Search

Purpose To evaluate the association between ellipsoid zone (EZ) on spectral domain optical coherence tomography (SD-OCT) and visual acuity letter score (VALS) in participants with retinal vein occlusion in the Study of Comparative Treatments for Retinal Vein Occlusion 2. Methods SD-OCT scans of 362 participants were qualitatively assessed at baseline and months 1, 6, 12, and 24 for EZ status as normal, patchy, or absent. The thickness of EZ layer in the central subfield was also obtained using machine learning. Results EZ assessments were not possible at baseline due to signal blockage in >75% of eyes. At month 1, EZ was normal in 37.6%, patchy in 48.1%, and absent in 14.3%. EZ was measurable in 48.7% with a mean area of 0.07 ± 0.16 mm2. Mean VALS was better in eyes without an EZ defect compared to eyes with an EZ defect (P < 0.0001 at all visits). EZ defect at month 1 was associated with poorer VALS at all follow-up visits (P < 0.0001). Conclusions Both qualitative and quantitative assessments of EZ status strongly correlated with VALS. Absence of EZ was associated with poorer VALS at both corresponding and future visits, with larger areas of EZ loss associated with worse VALS. Translational Relevance Assessment of EZ can be used to identify patients with potentially poor response in eyes with retinal vein occlusion.

Background and objectiveTo develop a semi-automated, machine-learning based workflow to evaluate the ellipsoid zone (EZ) assessed by spectral domain optical coherence tomography (SD-OCT) in eyes with macular edema secondary to central retinal or hemi-retinal vein occlusion in SCORE2 treated with anti-vascular endothelial growth factor agents.MethodsSD-OCT macular volume scans of a randomly selected subset of 75 SCORE2 study eyes were converted to the Digital Imaging and Communications in Medicine (DICOM) format, and the EZ layer was segmented using nonproprietary software. Segmented layer coordinates were exported and used to generate en face EZ thickness maps. Within the central subfield, the area of EZ defect was measured using manual and semi-automated approaches via a customized workflow in the open-source data analytics platform, Konstanz Information Miner (KNIME).ResultsA total of 184 volume scans from 74 study eyes were analyzed. The mean±SD area of EZ defect was similar between manual (0.19±0.22 mm2) and semi-automated measurements (0.19±0.21 mm2, p = 0.93; intra-class correlation coefficient = 0.90; average bias = 0.01, 95% confidence interval of limits of agreement -0.18-0.20).ConclusionsA customized workflow generated via an open-source data analytics platform that applied machine-learning methods demonstrated reliable measurements of EZ area defect from en face thickness maps. The result of our semi-automated approach were comparable to manual measurements.