Purpose Fundus fluorescein angiography (FFA) is essential for diagnosing and managing retinal vascular diseases, while its evaluation is time-consuming and subject to inter-observer variability. We aim to develop a deep-learning-based model for accurate multi-lesion segmentation for these diseases.

Methods A dataset comprising 428 standard 55° and 53 ultra-wide-field (UWF) FFA images was labeled for various lesions, including non-perfusion areas (NPA), microaneurysms (MA), neovascularization (NV) and laser spots. A U-net-based network was trained and validated (80%) to segment FFA lesions and then tested (20%), with performance assessed via Dice score and Intersection over Union (IoU).

Results Our model achieved Dice scores for NPA, MA, NV, and Laser on 55° FFA images at 0.65±0.24, 0.70±0.13, 0.73±0.23 and 0.70±0.17, respectively. UWF results were slightly lower for NPA (0.48±0.21, p=0.02), MA (0.58±0.19, p=0.01), NV (0.50±0.34, p=0.14), but similar for Laser (0.74±0.03, p=0.90). Notably, NV segmentation in choroidal neovascularization achieved a high Dice score of 0.90±0.09, surpassing those in DR (0.68±0.22) and RVO (0.62±0.28), p<0.01. In RVO, NPA segmentation outperformed that in DR, scoring 0.77±0.25 versus 0.59±0.22, p<0.01, while in DR, MA segmentation was superior to that in RVO, with scores of 0.70±0.18 compared to 0.53±0.20, p<0.01. Moreover, NV segmentation was significantly stronger in venous phase (0.77±0.17) and late phase (0.75±0.24) compared to arteriovenous phase (0.50±0.32), p<0.05.

Conclusion This study has established a model for precise multi-lesion segmentation in retinal vascular diseases using 55° and UWF FFA images. This multi-lesion segmentation model has the potential to expand databases, ease grader burden and standardize FFA image interpretation, thereby improving disease management. Furthermore, it enhances interpretable AI, fostering the development of sophisticated systems and promoting cross-modal image generation for medical applications.

Synopsis We developed deep-learning models for segmenting multiple retinal lesions in both normal and ultra-field FFA images; the satisfactory performances set the foundation for quantifiable clinical biomarker assessment and building interpretable generative artificial intelligence.

The authors have declared no competing interest.

This study was supported by Global STEM Professorship Scheme(P0046113), Start-up Fund for RAPs under the Strategic Hiring Scheme (P0048623) from HKSAR and Henry G. Leong Endowed Professorship in Elderly Vision Health.

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

The Institutional Review Board of the Hong Kong Polytechnic University approved the study (HSEARS20240301004).

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

Funding Information: This study was supported by Global STEM Professorship Scheme(P0046113), Start-up Fund for RAPs under the Strategic Hiring Scheme (P0048623) from HKSAR and Henry G. Leong Endowed Professorship in Elderly Vision Health.

All data produced in the present study are available upon reasonable request to the authors