Advertisement

A Deep Learning Approach for Semantic Segmentation of Gonioscopic Images to Support Glaucoma Categorization

Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1248)

Abstract

We present a deep learning semantic segmentation algorithm for processing images acquired by a novel ophthalmic device, the NIDEK GS-1. The proposed model can sophisticate the current reference exam, called gonioscopy, for evaluating the risk of developing glaucoma, a severe eye pathology with a considerable worldwide impact in terms of costs and negative effects on affected people’s quality of life, and for inferring its categorization. The target eye region of gonioscopy is the interface between the iris and the cornea, and the anatomical structures that are located there. Our approach exploits a dense U-net architecture and is the first automatic system segmenting irido-corneal interface images from the novel device. Results show promising performance, providing about 88% of mean pixel-wise classification accuracy in a 5-fold cross-validation experiment on a very limited size dataset of annotated images.

Keywords

Image segmentation Deep learning Gonioscopy 

Notes

Acknowledgement

We thank the CVIP/VAMPIRE research team of the University of Dundee, Dundee (UK) and the VAMPIRE research team of the University of Edinburgh, Edinburgh (UK) for useful discussions and suggestions.

Disclosure

This work is fully funded by a Ph.D. studentship from NIDEK Technologies Srl.

References

  1. 1.
    Abràmoff, M.D., et al.: Improved automated detection of diabetic retinopathy on a publicly available dataset through integration of deep learning. Invest. Opthalmol. Vis. Sci. 57(13), 5200 (2016).  https://doi.org/10.1167/iovs.16-19964CrossRefGoogle Scholar
  2. 2.
    Alward, W.: Color Atlas of Gonioscopy. American Academy of Ophthalmology, San Francisco (2008)Google Scholar
  3. 3.
    Ben-Cohen, A., et al.: Retinal layers segmentation using fully convolutional network in OCT images (2017)Google Scholar
  4. 4.
    Chandra, A., Gupta, A., Gupta, V., Sihota, R., Azad, R., Chandra, P.: Comparative evaluation of RetCam vs. gonioscopy images in congenital glaucoma. Indian J. Ophthalmol. 62(2), 163 (2014).  https://doi.org/10.4103/0301-4738.116487CrossRefGoogle Scholar
  5. 5.
    Cheng, J., et al.: Closed angle glaucoma detection in RetCam images. In: 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology. IEEE, August 2010.  https://doi.org/10.1109/iembs.2010.5627290
  6. 6.
    Dutta, A., Zisserman, A.: The VIA annotation software for images, audio and video. In: Proceedings of the 27th ACM International Conference on Multimedia, MM 2019. ACM, New York (2019).  https://doi.org/10.1145/3343031.3350535
  7. 7.
    Fang, L., Cunefare, D., Wang, C., Guymer, R.H., Li, S., Farsiu, S.: Automatic segmentation of nine retinal layer boundaries in OCT images of non-exudative AMD patients using deep learning and graph search. Biomed. Opt. Express 8(5), 2732 (2017).  https://doi.org/10.1364/boe.8.002732CrossRefGoogle Scholar
  8. 8.
    Fauw, J.D., et al.: Clinically applicable deep learning for diagnosis and referral in retinal disease. Nat. Med. 24(9), 1342–1350 (2018).  https://doi.org/10.1038/s41591-018-0107-6CrossRefGoogle Scholar
  9. 9.
    He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: The IEEE International Conference on Computer Vision (ICCV), December 2015Google Scholar
  10. 10.
    Heckbert, P.: Graphics Gems IV. AP Professional, Boston (1994)zbMATHGoogle Scholar
  11. 11.
