Adaptive contour prediction in postoperative OCT imaging using domain-adaptive generative adversarial networks

Photodiagnosis and Photodynamic Therapy · Published 2026-06-28 · DOI 10.1016/j.pdpdt.2026.105555

Free full text

Authors (10)

Shaopeng Liu, Kai Wang, Xiaohang Wu, Fabao Xu, Ying Zhou, Haoran Cen, Haobin Zhang, Peng Liang, Yang Chen, Xu Lu

Abstract

Optical Coherence Tomography (OCT) imaging plays a pivotal role in diagnosing ophthalmic diseases. This study introduces a domain-adaptive generative adversarial network (DaCGAN) to predict postoperative OCT contours from preoperative images, addressing the challenges of limited paired data and incomplete contour structures. DaCGAN integrates data from different diseases and employs preoperative contours to enhance prediction accuracy. Experimental results on Diabetic Macular Edema and Retinal Vein Occlusion datasets demonstrate the superiority of DaCGAN over existing methods, with improvements in SSIM, MSE, and PSNR metrics. Our approach offers a cost-effective solution for postoperative image prediction, potentially benefiting clinical diagnosis and treatment planning.

Abstract from DOAJ. Public domain (CC0 1.0).

Read the article at the publisher →

Publication details

Year
2026

Citation

Liu, S., Wang, K., Wu, X., et al. (2026). Adaptive contour prediction in postoperative OCT imaging using domain-adaptive generative adversarial networks. Photodiagnosis and Photodynamic Therapy. https://doi.org/10.1016/j.pdpdt.2026.105555

Related articles