Deep Learning Empowered Parallelized Metasurface Computed Tomography Snapshot Spectral Imaging
Advanced Materials · 2025-07 · 37 (27)
DOI: 10.1002/adma.202419383 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Materials, online erschienen am 24.04.2025. Verfasst von Kaiyang Ding und 7 weiteren Autor:innen. Beteiligte Einrichtung: Shenzhen International Graduate School, Institute for Data and Information Studies, Tsinghua University, Shenzhen, 518055, China. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shenzhen Fundamental Research, Shenzhen Science and Technology Program.
Abstract (Originalsprache)
Snapshot spectral imaging is an emerging technology for fast data acquisition in dynamic environments, capturing high‐volume spatial‐spectral information in a single snapshot. However, it suffers from bulky cascading optics and cannot be directly used in space‐restricted scenarios such as endoscope‐assisted brain microsurgery and real‐time cellular tissue imaging. In this work, an ultracompact strategy of parallelized metasurface computed tomography empowered by generative deep learning is proposed, which can effectively reduce the optics volume in snapshot spectral imaging from cm 3 scale to sub‐mm 3 scale while retaining high resolution and speed of imaging so that the above‐mentioned pain point problem is well addressed. The system comprises seven multifunctional sub‐metasurfaces simultaneously acquiring multi‐angle spectral projection and integration information of the target, uses the system‐calibrated point spread functions as wavelength and spatial position distributions, and incorporates a generative adversarial deep neural network for fast reconstruction of spatial‐spectral multiplexed images. Experimental results show that single snapshot imaging can be achieved in 38 ms with a spectral resolution of 10 nm in the spectral range of 450–650 nm. This technique paves the way for snapshot spectral imaging integration into various highly miniaturized microscopy and endoscopic imaging systems in applications such as advanced medical diagnosis.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Shenzhen International Graduate School, Institute for Data and Information Studies, Tsinghua University, Shenzhen, 518055, China.
- Pengcheng Laboratory, Shenzhen, 518055, China.
- State Key Laboratory of Precision Measurement Technology and Instruments, Department of Precision Instrument, Tsinghua University, Beijing, 100084, China.
ORCID-Profile: Benfeng Bai
Förderung
- National Natural Science Foundation of China
- Shenzhen Fundamental Research
- Shenzhen Science and Technology Program
- Shenzhen Science and Technology Innovation Program
Zitieren
APA
Ding, K., Zhou, Q., Chen, M., Shao, K., Wang, X., Liang, X., Ni, K., & Bai, B. (2025). Deep Learning Empowered Parallelized Metasurface Computed Tomography Snapshot Spectral Imaging. Advanced Materials, 37(27). https://doi.org/10.1002/adma.202419383
Vancouver
Ding K, Zhou Q, Chen M, Shao K, Wang X, Liang X, et al. Deep Learning Empowered Parallelized Metasurface Computed Tomography Snapshot Spectral Imaging. Advanced Materials. 2025;37(27). doi:10.1002/adma.202419383
BibTeX
@article{Ding2025,
author = {Ding, Kaiyang and Zhou, Qian and Chen, Mengyuan and Shao, Kuizhi and Wang, Xiaohao and Liang, Xiaojun and Ni, Kai and Bai, Benfeng},
title = {Deep Learning Empowered Parallelized Metasurface Computed Tomography Snapshot Spectral Imaging},
journal = {Advanced Materials},
year = {2025},
volume = {37},
number = {27},
doi = {10.1002/adma.202419383}
}
EUVIMED