Macular atrophy is a common complication in neovascular age-related macular degeneration (AMD) and is associated with poorer visual outcomes. This study evaluated inter-reader and inter-modality variability in measuring macular atrophy in previously-treated neovascular AMD eyes without exudation, using six imaging modalities. Prospective, cohort study. Thirty participants with previously-treated neovascular AMD, showing no signs of exudation at the time of enrollment, and exhibiting macular atrophy. During the same clinic visit, patients were imaged using six different imaging modalities: color fundus photography (CFP; Clarus, Carl Zeiss Meditec), near-infrared imaging (NIR; Spectralis; Heidelberg Engineering, Heidelberg, Germany), structural optical coherence tomography (OCT; Spectralis; Heidelberg Engineering, Heidelberg, Germany), green fundus autofluorescence (GAF; Clarus, Carl Zeiss Meditec), blue fundus autofluorescence (BAF; Spectralis; Heidelberg Engineering, Heidelberg, Germany), and pseudocolor imaging (MultiColor; Spectralis; Heidelberg Engineering, Heidelberg, Germany). Two readers independently measured the macular atrophy area. Inter-reader and inter-modality agreement. The 95% coefficient of repeatability (CR) was 5.98 mm² for CFP, 4.46 mm² for MultiColor, 3.90 mm² for BAF, 3.92 mm² for GAF, 4.86 mm² for NIR, and 3.55 mm² for OCT. Similarly, the coefficient of variation (CV) was lowest for the OCT-based grading at 0.08 and highest for the NIR-based grading at 0.28. Accordingly, the intraclass correlation coefficient (ICC) was 0.742 for CFP, 0.805 for MultiColor, 0.857 for BAF, 0.850 for GAF, 0.755 for NIR, and 0.917 for OCT. The 6 different imaging modalities presented measurements with different mean values, with only a limited number of comparisons not significantly different between the instruments, although measurements were correlated. The largest size of macular atrophy was with the structural OCT-based grading (median=4.65 mm²; interquartile range [IQR]=4.78 mm²) and the smallest was with the CFP-based grading (median=3.86 mm²; IQR=5.06 mm²). Inconsistencies arose from various factors. In patients with neovascular AMD, macular atrophy measurements vary significantly depending on the imaging technique used. CFP-based assessments yielded the smallest macular atrophy sizes, while structural OCT-based assessments produced the largest. These discrepancies stem from both the inherent limitations of each modality in assessing RPE atrophy and factors related to neovascularization, such as the coexistence of fibrosis.

Background and objectives: Age-related macular degeneration (AMD) is a complex and multifactorial condition that can lead to permanent vision loss once it progresses to the neovascular exudative stage. This review aims to summarize the use of deep learning in neovascular AMD. Materials and Methods: Pubmed search. Results: Deep learning has demonstrated effectiveness in analyzing structural OCT images in patients with neovascular AMD. This review outlines the role of deep learning in identifying and measuring biomarkers linked to an elevated risk of transitioning to the neovascular form of AMD. Additionally, deep learning techniques can quantify critical OCT features associated with neovascular AMD, which have prognostic implications for these patients. Incorporating deep learning into the assessment of neovascular AMD eyes holds promise for enhancing clinical management strategies for affected individuals. Conclusion: Several studies have demonstrated effectiveness of deep learning in assessing neovascular AMD patients and this has a promising role in the assessment of these patients.

To assess inter-reader and intermodality variability in quantifying macular fibrosis in patients with neovascular age-related macular degeneration (AMD) using 4 imaging modalities: color fundus photography (CFP), near-infrared reflectance (NIR), structural optical coherence tomography (OCT), and MultiColor imaging. Prospective, cross-sectional case series. Thirty eyes of 30 patients with neovascular AMD and macular fibrosis, previously treated with anti-vascular endothelial growth factor therapy. Imaging was performed using CFP, NIR, structural OCT, and MultiColor modalities. Two masked graders evaluated the size of macular fibrosis using each modality. The study assessed inter-reader agreement using the intraclass correlation coefficient (ICC), coefficient of variation (CV), and 95% coefficient of repeatability. Intermodality variability was analyzed using repeated measures ANOVA and pairwise comparisons. Structural OCT demonstrated the highest inter-reader agreement (ICC = 0.983; CV = 0.04), while NIR exhibited the lowest (ICC = 0.461; CV = 0.26). The median macular fibrosis size was largest on structural OCT (4.87 mm²) and smallest on MultiColor imaging (2.03 mm²). Significant differences were observed between imaging modalities, with fibrosis measurements from different modalities not consistently comparable. Structural OCT is the most reliable modality for quantifying macular fibrosis in neovascular AMD. The observed intermodality variability highlights the need for standardized criteria in fibrosis assessment across imaging techniques, as differences can impact clinical interpretation and management.