Automated detection and differentiation of drusen, exudates, and cotton-wool spots in digital color fundus photographs for diabetic retinopathy diagnosis
- PMID: 17460289
- PMCID: PMC2739583
- DOI: 10.1167/iovs.06-0996
Automated detection and differentiation of drusen, exudates, and cotton-wool spots in digital color fundus photographs for diabetic retinopathy diagnosis
Abstract
Purpose: To describe and evaluate a machine learning-based, automated system to detect exudates and cotton-wool spots in digital color fundus photographs and differentiate them from drusen, for early diagnosis of diabetic retinopathy.
Methods: Three hundred retinal images from one eye of 300 patients with diabetes were selected from a diabetic retinopathy telediagnosis database (nonmydriatic camera, two-field photography): 100 with previously diagnosed bright lesions and 200 without. A machine learning computer program was developed that can identify and differentiate among drusen, (hard) exudates, and cotton-wool spots. A human expert standard for the 300 images was obtained by consensus annotation by two retinal specialists. Sensitivities and specificities of the annotations on the 300 images by the automated system and a third retinal specialist were determined.
Results: The system achieved an area under the receiver operating characteristic (ROC) curve of 0.95 and sensitivity/specificity pairs of 0.95/0.88 for the detection of bright lesions of any type, and 0.95/0.86, 0.70/0.93, and 0.77/0.88 for the detection of exudates, cotton-wool spots, and drusen, respectively. The third retinal specialist achieved pairs of 0.95/0.74 for bright lesions and 0.90/0.98, 0.87/0.98, and 0.92/0.79 per lesion type.
Conclusions: A machine learning-based, automated system capable of detecting exudates and cotton-wool spots and differentiating them from drusen in color images obtained in community based diabetic patients has been developed and approaches the performance level of retinal experts. If the machine learning can be improved with additional training data sets, it may be useful for detecting clinically important bright lesions, enhancing early diagnosis, and reducing visual loss in patients with diabetes.
Figures
![Figure 1](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/2739583/bin/nihms52354f1.gif)
![Figure 2](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/2739583/bin/nihms52354f2.gif)
![Figure 3](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/2739583/bin/nihms52354f3.gif)
Similar articles
-
Image quality assessment of retinal fundus photographs for diabetic retinopathy in the machine learning era: a review.Eye (Lond). 2024 Feb;38(3):426-433. doi: 10.1038/s41433-023-02717-3. Epub 2023 Sep 4. Eye (Lond). 2024. PMID: 37667028 Review.
-
Automated System for Referral of Cotton-Wool Spots.Curr Diabetes Rev. 2018;14(2):168-174. doi: 10.2174/1573399812666161201114309. Curr Diabetes Rev. 2018. PMID: 27908249
-
A Review on Recent Developments for Detection of Diabetic Retinopathy.Scientifica (Cairo). 2016;2016:6838976. doi: 10.1155/2016/6838976. Epub 2016 Sep 29. Scientifica (Cairo). 2016. PMID: 27777811 Free PMC article. Review.
-
Detection of Hard Exudates in Colour Fundus Images Using Fuzzy Support Vector Machine-Based Expert System.J Digit Imaging. 2015 Dec;28(6):761-8. doi: 10.1007/s10278-015-9793-5. J Digit Imaging. 2015. PMID: 25822397 Free PMC article.
-
Automated detection of fundus photographic red lesions in diabetic retinopathy.Invest Ophthalmol Vis Sci. 2003 Feb;44(2):761-6. doi: 10.1167/iovs.02-0418. Invest Ophthalmol Vis Sci. 2003. PMID: 12556411
Cited by
-
An effective and comprehensible method to detect and evaluate retinal damage due to diabetes complications.PeerJ Comput Sci. 2023 Sep 26;9:e1585. doi: 10.7717/peerj-cs.1585. eCollection 2023. PeerJ Comput Sci. 2023. PMID: 37810367 Free PMC article.
-
Automated Detection and Segmentation of Exudates for the Screening of Background Retinopathy.J Healthc Eng. 2023 Jul 14;2023:4537253. doi: 10.1155/2023/4537253. eCollection 2023. J Healthc Eng. 2023. Retraction in: J Healthc Eng. 2023 Nov 29;2023:9867197. doi: 10.1155/2023/9867197. PMID: 37483301 Free PMC article. Retracted.
-
Automated Diagnosis of Diabetic Retinopathy Using Deep Learning: On the Search of Segmented Retinal Blood Vessel Images for Better Performance.Bioengineering (Basel). 2023 Mar 26;10(4):413. doi: 10.3390/bioengineering10040413. Bioengineering (Basel). 2023. PMID: 37106599 Free PMC article.
-
Everything real about unreal artificial intelligence in diabetic retinopathy and in ocular pathologies.World J Diabetes. 2022 Oct 15;13(10):822-834. doi: 10.4239/wjd.v13.i10.822. World J Diabetes. 2022. PMID: 36311999 Free PMC article. Review.
-
Weakly Supervised Sensitive Heatmap framework to classify and localize diabetic retinopathy lesions.Sci Rep. 2021 Dec 8;11(1):23631. doi: 10.1038/s41598-021-02834-7. Sci Rep. 2021. PMID: 34880311 Free PMC article.
References
-
- Klonoff DC, Schwartz DM. An economic analysis of interventions for diabetes. Diabetes Care. 2000;23:390–404. - PubMed
-
- Kinyoun J, Barton F, Fisher M, Hubbard L, Aiello L, Ferris F., III Detection of diabetic macular edema. Ophthalmoscopy versus photography--Early Treatment Diabetic Retinopathy Study Report Number 5. The ETDRS Research Group. Ophthalmology. 1989;96:746–750. - PubMed
-
- Early Treatment Diabetic Retinopathy Study Research Group. Early photocoagulation for diabetic retinopathy. ETDRS report number 9. Ophthalmology. 1991;98:766–785. - PubMed
-
- Bresnick GH, Mukamel DB, Dickinson JC, Cole DR. A screening approach to the surveillance of patients with diabetes for the presence of vision-threatening retinopathy. Ophthalmology. 2000;107:19–24. - PubMed
-
- Wilson C, Horton M, Cavallerano J, Aiello LM. The Use of Retinal Imaging Technology Increases the Rates of Screening and Treatment of Diabetic Retinopathy. Diabetes Care [IN PRINT, GET FROM MEDLINE] 2004 - PubMed
Publication types
MeSH terms
Grants and funding
LinkOut - more resources
Full Text Sources
Other Literature Sources
Medical