Abstract
Purpose
The study aims to classify the eyes with proliferative diabetic retinopathy (PDR) and non-proliferative diabetic retinopathy (NPDR) based on the optical coherence tomography angiography (OCTA) vascular density maps using a supervised machine learning algorithm.
Methods
OCTA vascular density maps (at superficial capillary plexus (SCP), deep capillary plexus (DCP), and total retina (R) levels) of 148 eyes from 78 patients with diabetic retinopathy (45 PDR and 103 NPDR) was used to classify the images to NPDR and PDR groups based on a supervised machine learning algorithm known as the support vector machine (SVM) classifier optimized by a genetic evolutionary algorithm.
Results
The implemented algorithm in three different models reached up to 85% accuracy in classifying PDR and NPDR in all three levels of vascular density maps. The deep retinal layer vascular density map demonstrated the best performance with a 90% accuracy in discriminating between PDR and NPDR.
Conclusions
The current study on a limited number of patients with diabetic retinopathy demonstrated that a supervised machine learning–based method known as SVM can be used to differentiate PDR and NPDR patients using OCTA vascular density maps.
Similar content being viewed by others
Data availability
The data generated during or/and analyzed during the current study are available from the corresponding author.
References
Solomon SD, Chew E, Duh EJ et al (2017) Diabetic retinopathy: a position statement by the American Diabetes Association. Diabetes Care 40:412–418. https://doi.org/10.2337/dc16-2641
Kobrin Klein BE (2007) Overview of epidemiologic studies of diabetic retinopathy. Ophthalmic Epidemiol 14:179–183. https://doi.org/10.1080/09286580701396720
Antonetti DA, Klein R, Gardner TW (2012) Diabetic retinopathy. N Engl J Med 366:1227–1239. https://doi.org/10.1056/nejmra1005073
Cheung N, Mitchell P, Wong TY (2010) Diabetic retinopathy. Lancet 376:124–136. https://doi.org/10.1016/s0140-6736(09)62124-3
(1976) Preliminary report on effects of photocoagulation therapy. Am J Ophthalmol 81:397–402. https://doi.org/10.1016/0002-9394(76)90292-0
Riaskoff S (1981) Photocoagulation treatment of proliferative diabetic retinopathy. Bull Soc Belge Ophtalmol 197:9–17. https://doi.org/10.1016/s0161-6420(81)34978-1
(1985) Photocoagulation For Diabetic Macular Edema: Early Treatment Diabetic Retinopathy Study Report Number 1 Early Treatment Diabetic Retinopathy Study Research Group. Arch Ophthalmol 103:1796–1806. https://doi.org/10.1001/archopht.1985.01050120030015
Edwards P (2010) Randomized trial evaluating ranibizumab plus prompt or deferred laser or triamcinolone plus prompt laser for diabetic macular edema. Acta Ophthalmol 88:0. https://doi.org/10.1111/j.1755-3768.2010.4111.x
Vander JF (2011) A prospective randomized trial of intravitreal bevacizumab or laser therapy in the management of diabetic macular edema (BOLT study): 12-month data: report 2. Yearb Ophthalmol 2011:123–124. https://doi.org/10.1016/j.yoph.2010.12.006
Brucker AJ, Qin H, Antoszyk AN et al (2009) Observational study of the development of diabetic macular edema following panretinal (scatter) photocoagulation given in 1 or 4 sittings. Arch Ophthalmol 127:132–140. https://doi.org/10.1001/archophthalmol.2008.565
Faghihi H, Riazi-Esfahani H, Khodabande A et al (2021) Effect of panretinal photocoagulation on macular vasculature using optical coherence tomography angiography. Eur J Ophthalmol 31:1877–1884
Falavarjani K, Khadamy J, Aghdam K (2018) An update on optical coherence tomography angiography in diabetic retinopathy. J Ophthalmic Vis Res 13:487. https://doi.org/10.4103/jovr.jovr_57_18
Mirshahi R, Riazi-Esfahani H, Khalili Pour E et al (2021) Differentiating features of OCT angiography in diabetic macular edema. Sci Rep 11(1):23398. https://doi.org/10.1038/s41598-021-02859-y
Falavarjani KG, Sarraf D (2017) Optical coherence tomography angiography of the retina and choroid; current applications and future directions. J Curr Ophthalmol 29:1–4. https://doi.org/10.1016/j.joco.2017.02.005
Gulshan V, Peng L, Coram M et al (2016) Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316:2402. https://doi.org/10.1001/jama.2016.17216
Abràmoff MD, Lou Y, Erginay A et al (2016) Improved automated detection of diabetic retinopathy on a publicly available dataset through integration of deep learning. Investig Opthalmology Vis Sci 57:5200. https://doi.org/10.1167/iovs.16-19964
Ghazal M, Ali SS, Mahmoud AH et al (2020) Accurate detection of non-proliferative diabetic retinopathy in optical coherence tomography images using convolutional neural networks. IEEE Access 8:34387–34397. https://doi.org/10.1109/access.2020.2974158
