Propagating Structural Guidance: Synthesizing Fluorescein Angiography from Fundus Images and Sparse OCT Scans
2026-06-15 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors developed a new method to create detailed images of retinal blood vessels (FFA) using easier-to-get color photos of the eye (CFP) combined with 3D scans (OCT). They combined these three types of images from many patients to help the method learn better. Their system aligns information from the OCT scans with the color photos and uses special techniques to link these images to the detailed blood vessel pictures. This produces more accurate synthetic FFA images, which can help doctors diagnose eye diseases without needing invasive tests. Their results show better performance than previous methods and potential use in regular eye exams.
Fundus fluorescein angiography (FFA)Color fundus photography (CFP)Optical coherence tomography (OCT)Retinal imagingCross-modal fusionContrastive learningImage synthesisVascular abnormalitiesToken alignment
Authors
Tengfei Ma, Ruiqi Wu, Chenran Zhang, Ye Geng, Na Su, Xiangyuan Duanmu, Tao Zhou, Yi Zhou, Wen Fan
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.