Deep-learning automated quantification of longitudinal OCT scans demonstrates reduced RPE loss rate, preservation of intact macular area and predictive value of isolated photoreceptor degeneration in geographic atrophy patients receiving C3 inhibition treatment

Abstract

ObjectiveTo evaluate the role of automated optical coherence tomography (OCT) segmentation, using a validated deep-learning model, for assessing the effect of C3 inhibition on the area of geographic atrophy (GA); the constituent features of GA on OCT (photoreceptor degeneration (PRD), retinal pigment epithelium (RPE) loss and hypertransmission); and the area of unaffected healthy macula.To identify OCT predictive biomarkers for GA growth.MethodsPost hoc analysis of the FILLY trial using a deep-learning model for spectral domain OCT (SD-OCT) autosegmentation. 246 patients were randomised 1:1:1 into pegcetacoplan monthly (PM), pegcetacoplan every other month (PEOM) and sham treatment (pooled) for 12 months of treatment and 6 months of therapy-free monitoring. Only participants with Heidelberg SD-OCT were included (n=197, single eye per participant).The primary efficacy endpoint was the square root transformed change in area of GA as complete RPE and outer retinal atrophy (cRORA) in each treatment arm at 12 months, with secondary endpoints including RPE loss, hypertransmission, PRD and intact macular area.ResultsEyes treated PM showed significantly slower mean change of cRORA progression at 12 and 18 months (0.151 and 0.277 mm, p=0.0039; 0.251 and 0.396 mm, p=0.039, respectively) and RPE loss (0.147 and 0.287 mm, p=0.0008; 0.242 and 0.410 mm, p=0.00809). PEOM showed significantly slower mean change of RPE loss compared with sham at 12 months (p=0.0313). Intact macular areas were preserved in PM compared with sham at 12 and 18 months (p=0.0095 and p=0.044). PRD in isolation and intact macula areas was predictive of reduced cRORA growth at 12 months (coefficient 0.0195, p=0.01 and 0.00752, p=0.02, respectively)ConclusionThe OCT evidence suggests that pegcetacoplan slows progression of cRORA overall and RPE loss specifically while protecting the remaining photoreceptors and slowing the progression of healthy retina to iRORA.

Pegcetacoplan Treatment and Consensus Features of Geographic Atrophy Over 24 Months

“…A smaller least squares mean difference compared to sham was observed in the pegcetacoplan every other month group at month 24 for RPE loss and hypertransmission. PRD in isolation represents an earlier stage in GA development and has been shown to be prognostic for GA progression (eFigure 6 in Supplement 2). Negative growth (ie, reduction) of PRD in isolation was observed with the pegcetacoplan monthly and pegcetacoplan every other month groups at every time point following baseline up to 24 postbaseline (mean [SE] pegcetacoplan monthly −0.53 [0.10] vs pegcetacoplan every other month, −0.68 [0.09] mm 2 ).…”

“…These barriers might be mitigated by automated image segmentation algorithms. We recently developed a deep-learning based platform that uses CAM-defined OCT features to detect and quantify GA and its components (ie, quantitative OCT biomarkers), with a grading performance comparable to human specialist graders on an external validation dataset . Despite its widespread availability and advantages for detailed diagnosis and monitoring of GA, SD-OCT has yet to follow its own precedent in neovascular AMD, where it is the primary imaging modality used to inform both routine clinical practice and anatomic outcomes in trials …”

Bibliometric analysis of artificial intelligence and optical coherence tomography images: research hotspots and frontiers

“…Consequently, the utilization of neural networks in OCT is a rapidly growing trend that could significantly streamline the diagnostic process, reduce diagnostic errors, and improve the accuracy of disease diagnosis. Fu et al [40] utilized a neural network model to assess the role of automated OCT segmentation in evaluating the impact of C3 inhibition on geographic atrophy, identify OCT predictive biomarkers for geographic atrophy growth, and demonstrate that pegcetacoplan slows the progression of complete retinal pigment epithelium and outer retinal atrophy, reduces retinal pigment epithelium loss, protects photoreceptors, and slows the progression of healthy retina. Xu et al [41] combined a CNN and a graph neural network, cascaded neural network, which can automatically segment and differentiate retinal arteriole and venule solely based on optical coherence tomography angiography (OCTA), offering the potential to enhance OCTA image information for the diagnosis of various eye diseases and systemic diseases, such as DR, hypertension, and cardiovascular diseases.…”