Advertisement

Multi-context Deep Network for Angle-Closure Glaucoma Screening in Anterior Segment OCT

  • Huazhu Fu
  • Yanwu XuEmail author
  • Stephen Lin
  • Damon Wing Kee Wong
  • Baskaran Mani
  • Meenakshi Mahesh
  • Tin Aung
  • Jiang Liu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11071)

Abstract

A major cause of irreversible visual impairment is angle-closure glaucoma, which can be screened through imagery from Anterior Segment Optical Coherence Tomography (AS-OCT). Previous computational diagnostic techniques address this screening problem by extracting specific clinical measurements or handcrafted visual features from the images for classification. In this paper, we instead propose to learn from training data a discriminative representation that may capture subtle visual cues not modeled by predefined features. Based on clinical priors, we formulate this learning with a presented Multi-Context Deep Network (MCDN) architecture, in which parallel Convolutional Neural Networks are applied to particular image regions and at corresponding scales known to be informative for clinically diagnosing angle-closure glaucoma. The output feature maps of the parallel streams are merged into a classification layer to produce the deep screening result. Moreover, we incorporate estimated clinical parameters to further enhance performance. On a clinical AS-OCT dataset, our system is validated through comparisons to previous screening methods.

References

  1. 1.
    Ciregan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: CVPR, pp. 3642–3649 (2012)Google Scholar
  2. 2.
    Fu, H., Cheng, J., Xu, Y., Wong, D., Liu, J., Cao, X.: Joint optic disc and cup segmentation based on multi-label deep network and polar transformation. IEEE Trans. Med. Imaging 37(7), 1597–1605 (2018)CrossRefGoogle Scholar
  3. 3.
    Fu, H., et al.: Disc-aware ensemble network for glaucoma screening from fundus image. IEEE Trans. Med. Imaging (2018)Google Scholar
  4. 4.
    Fu, H., Xu, Y., Lin, S., Wong, D.W.K., Liu, J.: DeepVessel: Retinal Vessel Segmentation via Deep Learning and Conditional Random Field. In: MICCAI, pp. 132–139 (2016)Google Scholar
  5. 5.
    Fu, H., et al.: Segmentation and quantification for angle-closure glaucoma assessment in anterior segment OCT. IEEE Trans. Med. Imaging 36(9), 1930–1938 (2017)CrossRefGoogle Scholar
  6. 6.
    Fu, H., et al.: Automatic anterior chamber angle structure segmentation in AS-OCT image based on label transfer. In: EMBC, pp. 1288–1291 (2016)Google Scholar
  7. 7.
    Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)Google Scholar
  8. 8.
    Gulshan, V., Peng, L., Coram, M., et al.: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. J. Am. Med. Assoc. 304(6), 649–656 (2016)Google Scholar
  9. 9.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML, pp. 448–456 (2015)Google Scholar
  10. 10.
    Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)Google Scholar
  11. 11.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)CrossRefGoogle Scholar
  12. 12.
    Leung, C., Weinreb, R.: Anterior chamber angle imaging with optical coherence tomography. Eye 25(3), 261–267 (2011)CrossRefGoogle Scholar
  13. 13.
    Nongpiur, M., Haaland, B., Friedman, D., et al.: Classification algorithms based on anterior segment optical coherence tomography measurements for detection of angle closure. Ophthalmology 120(1), 48–54 (2013)CrossRefGoogle Scholar
  14. 14.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv 1409.1556 (2014)Google Scholar
  15. 15.
    Tian, J., Marziliano, P., Baskaran, M., Wong, H., Aung, T.: Automatic anterior chamber angle assessment for HD-OCT images. IEEE Trans. Biomed. Eng. 58(11), 3242–3249 (2011)CrossRefGoogle Scholar
  16. 16.
    Wu, R., Nongpiur, M., He, M., et al.: Association of narrow angles with anterior chamber area and volume measured with anterior-segment optical coherence tomography. Arch. Ophthalmol. 129(5), 569–574 (2011)CrossRefGoogle Scholar
  17. 17.
    Xu, Y., et al.: Automated anterior chamber angle localization and glaucoma type classification in OCT images. In: EMBC, pp. 7380–7383 (2013)Google Scholar
  18. 18.
    Xu, Y., et al.: Anterior chamber angle classification using multiscale histograms of oriented gradients for glaucoma subtype identification. In: EMBC, pp. 3167–3170 (2012)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Huazhu Fu
    • 1
  • Yanwu Xu
    • 2
    Email author
  • Stephen Lin
    • 3
  • Damon Wing Kee Wong
    • 1
  • Baskaran Mani
    • 4
  • Meenakshi Mahesh
    • 4
  • Tin Aung
    • 4
  • Jiang Liu
    • 5
  1. 1.Institute for Infocomm ResearchA*STARSingaporeSingapore
  2. 2.Guangzhou Shiyuan Electronic Technology Company LimitedShenzhenChina
  3. 3.Microsoft ResearchBeijingChina
  4. 4.Singapore Eye Research InstituteSingaporeSingapore
  5. 5.Cixi Institute of Biomedical EngineeringCASNingboChina

Personalised recommendations