Purpose The objective of the study was to evaluate the accuracy of the Notal OCT Analyzer (NOA) versus that of a retina specialist (RS) in the automated detection of fluid on optical coherence tomography (OCT). Design A study of the performance of the NOA compared with the results from 3 RSs. Participants A selection of 155 anonymized OCT scans (Zeiss Cirrus; Carl Zeiss Meditec, Dublin, CA) from an image repository at a single tertiary referral retina center (Belfast Health and Social Care Trust, Belfast, United Kingdom) after approval from the local data guardian of the clinical site. Methods One hundred fifty-five OCT cube scans were stripped of all clinical identifiers and exported. The NOA and 3 independent RSs analyzed all 128 B-scans of each cube scan for the presence of intraretinal fluid, subretinal fluid, and sub–retinal pigment epithelium fluid. The NOA also ranked individual B-scans of each volume scan for likelihood of CNV activity, which was subjected to a second grading session by the 3 RSs. Main Outcome Measures The NOA's sensitivity and specificity versus the RS grading and the NOA's performance in ranking B-scans for activity. Results One hundred forty-two cube scans met the inclusion criteria for the primary analysis. On testing the RS grading versus the NOA, the accuracy was 91% (95% confidence interval [CI], ±7%), sensitivity was 92% (95% CI, ±6%), and specificity was 91% (95% CI, ±6%), meeting the primary outcome. The graders’ accuracy when compared with the majority of the other graders (including a fourth grader) was 93%. On average, the 3 graders could identify fluid in 95% of scans by just reviewing a single cross-section with the highest NOA score and 99.5% of scans with fluid by viewing the top 3 cross-sections. Conclusions Concordance between the NOA and the RS determination of lesion activity was extremely high. The level of discrepancy between the RS and the NOA results was similar to the NOA's mismatches. Our results show that automated delineation of the retinal contours combined with interpretation of disease activity is feasible and has the potential to become a powerful tool in terms of its clinical applications.