Knowledge-Enhanced AI Drives Diagnosis of Multiple Retinal Diseases in Fundus Fluorescein Angiography

Ming-Ming Duan¹Hui Qi²Xiang Tu^2*

• ¹Jiujiang City Key Laboratory of Cell Therapy, jiujiang, China
• ²Seventh Affiliated Hospital, Sun Yat-sen University, Shenzhen, China

Purpose: This study aimed to develop and validate a deep learning model for the accurate multi-class classification of six retinal diseases from Fundus Fluorescein Angiography (FFA) images. Methods: We employed a knowledge-enhanced pre-training strategy (KeepFIT) using a ResNet-50 image encoder on two large FFA corpora: a curated atlas and a clinical report dataset. The resulting visual encoder was fine-tuned to classify six conditions, including diabetic retinopathy and macular degeneration. The model's performance and generalizability were assessed on two independent test sets, one from an external institution. Results: Our proposed deep learning model, leveraging a knowledge-enhanced pre-training strategy, demonstrated robust performance in classifying six distinct retinal diseases from Fundus Fluorescein Angiography images. The model achieved a strong and consistent micro-average Area Under the Curve (AUC) of 0.92 across two independent test sets. Notably, it showed excellent classification performance for critical conditions such as Venous Occlusion and Neovascular Age-Related Macular Degeneration, with AUC values reaching 0.95 and 0.96, respectively. Conclusion: The knowledge-enhanced pre-training strategy significantly improves the diagnostic accuracy and generalizability of deep learning models for FFA analysis. This approach provides a scalable and effective framework for automated retinal disease screening, holding significant potential for clinical decision support, especially in resource-limited settings.