Skip to main content
SpringerLink
Log in

DSLN: Dual-tutor student learning network for multiracial glaucoma detection

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Accurate early glaucoma detection is crucial to prevent further vision loss. However, using the off-the-shelf models against fundus image datasets of different races may lead to degraded performance due to domain shift. To address the issue, this paper proposes a dual-tutor student learning network (DSLN) for multiracial glaucoma detection. The proposed DSLN consists of an inter-image tutor, an intra-image tutor, student model and backbone network, which combines the advantages of domain adaptation and semi-supervised learning. The inter-image tutor uses CycleGAN for style transfer to reduce the appearance differences between labeled source domain and labeled target domain images, and transfers the learned knowledge to the student model by minimizing knowledge distillation loss. The intra-image tutor adopts the exponential moving average to leverage the unlabeled target domain and transfers the knowledge to the student model by minimizing prediction consistency loss. Moreover, the student model not only directly learns knowledge from the labeled target domain images, but also learns the intra-image knowledge and inter-image knowledge transfer by two tutors. Furthermore, the backbone integrates the context features of the local optic disc region and global fundus image via modified ResNet50. We conduct extensive experiments on three scenarios constructed from nine public fundus image datasets of three races. Comprehensive experimental results show that the proposed DSLN framework outperforms the state-of-the-art models and has good robustness and generalization: it can effectively overcome domain shift and accurately detect glaucoma from multi-ethnic fundus images.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17

Similar content being viewed by others

Availability of data and materials

Data related to the current study are available from the corresponding author on reasonable request.

References

  1. Tham Y-C, Li X, Wong TY, Quigley HA, Aung T, Cheng C-Y (2014) Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis. Ophthalmology 121(11):2081–2090

    Article  Google Scholar 

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

    Article  Google Scholar 

  3. Sarhan A, Rokne J, Alhajj R (2019) Glaucoma detection using image processing techniques: a literature review. Comput Med Imagd Graphics 78:101657

    Article  Google Scholar 

  4. Shilpa SK, Dinkar MY (2019) Retinal fundus image for glaucoma detection: a review and study. J Intell Syst 28(1):43–56

    Article  Google Scholar 

  5. Wu J, Yu S, Chen W, Ma K, Fu R, Liu H, Di X, Zheng Y (2020) Leveraging undiagnosed data for glaucoma classification with teacher-student learning. In:International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 731–740. Springer

  6. Diaz-Pinto A, Colomer A, Naranjo V, Morales S, Xu Y, FrangiAlejandro F (2019) Retinal image synthesis and semi-supervised learning for glaucoma assessment. IEEE Trans Med Imag 38(9):2211–2218

    Article  Google Scholar 

  7. Wang S, Lequan Y, Yang X, Chi-Wing F, Heng P-A (2019) Patch-based output space adversarial learning for joint optic disc and cup segmentation. IEEE Trans Medical Imag 38(11):2485–2495

    Article  Google Scholar 

  8. Liu P, Kong B, Li Z, Zhang S, Fang R (2019) Cfea: Collaborative feature ensembling adaptation for domain adaptation in unsupervised optic disc and cup segmentation. In:International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 521–529. Springer

  9. Zhu J-Y, Park T, Isola P, Efros A (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In:Proceedings of the IEEE international conference on computer vision, pp. 2223–2232

  10. Ashish I, Partha Sarathi M, Kishore DM (2015) An adaptive threshold based image processing technique for improved glaucoma detection and classification. Computer Methods Programs Biomed 122(2):229–244

    Article  Google Scholar 

  11. Tehmina K, Usman AM, Samina K, Amina J (2017) Improved automated detection of glaucoma from fundus image using hybrid structural and textural features. IET Image Process 11(9):693–700

    Article  Google Scholar 

  12. Koh JEW, Ng EYK, Bhandary SV, Laude A, Rajendra Acharya U (2018) Automated detection of retinal health using phog and surf features extracted from fundus images. Appl Intell 48(5):1379–1393

    Google Scholar 

  13. Claro M, Veras R, Santana A, Araújo F, Silva R, Almeida J, Leite D (2019) An hybrid feature space from texture information and transfer learning for glaucoma classification. J Visual Commun Image Represent 64:102597

    Article  Google Scholar 

  14. Kausu TR, Gopi Varun P, Wahid Khan A, Doma Wangchuk, Niwas Swamidoss Issac (2018) Combination of clinical and multiresolution features for glaucoma detection and its classification using fundus images. Biocybern Biomed Eng 38(2):329–341

