Abstract

Calculating the cup-to-disc ratio is one of the methods for glaucoma screening with other clinical features. In this paper, we propose a graph convolutional network (GCN) based method to implement the optic disc (OD) and optic cup (OC) segmentation task. We first present a multi-scale convolutional neural network (CNN) as the feature map extractor to generate feature map. The GCN takes the feature map concatenated with the graph nodes as the input for segmentation task. The experimental results on the REFUGE dataset show that the Jaccard index (Jacc) of the proposed method on OD and OC are 95.64% and 91.60%, respectively, while the Dice similarity coefficients (DSC) are 97.76% and 95.58%, respectively. The proposed method outperforms the state-of-the-art methods on the REFUGE leaderboard. We also evaluate the proposed method on the Drishthi-GS1 dataset. The results show that the proposed method outperforms the state-of-the-art methods.

© 2020 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. Y.-C. Tham, X. Li, T. Y. Wong, H. A. Quigley, T. Aung, and C.-Y. Cheng, “Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis,” Ophthalmology 121(11), 2081–2090 (2014).
    [Crossref]
  2. J. Yohannan and M. V. Boland, “The evolving role of the relationship between optic nerve structure and function in glaucoma,” Ophthalmology 124(12), S66–S70 (2017).
    [Crossref]
  3. Z. Li, Y. He, S. Keel, W. Meng, R. T. Chang, and M. He, “Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs,” Ophthalmology 125(8), 1199–1206 (2018).
    [Crossref]
  4. J. I. Orlando, H. Fu, J. B. Breda, K. van Keer, D. R. Bathula, A. Diaz-Pinto, R. Fang, P.-A. Heng, J. Kim, and J. Lee, “Refuge challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs,” Med. Image Anal. 59, 101570 (2020).
    [Crossref]
  5. M. S. Haleem, L. Han, J. Van Hemert, and B. Li, “Automatic extraction of retinal features from colour retinal images for glaucoma diagnosis: a review,” Comput. Med. Imag. Grap. 37(7-8), 581–596 (2013).
    [Crossref]
  6. A. Almazroa, R. Burman, K. Raahemifar, and V. Lakshminarayanan, “Optic disc and optic cup segmentation methodologies for glaucoma image detection: a survey,” J. Ophthalmol. 2015, 1–28 (2015).
    [Crossref]
  7. N. Thakur and M. Juneja, “Survey on segmentation and classification approaches of optic cup and optic disc for diagnosis of glaucoma,” Biomed. Signal Process. Control. 42, 162–189 (2018).
    [Crossref]
  8. G. Litjens, T. Kooi, B. E. Bejnordi, A. A. A. Setio, F. Ciompi, M. Ghafoorian, J. A. Van Der Laak, B. Van Ginneken, and C. I. Sánchez, “A survey on deep learning in medical image analysis,” Med. Image Anal. 42, 60–88 (2017).
    [Crossref]
  9. A. Aquino, M. E. Gegúndez-Arias, and D. Marín, “Detecting the optic disc boundary in digital fundus images using morphological, edge detection, and feature extraction techniques,” IEEE Trans. Med. Imaging 29(11), 1860–1869 (2010).
    [Crossref]
  10. J. Cheng, J. Liu, D. W. K. Wong, F. Yin, C. Cheung, M. Baskaran, T. Aung, and T. Y. Wong, “Automatic optic disc segmentation with peripapillary atrophy elimination,” in 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, (IEEE, 2011), pp. 6224–6227.
  11. M. Lalonde, M. Beaulieu, and L. Gagnon, “Fast and robust optic disc detection using pyramidal decomposition and hausdorff-based template matching,” IEEE Trans. Med. Imaging 20(11), 1193–1200 (2001).
    [Crossref]
  12. D. Wong, J. Liu, J. Lim, X. Jia, F. Yin, H. Li, and T. Wong, “Level-set based automatic cup-to-disc ratio determination using retinal fundus images in argali,” in 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, (IEEE, 2008), pp. 2266–2269.
  13. Y. Zheng, D. Stambolian, J. O’Brien, and J. C. Gee, “Optic disc and cup segmentation from color fundus photograph using graph cut with priors,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, (Springer, 2013), pp. 75–82.
  14. B. Dai, X. Wu, and W. Bu, “Optic disc segmentation based on variational model with multiple energies,” Pattern Recognit. 64, 226–235 (2017).
    [Crossref]
  15. A. Osareh, M. Mirmehdi, B. Thomas, and R. Markham, “Comparison of colour spaces for optic disc localisation in retinal images,” in Object recognition supported by user interaction for service robots, vol. 1 (IEEE, 2002), pp. 743–746.
  16. J. Lowell, A. Hunter, D. Steel, A. Basu, R. Ryder, E. Fletcher, and L. Kennedy, “Optic nerve head segmentation,” IEEE Trans. Med. Imaging 23(2), 256–264 (2004).
    [Crossref]
  17. J. Xu, O. Chutatape, E. Sung, C. Zheng, and P. C. T. Kuan, “Optic disk feature extraction via modified deformable model technique for glaucoma analysis,” Pattern recognition 40(7), 2063–2076 (2007).
    [Crossref]
  18. G. D. Joshi, J. Sivaswamy, and S. Krishnadas, “Optic disk and cup segmentation from monocular color retinal images for glaucoma assessment,” IEEE Trans. Med. Imaging 30(6), 1192–1205 (2011).
    [Crossref]
  19. J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, (2015), pp. 3431–3440.
  20. O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in International Conference on Medical image computing and computer-assisted intervention, (Springer, 2015), pp. 234–241.
  21. H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, “Pyramid scene parsing network,” in Proceedings of the IEEE conference on computer vision and pattern recognition, (2017), pp. 2881–2890.
  22. L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” in Proceedings of the European conference on computer vision (ECCV), (2018), pp. 801–818.
  23. H. Fu, J. Cheng, Y. Xu, D. W. K. Wong, J. Liu, and X. Cao, “Joint optic disc and cup segmentation based on multi-label deep network and polar transformation,” IEEE Trans. Med. Imaging 37(7), 1597–1605 (2018).
    [Crossref]
  24. K.-K. Maninis, J. Pont-Tuset, P. Arbeláez, and L. Van Gool, “Deep retinal image understanding,” in International conference on medical image computing and computer-assisted intervention, (Springer, 2016), pp. 140–148.
  25. K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, (2014).
  26. H. Ling, J. Gao, A. Kar, W. Chen, and S. Fidler, “Fast interactive object annotation with curve-gcn,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2019), pp. 5257–5266.
  27. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, (2016), pp. 770–778.
  28. G. E. Dahl, T. N. Sainath, and G. E. Hinton, “Improving deep neural networks for lvcsr using rectified linear units and dropout,” in 2013 IEEE international conference on acoustics, speech and signal processing, (IEEE, 2013), pp. 8609–8613.
  29. T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” arXiv preprint arXiv:1609.02907 (2016).
  30. J. Sivaswamy, S. Krishnadas, A. Chakravarty, G. Joshi, and A. S. Tabish et al., “A comprehensive retinal image dataset for the assessment of glaucoma from the optic nerve head analysis,” JSM Biomed. Imaging Data Pap. 2, 1004 (2015).
  31. J. Sivaswamy, S. Krishnadas, G. D. Joshi, M. Jain, and A. U. S. Tabish, “Drishti-gs: Retinal image dataset for optic nerve head (onh) segmentation,” in 2014 IEEE 11th international symposium on biomedical imaging (ISBI), (IEEE, 2014), pp. 53–56.
  32. Z. Wang, N. Dong, S. D. Rosario, M. Xu, P. Xie, and E. P. Xing, “Ellipse detection of optic disc-and-cup boundary in fundus images,” in 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), (IEEE, 2019), pp. 601–604.
  33. S. M. Shankaranarayana, K. Ram, K. Mitra, and M. Sivaprakasam, “Fully convolutional networks for monocular retinal depth estimation and optic disc-cup segmentation,” IEEE J. Biomed. Health Inform. 23(4), 1417–1426 (2019).
    [Crossref]
  34. Z. Zhang, H. Fu, H. Dai, J. Shen, Y. Pang, and L. Shao, “Et-net: A generic edge-attention guidance network for medical image segmentation,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, (Springer, 2019), pp. 442–450.

