Automated diabetic retinopathy detection in smartphone-based fundus photography using artificial intelligence

• Published in: Eye (London) Vol. 32; no. 6; pp. 1138 - 1144
• Main Authors: Rajalakshmi, Ramachandran, Subashini, Radhakrishnan, Anjana, Ranjit Mohan, Mohan, Viswanathan
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 01.06.2018; Nature Publishing Group
• Subjects: 692/308/409; 692/699/3161/3175; Adult; Artificial intelligence; Automation; Computer programs; Diabetes; Diabetes mellitus; Diabetes mellitus (non-insulin dependent); Diabetic retinopathy; Diabetic Retinopathy - diagnostic imaging; Diagnosis, Computer-Assisted - instrumentation; Diagnosis, Computer-Assisted - methods; Edema; Female; Humans; Laboratory Medicine; Male; Medical personnel; Medicine; Medicine & Public Health; Middle Aged; Ophthalmology; Pharmaceutical Sciences/Technology; Photography; Photography - instrumentation; Photography - methods; Predictive Value of Tests; Retina; Retina - diagnostic imaging; Retinopathy; Sensitivity and Specificity; Smartphone; Smartphones; Software; Surgery; Surgical Oncology
• ISSN: 0950-222X; 1476-5454; 1476-5454
• DOI: 10.1038/s41433-018-0064-9

Objectives To assess the role of artificial intelligence (AI)-based automated software for detection of diabetic retinopathy (DR) and sight-threatening DR (STDR) by fundus photography taken using a smartphone-based device and validate it against ophthalmologist’s grading. Methods Three hundred and one patients with type 2 diabetes underwent retinal photography with Remidio ‘Fundus on phone’ (FOP), a smartphone-based device, at a tertiary care diabetes centre in India. Grading of DR was performed by the ophthalmologists using International Clinical DR (ICDR) classification scale. STDR was defined by the presence of severe non-proliferative DR, proliferative DR or diabetic macular oedema (DME). The retinal photographs were graded using a validated AI DR screening software (EyeArt TM ) designed to identify DR, referable DR (moderate non-proliferative DR or worse and/or DME) or STDR. The sensitivity and specificity of automated grading were assessed and validated against the ophthalmologists’ grading. Results Retinal images of 296 patients were graded. DR was detected by the ophthalmologists in 191 (64.5%) and by the AI software in 203 (68.6%) patients while STDR was detected in 112 (37.8%) and 146 (49.3%) patients, respectively. The AI software showed 95.8% (95% CI 92.9–98.7) sensitivity and 80.2% (95% CI 72.6–87.8) specificity for detecting any DR and 99.1% (95% CI 95.1–99.9) sensitivity and 80.4% (95% CI 73.9–85.9) specificity in detecting STDR with a kappa agreement of k  = 0.78 ( p  < 0.001) and k  = 0.75 ( p  < 0.001), respectively. Conclusions Automated AI analysis of FOP smartphone retinal imaging has very high sensitivity for detecting DR and STDR and thus can be an initial tool for mass retinal screening in people with diabetes.