Skip to main content
SpringerLink
Log in

CAFR-CNN: coarse-to-fine adaptive faster R-CNN for cross-domain joint optic disc and cup segmentation

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Glaucoma is a leading cause of blindness. Accurate and efficient segmentation of the optic disc and cup from fundus images is important for glaucoma screening. However, using off-the-shelf networks against new datasets may lead to degraded performances due to domain shift. To address this issue, in this paper, we propose a coarse-to-fine adaptive Faster R-CNN framework for cross-domain joint optic disc and cup segmentation. The proposed CAFR-CNN consists of the Faster R-CNN detector, a spatial attention-based region alignment module, a pyramid ROI alignment module and a prototype-based semantic alignment module. The Faster R-CNN detector extracts features from fundus images using a VGG16 network as a backbone. The spatial attention-based region alignment module extracts the region of interest through a spatial mechanism and aligns the feature distribution from different domains via multilayer adversarial learning to achieve a coarse-grained adaptation. The pyramid ROI alignment module learns multilevel contextual features to prevent misclassifications due to the similar appearances of the optic disc and cup. The prototype-based semantic alignment module minimizes the distance of global prototypes with the same category between the target domain and source domain to achieve a fine-grained adaptation. We evaluated the proposed CAFR-CNN framework under different scenarios constructed from four public retinal fundus image datasets (REFUGE2, DRISHTI-GS, DRIONS-DB and RIM-ONE-r3). The experimental results show that the proposed method outperforms the current state-of-the-art methods and has good accuracy and robustness: it not only avoids the adverse effects of low contrast and noise interference but also preserves the shape priors and generates more accurate contours.

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

Similar content being viewed by others

References

  1. Mary VS, Rajsingh EB, Naik GR (2016) Retinal fundus image analysis for diagnosis of glaucoma: a comprehensive survey. IEEE Access 4:4327–4354

    Article  Google Scholar 

  2. Tham Y-C et al (2014) Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis. Ophthalmology 121:2081–2090

    Article  Google Scholar 

  3. Drance S et al (2001) Risk factors for progression of visual field abnormalities in normal-tension glaucoma. Am J Ophthal 131:699–708

    Article  Google Scholar 

  4. Baum J et al (1995) Assessment of intraocular pressure by palpation. Am J Ophthal 119:650–651

    Article  Google Scholar 

  5. Garway-Heath DF, Hitchings RA (1998) Quantitative evaluation of the optic nerve head in early glaucoma. Br J Ophthalmol 82:352–361

    Article  Google Scholar 

  6. Jonas JB et al (2000) Ranking of optic disc variables for detection of glaucomatous optic nerve damage. Invest Ophthal Vis Sci 41:1764–1773

    Google Scholar 

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

    Article  Google Scholar 

  8. Aquino G et al (2020) Novel nonlinear hypothesis for the delta parallel robot modeling. IEEE Access 8(1):46324–46334

    Article  Google Scholar 

  9. de Jesús Rubio J (2009) SOFMLS: online self-organizing fuzzy modified least-squares network. IEEE Trans Fuzzy Syst 17(6):1296–1309

    Article  Google Scholar 

  10. Chiang H-S, Chen M-Y, Huang Y-J (2019) Wavelet-based EEG processing for epilepsy detection using fuzzy entropy and associative petri net. IEEE Access 7:103255–103262

    Article  Google Scholar 

  11. Elias I, Rubio JJ, Martinez DI et al (2020) Genetic algorithm with radial basis mapping network for the electricity consumption modeling. Appl Sci 10(12):4239

    Article  Google Scholar 

  12. Meda-Campaña JA (2018) On the estimation and control of nonlinear systems with parametric uncertainties and noisy outputs. IEEE Access 6:31968–31973

    Article  Google Scholar 

  13. Hernández G, Zamora E, Sossa H et al (2020) Hybrid neural networks for big data classification. Neurocomputing 390:327–340

    Article  Google Scholar 

  14. Orlando JI et al (2020) Refuge challenge: a unified framework for evaluating automated methods for glaucoma assessment from fundus photographs. Med Image Anal 59:101570

