Search

Purpose: Genome-wide association studies have recently uncovered many loci associated with variation in intraocular pressure (IOP). Artificial intelligence (AI) can be used to interrogate the effect of specific genetic knockouts on the morphology of trabecular meshwork cells (TMCs) and thus, IOP regulation. Design: Experimental study. Subjects: Primary TMCs collected from human donors. Methods: Sixty-two genes at 55 loci associated with IOP variation were knocked out in primary TMC lines. All cells underwent high-throughput microscopy imaging after being stained with a 5-channel fluorescent cell staining protocol. A convolutional neural network was trained to distinguish between gene knockout and normal control cell images. The area under the receiver operator curve (AUC) metric was used to quantify morphological variation in gene knockouts to identify potential pathological perturbations. Main Outcome Measures: Degree of morphological variation as measured by deep learning algorithm accuracy of differentiation from normal controls. Results: Cells where LTBP2 or BCAS3 had been perturbed demonstrated the greatest morphological variation from normal TMCs (AUC 0.851, standard deviation [SD] 0.030; and AUC 0.845, SD 0.020, respectively). Of 7 multigene loci, 5 had statistically significant differences in AUC (P

Purpose: To examine the distribution of foveal avascular zone (FAZ) parameters, with and without correction for lateral magnification, in a large cohort of healthy young adults. Design: Cross-sectional, observational cohort study. Participants: A total of 504 healthy adults, 27 to 30 years of age. Methods: Participants underwent a comprehensive ophthalmic examination including axial length measurement and OCT angiography (OCTA) imaging of the macula. OCT angiography images of combined superficial and deep retinal vessel plexuses were processed via a custom software to extract foveal avascular zone area (FAZA) and foveal density-300 (FD-300), the vessel density in a 300-μm wide annulus surrounding the FAZ, with and without correction for lateral magnification. Bland–Altman analyses were performed to examine the effect of lateral magnification on FAZA and FD-300, as well as to evaluate the interocular agreement in both parameters. Linear mixed-effects models were used to examine the relationship between retinal thicknesses and OCTA parameters. Main Outcome Measures: The FAZA and FD-300, corrected for lateral magnification. Results: The mean (standard deviation [SD]) of laterally corrected FAZA and FD-300 was 0.22 mm2 (0.10 mm2) and 51.9% (3.2%), respectively. Relative to uncorrected data, 55.6% of corrected FAZA showed a relative change > 5%, whereas all FD-300 changes were within 5%. There was good interocular symmetry (mean right eye–left eye difference, 95% limits of agreement [LoA]) in both FAZA (0.006 mm2, -0.05 mm2, to 0.07 mm2) and FD-300 (-0.05%, -5.39%, to 5.30%). There were significant negative associations between central retinal thickness and FAZA (β = -0.0029), as well as between central retinal thickness and FD-300 (β = -0.044), with the relationships driven by inner, not outer, retina. Conclusions: We reported lateral magnification adjusted normative values for FAZA and FD-300 in a large cohort of young, healthy eyes. Clinicians should strongly consider accounting for lateral magnification when evaluating FAZA. Good interocular agreement in FAZA and FD-300 suggests the contralateral eye can be used as control data.