The role of haemorrhage and exudate detection in automated grading of diabetic retinopathy

Alan D Fleming, Keith A Goatman, Sam Philip, Graeme J Williams, Gordon J Prescott, Graham S Scotland, Paul McNamee, Graham P Leese, William N Wykes, Peter F Sharp, John A Olson, Scottish Diabetic Retinopathy Clinical Research Network

Research output: Contribution to journalArticle

54 Citations (Scopus)

Abstract

Background/aims: Automated grading has the potential to improve the efficiency of diabetic retinopathy screening services. While disease/no disease grading can be performed using only microaneurysm detection and image-quality assessment, automated recognition of other types of lesions may be advantageous. This study investigated whether inclusion of automated recognition of exudates and haemorrhages improves the detection of observable/referable diabetic retinopathy.

Methods: Images from 1253 patients with observable/referable retinopathy and 6333 patients with non-referable retinopathy were obtained from three grading centres. All images were reference-graded, and automated disease/no disease assessments were made based on microaneurysm detection and combined microaneurysm, exudate and haemorrhage detection.

Results: Introduction of algorithms for exudates and haemorrhages resulted in a statistically significant increase in the sensitivity for detection of observable/referable retinopathy from 94.9% (95% CI 93.5 to 96.0) to 96.6% (95.4 to 97.4) without affecting manual grading workload.

Conclusion: Automated detection of exudates and haemorrhages improved the detection of observable/referable retinopathy.

Original languageEnglish
Pages (from-to)706-711
Number of pages6
JournalBritish Journal of Ophthalmology
Volume94
Issue number6
Early online date5 Aug 2009
DOIs
Publication statusPublished - Jun 2010

Fingerprint

Diabetic Retinopathy
Exudates and Transudates
Hemorrhage
Workload
Microaneurysm

Keywords

  • algorithms
  • diabetic retinopathy
  • diagnosis, computer-assisted
  • diagnostic techniques, ophthalmological
  • exudates and transudates
  • humans
  • image interpretation, computer-assisted
  • mass screening
  • reference standards
  • retinal hemorrhage
  • severity of illness index

Cite this

The role of haemorrhage and exudate detection in automated grading of diabetic retinopathy. / Fleming, Alan D; Goatman, Keith A; Philip, Sam; Williams, Graeme J; Prescott, Gordon J; Scotland, Graham S; McNamee, Paul; Leese, Graham P; Wykes, William N; Sharp, Peter F; Olson, John A; Scottish Diabetic Retinopathy Clinical Research Network.

In: British Journal of Ophthalmology, Vol. 94, No. 6, 06.2010, p. 706-711.

Research output: Contribution to journalArticle

Fleming, Alan D ; Goatman, Keith A ; Philip, Sam ; Williams, Graeme J ; Prescott, Gordon J ; Scotland, Graham S ; McNamee, Paul ; Leese, Graham P ; Wykes, William N ; Sharp, Peter F ; Olson, John A ; Scottish Diabetic Retinopathy Clinical Research Network. / The role of haemorrhage and exudate detection in automated grading of diabetic retinopathy. In: British Journal of Ophthalmology. 2010 ; Vol. 94, No. 6. pp. 706-711.
@article{f89a87df16544417b689d47a18b25ebc,
title = "The role of haemorrhage and exudate detection in automated grading of diabetic retinopathy",
abstract = "Background/aims: Automated grading has the potential to improve the efficiency of diabetic retinopathy screening services. While disease/no disease grading can be performed using only microaneurysm detection and image-quality assessment, automated recognition of other types of lesions may be advantageous. This study investigated whether inclusion of automated recognition of exudates and haemorrhages improves the detection of observable/referable diabetic retinopathy.Methods: Images from 1253 patients with observable/referable retinopathy and 6333 patients with non-referable retinopathy were obtained from three grading centres. All images were reference-graded, and automated disease/no disease assessments were made based on microaneurysm detection and combined microaneurysm, exudate and haemorrhage detection.Results: Introduction of algorithms for exudates and haemorrhages resulted in a statistically significant increase in the sensitivity for detection of observable/referable retinopathy from 94.9{\%} (95{\%} CI 93.5 to 96.0) to 96.6{\%} (95.4 to 97.4) without affecting manual grading workload.Conclusion: Automated detection of exudates and haemorrhages improved the detection of observable/referable retinopathy.",
keywords = "algorithms, diabetic retinopathy, diagnosis, computer-assisted, diagnostic techniques, ophthalmological, exudates and transudates, humans, image interpretation, computer-assisted, mass screening, reference standards, retinal hemorrhage, severity of illness index",
author = "Fleming, {Alan D} and Goatman, {Keith A} and Sam Philip and Williams, {Graeme J} and Prescott, {Gordon J} and Scotland, {Graham S} and Paul McNamee and Leese, {Graham P} and Wykes, {William N} and Sharp, {Peter F} and Olson, {John A} and {Scottish Diabetic Retinopathy Clinical Research Network}",
year = "2010",
month = "6",
doi = "10.1136/bjo.2008.149807",
language = "English",
volume = "94",
pages = "706--711",
journal = "British Journal of Ophthalmology",
issn = "0007-1161",
publisher = "BMJ Publishing Group",
number = "6",