Alam M, Zhang Y, Lim JI et al (2020) Quantitative optical coherence tomography angiography features for objective classification and staging of diabetic retinopathy. Retina 40:322–332. https://doi.org/10.1097/iae.0000000000002373
Heisler M, Karst S, Lo J et al (2020) Ensemble deep learning for diabetic retinopathy detection using optical coherence tomography angiography. Transl Vis Sci Technol 9:20. https://doi.org/10.1167/tvst.9.2.20
Zang P, Gao L, Hormel TT et al (2021) DcardNet: diabetic retinopathy classification at multiple levels based on structural and angiographic optical coherence tomography. IEEE Trans Biomed Eng 68:1859–1870. https://doi.org/10.1109/tbme.2020.3027231
Gargeya R, Leng T (2017) Automated identification of diabetic retinopathy using deep learning. Ophthalmology 124:962–969. https://doi.org/10.1016/j.ophtha.2017.02.008
Usman Akram M, Khalid S, Tariq A et al (2014) Detection and classification of retinal lesions for grading of diabetic retinopathy. Comput Biol Med 45:161–171. https://doi.org/10.1016/j.compbiomed.2013.11.014
Ruamviboonsuk P, Krause J, Chotcomwongse P, et al (2019) Deep learning versus human graders for classifying diabetic retinopathy severity in a nationwide screening program. npj Digit Med 2:. https://doi.org/10.1038/s41746-019-0099-8
Eladawi N, Elmogy M, Ghazal M et al (2019) Early signs detection of diabetic retinopathy using optical coherence tomography angiography scans based on 3D multi-path convolutional neural network. 2019 IEEE International Conference on Image Processing (ICIP): 1390–1394. https://doi.org/10.1109/ICIP.2019.8803031
Sandhu HS, Eladawi N, Elmogy M et al (2018) Automated diabetic retinopathy detection using optical coherence tomography angiography: a pilot study. Br J Ophthalmol 102:1564–1569. https://doi.org/10.1136/bjophthalmol-2017-311489
Sandhu HS, Elmogy M, Taher Sharafeldeen A et al (2020) Automated diagnosis of diabetic retinopathy using clinical biomarkers, optical coherence tomography, and optical coherence tomography angiography. Am J Ophthalmol 216:201–206. https://doi.org/10.1016/j.ajo.2020.01.016
ElTanboly A, Ismail M, Shalaby A et al (2017) A computer-aided diagnostic system for detecting diabetic retinopathy in optical coherence tomography images. Med Phys 44:914–923. https://doi.org/10.1002/mp.12071
Sandhu HS, Eltanboly A, Shalaby A et al (2018) Automated diagnosis and grading of diabetic retinopathy using optical coherence tomography. Investig Opthalmology Vis Sci 59:3155. https://doi.org/10.1167/iovs.17-23677
Yang W, Wang K, Zuo W (2012) Neighborhood component feature selection for high-dimensional data. J Comput 7. https://doi.org/10.4304/jcp.7.1.161-168
Suthaharan S (2016) Support vector machine. Machine learning models and algorithms for big data classification. Springer, Boston, pp 207–235. https://doi.org/10.1007/978-1-4899-7641-3_9
Whitley D (1994) A genetic algorithm tutorial. Stat Comput 4:. https://doi.org/10.1007/bf00175354
Flaxel CJ, Adelman RA, Bailey ST et al (2020) Diabetic retinopathy preferred practice pattern®. Ophthalmology 127:66–145. https://doi.org/10.1016/j.ophtha.2019.09.025
Idris I, Sellahewa L, Simpson C et al (2014) Grader agreement, and sensitivity and specificity of digital photography in a community optometry-based diabetic eye screening program. Clin Ophthalmol 8:1345–9. https://doi.org/10.2147/opth.s61483
Ruamviboonsuk P, Teerasuwanajak K, Tiensuwan M, Yuttitham K (2006) Interobserver agreement in the interpretation of single-field digital fundus images for diabetic retinopathy screening. Ophthalmology 113:826–832. https://doi.org/10.1016/j.ophtha.2005.11.021
World Health Organization, PEPFAR & UNAIDS (2007) Task shifting: rational redistribution of tasks among health workforce teams: global recommendations and guidelines. World Health Organization. https://apps.who.int/iris/handle/10665/43821
Wang LZ, Cheung CY, Tapp RJ et al (2017) Availability and variability in guidelines on diabetic retinopathy screening in Asian countries. Br J Ophthalmol 101:1352–1360. https://doi.org/10.1136/bjophthalmol-2016-310002
van der Heijden AA, Abramoff MD, Verbraak F et al (2017) Validation of automated screening for referable diabetic retinopathy with the IDx-DR device in the Hoorn Diabetes Care System. Acta Ophthalmol 96:63–68. https://doi.org/10.1111/aos.13613
Ting DSW, Cheung CY-L, Lim G et al (2017) Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA 318:2211. https://doi.org/10.1001/jama.2017.18152
Esteva A, Kuprel B, Novoa RA et al (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542:115–118. https://doi.org/10.1038/nature21056
Shen D, Wu G, Suk H-I (2017) Deep learning in medical image analysis. Annu Rev Biomed Eng 19:221–248. https://doi.org/10.1146/annurev-bioeng-071516-044442
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444. https://doi.org/10.1038/nature14539
