A framework for the discovery of retinal biomarkers in Optical Coherence Tomography Angiography (OCTA)

Ylenia Giarratano; Alisa Pavel; Jie Lian; Rayna Andreeva; Alessandro Fontanella; Rik Sarkar; Laura J. Reid; Shareen Forbes; Dan Pugh; Tariq Farrah; Neeraj Dhaun; Baljean Dhillon; Tom MacGillivray; Miguel O. Bernabeu

doi:10.1007/978-3-030-63419-3_16

A framework for the discovery of retinal biomarkers in Optical Coherence Tomography Angiography (OCTA)

Ylenia Giarratano, Alisa Pavel, Jie Lian, Rayna Andreeva, Alessandro Fontanella, Rik Sarkar, Laura J. Reid, Shareen Forbes, Dan Pugh, Tariq Farrah, Neeraj Dhaun, Baljean Dhillon, Tom MacGillivray, Miguel O. Bernabeu

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

Abstract / Description of output

Recent studies have demonstrated the potential of OCTA retinal imaging for the discovery of biomarkers of vascular disease of the eye and other organs. Furthermore, advances in deep learning have made it possible to train algorithms for the automated detection of such biomarkers. However, two key limitations of this approach are the need for large numbers of labeled images to train the algorithms, which are often not met by the typical single-centre prospective studies in the literature, and the lack of interpretability of the features learned during training. In the current study, we developed a network analysis framework to characterise retinal vasculature where geometric and topological information are exploited to increase the performance of classifiers trained on tens of OCTA images. We demonstrate our approach in two different diseases with a retinal vascular footprint: diabetic retinopathy (DR) and chronic kidney disease (CKD). Our approach enables the discovery of previously unreported retinal vascular morphological differences in DR and CKD, and demonstrate the potential of OCTA for automated disease assessment.

Original language	English
Title of host publication	Ophthalmic Medical Image Analysis (OMIA 2020)
Editors	Huazhu Fu, Mona K. Garvin, Tom MacGillivray, Yanwu Xu, Yalin Zheng
Publisher	Springer
Pages	155-164
Number of pages	10
ISBN (Electronic)	978-3-030-63419-3
ISBN (Print)	978-3-030-63418-6
DOIs	https://doi.org/10.1007/978-3-030-63419-3_16
Publication status	Published - 20 Nov 2020
Event	7th MICCAI Workshop on Ophthalmic Medical Image Analysis - Lima, Peru Duration: 8 Oct 2020 → 8 Oct 2020 https://sites.google.com/view/omia7/home?authuser=0

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	12069
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Workshop

Workshop	7th MICCAI Workshop on Ophthalmic Medical Image Analysis
Abbreviated title	OMIA7
Country/Territory	Peru
City	Lima
Period	8/10/20 → 8/10/20
Internet address	https://sites.google.com/view/omia7/home?authuser=0

Keywords / Materials (for Non-textual outputs)

Optical coherence tomography angiography
Vascular network
Graph analysis
Retinal biomarkers

Access to Document

10.1007/978-3-030-63419-3_16Licence: All Rights Reserved

A framework for the_GIARRATANO_DOA12082020_AFVAccepted author manuscript, 3.03 MBLicence: All Rights Reserved

https://link.springer.com/chapter/10.1007/978-3-030-63419-3_16Licence: All Rights Reserved

Image Analysis Core
Tom MacGillivray (Manager) & Calum Gray (Other)
Work Enabled by Edinburgh Clinical Research Facility
Facility/equipment: Facility

Cite this

Giarratano, Y., Pavel, A., Lian, J., Andreeva, R., Fontanella, A., Sarkar, R., Reid, L. J., Forbes, S., Pugh, D., Farrah, T., Dhaun, N., Dhillon, B., MacGillivray, T., & Bernabeu, M. O. (2020). A framework for the discovery of retinal biomarkers in Optical Coherence Tomography Angiography (OCTA). In H. Fu, M. K. Garvin, T. MacGillivray, Y. Xu, & Y. Zheng (Eds.), Ophthalmic Medical Image Analysis (OMIA 2020) (pp. 155-164). (Lecture Notes in Computer Science ; Vol. 12069). Springer. https://doi.org/10.1007/978-3-030-63419-3_16

