Automated quantification of retinal vessel morphometry in the UK biobank cohort

on behalf of the UK Biobank Eye and Vision Consortium

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

The morphometric characteristics of the retinal vascular network have been associated with risk markers of many systemic and vascular diseases. However, analysis of data from large population based studies is needed to help resolve uncertainties in these associations. QUARTZ (QUantitative Analysis of Retinal vessel Topology and siZe) is a fully automated retinal image analysis system that has been designed to process large numbers of retinal images and obtains quantitative measures of vessel morphology to be used in epidemiological studies. QUARTZ has been used to process retinal images from UK Biobank which is a large population-based cohort study. In this paper, we address issues of robustness with respect to processing large datasets and validate QUARTZ using a subset of 4,692 UK Biobank retinal images. Ground truth data produced by human observers for validation have been made available online. Following validation, 135,867 retinal images (68,549 participants) from the UK Biobank study were processed by QUARTZ. 71.53% of these images were classified as being of adequate quality, which equated to 80.90% participants with at least one image of adequate quality. The vessel morphometric data are currently being used in epidemiological studies. The intention of the UK Biobank Eye and Vision Consortium is to include these derived measures in the UK Biobank data archive.

Original languageEnglish
Title of host publicationProceedings of the 7th International Conference on Image Processing Theory, Tools and Applications (IPTA 2017)
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Electronic)9781538618417
DOIs
Publication statusPublished - 12 Mar 2018
Event7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017 - Montreal, Canada
Duration: 28 Nov 201701 Dec 2017

Publication series

NameInternational Conference on Image Processing Theory, Tools and Applications (IPTA): Proceedings
PublisherIEEE
ISSN (Electronic)2154-512X

Conference

Conference7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017
CountryCanada
CityMontreal
Period28/11/201701/12/2017

Fingerprint

Retinal Vessels
Image analysis
Epidemiologic Studies
Topology
Processing
Chemical analysis
Vascular Diseases
Population
Uncertainty
Cohort Studies
Datasets
UK-4

Keywords

  • Disease biomarkers
  • Large retinal datasets
  • Retinal image analysis
  • UK Biobank

Cite this

on behalf of the UK Biobank Eye and Vision Consortium (2018). Automated quantification of retinal vessel morphometry in the UK biobank cohort. In Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications (IPTA 2017) (International Conference on Image Processing Theory, Tools and Applications (IPTA): Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IPTA.2017.8310108
on behalf of the UK Biobank Eye and Vision Consortium. / Automated quantification of retinal vessel morphometry in the UK biobank cohort. Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications (IPTA 2017). Institute of Electrical and Electronics Engineers Inc., 2018. (International Conference on Image Processing Theory, Tools and Applications (IPTA): Proceedings).
@inproceedings{85f107ab3aa244af9d84a87349e577fb,
title = "Automated quantification of retinal vessel morphometry in the UK biobank cohort",
abstract = "The morphometric characteristics of the retinal vascular network have been associated with risk markers of many systemic and vascular diseases. However, analysis of data from large population based studies is needed to help resolve uncertainties in these associations. QUARTZ (QUantitative Analysis of Retinal vessel Topology and siZe) is a fully automated retinal image analysis system that has been designed to process large numbers of retinal images and obtains quantitative measures of vessel morphology to be used in epidemiological studies. QUARTZ has been used to process retinal images from UK Biobank which is a large population-based cohort study. In this paper, we address issues of robustness with respect to processing large datasets and validate QUARTZ using a subset of 4,692 UK Biobank retinal images. Ground truth data produced by human observers for validation have been made available online. Following validation, 135,867 retinal images (68,549 participants) from the UK Biobank study were processed by QUARTZ. 71.53{\%} of these images were classified as being of adequate quality, which equated to 80.90{\%} participants with at least one image of adequate quality. The vessel morphometric data are currently being used in epidemiological studies. The intention of the UK Biobank Eye and Vision Consortium is to include these derived measures in the UK Biobank data archive.",
keywords = "Disease biomarkers, Large retinal datasets, Retinal image analysis, UK Biobank",
author = "{on behalf of the UK Biobank Eye and Vision Consortium} and Welikala, {R. A.} and Fraz, {M. M.} and Habib, {M. M.} and S. Daniel-Tong and M. Yates and Foster, {P. J.} and Whincup, {P. H.} and Rudnicka, {A. R.} and Owen, {C. G.} and Strachan, {D. P.} and Barman, {S. A.} and Tariq Aslam and Sarah Barman and {Paul Bishop}, S. and Peter Blows and Catey Bunce and Roxana Carare and Usha Chakravarthy and Michelle Chan and Antonietta Chianca and Valentina Cipriani and David Crabb and Philippa Cumberland and Alexander Day and Parul Desai and Bal Dhillon and Andrew Dick and Paul Foster and John Gallacher and Garway-Heath, {David Ted} and Srini Goverdhan and Jeremy Guggenheim and Priyal Gupta and Chris Hammond and Ruth Hogg and Anne Hughes and Pearse Keane and Khaw, {Sir Peng Tee} and Anthony Khawaja and Gerassimos Lascaratos and Andrew Lotery and Phil Luthert and Tom Mac-Gillivray and Sarah Mackie and Keith Martin and Michelle McGaughey and Bernadette McGuinness and Gareth McKay and Martin McKibbin and Tunde Peto",
year = "2018",
month = "3",
day = "12",
doi = "10.1109/IPTA.2017.8310108",
language = "English",
series = "International Conference on Image Processing Theory, Tools and Applications (IPTA): Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications (IPTA 2017)",

}

on behalf of the UK Biobank Eye and Vision Consortium 2018, Automated quantification of retinal vessel morphometry in the UK biobank cohort. in Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications (IPTA 2017). International Conference on Image Processing Theory, Tools and Applications (IPTA): Proceedings, Institute of Electrical and Electronics Engineers Inc., 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017, Montreal, Canada, 28/11/2017. https://doi.org/10.1109/IPTA.2017.8310108

Automated quantification of retinal vessel morphometry in the UK biobank cohort. / on behalf of the UK Biobank Eye and Vision Consortium.

Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications (IPTA 2017). Institute of Electrical and Electronics Engineers Inc., 2018. (International Conference on Image Processing Theory, Tools and Applications (IPTA): Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Automated quantification of retinal vessel morphometry in the UK biobank cohort

AU - on behalf of the UK Biobank Eye and Vision Consortium

AU - Welikala, R. A.

AU - Fraz, M. M.

AU - Habib, M. M.

AU - Daniel-Tong, S.

AU - Yates, M.

AU - Foster, P. J.

AU - Whincup, P. H.

AU - Rudnicka, A. R.

AU - Owen, C. G.

AU - Strachan, D. P.

AU - Barman, S. A.

AU - Aslam, Tariq

AU - Barman, Sarah

AU - Paul Bishop, S.

AU - Blows, Peter

AU - Bunce, Catey

AU - Carare, Roxana

AU - Chakravarthy, Usha

AU - Chan, Michelle

AU - Chianca, Antonietta

AU - Cipriani, Valentina

AU - Crabb, David

AU - Cumberland, Philippa

AU - Day, Alexander

AU - Desai, Parul

AU - Dhillon, Bal

AU - Dick, Andrew

AU - Foster, Paul

AU - Gallacher, John

AU - Garway-Heath, David Ted

AU - Goverdhan, Srini

AU - Guggenheim, Jeremy

AU - Gupta, Priyal

AU - Hammond, Chris

AU - Hogg, Ruth

AU - Hughes, Anne

AU - Keane, Pearse

AU - Khaw, Sir Peng Tee

AU - Khawaja, Anthony

AU - Lascaratos, Gerassimos

AU - Lotery, Andrew

AU - Luthert, Phil

AU - Mac-Gillivray, Tom

AU - Mackie, Sarah

AU - Martin, Keith

AU - McGaughey, Michelle

AU - McGuinness, Bernadette

AU - McKay, Gareth

AU - McKibbin, Martin

AU - Peto, Tunde

PY - 2018/3/12

Y1 - 2018/3/12

N2 - The morphometric characteristics of the retinal vascular network have been associated with risk markers of many systemic and vascular diseases. However, analysis of data from large population based studies is needed to help resolve uncertainties in these associations. QUARTZ (QUantitative Analysis of Retinal vessel Topology and siZe) is a fully automated retinal image analysis system that has been designed to process large numbers of retinal images and obtains quantitative measures of vessel morphology to be used in epidemiological studies. QUARTZ has been used to process retinal images from UK Biobank which is a large population-based cohort study. In this paper, we address issues of robustness with respect to processing large datasets and validate QUARTZ using a subset of 4,692 UK Biobank retinal images. Ground truth data produced by human observers for validation have been made available online. Following validation, 135,867 retinal images (68,549 participants) from the UK Biobank study were processed by QUARTZ. 71.53% of these images were classified as being of adequate quality, which equated to 80.90% participants with at least one image of adequate quality. The vessel morphometric data are currently being used in epidemiological studies. The intention of the UK Biobank Eye and Vision Consortium is to include these derived measures in the UK Biobank data archive.

AB - The morphometric characteristics of the retinal vascular network have been associated with risk markers of many systemic and vascular diseases. However, analysis of data from large population based studies is needed to help resolve uncertainties in these associations. QUARTZ (QUantitative Analysis of Retinal vessel Topology and siZe) is a fully automated retinal image analysis system that has been designed to process large numbers of retinal images and obtains quantitative measures of vessel morphology to be used in epidemiological studies. QUARTZ has been used to process retinal images from UK Biobank which is a large population-based cohort study. In this paper, we address issues of robustness with respect to processing large datasets and validate QUARTZ using a subset of 4,692 UK Biobank retinal images. Ground truth data produced by human observers for validation have been made available online. Following validation, 135,867 retinal images (68,549 participants) from the UK Biobank study were processed by QUARTZ. 71.53% of these images were classified as being of adequate quality, which equated to 80.90% participants with at least one image of adequate quality. The vessel morphometric data are currently being used in epidemiological studies. The intention of the UK Biobank Eye and Vision Consortium is to include these derived measures in the UK Biobank data archive.

KW - Disease biomarkers

KW - Large retinal datasets

KW - Retinal image analysis

KW - UK Biobank

UR - http://www.scopus.com/inward/record.url?scp=85050700370&partnerID=8YFLogxK

U2 - 10.1109/IPTA.2017.8310108

DO - 10.1109/IPTA.2017.8310108

M3 - Conference contribution

AN - SCOPUS:85050700370

T3 - International Conference on Image Processing Theory, Tools and Applications (IPTA): Proceedings

BT - Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications (IPTA 2017)

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

on behalf of the UK Biobank Eye and Vision Consortium. Automated quantification of retinal vessel morphometry in the UK biobank cohort. In Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications (IPTA 2017). Institute of Electrical and Electronics Engineers Inc. 2018. (International Conference on Image Processing Theory, Tools and Applications (IPTA): Proceedings). https://doi.org/10.1109/IPTA.2017.8310108