Abstract
Purpose
Glaucoma is an eye disease that is chronic, asymptomatic, and cannot be cured once it progresses. An important step in clinical analysis of glaucoma is to measure the cup-to-disc ratio (CDR). Optic cup segmentation is a challenging task (as compared to detecting the optic disk, for instance), due to poor contrast on the cup boundary region, and occlusion from veins and arteries. Contemporary systems are based on image processing/computer vision and/or machine learning. However, obtaining accurate optic cup segmentation over large datasets is still a challenge.
Methods
We propose a novel asymmetric “multi-encoder U-Net”/Y-Net architecture with Inception and context blocks in the bottleneck layer. The architecture has an ResNet34-based primary encoder and a light-and-efficient EfficientNetB0 auxiliary encoder. The asymmetry involves avoiding multi-stage skip connections from the auxiliary encoder to the decoder. This avoids the complexity of feature map concatenation at different levels. The Inception block in the bottleneck layer performs feature enrichment. Different receptive fields in parallel paths result in multi-scale optic cup features. The next cascaded context block helps maintain spatial consistency of the multi-scale feature maps.
Results and discussion
We have experimented extensively on four public datasets, and the challenging AIIMS community camp (private) dataset. The proposed network outperforms the state of the art with an average Dice coefficient of 91.11% and 87.77% on the Drishti-GS Sivaswamy et al. (2014) and Refugee Maninis and Pont-Tuset (2010) public datasets. Our ablation studies with different competing architectures also show the proposed method achieving the highest Dice coefficient and cup overlap percentage. The training itself achieves a much lower train-validation loss, as seen over a large number of epochs.
Conclusion
The novel architecture has each sub-part geared towards getting good optic cup segmentation performance across a large number of datasets. The network shows robust segmentation performance on challenging images with various retinal artifacts (blurring, poor illumination, and clinical pathologies).
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Al-Bander, B, Williams B, Al-Nuaimy W, Al-Taee M, Pratt H, Zheng Y. Dense fully convolutional segmentation of the optic disc and cup in colour fundus for glaucoma diagnosis. Symmetry 2018;10:1–16.
Algazi, VR, Keltner JL, Johnson CA. 1985. Computer analysis of the optic cup in glaucoma. Investigative ophthalmology and visual science.
Badrinarayanan, V, Kendall A, Cipolla R. Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 2017;39(12):2481–2495.
Chakravarty, A, Sivaswamy J. Joint optic disc and cup boundary extraction from monocular fundus images. Comput Methods Prog Biomed 2017;147:51–61.
Chen, LC, Papandreou G, Schroff F, Adam H. 2017. Rethinking atrous convolution for semantic image segmentation. CoRR.
Dada, T, Coote M. 2010. Clinical evaluation of optic nerve head. International society of glaucoma surgery.
Deng, J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L. ImageNet: a large-scale hierarchical image database. Proceeding IEEE international conference on computer vision and pattern recognition (CVPR), pp 248–255; 2009.
Fu, H, Cheng J, Xu Y, Zhang C, Wong DWK, Liu J, Cao X. Disc-aware ensemble network for glaucoma screening from fundus image. IEEE Trans Med Imaging 2018;37:2493–2501.
He, K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Proceedings IEEE international conference on computer vision and pattern recognition (CVPR), pp 770–778; 2016.
Hu, M, Zhu C, Li X, Xu Y. Optic cup segmentation from fundus images for glaucoma diagnosis. Bioengineered 2017;8(1):21–28.
Jiang, Y, Tan N, Peng T. Optic disc and cup segmentation based on deep convolutional generative adversarial networks. IEEE Access 2019;7:64483–64493.
Kamble, R, Samanta P, Singhal N. Optic disc, cup and fovea detection from retinal images using U-Net++ with EfficientNet encoder. Ophthalmic medical image analysis, springer international publishing, pp 93–103; 2020.
Khalid, NEA, Noor NM, Ariff NM. Fuzzy c-means (FCM) for optic cup and disc segmentation with morphological operation. Procedia Comput Sci 2014;42:255–262.
Liu, Q, Hong X, Li S, Chen Z, Zhao G, Zou B. A spatial-aware joint optic disc and cup segmentation method. Neurocomputing 2019a;359:285–297.