2020 (1)

J. I. Orlando, H. Fu, J. B. Breda, K. van Keer, D. R. Bathula, A. Diaz-Pinto, R. Fang, P.-A. Heng, J. Kim, and J. Lee, “Refuge challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs,” Med. Image Anal. 59, 101570 (2020).
[Crossref]

2019 (1)

S. M. Shankaranarayana, K. Ram, K. Mitra, and M. Sivaprakasam, “Fully convolutional networks for monocular retinal depth estimation and optic disc-cup segmentation,” IEEE J. Biomed. Health Inform. 23(4), 1417–1426 (2019).
[Crossref]

2018 (3)

N. Thakur and M. Juneja, “Survey on segmentation and classification approaches of optic cup and optic disc for diagnosis of glaucoma,” Biomed. Signal Process. Control. 42, 162–189 (2018).
[Crossref]

Z. Li, Y. He, S. Keel, W. Meng, R. T. Chang, and M. He, “Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs,” Ophthalmology 125(8), 1199–1206 (2018).
[Crossref]

H. Fu, J. Cheng, Y. Xu, D. W. K. Wong, J. Liu, and X. Cao, “Joint optic disc and cup segmentation based on multi-label deep network and polar transformation,” IEEE Trans. Med. Imaging 37(7), 1597–1605 (2018).
[Crossref]

2017 (3)

B. Dai, X. Wu, and W. Bu, “Optic disc segmentation based on variational model with multiple energies,” Pattern Recognit. 64, 226–235 (2017).
[Crossref]

G. Litjens, T. Kooi, B. E. Bejnordi, A. A. A. Setio, F. Ciompi, M. Ghafoorian, J. A. Van Der Laak, B. Van Ginneken, and C. I. Sánchez, “A survey on deep learning in medical image analysis,” Med. Image Anal. 42, 60–88 (2017).
[Crossref]

J. Yohannan and M. V. Boland, “The evolving role of the relationship between optic nerve structure and function in glaucoma,” Ophthalmology 124(12), S66–S70 (2017).
[Crossref]

2015 (2)

A. Almazroa, R. Burman, K. Raahemifar, and V. Lakshminarayanan, “Optic disc and optic cup segmentation methodologies for glaucoma image detection: a survey,” J. Ophthalmol. 2015, 1–28 (2015).
[Crossref]

J. Sivaswamy, S. Krishnadas, A. Chakravarty, G. Joshi, and A. S. Tabish et al., “A comprehensive retinal image dataset for the assessment of glaucoma from the optic nerve head analysis,” JSM Biomed. Imaging Data Pap. 2, 1004 (2015).

2014 (1)

Y.-C. Tham, X. Li, T. Y. Wong, H. A. Quigley, T. Aung, and C.-Y. Cheng, “Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis,” Ophthalmology 121(11), 2081–2090 (2014).
[Crossref]

2013 (1)

M. S. Haleem, L. Han, J. Van Hemert, and B. Li, “Automatic extraction of retinal features from colour retinal images for glaucoma diagnosis: a review,” Comput. Med. Imag. Grap. 37(7-8), 581–596 (2013).
[Crossref]

2011 (1)

G. D. Joshi, J. Sivaswamy, and S. Krishnadas, “Optic disk and cup segmentation from monocular color retinal images for glaucoma assessment,” IEEE Trans. Med. Imaging 30(6), 1192–1205 (2011).
[Crossref]

2010 (1)

A. Aquino, M. E. Gegúndez-Arias, and D. Marín, “Detecting the optic disc boundary in digital fundus images using morphological, edge detection, and feature extraction techniques,” IEEE Trans. Med. Imaging 29(11), 1860–1869 (2010).
[Crossref]

2007 (1)

J. Xu, O. Chutatape, E. Sung, C. Zheng, and P. C. T. Kuan, “Optic disk feature extraction via modified deformable model technique for glaucoma analysis,” Pattern recognition 40(7), 2063–2076 (2007).
[Crossref]

2004 (1)

J. Lowell, A. Hunter, D. Steel, A. Basu, R. Ryder, E. Fletcher, and L. Kennedy, “Optic nerve head segmentation,” IEEE Trans. Med. Imaging 23(2), 256–264 (2004).
[Crossref]

2001 (1)

M. Lalonde, M. Beaulieu, and L. Gagnon, “Fast and robust optic disc detection using pyramidal decomposition and hausdorff-based template matching,” IEEE Trans. Med. Imaging 20(11), 1193–1200 (2001).
[Crossref]

Adam, H.

L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” in Proceedings of the European conference on computer vision (ECCV), (2018), pp. 801–818.

Almazroa, A.

A. Almazroa, R. Burman, K. Raahemifar, and V. Lakshminarayanan, “Optic disc and optic cup segmentation methodologies for glaucoma image detection: a survey,” J. Ophthalmol. 2015, 1–28 (2015).
[Crossref]

Aquino, A.

A. Aquino, M. E. Gegúndez-Arias, and D. Marín, “Detecting the optic disc boundary in digital fundus images using morphological, edge detection, and feature extraction techniques,” IEEE Trans. Med. Imaging 29(11), 1860–1869 (2010).
[Crossref]

Arbeláez, P.

K.-K. Maninis, J. Pont-Tuset, P. Arbeláez, and L. Van Gool, “Deep retinal image understanding,” in International conference on medical image computing and computer-assisted intervention, (Springer, 2016), pp. 140–148.

Aung, T.

Y.-C. Tham, X. Li, T. Y. Wong, H. A. Quigley, T. Aung, and C.-Y. Cheng, “Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis,” Ophthalmology 121(11), 2081–2090 (2014).
[Crossref]

J. Cheng, J. Liu, D. W. K. Wong, F. Yin, C. Cheung, M. Baskaran, T. Aung, and T. Y. Wong, “Automatic optic disc segmentation with peripapillary atrophy elimination,” in 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, (IEEE, 2011), pp. 6224–6227.

Baskaran, M.

J. Cheng, J. Liu, D. W. K. Wong, F. Yin, C. Cheung, M. Baskaran, T. Aung, and T. Y. Wong, “Automatic optic disc segmentation with peripapillary atrophy elimination,” in 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, (IEEE, 2011), pp. 6224–6227.

Basu, A.

J. Lowell, A. Hunter, D. Steel, A. Basu, R. Ryder, E. Fletcher, and L. Kennedy, “Optic nerve head segmentation,” IEEE Trans. Med. Imaging 23(2), 256–264 (2004).
[Crossref]

Bathula, D. R.

J. I. Orlando, H. Fu, J. B. Breda, K. van Keer, D. R. Bathula, A. Diaz-Pinto, R. Fang, P.-A. Heng, J. Kim, and J. Lee, “Refuge challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs,” Med. Image Anal. 59, 101570 (2020).
[Crossref]

Beaulieu, M.

M. Lalonde, M. Beaulieu, and L. Gagnon, “Fast and robust optic disc detection using pyramidal decomposition and hausdorff-based template matching,” IEEE Trans. Med. Imaging 20(11), 1193–1200 (2001).
[Crossref]

Bejnordi, B. E.

G. Litjens, T. Kooi, B. E. Bejnordi, A. A. A. Setio, F. Ciompi, M. Ghafoorian, J. A. Van Der Laak, B. Van Ginneken, and C. I. Sánchez, “A survey on deep learning in medical image analysis,” Med. Image Anal. 42, 60–88 (2017).
[Crossref]

Boland, M. V.

J. Yohannan and M. V. Boland, “The evolving role of the relationship between optic nerve structure and function in glaucoma,” Ophthalmology 124(12), S66–S70 (2017).
[Crossref]

Breda, J. B.

J. I. Orlando, H. Fu, J. B. Breda, K. van Keer, D. R. Bathula, A. Diaz-Pinto, R. Fang, P.-A. Heng, J. Kim, and J. Lee, “Refuge challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs,” Med. Image Anal. 59, 101570 (2020).
[Crossref]

Brox, T.