    Article  Google Scholar 

  15. Mohamed Nur Ayuni, Zulkifley Mohd Asyraf, Zaki Wan Mimi Diyana Wan, Hussain Aini (2019) An automated glaucoma screening system using cup-to-disc ratio via simple linear iterative clustering superpixel approach. Biomed Signal Processing Control 53:101454

    Article  Google Scholar 

  16. Sun Jindong, Peng Yanjun, Guo Yanfei, Li Dapeng (2021) Segmentation of the multimodal brain tumor image used the multi-pathway architecture method based on 3d fcn. Neurocomputing 423:34–45

    Article  Google Scholar 

  17. Li Zhixi, He Yifan, Keel Stuart, Meng Wei, Chang Robert T, He Mingguang (2018) Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs. Ophthalmology 125(8):1199–1206

    Article  Google Scholar 

  18. Liu H, Liu Li I, Wormstone M, Qiao C, Zhang C, Liu P, Li S, Wang H, Mou D, Pang R et al (2019) Development and validation of a deep learning system to detect glaucomatous optic neuropathy using fundus photographs. Jama Ophthalmol 137(12):1353–1360

    Article  Google Scholar 

  19. Christopher M, Belghith A, Bowd C, Proudfoot JA, Goldbaum MH, Weinreb RN, Girkin CA, Liebmann JM, Zangwill LM (2018) Performance of deep learning architectures and transfer learning for detecting glaucomatous optic neuropathy in fundus photographs. Sci Rep 8(1):1–13

    Article  Google Scholar 

  20. Li L, Mai X, Liu H, Li Y, Wang X, Jiang L, Wang Z, Fan X, Wang N (2019) A large-scale database and a cnn model for attention-based glaucoma detection. IEEE Trans Med Imag 39(2):413–424

    Article  Google Scholar 

  21. Huazhu F, Cheng J, Yanwu X, Zhang C, Wong DWK, Liu J, Cao X (2018) Disc-aware ensemble network for glaucoma screening from fundus image. IEEE Trans Med Imag 37(11):2493–2501

    Article  Google Scholar 

  22. Bisneto TRV, Filho AO de Carvalho, Magalhães DMV (2020) Generative adversarial network and texture features applied to automatic glaucoma detection. Appl Soft Comput, 90:106165

  23. Chai Y, Liu H, Jie X (2018) Glaucoma diagnosis based on both hidden features and domain knowledge through deep learning models. Knowledge-Based Syst 161:147–156

    Article  Google Scholar 

  24. Mehta P, Petersen CA, Wen JC, Banitt MR, Chen PP, Bojikian KD, Egan C, Lee S-I, Balazinska M, Lee AY et al (2021) Automated detection of glaucoma with interpretable machine learning using clinical data and multi-modal retinal images. Am J Ophthalmol

  25. Bajwa MN, Malik MI, Siddiqui SA, Dengel A, Shafait F, Neumeier W, Ahmed S (2019) Two-stage framework for optic disc localization and glaucoma classification in retinal fundus images using deep learning. BMC Med Inf Decision Making 19(1):136

    Article  Google Scholar 

  26. Harish Kumar JR, Seelamantula CS, Kamath YS, Jampala R (2019) Rim-to-disc ratio outperforms cup-to-disc ratio for glaucoma prescreening. Sci Rep 9(1):1–9

    Article  Google Scholar 

  27. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In:Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2818–2826

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

  29. Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In:International Conference on Learning Representations

  30. Wang S, Wang X, Yong H, Shen Y, Yang Z, Gan M, Lei B (2020) Diabetic retinopathy diagnosis using multichannel generative adversarial network with semisupervision. IEEE Trans Autom Sci Eng 18(2):574–585

    Article  Google Scholar 

  31. Yu W, Lei B, Ng MK, Cheung AC, Shen Y, Wang S (2021) Tensorizing GAN with high-order pooling for Alzheimer’s disease assessment. IEEE Transactions on Neural Networks and Learning Systems, pp. 1–15

  32. Sivaswamy J, Krishnadas SR, Joshi GD, Jain M, TabishA US (2014) Drishti-gs: Retinal image dataset for optic nerve head (onh) segmentation. In:2014 IEEE 11th international symposium on biomedical imaging (ISBI), pp. 53–56. IEEE

