Unsupervised detection of Small Hyperreflective Features in Ultrahigh Resolution Optical Coherence Tomography

Marcel Reimann; Jungeun Won; Hiroyuki Takahashi; Antonio Yaghy; Yunchan Hwang; Stefan Ploner; Junhong Lin; Jessica Girgis; Kenneth Lam; Siyu Chen; Nadia K. Waheed; Andreas Maier; James G. Fujimoto

doi:10.1007/978-3-658-41657-7_50

Unsupervised detection of Small Hyperreflective Features in Ultrahigh Resolution Optical Coherence Tomography

Marcel Reimann^*, Jungeun Won, Hiroyuki Takahashi, Antonio Yaghy, Yunchan Hwang, Stefan Ploner, Junhong Lin, Jessica Girgis, Kenneth Lam, Siyu Chen, Nadia K. Waheed, Andreas Maier, James G. Fujimoto

^*Corresponding author for this work

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

Abstract

Recent advances in optical coherence tomography such as the development of high speed ultrahigh resolution scanners and corresponding signal processing techniques may reveal new potential biomarkers in retinal diseases. Newly visible features are, for example, small hyperreflective specks in age-related macular degeneration. Identifying these new markers is crucial to investigate potential association with disease progression and treatment outcomes. Therefore, it is necessary to reliably detect these features in 3D volumetric scans. Because manual labeling of entire volumes is infeasible a need for automatic detection arises. Labeled datasets are often not publicly available and there are usually large variations in scan protocols and scanner types. Thus, this work focuses on an unsupervised approach that is based on local peak-detection and random walker segmentation to detect small features on each B-scan of the volume.

Original language	English
Title of host publication	Bildverarbeitung für die Medizin 2023 Proceedings, German Workshop on Medical Image Computing, Braunschweig
Editors	Thomas M. Deserno, Heinz Handels, Andreas Maier, Klaus Maier-Hein, Christoph Palm, Thomas Tolxdorff
Number of pages	6
Publisher	Springer Science and Business Media Deutschland GmbH
Publication date	2023
Pages	232-237
ISBN (Print)	9783658416560
DOIs	https://doi.org/10.1007/978-3-658-41657-7_50
Publication status	Published - 2023
Externally published	Yes
Event	Bildverarbeitung für die Medizin Workshop, BVM 2023 - Braunschweig, Germany Duration: 2 Jul 2023 → 4 Jul 2023

Conference

Conference	Bildverarbeitung für die Medizin Workshop, BVM 2023
Country/Territory	Germany
City	Braunschweig
Period	02/07/2023 → 04/07/2023

Series	Informatik aktuell
ISSN	1431-472X

Bibliographical note

Funding Information:
Acknowledgement. We acknowledge funding by the National Institutes of Health, project 5-R01-EY011289-36, and the German Research Foundation, project 508075009.

Publisher Copyright:
© 2023 Der/die Autor(en), exklusiv lizenziert an Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature.

Access to Document

10.1007/978-3-658-41657-7_50

Library access?

Check availability at the Royal Danish Library

Cite this

Reimann, M., Won, J., Takahashi, H., Yaghy, A., Hwang, Y., Ploner, S., Lin, J., Girgis, J., Lam, K., Chen, S., Waheed, N. K., Maier, A., & Fujimoto, J. G. (2023). Unsupervised detection of Small Hyperreflective Features in Ultrahigh Resolution Optical Coherence Tomography. In T. M. Deserno, H. Handels, A. Maier, K. Maier-Hein, C. Palm, & T. Tolxdorff (Eds.), Bildverarbeitung für die Medizin 2023 Proceedings, German Workshop on Medical Image Computing, Braunschweig (pp. 232-237). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-658-41657-7_50

Unsupervised detection of Small Hyperreflective Features in Ultrahigh Resolution Optical Coherence Tomography. / Reimann, Marcel; Won, Jungeun; Takahashi, Hiroyuki et al.
Bildverarbeitung für die Medizin 2023 Proceedings, German Workshop on Medical Image Computing, Braunschweig. ed. / Thomas M. Deserno; Heinz Handels; Andreas Maier; Klaus Maier-Hein; Christoph Palm; Thomas Tolxdorff. Springer Science and Business Media Deutschland GmbH, 2023. p. 232-237 (Informatik aktuell).

