Neural Network-based Isolectin B₄ Flat-Mount Analysis in a Novel AAV-hVEGF-Induced Diabetic Retinopathy Animal Model

Abstract

Purpose : Diabetic retinopathy (DR) is a complex disease displaying diverse vascular-associated complications, including upregulation of vascular endothelial growth factor (VEGF)-A_165, enhanced retinal angiogenesis, and neovascularization. Current animal models do not fully replicate the spectrum of DR pathologies. In this study, we aim to evaluate the efficacy of adeno-associated virus (AAV)-mediated long-term expression of human VEGF to establish angiogenic DR-related phenotypes in Brown Norway rats, as well as validate a novel artificial intelligence (AI) framework for autonomous quantification of retinal angiogenesis in a newly established DR model.

Methods : Brown Norway rats received single unilateral intravitreal injection of AAV-hVEGF165.V5 (5×10¹⁰ vg/eye) in the right eye on Day 0. The progression of retinal pathology was monitored weekly via fluorescein angiography (FA). Six weeks post-AAV administration eyes were enucleated, and retinal flat-mounts were stained with Isolectin B₄ and panoramic flat-mount images were captured using fluorescent microscope. For the automated quantification of retinal angiogenesis, we employed a combination of deep learning with traditional computer vision algorithms. The artificial intelligence (AI) component for blood vessel recognition in retinal flat-mounts was based on transfer learning approach when a pre-trained U-Net architecture neural network was fine-tuned with Recovery-FA19 fluorescein angiography dataset derived from human subjects. The neural network-generated vascular masks were processed to quantify vascular area, total vessel length, and number of branch points.

Results : AAV-hVEGF injection successfully induced DR-related features, manifesting as progressive vascular leakage and retinal angiogenesis. An increase was found in vascular area (18 ± 0.4% of total retina, p<0.001), total vessel length (793 ± 26 per 100x100px², p<0.001), and branch points (12 ± 0.5 per 100x100px², p<0.001) 6 weeks following AAV-hVEGF injection when compared to non-injected eyes (14 ± 0.2, 507 ± 11, and 6 ± 0.2, respectively).

Conclusions : AAV-mediated expression of human VEGF in rat retinas, demonstrates an easy-to-use model that recapitulates several aspects of DR pathology. Our data validates the effectiveness of our novel AI algorithm in quantifying retinal vasculature within the newly established DR model.

This abstract was presented at the 2024 ARVO Annual Meeting, held in Seattle, WA, May 5-9, 2024.