    Article  Google Scholar 

  15. Carmona EJ, Rincón M, García-Feijoo J, Martínez-de-la-Casa JM (2008) Identification of the optic nerve head with genetic algorithms. Artif Intell Med 43:243–259

    Article  Google Scholar 

  16. Sivaswamy J et al (2014) Drishti-gs: retinal image dataset for optic nerve head (onh) segmentation. In: 2014 IEEE 11th international symposium on biomedical imaging (ISBI). IEEE

  17. Fumero F et al (2011) RIM-ONE: an open retinal image database for optic nerve evaluation. In: 2011 24th international symposium on computer-based medical systems (CBMS). IEEE

  18. Zhang Z et al (2009) Convex hull based neuro-retinal optic cup ellipse optimization in glaucoma diagnosis. In: 2009 annual international conference of the IEEE engineering in medicine and biology society. IEEE

  19. Khalil T et al (2017) Improved automated detection of glaucoma from fundus image using hybrid structural and textural features. IET Image Process 11:693–700

    Article  Google Scholar 

  20. Cheng J et al (2015) Sparse dissimilarity-constrained coding for glaucoma screening. IEEE Trans Biomed Eng 62:1395–1403

    Article  Google Scholar 

  21. Mary MCVS et al (2015) An empirical study on optic disc segmentation using an active contour model. Biomed Sig Process Control 18:19–29

    Article  Google Scholar 

  22. Damon WWK et al (2012) Automatic detection of the optic cup using vessel kinking in digital retinal fundus images. In: 2012 9th IEEE international symposium on biomedical imaging (ISBI). IEEE

  23. Balakrishnan U (2017) NDC-IVM: an automatic segmentation of optic disc and cup region from medical images for glaucoma detection. J Innov Optical Health Sci 10:1750007

    Article  Google Scholar 

  24. Maninis K-K et al (2016) Deep retinal image understanding. In: International conference on medical image computing and computer-assisted intervention. Springer, Cham, pp 140–148

  25. Sevastopolsky A (2017) Optic disc and cup segmentation methods for glaucoma detection with modification of U-Net convolutional neural network. Pattern Recogn Image Anal 27:618–624

    Article  Google Scholar 

  26. Fu H et al (2017) Joint optic disc and cup segmentation based on multi-label deep network and polar transformation. IEEE Trans Med Imag 37:1597–1605

    Article  Google Scholar 

  27. Liu Q et al (2019) DDNet: cartesian-polar dual-domain network for the joint optic disc and cup segmentation. arXiv:1904.08773

  28. Jiang Y, Tan N, Peng T (2019) Optic disc and cup segmentation based on deep convolutional generative adversarial networks. IEEE Access 7:64483–64493

    Article  Google Scholar 

  29. Al-Bander B et al (2018) Dense fully convolutional segmentation of the optic disc and cup in colour fundus for glaucoma diagnosis. Symmetry 10:87

    Article  Google Scholar 

  30. Iandola F et al (2014) Densenet: implementing efficient convnet descriptor pyramids. arXiv:1404.1869

  31. Liu Q et al (2019) A spatial-aware joint optic disc and cup segmentation method. Neurocomputing 359:285–297

    Article  Google Scholar 

  32. Jiang Y et al (2019) Jointrcnn: a region-based convolutional neural network for optic disc and cup segmentation. IEEE Trans Biomed Eng 67:335–343

    Article  Google Scholar 

  33. Shankaranarayana SM et al (2019) Fully convolutional networks for monocular retinal depth estimation and optic disc-cup segmentation. IEEE J Biomed Health Inf 23:1417–1426

    Article  Google Scholar 

  34. Wang S et al (2019) Patch-based output space adversarial learning for joint optic disc and cup segmentation. IEEE Trans Med Imag 38:2485–2495

    Article  Google Scholar 

  35. Liu P et al (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. Springer, Cham, pp 521–529

  36. Chen C et al (2019) Synergistic image and feature adaptation: towards cross-modality domain adaptation for medical image segmentation. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 865–872