@inproceedings{7455ac11909e4aaaa4144984c4990ab1,

title = "A framework for the discovery of retinal biomarkers in Optical Coherence Tomography Angiography (OCTA)",

abstract = "Recent studies have demonstrated the potential of OCTA retinal imaging for the discovery of biomarkers of vascular disease of the eye and other organs. Furthermore, advances in deep learning have made it possible to train algorithms for the automated detection of such biomarkers. However, two key limitations of this approach are the need for large numbers of labeled images to train the algorithms, which are often not met by the typical single-centre prospective studies in the literature, and the lack of interpretability of the features learned during training. In the current study, we developed a network analysis framework to characterise retinal vasculature where geometric and topological information are exploited to increase the performance of classifiers trained on tens of OCTA images. We demonstrate our approach in two different diseases with a retinal vascular footprint: diabetic retinopathy (DR) and chronic kidney disease (CKD). Our approach enables the discovery of previously unreported retinal vascular morphological differences in DR and CKD, and demonstrate the potential of OCTA for automated disease assessment.",

keywords = "Optical coherence tomography angiography, Vascular network, Graph analysis, Retinal biomarkers",

author = "Ylenia Giarratano and Alisa Pavel and Jie Lian and Rayna Andreeva and Alessandro Fontanella and Rik Sarkar and Reid, {Laura J.} and Shareen Forbes and Dan Pugh and Tariq Farrah and Neeraj Dhaun and Baljean Dhillon and Tom MacGillivray and Bernabeu, {Miguel O.}",

year = "2020",

month = nov,

day = "20",

doi = "10.1007/978-3-030-63419-3_16",

language = "English",

isbn = "978-3-030-63418-6",

series = "Lecture Notes in Computer Science ",

publisher = "Springer",

pages = "155--164",

editor = "Huazhu Fu and Garvin, {Mona K.} and Tom MacGillivray and Yanwu Xu and Yalin Zheng",

booktitle = "Ophthalmic Medical Image Analysis (OMIA 2020)",

note = "7th MICCAI Workshop on Ophthalmic Medical Image Analysis , OMIA7 ; Conference date: 08-10-2020 Through 08-10-2020",

url = "https://sites.google.com/view/omia7/home?authuser=0",

}

Giarratano, Y, Pavel, A, Lian, J, Andreeva, R, Fontanella, A, Sarkar, R, Reid, LJ, Forbes, S, Pugh, D, Farrah, T, Dhaun, N , Dhillon, B , MacGillivray, T & Bernabeu, MO 2020, A framework for the discovery of retinal biomarkers in Optical Coherence Tomography Angiography (OCTA). in H Fu, MK Garvin, T MacGillivray, Y Xu & Y Zheng (eds), Ophthalmic Medical Image Analysis (OMIA 2020). Lecture Notes in Computer Science , vol. 12069, Springer, pp. 155-164, 7th MICCAI Workshop on Ophthalmic Medical Image Analysis , Lima, Peru, 8/10/20. https://doi.org/10.1007/978-3-030-63419-3_16

A framework for the discovery of retinal biomarkers in Optical Coherence Tomography Angiography (OCTA). / Giarratano, Ylenia; Pavel, Alisa; Lian, Jie et al.
Ophthalmic Medical Image Analysis (OMIA 2020). ed. / Huazhu Fu; Mona K. Garvin; Tom MacGillivray; Yanwu Xu; Yalin Zheng. Springer, 2020. p. 155-164 (Lecture Notes in Computer Science ; Vol. 12069).