}

TY - JOUR

T1 - The role of haemorrhage and exudate detection in automated grading of diabetic retinopathy

AU - Fleming, Alan D

AU - Goatman, Keith A

AU - Philip, Sam

AU - Williams, Graeme J

AU - Prescott, Gordon J

AU - Scotland, Graham S

AU - McNamee, Paul

AU - Leese, Graham P

AU - Wykes, William N

AU - Sharp, Peter F

AU - Olson, John A

AU - Scottish Diabetic Retinopathy Clinical Research Network

PY - 2010/6

Y1 - 2010/6

N2 - Background/aims: Automated grading has the potential to improve the efficiency of diabetic retinopathy screening services. While disease/no disease grading can be performed using only microaneurysm detection and image-quality assessment, automated recognition of other types of lesions may be advantageous. This study investigated whether inclusion of automated recognition of exudates and haemorrhages improves the detection of observable/referable diabetic retinopathy.Methods: Images from 1253 patients with observable/referable retinopathy and 6333 patients with non-referable retinopathy were obtained from three grading centres. All images were reference-graded, and automated disease/no disease assessments were made based on microaneurysm detection and combined microaneurysm, exudate and haemorrhage detection.Results: Introduction of algorithms for exudates and haemorrhages resulted in a statistically significant increase in the sensitivity for detection of observable/referable retinopathy from 94.9% (95% CI 93.5 to 96.0) to 96.6% (95.4 to 97.4) without affecting manual grading workload.Conclusion: Automated detection of exudates and haemorrhages improved the detection of observable/referable retinopathy.

AB - Background/aims: Automated grading has the potential to improve the efficiency of diabetic retinopathy screening services. While disease/no disease grading can be performed using only microaneurysm detection and image-quality assessment, automated recognition of other types of lesions may be advantageous. This study investigated whether inclusion of automated recognition of exudates and haemorrhages improves the detection of observable/referable diabetic retinopathy.Methods: Images from 1253 patients with observable/referable retinopathy and 6333 patients with non-referable retinopathy were obtained from three grading centres. All images were reference-graded, and automated disease/no disease assessments were made based on microaneurysm detection and combined microaneurysm, exudate and haemorrhage detection.Results: Introduction of algorithms for exudates and haemorrhages resulted in a statistically significant increase in the sensitivity for detection of observable/referable retinopathy from 94.9% (95% CI 93.5 to 96.0) to 96.6% (95.4 to 97.4) without affecting manual grading workload.Conclusion: Automated detection of exudates and haemorrhages improved the detection of observable/referable retinopathy.

KW - algorithms

KW - diabetic retinopathy

KW - diagnosis, computer-assisted

KW - diagnostic techniques, ophthalmological

KW - exudates and transudates

KW - humans

KW - image interpretation, computer-assisted

KW - mass screening

KW - reference standards

KW - retinal hemorrhage

KW - severity of illness index

U2 - 10.1136/bjo.2008.149807

DO - 10.1136/bjo.2008.149807

M3 - Article

C2 - 19661069

VL - 94

SP - 706

EP - 711

JO - British Journal of Ophthalmology

JF - British Journal of Ophthalmology

SN - 0007-1161

IS - 6

ER -