Machine Learning and Deep Learning Techniques for Optic Disc and Cup Segmentation – A Review

Figures & data

Table 1 Summary of Glaucoma Prevalence Studies Around the World

Author	Year	Method	Findings
Quigley^Citation2	1996	Review of published data	By 2000, the number of people with primary glaucoma estimated 66.8 million. 6.7 million.
Quigley and Broman^Citation3	2006	Review of published data	79.6 million people with primary open-angle glaucoma (POAG) and primary angle closure glaucoma (PACG) in 2020.
Eid et al^Citation4	2009	Review of clinic data (Hospital-based study)	Prevalence of (POAG) in the western region in Saudi Arabia was 30.5%, primary angle closure 24.7%, neovascular 7.6%, surgically induced 6.5%, and exfoliative 5.2%.
Al-Obeidan et al^Citation5	2011	Review of clinic data (Hospital-based study)	The prevalence of (PACG) in Riyadh, Saudi Arabia was (46.6%) followed by primary angle closure (PAC) (17.2%), then primary open angle glaucoma (POAG) (12.8%). Secondary glaucoma (13%).
Day et al^Citation6	2012	Systematic review	In European Population, the prevalence of PACG in 40 years or more is 0.4%.
Tham et al^Citation7	2014	Systematic review and meta-analysis	The number of people (aged 40–80 years) estimated to be 76 million in 2020, and estimated to be 111.8 million in 2040.
Kapetanakis et al^Citation8	2016	Systematic review of published population-based surveys	Globally 57.5 million people were affected by POAG in 2015, rising to 65.5 million by 2020.
Chan et al^Citation9	2016	Systematic review and meta-analysis	In Asia in 2013, the overall glaucoma prevalence was 3.54%. POAG (2.34%) predominated over PACG (0.73%).
Gupta et al^Citation10	2016	National examination survey	The estimated prevalence of glaucoma in the US for 40 years of age and older was (2.1%). Glaucoma affected 2.9 million individuals, 2.3 million people 60 years of age and older.
Flaxman et al^Citation11	2017	Systematic review and meta-analysis	In 2015, the global population with moderate or severe vision impairment due to glaucoma were (4 million) By 2020, the global population with moderate or severe vision impairment due to glaucoma rise to 4·5 million.
Khandekar et al^Citation12	2019	Community-based survey	The prevalence of glaucoma in Riyadh, Saudi Arabia was 5.6%.
Zhang et al^Citation13	2020	Systematic Review and meta-analysis	The global PACG prevalence was 0.6% (17 million) for the last 20 years

Table 2 Current Available Public Datasets with Labelling and Manual Annotation for Glaucoma Fundus Images