O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in International Conference on Medical image computing and computer-assisted intervention, (Springer, 2015), pp. 234–241.

Bu, W.

B. Dai, X. Wu, and W. Bu, “Optic disc segmentation based on variational model with multiple energies,” Pattern Recognit. 64, 226–235 (2017).
[Crossref]

Burman, R.

A. Almazroa, R. Burman, K. Raahemifar, and V. Lakshminarayanan, “Optic disc and optic cup segmentation methodologies for glaucoma image detection: a survey,” J. Ophthalmol. 2015, 1–28 (2015).
[Crossref]

Cao, X.

H. Fu, J. Cheng, Y. Xu, D. W. K. Wong, J. Liu, and X. Cao, “Joint optic disc and cup segmentation based on multi-label deep network and polar transformation,” IEEE Trans. Med. Imaging 37(7), 1597–1605 (2018).
[Crossref]

Chakravarty, A.

J. Sivaswamy, S. Krishnadas, A. Chakravarty, G. Joshi, and A. S. Tabish et al., “A comprehensive retinal image dataset for the assessment of glaucoma from the optic nerve head analysis,” JSM Biomed. Imaging Data Pap. 2, 1004 (2015).

Chang, R. T.

Z. Li, Y. He, S. Keel, W. Meng, R. T. Chang, and M. He, “Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs,” Ophthalmology 125(8), 1199–1206 (2018).
[Crossref]

Chen, L.-C.

L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” in Proceedings of the European conference on computer vision (ECCV), (2018), pp. 801–818.

Chen, W.

H. Ling, J. Gao, A. Kar, W. Chen, and S. Fidler, “Fast interactive object annotation with curve-gcn,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2019), pp. 5257–5266.

Cheng, C.-Y.

Y.-C. Tham, X. Li, T. Y. Wong, H. A. Quigley, T. Aung, and C.-Y. Cheng, “Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis,” Ophthalmology 121(11), 2081–2090 (2014).
[Crossref]

Cheng, J.

H. Fu, J. Cheng, Y. Xu, D. W. K. Wong, J. Liu, and X. Cao, “Joint optic disc and cup segmentation based on multi-label deep network and polar transformation,” IEEE Trans. Med. Imaging 37(7), 1597–1605 (2018).
[Crossref]

J. Cheng, J. Liu, D. W. K. Wong, F. Yin, C. Cheung, M. Baskaran, T. Aung, and T. Y. Wong, “Automatic optic disc segmentation with peripapillary atrophy elimination,” in 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, (IEEE, 2011), pp. 6224–6227.

Cheung, C.

J. Cheng, J. Liu, D. W. K. Wong, F. Yin, C. Cheung, M. Baskaran, T. Aung, and T. Y. Wong, “Automatic optic disc segmentation with peripapillary atrophy elimination,” in 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, (IEEE, 2011), pp. 6224–6227.

Chutatape, O.

J. Xu, O. Chutatape, E. Sung, C. Zheng, and P. C. T. Kuan, “Optic disk feature extraction via modified deformable model technique for glaucoma analysis,” Pattern recognition 40(7), 2063–2076 (2007).
[Crossref]

Ciompi, F.

G. Litjens, T. Kooi, B. E. Bejnordi, A. A. A. Setio, F. Ciompi, M. Ghafoorian, J. A. Van Der Laak, B. Van Ginneken, and C. I. Sánchez, “A survey on deep learning in medical image analysis,” Med. Image Anal. 42, 60–88 (2017).
[Crossref]

Dahl, G. E.

G. E. Dahl, T. N. Sainath, and G. E. Hinton, “Improving deep neural networks for lvcsr using rectified linear units and dropout,” in 2013 IEEE international conference on acoustics, speech and signal processing, (IEEE, 2013), pp. 8609–8613.

Dai, B.

B. Dai, X. Wu, and W. Bu, “Optic disc segmentation based on variational model with multiple energies,” Pattern Recognit. 64, 226–235 (2017).
[Crossref]

Dai, H.

Z. Zhang, H. Fu, H. Dai, J. Shen, Y. Pang, and L. Shao, “Et-net: A generic edge-attention guidance network for medical image segmentation,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, (Springer, 2019), pp. 442–450.

Darrell, T.

J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, (2015), pp. 3431–3440.

Diaz-Pinto, A.

J. I. Orlando, H. Fu, J. B. Breda, K. van Keer, D. R. Bathula, A. Diaz-Pinto, R. Fang, P.-A. Heng, J. Kim, and J. Lee, “Refuge challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs,” Med. Image Anal. 59, 101570 (2020).
[Crossref]

Dong, N.

Z. Wang, N. Dong, S. D. Rosario, M. Xu, P. Xie, and E. P. Xing, “Ellipse detection of optic disc-and-cup boundary in fundus images,” in 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), (IEEE, 2019), pp. 601–604.

Fang, R.

J. I. Orlando, H. Fu, J. B. Breda, K. van Keer, D. R. Bathula, A. Diaz-Pinto, R. Fang, P.-A. Heng, J. Kim, and J. Lee, “Refuge challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs,” Med. Image Anal. 59, 101570 (2020).
[Crossref]

Fidler, S.

H. Ling, J. Gao, A. Kar, W. Chen, and S. Fidler, “Fast interactive object annotation with curve-gcn,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2019), pp. 5257–5266.

Fischer, P.

O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in International Conference on Medical image computing and computer-assisted intervention, (Springer, 2015), pp. 234–241.

Fletcher, E.

J. Lowell, A. Hunter, D. Steel, A. Basu, R. Ryder, E. Fletcher, and L. Kennedy, “Optic nerve head segmentation,” IEEE Trans. Med. Imaging 23(2), 256–264 (2004).
[Crossref]

Fu, H.

J. I. Orlando, H. Fu, J. B. Breda, K. van Keer, D. R. Bathula, A. Diaz-Pinto, R. Fang, P.-A. Heng, J. Kim, and J. Lee, “Refuge challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs,” Med. Image Anal. 59, 101570 (2020).
[Crossref]

H. Fu, J. Cheng, Y. Xu, D. W. K. Wong, J. Liu, and X. Cao, “Joint optic disc and cup segmentation based on multi-label deep network and polar transformation,” IEEE Trans. Med. Imaging 37(7), 1597–1605 (2018).
[Crossref]

Z. Zhang, H. Fu, H. Dai, J. Shen, Y. Pang, and L. Shao, “Et-net: A generic edge-attention guidance network for medical image segmentation,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, (Springer, 2019), pp. 442–450.

Gagnon, L.

M. Lalonde, M. Beaulieu, and L. Gagnon, “Fast and robust optic disc detection using pyramidal decomposition and hausdorff-based template matching,” IEEE Trans. Med. Imaging 20(11), 1193–1200 (2001).
[Crossref]

Gao, J.

H. Ling, J. Gao, A. Kar, W. Chen, and S. Fidler, “Fast interactive object annotation with curve-gcn,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2019), pp. 5257–5266.

Gee, J. C.

Y. Zheng, D. Stambolian, J. O’Brien, and J. C. Gee, “Optic disc and cup segmentation from color fundus photograph using graph cut with priors,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, (Springer, 2013), pp. 75–82.

Gegúndez-Arias, M. E.

A. Aquino, M. E. Gegúndez-Arias, and D. Marín, “Detecting the optic disc boundary in digital fundus images using morphological, edge detection, and feature extraction techniques,” IEEE Trans. Med. Imaging 29(11), 1860–1869 (2010).
[Crossref]

Ghafoorian, M.

G. Litjens, T. Kooi, B. E. Bejnordi, A. A. A. Setio, F. Ciompi, M. Ghafoorian, J. A. Van Der Laak, B. Van Ginneken, and C. I. Sánchez, “A survey on deep learning in medical image analysis,” Med. Image Anal. 42, 60–88 (2017).
[Crossref]

Haleem, M. S.