Silver D, Schrittwieser J, Simonyan K et al (2017) Mastering the game of Go without human knowledge. Nature 550:354–359. https://doi.org/10.1038/nature24270
Sun JK (2019) Clinical applicability of assessing peripheral nonperfusion on ultra-widefield angiography. JAMA Ophthalmol 137:632. https://doi.org/10.1001/jamaophthalmol.2019.0411
Fan W, Wang K, Ghasemi Falavarjani K et al (2017) Distribution of nonperfusion area on ultra-widefield fluorescein angiography in eyes with diabetic macular edema: DAVE study. Am J Ophthalmol 180:110–116. https://doi.org/10.1016/j.ajo.2017.05.024
Pearce E, Sivaprasad S (2020) A review of advancements and evidence gaps in diabetic retinopathy screening models. Clin Ophthalmol 14:3285. https://doi.org/10.2147/OPTH.S267521
Dai L, Wu L, Li H et al (2021) A deep learning system for detecting diabetic retinopathy across the disease spectrum - Nature Communications. Nat Commun 12:1–11. https://doi.org/10.1038/s41467-021-23458-5
Saif PS, Salman AE-RG, Omran NAH, Farweez YAT (2020) Assessment of diabetic retinopathy vascular density maps. Clin Ophthalmol 14:3941–3953. https://doi.org/10.2147/OPTH.S256963
Bénédicte Dupas MD (2018) Association between vessel density and visual acuity in patients with diabetic retinopathy and poorly. JAMA Ophthalmol 136:721–728. https://doi.org/10.1001/jamaophthalmol.2018.1319
Lavia C, Couturier A, Erginay A et al (2019) Reduced vessel density in the superficial and deep plexuses in diabetic retinopathy is associated with structural changes in corresponding retinal layers. PLoS One 14:e0219164. https://doi.org/10.1371/journal.pone.0219164
Lavia C, Mecê P, Nassisi M et al (2020) Retinal capillary plexus pattern and density from fovea to periphery measured in healthy eyes with swept-source optical coherence tomography angiography — scientific reports. Sci Rep 10:1–11. https://doi.org/10.1038/s41598-020-58359-y
Dupas B, Minvielle W, Bonnin S et al (2018) Association between vessel density and visual acuity in patients with diabetic retinopathy and poorly controlled type 1 diabetes. JAMA Ophthalmol 136:721–728. https://doi.org/10.1001/jamaophthalmol.2018.1319
Falavarjani KG, Mirshahi R, Riazi-Esfahani H et al (2021) Spatial distribution of diabetic capillary non-perfusion. Microcirculation 28:e12719. https://doi.org/10.1111/micc.12719
Scarinci F, Nesper PL, Fawzi AA (2016) Deep retinal capillary nonperfusion is associated with photoreceptor disruption in diabetic macular ischemia. Am J Ophthalmol 168:129–138. https://doi.org/10.1016/j.ajo.2016.05.002
Zang P, Gao L, Hormel TT et al (2020) DcardNet: diabetic retinopathy classification at multiple levels based on structural and angiographic optical coherence tomography. IEEE Trans Biomed Eng 68:1859–1870. https://doi.org/10.1109/TBME.2020.3027231
Silva PS, Dela Cruz AJ, Ledesma MG et al (2015) Diabetic retinopathy severity and peripheral lesions are associated with nonperfusion on ultrawide field angiography. Ophthalmology 122:2465–2472. https://doi.org/10.1016/j.ophtha.2015.07.034
Silva PS, Cavallerano JD, Sun JK et al (2013) Peripheral lesions identified by mydriatic ultrawide field imaging: distribution and potential impact on diabetic retinopathy severity. Ophthalmology 120:2587–2595. https://doi.org/10.1016/j.ophtha.2013.05.004
Wessel MM, Aaker GD, Parlitsis G et al (2012) Ultra–wide-field angiography improves the detection and classification of diabetic retinopathy. Retina 32:785–791. https://doi.org/10.1097/iae.0b013e3182278b64
Price L, Au S, Chong V (2015) Optomap ultrawide field imaging identifies additional retinal abnormalities in patients with diabetic retinopathy. Clin Ophthalmol 9:527–531. https://doi.org/10.2147/opth.s79448
Borrelli E, Sacconi R, Querques L et al (2020) Quantification of diabetic macular ischemia using novel three-dimensional optical coherence tomography angiography metrics. J Biophotonics 13:e202000152. https://doi.org/10.1002/jbio.202000152
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethics approval
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional review board of Tehran University of Medical Sciences and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards (IRB Code: IR.TUMS.REC.1399.019).
Informed consent
Informed consent was obtained from all individual participants included in the study.
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Khalili Pour, E., Rezaee, K., Azimi, H. et al. Automated machine learning–based classification of proliferative and non-proliferative diabetic retinopathy using optical coherence tomography angiography vascular density maps. Graefes Arch Clin Exp Ophthalmol 261, 391–399 (2023). https://doi.org/10.1007/s00417-022-05818-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00417-022-05818-z