Synthetic high-resolution, volumetric and wide field-of-view optical coherence tomography images with generative adversarial networks

Chuan Bor Chueh; Ting Hao Chen; Yu Yu Li; Ming Che Tu; Shih Jung Cheng; Cheng Kuang Lee; Simon See; Hsiang Chieh Lee

doi:10.1117/12.2670516

Synthetic high-resolution, volumetric and wide field-of-view optical coherence tomography images with generative adversarial networks

Chuan Bor Chueh, Ting Hao Chen, Yu Yu Li, Ming Che Tu, Shih Jung Cheng, Cheng Kuang Lee, Simon See, Hsiang Chieh Lee^*

^*Corresponding author for this work

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

Abstract

Optical coherence tomography (OCT) has been widely used in many clinical apartments. The trade-off between field-of-view (FOV) and transverse resolution has always become critical. High-resolution (HR) image reconstruction of OCT has the potential to increase the resolution without reducing the FOV. Although it has been widely explored in these years, it is hard to find one-to-one paired high-resolution for reference. The SR methods are used to improve the cross-sectional OCT image only. Therefore, we build a custom-design, wide field-of-view (FOV), multi-scale optical coherence tomography that can allow us to produce excellent high- and low-resolution one-to-one mapping volumetric data set. With the SR methods, we can reduce the acquisition of synthetic high-resolution volumetric images by up to four times.

Original language	English
Title of host publication	Optical Coherence Imaging Techniques and Imaging in Scattering Media V
Editors	Benjamin J. Vakoc, Maciej Wojtkowski, Yoshiaki Yasuno
Publisher	SPIE
ISBN (Electronic)	9781510664739
DOIs	https://doi.org/10.1117/12.2670516
State	Published - 2023
Externally published	Yes
Event	Optical Coherence Imaging Techniques and Imaging in Scattering Media V 2023 - Munich, Germany Duration: 25 06 2023 → 29 06 2023

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	12632
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	Optical Coherence Imaging Techniques and Imaging in Scattering Media V 2023
Country/Territory	Germany
City	Munich
Period	25/06/23 → 29/06/23

Bibliographical note

Publisher Copyright:
© 2023 SPIE. All rights reserved.

Keywords

GAN
deep learning
multi-scale imaging
optical coherence tomography
super-resolution

Access to Document

10.1117/12.2670516

Cite this

Chueh, C. B., Chen, T. H., Li, Y. Y., Tu, M. C., Cheng, S. J., Lee, C. K., See, S., & Lee, H. C. (2023). Synthetic high-resolution, volumetric and wide field-of-view optical coherence tomography images with generative adversarial networks. In B. J. Vakoc, M. Wojtkowski, & Y. Yasuno (Eds.), Optical Coherence Imaging Techniques and Imaging in Scattering Media V Article 126321V (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 12632). SPIE. https://doi.org/10.1117/12.2670516

Chueh, Chuan Bor ; Chen, Ting Hao ; Li, Yu Yu et al. / Synthetic high-resolution, volumetric and wide field-of-view optical coherence tomography images with generative adversarial networks. Optical Coherence Imaging Techniques and Imaging in Scattering Media V. editor / Benjamin J. Vakoc ; Maciej Wojtkowski ; Yoshiaki Yasuno. SPIE, 2023. (Proceedings of SPIE - The International Society for Optical Engineering).

@inproceedings{53fdeea2ca2d48aca68657eabdb72522,

title = "Synthetic high-resolution, volumetric and wide field-of-view optical coherence tomography images with generative adversarial networks",

abstract = "Optical coherence tomography (OCT) has been widely used in many clinical apartments. The trade-off between field-of-view (FOV) and transverse resolution has always become critical. High-resolution (HR) image reconstruction of OCT has the potential to increase the resolution without reducing the FOV. Although it has been widely explored in these years, it is hard to find one-to-one paired high-resolution for reference. The SR methods are used to improve the cross-sectional OCT image only. Therefore, we build a custom-design, wide field-of-view (FOV), multi-scale optical coherence tomography that can allow us to produce excellent high- and low-resolution one-to-one mapping volumetric data set. With the SR methods, we can reduce the acquisition of synthetic high-resolution volumetric images by up to four times.",

keywords = "GAN, deep learning, multi-scale imaging, optical coherence tomography, super-resolution",

author = "Chueh, {Chuan Bor} and Chen, {Ting Hao} and Li, {Yu Yu} and Tu, {Ming Che} and Cheng, {Shih Jung} and Lee, {Cheng Kuang} and Simon See and Lee, {Hsiang Chieh}",