M. S. Haleem, L. Han, J. Van Hemert, and B. Li, “Automatic extraction of retinal features from colour retinal images for glaucoma diagnosis: a review,” Comput. Med. Imag. Grap. 37(7-8), 581–596 (2013).
[Crossref]

Han, L.

M. S. Haleem, L. Han, J. Van Hemert, and B. Li, “Automatic extraction of retinal features from colour retinal images for glaucoma diagnosis: a review,” Comput. Med. Imag. Grap. 37(7-8), 581–596 (2013).
[Crossref]

He, K.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, (2016), pp. 770–778.

He, M.

Z. Li, Y. He, S. Keel, W. Meng, R. T. Chang, and M. He, “Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs,” Ophthalmology 125(8), 1199–1206 (2018).
[Crossref]

He, Y.

Z. Li, Y. He, S. Keel, W. Meng, R. T. Chang, and M. He, “Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs,” Ophthalmology 125(8), 1199–1206 (2018).
[Crossref]

Heng, P.-A.

J. I. Orlando, H. Fu, J. B. Breda, K. van Keer, D. R. Bathula, A. Diaz-Pinto, R. Fang, P.-A. Heng, J. Kim, and J. Lee, “Refuge challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs,” Med. Image Anal. 59, 101570 (2020).
[Crossref]

Hinton, G. E.

G. E. Dahl, T. N. Sainath, and G. E. Hinton, “Improving deep neural networks for lvcsr using rectified linear units and dropout,” in 2013 IEEE international conference on acoustics, speech and signal processing, (IEEE, 2013), pp. 8609–8613.

Hunter, A.

J. Lowell, A. Hunter, D. Steel, A. Basu, R. Ryder, E. Fletcher, and L. Kennedy, “Optic nerve head segmentation,” IEEE Trans. Med. Imaging 23(2), 256–264 (2004).
[Crossref]

Jain, M.

J. Sivaswamy, S. Krishnadas, G. D. Joshi, M. Jain, and A. U. S. Tabish, “Drishti-gs: Retinal image dataset for optic nerve head (onh) segmentation,” in 2014 IEEE 11th international symposium on biomedical imaging (ISBI), (IEEE, 2014), pp. 53–56.

Jia, J.

H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, “Pyramid scene parsing network,” in Proceedings of the IEEE conference on computer vision and pattern recognition, (2017), pp. 2881–2890.

Jia, X.

D. Wong, J. Liu, J. Lim, X. Jia, F. Yin, H. Li, and T. Wong, “Level-set based automatic cup-to-disc ratio determination using retinal fundus images in argali,” in 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, (IEEE, 2008), pp. 2266–2269.

Joshi, G.

J. Sivaswamy, S. Krishnadas, A. Chakravarty, G. Joshi, and A. S. Tabish et al., “A comprehensive retinal image dataset for the assessment of glaucoma from the optic nerve head analysis,” JSM Biomed. Imaging Data Pap. 2, 1004 (2015).

Joshi, G. D.

G. D. Joshi, J. Sivaswamy, and S. Krishnadas, “Optic disk and cup segmentation from monocular color retinal images for glaucoma assessment,” IEEE Trans. Med. Imaging 30(6), 1192–1205 (2011).
[Crossref]

J. Sivaswamy, S. Krishnadas, G. D. Joshi, M. Jain, and A. U. S. Tabish, “Drishti-gs: Retinal image dataset for optic nerve head (onh) segmentation,” in 2014 IEEE 11th international symposium on biomedical imaging (ISBI), (IEEE, 2014), pp. 53–56.

Juneja, M.

N. Thakur and M. Juneja, “Survey on segmentation and classification approaches of optic cup and optic disc for diagnosis of glaucoma,” Biomed. Signal Process. Control. 42, 162–189 (2018).
[Crossref]

Kar, A.

H. Ling, J. Gao, A. Kar, W. Chen, and S. Fidler, “Fast interactive object annotation with curve-gcn,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2019), pp. 5257–5266.

Keel, S.

Z. Li, Y. He, S. Keel, W. Meng, R. T. Chang, and M. He, “Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs,” Ophthalmology 125(8), 1199–1206 (2018).
[Crossref]

Kennedy, L.

J. Lowell, A. Hunter, D. Steel, A. Basu, R. Ryder, E. Fletcher, and L. Kennedy, “Optic nerve head segmentation,” IEEE Trans. Med. Imaging 23(2), 256–264 (2004).
[Crossref]

Kim, J.

J. I. Orlando, H. Fu, J. B. Breda, K. van Keer, D. R. Bathula, A. Diaz-Pinto, R. Fang, P.-A. Heng, J. Kim, and J. Lee, “Refuge challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs,” Med. Image Anal. 59, 101570 (2020).
[Crossref]

Kipf, T. N.

T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” arXiv preprint arXiv:1609.02907 (2016).

Kooi, T.

G. Litjens, T. Kooi, B. E. Bejnordi, A. A. A. Setio, F. Ciompi, M. Ghafoorian, J. A. Van Der Laak, B. Van Ginneken, and C. I. Sánchez, “A survey on deep learning in medical image analysis,” Med. Image Anal. 42, 60–88 (2017).
[Crossref]

Krishnadas, S.

J. Sivaswamy, S. Krishnadas, A. Chakravarty, G. Joshi, and A. S. Tabish et al., “A comprehensive retinal image dataset for the assessment of glaucoma from the optic nerve head analysis,” JSM Biomed. Imaging Data Pap. 2, 1004 (2015).

G. D. Joshi, J. Sivaswamy, and S. Krishnadas, “Optic disk and cup segmentation from monocular color retinal images for glaucoma assessment,” IEEE Trans. Med. Imaging 30(6), 1192–1205 (2011).
[Crossref]

J. Sivaswamy, S. Krishnadas, G. D. Joshi, M. Jain, and A. U. S. Tabish, “Drishti-gs: Retinal image dataset for optic nerve head (onh) segmentation,” in 2014 IEEE 11th international symposium on biomedical imaging (ISBI), (IEEE, 2014), pp. 53–56.

Kuan, P. C. T.

J. Xu, O. Chutatape, E. Sung, C. Zheng, and P. C. T. Kuan, “Optic disk feature extraction via modified deformable model technique for glaucoma analysis,” Pattern recognition 40(7), 2063–2076 (2007).
[Crossref]

Lakshminarayanan, V.

A. Almazroa, R. Burman, K. Raahemifar, and V. Lakshminarayanan, “Optic disc and optic cup segmentation methodologies for glaucoma image detection: a survey,” J. Ophthalmol. 2015, 1–28 (2015).
[Crossref]

Lalonde, M.

M. Lalonde, M. Beaulieu, and L. Gagnon, “Fast and robust optic disc detection using pyramidal decomposition and hausdorff-based template matching,” IEEE Trans. Med. Imaging 20(11), 1193–1200 (2001).
[Crossref]

Lee, J.

J. I. Orlando, H. Fu, J. B. Breda, K. van Keer, D. R. Bathula, A. Diaz-Pinto, R. Fang, P.-A. Heng, J. Kim, and J. Lee, “Refuge challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs,” Med. Image Anal. 59, 101570 (2020).
[Crossref]

Li, B.

M. S. Haleem, L. Han, J. Van Hemert, and B. Li, “Automatic extraction of retinal features from colour retinal images for glaucoma diagnosis: a review,” Comput. Med. Imag. Grap. 37(7-8), 581–596 (2013).
[Crossref]

Li, H.

D. Wong, J. Liu, J. Lim, X. Jia, F. Yin, H. Li, and T. Wong, “Level-set based automatic cup-to-disc ratio determination using retinal fundus images in argali,” in 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, (IEEE, 2008), pp. 2266–2269.

Li, X.

Y.-C. Tham, X. Li, T. Y. Wong, H. A. Quigley, T. Aung, and C.-Y. Cheng, “Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis,” Ophthalmology 121(11), 2081–2090 (2014).
[Crossref]

Li, Z.

Z. Li, Y. He, S. Keel, W. Meng, R. T. Chang, and M. He, “Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs,” Ophthalmology 125(8), 1199–1206 (2018).
[Crossref]

Lim, J.

