Segmentation of macular neovascularization and leakage in fluorescein angiography images in neovascular age-related macular degeneration using deep learning.

BACKGROUND/OBJECTIVES: We aim to develop an objective fully automated Artificial intelligence (AI) algorithm for MNV lesion size and leakage area segmentation on fluorescein angiography (FA) in patients with neovascular age-related macular degeneration (nAMD). SUBJECTS/METHODS: Two FA image datasets collected form large prospective multicentre trials consisting of 4710 images from 513 patients and 4558 images from 514 patients were used to develop and evaluate a deep learning-based algorithm to detect CNV lesion size and leakage area automatically. Manual segmentation of was performed by certified FA graders of the Vienna Reading Center. Precision, Recall and F1 score between AI predictions and manual annotations were computed. In addition, two masked retina experts conducted a clinical-applicability evaluation, comparing the quality of AI based and manual segmentations. RESULTS: For CNV lesion size and leakage area segmentation, we obtained F1 scores of 0.73 and 0.65, respectively. Expert review resulted in a slight preference for the automated segmentations in both datasets. The quality of automated segmentations was slightly more often judged as good compared to manual annotations. CONCLUSIONS: CNV lesion size and leakage area can be segmented by our automated model at human-level performance, its output being well-accepted during clinical applicability testing. The results provide proof-of-concept that an automated deep learning approach can improve efficacy of objective biomarker analysis in FA images and will be well-suited for clinical application.

THE IMPACT OF THE VITREOMACULAR INTERFACE ON FUNCTIONAL AND ANATOMICAL OUTCOMES IN DIABETIC MACULAR EDEMA TREATED WITH THREE DIFFERENT ANTI-VEGF AGENTS: Post Hoc Analysis of The Protocol T Study.

PURPOSE: To investigate the impact of baseline vitreomacular interface status on treatment outcomes in patients treated with three different anti-vascular endothelial growth factors for diabetic macular edema. METHODS: Post hoc analysis from patients enrolled in the DRCR.net Protocol T study. Optical coherence tomography images were analyzed at baseline and at the end of follow-up to identify the presence of complete vitreomacular adhesion, partial vitreomacular adhesion, vitreomacular traction syndrome, and complete posterior vitreous detachment. RESULTS: Six hundred and twenty-nine eyes were eligible for the study based on the study criteria. Complete adhesion eyes gained on average +3.7 more ETDRS letters compared with the complete posterior vitreous detachment group at the end of the 12 months follow-up ( P < 0.001). Baseline vitreomacular interface status had no significant influence on central subfield thickness at 12 months ( P = 0.144). There was no difference between the treatment arms based on effect of baseline vitreomacular interface status on best-corrected visual acuity gain. CONCLUSION: This study provides evidence that vitreomacular interface status affects functional outcomes in diabetic macular edema patients treated with anti-vascular endothelial growth factor injections. The presence of complete or partial vitreomacular adhesion at baseline may be associated with a larger treatment benefit than those with complete posterior vitreous detachment.