Propagating Structural Guidance: Synthesizing Fluorescein Angiography from Fundus Images and Sparse OCT Scans

2026-06-15

AI Summary

This work addresses the limitations of conventional approaches that rely solely on color fundus photographs to synthesize fluorescein fundus angiography (FFA), which often fail to reconstruct functional vascular details and subtle lesions due to the absence of deep retinal structural information. To overcome this, the authors propose a novel structure-guided FFA synthesis framework, introducing the first trilaterally aligned multimodal retinal imaging dataset. They design a Spatially Aligned Cross-Modal Fusion (SACMF) module that projects OCT-derived depth features onto the fundus plane and injects them into the encoder via adaptive layer normalization. Additionally, a Token-level Cross-Modal Alignment (TCMA) strategy is employed to enhance feature consistency at spatially corresponding locations. The proposed method significantly outperforms existing techniques in both FFA synthesis quality and downstream disease diagnostic performance, demonstrating strong potential as a non-invasive clinical decision-support tool.

Abstract

Fundus fluorescein angiography (FFA) is critical for assessing retinal vascular abnormalities, but its acquisition is invasive and not always feasible. In contrast, color fundus photography (CFP) is non-invasive and widely accessible, which has motivated studies on CFP-to-FFA synthesis. However, prior works rely solely on CFP surface texture, fundamentally limiting the ability to reconstruct functional vascular information and subtle pathological changes. To address this, we propose a novel framework that synthesizes FFA from CFP with structural guidance provided by optical coherence tomography (OCT). We construct a multi-modal retinal imaging dataset with paired CFP, FFA, and OCT from 3,676 patient eyes--the first tri-modally aligned dataset in retinal imaging. To bridge the spatial gap between OCT and fundus modalities, we propose a Spatially Aligned Cross-Modal Fusion (SACMF) module that projects depth-resolved OCT features onto the fundus plane and injects them into the CFP encoder via adaptive layer normalization. Beyond feature fusion, we further introduce Token-wise Cross-Modality Alignment (TCMA), a token-level contrastive learning strategy that explicitly aligns CFP and FFA representations at corresponding spatial positions. Our method achieves superior synthesis performance compared to state-of-the-art methods. Moreover, extensive experiments demonstrate that the FFA images synthesized by our approach bring greater improvements in downstream disease diagnosis performance than existing methods, highlighting the clinical potential of our approach as a non-invasive decision-support tool in routine workflows. The code is available at https://github.com/while-plus/OCT-guide-FFA-Syn.

Problem

• Fluorescein Angiography Synthesis
• Retinal Imaging
• Multi-modal Fusion
• Non-invasive Diagnosis
• Structural Guidance

Innovation

• cross-modal synthesis
• structural guidance
• spatial alignment
• contrastive learning
• multi-modal retinal imaging