D. Wong, J. Liu, J. Lim, X. Jia, F. Yin, H. Li, and T. Wong, “Level-set based automatic cup-to-disc ratio determination using retinal fundus images in argali,” in 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, (IEEE, 2008), pp. 2266–2269.

Ling, H.

H. Ling, J. Gao, A. Kar, W. Chen, and S. Fidler, “Fast interactive object annotation with curve-gcn,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2019), pp. 5257–5266.

Litjens, G.

G. Litjens, T. Kooi, B. E. Bejnordi, A. A. A. Setio, F. Ciompi, M. Ghafoorian, J. A. Van Der Laak, B. Van Ginneken, and C. I. Sánchez, “A survey on deep learning in medical image analysis,” Med. Image Anal. 42, 60–88 (2017).
[Crossref]

Liu, J.

H. Fu, J. Cheng, Y. Xu, D. W. K. Wong, J. Liu, and X. Cao, “Joint optic disc and cup segmentation based on multi-label deep network and polar transformation,” IEEE Trans. Med. Imaging 37(7), 1597–1605 (2018).
[Crossref]

J. Cheng, J. Liu, D. W. K. Wong, F. Yin, C. Cheung, M. Baskaran, T. Aung, and T. Y. Wong, “Automatic optic disc segmentation with peripapillary atrophy elimination,” in 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, (IEEE, 2011), pp. 6224–6227.

D. Wong, J. Liu, J. Lim, X. Jia, F. Yin, H. Li, and T. Wong, “Level-set based automatic cup-to-disc ratio determination using retinal fundus images in argali,” in 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, (IEEE, 2008), pp. 2266–2269.

Long, J.

J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, (2015), pp. 3431–3440.

Lowell, J.

J. Lowell, A. Hunter, D. Steel, A. Basu, R. Ryder, E. Fletcher, and L. Kennedy, “Optic nerve head segmentation,” IEEE Trans. Med. Imaging 23(2), 256–264 (2004).
[Crossref]

Maninis, K.-K.

K.-K. Maninis, J. Pont-Tuset, P. Arbeláez, and L. Van Gool, “Deep retinal image understanding,” in International conference on medical image computing and computer-assisted intervention, (Springer, 2016), pp. 140–148.

Marín, D.

A. Aquino, M. E. Gegúndez-Arias, and D. Marín, “Detecting the optic disc boundary in digital fundus images using morphological, edge detection, and feature extraction techniques,” IEEE Trans. Med. Imaging 29(11), 1860–1869 (2010).
[Crossref]

Markham, R.

A. Osareh, M. Mirmehdi, B. Thomas, and R. Markham, “Comparison of colour spaces for optic disc localisation in retinal images,” in Object recognition supported by user interaction for service robots, vol. 1 (IEEE, 2002), pp. 743–746.

Meng, W.

Z. Li, Y. He, S. Keel, W. Meng, R. T. Chang, and M. He, “Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs,” Ophthalmology 125(8), 1199–1206 (2018).
[Crossref]

Mirmehdi, M.

A. Osareh, M. Mirmehdi, B. Thomas, and R. Markham, “Comparison of colour spaces for optic disc localisation in retinal images,” in Object recognition supported by user interaction for service robots, vol. 1 (IEEE, 2002), pp. 743–746.

Mitra, K.

S. M. Shankaranarayana, K. Ram, K. Mitra, and M. Sivaprakasam, “Fully convolutional networks for monocular retinal depth estimation and optic disc-cup segmentation,” IEEE J. Biomed. Health Inform. 23(4), 1417–1426 (2019).
[Crossref]

O’Brien, J.

Y. Zheng, D. Stambolian, J. O’Brien, and J. C. Gee, “Optic disc and cup segmentation from color fundus photograph using graph cut with priors,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, (Springer, 2013), pp. 75–82.

Orlando, J. I.

J. I. Orlando, H. Fu, J. B. Breda, K. van Keer, D. R. Bathula, A. Diaz-Pinto, R. Fang, P.-A. Heng, J. Kim, and J. Lee, “Refuge challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs,” Med. Image Anal. 59, 101570 (2020).
[Crossref]

Osareh, A.

A. Osareh, M. Mirmehdi, B. Thomas, and R. Markham, “Comparison of colour spaces for optic disc localisation in retinal images,” in Object recognition supported by user interaction for service robots, vol. 1 (IEEE, 2002), pp. 743–746.

Pang, Y.

Z. Zhang, H. Fu, H. Dai, J. Shen, Y. Pang, and L. Shao, “Et-net: A generic edge-attention guidance network for medical image segmentation,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, (Springer, 2019), pp. 442–450.

Papandreou, G.

L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” in Proceedings of the European conference on computer vision (ECCV), (2018), pp. 801–818.

Pont-Tuset, J.

K.-K. Maninis, J. Pont-Tuset, P. Arbeláez, and L. Van Gool, “Deep retinal image understanding,” in International conference on medical image computing and computer-assisted intervention, (Springer, 2016), pp. 140–148.

Qi, X.

H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, “Pyramid scene parsing network,” in Proceedings of the IEEE conference on computer vision and pattern recognition, (2017), pp. 2881–2890.

Quigley, H. A.

Y.-C. Tham, X. Li, T. Y. Wong, H. A. Quigley, T. Aung, and C.-Y. Cheng, “Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis,” Ophthalmology 121(11), 2081–2090 (2014).
[Crossref]

Raahemifar, K.

A. Almazroa, R. Burman, K. Raahemifar, and V. Lakshminarayanan, “Optic disc and optic cup segmentation methodologies for glaucoma image detection: a survey,” J. Ophthalmol. 2015, 1–28 (2015).
[Crossref]

Ram, K.

S. M. Shankaranarayana, K. Ram, K. Mitra, and M. Sivaprakasam, “Fully convolutional networks for monocular retinal depth estimation and optic disc-cup segmentation,” IEEE J. Biomed. Health Inform. 23(4), 1417–1426 (2019).
[Crossref]

Ren, S.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, (2016), pp. 770–778.

Ronneberger, O.

O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in International Conference on Medical image computing and computer-assisted intervention, (Springer, 2015), pp. 234–241.

Rosario, S. D.

Z. Wang, N. Dong, S. D. Rosario, M. Xu, P. Xie, and E. P. Xing, “Ellipse detection of optic disc-and-cup boundary in fundus images,” in 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), (IEEE, 2019), pp. 601–604.

Ryder, R.

J. Lowell, A. Hunter, D. Steel, A. Basu, R. Ryder, E. Fletcher, and L. Kennedy, “Optic nerve head segmentation,” IEEE Trans. Med. Imaging 23(2), 256–264 (2004).
[Crossref]

Sainath, T. N.

G. E. Dahl, T. N. Sainath, and G. E. Hinton, “Improving deep neural networks for lvcsr using rectified linear units and dropout,” in 2013 IEEE international conference on acoustics, speech and signal processing, (IEEE, 2013), pp. 8609–8613.

Sánchez, C. I.

G. Litjens, T. Kooi, B. E. Bejnordi, A. A. A. Setio, F. Ciompi, M. Ghafoorian, J. A. Van Der Laak, B. Van Ginneken, and C. I. Sánchez, “A survey on deep learning in medical image analysis,” Med. Image Anal. 42, 60–88 (2017).
[Crossref]

Schroff, F.

L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” in Proceedings of the European conference on computer vision (ECCV), (2018), pp. 801–818.

Setio, A. A. A.

G. Litjens, T. Kooi, B. E. Bejnordi, A. A. A. Setio, F. Ciompi, M. Ghafoorian, J. A. Van Der Laak, B. Van Ginneken, and C. I. Sánchez, “A survey on deep learning in medical image analysis,” Med. Image Anal. 42, 60–88 (2017).
[Crossref]

Shankaranarayana, S. M.

S. M. Shankaranarayana, K. Ram, K. Mitra, and M. Sivaprakasam, “Fully convolutional networks for monocular retinal depth estimation and optic disc-cup segmentation,” IEEE J. Biomed. Health Inform. 23(4), 1417–1426 (2019).
[Crossref]

Shao, L.

