AI-Driven Detection of Retinal Structural Changes Through Semi-Supervised OCT Image Analysis

Authors

  • Ekapad Salvi Department of Computer Science, University of New Hampshire, Durham, NH, USA.

Keywords:

semi-supervised learning; optical coherence tomography; retinal structural change; uncertainty calibration; pseudo-labeling; longitudinal image analysis

Abstract

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

2026-09-24

How to Cite

Ekapad Salvi. (2026). AI-Driven Detection of Retinal Structural Changes Through Semi-Supervised OCT Image Analysis. International Journal of Clinical and Translational Medicine, 2(2). Retrieved from https://ijctmed.org/index.php/home/article/view/242