ROFI: A Deep Learning-Based Ophthalmic Sign-Preserving and Reversible Patient Face Anonymizer
Not on the map. Why?
Abstract (arXiv)
Patient face images provide a convenient mean for evaluating eye diseases, while also raising privacy concerns. Here, we introduce ROFI, a deep learning-based privacy protection framework for ophthalmology. Using weakly supervised learning and neural identity translation, ROFI anonymizes facial features while retaining disease features (over 98% accuracy, kappa > 0.90). It achieves 100% diagnostic sensitivity and high agreement (kappa > 0.90) across eleven eye diseases in three cohorts, anonymizing over 95% of images. ROFI works with AI systems, maintaining original diagnoses (kappa > 0.80), and supports secure image reversal (over 98% similarity), enabling audits and long-term care. These results show ROFI's effectiveness of protecting patient privacy in the digital medicine era.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 51 of its 158 references that are in the map. First posted on arXiv 13 Oct 2025.
Builds on
51 of 158 references.
References · 51
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
- 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
- 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
- 2016Adversarial examples in the physical worldcited by 1,762
- 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
- 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
38 more
- 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
- 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
- 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 738
- 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
- 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 640
- 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 475
- 2021SimSwap: An Efficient Framework For High Fidelity Face Swappingcited by 243
- 2021Adversary Instantiation: Lower Bounds for Differentially Private Machine Learningcited by 193
- 2023On the Challenges and Perspectives of Foundation Models for Medical Image Analysiscited by 135
- 2016Fast Face-swap Using Convolutional Neural Networkscited by 119
- 2021One Shot Face Swapping on Megapixelscited by 105
- 2021GAN-Control: Explicitly Controllable GANscited by 91
- 2018Data Augmentation using Random Image Cropping and Patching for Deep CNNscited by 87
- 2019Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory & Practicecited by 71
- 2019AnonymousNet: Natural Face De-Identification with Measurable Privacycited by 50
- 2022Region-Aware Face Swappingcited by 45
- 2018On Low-Resolution Face Recognition in the Wild: Comparisons and New Techniquescited by 34
- 2020FACEGAN: Facial Attribute Controllable rEenactment GANcited by 32
- 2024GAIA: Rethinking Action Quality Assessment for AI-Generated Videoscited by 30
- 2019Password-conditioned Anonymization and Deanonymization with Face Identity Transformerscited by 24
- 2021DP-Image: Differential Privacy for Image Data in Feature Spacecited by 23
- 2023RiDDLE: Reversible and Diversified De-identification with Latent Encryptorcited by 21
- 2024G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priorscited by 20
- 2021Self-Conditioned Probabilistic Learning of Video Rescalingcited by 19
- 2022A Coding Framework and Benchmark towards Low-Bitrate Video Understandingcited by 17
- 2016Trunk-Branch Ensemble Convolutional Neural Networks for Video-based Face Recognitioncited by 16
- 2019Dataset Growth in Medical Image Analysis Researchcited by 16
- 2021EAN: Event Adaptive Network for Enhanced Action Recognitioncited by 16
- 2017Interspecies Knowledge Transfer for Facial Keypoint Detectioncited by 13
- 2025Image Quality Assessment: From Human to Machine Preferencecited by 12
- 2024Free-VSC: Free Semantics from Visual Foundation Models for Unsupervised Video Semantic Compressioncited by 9
- 2023Disguise without Disruption: Utility-Preserving Face De-Identificationcited by 8
- 2025Information Density Principle for MLLM Benchmarkscited by 8
- 2025Towards All-in-One Medical Image Re-Identificationcited by 6
- 2025Can Large Models Fool the Eye? A New Turing Test for Biological Animationcited by 6
- 2025MedOmni-45deg: A Safety-Performance Benchmark for Reasoning-Oriented LLMs in Medicinecited by 6
- 2024Medical Manifestation-Aware De-Identificationcited by 4
- 2019Artificial Intelligence for Pediatric Ophthalmologycited by 3
50 most cited of 51 All 51 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.
- 2026A3: Towards Advertising Aesthetic Assessmentcited by 0
- 2026A3: Towards Advertising Aesthetic Assessment25 Mar 2026