Resource-Efficient Inspection of Two-Photon Lithography via Cross-Modal Machine Learning from Electron to Optical Microscopy
Micromachines · 15.11.2026 · 17 (11) · 1328
DOI: 10.3390/mi17111328 ↗Kurz gefasst
Fachartikel in der Zeitschrift Micromachines, online erschienen am 15.11.2026. Verfasst von Aditya Ghosh und 2 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Georgia Tech’s Office of Commercialization, US Department of Energy, Office of Science, Fusion Energy Sciences, Georgia Research Alliance.
Abstract (Originalsprache)
Iterative process optimization in two-photon lithography (TPL) is fundamentally constrained by a critical metrology bottleneck: the reliance on slow, resource-intensive, and destructive scanning electron microscopy (SEM) for structural verification. To overcome this bottleneck, we introduce a resource-efficient inspection framework that provides high-fidelity fabrication feedback using only rapid, in-situ optical imaging. By leveraging cross-modal machine learning to transfer high-resolution metrological knowledge from SEM to optical microscopy, our approach significantly reduces the need for high-resolution microscopy and the time-consuming post-illumination processing steps during the optimization loop. We implement a dual-scale inspection strategy applied to grayscale projection TPL, which is a high-throughput layer-by-layer printing technique. At the global scale, a structure-level model provides highly reliable screening of complete samples, achieving 95% grouped accuracy and 100% within-one-score accuracy across an eight-level ordinal scale. Complementing this, an area-level model enables the granular detection of localized polymerization deviations within specific geometric sectors with 88% accuracy. We demonstrate the framework’s adaptability through transfer learning, where pre-training on cylindrical structures reduced the mean absolute error on unseen 3D woodpiles by 79%. Ultimately, this rapid cross-modal inspection approach enables high-fidelity structural assessment using only optical microscopy, eliminating routine SEM inspection and providing a scalable pathway for quality assessment in nanoscale 3D printing.
Förderung
- Georgia Tech’s Office of Commercialization
- US Department of Energy, Office of Science, Fusion Energy Sciences
- Georgia Research Alliance
- National Science Foundation
Zitieren
APA
Ghosh, A., Kim, H., & Saha, S. K. (2026). Resource-Efficient Inspection of Two-Photon Lithography via Cross-Modal Machine Learning from Electron to Optical Microscopy. Micromachines, 17(11), 1328. https://doi.org/10.3390/mi17111328
Vancouver
Ghosh A, Kim H, Saha SK. Resource-Efficient Inspection of Two-Photon Lithography via Cross-Modal Machine Learning from Electron to Optical Microscopy. Micromachines. 2026;17(11):1328. doi:10.3390/mi17111328
BibTeX
@article{Ghosh2026,
author = {Ghosh, Aditya and Kim, Harnjoo and Saha, Sourabh K.},
title = {Resource-Efficient Inspection of Two-Photon Lithography via Cross-Modal Machine Learning from Electron to Optical Microscopy},
journal = {Micromachines},
year = {2026},
volume = {17},
number = {11},
pages = {1328},
doi = {10.3390/mi17111328}
}
EUVIMED