Computer aided diabetic retinopathy detection based on ophthalmic photography: a systematic review and Meta-analysis

• Main Authors: Hui-Qun Wu, Yan-Xing Shan, Huan Wu, Di-Ru Zhu, Hui-Min Tao, Hua-Gen Wei, Xiao-Yan Shen, Ai-Min Sang, Jian-Cheng Dong
• Format: Article
• Language: English
• Published: Press of International Journal of Ophthalmology (IJO PRESS) 2019-12-01
• Series: International Journal of Ophthalmology
• Subjects: meta-analysis; diabetic retinopathy; computer aided detection
• Online Access: http://www.ijo.cn/en_publish/2019/12/20191214.pdf

AIM: To ensure the diagnostic value of computer aided techniques in diabetic retinopathy (DR) detection based on ophthalmic photography (OP). METHODS: PubMed, EMBASE, Ei village, IEEE Xplore and Cochrane Library database were searched systematically for literatures about computer aided detection (CAD) in DR detection. The methodological quality of included studies was appraised by the Quality Assessment Tool for Diagnostic Accuracy Studies (QUADAS-2). Meta-DiSc was utilized and a random effects model was plotted to summarize data from those included studies. Summary receiver operating characteristic curves were selected to estimate the overall test performance. Subgroup analysis was used to identify the efficiency of CAD in detecting DR, exudates (EXs), microaneurysms (MAs) as well as hemorrhages (HMs), and neovascularizations (NVs). Publication bias was analyzed using STATA. RESULTS: Fourteen articles were finally included in this Meta-analysis after literature review. Pooled sensitivity and specificity were 90% (95%CI, 85%-94%) and 90% (95%CI, 80%-96%) respectively for CAD in DR detection. With regard to CAD in EXs detecting, pooled sensitivity, specificity were 89% (95%CI, 88%-90%) and 99% (95%CI, 99%-99%) respectively. In aspect of MAs and HMs detection, pooled sensitivity and specificity of CAD were 42% (95%CI, 41%-44%) and 93% (95%CI, 93%-93%) respectively. Besides, pooled sensitivity and specificity were 94% (95%CI, 89%-97%) and 87% (95%CI, 83%-90%) respectively for CAD in NVs detection. No potential publication bias was observed. CONCLUSION: CAD demonstrates overall high diagnostic accuracy for detecting DR and pathological lesions based on OP. Further prospective clinical trials are needed to prove such effect.