2D alpha‑shapes to quantify retinal microvasculature morphology and their application to proliferative diabetic retinopathy characterisation in fundus photographs

Emma Pead; Ylenia Giarratano; Andrew Tatham; Miguel O. Bernabeu; Baljean Dhillon; Emanuele Trucco; Tom MacGillivray

doi:https://doi.org/10.1038/s41598-021-02329-5

2D alpha‑shapes to quantify retinal microvasculature morphology and their application to proliferative diabetic retinopathy characterisation in fundus photographs

Emma Pead^*, Ylenia Giarratano, Andrew Tatham, Miguel O. Bernabeu, Baljean Dhillon, Emanuele Trucco, Tom MacGillivray

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract / Description of output

The use of 2D alpha-shapes (α-shapes) to quantify morphological features of the retinal
microvasculature could lead to imaging biomarkers for proliferative diabetic retinopathy (PDR).
We tested our approach using the MESSIDOR dataset that consists of colour fundus photographs
from 547 healthy individuals, 149 with mild diabetic retinopathy (DR), 239 with moderate DR, 199
pre-PDR and 53 PDR. The skeleton (centrelines) of the automatically segmented retinal vasculature
was represented as an α-shape and the proposed parameters, complexity (Opαmin), spread (OpA),
global shape (VS) and presence of abnormal angiogenesis (Gradα) were computed. In cross-sectional
analysis, individuals with PDR had a lower Opαmin, OpA and Gradα indicating a vasculature that is more
complex, less spread (i.e. dense) and the presence of numerous small vessels. The results show that
α-shape parameters characterise vascular abnormalities predictive of PDR (AUC 0.73; 95% CI [0.73
0.74]) and have therefore potential to reveal changes in retinal microvascular morphology.

Original language	English
Article number	22814 (2021)
Journal	Scientific Reports
Volume	11
DOIs	https://doi.org/10.1038/s41598-021-02329-5
Publication status	Published - 24 Nov 2021

Access to Document

https://doi.org/10.1038/s41598-021-02329-5Licence: Creative Commons: Attribution (CC-BY)

s41598-021-02329-5Final published version, 1.71 MBLicence: Creative Commons: Attribution (CC-BY)
41598_2021_Article_2329Final published version, 1.71 MBLicence: Creative Commons: Attribution (CC-BY)

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

Cite this

@article{11db12b6d070496ea62df366d8a84bc2,

title = "2D alpha‑shapes to quantify retinal microvasculature morphology and their application to proliferative diabetic retinopathy characterisation in fundus photographs",

abstract = "The use of 2D alpha-shapes (α-shapes) to quantify morphological features of the retinal microvasculature could lead to imaging biomarkers for proliferative diabetic retinopathy (PDR). We tested our approach using the MESSIDOR dataset that consists of colour fundus photographs from 547 healthy individuals, 149 with mild diabetic retinopathy (DR), 239 with moderate DR, 199 pre-PDR and 53 PDR. The skeleton (centrelines) of the automatically segmented retinal vasculature was represented as an α-shape and the proposed parameters, complexity (Opαmin), spread (OpA), global shape (VS) and presence of abnormal angiogenesis (Gradα) were computed. In cross-sectional analysis, individuals with PDR had a lower Opαmin, OpA and Gradα indicating a vasculature that is more complex, less spread (i.e. dense) and the presence of numerous small vessels. The results show that α-shape parameters characterise vascular abnormalities predictive of PDR (AUC 0.73; 95% CI [0.73 0.74]) and have therefore potential to reveal changes in retinal microvascular morphology.",

author = "Emma Pead and Ylenia Giarratano and Andrew Tatham and Bernabeu, {Miguel O.} and Baljean Dhillon and Emanuele Trucco and Tom MacGillivray",

year = "2021",

month = nov,

day = "24",

doi = "https://doi.org/10.1038/s41598-021-02329-5",

language = "English",

volume = "11",

journal = "Scientific Reports",

issn = "2045-2322",

publisher = "Nature Publishing Group",

}

TY - JOUR

T1 - 2D alpha‑shapes to quantify retinal microvasculature morphology and their application to proliferative diabetic retinopathy characterisation in fundus photographs

AU - Pead, Emma

AU - Giarratano, Ylenia

AU - Tatham, Andrew

AU - Bernabeu, Miguel O.

AU - Dhillon, Baljean

AU - Trucco, Emanuele

AU - MacGillivray, Tom

PY - 2021/11/24

Y1 - 2021/11/24

N2 - The use of 2D alpha-shapes (α-shapes) to quantify morphological features of the retinal microvasculature could lead to imaging biomarkers for proliferative diabetic retinopathy (PDR). We tested our approach using the MESSIDOR dataset that consists of colour fundus photographs from 547 healthy individuals, 149 with mild diabetic retinopathy (DR), 239 with moderate DR, 199 pre-PDR and 53 PDR. The skeleton (centrelines) of the automatically segmented retinal vasculature was represented as an α-shape and the proposed parameters, complexity (Opαmin), spread (OpA), global shape (VS) and presence of abnormal angiogenesis (Gradα) were computed. In cross-sectional analysis, individuals with PDR had a lower Opαmin, OpA and Gradα indicating a vasculature that is more complex, less spread (i.e. dense) and the presence of numerous small vessels. The results show that α-shape parameters characterise vascular abnormalities predictive of PDR (AUC 0.73; 95% CI [0.73 0.74]) and have therefore potential to reveal changes in retinal microvascular morphology.

AB - The use of 2D alpha-shapes (α-shapes) to quantify morphological features of the retinal microvasculature could lead to imaging biomarkers for proliferative diabetic retinopathy (PDR). We tested our approach using the MESSIDOR dataset that consists of colour fundus photographs from 547 healthy individuals, 149 with mild diabetic retinopathy (DR), 239 with moderate DR, 199 pre-PDR and 53 PDR. The skeleton (centrelines) of the automatically segmented retinal vasculature was represented as an α-shape and the proposed parameters, complexity (Opαmin), spread (OpA), global shape (VS) and presence of abnormal angiogenesis (Gradα) were computed. In cross-sectional analysis, individuals with PDR had a lower Opαmin, OpA and Gradα indicating a vasculature that is more complex, less spread (i.e. dense) and the presence of numerous small vessels. The results show that α-shape parameters characterise vascular abnormalities predictive of PDR (AUC 0.73; 95% CI [0.73 0.74]) and have therefore potential to reveal changes in retinal microvascular morphology.

U2 - https://doi.org/10.1038/s41598-021-02329-5

DO - https://doi.org/10.1038/s41598-021-02329-5

M3 - Article

SN - 2045-2322

VL - 11

JO - Scientific Reports

JF - Scientific Reports

M1 - 22814 (2021)

ER -

2D alpha‑shapes to quantify retinal microvasculature morphology and their application to proliferative diabetic retinopathy characterisation in fundus photographs

Abstract / Description of output

Access to Document

Fingerprint

Equipment

Image Analysis Core

Cite this