Z. Zhang, H. Fu, H. Dai, J. Shen, Y. Pang, and L. Shao, “Et-net: A generic edge-attention guidance network for medical image segmentation,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, (Springer, 2019), pp. 442–450.

Shelhamer, E.

J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, (2015), pp. 3431–3440.

Shen, J.

Z. Zhang, H. Fu, H. Dai, J. Shen, Y. Pang, and L. Shao, “Et-net: A generic edge-attention guidance network for medical image segmentation,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, (Springer, 2019), pp. 442–450.

Shi, J.

H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, “Pyramid scene parsing network,” in Proceedings of the IEEE conference on computer vision and pattern recognition, (2017), pp. 2881–2890.

Simonyan, K.

K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, (2014).

Sivaprakasam, M.

S. M. Shankaranarayana, K. Ram, K. Mitra, and M. Sivaprakasam, “Fully convolutional networks for monocular retinal depth estimation and optic disc-cup segmentation,” IEEE J. Biomed. Health Inform. 23(4), 1417–1426 (2019).
[Crossref]

Sivaswamy, J.

J. Sivaswamy, S. Krishnadas, A. Chakravarty, G. Joshi, and A. S. Tabish et al., “A comprehensive retinal image dataset for the assessment of glaucoma from the optic nerve head analysis,” JSM Biomed. Imaging Data Pap. 2, 1004 (2015).

G. D. Joshi, J. Sivaswamy, and S. Krishnadas, “Optic disk and cup segmentation from monocular color retinal images for glaucoma assessment,” IEEE Trans. Med. Imaging 30(6), 1192–1205 (2011).
[Crossref]

J. Sivaswamy, S. Krishnadas, G. D. Joshi, M. Jain, and A. U. S. Tabish, “Drishti-gs: Retinal image dataset for optic nerve head (onh) segmentation,” in 2014 IEEE 11th international symposium on biomedical imaging (ISBI), (IEEE, 2014), pp. 53–56.

Stambolian, D.

Y. Zheng, D. Stambolian, J. O’Brien, and J. C. Gee, “Optic disc and cup segmentation from color fundus photograph using graph cut with priors,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, (Springer, 2013), pp. 75–82.

Steel, D.

J. Lowell, A. Hunter, D. Steel, A. Basu, R. Ryder, E. Fletcher, and L. Kennedy, “Optic nerve head segmentation,” IEEE Trans. Med. Imaging 23(2), 256–264 (2004).
[Crossref]

Sun, J.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, (2016), pp. 770–778.

Sung, E.

J. Xu, O. Chutatape, E. Sung, C. Zheng, and P. C. T. Kuan, “Optic disk feature extraction via modified deformable model technique for glaucoma analysis,” Pattern recognition 40(7), 2063–2076 (2007).
[Crossref]

Tabish, A. S.

J. Sivaswamy, S. Krishnadas, A. Chakravarty, G. Joshi, and A. S. Tabish et al., “A comprehensive retinal image dataset for the assessment of glaucoma from the optic nerve head analysis,” JSM Biomed. Imaging Data Pap. 2, 1004 (2015).

Tabish, A. U. S.

J. Sivaswamy, S. Krishnadas, G. D. Joshi, M. Jain, and A. U. S. Tabish, “Drishti-gs: Retinal image dataset for optic nerve head (onh) segmentation,” in 2014 IEEE 11th international symposium on biomedical imaging (ISBI), (IEEE, 2014), pp. 53–56.

Thakur, N.

N. Thakur and M. Juneja, “Survey on segmentation and classification approaches of optic cup and optic disc for diagnosis of glaucoma,” Biomed. Signal Process. Control. 42, 162–189 (2018).
[Crossref]

Tham, Y.-C.

Y.-C. Tham, X. Li, T. Y. Wong, H. A. Quigley, T. Aung, and C.-Y. Cheng, “Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis,” Ophthalmology 121(11), 2081–2090 (2014).
[Crossref]

Thomas, B.

A. Osareh, M. Mirmehdi, B. Thomas, and R. Markham, “Comparison of colour spaces for optic disc localisation in retinal images,” in Object recognition supported by user interaction for service robots, vol. 1 (IEEE, 2002), pp. 743–746.

Van Der Laak, J. A.

G. Litjens, T. Kooi, B. E. Bejnordi, A. A. A. Setio, F. Ciompi, M. Ghafoorian, J. A. Van Der Laak, B. Van Ginneken, and C. I. Sánchez, “A survey on deep learning in medical image analysis,” Med. Image Anal. 42, 60–88 (2017).
[Crossref]

Van Ginneken, B.

G. Litjens, T. Kooi, B. E. Bejnordi, A. A. A. Setio, F. Ciompi, M. Ghafoorian, J. A. Van Der Laak, B. Van Ginneken, and C. I. Sánchez, “A survey on deep learning in medical image analysis,” Med. Image Anal. 42, 60–88 (2017).
[Crossref]

Van Gool, L.

K.-K. Maninis, J. Pont-Tuset, P. Arbeláez, and L. Van Gool, “Deep retinal image understanding,” in International conference on medical image computing and computer-assisted intervention, (Springer, 2016), pp. 140–148.

Van Hemert, J.

M. S. Haleem, L. Han, J. Van Hemert, and B. Li, “Automatic extraction of retinal features from colour retinal images for glaucoma diagnosis: a review,” Comput. Med. Imag. Grap. 37(7-8), 581–596 (2013).
[Crossref]

van Keer, K.

J. I. Orlando, H. Fu, J. B. Breda, K. van Keer, D. R. Bathula, A. Diaz-Pinto, R. Fang, P.-A. Heng, J. Kim, and J. Lee, “Refuge challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs,” Med. Image Anal. 59, 101570 (2020).
[Crossref]

Wang, X.

H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, “Pyramid scene parsing network,” in Proceedings of the IEEE conference on computer vision and pattern recognition, (2017), pp. 2881–2890.

Wang, Z.

Z. Wang, N. Dong, S. D. Rosario, M. Xu, P. Xie, and E. P. Xing, “Ellipse detection of optic disc-and-cup boundary in fundus images,” in 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), (IEEE, 2019), pp. 601–604.

Welling, M.

T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” arXiv preprint arXiv:1609.02907 (2016).

Wong, D.

D. Wong, J. Liu, J. Lim, X. Jia, F. Yin, H. Li, and T. Wong, “Level-set based automatic cup-to-disc ratio determination using retinal fundus images in argali,” in 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, (IEEE, 2008), pp. 2266–2269.

Wong, D. W. K.

H. Fu, J. Cheng, Y. Xu, D. W. K. Wong, J. Liu, and X. Cao, “Joint optic disc and cup segmentation based on multi-label deep network and polar transformation,” IEEE Trans. Med. Imaging 37(7), 1597–1605 (2018).
[Crossref]

J. Cheng, J. Liu, D. W. K. Wong, F. Yin, C. Cheung, M. Baskaran, T. Aung, and T. Y. Wong, “Automatic optic disc segmentation with peripapillary atrophy elimination,” in 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, (IEEE, 2011), pp. 6224–6227.

Wong, T.

D. Wong, J. Liu, J. Lim, X. Jia, F. Yin, H. Li, and T. Wong, “Level-set based automatic cup-to-disc ratio determination using retinal fundus images in argali,” in 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, (IEEE, 2008), pp. 2266–2269.

Wong, T. Y.

Y.-C. Tham, X. Li, T. Y. Wong, H. A. Quigley, T. Aung, and C.-Y. Cheng, “Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis,” Ophthalmology 121(11), 2081–2090 (2014).
[Crossref]

J. Cheng, J. Liu, D. W. K. Wong, F. Yin, C. Cheung, M. Baskaran, T. Aung, and T. Y. Wong, “Automatic optic disc segmentation with peripapillary atrophy elimination,” in 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, (IEEE, 2011), pp. 6224–6227.

Wu, X.

B. Dai, X. Wu, and W. Bu, “Optic disc segmentation based on variational model with multiple energies,” Pattern Recognit. 64, 226–235 (2017).
[Crossref]

Xie, P.

