopy for industrial super-resolution imaging},
  journal = {Optics Express},
  year = {2026},
  volume = {34},
  number = {11},
  pages = {20197},
  doi = {10.1364/oe.600149}
}
Kostenlos starten →