note = "Publisher Copyright: {\textcopyright} 2023 SPIE. All rights reserved.; Optical Coherence Imaging Techniques and Imaging in Scattering Media V 2023 ; Conference date: 25-06-2023 Through 29-06-2023",

year = "2023",

doi = "10.1117/12.2670516",

language = "英语",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

editor = "Vakoc, {Benjamin J.} and Maciej Wojtkowski and Yoshiaki Yasuno",

booktitle = "Optical Coherence Imaging Techniques and Imaging in Scattering Media V",

address = "美国",

}

Chueh, CB, Chen, TH, Li, YY, Tu, MC, Cheng, SJ, Lee, CK, See, S & Lee, HC 2023, Synthetic high-resolution, volumetric and wide field-of-view optical coherence tomography images with generative adversarial networks. in BJ Vakoc, M Wojtkowski & Y Yasuno (eds), Optical Coherence Imaging Techniques and Imaging in Scattering Media V., 126321V, Proceedings of SPIE - The International Society for Optical Engineering, vol. 12632, SPIE, Optical Coherence Imaging Techniques and Imaging in Scattering Media V 2023, Munich, Germany, 25/06/23. https://doi.org/10.1117/12.2670516

Synthetic high-resolution, volumetric and wide field-of-view optical coherence tomography images with generative adversarial networks. / Chueh, Chuan Bor; Chen, Ting Hao; Li, Yu Yu et al.
Optical Coherence Imaging Techniques and Imaging in Scattering Media V. ed. / Benjamin J. Vakoc; Maciej Wojtkowski; Yoshiaki Yasuno. SPIE, 2023. 126321V (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 12632).

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

TY - GEN

T1 - Synthetic high-resolution, volumetric and wide field-of-view optical coherence tomography images with generative adversarial networks

AU - Chueh, Chuan Bor

AU - Chen, Ting Hao

AU - Li, Yu Yu

AU - Tu, Ming Che

AU - Cheng, Shih Jung

AU - Lee, Cheng Kuang

AU - See, Simon

AU - Lee, Hsiang Chieh

PY - 2023

Y1 - 2023

N2 - Optical coherence tomography (OCT) has been widely used in many clinical apartments. The trade-off between field-of-view (FOV) and transverse resolution has always become critical. High-resolution (HR) image reconstruction of OCT has the potential to increase the resolution without reducing the FOV. Although it has been widely explored in these years, it is hard to find one-to-one paired high-resolution for reference. The SR methods are used to improve the cross-sectional OCT image only. Therefore, we build a custom-design, wide field-of-view (FOV), multi-scale optical coherence tomography that can allow us to produce excellent high- and low-resolution one-to-one mapping volumetric data set. With the SR methods, we can reduce the acquisition of synthetic high-resolution volumetric images by up to four times.

AB - Optical coherence tomography (OCT) has been widely used in many clinical apartments. The trade-off between field-of-view (FOV) and transverse resolution has always become critical. High-resolution (HR) image reconstruction of OCT has the potential to increase the resolution without reducing the FOV. Although it has been widely explored in these years, it is hard to find one-to-one paired high-resolution for reference. The SR methods are used to improve the cross-sectional OCT image only. Therefore, we build a custom-design, wide field-of-view (FOV), multi-scale optical coherence tomography that can allow us to produce excellent high- and low-resolution one-to-one mapping volumetric data set. With the SR methods, we can reduce the acquisition of synthetic high-resolution volumetric images by up to four times.

KW - GAN

KW - deep learning

KW - multi-scale imaging

KW - optical coherence tomography

KW - super-resolution

UR - http://www.scopus.com/inward/record.url?scp=85172921489&partnerID=8YFLogxK

U2 - 10.1117/12.2670516

DO - 10.1117/12.2670516

M3 - 会议稿件

AN - SCOPUS:85172921489

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Optical Coherence Imaging Techniques and Imaging in Scattering Media V

A2 - Vakoc, Benjamin J.

A2 - Wojtkowski, Maciej

A2 - Yasuno, Yoshiaki

PB - SPIE

T2 - Optical Coherence Imaging Techniques and Imaging in Scattering Media V 2023

Y2 - 25 June 2023 through 29 June 2023

ER -

Chueh CB, Chen TH, Li YY, Tu MC, Cheng SJ, Lee CK et al. Synthetic high-resolution, volumetric and wide field-of-view optical coherence tomography images with generative adversarial networks. In Vakoc BJ, Wojtkowski M, Yasuno Y, editors, Optical Coherence Imaging Techniques and Imaging in Scattering Media V. SPIE. 2023. 126321V. (Proceedings of SPIE - The International Society for Optical Engineering). doi: 10.1117/12.2670516

Synthetic high-resolution, volumetric and wide field-of-view optical coherence tomography images with generative adversarial networks

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this