Abstract
BackgroundPhotographic diabetic retinopathy screening requires labour-intensive grading of retinal images by humans. Automated retinal image analysis software (ARIAS) could provide an alternative to human grading. We compare the performance of...
Highlights
Diabetic retinopathy is one of the most common microvascular complications of diabetes.[1]
This study aims to compare the screening performance of a commercially available automated retinal image analysis software (ARIAS) (EyeArt) on images obtained with two platforms with different optical properties and field of view, the truecolour wide-field confocal scanner (EIDON) and English National Diabetic Eye Screening Programme (NDESP)-approved fundus cameras against
The prevalence of retinopathy according to the final human NDESP grades for R0,.R1,.M1,.R2 and R3 was
Summary
Diabetic retinopathy is one of the most common microvascular complications of diabetes.[1]. Artificial intelligence-enabled automated retinal image analysis software (ARIAS) allow accurate and speedy detection of retinopathy without the need for human graders.[6,7,8,9,10,11,12,13,14] The diagnostic accuracy of ARIAS have been reported to be comparable to that of expert graders on 45 degree 2-field conventional digital photographs.[14,15]. Photographic diabetic retinopathy screening requires labour-intensive grading of retinal images by humans. Automated retinal image analysis software.(ARIAS) could provide an alternative to human grading. We compare the performance of an ARIAS using true-colour, widefield confocal scanning images and standard fundus images in the English National Diabetic Eye. Screening Programme.(NDESP) against human grading
Sign-in/Register to view highlights & summary 
Submitted Version (
Free)
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call