| Popis: |
Li Xie,1 Ehsan Vaghefi,1,2 Song Yang,1 David Han,1,2 John Marshall,3 David Squirrell1,4 1Toku Eyes Limited, Auckland, New Zealand; 2School of Optometry and Vision Science, The University of Auckland, Auckland, New Zealand; 3Institute of Ophthalmology, UCL, London, UK; 4Department of Ophthalmology, Auckland District Health Board, Auckland, New ZealandCorrespondence: Ehsan Vaghefi, Tel +6493737599, Email e.vaghefi@auckland.ac.nzPurpose: To create an ensemble of Convolutional Neural Networks (CNNs), capable of detecting and stratifying the risk of progressive age-related macular degeneration (AMD) from retinal photographs.Design: Retrospective cohort study.Methods: Three individual CNNs are trained to accurately detect 1) advanced AMD, 2) drusen size and 3) the presence or otherwise of pigmentary abnormalities, from macular centered retinal images were developed. The CNNs were then arranged in a âcascadingâ architecture to calculate the Age-related Eye Disease Study (AREDS) Simplified 5-level risk Severity score (Risk Score 0 â Risk Score 4), for test images. The process was repeated creating a simplified binary âlow riskâ (Scores 0â 2) and âhigh riskâ (Risk Score 3â 4) classification.Participants: There were a total of 188,006 images, of which 118,254 images were deemed gradable, representing 4591 patients, from the AREDS1 dataset. The gradable images were split into 50%/25%/25% ratios for training, validation and test purposes.Main Outcome Measures: The ability of the ensemble of CNNs using retinal images to predict an individualâs risk of experiencing progression of their AMD based on the AREDS 5-step Simplified Severity Scale.Results: When assessed against the 5-step Simplified Severity Scale, the results generated by the ensemble of CNNâs achieved an accuracy of 80.43% (quadratic kappa 0.870). When assessed against a simplified binary (Low Risk/High Risk) classification, an accuracy of 98.08%, sensitivity of ⥠85% and specificity of ⥠99% was achieved.Conclusion: We have created an ensemble of neural networks, trained on the AREDS 1 dataset, that is able to accurately calculate an individualâs score on the AREDS 5-step Simplified Severity Scale for AMD. If the results presented were replicated, then this ensemble of CNNs could be used as a screening tool that has the potential to significantly improve health outcomes by identifying asymptomatic individuals who would benefit from AREDS2 macular supplements.Keywords: AREDS, Simplified Severity Scale, AMD, neural networks |
