AI-Driven Detection of Retinal Structural Changes Through Semi-Supervised OCT Image Analysis
Keywords:
semi-supervised learning; optical coherence tomography; retinal structural change; uncertainty calibration; pseudo-labeling; longitudinal image analysisAbstract
Retinal optical coherence tomography (OCT) provides cross-sectional views of the neurosensory retina and retinal pigment epithelium, making it central to the detection of fluid, drusen, atrophy, layer disruption, and other structural abnormalities. A persistent difficulty is that clinically useful detection must be spatially precise and longitudinally sensitive while annotated OCT volumes remain scarce, heterogeneous across devices, and expensive to grade. This paper develops a semi-supervised framework for detecting retinal structural changes that treats segmentation as a spatial prior rather than as an isolated endpoint. A U-Net-style segmentation model is trained on labeled scans and regularized on unlabeled scans through class-specific pseudo-labeling, entropy-based reliability weighting, and consistency between augmented student and teacher predictions. A registered longitudinal branch converts layer and lesion probability maps into structural change scores, which are combined with predictive reliability in a detection rule. The composite objective balances supervised segmentation, unlabeled-data consistency, and temporal change consistency. The analysis specifies failure modes that matter in OCT, including confirmation bias from pseudo-labels, false change caused by registration error, speckle and vessel-shadow artifacts, and calibration drift under device shift. It also defines an evaluation logic based on patient-level splits, external device testing, lesion-wise detection metrics, calibration assessment, and ablation of uncertainty and longitudinal components. The contribution is a coherent formulation that links semi-supervised representation learning to clinically meaningful structural change endpoints and provides a technically explicit basis for label-efficient OCT analysis.
References
1. Schmidt-Erfurth, U., Sadeghipour, A., Gerendas, B. S., Waldstein, S. M., & Bogunović, H. (2018). Artificial intelligence in retina. Progress in Retinal and Eye Research, 67, 1–29. https://doi.org/10.1016/j.preteyeres.2018.07.001
2. Schlegl, T., Waldstein, S. M., Bogunović, H., Endstrasser, F., Sadeghipour, A., Philip, A. M., Podkowinski, D., Gerendas, B. S., Langs, G., & Schmidt-Erfurth, U. (2018). Fully automated detection and quantification of macular fluid in OCT using deep learning. Ophthalmology, 125(4), 549–558. https://doi.org/10.1016/j.ophtha.2017.10.031
3. Lee, C. S., Baughman, D. M., & Lee, A. Y. (2017). Deep learning is effective for classifying normal versus age-related macular degeneration OCT images. Ophthalmology Retina, 1(4), 322–327. https://doi.org/10.1016/j.oret.2016.12.009
4. Chiu, S. J., Li, X. T., Nicholas, P., Toth, C. A., Izatt, J. A., & Farsiu, S. (2010). Automatic segmentation of seven retinal layers in SDOCT images congruent with expert manual segmentation. Optics Express, 18(18), 19413–19428. https://doi.org/10.1364/OE.18.019413
5. Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015 (Lecture Notes in Computer Science, Vol. 9351, pp. 234–241). Springer. https://doi.org/10.1007/978-3-319-24574-4_28
6. Tarvainen, A., & Valpola, H. (2017). Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in Neural Information Processing Systems, 30, 1195–1204.
7. Laine, S., & Aila, T. (2017). Temporal ensembling for semi-supervised learning. International Conference on Learning Representations.
8. Liu, S., Jin, J., Li, W., & Yan, X. (2026). Segmentation-Guided Semi-Supervised Landmark Detection on Intraoral 3D Scans. Preprints. https://doi.org/10.20944/preprints202609.1722.v1
9. Sohn, K., Berthelot, D., Li, C.-L., Zhang, Z., Carlini, N., Cubuk, E. D., Kurakin, A., Zhang, H., & Raffel, C. (2020). FixMatch: Simplifying semi-supervised learning with consistency and confidence. Advances in Neural Information Processing Systems, 33, 596–608.
10. Xie, Q., Dai, Z., Hovy, E., Luong, M.-T., & Le, Q. V. (2020). Unsupervised data augmentation for consistency training. Advances in Neural Information Processing Systems, 33, 6256–6268.
11. Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., & Raffel, C. (2019). MixMatch: A holistic approach to semi-supervised learning. Advances in Neural Information Processing Systems, 32.
12. van Engelen, J. E., & Hoos, H. H. (2020). A survey on semi-supervised learning. Machine Learning, 109(2), 373–440. https://doi.org/10.1007/s10994-019-05855-6
13. Kendall, A., & Gal, Y. (2017). What uncertainties do we need in Bayesian deep learning for computer vision? Advances in Neural Information Processing Systems, 30, 5574–5584.
14. Gal, Y., & Ghahramani, Z. (2016). Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. In Proceedings of the 33rd International Conference on Machine Learning (PMLR, Vol. 48, pp. 1050–1059).
15. Lakshminarayanan, B., Pritzel, A., & Blundell, C. (2017). Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in Neural Information Processing Systems, 30, 6402–6413.
16. Bogunović, H., Venhuizen, F., Klimscha, S., Apostolopoulos, S., Bab-Hadiashar, A., Bagci, U., Beg, M. F., Bekkers, E., Bhandary, S., Bhavna, R., et al. (2019). RETOUCH: The retinal OCT fluid detection and segmentation benchmark and challenge. IEEE Transactions on Medical Imaging, 38(8), 1858–1874. https://doi.org/10.1109/TMI.2019.2901398
17. De Fauw, J., Ledsam, J. R., Romera-Paredes, B., Nikolov, S., Tomasev, N., Blackwell, S., Askham, H., Glocker, B., O'Donoghue, K., Visentin, D., et al. (2018). Clinically applicable deep learning for diagnosis and referral in retinal disease. Nature Medicine, 24(9), 1342–1350. https://doi.org/10.1038/s41591-018-0107-6
18. Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., Venugopalan, S., Widner, K., Madams, T., Cuadros, J., et al. (2016). Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA, 316(22), 2402–2410. https://doi.org/10.1001/jama.2016.17216
19. Wilkinson, C. P., Ferris, F. L., Klein, R. E., Lee, P. P., Agardh, C. D., Davis, M., Dills, D., Kampik, A., Pararajasegaram, R., & Verdaguer, J. T. (2003). Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales. Ophthalmology, 110(9), 1677–1682. https://doi.org/10.1016/S0161-6420(03)00475-5
20. Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018). DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4), 834–848. https://doi.org/10.1109/TPAMI.2017.2699184
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Clinical and Translational Medicine

This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.