Data Name	No of Images	Collection/Annotation Method	Data Source	Acquisition Device	Comments/Data Collection Purpose
RIM-ONE^Citation47	169 ONH image from full fundus images (manually cropped)	Patients’ selection and segmentation by 4 ophthalmologists and 1 optometrist. Each image has 5 manual segmentations.	1) Hospital Universitario de Canarias, 2) Hospital Clínico San Carlos, and 3) Hospital Universitario Miguel Servet	Non-mydriatic retinal photographs Nidek AFC-210 with a body of a Canon EOS 5D Mark II of 21.1 megapixels
REFUGE^Citation48	1200 fundus images with ground truth segmentations and labelled with (glaucomatous or non-glaucomatous)	Provided by seven independent glaucoma specialists from the Zhongshan Ophthalmic Center (Sun Yat-sen University, China), with an average experience of 8 years in the field. Manually drawing a tilted ellipse by means of a free annotation tool with capabilities for image review, zoom and ellipse fitting (electronic)	These photos correspond to Chinese patients, retrieved retrospectively from multiple sources, including several hospitals and clinical studies	1) Zeiss Visucam 500 fundus camera with a resolution of 2124×2056 pixels (400 images) 2) Canon CR2 device with a resolution of 1634×1634 pixels (800 images)
Drishti-GS^Citation49	101 images. It is divided into 50 training and 51 testing images.	Ground truth was collected from four glaucoma experts with experience of 3, 5, 9, and 20 years, respectively. A dedicated tool was developed to get the boundary marking on images from human experts. (electronic)	Collected at Aravind eye hospital, Madurai from visitors to the hospital, with their consent.		Dimension 2896×1944 pixels
DRIONSDB^Citation50	110 images	2 experts manual or semiautomatic tracing of the papillary contour and other ONH structures	Ophthalmology Service at Miguel Servet Hospital, Saragossa (Spain)	The images were acquired with a color analogical fundus camera (not specified)	Identification of the optic nerve head with genetic algorithms for optic nerve head segmentation benchmarking
ORIGA 650^Citation51,Citation52	650 images;168 images from glaucomatous eyes, and 482 normal eyes	1st set: 3–6 well trained graders 2nd set: marked by a single well trained independent senior glaucoma specialist. Two sets of manually segmented disc and cup boundaries obtained A grading software is designed to mark a free number of points along the boundaries of the optic disc and optic cup. However, CDR is computed manually	Singapore Malay Eye Study (SiMES)	Using Canon CR-DGi	To assess the risk factors of visual impairment in Singapore Malay community. Each set has 325 randomly selected image
RIGA^Citation53	750 color fundus images	The optic disc and cup boundaries of each image were manually annotated by independent six experienced ophthalmologists	450 MESSIDOR; 195 Bin Rushed Ophthalmic Center; 95 Magrabi Eye center	MESSIDOR; Topcon TRC NW6 non-mydriatic retinograph, (FoV) 45 degrees Bin Rushed: CanonCR2 non-mydriatic digital retinal camera; (FoV) 45 degrees Magrabi: Topcon TRC 50D Xmydriatic retinal camera; (FoV) available in 20, 30, and 35	Image Sizes: MESSIDOR; 2240×1488 Bin Rushed; 2376×1584 Magrabi; 2743X1936
LAG dataset^Citation54	11,760 images positive glaucoma (4878) or negative glaucoma (6882)	Obtained from ophthalmologists through a simulated eye-tracking experiment	Beijing Tongren hospital
ACRIMA dataset^Citation55	705 images positive glaucoma (396) and normal are (309)	All data collected through ACRIMA project and were annotated by two glaucoma experts with 8 years of experience		Topcon TRC retinal camera

Table 3 Comparison of Optic Cup (OC) and Optic Disc (OD) Segmentation Methods on REFUGE Test Set Using Different Metrics

Method	Optic Cup				Optic Disc
	Sensitivity (%)	Specificity (%)	Jaccard (%)	Dice (%)	Sensitivity (%)	Specificity (%)	Jaccard (%)	Dice (%)
DDSC-Net based^Citation64	0.9209	–	0.8065	0.8903	0.9814	–	0.9239	0.9601
GCN^Citation63	94.93	99.99	91.60	95.58	98.73	99.95	95.64	97.76
Team CUHKMED^Citation48	–	–	–	88.26	–	–	–	96.02
Team Masker^Citation48	–	–	–	88.37	–	–	–	94.64
Team BUCT^Citation48	–	–	–	87.28	–	–	–	95.25
Team NKSG^Citation48	–	–	–	86.43	–	–	–	94.88
Team VRT^Citation48	–	–	–	86.00	–	–	–	95.32
MULTI-MODEL-PRE-TRAINING^Citation64	–	–	79.02	–	–	–	92.25	–

Table 4 Deep Learning and Machine Learning Methods for Optic Cup and Disc Segmentation

