Skip to main content
Springer Nature Link
Log in

Semi-supervised Learning for Nerve Segmentation in Corneal Confocal Microscope Photography

  • Conference paper
  • First Online:
Medical Image Computing and Computer Assisted Intervention – MICCAI 2022 (MICCAI 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13434))

  • 6654 Accesses

Abstract

Corneal nerve fiber medical indicators are promising metrics for diagnosis of diabetic peripheral neuropathy. However, automatic nerve segmentation still faces the issues of insufficient data and expensive annotations. We propose a semi-supervised learning framework for CCM image segmentation. It includes self-supervised pre-training, supervised fine-tuning and self-training. The contrastive learning for pre-training pays more attention to global features and ignores local semantics, which is not friendly to the downstream segmentation task. Consequently, we adopt pre-training using masked image modeling as a proxy task on unlabeled images. After supervised fine-tuning, self-training is employed to make full use of unlabeled data. Experimental results show that our proposed method is effective and better than the supervised learning using nerve annotations with three-pixel-width dilation.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Bao, H., et al.: BEIT: BERT pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)

  2. Chen, T., et al.: A simple framework for contrastive learning of visual representations. In: ICML, pp. 1597–1607 (2020)

    Google Scholar 

  3. Chen, X., et al.: Context autoencoder for self-supervised representation learning. arXiv preprint arXiv:2202.03026 (2022)

  4. Chen, X., et al.: Semi-supervised semantic segmentation with cross pseudo supervision. In: CVPR, pp. 2613–2622 (2021)

    Google Scholar 

  5. Chen, X., et al.: Small nerve fiber quantification in the diagnosis of diabetic sensorimotor polyneuropathy: comparing corneal confocal microscopy with intraepidermal nerve fiber density. Diabetes Care 38(6), 1138–1144 (2015)

    Article  Google Scholar 

  6. Ferdousi, M., et al.: Diagnosis of neuropathy and risk factors for corneal nerve loss in type 1 and type 2 diabetes: a corneal confocal microscopy study. Diabetes Care 44(1), 150–156 (2021)

    Article  Google Scholar 

  7. Grill, J.B., et al.: Bootstrap your own latent - a new approach to self-supervised learning. In: NIPS, vol. 33, pp. 21271–21284 (2020)

    Google Scholar 

  8. He, K., et al.: Momentum contrast for unsupervised visual representation learning. In: CVPR, pp. 9729–9738 (2020)

    Google Scholar 

  9. He, K., et al.: Masked autoencoders are scalable vision learners. arXiv preprint arXiv:2111.06377 (2021)

  10. Kim, J., et al.: Automatic analysis of corneal nerves imaged using in vivo confocal microscopy. Clin. Exp. Optom. 101(2), 147–161 (2018)

    Article  Google Scholar 

  11. Kucharski, A., et al.: CNN-watershed: a watershed transform with predicted markers for corneal endothelium image segmentation. Biomed. Sign. Process. Control 68, 102805 (2021)

    Article  Google Scholar 

  12. Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: CVPR, pp. 4681–4690 (2017)

    Google Scholar 

  13. Lee, D.H.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: ICML, p. 896 (2013)

    Google Scholar 

  14. Lin, L., et al.: Automated segmentation of corneal nerves in confocal microscopy via contrastive learning based synthesis and quality enhancement. In: ISBI, pp. 1314–1318 (2021)

    Google Scholar 

  15. Mou, L., et al.: CS2-net: deep learning segmentation of curvilinear structures in medical imaging. Med. Image Anal. 67, 101874 (2021)

    Article  Google Scholar 

  16. Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving Jigsaw puzzles. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 69–84. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46466-4_5

    Chapter  Google Scholar 

  17. Pathak, D., et al.: Context encoders: Feature learning by inpainting. In: CVPR, pp. 2536–2544 (2016)

    Google Scholar 

  18. Pham, H., et al.: Meta pseudo labels. In: CVPR, pp. 11557–11568 (2021)

    Google Scholar 

  19. 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_28

    Chapter  Google Scholar 

  20. Salahuddin, T., et al.: Evaluation of loss functions for segmentation of corneal nerves. In: IECBES, pp. 533–537 (2021)

    Google Scholar 

  21. Samuli, L., et al.: Temporal ensembling for semi-supervised learning. In: ICLR, pp. 6–17 (2017)

    Google Scholar 

  22. Scarpa, F., et al.: Automatic evaluation of corneal nerve tortuosity in images from in vivo confocal microscopy. Invest. Opthalmol. Visual Sci. 52(9), 6404–6408 (2011)

    Article  Google Scholar 

  23. Shtein, R.M., et al.: Corneal confocal microscopy as a measure of diabetic neuropathy. Diabetes 62(1), 25–26 (2013)

    Article  Google Scholar 

  24. Tarvainen, A., et al.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: NIPS, vol. 30, pp. 1195–1204 (2017)

    Google Scholar 

  25. Tavakoli, M., et al.: Corneal confocal microscopy: a novel noninvasive test to diagnose and stratify the severity of human diabetic neuropathy. Diabetes Care 33(8), 1792–1797 (2010)

    Article  Google Scholar 

  26. Tavakoli, M., et al.: Dual-model automatic detection of nerve-fibres in corneal confocal microscopy images. In: ICLR, 13, no. 1, pp. 300–307 (2010)