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

TY - GEN

T1 - A framework for the discovery of retinal biomarkers in Optical Coherence Tomography Angiography (OCTA)

AU - Giarratano, Ylenia

AU - Pavel, Alisa

AU - Lian, Jie

AU - Andreeva, Rayna

AU - Fontanella, Alessandro

AU - Sarkar, Rik

AU - Reid, Laura J.

AU - Forbes, Shareen

AU - Pugh, Dan

AU - Farrah, Tariq

AU - Dhaun, Neeraj

AU - Dhillon, Baljean

AU - MacGillivray, Tom

AU - Bernabeu, Miguel O.

PY - 2020/11/20

Y1 - 2020/11/20

N2 - Recent studies have demonstrated the potential of OCTA retinal imaging for the discovery of biomarkers of vascular disease of the eye and other organs. Furthermore, advances in deep learning have made it possible to train algorithms for the automated detection of such biomarkers. However, two key limitations of this approach are the need for large numbers of labeled images to train the algorithms, which are often not met by the typical single-centre prospective studies in the literature, and the lack of interpretability of the features learned during training. In the current study, we developed a network analysis framework to characterise retinal vasculature where geometric and topological information are exploited to increase the performance of classifiers trained on tens of OCTA images. We demonstrate our approach in two different diseases with a retinal vascular footprint: diabetic retinopathy (DR) and chronic kidney disease (CKD). Our approach enables the discovery of previously unreported retinal vascular morphological differences in DR and CKD, and demonstrate the potential of OCTA for automated disease assessment.

AB - Recent studies have demonstrated the potential of OCTA retinal imaging for the discovery of biomarkers of vascular disease of the eye and other organs. Furthermore, advances in deep learning have made it possible to train algorithms for the automated detection of such biomarkers. However, two key limitations of this approach are the need for large numbers of labeled images to train the algorithms, which are often not met by the typical single-centre prospective studies in the literature, and the lack of interpretability of the features learned during training. In the current study, we developed a network analysis framework to characterise retinal vasculature where geometric and topological information are exploited to increase the performance of classifiers trained on tens of OCTA images. We demonstrate our approach in two different diseases with a retinal vascular footprint: diabetic retinopathy (DR) and chronic kidney disease (CKD). Our approach enables the discovery of previously unreported retinal vascular morphological differences in DR and CKD, and demonstrate the potential of OCTA for automated disease assessment.

KW - Optical coherence tomography angiography

KW - Vascular network

KW - Graph analysis

KW - Retinal biomarkers

U2 - 10.1007/978-3-030-63419-3_16

DO - 10.1007/978-3-030-63419-3_16

M3 - Conference contribution

SN - 978-3-030-63418-6

T3 - Lecture Notes in Computer Science

SP - 155

EP - 164

BT - Ophthalmic Medical Image Analysis (OMIA 2020)

A2 - Fu, Huazhu

A2 - Garvin, Mona K.

A2 - MacGillivray, Tom

A2 - Xu, Yanwu

A2 - Zheng, Yalin

PB - Springer

T2 - 7th MICCAI Workshop on Ophthalmic Medical Image Analysis

Y2 - 8 October 2020 through 8 October 2020

ER -

Giarratano Y, Pavel A, Lian J, Andreeva R, Fontanella A, Sarkar R et al. A framework for the discovery of retinal biomarkers in Optical Coherence Tomography Angiography (OCTA). In Fu H, Garvin MK, MacGillivray T, Xu Y, Zheng Y, editors, Ophthalmic Medical Image Analysis (OMIA 2020). Springer. 2020. p. 155-164. (Lecture Notes in Computer Science ). doi: 10.1007/978-3-030-63419-3_16

A framework for the discovery of retinal biomarkers in Optical Coherence Tomography Angiography (OCTA)

Abstract / Description of output

Publication series

Workshop

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Equipment

Image Analysis Core

Cite this