Super‐Resolution Near‐Infrared Fluorescence Microscopy of Single‐Walled Carbon Nanotubes Using Deep Learning
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...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley-VCH
2022-11-01
|
Series: | Advanced Photonics Research |
Subjects: | |
Online Access: | https://doi.org/10.1002/adpr.202200244 |
_version_ | 1811332850074517504 |
---|---|
author | Barak Kagan Adi Hendler-Neumark Verena Wulf Dotan Kamber Roni Ehrlich Gili Bisker |
author_facet | Barak Kagan Adi Hendler-Neumark Verena Wulf Dotan Kamber Roni Ehrlich Gili Bisker |
author_sort | Barak Kagan |
collection | DOAJ |
description | 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. |
first_indexed | 2024-04-13T16:43:17Z |
format | Article |
id | doaj.art-e2c2c3b0955b4705951f512264ed1e20 |
institution | Directory Open Access Journal |
issn | 2699-9293 |
language | English |
last_indexed | 2024-04-13T16:43:17Z |
publishDate | 2022-11-01 |
publisher | Wiley-VCH |
record_format | Article |
series | Advanced Photonics Research |
spelling | doaj.art-e2c2c3b0955b4705951f512264ed1e202022-12-22T02:39:10ZengWiley-VCHAdvanced Photonics Research2699-92932022-11-01311n/an/a10.1002/adpr.202200244Super‐Resolution Near‐Infrared Fluorescence Microscopy of Single‐Walled Carbon Nanotubes Using Deep LearningBarak Kagan0Adi Hendler-Neumark1Verena Wulf2Dotan Kamber3Roni Ehrlich4Gili Bisker5Department of Biomedical Engineering Faculty of Engineering Tel Aviv University Tel Aviv 6997801 IsraelDepartment of Biomedical Engineering Faculty of Engineering Tel Aviv University Tel Aviv 6997801 IsraelDepartment of Biomedical Engineering Faculty of Engineering Tel Aviv University Tel Aviv 6997801 IsraelDepartment of Biomedical Engineering Faculty of Engineering Tel Aviv University Tel Aviv 6997801 IsraelDepartment of Biomedical Engineering Faculty of Engineering Tel Aviv University Tel Aviv 6997801 IsraelDepartment of Biomedical Engineering Faculty of Engineering Tel Aviv University Tel Aviv 6997801 IsraelSingle‐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.https://doi.org/10.1002/adpr.202200244convolutional neural networksdeep learningfluorescent nanoparticlesnear-infrared imagingsingle-walled carbon nanotubessuper-resolution |
spellingShingle | Barak Kagan Adi Hendler-Neumark Verena Wulf Dotan Kamber Roni Ehrlich Gili Bisker Super‐Resolution Near‐Infrared Fluorescence Microscopy of Single‐Walled Carbon Nanotubes Using Deep Learning Advanced Photonics Research convolutional neural networks deep learning fluorescent nanoparticles near-infrared imaging single-walled carbon nanotubes super-resolution |
title | Super‐Resolution Near‐Infrared Fluorescence Microscopy of Single‐Walled Carbon Nanotubes Using Deep Learning |
title_full | Super‐Resolution Near‐Infrared Fluorescence Microscopy of Single‐Walled Carbon Nanotubes Using Deep Learning |
title_fullStr | Super‐Resolution Near‐Infrared Fluorescence Microscopy of Single‐Walled Carbon Nanotubes Using Deep Learning |
title_full_unstemmed | Super‐Resolution Near‐Infrared Fluorescence Microscopy of Single‐Walled Carbon Nanotubes Using Deep Learning |
title_short | Super‐Resolution Near‐Infrared Fluorescence Microscopy of Single‐Walled Carbon Nanotubes Using Deep Learning |
title_sort | super resolution near infrared fluorescence microscopy of single walled carbon nanotubes using deep learning |
topic | convolutional neural networks deep learning fluorescent nanoparticles near-infrared imaging single-walled carbon nanotubes super-resolution |
url | https://doi.org/10.1002/adpr.202200244 |
work_keys_str_mv | AT barakkagan superresolutionnearinfraredfluorescencemicroscopyofsinglewalledcarbonnanotubesusingdeeplearning AT adihendlerneumark superresolutionnearinfraredfluorescencemicroscopyofsinglewalledcarbonnanotubesusingdeeplearning AT verenawulf superresolutionnearinfraredfluorescencemicroscopyofsinglewalledcarbonnanotubesusingdeeplearning AT dotankamber superresolutionnearinfraredfluorescencemicroscopyofsinglewalledcarbonnanotubesusingdeeplearning AT roniehrlich superresolutionnearinfraredfluorescencemicroscopyofsinglewalledcarbonnanotubesusingdeeplearning AT gilibisker superresolutionnearinfraredfluorescencemicroscopyofsinglewalledcarbonnanotubesusingdeeplearning |