Journal
ADVANCED PHOTONICS RESEARCH
Volume 3, Issue 11, Pages -Publisher
WILEY
DOI: 10.1002/adpr.202200244
Keywords
convolutional neural networks; deep learning; fluorescent nanoparticles; near-infrared imaging; single-walled carbon nanotubes; super-resolution
Categories
Funding
- Zuckerman STEM Leadership Program
- Israel Science Foundation [456/18, 196/22]
- Ministry of Science, Technology, and Space, Israel [3-17426]
- Israeli Ministry of Defense-CBRN Defense Division
- ERC NanoNonEq [101039127]
- Nicholas and Elizabeth Slezak Super Center or Cardiac Research and Biomedical Engineering at Tel Aviv University
- Zimin Institute for Engineering Solutions Advancing Better Lives
- Tel Aviv University Center for Combating Pandemics
- Tel Aviv University Center for AI and Data Science
- Ministry of Science, Technology, and Space, Israel
- Marian Gertner Institute for Medical Nanosystems
- European Research Council (ERC) [101039127] Funding Source: European Research Council (ERC)
Ask authors/readers for more resources
In this study, a computational method for enhancing the spatial resolution of near-infrared fluorescence images of single-walled carbon nanotubes (SWCNTs) was developed using deep learning and convolutional neural networks, along with the super-resolution radial fluctuation (SRRF) algorithm. The method achieved an average improvement of 22% in resolution and 47% in signal-to-noise ratio (SNR) compared to the original images. It was demonstrated to be effective for a variety of SWCNT densities and length distributions, and could be used for real-time video imaging under challenging SNR conditions.
Single-walled carbon nanotubes (SWCNTs) have unique optical and physical properties, with numerous biomedical imaging and sensing applications, owing to their near-infrared (nIR) fluorescence which overlaps with the biological transparency window. However, their longer emission wavelengths compared to emitters in the visible range result in a lower resolution due to the diffraction limit. Moreover, the elongated high-aspect-ratio structure of SWCNTs poses an additional challenge on super-resolution techniques that assume point emitters. Utilizing the advantages of deep learning and convolutional neural networks, along with the super-resolution radial fluctuation (SRRF) algorithm for network training, a fast, parameter-free, computational method is offered for enhancing the spatial resolution of nIR fluorescence images of SWCNTs. An average improvement of 22% in the resolution and 47% in signal-to-noise ratio (SNR) compared to the original images is shown, whereas SRRF leads to only 24% SNR improvement. The approach is demonstrated for a variety of SWCNT densities and length distributions, and a wide range of imaging conditions with challenging SNRs, including real-time videos, without compromising the temporal resolution. The results open the path for accelerated and accessible super-resolution of nIR fluorescent SWCNTs images, further advancing their applicability as nanoscale optical probes.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available