Architecture	Method	Evaluation Technique	Dataset
CDED-Net^Citation67	Other	Dice, Jaccard, Sensitivity, Specificity	DRISHTI-GS, RIM-ONE and REFUGE
Coarse-to-Fine^Citation68	U-Net	IOU, DSC, Accuracy, Sensitivity, DLA and MDCP	DIARETDB0, DIARETDB1,^Citation69 and MESSIDOR
Multi-task CNN^Citation70	U-Net	Mean, std	REFUGE
CE-NET^Citation71	U-Net	Mean, std (overlapping error)	ORIGA, MESSIDOR and RIM-ONE
FC-DenseNet^Citation72	U-Net	Dice, Jaccard, Sensitivity, Specificity, Accuracy	ORIGA, DRIONS-DB, Drishti-GS, ONHSD, RIMONE
Disc-aware Ensemble Network^Citation73	U-Net	AUC, B-Accuracy, Sensitivity, Specificity	ORIGA, SCES, SINDI.
ET-Net^Citation74	Other	Dice, mIoU	REFUGE, Drishti-GS
GAN and texture analysis^Citation75	GAN	Dice	DRISHTI-GS, RIM-ONE
Ensamble-based CNN^Citation76	CNN	F-score, precision, recall, BDL	DRISHTI-GS
Hierarchical Attention Network^Citation77	Other	Dice	REFUGE
M-Net with polar transformation^Citation78	U-Net	Overlapping error (E) and Balanced accuracy (A)	ORIGA, SCES.
Semi-supervised cGAN^Citation79	GAN	IoU, mIoU	ORIGA, REFUGE.
Medinoid^Citation80	CNN	Accuracy, Sensitivity, Specificity, F1, Precision	Private data set
GL-Net^Citation65	GAN	Precision, Recall, F1, BDL	Drishti-GS1
Modified U-NET^Citation81	U-Net	IoU and Dice	DRIONS-DB, RIM-ONE v.3, DRISHTI-GS
R-CNN^Citation82	CNN	Overlapping ratio	ORIGA
Patched-based GAN^Citation83	GAN	Dice	Drishti-GS, RIM-ONE-r3, REFUGE
cGAN^Citation84	GAN	Accuracy, Dice, Jaccard, Sensitivity, Specificity	DRISHTI-GS1, RIM-ONE
Modified U-Net^Citation85	U-Net	Dice, Jaccard	RIGA, DRISHTI-GS1, RIM-ONE
Modified U-Net^Citation86	U-Net	IoU, Dice	DRISHTI-GS, RIM-ONE v.3
Stacked U-Net^Citation87	U-Net	IoU, Dice	DRIONS-DB, RIM-ONE v.3, DRISHTI-GS
Shape Regression^Citation88	Other	F-score	Drishti-GS
cGAN^Citation89	GAN	AU-ROC and AU-PR	DRIONS-DB, RIM-ONE and Drishti-GS
Two Sage CNN^Citation90	CNN	N/A	ORIGA, HRF,^Citation91 DRIONS-DB, Messidor
Multi-Task Learning^Citation92	CNN	Dice	ORIGA
FCNN^Citation48	CNN	Accuracy, Sensitivity, Specificity	ORIGA, RIMONEr3 and DRISHTI-GS
GAN-DA^Citation93	GAN	DICE	Drishti-GS, REFUGE
DeepLab-v3^Citation94	Encoder Decoder CNN	Accuracy, Dice, IoU	REFUGE, ACRIMA, ORIGA, RIM-ONE and DRISTI-GS1
Custom CNN^Citation93	CNN	Sensitivity, Specificity	DRIVE

Figure 1 Tan et al proposed CNN architecture.

Notes: Reprinted from: Tan JH, Acharya UR, Bhandary SV, Chua KC, Sivaprasad S. Segmentation of optic disc, fovea and retinal vasculature using a single convolutional neural network. J Comput Sci. 2017;20:70–79.⁹⁴ Copyright 2017, with permission from Elsevier.

Figure 2 Spatial pyramid pooling layer: pooling features extracted using different window sizes on the feature maps.

Notes: © 2015 IEEE. Reprinted, with permission, from: He K, Zhang X, Ren S, Sun J. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell. 2015;37(9):1904–1916.⁹⁸.

Figure 3 U-net architecture (example for 32×32 pixels in the lowest resolution). Each blue box corresponds to a multi-channel feature map. The number of channels is denoted on top of the box. The x-y-size is provided at the lower left edge of the box. White boxes represent copied feature maps. The arrows denote the different operation.