    Google Scholar 

  27. Wei, S., et al.: A deep learning model for automated sub-basal corneal nerve segmentation and evaluation using in vivo confocal microscopy. Transl. Vis. Sci. Technol. 9(2), 32–32 (2020)

    Article  Google Scholar 

  28. Williams, B.M., et al.: An artificial intelligence-based deep learning algorithm for the diagnosis of diabetic neuropathy using corneal confocal microscopy: a development and validation study. Diabetologia 63(2), 419–430 (2019). https://doi.org/10.1007/s00125-019-05023-4

    Article  Google Scholar 

  29. Xie, Q., et al.: Self-training with noisy student improves imagenet classification. In: CVPR, pp. 10687–10698 (2020)

    Google Scholar 

  30. Xie, Q., et al.: Unsupervised data augmentation for consistency training. In: NIPS, vol. 33, pp. 6256–6268 (2020)

    Google Scholar 

  31. Xie, Z., et al.: SimMIM: a simple framework for masked image modeling. arXiv preprint arXiv:2111.09886 (2021)

  32. Yang, C., et al.: Multi-discriminator adversarial convolutional network for nerve fiber segmentation in confocal corneal microscopy images. IEEE J. Biomed. Health Inform. 26(2), 648–659 (2022)

    Article  Google Scholar 

  33. Yildiz, E., et al.: Generative adversarial network based automatic segmentation of corneal subbasal nerves on in vivo confocal microscopy images. Transl. Vis. Sci. Technol. 10(6), 33–33 (2021)

    Article  Google Scholar 

  34. Yu, J., et al.: Free-form image inpainting with gated convolution. In: ICCV (2019)

    Google Scholar 

  35. Yu, L., Wang, S., Li, X., Fu, C.-W., Heng, P.-A.: Uncertainty-aware self-ensembling model for semi-supervised 3D left atrium segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 605–613. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32245-8_67

    Chapter  Google Scholar 

  36. Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 649–666. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_40

    Chapter  Google Scholar 

  37. Zhang, Y., Yang, L., Chen, J., Fredericksen, M., Hughes, D.P., Chen, D.Z.: Deep adversarial networks for biomedical image segmentation utilizing unannotated images. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 408–416. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66179-7_47

    Chapter  Google Scholar 

  38. Zhao, Y., et al.: Automated tortuosity analysis of nerve fibers in corneal confocal microscopy. IEEE Trans. Med. Imaging 39(9), 2725–2737 (2020)

    Article  Google Scholar 

  39. Zhou, J., et al.: iBot: image BERT pre-training with online tokenizer. arXiv preprint arXiv:2111.07832 (2021)

  40. Ziegler, D., et al.: Early detection of nerve fiber loss by corneal confocal microscopy and skin biopsy in recently diagnosed type 2 diabetes. Diabetes 63(7), 2454–2463 (2014)

    Article  Google Scholar 

  41. Zoph, B., et al.: Rethinking pre-training and self-training. In: NIPS, vol. 33, pp. 3833–3845 (2020)

    Google Scholar 

Download references

Acknowledgements

This work is supported by China National Key R &D Program (No. 2020YFC2009006 and 2020YFC2009000), and Natural Science Basic Research Plan in Shaanxi Province of China (2020JM-129).

Author information

Authors and Affiliations

  1. School of Electronics and Information, Northwestern Polytechnical University, Xi’an, 710072, China

    Jun Wu, Bo Shen & Hanwen Zhang

  2. Department of Ophthalmology, Beijing Hospital, Beijing, 100730, China

    Jianing Wang & Jianfeng Huang

  3. Department of Endocrinology, Beijing Hospital, Beijing, 100730, China

    Qi Pan & Lixin Guo

  4. National Center of Gerontology, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing, 100730, China

    Jianing Wang, Qi Pan, Jianfeng Huang & Lixin Guo

  5. Vistel AI Lab, Visionary Intelligence Ltd., Beijing, 100080, China

    Jianchun Zhao & Dayong Ding

  6. Key Lab of DEKE, Renmin University of China, Beijing, 100872, China

    Gang Yang & Xirong Li

Authors
  1. Jun Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bo Shen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hanwen Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jianing Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Qi Pan
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jianfeng Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Lixin Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Jianchun Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Gang Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Xirong Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Dayong Ding
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Qi Pan .

Editor information

Editors and Affiliations

  1. Rochester Institute of Technology, Rochester, NY, USA

    Linwei Wang

  2. Chinese University of Hong Kong, Hong Kong, Hong Kong

    Qi Dou

  3. University of Virginia, Charlottesville, VA, USA

    P. Thomas Fletcher

  4. National Center for Tumor Diseases (NCT/UCC), Dresden, Germany

    Stefanie Speidel

  5. Case Western Reserve University, Cleveland, OH, USA

    Shuo Li

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Wu, J. et al. (2022). Semi-supervised Learning for Nerve Segmentation in Corneal Confocal Microscope Photography. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds) Medical Image Computing and Computer Assisted Intervention – MICCAI 2022. MICCAI 2022. Lecture Notes in Computer Science, vol 13434. Springer, Cham. https://doi.org/10.1007/978-3-031-16440-8_5

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-16440-8_5

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-16439-2

  • Online ISBN: 978-3-031-16440-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Societies and partnerships