ArticleOphthalmology science2021
Deepfakes in Ophthalmology: Applications and Realism of Synthetic Retinal Images from Generative Adversarial Networks.
Article in Ophthalmology science, 2021. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 29 papers, 1 of them a synthesis that pooled it.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
29 citing papers in PubMed, 1 synthesis or guideline pooled it, 50 citations in OpenAlex.
- Ophthalmic Image Synthesis and Analysis with Generative Adversarial Network Artificial Intelligence.Journal of imaging informatics in medicine · 2026Pooled it
- Characterization of vascular tortuosity throughout the murine oxygen-induced retinopathy model of ischemic retinopathy.JCI insight · 2026Article
- FunduSegmenter: Leveraging the RETFound Foundation Model for Joint Optic Disc and Optic Cup Segmentation in Retinal Fundus Images.Translational vision science & technology · 2026Article
- Applications of Generative Artificial Intelligence for Strabismus Surgery Video-Based Education.Ophthalmology science · 2026Article
- AI-Based RGB Image Generation From RG Fundus Images Using Pix2Pix: Validation by Quantitative and Observer-Based Evaluations.Translational vision science & technology · 2026Article
- Augmenting a prognostic deep learning system for referable diabetic retinopathy and maculopathy with synthetic retinal images.Communications medicine · 2025Article
- AI deepfake: GPT-4o can produce near-authentic fundus images.Eye (London, England) · 2025Article
- Possible Health Benefits and Risks of DeepFake Videos: A Qualitative Study in Nursing Students.Nursing reports (Pavia, Italy) · 2024Article
- Novel artificial intelligence algorithms for diabetic retinopathy and diabetic macular edema.Eye and vision (London, England) · 2024Review
- A survey of recent methods for addressing AI fairness and bias in biomedicine.Journal of biomedical informatics · 2024Review
- Optical coherence tomography choroidal enhancement using generative deep learning.NPJ digital medicine · 2024Article
- Recognition of Genetic Conditions After Learning With Images Created Using Generative Artificial Intelligence.JAMA network open · 2024Article
- Article
- Translating color fundus photography to indocyanine green angiography using deep-learning for age-related macular degeneration screening.NPJ digital medicine · 2024Article
- Genome-wide association identifies novel ROP risk loci in a multiethnic cohort.Communications biology · 2024Article
- Bridging the Camera Domain Gap With Image-to-Image Translation Improves Glaucoma Diagnosis.Translational vision science & technology · 2023Article
- Translation of Color Fundus Photography into Fluorescein Angiography Using Deep Learning for Enhanced Diabetic Retinopathy Screening.Ophthalmology science · 2023Article
- Artificial CT images can enhance variation of case images in diagnostic radiology skills training.Insights into imaging · 2023Article
- Unobtrusive biometric data de-identification of fundus images using latent space disentanglement.Biomedical optics express · 2023Article
- Generative Methods for Pediatric Genetics Education.medRxiv : the preprint server for health sciences · 2023Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
9 authors at 6 institutions in 1 country.
Funding
Abstract
Purpose: Generative adversarial networks (GANs) are deep learning (DL) models that can create and modify realistic-appearing synthetic images, or deepfakes, from real images. The purpose of our study was to evaluate the ability of experts to discern synthesized retinal fundus images from real fundus images and to review the current uses and limitations of GANs in ophthalmology. Design: Development and expert evaluation of a GAN and an informal review of the literature. Participants: A total of 4282 image pairs of fundus images and retinal vessel maps acquired from a multicenter ROP screening program. Methods: Pix2Pix HD, a high-resolution GAN, was first trained and validated on fundus and vessel map image pairs and subsequently used to generate 880 images from a held-out test set. Fifty synthetic images from this test set and 50 different real images were presented to 4 expert ROP ophthalmologists using a custom online system for evaluation of whether the images were real or synthetic. Literature was reviewed on PubMed and Google Scholars using combinations of the terms Main Outcome Measures: Expert ability to discern real versus synthetic images was evaluated using percent accuracy. Statistical significance was evaluated using a Fisher exact test, with Results: The expert majority correctly identified 59% of images as being real or synthetic ( Conclusions: Generative adversarial networks can create synthetic fundus images that are indiscernible from real fundus images by expert ROP ophthalmologists. Synthetic images may improve dataset augmentation for DL, may be used in trainee education, and may have implications for patient privacy.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.