Deep learning boosts the imaging speed of photoacoustic endomicroscopy

Tianrui Zhao; Mengjie Shi; Sebastien Ourselin; Tom Vercauteren; Wenfeng Xia

doi:10.1117/12.2649088

Deep learning boosts the imaging speed of photoacoustic endomicroscopy

Tianrui Zhao, Mengjie Shi, Sebastien Ourselin, Tom Vercauteren, Wenfeng Xia

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

1 Citation (Scopus)

113 Downloads (Pure)

Abstract

High-speed photoacoustic (PA) endomicroscopy imaging is desired for real-time guidance of minimally invasive surgery. However, the imaging speed of wavefront shaping-based endomicroscopy has been limited by the speed of spatial light modulators. In this work, a deep convolutional neural network was used to improve the imaging speed of a newly developed PA endomicroscopy system by enhancing sparsely sampled PA images. With a carbon fibre phantom, this method increased the imaging speed by 16 times without significantly affecting the image quality. With further validation on more complex datasets, this approach is promising to achieve real-time PA endomicroscopy imaging via wavefront shaping.

Original language	English
Title of host publication	Proc. SPIE 12379
Subtitle of host publication	Photons Plus Ultrasound: Imaging and Sensing 2023
Editors	Alexander A. Oraevsky, Lihong V. Wang
Number of pages	5
Volume	12379
ISBN (Electronic)	9781510658639
DOIs	https://doi.org/10.1117/12.2649088
Publication status	Published - 9 Mar 2023

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume	12379
ISSN (Print)	1605-7422

Access to Document

10.1117/12.2649088

Deep learning boosts the_ZHAO_2023_GREEN AAM
Copyright notice format: Copyright 2023 Society of Photo-Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.
Accepted author manuscript, 1.48 MBLicence: Other

Cite this

Zhao, T., Shi, M., Ourselin, S., Vercauteren, T., & Xia, W. (2023). Deep learning boosts the imaging speed of photoacoustic endomicroscopy. In A. A. Oraevsky, & L. V. Wang (Eds.), Proc. SPIE 12379: Photons Plus Ultrasound: Imaging and Sensing 2023 (Vol. 12379). Article 123790J (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 12379). https://doi.org/10.1117/12.2649088

@inbook{5c0649bd282541bdb271dbec8d65f08b,

title = "Deep learning boosts the imaging speed of photoacoustic endomicroscopy",

abstract = "High-speed photoacoustic (PA) endomicroscopy imaging is desired for real-time guidance of minimally invasive surgery. However, the imaging speed of wavefront shaping-based endomicroscopy has been limited by the speed of spatial light modulators. In this work, a deep convolutional neural network was used to improve the imaging speed of a newly developed PA endomicroscopy system by enhancing sparsely sampled PA images. With a carbon fibre phantom, this method increased the imaging speed by 16 times without significantly affecting the image quality. With further validation on more complex datasets, this approach is promising to achieve real-time PA endomicroscopy imaging via wavefront shaping.",

author = "Tianrui Zhao and Mengjie Shi and Sebastien Ourselin and Tom Vercauteren and Wenfeng Xia",

note = "Funding Information: This research was funded by the Academy of Medical Sciences/the Wellcome Trust/the Government Department of Business, Energy and Industrial Strategy/the British Heart Foundation/Diabetes UK Springboard Award [SBF006/1136], Wellcome Trust, United Kingdom (203148/Z/16/Z, WT101957), Engineering and Physical Sciences Research Council, United Kingdom (NS/A000027/1, NS/A000049/1), and King{\textquoteright}s - China Scholarship Council PhD Scholarship Program (K-CSC) (202008060071). For the purpose of open access, the authors have applied a CC BY public copyright license to any author-accepted manuscript version arising from this submission. Publisher Copyright: {\textcopyright} 2023 SPIE.",

year = "2023",

month = mar,

day = "9",

doi = "10.1117/12.2649088",

language = "English",

volume = "12379",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

editor = "Oraevsky, {Alexander A.} and Wang, {Lihong V.}",

booktitle = "Proc. SPIE 12379",

}

Deep learning boosts the imaging speed of photoacoustic endomicroscopy. / Zhao, Tianrui ; Shi, Mengjie ; Ourselin, Sebastien et al.
Proc. SPIE 12379: Photons Plus Ultrasound: Imaging and Sensing 2023. ed. / Alexander A. Oraevsky; Lihong V. Wang. Vol. 12379 2023. 123790J (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 12379).

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

TY - CHAP

T1 - Deep learning boosts the imaging speed of photoacoustic endomicroscopy

AU - Zhao, Tianrui

AU - Shi, Mengjie

AU - Ourselin, Sebastien

AU - Vercauteren, Tom

AU - Xia, Wenfeng

N1 - Funding Information: This research was funded by the Academy of Medical Sciences/the Wellcome Trust/the Government Department of Business, Energy and Industrial Strategy/the British Heart Foundation/Diabetes UK Springboard Award [SBF006/1136], Wellcome Trust, United Kingdom (203148/Z/16/Z, WT101957), Engineering and Physical Sciences Research Council, United Kingdom (NS/A000027/1, NS/A000049/1), and King’s - China Scholarship Council PhD Scholarship Program (K-CSC) (202008060071). For the purpose of open access, the authors have applied a CC BY public copyright license to any author-accepted manuscript version arising from this submission. Publisher Copyright: © 2023 SPIE.

PY - 2023/3/9

Y1 - 2023/3/9

N2 - High-speed photoacoustic (PA) endomicroscopy imaging is desired for real-time guidance of minimally invasive surgery. However, the imaging speed of wavefront shaping-based endomicroscopy has been limited by the speed of spatial light modulators. In this work, a deep convolutional neural network was used to improve the imaging speed of a newly developed PA endomicroscopy system by enhancing sparsely sampled PA images. With a carbon fibre phantom, this method increased the imaging speed by 16 times without significantly affecting the image quality. With further validation on more complex datasets, this approach is promising to achieve real-time PA endomicroscopy imaging via wavefront shaping.

AB - High-speed photoacoustic (PA) endomicroscopy imaging is desired for real-time guidance of minimally invasive surgery. However, the imaging speed of wavefront shaping-based endomicroscopy has been limited by the speed of spatial light modulators. In this work, a deep convolutional neural network was used to improve the imaging speed of a newly developed PA endomicroscopy system by enhancing sparsely sampled PA images. With a carbon fibre phantom, this method increased the imaging speed by 16 times without significantly affecting the image quality. With further validation on more complex datasets, this approach is promising to achieve real-time PA endomicroscopy imaging via wavefront shaping.

UR - http://www.scopus.com/inward/record.url?scp=85158934020&partnerID=8YFLogxK

U2 - 10.1117/12.2649088

DO - 10.1117/12.2649088

M3 - Conference paper

VL - 12379

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Proc. SPIE 12379

A2 - Oraevsky, Alexander A.

A2 - Wang, Lihong V.

ER -

Deep learning boosts the imaging speed of photoacoustic endomicroscopy

Abstract

Publication series

Access to Document

Other files and links

Fingerprint

Cite this