Facilitating diabetic retinopathy screening using automated retinal image analysis in underresourced settings

Abstract

Aim To evaluate an automated retinal image analysis (ARIA) of indigenous retinal fundus images against a human grading comparator for the classification of diabetic retinopathy (DR) status. Methods Indigenous Australian adults with type 2 diabetes (n = 410) from three remote and very remote primary‐care services in the Northern Territory, Australia, underwent teleretinal DR screening. A single, central retinal fundus photograph (opportunistic mydriasis) for each eye was later regraded using a single ARIA and a UK human grader and national DR classification system. The sensitivity and specificity of ARIA were assessed relative to the comparator. Proportionate agreement and a Kappa statistic were also computed. Results Retinal images from 391 and 393 participants were gradable for ‘Any DR’ by the human grader and ARIA grader, respectively. ‘Any DR’ was detected by the human grader in 185 (47.3%) participants and by ARIA in 202 (48.6%) participants (agreement =88.0%, Kappa = 0.76,), whereas proliferative DR was detected in 31 (7.9%) and 37 (9.4%) participants (agreement = 98.2%, Kappa = 0.89,), respectively. The ARIA software had 91.4 (95% CI, 86.3–95.0) sensitivity and 85.0 (95% CI, 79.3–89.5) specificity for detecting ‘Any DR’ and 96.8 (95% CI, 83.3–99.9) sensitivity and 98.3 (95% CI, 96.4–99.4) specificity for detecting proliferative DR. Conclusions This ARIA software has high sensitivity for detecting ‘Any DR’, hence could be used as a triage tool for human graders. High sensitivity was also found for detection of proliferative DR by ARIA. Future versions of this ARIA should include maculopathy and referable DR (CSME and/or PDR). Such ARIA software may benefit diabetes care in less‐resourced regions.

Deep learning for automatic diagnosis of fundus diseases on optical coherence tomography images

“…Screening for fundus diseases is very important, and it is necessary to minimize the human and nancial consumption caused by screening, especially in underdeveloped areas. Therefore, the use of deep learning technology to assist in the diagnosis of fundus diseases is worth investigating 5,20 . However, the accuracy of a deep learning model depends on the amount of data.…”

“…These fundus diseases can lead to metamorphopsia, visual eld defects, irreversible blurred vision, or even blindness without accurate diagnosis and timely appropriate treatment. However, in developing countries or rural and remote areas, where there are insu cient ophthalmic services and a shortage of ophthalmologists, early detection and timely referral for treatment may not be available 5 . Therefore, large-scale screening of fundus diseases is necessary for preventing blindness 6,7 .…”

“…For diseases of the retina and macular, OCT has signi cant advantages in diagnosing fundus diseases 8,9 ; however, the diagnosis of fundus diseases using OCT images depends mainly on the ophthalmologist's judgment. Large-scale fundus disease screening will greatly increase the workload of ophthalmologists 5 ; therefore, a disease detection system using OCT images should be developed to avoid missed diagnoses and consequently delay treatment.…”

Feasibility and acceptance of artificial intelligence-based diabetic retinopathy screening in Rwanda

“…[3] Therefore, effective task-shifting to non-ophthalmologists is a necessity. [10] Quinn et al [30] have suggested that automated technology for DR screening in low-resource settings significantly reduces demand for human graders. Using non-ophthalmologists trained in capturing retinal images, in tandem with AI-supported interpretation for referrals as this study did, will be crucial to improve access to sight-saving screening services in Africa, the global region poised for the greatest rise in the diabetes burden.…”

Focussing care

“…Data from remote and very remote areas in Australia suggest that opportunistic retinal photography with artificial intelligence (AI)‐based grading has a 91.4% sensitivity for detecting any retinopathy in an individual 7 . Very remote Australia is vastly different from predominantly urban‐deprived areas in England and Wales but the principle of opportunistic photography to capture those at highest risk is attractive and, while there may be additional cost in establishing a mobile service that attends schools, colleges, shopping centres and other areas where young people with type 1 diabetes might be identified, the cost savings of using AI to grade and the avoidance of later treatment and sight loss may make such an approach effective at a regional level.…”