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

  34. Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In:Thirty-first AAAI conference on artificial intelligence, pp. 4278–4284

  35. Budai A, Bock R, Maier A, Hornegger J, Michelson G (2013) Robust vessel segmentation in fundus images. Int J Biomed Imag

  36. Zhang Z, Yin FS, Liu J, Wong WK, Tan NM, Lee BH, Cheng J, Wong TY (2010) 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, pp. 3065–3068. IEEE

  37. Mahmudi T, Kafieh R, Rabbani H, Akhlagi M et al (2014) Comparison of macular octs in right and left eyes of normal people. In:Medical Imaging 2014: Biomedical Applications in Molecular, Structural, and Functional Imaging, 9038: 90381W. International Society for Optics and Photonics

  38. Orlando JI, Fu H, Breda JB, Keer K van, Bathula DR, Diaz-Pinto A, Fang R, Heng P-A, Kim J, Lee J et al (2020) Refuge challenge: a unified framework for evaluating automated methods for glaucoma assessment from fundus photographs. Medical Image Anal, 59:101570

  39. Diaz-Pinto A, Morales S, Naranjo V, Köhler T, Mossi JM, Navea A (2019) Cnns for automatic glaucoma assessment using fundus images: an extensive validation. Biomed Eng Online 18(1):29

    Article  Google Scholar 

  40. Almazroa A, Alodhayb S, Osman E, Ramadan E, Hummadi M, Dlaim M, Alkatee M, Raahemifar K, Lakshminarayanan V (2018) Retinal fundus images for glaucoma analysis: the riga dataset. In:Medical Imaging 2018: Imaging Informatics for Healthcare, Research, and Applications, vol. 10579, p. 105790B. International Society for Optics and Photonics

  41. Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In:2009 IEEE conference on computer vision and pattern recognition, pp. 248–255. IEEE

  42. Kingma DP, Ba J (2015) Adam: A method for stochastic optimization. In:International conference on learning representation, pp. 1–15

  43. Poonguzhali E, Malaya KN (2021) Glaucoma assessment from color fundus images using convolutional neural network. Int J Imag Syst Technol 31(2):955–971

    Article  Google Scholar 

  44. Raghavendra U, Fujita H, Bhandary SV, Gudigar A, Tan JH, Rajendra Acharya U (2018) Deep convolution neural network for accurate diagnosis of glaucoma using digital fundus images. Inf Sci 441:41–49

    Article  MathSciNet  Google Scholar 

  45. Lee D-H et al (2013) Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In Workshop on challenges in representation learning, ICML, 3: 896

  46. Chollet F (2017) Xception: Deep learning with depthwise separable convolutions. In:Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1251–1258

Download references

Acknowledgements

The authors gratefully acknowledge the financial supports by the National Natural Science Foundation of China (Grant No. 61976126), Shandong Nature Science Foundation of China (Grant No. ZR2019MF003, ZR2020MF132, ZR2020MH291).

Funding

This work was supported in part by the National Natural Science Foundation of China (Grant No. 61976126), Shandong Nature Science Foundation of China (Grant No. ZR2019MF003, ZR2020MF132, ZR2020MH291).

Author information

Authors and Affiliations

  1. College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, 266590, Shandong, China

    Yanfei Guo, Yanjun Peng, Jindong Sun, Dapeng Li & Bin Zhang

  2. Shandong Province Key Laboratory of Wisdom Mining Information Technology, Shandong University of Science and Technology, Qingdao, 266590, Shandong, China

    Yanjun Peng

Authors
  1. Yanfei Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yanjun Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jindong Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Dapeng Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Bin Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Yanfei Guo contributed to conceptualization, methodology, software, writing the original draft. Yanjun Peng helped in data curation, supervision. Jindong Sun contributed to investigation, formal analysis, software. Dapeng Li contributed to visualization, writing—review and editing. Bin Zhang contributed to resources, project administration.

Corresponding author

Correspondence to Yanjun Peng.

Ethics declarations

Conflicts of interest

The authors declare that they have no conflicts of interest.

Code availability

Some of the codes generated or used during the study are available from the corresponding author by request.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Guo, Y., Peng, Y., Sun, J. et al. DSLN: Dual-tutor student learning network for multiracial glaucoma detection. Neural Comput & Applic 34, 11885–11910 (2022). https://doi.org/10.1007/s00521-022-07078-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-022-07078-8

Keywords

Search

Navigation