PRETI: Patient-Aware Retinal Foundation Model via Metadata-Guided Representation Learning
Preprint
Abstract
Retinal foundation models have significantly advanced retinal image analysis by leveraging self-supervised learning to reduce dependence on labeled data while achieving strong generalization. Many recent approaches enhance retinal image understanding using report supervision, but obtaining clinical reports is often costly and challenging. In contrast, metadata (e.g., age, gender) is widely available and serves as a valuable resource for analyzing disease progression. To effectively incorporate patient-specific information, we propose PRETI, a retinal foundation model that integrates metadata-aware learning with robust self-supervised representation learning. We introduce Learnable Metadata Embedding (LME), which dynamically refines metadata representations. Additionally, we construct patient-level data pairs, associating images from the same individual to improve robustness against non-clinical variations. To further optimize retinal image representation, we propose Retina-Aware Adaptive Masking (RAAM), a strategy that selectively applies masking within the retinal region and dynamically adjusts the masking ratio during training. PRETI captures both global structures and fine-grained pathological details, resulting in superior diagnostic performance. Extensive experiments demonstrate that PRETI achieves state-of-the-art results across diverse diseases and biomarker predictions using in-house and public data, indicating the importance of metadata-guided foundation models in retinal disease analysis. Our code and pretrained model are available at https://github.com/MICV-yonsei/PRETIKeywords
All Related Versions
This publication has 26 references indexed in Scilit:
- A Foundation Language-Image Model of the Retina (FLAIR): encoding expert knowledge in text supervisionMedical Image Analysis, 2024
- Metadata-enhanced contrastive learning from retinal optical coherence tomography imagesMedical Image Analysis, 2024
- A foundation model for generalizable disease detection from retinal imagesNature, 2023
- Foundation models for generalist medical artificial intelligenceNature, 2023
- Symmetry of Macular Fundus Features in Age-Related Macular DegenerationOphthalmology Retina, 2023
- A multimodal transformer to fuse images and metadata for skin disease classificationThe Visual Computer, 2022
- Automatic detection of 39 fundus diseases and conditions in retinal photographs using deep neural networksNature Communications, 2021
- A deep-learning system for the assessment of cardiovascular disease risk via the measurement of retinal-vessel calibreNature Biomedical Engineering, 2020
- Symmetry of peripheral retinal nonperfusion in diabetic retinopathy by ischemic indexJournal of Optometry, 2018
- Perceptual Losses for Real-Time Style Transfer and Super-Resolution2016