  37. Zhang Y et al (2018) Task driven generative modeling for unsupervised domain adaptation: application to x-ray image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, Cham, pp 599–607

  38. Zhang Z, Yang L, Zheng Y (2018) Translating and segmenting multimodal medical volumes with cycle-and shape-consistency generative adversarial network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9242–9251

  39. Chen C et al (2018) Semantic-aware generative adversarial nets for unsupervised domain adaptation in chest x-ray segmentation. In: International workshop on machine learning in medical imaging. Springer, Cham, pp 143–151

  40. Liu D et al (2020) Unsupervised instance segmentation in microscopy images via panoptic domain adaptation and task re-weighting. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 4243–4252

  41. Dong J et al (2020) What can be transferred: unsupervised domain adaptation for endoscopic lesions segmentation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, vol 33, pp 865–872

  42. Zhao H et al (2017) Pyramid scene parsing network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2881–2890

  43. Boney R, Ilin A (2017) Semi-supervised few-shot learning with prototypical networks. CoRR arXiv:1711.10856

  44. Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. In: Advances in neural information processing systems, pp 4077–4087

  45. Chen C et al (2019) Progressive feature alignment for unsupervised domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 627–636

  46. Xie S et al (2018) Learning semantic representations for unsupervised domain adaptation. In: International conference on machine learning, pp 5423–5432

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

  48. Deng J et al (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. IEEE, pp 248–255

  49. Kingma DP, Adam JB (2014) A method for stochastic optimization. arXiv:1412.6980

  50. Son J, Park SJ, Jung K-H (2019) Towards accurate segmentation of retinal vessels and the optic disc in fundoscopic images with generative adversarial networks. J Digit Imag 32:499–512

    Article  Google Scholar 

  51. Xu Y et al (2014) Optic cup segmentation for glaucoma detection using low-rank superpixel representation. In: International conference on medical image computing and computer-assisted intervention. Springer, Cham, pp 788–795

  52. Cheng J et al (2017) Quadratic divergence regularized SVM for optic disc segmentation. Biomed Opt Express 8:2687–2696

    Article  Google Scholar 

  53. Szegedy C et al (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9

  54. Wang S et al (2019) Boundary and entropy-driven adversarial learning for fundus image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, Cham, pp 102–110

  55. Yin P et al (2019) PM-net: pyramid multi-label network for joint optic disc and cup segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, Cham, pp 129–137

  56. Zhang Z et al (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. IEEE, pp 3065–3068

  57. Baskaran M et al (2015) The prevalence and types of glaucoma in an urban Chinese population: the Singapore Chinese eye study. JAMA Ophthal 133(8):874–880

    Article  Google Scholar 

  58. Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) Ssd: single shot multibox detector. In: European conference on computer vision. Springer, Cham, pp 21–37

  59. Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580–587

  60. Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440–1448

  61. Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv:1804.02767

  62. Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, pp 91–99

  63. Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510–4520

  64. 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

  65. Iandola F, Moskewicz M, Karayev S, Girshick R, Darrell T, Keutzer K (2014) Densenet: implementing efficient convnet descriptor pyramids. arXiv:1404.1869

  66. 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

  67. 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

Download references

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. ZR2019 MF003, ZR2017 MF054].

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 & Bin Zhang

  2. 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. Bin Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Yanfei Guo proposed the method and conducted the experiments, analysed the data and wrote the manuscript. Yanjun Peng supervised the project and participated in manuscript revisions. Bin Zhang provided critical reviews that helped improve the manuscript.

Corresponding author

Correspondence to Yanjun Peng.

Ethics declarations

Conflict of interests

The authors declare that they have no conflicts of interest.

Additional information

Availability of data and materials

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

Code availability

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

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. & Zhang, B. CAFR-CNN: coarse-to-fine adaptive faster R-CNN for cross-domain joint optic disc and cup segmentation. Appl Intell 51, 5701–5725 (2021). https://doi.org/10.1007/s10489-020-02145-w

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-020-02145-w

Keywords

Search

Navigation