Notes: Reprinted by permission from Springer Nature from: Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells W, Frangi A (eds). Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. MICCAI 2015. Lecture Notes in Computer Science, vol 9351. Springer, Cham; 2015:234–241.¹⁰² Copyright © Springer International Publishing Switzerland 2015. Available from: https://link.springer.com/book/10.1007/978-3-319-24574-4.

Figure 4 GAN general architecture consists of Generator (G) which output a synthetic sample given a noise variable input and a Discriminator (D) which estimate the probability of a given sample coming from real dataset. Both components are built based on neural network.

Notes: © 2018 IEEE. Reprinted, with permission, from: Creswell A, White T, Dumoulin V, Arulkumaran K, Sengupta B, Bharath AA. Generative adversarial networks: An overview. IEEE Signal Process Mag. 2018;35(1):53–65.¹⁰⁸.

Quigley HA. Number of people with glaucoma worldwide. Br J Ophthalmol. 1996;80(5):389–393. doi:10.1136/bjo.80.5.389

 PubMed Web of Science ®Google Scholar

Quigley HA, Broman AT. The number of people with glaucoma worldwide in 2010 and 2020. Br J Ophthalmol. 2006;90(3):262–267. doi:10.1136/bjo.2005.081224

 PubMed Web of Science ®Google Scholar

Eid TM, el-Hawary I, el-Menawy W. Prevalence of glaucoma types and legal blindness from glaucoma in the western region of Saudi Arabia: a hospital-based study. Int Ophthalmol. 2009;29(6):477–483. doi:10.1007/s10792-008-9269-4

 PubMedGoogle Scholar

Al obeidan SA, Dewedar A, Osman EA, Mousa A. The profile of glaucoma in a Tertiary Ophthalmic University Center in Riyadh, Saudi Arabia. Saudi J Ophthalmol. 2011;25(4):373–379. doi:10.1016/j.sjopt.2011.09.001

 PubMedGoogle Scholar

Day AC, Baio G, Gazzard G, et al. The prevalence of primary angle closure glaucoma in European derived populations: a systematic review. Br J Ophthalmol. 2012;96(9):1162–1167. doi:10.1136/bjophthalmol-2011-301189

 PubMed Web of Science ®Google Scholar

Tham YC, Li X, Wong TY, Quigley HA, Aung T, Cheng CY. Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis. Ophthalmology. 2014;121(11):2081–2090. doi:10.1016/j.ophtha.2014.05.013

 PubMed Web of Science ®Google Scholar

Kapetanakis VV, Chan MP, Foster PJ, Cook DG, Owen CG, Rudnicka AR. Global variations and time trends in the prevalence of primary open angle glaucoma (POAG): a systematic review and meta-analysis. Br J Ophthalmol. 2016;100(1):86–93. doi:10.1136/bjophthalmol-2015-307223

 PubMed Web of Science ®Google Scholar

Chan EWE, Li X, Tham YC, et al. Glaucoma in Asia: regional prevalence variations and future projections. Br J Ophthalmol. 2016;100(1):78–85. doi:10.1136/bjophthalmol-2014-306102

 PubMed Web of Science ®Google Scholar

Gupta P, Zhao D, Guallar E, Ko F, Boland MV, Friedman DS. Prevalence of glaucoma in the United States: the 2005–2008 national health and nutrition examination survey. Invest Ophthalmol Vis Sci. 2016;57(6):2905–2913. doi:10.1167/iovs.15-18469

 PubMed Web of Science ®Google Scholar

Flaxman SR, Bourne RR, Resnikoff S, et al. Global causes of blindness and distance vision impairment 1990–2020: a systematic review and meta-analysis. Lancet Glob Health. 2017;5(12):e1221–e1234. doi:10.1016/S2214-109X(17)30393-5

 PubMed Web of Science ®Google Scholar

Khandekar R, Chauhan D, Yasir ZH, Al-Zobidi M, Judaibi R, Edward DP. The prevalence and determinants of glaucoma among 40 years and older Saudi residents in the Riyadh Governorate (except the Capital)–A community based survey. Saudi J Ophthalmol. 2019;33(4):332–337. doi:10.1016/j.sjopt.2019.02.006

 PubMed Web of Science ®Google Scholar

Zhang N, Wang J, Chen B, Li Y, Jiang B. Prevalence of primary angle closure glaucoma in the last 20 years: a meta-analysis and systematic review. Front Med. 2020;7:624179.

