Photoreceptor degeneration in ABCA4-associated retinopathy and its genetic correlates

Abstract

BACKGROUNDOutcome measures sensitive to disease progression are needed for ATP-binding cassette, sub-family A, member 4-associated (ABCA4-associated) retinopathy. We aimed to quantify ellipsoid zone (EZ) loss and photoreceptor degeneration beyond EZ-loss in ABCA4-associated retinopathy and investigate associations between photoreceptor degeneration, genotype, and age.METHODSWe analyzed 132 eyes from 66 patients (of 67 enrolled) with molecularly confirmed ABCA4-associated retinopathy from a prospective natural history study with a median [IQR] follow-up of 4.2 years [3.1, 5.1]. Longitudinal spectral-domain optical coherence tomography volume scans (37 B-scans, 30° × 15°) were segmented using a deep learning (DL) approach. For genotype-phenotype analysis, a model of ABCA4 variants was applied with the age of criterion EZ-loss (6.25 mm2) as the dependent variable.RESULTSPatients exhibited an average (square-root-transformed) EZ-loss progression rate of [95% CI] 0.09 mm/y [0.06, 0.11]. Outer nuclear layer (ONL) thinning extended beyond the area of EZ-loss. The average distance from the EZ-loss boundary to normalization of ONL thickness (to ±2 z score units) was 3.20° [2.53, 3.87]. Inner segment (IS) and outer segment (OS) thinning was less pronounced, with an average distance from the EZ-loss boundary to layer thickness normalization of 1.20° [0.91, 1.48] for the IS and 0.60° [0.49, 0.72] for the OS. An additive model of allele severity explained 52.7% of variability in the age of criterion EZ-loss.CONCLUSIONPatients with ABCA4-associated retinopathy exhibited significant alterations of photoreceptors outside of EZ-loss. DL-based analysis of photoreceptor laminae may help monitor disease progression and estimate the severity of ABCA4 variants.TRIAL REGISTRATIONClinicalTrials.gov identifier: NCT01736293.FUNDINGNational Eye Institute Intramural Research Program and German Research Foundation grant PF950/1-1.

Keywords: Genetic diseases; Ophthalmology; Retinopathy.

Figure 1. Feature extraction.

(A) Six retinal layers were segmented using a convolutional neural network. (B) Subsequently, en face projections were generated for each layer. (C) The area of ellipsoid zone (EZ) loss (shown in red) could be identified on the photoreceptor outer segment (OS) thickness map. (D and E) To account for age and retinal topography, the retinal thickness data for each A-scan (i.e., pixel in the en face map) were normalized in a pointwise manner using normal data as z score. (E) Retinal layer thicknesses in relation to the EZ boundary were extracted along evenly spaced contour lines (0.43° between the contour lines). RPE, retinal pigment epithelium.

Figure 2. Progression of EZ-loss.

(A) The first panel shows the square-root-transformed progression of EZ-loss over time (with a rolling median filter, span: ±1 year). The red dashed line shows the mixed model estimate for EZ-loss progression. (B) The second panel shows the log-likelihood (y axis) for mixed models of EZ-loss (dependent variable) as a function of time (independent variable). Models were fit with a range of Box-Cox transformations (λ 0 to 1) of the dependent variable EZ-loss. Based on the log-likelihood (45), a Box-Cox transformation parameter λ of 0.4 was optimal, which approximates square-root transformation (i.e., Box-Cox λ of 0.5). Supplemental Figure 9 shows the EZ-loss progression for exemplary eyes. These plots include data acquired prior to the baseline visit of the natural history study up to the last visit of each patient (N of patients = 66).

Figure 3. Retinal layer abnormalities outside the area of ellipsoid zone (EZ) loss.

The line plots show the normalized retinal layer thicknesses (y axis) outside the area of EZ-loss in eyes with STGD1 as a function of the distance to the EZ-loss boundary (x axis). The horizontal, red, dashed lines denote ±2 z score units (i.e., the normative range). The vertical, black, dashed lines indicate the distances 0.43°, 1.29°, 2.58°, 5.16°, and 7.73° (multiples of a Goldmann III stimulus diameter) to the EZ-loss boundary, which correspond to the average distance to normalization of thickness for the inner retina (INNER), outer nuclear layer (ONL), and photoreceptor inner segments (IS) and outer segments (OS). For these distances, changes over time in layer thicknesses are shown in Figure 4. Of note, INNER, ONL, IS, and OS are all severely thinned even outside the area of EZ-loss. The retinal pigment epithelium (RPE) shows thickening outside of EZ-loss. For the choroid (CHO), no marked changes in terms of thickness are evident. These plots are based on the data from the baseline of the natural history up to the last visit of each patient (N of patients = 66).

Figure 4. Rate of change in layer thickness per year.

The parallel line plots show the change in normalized layer thicknesses (y axis) over time (x axis) as a function of the distance to the EZ-loss boundary at baseline (panels). Each line denotes data from an individual eye. The red dashed lines are derived from mixed model estimates for the change over time. Of note, there is no evidence of “retina-wide” photoreceptor loss in this cohort. These plots are based on the data from baseline of the natural history up to the last visit of each patient (N of patients = 66).

Figure 5. Comparison of the allele severity estimates with prior publications.

(A) The first panel shows the comparison to overlapping data on 12 variants from Cideciyan et al. 2009 (17). The x axis shows the delay of disease initiation relative to a null mutation as estimated by Cideciyan et al. 2009. The y axis shows the estimates for the delay of disease initiation relative to a null mutation in the present study (age of criterion EZ-loss minus 6.88 years [estimate for age of criterion EZ-loss for a null mutation]). Interestingly, these prior data explained (R²) 43.5% of the variability in the delay of disease initiation observed in our data. (B) The second panel shows the comparison to overlapping data on 12 variants from Fakin et al. 2016 (4). The x axis shows the ordinal-scaled classification from Fakin et al. 2016. The y axis shows the estimates for the delay of disease initiation relative to a null mutation in the present study. The red horizontal lines indicate the median in the observed delay of disease initiation for each category.