Z. Wang, N. Dong, S. D. Rosario, M. Xu, P. Xie, and E. P. Xing, “Ellipse detection of optic disc-and-cup boundary in fundus images,” in 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), (IEEE, 2019), pp. 601–604.

Xing, E. P.

Z. Wang, N. Dong, S. D. Rosario, M. Xu, P. Xie, and E. P. Xing, “Ellipse detection of optic disc-and-cup boundary in fundus images,” in 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), (IEEE, 2019), pp. 601–604.

Xu, J.

J. Xu, O. Chutatape, E. Sung, C. Zheng, and P. C. T. Kuan, “Optic disk feature extraction via modified deformable model technique for glaucoma analysis,” Pattern recognition 40(7), 2063–2076 (2007).
[Crossref]

Xu, M.

Z. Wang, N. Dong, S. D. Rosario, M. Xu, P. Xie, and E. P. Xing, “Ellipse detection of optic disc-and-cup boundary in fundus images,” in 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), (IEEE, 2019), pp. 601–604.

Xu, Y.

H. Fu, J. Cheng, Y. Xu, D. W. K. Wong, J. Liu, and X. Cao, “Joint optic disc and cup segmentation based on multi-label deep network and polar transformation,” IEEE Trans. Med. Imaging 37(7), 1597–1605 (2018).
[Crossref]

Yin, F.

J. Cheng, J. Liu, D. W. K. Wong, F. Yin, C. Cheung, M. Baskaran, T. Aung, and T. Y. Wong, “Automatic optic disc segmentation with peripapillary atrophy elimination,” in 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, (IEEE, 2011), pp. 6224–6227.

D. Wong, J. Liu, J. Lim, X. Jia, F. Yin, H. Li, and T. Wong, “Level-set based automatic cup-to-disc ratio determination using retinal fundus images in argali,” in 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, (IEEE, 2008), pp. 2266–2269.

Yohannan, J.

J. Yohannan and M. V. Boland, “The evolving role of the relationship between optic nerve structure and function in glaucoma,” Ophthalmology 124(12), S66–S70 (2017).
[Crossref]

Zhang, X.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, (2016), pp. 770–778.

Zhang, Z.

Z. Zhang, H. Fu, H. Dai, J. Shen, Y. Pang, and L. Shao, “Et-net: A generic edge-attention guidance network for medical image segmentation,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, (Springer, 2019), pp. 442–450.

Zhao, H.

H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, “Pyramid scene parsing network,” in Proceedings of the IEEE conference on computer vision and pattern recognition, (2017), pp. 2881–2890.

Zheng, C.

J. Xu, O. Chutatape, E. Sung, C. Zheng, and P. C. T. Kuan, “Optic disk feature extraction via modified deformable model technique for glaucoma analysis,” Pattern recognition 40(7), 2063–2076 (2007).
[Crossref]

Zheng, Y.

Y. Zheng, D. Stambolian, J. O’Brien, and J. C. Gee, “Optic disc and cup segmentation from color fundus photograph using graph cut with priors,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, (Springer, 2013), pp. 75–82.

Zhu, Y.

L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” in Proceedings of the European conference on computer vision (ECCV), (2018), pp. 801–818.

Zisserman, A.

K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, (2014).

Biomed. Signal Process. Control. (1)

N. Thakur and M. Juneja, “Survey on segmentation and classification approaches of optic cup and optic disc for diagnosis of glaucoma,” Biomed. Signal Process. Control. 42, 162–189 (2018).
[Crossref]

Comput. Med. Imag. Grap. (1)

M. S. Haleem, L. Han, J. Van Hemert, and B. Li, “Automatic extraction of retinal features from colour retinal images for glaucoma diagnosis: a review,” Comput. Med. Imag. Grap. 37(7-8), 581–596 (2013).
[Crossref]

IEEE J. Biomed. Health Inform. (1)

S. M. Shankaranarayana, K. Ram, K. Mitra, and M. Sivaprakasam, “Fully convolutional networks for monocular retinal depth estimation and optic disc-cup segmentation,” IEEE J. Biomed. Health Inform. 23(4), 1417–1426 (2019).
[Crossref]

IEEE Trans. Med. Imaging (5)

H. Fu, J. Cheng, Y. Xu, D. W. K. Wong, J. Liu, and X. Cao, “Joint optic disc and cup segmentation based on multi-label deep network and polar transformation,” IEEE Trans. Med. Imaging 37(7), 1597–1605 (2018).
[Crossref]

J. Lowell, A. Hunter, D. Steel, A. Basu, R. Ryder, E. Fletcher, and L. Kennedy, “Optic nerve head segmentation,” IEEE Trans. Med. Imaging 23(2), 256–264 (2004).
[Crossref]

A. Aquino, M. E. Gegúndez-Arias, and D. Marín, “Detecting the optic disc boundary in digital fundus images using morphological, edge detection, and feature extraction techniques,” IEEE Trans. Med. Imaging 29(11), 1860–1869 (2010).
[Crossref]

M. Lalonde, M. Beaulieu, and L. Gagnon, “Fast and robust optic disc detection using pyramidal decomposition and hausdorff-based template matching,” IEEE Trans. Med. Imaging 20(11), 1193–1200 (2001).
[Crossref]

G. D. Joshi, J. Sivaswamy, and S. Krishnadas, “Optic disk and cup segmentation from monocular color retinal images for glaucoma assessment,” IEEE Trans. Med. Imaging 30(6), 1192–1205 (2011).
[Crossref]

J. Ophthalmol. (1)

A. Almazroa, R. Burman, K. Raahemifar, and V. Lakshminarayanan, “Optic disc and optic cup segmentation methodologies for glaucoma image detection: a survey,” J. Ophthalmol. 2015, 1–28 (2015).
[Crossref]

JSM Biomed. Imaging Data Pap. (1)

J. Sivaswamy, S. Krishnadas, A. Chakravarty, G. Joshi, and A. S. Tabish et al., “A comprehensive retinal image dataset for the assessment of glaucoma from the optic nerve head analysis,” JSM Biomed. Imaging Data Pap. 2, 1004 (2015).

Med. Image Anal. (2)

J. I. Orlando, H. Fu, J. B. Breda, K. van Keer, D. R. Bathula, A. Diaz-Pinto, R. Fang, P.-A. Heng, J. Kim, and J. Lee, “Refuge challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs,” Med. Image Anal. 59, 101570 (2020).
[Crossref]

G. Litjens, T. Kooi, B. E. Bejnordi, A. A. A. Setio, F. Ciompi, M. Ghafoorian, J. A. Van Der Laak, B. Van Ginneken, and C. I. Sánchez, “A survey on deep learning in medical image analysis,” Med. Image Anal. 42, 60–88 (2017).
[Crossref]

Ophthalmology (3)

Y.-C. Tham, X. Li, T. Y. Wong, H. A. Quigley, T. Aung, and C.-Y. Cheng, “Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis,” Ophthalmology 121(11), 2081–2090 (2014).
[Crossref]

J. Yohannan and M. V. Boland, “The evolving role of the relationship between optic nerve structure and function in glaucoma,” Ophthalmology 124(12), S66–S70 (2017).
[Crossref]

Z. Li, Y. He, S. Keel, W. Meng, R. T. Chang, and M. He, “Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs,” Ophthalmology 125(8), 1199–1206 (2018).
[Crossref]

Pattern Recognit. (1)

B. Dai, X. Wu, and W. Bu, “Optic disc segmentation based on variational model with multiple energies,” Pattern Recognit. 64, 226–235 (2017).
[Crossref]

Pattern recognition (1)

J. Xu, O. Chutatape, E. Sung, C. Zheng, and P. C. T. Kuan, “Optic disk feature extraction via modified deformable model technique for glaucoma analysis,” Pattern recognition 40(7), 2063–2076 (2007).
[Crossref]

Other (17)

J. Sivaswamy, S. Krishnadas, G. D. Joshi, M. Jain, and A. U. S. Tabish, “Drishti-gs: Retinal image dataset for optic nerve head (onh) segmentation,” in 2014 IEEE 11th international symposium on biomedical imaging (ISBI), (IEEE, 2014), pp. 53–56.