 Web of Science ®Google Scholar

Fumero F, Alayón S, Sanchez JL, Sigut J, Gonzalez-Hernandez M. RIM-ONE: an open retinal image database for optic nerve evaluation. In: 2011 24th international symposium on computer-based medical systems (CBMS); IEEE; June, 2011:1–6.

 Google Scholar

Orlando JI, Fu H, Breda JB, et al. Refuge challenge: a unified framework for evaluating automated methods for glaucoma assessment from fundus photographs. Med Image Anal. 2020;59:101570. doi:10.1016/j.media.2019.101570

 PubMed Web of Science ®Google Scholar

Sivaswamy J, Krishnadas SR, Joshi GD, Jain M, Tabish AUS. Drishti-gs: retinal image dataset for optic nerve head (onh) segmentation. In: 2014 IEEE 11th international symposium on biomedical imaging (ISBI); IEEE; April, 2014:53–56.

 Google Scholar

Carmona EJ, Rincón M, García-Feijoó J, Martínez-de-la-casa JM. Identification of the optic nerve head with genetic algorithms. Artif Intell Med. 2008;43(3):243–259. doi:10.1016/j.artmed.2008.04.005

 PubMed Web of Science ®Google Scholar

Cheng J, Zhang Z, Tao D, et al. Similarity regularized sparse group lasso for cup to disc ratio computation. Biomed Opt Express. 2017;8(8):3763–3777. doi:10.1364/BOE.8.003763

 PubMed Web of Science ®Google Scholar

Zhang Z, Yin FS, Liu J, et al. Origa-light: an online retinal fundus image database for glaucoma analysis and research. In 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology; IEEE; August, 2010:3065–3068.

 Google Scholar

Almazroa A, Alodhayb S, Osman E, et al. Retinal fundus images for glaucoma analysis: the Riga dataset. In: Medical Imaging 2018: Imaging Informatics for Healthcare, Research, and Applications. Vol. 10579. International Society for Optics and Photonics; March, 2018:105790B.

 Google Scholar

Li L, Xu M, Liu H, et al. A large-scale database and a CNN model for attention-based glaucoma detection. IEEE Trans Med Imaging. 2019;39(2):413–424. doi:10.1109/TMI.2019.2927226

 PubMed Web of Science ®Google Scholar

Diaz-Pinto A, Morales S, Naranjo V, et al. CNNs for automatic glaucoma assessment using fundus images: an extensive validation. Biomed Eng Online. 2019;18(1):1–19. doi:10.1186/s12938-019-0649-y

 PubMed Web of Science ®Google Scholar

Liu B, Pan D, Song H. Joint optic disc and cup segmentation based on densely connected depthwise separable convolution deep network. BMC Med Imaging. 2021;21(1):1–12. doi:10.1186/s12880-020-00528-6

 PubMed Web of Science ®Google Scholar

Tian Z, Zheng Y, Li X, Du S, Xu X. Graph convolutional network based optic disc and cup segmentation on fundus images. Biomed Opt Express. 2020;11(6):3043–3057. doi:10.1364/BOE.390056

 PubMed Web of Science ®Google Scholar

Tabassum M, Khan TM, Arsalan M, et al. CDED-Net: joint segmentation of optic disc and optic cup for glaucoma screening. IEEE Access. 2020;8:102733–102747. doi:10.1109/ACCESS.2020.2998635

 Web of Science ®Google Scholar

Wang L, Liu H, Lu Y, Chen H, Zhang J, Pu J. A coarse-to-fine deep learning framework for optic disc segmentation in fundus images. Biomed Signal Process Control. 2019;51:82–89. doi:10.1016/j.bspc.2019.01.022

 PubMed Web of Science ®Google Scholar

Kälviäinen RVJPH, Uusitalo H. DIARETDB1 diabetic retinopathy database and evaluation protocol. In: Medical Image Understanding and Analysis. Vol. 2007. Citeseer; 2007:61.

