Untrained deep learning-based differential phase-contrast microscopy
Optics Letters · 2023
DOI: 10.1364/ol.493391 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Letters, 2023. Verfasst von Baekcheon Seong und 5 weiteren Autor:innen. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 20 Literaturangaben. Gefördert von: Ministry of Science and ICT, South Korea, Samsung.
Abstract (Originalsprache)
Quantitative differential phase-contrast (DPC) microscopy produces phase images of transparent objects based on a number of intensity images. To reconstruct the phase, in DPC microscopy, a linearized model for weakly scattering objects is considered; this limits the range of objects to be imaged, and requires additional measurements and complicated algorithms to correct for system aberrations. Here, we present a self-calibrated DPC microscope using an untrained neural network (UNN), which incorporates the nonlinear image formation model. Our method alleviates the restrictions on the object to be imaged and simultaneously reconstructs the complex object information and aberrations, without any training dataset. We demonstrate the viability of UNN-DPC microscopy through both numerical simulations and LED microscope-based experiments.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- Ministry of Science and ICT, South Korea
- Samsung
Zitieren
APA
Seong, B., Kim, I., Moon, T., Ranathunga, M., Kim, D., & Joo, C. (2023). Untrained deep learning-based differential phase-contrast microscopy. Optics Letters. https://doi.org/10.1364/ol.493391
Vancouver
Seong B, Kim I, Moon T, Ranathunga M, Kim D, Joo C. Untrained deep learning-based differential phase-contrast microscopy. Optics Letters. 2023. doi:10.1364/ol.493391
BibTeX
@article{Seong2023,
author = {Seong, Baekcheon and Kim, Ingyoung and Moon, Taegyun and Ranathunga, Malith and Kim, Daesuk and Joo, Chulmin},
title = {Untrained deep learning-based differential phase-contrast microscopy},
journal = {Optics Letters},
year = {2023},
doi = {10.1364/ol.493391}
}
EUVIMED