Detection of Diabetic Retinopathy from Ultra-Widefield Scanning Laser Ophthalmoscope Images: A Multicenter Deep Learning Analysis
Publication in refereed journal
Officially Accepted for Publication

Times Cited
Altmetrics Information

Other information
To develop a deep learning (DL) system that can detect referable diabetic retinopathy (RDR) and vision-threatening diabetic retinopathy (VTDR) from images obtained on ultra-widefield scanning laser ophthalmoscope (UWF-SLO).
Observational, cross-sectional study.
A total of 9392 UWF-SLO images of 1903 eyes from 1022 subjects with diabetes from Hong Kong, the United Kingdom, India, and Argentina.
All images were labeled according to the presence or absence of RDR and the presence or absence of VTDR. Labeling was performed by retina specialists from fundus examination, according to the International Clinical Diabetic Retinopathy Disease Severity Scale. Three convolutional neural networks (ResNet50) were trained with a transfer-learning procedure for assessing gradability and identifying VTDR and RDR. External validation was performed on 4 datasets spanning different geographical regions.
Main Outcome Measures:
Area under the receiver operating characteristic curve (AUROC); area under the precision-recall curve (AUPRC); sensitivity, specificity, and accuracy of the DL system in gradability assessment; and detection of RDR and VTDR.
For gradability assessment, the system achieved an AUROC of 0.923 (95% confidence interval [CI], 0.892–0.947), sensitivity of 86.5% (95% CI, 77.6–92.8), and specificity of 82.1% (95% CI, 77.3–86.2) for the primary validation dataset, and >0.82 AUROCs, >79.6% sensitivity, and >70.4% specificity for the geographical external validation datasets. For detecting RDR and VTDR, the AUROCs were 0.981 (95% CI, 0.977–0.984) and 0.966 (95% CI, 0.961–0.971), with sensitivities of 94.9% (95% CI, 92.3–97.9) and 87.2% (95% CI, 81.5–91.6), specificities of 95.1% (95% CI, 90.6–97.9) and 95.8% (95% CI, 93.3–97.6), and positive predictive values (PPVs) of 98.0% (95% CI, 96.1–99.0) and 91.1% (95% CI, 86.3–94.3) for the primary validation dataset, respectively. The AUROCs and accuracies for detecting both RDR and VTDR were >0.9% and >80%, respectively, for the geographical external validation datasets. The AUPRCs were >0.9, and sensitivities, specificities, and PPVs were >80% for the geographical external validation datasets for RDR and VTDR detection.
The excellent performance achieved with this DL system for image quality assessment and detection of RDR and VTDR in UWF-SLO images highlights its potential as an efficient and effective diabetic retinopathy screening tool.
Acceptance Date26/01/2021
All Author(s) ListFangyao Tang, Phoomraphee Luenam, An Ran Ran, Ahmed Abdul Quadeer, Rajiv Raman, Piyali Sen, Rehana Khan, Anantharaman Giridhar, Swathy Haridas, Matias Iglicki, Dinah Zur, Anat Loewenstein, Hermino P. Negri, Simon Szeto, Bryce Ka Yau Lam, Clement C. Tham, Sobha Sivaprasad, Matthew Mckay, Carol Y. Cheung
Journal nameOphthalmology Retina
PublisherElsevier Inc.
LanguagesEnglish-United Kingdom
KeywordsArtificial intelligence, Deep learning, Diabetic retinopathy, Imaging, Ultra-widefield scanning laser ophthalmoscopy

Last updated on 2021-16-10 at 23:56