Abstract
Computerized medical evaluation of the corneal endothelium is challenging because it requires costly equipment and specialized personnel, not to mention that conventional techniques require manual annotations that are difficult to acquire. This study aims to obtain reliable segmentations without requiring large data sets labeled by expert personnel. To address this problem, we use the Barlow Twins approach to pre-train the encoder of a UNet model in an unsupervised manner. Then, with few labeled data, we train the segmentation. Encouraging results show that it is possible to address the challenge of limited data availability using self-supervised learning. This model achieved a precision of 86%, obtaining a satisfactory performance. Using many images to learn good representations and a few labeled images to learn the semantic segmentation task is feasible.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Jeang, L.J., Margo, C.E., Espana, E.M.: Diseases of the corneal endothelium. Exp. Eye Res. 205, 108495 (2021)
Catala, P., et al.: Approaches for corneal endothelium regenerative medicine. Prog. Retin. Eye Res. 87, 100987 (2022)
Sierra, J.S., et al.: Corneal endothelium assessment in specular microscopy images with Fuchs’ dystrophy via deep regression of signed distance maps. Biomed. Opt. Express 14(1), 335–351 (2023)
Knauer, C., Pfeiffer, N.: The value of vision. Graefes Arch. Clin. Exp. Ophthalmol. 246, 477–482 (2008)
Huang, J., Maram, J., Tepelus, T.C., Sadda, S.R., Chopra, V., Lee, O.L.: Comparison of noncontact specular and confocal microscopy for evaluation of corneal endothelium. Eye Contact Lens Sci. Clin. Pract. 44, 144–150 (2017)
Price, M.O., Fairchild, K.M., Price, F.W.: Comparison of manual and automated endothelial cell density analysis in normal eyes and DSEK eyes. Cornea 32(5), 567–573 (2013). https://doi.org/10.1097/ico.0b013e31825de8fa
Luft, N., Hirnschall, N., Schuschitz, S., Draschl, P., Findl, O.: Comparison of 4 specular microscopes in healthy eyes and eyes with cornea guttata or corneal grafts. Cornea 34(4), 381–386 (2015). https://doi.org/10.1097/ico.0000000000000385
Gasser, L., Reinhard, T., Böhringer, D.: Comparison of corneal endothelial cell measurements by two non-contact specular microscopes. BMC Ophthalmol. 15, 87 (2015). https://doi.org/10.1186/s12886-015-0068-1
Piórkowski, A., Gronkowska–Serafin, J.: Towards precise segmentation of corneal endothelial cells. In: Ortuño, F., Rojas, I. (eds.) IWBBIO 2015. LNCS, vol. 9043, pp. 240–249. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-16483-0_25
Selig, B., Vermeer, K., Rieger, B., Hillenaar, T., Luengo Hendriks, C.: Fully automatic evaluation of the corneal endothelium from in vivo confocal microscopy. BMC Med. Imaging 15, 13 (2015). https://doi.org/10.1186/s12880-015-0054-3
Shilpashree, P., Kaggere, S., Sudhir, R., Srinivas, S.: Automated image segmentation of the corneal endothelium in patients with Fuchs dystrophy. Transl. Vis. Sci. Technol. 10, 27 (2021). https://doi.org/10.1167/tvst.10.13.27
Daniel, M., et al.: Automated segmentation of the corneal endothelium in a large set of ‘real-world’ specular microscopy images using the U-net architecture. Sci. Rep. 9 (2019). https://doi.org/10.1038/s41598-019-41034-2
Vigueras-Guillén, J., et al.: DenseUNets with feedback non-local attention for the segmentation of specular microscopy images of the corneal endothelium with guttae. Sci. Rep. 12 (2022). https://doi.org/10.1038/s41598-022-18180-1
Caron, M., et al.: Emerging Properties in Self-supervised Vision Transformers (2021)
Zbontar, J., Jing, L., Misra, I., LeCun, Y., Deny, S.: Barlow twins: self-supervised learning via redundancy reduction. In: International Conference on Machine Learning, pp. 12310–12320. PMLR (2021)
Punn, N.S., Agarwal, S.: BT-Unet: a self-supervised learning framework for biomedical image segmentation using Barlow twins with U-net models. Mach. Learn. 111(12), 4585–4600 (2022)
Jiao, R., Zhang, Y., Ding, L., Cai, R., Zhang, J.: Learning with Limited Annotations: A Survey on Deep Semi-supervised Learning for Medical Image Segmentation (2022)
Wu, Y., et al.: Mutual Consistency Learning for Semi-supervised Medical Image Segmentation (2022)
Fang, K., Li, W.-J.: DMNet: difference minimization network for semi-supervised segmentation in medical images. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12261, pp. 532–541. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59710-8_52
Chen, S., Bortsova, G., Juarez, A.G.-U., Tulder, G., Bruijne, M.: Multi-task Attention-Based Semi-supervised Learning for Medical Image Segmentation (2019)
Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Pathak, D., Krähenbühl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2536–2544 (2016). https://doi.org/10.1109/CVPR.2016.278
Balestriero, R., LeCun, Y.: Contrastive and Non-contrastive Self-supervised Learning Recover Global and Local Spectral Embedding Methods (2022)
Grill, J.-B., et al.: Bootstrap your own latent: a new approach to self-supervised learning (2020)
Ghosh, S., Seth, A., Mittal, D., Singh, M., Umesh, S.: DeLoRes: Decorrelating Latent Spaces for Low-Resource Audio Representation Learning (2022)
Wang, R., Lei, T., Cui, R., Zhang, B., Meng, H., Nandi, A.K.: Medical image segmentation using deep learning: a survey. IET Image Proc. 16(5), 1243–1267 (2022). https://doi.org/10.1049/ipr2.12419
Vigueras-Guillén, J.P., et al.: Fully convolutional architecture vs sliding-window CNN for corneal endothelium cell segmentation. BMC Biomed. Eng. 1, 4 (2019). https://doi.org/10.1186/s42490-019-0003-2
Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (2019)
Noroozi, M., Favaro, P.: Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles (2017)
Liu, C., et al.: CUTS: A Fully Unsupervised Framework for Medical Image Segmentation (2023)
Felfeliyan, B., et al.: Self-supervised-RCNN for Medical Image Segmentation with Limited Data Annotation (2022)
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
Marsocci, V., Scardapane, S.: Continual Barlow twins: continual self-supervised learning for remote sensing semantic segmentation. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 16, 5049–5060 (2023). https://doi.org/10.1109/JSTARS.2023.3280029
Acknowledgments
This work has been partly funded by Ministerio de Ciencia, Tecnología e Innovacioón, Colombia, Project 124489786239 (Contract 763-2021), Universidad Tecnológica de Bolívar (UTB) Project CI2021P02. K. Mendoza and F. Quintero thank UTB for a post-graduate scholarship. S. Sanchez thanks Fondo Bicentenario for a Ph.D. Scholarship.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sanchez, S. et al. (2024). Self-supervised Deep-Learning Segmentation of Corneal Endothelium Specular Microscopy Images. In: Orjuela-Cañón, A.D., Lopez, J.A., Arias-Londoño, J.D. (eds) Applications of Computational Intelligence. ColCACI 2023. Communications in Computer and Information Science, vol 1865. Springer, Cham. https://doi.org/10.1007/978-3-031-48415-5_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-48415-5_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48414-8
Online ISBN: 978-3-031-48415-5
eBook Packages: Computer ScienceComputer Science (R0)