 Google Scholar

Chakravarty A, Sivswamy J. A deep learning based joint segmentation and classification framework for glaucoma assessment in retinal color fundus images; 2018. Available from: https://arxiv.org/abs/1808.01355. Accessed February 26, 2022.

 Google Scholar

Gu Z, Cheng J, Fu H, et al. Ce-net: context encoder network for 2d medical image segmentation. IEEE Trans Med Imaging. 2019;38(10):2281–2292. doi:10.1109/TMI.2019.2903562

 PubMed Web of Science ®Google Scholar

Al-Bander B, Williams BM, Al-Nuaimy W, Al-Taee MA, Pratt H, Zheng Y. Dense fully convolutional segmentation of the optic disc and cup in colour fundus for glaucoma diagnosis. Symmetry. 2018;10(4):87. doi:10.3390/sym10040087

 Google Scholar

Fu H, Cheng J, Xu Y, et al. Disc-aware ensemble network for glaucoma screening from fundus image. IEEE Trans Med Imaging. 2018;37(11):2493–2501. doi:10.1109/TMI.2018.2837012

 PubMed Web of Science ®Google Scholar

Zhang Z, Fu H, Dai H, Shen J, Pang Y, Shao L. Et-net: a generic edge-attention guidance network for medical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention; October, 2019:442–450; Springer, Cham.

 Google Scholar

Bisneto TRV, de Carvalho Filho AO, Magalhães DMV. Generative adversarial network and texture features applied to automatic glaucoma detection. Appl Soft Comput. 2020;90:106165. doi:10.1016/j.asoc.2020.106165

 Web of Science ®Google Scholar

Zilly J, Buhmann JM, Mahapatra D. Glaucoma detection using entropy sampling and ensemble learning for automatic optic cup and disc segmentation. Comput Med Imaging Graph. 2017;55:28–41. doi:10.1016/j.compmedimag.2016.07.012

 PubMed Web of Science ®Google Scholar

Ding F, Yang G, Liu J, et al. Hierarchical attention networks for medical image segmentation; 2019. Available from: https://arxiv.org/abs/1911.08777. Accessed February 26, 2022.

 Google Scholar

Fu H, Cheng J, Xu Y, Wong DWK, Liu J, Cao X. Joint optic disc and cup segmentation based on multi-label deep network and polar transformation. IEEE Trans Med Imaging. 2018;37(7):1597–1605. doi:10.1109/TMI.2018.2791488

 PubMed Web of Science ®Google Scholar

Liu S, Hong J, Lu X, et al. Joint optic disc and cup segmentation using semi-supervised conditional GANs. Comput Biol Med. 2019;115:103485. doi:10.1016/j.compbiomed.2019.103485

 PubMed Web of Science ®Google Scholar

Kim M, Han JC, Hyun SH, et al. Medinoid: computer-aided diagnosis and localization of glaucoma using deep learning. Appl Sci. 2019;9(15):3064. doi:10.3390/app9153064

 Google Scholar

Kuruvilla J, Sukumaran D, Sankar A, Joy SP. A review on image processing and image segmentation. In: 2016 international conference on data mining and advanced computing (SAPIENCE); IEEE; March, 2016:198–203.

 Google Scholar

Sevastopolsky A. Optic disc and cup segmentation methods for glaucoma detection with modification of U-Net convolutional neural network. Pattern Recognit Image Anal. 2017;27(3):618–624. doi:10.1134/S1054661817030269

 Google Scholar

Sun X, Xu Y, Zhao W, You T, Liu J. Optic disc segmentation from retinal fundus images via deep object detection networks. In: 2018 40th annual international conference of the IEEE engineering in medicine and biology society (EMBC); IEEE; July, 2018:5954–5957.