Z. Wang, N. Dong, S. D. Rosario, M. Xu, P. Xie, and E. P. Xing, “Ellipse detection of optic disc-and-cup boundary in fundus images,” in 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), (IEEE, 2019), pp. 601–604.

K.-K. Maninis, J. Pont-Tuset, P. Arbeláez, and L. Van Gool, “Deep retinal image understanding,” in International conference on medical image computing and computer-assisted intervention, (Springer, 2016), pp. 140–148.

K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, (2014).

H. Ling, J. Gao, A. Kar, W. Chen, and S. Fidler, “Fast interactive object annotation with curve-gcn,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2019), pp. 5257–5266.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, (2016), pp. 770–778.

G. E. Dahl, T. N. Sainath, and G. E. Hinton, “Improving deep neural networks for lvcsr using rectified linear units and dropout,” in 2013 IEEE international conference on acoustics, speech and signal processing, (IEEE, 2013), pp. 8609–8613.

T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” arXiv preprint arXiv:1609.02907 (2016).

Z. Zhang, H. Fu, H. Dai, J. Shen, Y. Pang, and L. Shao, “Et-net: A generic edge-attention guidance network for medical image segmentation,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, (Springer, 2019), pp. 442–450.

A. Osareh, M. Mirmehdi, B. Thomas, and R. Markham, “Comparison of colour spaces for optic disc localisation in retinal images,” in Object recognition supported by user interaction for service robots, vol. 1 (IEEE, 2002), pp. 743–746.

D. Wong, J. Liu, J. Lim, X. Jia, F. Yin, H. Li, and T. Wong, “Level-set based automatic cup-to-disc ratio determination using retinal fundus images in argali,” in 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, (IEEE, 2008), pp. 2266–2269.

Y. Zheng, D. Stambolian, J. O’Brien, and J. C. Gee, “Optic disc and cup segmentation from color fundus photograph using graph cut with priors,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, (Springer, 2013), pp. 75–82.

J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, (2015), pp. 3431–3440.

O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in International Conference on Medical image computing and computer-assisted intervention, (Springer, 2015), pp. 234–241.

H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, “Pyramid scene parsing network,” in Proceedings of the IEEE conference on computer vision and pattern recognition, (2017), pp. 2881–2890.

L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” in Proceedings of the European conference on computer vision (ECCV), (2018), pp. 801–818.

J. Cheng, J. Liu, D. W. K. Wong, F. Yin, C. Cheung, M. Baskaran, T. Aung, and T. Y. Wong, “Automatic optic disc segmentation with peripapillary atrophy elimination,” in 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, (IEEE, 2011), pp. 6224–6227.

Cited By

OSA participates in Crossref's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (14)

Fig. 1.
Fig. 1. Examples of (a) normal and (b) glaucoma fundus images from REFUGE [4] dataset. The right-hand image of each example contains enlarged optic disc area, where optic disc and cup are indicated by outer blue and inner green lines, respectively. The vertical lines indicate the diameter of the optic disc and cup. Note that the eye with glaucoma has a much larger cup-to-disc ratio than the normal eye.
Fig. 2.
Fig. 2. Examples of optic disc (OD) and optic cup (OC) appearance from REFUGE [4] dataset. The first row shows different colors of optic disc, which are (a) Yellowish OD, (b) Whitish OD, (c) Reddish OD, (d) Brownish OD. The second row shows several challenging examples, which are (e) obscure border between optic disc and cup, (f, g) blurred border between optic disc and other area and (h) structure change of OD.
Fig. 3.
Fig. 3. Overview of the proposed method. C-Net, a multi-scale convolutional neural network, outputs the feature map of the input images. G-Net, a graph convolutional network, takes the output of C-Net and the initial graph nodes as input. The output of a fully connected layer following the G-Net is our final segmentation result.
Fig. 4.
Fig. 4. C-Net architecture. In the figure, $7 \times 7$conv and $3 \times 3$conv represent $7 \times 7$ and $3 \times 3$ convolution operation, respectively, while $\times 2$up and $\times 4$up represent bilinear up-sampling operation with 2 and 4 scale factors, respectively. The numbers on the arrows represent the sizes of feature maps. The pyramid parsing module (PPM) [21] was used to extract multi-scale features.
Fig. 5.
Fig. 5. G-Net architecture. The graph convolution operation (GCO) is used at the beginning and end of the G-Net to adjust the feature dimension. The residual graph convolution operation (ResGCO) is used to learn more representative feature for segmentation.
Fig. 6.
Fig. 6. The connection of the C-Net and G-Net. It shows how the C-Net feature linked with the nodes.
Fig. 7.
Fig. 7. The loss curve of the training process. The number of epochs was 27.
Fig. 8.
Fig. 8. The receiver operating characteristics (ROC) curves and the area under the curve (AUC) values of the proposed method and the ground truth on REFUGE test set.
Fig. 9.
Fig. 9. Correlation analysis of the segmentation results with ground-truth for (a) optic disc (OD) and (b) optic cup (OC), which uses area as the evaluation standard. The black line indicates no systematic difference. $c$ and $r^2$ represent correlation coefficient and determination coefficient, respectively.
Fig. 10.
Fig. 10. Bland-Altman plot of the agreement between the manually labeled regions and the segmentation results obtained from the proposed method for (a) optic disc (OD) and (b) optic cup (OC). Area was used as the evaluation standard. The horizontal and vertical axis represent the average value and the difference of the predicted (PRE) area and the manually labelled (i.e. ground-truth (GT)) area, respectively.
Fig. 11.
Fig. 11. Jacc distribution of different segmentation methods on optic disc (OD) and optic cup (OC). The box plot is composed of 5 metrics, which are minimum value, lower quartile, median, upper quartile, and maximum value. The red points represent outliers.
Fig. 12.
Fig. 12. Result visualization of optic disc (OD) and optic cup (OC) segmentation, where blue curves are manually labelled by expert and red curves are predictions of the methods. The first to fourth rows show the different appearance of OD and OC, including boundary blurring between OD and OC (the first row), blurring between OD and external area (the second row) and structural changes of OD and OC (third and fourth row). Each column represents a segmentation method, which is FCN, U-Net, PSPNet, Deeplabv3+ and the proposed method, respectively.
Fig. 13.
Fig. 13. Segmentation results of the proposed method for glaucoma cases in (a) REFUGE test set and (b) Drishti-GS1 test set, respectively.
Fig. 14.
Fig. 14. The limitations of the proposed method. These images have blurred target edges and irregular border shape.

Tables (5)

Tables Icon

Table 1. Quantitative results of the proposed method on REFUGE test set. Avg., Std., Max and Min represent average values, standard deviations, maximum and minimum, respectively.

Tables Icon

Table 2. Comparison with the state-of-the-art methods. Dice similarity coefficients (DSC) metric was used for evaluating the optic cup and disc, while the mean absolute error (MAE) was used for evaluating the vertical cup-to-disc ratio (vCDR).

Tables Icon

Table 3. Comparison with other segmentation methods on REFUGE test set. Our method achieves the highest Jacc with the lowest standard deviation.

Tables Icon

Table 4. The segmentation result of the proposed method for glaucoma and normal images on the REUFGE test set.

Tables Icon

Table 5. Comparison with other state-of-the-art methods on Drishti-GS1 test set.

Equations (5)

Equations on this page are rendered with MathJax. Learn more.

H ( l + 1 ) = σ ( A ~ H ( l ) W ( l ) ) ,
L g p ( p v , g v ) = min j [ 0 , N 1 ] i = 0 N 1 | | p v i g v ( j + i ) % N | | 1 ,
J a c c = | Y k Y ^ k | | Y k Y ^ k | × 100 % ,     D S C = 2 | Y k Y ^ k | | Y k | + | Y ^ k | × 100 % ,
M A E = a b s ( v C D R ( Y ^ O C , Y ^ O D ) v C D R ( Y O C , Y O D ) ) ,
S e n . = T P T P + F N × 100 % ,     S p e c . = T N T N + F P × 100 % ,