Ophthalmology Science · 2023 · 42 citations · 22 references
Health ProfessionsOphthalmologyVision ScienceComputer VisionDiagnostic ImagingOcular ImagingDiabetic RetinopathyFluorescein AngiographyFundus PhotographyMacular AnatomyRetinal Image QualityRetinal ImagingAutomated Image GenerationColor Fundus PhotographyDiabetic Retinopathy AssessmentDiabetic Retinopathy DetectionFundus Fluorescein AngiographyRetinal Fundus PhotographySimilarity MeasuresSubjective Image Quality Assessment
Purpose: To develop and validate a deep learning model that can transform color fundus (CF) photography into corresponding venous and late-phase fundus fluorescein angiography (FFA) images. Design: Cross-sectional study. Participants: We included 51 370 CF-venous FFA pairs and 14 644 CF-late FFA pairs from 4438 patients for model development. External testing involved 50 eyes with CF-FFA pairs and 2 public datasets for diabetic retinopathy (DR) classification, with 86 952 CF from EyePACs, and 1744 CF from MESSIDOR2. Methods: We trained a deep-learning model to transform CF into corresponding venous and late-phase FFA images. The translated FFA images' quality was evaluated quantitatively on the internal test set and subjectively on 100 eyes with CF-FFA paired images (50 from external), based on the realisticity of the global image, anatomical landmarks (macula, optic disc, and vessels), and lesions. Moreover, we validated the clinical utility of the translated FFA for classifying 5-class DR and diabetic macular edema (DME) in the EyePACs and MESSIDOR2 datasets. Main Outcome Measures: Image generation was quantitatively assessed by structural similarity measures (SSIM), and subjectively by 2 clinical experts on a 5-point scale (1 refers real FFA); intragrader agreement was assessed by kappa. The DR classification accuracy was assessed by area under the receiver operating characteristic curve. Results: The SSIM of the translated FFA images were > 0.6, and the subjective quality scores ranged from 1.37 to 2.60. Both experts reported similar quality scores with substantial agreement (all kappas > 0.8). Adding the generated FFA on top of CF improved DR classification in the EyePACs and MESSIDOR2 datasets, with the area under the receiver operating characteristic curve increased from 0.912 to 0.939 on the EyePACs dataset and from 0.952 to 0.972 on the MESSIDOR2 dataset. The DME area under the receiver operating characteristic curve also increased from 0.927 to 0.974 in the MESSIDOR2 dataset. Conclusions: Our CF-to-FFA framework produced realistic FFA images. Moreover, adding the translated FFA images on top of CF improved the accuracy of DR screening. These results suggest that CF-to-FFA translation could be used as a surrogate method when FFA examination is not feasible and as a simple add-on to improve DR screening. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
22
The Measurement of Observer Agreement for Categorical Data
J. Richard Landis, Gary G. Koch · Biometrics · 1977 · 78.9K citations · Full text
Image quality assessment: from error visibility to structural similarity
Zhou Wang, Alan C. Bovik, Hamid R. Sheikh et al. · IEEE Transactions on Image Processing · 2004 · 56K citations
Martin A. Fischler, Robert C. Bolles · Communications of the ACM · 1981 · 25.5K citations · Full text
Generative Adversarial Networks: An Overview
Antonia Creswell, Tom White, Vincent Dumoulin et al. · IEEE Signal Processing Magazine · 2018 · 4.4K citations · Full text
Global Prevalence of Diabetic Retinopathy and Projection of Burden through 2045
Zhen Ling Teo, Yih Chung Tham, Marco Yu et al. · Ophthalmology · 2021 · 2.2K citations