OR WAIT null SECS
The post-hoc analysis suggests reliable quantification of photoreceptor loss is an essential tool to evaluate therapeutic efficacy in slowing GA progression.
New findings suggest the distinct quantification of photoreceptor loss using deep learning–based algorithms may offer an essential tool to evaluate therapeutic efficacy in slowing disease progression of geographic atrophy (GA).
The study data show photoreceptor loss and thinning are reduced by intravitreal complement C3 inhibition with pegcetacoplan.
“Automated quantification of photoreceptor loss/maintenance based on optical coherence tomography (OCT) images is an ideal approach to reliably monitor disease activity and therapeutic efficacy in GA management in clinical routine and regulatory trials,” wrote study author Ursula Schmidt-Erfurth, MD, Head of Department of Ophthalmology and Optometry, Medical University of Vienna.
The study investigators aimed to investigate the therapeutic effect of intravitreal pegcetacoplan on the inhibition of photoreceptor loss and thinning and geographic atrophy on conventional spectral-domain OCT (SD-OCT) imaging by deep learning-based automated photoreceptor qualification.
This study was a post-hoc analysis of a prospective, multicenter, randomized, sham-controlled, masked phase II trial investigating the safety and efficacy of pegcetacoplan for the treatment of GA due to age-related macular degeneration (AMD). Participants in the trial included the study eyes of 246 eyes of 246 patients, which were randomized 1:1:1 to monthly, bimonthly, and sham-controlled treatment.
Schmidt-Erfurth and colleagues performed fully automated, deep learning–based segmentation of retinal pigment epithelium (RPE) loss and photoreceptor loss thickness on SD-OCT volumes acquired at baseline and months 2, 6, and 12.
The differences in the change of photoreceptor loss area was compared among the treatment arms. The change in photoreceptor thickness adjacent to the GA borders and the entire 20° scanning area was compared between treatment arms.
The main outcome measures included square-root transformed photoreceptor loss area in mm or mm, photoreceptor thickness in mm, and photoreceptor loss/retinal pigment epithelium (RPE) loss ratio.
The study evaluated a total of 31,556 B-scans of 644 SD-OCT volumes of 161 study eyes from baseline to month 12. It included 52 randomized eyes to monthly treatment, 54 eyes to bimonthly treatment, and 56 eyes to sham-controlled treatment.
Data on the comparison of the mean change in photoreceptor loss area reveal statistically significantly less growth in the monthly groups at months 2 (–41 μm ± 219 vs. 77 μm ± 126; P = 0.0004), month 6 (–5 μm ± 221 vs. 156 μm ± 139; P < 0.0001), and month 12 (106 μm ± 400 vs. 283 μm ± 226; P = 0.0014) than in the sham-controlled group).
Moreover, photoreceptor thinning was significantly reduced under the monthly treatment compared with sham-controlled treatment within the GA junctional zone, as well as throughout the 20° area. Investigators observed a trend toward greater inhibition of photoreceptor loss than RPE loss under therapy.
The abstract, “The Effect of Pegcetacoplan Treatment on Photoreceptor Maintenance in Geographic Atrophy Monitored by Artificial Intelligence-Based OCT Analysis,” was published in Ophthalmology Retina.