This paper surveys representation learning methods applied to Optical Coherence Tomography (OCT) images in ophthalmology. It reviews techniques from early deep learning to current foundation models and vision-language systems. The survey categorizes methods by learning paradigms, including supervised, self-supervised, and generative approaches, and discusses their contributions and limitations. It also covers datasets, evaluation protocols, and identifies future research directions such as volumetric foundation model pretraining and privacy-preserving training. AI
Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →
IMPACT Provides a structured overview of AI techniques for medical image analysis, highlighting future research directions in foundation models and privacy.
RANK_REASON This is a survey paper published on arXiv detailing representation learning methods for medical imaging.