Skip to main content

Retinal Abnormalities Recognition Using Regional Multitask Learning

Part of the Lecture Notes in Computer Science book series (LNIP,volume 11764)

Abstract

The number of people suffering from retinal diseases increases with population aging and the popularity of electronic screens. Previous studies on deep learning based automatic screening generally focused on specific types of retinal diseases, such as diabetic retinopathy and glaucoma. Since patients may suffer from various types of retinal diseases simultaneously, these solutions are not clinically practical. To address this issue, we propose a novel deep learning based method that can recognise 36 different retinal diseases with a single model. More specifically, the proposed method uses a region-specific multi-task recognition model by learning diseases affecting different regions of the retina with three sub-networks. The three sub-networks are semantically trained to recognise diseases affecting optic-disc, macula and entire retina. Our contribution is two-fold. First, we use multitask learning for retinal disease classification and achieve significant improvements for recognising three main groups of retinal diseases in general, macular and optic-disc regions. Second, we collect a multi-label retinal dataset to the community as standard benchmark and release it for further research opportunities.

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-32239-7_4
  • Chapter length: 9 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   99.00
Price excludes VAT (USA)
  • ISBN: 978-3-030-32239-7
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   129.99
Price excludes VAT (USA)
Fig. 1.
Fig. 2.
Fig. 3.

Notes

  1. 1.

    https://www.kaggle.com/c/diabetic-retinopathy-detection.

  2. 2.

    We experimented with all Inception-V3/Inception-Resnet-V2 settings and figured out a mixture of them gave the best performance of all. Network training used Adam with a learning rate of 1e-5 which decayed every three epochs with ratio of 0.9 for total 14 epochs. We used Keras distributed machine learning system with 8 replicas running each on a NVidia 1080Ti GPU. The input size of general stream is 800, while the input size of macular and optic-task stream is 600 and 300 respectively.

  3. 3.

    We set a label named as other general, macular or optic-disc disease to indicate a gathering of rare diseases in each task. This label for optic-disc task represents disease such as morning glory syndrome, melanocytoma of optic disc, membrane tissue on the optic disc and etc.

References

  1. 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: a systematic review and meta-analysis. Ophthalmology 121(11), 2081–2090 (2014)

    CrossRef  Google Scholar 

  2. Wang, P., et al.: Development and validation of a deep-learning algorithm for the detection of polyps during colonoscopy. Nat. Biomed. Eng. 2(10), 741 (2018)

    Google Scholar 

  3. Playout, C., Duval, R., Cheriet, F.: A multitask learning architecture for simultaneous segmentation of bright and red lesions in fundus images. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11071, pp. 101–108. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00934-2_12

    CrossRef  Google Scholar 

  4. Grassmann, F., et al.: A deep learning algorithm for prediction of age-related eye disease study severity scale for age-related macular degeneration from color fundus photography. Ophthalmology 125(9), 1410–1420 (2018)

    CrossRef  Google Scholar 

  5. Fu, H., et al.: Disc-aware ensemble network for glaucoma screening from fundus image. IEEE Trans. Med. Imaging 37(11), 2493–2501 (2018)

    CrossRef  Google Scholar 

  6. Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568–576 (2014)

    Google Scholar 

  7. Redmon, J., Farhadi, A.: Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)

  8. Araújo, T., Aresta, G., Galdran, A., Costa, P., Mendonça, A.M., Campilho, A.: UOLO - automatic object detection and segmentation in biomedical images. In: Stoyanov, D., et al. (eds.) DLMIA/ML-CDS -2018. LNCS, vol. 11045, pp. 165–173. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00889-5_19

    CrossRef  Google Scholar 

  9. Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-NMS-improving object detection with one line of code. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5561–5569 (2017)

    Google Scholar 

  10. Sinthanayothin, C., Boyce, J.F., Cook, H.L., Williamson, T.H.: Automated localisation of the optic disc, fovea, and retinal blood vessels from digital colour fundus images. Br. J. Ophthalmol. 83(8), 902–910 (1999)

    CrossRef  Google Scholar 

  11. Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921–2929 (2016)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Zongyuan Ge .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 8399 KB)

Rights and permissions

Reprints and Permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Wang, X., Ju, L., Zhao, X., Ge, Z. (2019). Retinal Abnormalities Recognition Using Regional Multitask Learning. In: , et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. MICCAI 2019. Lecture Notes in Computer Science(), vol 11764. Springer, Cham. https://doi.org/10.1007/978-3-030-32239-7_4

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-32239-7_4

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-32238-0

  • Online ISBN: 978-3-030-32239-7

  • eBook Packages: Computer ScienceComputer Science (R0)