Liu, S, Hong J, Lu X, Jia X, Lin Z, Zhou Y, Liu Y, Zhang H. Joint optic disc and cup segmentation using semi-supervised conditional GANs. Comput Biol Med 2019b;115:1–12.
Maninis, KK, Pont-Tuset J. 2010. Retinal databases. http://www.vision.ee.ethz.ch/~cvlsegmentation/driu/downloads.html.
Mehta, S, Mercan E, Bartlett J, Weaver D, Elmore JG, Shapiro L. Y-Net: joint segmentation and classification for diagnosis of breast biopsy images. Proceeding medical image computing and computer-assisted intervention (MICCAI), pp 893–901; 2018.
Meyer, MI, Galdran A, Medonça AM, Campilho A. A pixel-wise distance regression approach for joint retinal optical disc and fovea detection. Proceeding medical image computing and computer-assisted intervention (MICCAI), pp 39–47; 2018.
Mittapalli, PS, Kande GB. Segmentation of optic disk and optic cup from digital fundus images for the assessment of glaucoma. Biomed Signal Process Control 2016;24:34–46.
Mohamed, NA, Zulkifley MA, Zaki WMDW, Hussain A. An automated glaucoma screening system using cup-to-disc ratio via simple linear iterative clustering superpixel approach. Biomed Signal Process Control 2019;53:101–454.
Mohammed, A, Yildirim S, Farup I, Pedersen M, Hovde O. Y-Net: a deep convolutional neural network for polyp detection. Proceeding british machine vision conference (BMVC), pp 1–11; 2018.
Muramatsu, C, Nakagawa T, Sawada A, Hatanaka Y, Hara T, Yamamoto T, Fujita H. Determination of cup-to-disc ratio of optical nerve head for diagnosis of glaucoma on stereo retinal fundus image pairs. Medical imaging; 2009.
Panda, R, Puhan NB, Mandal B, Panda G. Glauconet: patch-based residual deep learning network for optic disc and cup segmentation towards glaucoma assessment. SN Comput Sci 2021;2:1–17.
Ronneberger, O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. Proceeding medical image computing and computer-assisted intervention (MICCAI), pp 234–241; 2015.
Sanfilippo, PG, Cardini A, Sigal IA, Ruddle JB, Chua BE, Hewitt AW, Mackey DA. A geometric morphometric assessment of the optic cup in glaucoma. Exp Eye Res 2010;91(3):405–414.
Sivaswamy, J, Krishnadas SR, Joshi GD, Jain M, Ujjwal STA. Drishti-GS: retinal image dataset for optic nerve head (ONH) segmentation. Proceeding IEEE international symposium on biomedical imaging (ISBI); 2014.
Szegedy, C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. Proceeding IEEE international conference on computer vision and pattern recognition (CVPR), pp 1–9; 2015.
Tan, M, Le QV. EfficientNet: rethinking model scaling for convolutional neural networks. Proceeding international conference on machine learning (ICML), pp 1–11; 2019.
Tan, NM, Xu Y, Goh WB, Liu J. Robust multi-scale superpixel classification for optic cup localization. Comput Med Imaging Graph 2015;40:182–193.
Thakur, N, Juneja M. Optic disc and optic cup segmentation from retinal images using hybrid approach. Expert Syst Appl 2019;127:308–322.
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.
Wong, DWK, Liu J, Lim JH, Li H, Wong TY. Automated detection of kinks from blood vessels for optic cup segmentation in retinal images. Proceeding SPIE medical imaging; 2009. p. 1–9.
Xu, Y, Duan L, Lin S, Chen X, Wong DWK, Wong TY, Liu J. Optic cup segmentation for glaucoma detection using low-rank superpixel representation. Proceeding medical image computing and computer-assisted intervention (MICCAI), pp 788–795; 2014.
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.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
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 (e.g. a society or other partner) 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
Sharma, A., Agrawal, M., Dutta Roy, S. et al. Better feature extraction using multi-encoder convolutional neural networks for optic cup segmentation from digital fundus images. Res. Biomed. Eng. 39, 51–63 (2023). https://doi.org/10.1007/s42600-022-00249-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42600-022-00249-5