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

doi:10.1136/bjo.2008.149807

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 journal › Article › peer-review

74 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 language	English
Pages (from-to)	706-711
Number of pages	6
Journal	British Journal of Ophthalmology
Volume	94
Issue number	6
Early online date	5 Aug 2009
DOIs	https://doi.org/10.1136/bjo.2008.149807
Publication status	Published - Jun 2010

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

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1136/bjo.2008.149807Licence: Unspecified

Cite this

Fleming, A. D., Goatman, K. A., Philip, S., Williams, G. J., Prescott, G. J., Scotland, G. S., McNamee, P., Leese, G. P., Wykes, W. N., Sharp, P. F., Olson, J. A., & Scottish Diabetic Retinopathy Clinical Research Network (2010). The role of haemorrhage and exudate detection in automated grading of diabetic retinopathy. British Journal of Ophthalmology, 94(6), 706-711. https://doi.org/10.1136/bjo.2008.149807

Fleming, AD, Goatman, KA, Philip, S, Williams, GJ, Prescott, GJ, Scotland, GS , McNamee, P, Leese, GP, Wykes, WN, Sharp, PF , Olson, JA & Scottish Diabetic Retinopathy Clinical Research Network 2010, 'The role of haemorrhage and exudate detection in automated grading of diabetic retinopathy', British Journal of Ophthalmology, vol. 94, no. 6, pp. 706-711. https://doi.org/10.1136/bjo.2008.149807

@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 = jun,

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

SN - 0007-1161

VL - 94

SP - 706

EP - 711

JO - British Journal of Ophthalmology

JF - British Journal of Ophthalmology

IS - 6

ER -

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

Abstract

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this