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

Reimann, M, Won, J, Takahashi, H, Yaghy, A, Hwang, Y, Ploner, S, Lin, J, Girgis, J, Lam, K, Chen, S, Waheed, NK, Maier, A & Fujimoto, JG 2023, Unsupervised detection of Small Hyperreflective Features in Ultrahigh Resolution Optical Coherence Tomography. in TM Deserno, H Handels, A Maier, K Maier-Hein, C Palm & T Tolxdorff (eds), Bildverarbeitung für die Medizin 2023 Proceedings, German Workshop on Medical Image Computing, Braunschweig. Springer Science and Business Media Deutschland GmbH, Informatik aktuell, pp. 232-237, Bildverarbeitung für die Medizin Workshop, BVM 2023, Braunschweig, Germany, 02/07/2023. https://doi.org/10.1007/978-3-658-41657-7_50

Reimann M, Won J, Takahashi H, Yaghy A, Hwang Y, Ploner S et al. Unsupervised detection of Small Hyperreflective Features in Ultrahigh Resolution Optical Coherence Tomography. In Deserno TM, Handels H, Maier A, Maier-Hein K, Palm C, Tolxdorff T, editors, Bildverarbeitung für die Medizin 2023 Proceedings, German Workshop on Medical Image Computing, Braunschweig. Springer Science and Business Media Deutschland GmbH. 2023. p. 232-237. (Informatik aktuell). doi: 10.1007/978-3-658-41657-7_50

Reimann, Marcel ; Won, Jungeun ; Takahashi, Hiroyuki et al. / Unsupervised detection of Small Hyperreflective Features in Ultrahigh Resolution Optical Coherence Tomography. Bildverarbeitung für die Medizin 2023 Proceedings, German Workshop on Medical Image Computing, Braunschweig. editor / Thomas M. Deserno ; Heinz Handels ; Andreas Maier ; Klaus Maier-Hein ; Christoph Palm ; Thomas Tolxdorff. Springer Science and Business Media Deutschland GmbH, 2023. pp. 232-237 (Informatik aktuell).

@inproceedings{7d1a32b97039416b9af59fa104c696c1,

title = "Unsupervised detection of Small Hyperreflective Features in Ultrahigh Resolution Optical Coherence Tomography",

abstract = "Recent advances in optical coherence tomography such as the development of high speed ultrahigh resolution scanners and corresponding signal processing techniques may reveal new potential biomarkers in retinal diseases. Newly visible features are, for example, small hyperreflective specks in age-related macular degeneration. Identifying these new markers is crucial to investigate potential association with disease progression and treatment outcomes. Therefore, it is necessary to reliably detect these features in 3D volumetric scans. Because manual labeling of entire volumes is infeasible a need for automatic detection arises. Labeled datasets are often not publicly available and there are usually large variations in scan protocols and scanner types. Thus, this work focuses on an unsupervised approach that is based on local peak-detection and random walker segmentation to detect small features on each B-scan of the volume.",

author = "Marcel Reimann and Jungeun Won and Hiroyuki Takahashi and Antonio Yaghy and Yunchan Hwang and Stefan Ploner and Junhong Lin and Jessica Girgis and Kenneth Lam and Siyu Chen and Waheed, {Nadia K.} and Andreas Maier and Fujimoto, {James G.}",

note = "Funding Information: Acknowledgement. We acknowledge funding by the National Institutes of Health, project 5-R01-EY011289-36, and the German Research Foundation, project 508075009. Publisher Copyright: {\textcopyright} 2023 Der/die Autor(en), exklusiv lizenziert an Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature.; Bildverarbeitung f{\"u}r die Medizin Workshop, BVM 2023 ; Conference date: 02-07-2023 Through 04-07-2023",