    Hertzog, L.H., Albrecht, K.G., LaBree, L., Lee, P.P.: Glaucoma care and conformance with preferred practice patterns. Ophthalmology 103(7), 1009–1013 (1996).  https://doi.org/10.1016/s0161-6420(96)30573-3CrossRefGoogle Scholar
  12. 12.
    Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2017).  https://doi.org/10.1109/cvpr.2017.243
  13. 13.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on International Conference on Machine Learning, ICML 2015, vol. 37, pp. 448–456 (2015). JMLR.org
  14. 14.
    Jegou, S., Drozdzal, M., Vazquez, D., Romero, A., Bengio, Y.: The one hundred layers tiramisu: fully convolutional DenseNets for semantic segmentation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, July 2017Google Scholar
  15. 15.
    Li, Z., He, Y., Keel, S., Meng, W., Chang, R.T., He, M.: Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs. Ophthalmology 125(8), 1199–1206 (2018).  https://doi.org/10.1016/j.ophtha.2018.01.023CrossRefGoogle Scholar
  16. 16.
    Liu, X., et al.: Semi-supervised automatic segmentation of layer and fluid region in retinal optical coherence tomography images using adversarial learning. IEEE Access 7, 3046–3061 (2019).  https://doi.org/10.1109/access.2018.2889321CrossRefGoogle Scholar
  17. 17.
    Orlando, J.I., et al.: U2-Net: a Bayesian u-net model with epistemic uncertainty feedback for photoreceptor layer segmentation in pathological OCT scans. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). IEEE, April 2019.  https://doi.org/10.1109/isbi.2019.8759581
  18. 18.
    Pead, E., et al.: Automated detection of age-related macular degeneration in color fundus photography: a systematic review. Surv. Ophthalmol. 64(4), 498–511 (2019).  https://doi.org/10.1016/j.survophthal.2019.02.003CrossRefGoogle Scholar
  19. 19.
    Pekala, M., Joshi, N., Liu, T.A., Bressler, N., DeBuc, D.C., Burlina, P.: Deep learning based retinal OCT segmentation. Comput. Biol. Med. 114, 103445 (2019).  https://doi.org/10.1016/j.compbiomed.2019.103445CrossRefGoogle Scholar
  20. 20.
    Raghavendra, U., Fujita, H., Bhandary, S.V., Gudigar, A., Tan, J.H., Acharya, U.R.: Deep convolution neural network for accurate diagnosis of glaucoma using digital fundus images. Inf. Sci. 441, 41–49 (2018).  https://doi.org/10.1016/j.ins.2018.01.051MathSciNetCrossRefGoogle Scholar
  21. 21.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-24574-4_28CrossRefGoogle Scholar
  22. 22.
    Roy, A.G., et al.: ReLayNet: retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks. Biomed. Opt. Express 8(8), 3627–3642 ( 2017).  https://doi.org/10.1364/BOE.8.003627. http://www.osapublishing.org/boe/abstract.cfm?URI=boe-8-8-3627
  23. 23.
    Tham, Y.C., Li, X., Wong, T.Y., Quigley, H.A., Aung, T., Cheng, C.Y.: Global prevalence of glaucoma and projections of glaucoma burden through 2040. Ophthalmology 121(11), 2081–2090 (2014).  https://doi.org/10.1016/j.ophtha.2014.05.013CrossRefGoogle Scholar
  24. 24.
    Trucco, E., et al.: Validating retinal fundus image analysis algorithms: issues and a proposal. Invest. Opthalmol. Vis. Sci. 54(5), 3546 (2013).  https://doi.org/10.1167/iovs.12-10347CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.VAMPIRE Project, Computing, School of Science and EngineeringUniversity of DundeeDundeeUK
  2. 2.Clinica Oculistica, DiNOGMIUniversity of GenoaGenoaItaly
  3. 3.Department of OphthalmologyHospital Santa MariaLisbonPortugal
  4. 4.NIDEK Technologies Srl.AlbignasegoItaly
  5. 5.Department of OphthalmologyNinewells Hospital, NHS TaysideDundeeUK
  6. 6.Department of OphthalmologyUniversity of DundeeDundeeUK
  7. 7.Princess Alexandra Eye Pavilion, NHS LothianEdinburghUK
  8. 8.OphthalmologyUniversity of EdinburghEdinburghUK

Personalised recommendations