Multimodal imaging of experimental choroidal neovascularization.

Abstract

To compare choroidal neovascularization (CNV) lesion measurements obtained by in vivo imaging modalities, with whole mount histological preparations stained with isolectin GS-IB4, using a murine laser-induced CNV model. B6N.Cg-Tg(Csf1r-EGFP)1Hume/J heterozygous adult mice were subjected to laser-induced CNV and were monitored by fluorescein angiography (FA), multicolor (MC) fundus imaging and optical coherence tomography angiography (OCTA) at day 14 after CNV induction. Choroidal-retinal pigment epithelium (RPE) whole mounts were prepared at the end of the experiment and were stained with isolectin GS-IB4. CNV areas were measured in all different imaging modalities at day 14 after CNV from three independent raters and were compared to choroidal-RPE whole mounts. Intraclass correlation coefficient (ICC) type 2 (2-way random model) and its 95% confidence intervals (CI) were calculated to measure the correlation between different raters' measurements. Spearman's rank correlation coefficient (Spearman's r) was calculated for the comparison between FA, MC and OCTA data and histology data. FA (early and late) and MC correlates well with the CNV measurements ex vivo with FA having slightly better correlation than MC (FA early Spearman's r=0.7642, FA late Spearman's r=0.7097, and MC Spearman's r=0.7418), while the interobserver reliability was good for both techniques (FA early ICC=0.976, FA late ICC=0.964, and MC ICC=0.846). In contrast, OCTA showed a poor correlation with ex vivo measurements (Spearman's r=0.05716) and high variability between different raters (ICC=0.603). This study suggests that FA and MC imaging could be used for the evaluation of CNV areas in vivo while caution must be taken and comparison studies should be performed when OCTA is employed as a CNV monitoring tool in small rodents.