year = "2023",

doi = "10.1007/978-3-658-41657-7_50",

language = "English",

isbn = "9783658416560",

series = "Informatik aktuell",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "232--237",

editor = "Deserno, {Thomas M.} and Heinz Handels and Andreas Maier and Klaus Maier-Hein and Christoph Palm and Thomas Tolxdorff",

booktitle = "Bildverarbeitung f{\"u}r die Medizin 2023 Proceedings, German Workshop on Medical Image Computing, Braunschweig",

address = "Germany",

}

TY - GEN

T1 - Unsupervised detection of Small Hyperreflective Features in Ultrahigh Resolution Optical Coherence Tomography

AU - Reimann, Marcel

AU - Won, Jungeun

AU - Takahashi, Hiroyuki

AU - Yaghy, Antonio

AU - Hwang, Yunchan

AU - Ploner, Stefan

AU - Lin, Junhong

AU - Girgis, Jessica

AU - Lam, Kenneth

AU - Chen, Siyu

AU - Waheed, Nadia K.

AU - Maier, Andreas

AU - Fujimoto, James G.

N1 - Funding Information: Acknowledgement. We acknowledge funding by the National Institutes of Health, project 5-R01-EY011289-36, and the German Research Foundation, project 508075009. Publisher Copyright: © 2023 Der/die Autor(en), exklusiv lizenziert an Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature.

PY - 2023

Y1 - 2023

N2 - Recent advances in optical coherence tomography such as the development of high speed ultrahigh resolution scanners and corresponding signal processing techniques may reveal new potential biomarkers in retinal diseases. Newly visible features are, for example, small hyperreflective specks in age-related macular degeneration. Identifying these new markers is crucial to investigate potential association with disease progression and treatment outcomes. Therefore, it is necessary to reliably detect these features in 3D volumetric scans. Because manual labeling of entire volumes is infeasible a need for automatic detection arises. Labeled datasets are often not publicly available and there are usually large variations in scan protocols and scanner types. Thus, this work focuses on an unsupervised approach that is based on local peak-detection and random walker segmentation to detect small features on each B-scan of the volume.

AB - Recent advances in optical coherence tomography such as the development of high speed ultrahigh resolution scanners and corresponding signal processing techniques may reveal new potential biomarkers in retinal diseases. Newly visible features are, for example, small hyperreflective specks in age-related macular degeneration. Identifying these new markers is crucial to investigate potential association with disease progression and treatment outcomes. Therefore, it is necessary to reliably detect these features in 3D volumetric scans. Because manual labeling of entire volumes is infeasible a need for automatic detection arises. Labeled datasets are often not publicly available and there are usually large variations in scan protocols and scanner types. Thus, this work focuses on an unsupervised approach that is based on local peak-detection and random walker segmentation to detect small features on each B-scan of the volume.

UR - http://www.scopus.com/inward/record.url?scp=85164948017&partnerID=8YFLogxK

U2 - 10.1007/978-3-658-41657-7_50

DO - 10.1007/978-3-658-41657-7_50

M3 - Article in proceedings

AN - SCOPUS:85164948017

SN - 9783658416560

T3 - Informatik aktuell

SP - 232

EP - 237

BT - Bildverarbeitung für die Medizin 2023 Proceedings, German Workshop on Medical Image Computing, Braunschweig

A2 - Deserno, Thomas M.

A2 - Handels, Heinz

A2 - Maier, Andreas

A2 - Maier-Hein, Klaus

A2 - Palm, Christoph

A2 - Tolxdorff, Thomas

PB - Springer Science and Business Media Deutschland GmbH

T2 - Bildverarbeitung für die Medizin Workshop, BVM 2023

Y2 - 2 July 2023 through 4 July 2023

ER -

Unsupervised detection of Small Hyperreflective Features in Ultrahigh Resolution Optical Coherence Tomography

Abstract

Conference

Bibliographical note

Access to Document

Library access?

Other files and links

Cite this