Automated Quantification of Retinal Microvasculature from OCT Angiography using Dictionary-Based Vessel Segmentation

Astrid Margareta Elisabet Engberg*, Jesper H. Erichsen, Birgit Sander, Line Kessel, Anders Bjorholm Dahl, Vedrana Andersen Dahl

*Corresponding author for this work

Research output: Contribution to journalConference articleResearchpeer-review

95 Downloads (Pure)

Abstract

Investigations in how the retinal microvasculature correlates with ophthalmological conditions necessitate a method for measuring the microvasculature. Optical coherence tomography angiography (OCTA) depicts the superficial and the deep layer of the retina, but quantification of the microvascular network is still needed. Here, we propose an automatic quantitative analysis of the retinal microvasculature. We use a dictionary-based segmentation to detect larger vessels and capillaries in the retina and we extract features such as densities and vessel radius. The method is validated on repeated OCTA scans from healthy subjects, and we observe high intraclass correlation coecients and high agreement in a Bland-Altman analysis. The quantification method is also applied to pre- and postoperative scans of cataract patients. Here, we observe a higher variation between the measurements, which can be explained by the greater variation in scan quality. Statistical tests of both the healthy subjects and cataract patients show that our method is able to di↵erentiate subjects based on the extracted microvascular features.
Original languageEnglish
Book seriesCommunications in Computer and Information Science
Number of pages12
ISSN1865-0929
Publication statusAccepted/In press - 2019
Event23rd Conference on Medical Image Understanding and Analysis - University of Liverpool, Liverpool, United Kingdom
Duration: 24 Jul 201926 Jul 2019
https://miua2019.com/

Conference

Conference23rd Conference on Medical Image Understanding and Analysis
LocationUniversity of Liverpool
CountryUnited Kingdom
CityLiverpool
Period24/07/201926/07/2019
Internet address

Keywords

  • OCTA
  • Dictionary-based segmentation
  • Quantification

Cite this

@inproceedings{48307c4c574f462aa9f8f6a13acbc3ba,
title = "Automated Quantification of Retinal Microvasculature from OCT Angiography using Dictionary-Based Vessel Segmentation",
abstract = "Investigations in how the retinal microvasculature correlates with ophthalmological conditions necessitate a method for measuring the microvasculature. Optical coherence tomography angiography (OCTA) depicts the superficial and the deep layer of the retina, but quantification of the microvascular network is still needed. Here, we propose an automatic quantitative analysis of the retinal microvasculature. We use a dictionary-based segmentation to detect larger vessels and capillaries in the retina and we extract features such as densities and vessel radius. The method is validated on repeated OCTA scans from healthy subjects, and we observe high intraclass correlation coecients and high agreement in a Bland-Altman analysis. The quantification method is also applied to pre- and postoperative scans of cataract patients. Here, we observe a higher variation between the measurements, which can be explained by the greater variation in scan quality. Statistical tests of both the healthy subjects and cataract patients show that our method is able to di↵erentiate subjects based on the extracted microvascular features.",
keywords = "OCTA, Dictionary-based segmentation, Quantification",
author = "Engberg, {Astrid Margareta Elisabet} and Erichsen, {Jesper H.} and Birgit Sander and Line Kessel and Dahl, {Anders Bjorholm} and Dahl, {Vedrana Andersen}",
year = "2019",
language = "English",
journal = "Communications in Computer and Information Science",
issn = "1865-0929",
publisher = "Springer",

}

TY - GEN

T1 - Automated Quantification of Retinal Microvasculature from OCT Angiography using Dictionary-Based Vessel Segmentation

AU - Engberg, Astrid Margareta Elisabet

AU - Erichsen, Jesper H.

AU - Sander, Birgit

AU - Kessel, Line

AU - Dahl, Anders Bjorholm

AU - Dahl, Vedrana Andersen

PY - 2019

Y1 - 2019

N2 - Investigations in how the retinal microvasculature correlates with ophthalmological conditions necessitate a method for measuring the microvasculature. Optical coherence tomography angiography (OCTA) depicts the superficial and the deep layer of the retina, but quantification of the microvascular network is still needed. Here, we propose an automatic quantitative analysis of the retinal microvasculature. We use a dictionary-based segmentation to detect larger vessels and capillaries in the retina and we extract features such as densities and vessel radius. The method is validated on repeated OCTA scans from healthy subjects, and we observe high intraclass correlation coecients and high agreement in a Bland-Altman analysis. The quantification method is also applied to pre- and postoperative scans of cataract patients. Here, we observe a higher variation between the measurements, which can be explained by the greater variation in scan quality. Statistical tests of both the healthy subjects and cataract patients show that our method is able to di↵erentiate subjects based on the extracted microvascular features.

AB - Investigations in how the retinal microvasculature correlates with ophthalmological conditions necessitate a method for measuring the microvasculature. Optical coherence tomography angiography (OCTA) depicts the superficial and the deep layer of the retina, but quantification of the microvascular network is still needed. Here, we propose an automatic quantitative analysis of the retinal microvasculature. We use a dictionary-based segmentation to detect larger vessels and capillaries in the retina and we extract features such as densities and vessel radius. The method is validated on repeated OCTA scans from healthy subjects, and we observe high intraclass correlation coecients and high agreement in a Bland-Altman analysis. The quantification method is also applied to pre- and postoperative scans of cataract patients. Here, we observe a higher variation between the measurements, which can be explained by the greater variation in scan quality. Statistical tests of both the healthy subjects and cataract patients show that our method is able to di↵erentiate subjects based on the extracted microvascular features.

KW - OCTA

KW - Dictionary-based segmentation

KW - Quantification

M3 - Conference article

JO - Communications in Computer and Information Science

JF - Communications in Computer and Information Science

SN - 1865-0929

ER -