 Google Scholar

Wang S, Yu L, Yang X, Fu CW, Heng PA. Patch-based output space adversarial learning for joint optic disc and cup segmentation. IEEE Trans Med Imaging. 2019;38(11):2485–2495. doi:10.1109/TMI.2019.2899910

 PubMed Web of Science ®Google Scholar

Singh VK, Rashwan HA, Akram F, et al. Retinal optic disc segmentation using conditional generative adversarial network. In: CCIA; October, 2018:373–380.

 Google Scholar

Yu S, Xiao D, Frost S, Kanagasingam Y. Robust optic disc and cup segmentation with deep learning for glaucoma detection. Comput Med Imaging Graph. 2019;74:61–71. doi:10.1016/j.compmedimag.2019.02.005

 PubMed Web of Science ®Google Scholar

Joshua AO, Nelwamondo FV, Mabuza-Hocquet G. Segmentation of optic cup and disc for diagnosis of glaucoma on retinal fundus images. In: 2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA); IEEE; January, 2019:183–187.

 Google Scholar

Sevastopolsky A, Drapak S, Kiselev K, Snyder BM, Keenan JD, Georgievskaya A. Stack-u-net: refinement network for improved optic disc and cup image segmentation. In: Medical Imaging 2019: Image Processing. Vol. 10949. International Society for Optics and Photonics; March, 2019:1094928.

 Google Scholar

Sedai S, Roy P, Mahapatra D, Garnavi R. Segmentation of optic disc and optic cup in retinal fundus images using coupled shape regression. Proceedings of the Ophthalmic Medical Image Analysis International Workshop. Athens, Greece; 2016.

 Google Scholar

Son J, Park SJ, Jung KH. Towards accurate segmentation of retinal vessels and the optic disc in fundoscopic images with generative adversarial networks. J Digit Imaging. 2019;32(3):499–512. doi:10.1007/s10278-018-0126-3

 PubMed Web of Science ®Google Scholar

Bajwa MN, Malik MI, Siddiqui SA, et al. Two-stage framework for optic disc localization and glaucoma classification in retinal fundus images using deep learning. BMC Med Inform Decis Mak. 2019;19(1):1–16. doi:10.1186/s12911-018-0723-6

 PubMed Web of Science ®Google Scholar

Budai A, Odstrcilik J, Kolar R, et al. A public database for the evaluation of fundus image segmentation algorithms. Invest Ophthalmol Vis Sci. 2011;52(14):1345.

 PubMedGoogle Scholar

Zhao R, Liao W, Zou B, Chen Z, Li S. Weakly-supervised simultaneous evidence identification and segmentation for automated glaucoma diagnosis. In: Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 33, No. 01; July, 2019:809–816.

 Google Scholar

Sreng S, Maneerat N, Hamamoto K, Win KY. Deep learning for optic disc segmentation and glaucoma diagnosis on retinal images. Appl Sci. 2020;10(14):4916. doi:10.3390/app10144916

 Google Scholar

Tan JH, Acharya UR, Bhandary SV, Chua KC, Sivaprasad S. Segmentation of optic disc, fovea and retinal vasculature using a single convolutional neural network. J Comput Sci. 2017;20:70–79. doi:10.1016/j.jocs.2017.02.006

 Web of Science ®Google Scholar

He K, Zhang X, Ren S, Sun J. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell. 2015;37(9):1904–1916. doi:10.1109/TPAMI.2015.2389824

 PubMed Web of Science ®Google Scholar

Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention; October, 2015:234–241; Springer, Cham.

 Google Scholar

Creswell A, White T, Dumoulin V, Arulkumaran K, Sengupta B, Bharath AA. Generative adversarial networks: an overview. IEEE Signal Process Mag. 2018;35(1):53–65. doi:10.1109/MSP.2017.2765202

 Web of Science ®Google Scholar