Impact of retinal image quality – software aid for a low-cost device and effects on disease detection

摘要

Adequate image quality is a necessary component to any retinal screening program whether the cases are to be read by ahuman reader or processed by an artificial intelligence system (AI). The need for expanded screening for retinal diseaseshas led to the adoption of low-cost, portable cameras that are ideal for reaching large underserved populations. However,the low-cost cameras generally require a higher level of operator skill to produce high quality images in comparison withmore expensive table-top retinal cameras. This study, conducted at thirteen clinics in Monterrey, Mexico, comparesunreadable rates between a table-top retinal camera (Canon CR2-AF) and a low-cost portable camera (Volk Pictor Plus)before and after implementation of automatic image quality assessment software, Image Quality Analyzer (IQA). Thesoftware determines if an image is of adequate quality to be read by a human or AI system; what the image quality issuesare; and tips for fixing the issues. The process is performed in real time. Results show a significant decrease inunreadable cases (9% to 0%) for the Pictor Plus after IQA implementation bringing the percent of rejected cases in linewith the table-top camera (3% to 5%).