At the 2026 ARVO conference in Denver on Sunday, May 3, researchers Jacob Pichelmann, of Vienna-based RetInSight GmbH, and Reena Chopra, OD, of Topcon Healthcare, presented their paper, “Improving Community-Based OCT Screening Through Real-Time AI-Based Biomarker Visualization.” The purpose of the study, they stated, was to assess how—if at all—the use of artificial intelligence (AI) impacted the accuracy and efficiency of human graders in detecting biomarkers for retinal disease in 112 OCT volumes previously captured using Topcon’s Maestro 2 fundus camera.

The 12x9 mm images used for the study were sourced from the Institute for Digital Health Primary Eye Care data set. They were evaluated for signs of retinal pigment epithelium loss, intraretinal hyporeflective spaces, subretinal hyporeflective spaces, and pigment epithelial detachment—once by a human grader only, and once by a human grader with access to AI-based reports.

Results demonstrated that use of AI reports in the evaluations improved disease detection by 42% overall.

“While many fear AI will replace clinicians, our study shows it actually empowers them,” Mr. Pichelmann said. “By integrating AI analysis with Topcon’s Maestro imaging, clinicians became more accurate and consistent in identifying retinal biomarkers within a simulated community-based setting.”