Artificial intelligence-based quantitative analysis of interocular retinal vascular differences in school-age children with mild to moderate anisometropia.

Objective: To apply artificial intelligence (AI) technology for the quantitative analysis of interocular retinal vascular differences in color fundus photographs (CFP) among school-age children with mild to moderate anisometropia and to investigate their correlation with the degree of anisometropia. Methods: In this retrospective cross-sectional study, 33 children aged 6-9 years with mild to moderate anisometropia were enrolled. CFPs of both eyes were acquired. A deep learning-based AI algorithm was employed to quantitatively analyze interocular differences in the degree of fundus tessellation (FT), the extent of peripapillary atrophy (PPA), optic disc morphology, and retinal vascular characteristics. The correlations between these differences and the interocular spherical equivalent (SE) difference were assessed. Results: Eyes with lower SE values exhibited significantly higher FT density, larger FT areas across all regions, greater PPA area and extent, a larger optic disc ovality index, higher total vessel length density, and higher arterial fractal dimensions (D0, D1) compared to eyes with higher SE values. In contrast, the horizontal cup-to-disc ratio and the average venous tortuosity were significantly lower in the lower SE eyes (all Conclusion: Significant interocular differences in fundus structures are present in children with mild to moderate anisometropia. The magnitude of interocular difference in the PPA-to-optic disc diameter ratio shows a significant correlation with the degree of anisometropia. AI-based quantitative analysis provides an objective imaging basis for the early identification of anisometropia.