Abstract
Longitudinal imaging is able to capture both static anatomical structures and dynamic changes in disease progression towards earlier and better patient-specific pathology management. However, conventional approaches for detecting diabetic retinopathy (DR) rarely take advantage of longitudinal information to improve DR analysis. In this work, we investigate the benefit of exploiting self-supervised learning with a longitudinal nature for DR diagnosis purposes. We compare different longitudinal self-supervised learning (LSSL) methods to model the disease progression from longitudinal retinal color fundus photographs (CFP) to detect early DR severity changes using a pair of consecutive exams. The experiments were conducted on a longitudinal DR screening dataset with or without those trained encoders (LSSL) acting as a longitudinal pretext task. Results achieve an AUC of 0.875 for the baseline (model trained from scratch) and an AUC of 0.96 (95% CI: 0.9593-0.9655 DeLong test) with a p-value <2.2e–16 on early fusion using a simple ResNet alike architecture with frozen LSSL weights, suggesting that the LSSL latent space enables to encode the dynamic of DR progression.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Change history
15 September 2022
In an older version of this chapter, the title was incomplete. This has been corrected.
References
Albelwi, S.: Survey on self-supervised learning: auxiliary pretext tasks and contrastive learning methods in imaging. Entropy 24(4) (2022). https://doi.org/10.3390/e24040551, https://www.mdpi.com/1099-4300/24/4/551
Chamard, C., et al.: Ten-year incidence and assessment of safe screening intervals for diabetic retinopathy: the OPHDIAT study. Br. J. Ophthalmol. 105(3), 432–439 (2020). https://doi.org/10.1136/bjophthalmol-2020-316030
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations (2020). https://doi.org/10.48550/ARXIV.2002.05709, https://arxiv.org/abs/2002.05709
Gayathri, S., Gopi, V.P., Palanisamy, P.: A lightweight CNN for diabetic retinopathy classification from fundus images. Biomed. Signal Process. Control 62, 102115 (2020)
Huang, Y., Lin, L., Cheng, P., Lyu, J., Tang, X.: Lesion-based contrastive learning for diabetic retinopathy grading from fundus images (2021). https://doi.org/10.48550/ARXIV.2107.08274, https://arxiv.org/abs/2107.08274
Liu, X., et al.: Self-supervised learning: generative or contrastive. arXiv preprint arXiv:2006.08218 vol. 1, no. 2 (2020)
Massin, P., et al.: Ophdiat: a telemedical network screening system for diabetic retinopathy in the Île-de-france. Diab. Metab. 34, 227–34 (2008). https://doi.org/10.1016/j.diabet.2007.12.006
Ogurtsova, K., et al.: IDF diabetes atlas: global estimates for the prevalence of diabetes for 2015 and 2040. Diab. Res. Clin. Pract. 128, 40–50 (2017)
Ouyang, J., et al.: Self-supervised longitudinal neighbourhood embedding. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12902, pp. 80–89. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87196-3_8
Pratt, H., Coenen, F., Broadbent, D.M., Harding, S.P., Zheng, Y.: Convolutional neural networks for diabetic retinopathy. Procedia Comput. Sci. 90, 200–205 (2016). https://doi.org/10.1016/j.procs.2016.07.014, https://www.sciencedirect.com/science/article/pii/S1877050916311929, 20th Conference on Medical Image Understanding and Analysis (MIUA 2016)
Quellec, G., Charrière, K., Boudi, Y., Cochener, B., Lamard, M.: Deep image mining for diabetic retinopathy screening. Med. Image Anal.39, 178–193 (2017). https://doi.org/10.1016/j.media.2017.04.012, https://www.sciencedirect.com/science/article/pii/S136184151730066X
Rivail, A., et al.: Modeling disease progression in retinal OCTs with longitudinal self-supervised learning. In: Rekik, I., Adeli, E., Park, S.H. (eds.) PRIME 2019. LNCS, vol. 11843, pp. 44–52. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32281-6_5
Robin, X., et al.: pROC: an open-source package for r and s to analyze and compare ROC curves. BMC Bioinf. 12(1) (2011). https://doi.org/10.1186/1471-2105-12-77
Saeedi, P., et al.: Global and regional diabetes prevalence estimates for 2019 and projections for 2030 and 2045: results from the international diabetes federation diabetes atlas, 9th edn. Diab. Res. Clin. Pract. 157, 107843 (2019). https://doi.org/10.1016/j.diabres.2019.107843
Saha, S.K., Xiao, D., Bhuiyan, A., Wong, T.Y., Kanagasingam, Y.: Color fundus image registration techniques and applications for automated analysis of diabetic retinopathy progression: a review. Biomed. Sig. Process. Control 47, 288–302 (2019). https://doi.org/10.1016/j.bspc.2018.08.034
Vernhet, P., Durrleman, S.: Longitudinal self-supervision to disentangle inter-patient variability, pp. 231–241 (2021). https://doi.org/10.1007/978-3-030-87196-3
Yan, Y., et al.: Longitudinal detection of diabetic retinopathy early severity grade changes using deep learning. In: Fu, H., Garvin, M.K., MacGillivray, T., Xu, Y., Zheng, Y. (eds.) OMIA 2021. LNCS, vol. 12970, pp. 11–20. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87000-3_2
Zhao, Q., Liu, Z., Adeli, E., Pohl, K.M.: Longitudinal self-supervised learning. Med. Image Anal. 71 (2021). https://doi.org/10.1016/j.media.2021.102051
Acknowledgements
The work takes place in the framework of the ANR RHU project Evired. This work benefits from State aid managed by the French National Research Agency under “Investissement d’Avenir” program bearing the reference ANR-18-RHUS-0008
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zeghlache, R. et al. (2022). Detection of Diabetic Retinopathy Using Longitudinal Self-supervised Learning. In: Antony, B., Fu, H., Lee, C.S., MacGillivray, T., Xu, Y., Zheng, Y. (eds) Ophthalmic Medical Image Analysis. OMIA 2022. Lecture Notes in Computer Science, vol 13576. Springer, Cham. https://doi.org/10.1007/978-3-031-16525-2_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-16525-2_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16524-5
Online ISBN: 978-3-031-16525-2
eBook Packages: Computer ScienceComputer Science (R0)
