ROFI: a deep learning-based ophthalmic sign-preserving and reversible patient face anonymizer

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, κ > 0.90). It achieves 100% diagnostic sensitivity and high agreement (κ > 0.90) across eleven eye diseases in three cohorts, anonymizing over 95% of images. ROFI works with AI systems, maintaining original diagnoses (κ > 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.

Authors

Institutions

Publication Details

Journal
npj Digital Medicine
Published
2025-11-20
DOI
https://doi.org/10.1038/s41746-025-02062-7
Citations
2
Primary Topic
Retinal Imaging and Analysis
Type
article
Field-Weighted Citation Impact
2.72
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

ROFI: a deep learning-based ophthalmic sign-preserving and reversible patient face anonymizer

Rongzhao Zhang, Huifang Zhou, Wei Lü, Yuan Tian et al.
2 citations
npj Digital Medicine
Retinal Imaging and Analysis
2.72
article

ROFI: a deep learning-based ophthalmic sign-preserving and reversible patient face anonymizer

Rongzhao Zhang, Huifang Zhou, Wei Lü, Yuan Tian, Yankai Jiang, Yitong Chen, Chaoyu Lei, Xiaojun Xu, Xuefei Song, Jia Tan, Xianqun Fan, Wu Li, Xiaowei Liu, Yu Yu, Hong Chen, Min Zhou, Fang Li, Shuo Wang, Lin Li, Lingzi Qi
article en
2 citations

Abstract

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, κ > 0.90). It achieves 100% diagnostic sensitivity and high agreement (κ > 0.90) across eleven eye diseases in three cohorts, anonymizing over 95% of images. ROFI works with AI systems, maintaining original diagnoses (κ > 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.

npj Digital MedicineVol. 8(1)
Central South University (CN), Shanghai Jiao Tong University (CN), Dalian Medical University (CN), Chinese Academy of Medical Sciences & Peking Union Medical College (CN), Peking Union Medical College Hospital (CN), Wuhan University (CN), Shanghai Ninth People's Hospital (CN), Beijing Academy of Artificial Intelligence (CN), Second Affiliated Hospital of Dalian Medical University (CN), Wuhan Union Hospital (CN), Renmin Hospital of Wuhan University (CN), Huazhong University of Science and Technology Hospital (CN), Xiangya Hospital Central South University (CN), Union Hospital (CN), Shanghai Artificial Intelligence Laboratory (CN)
Openalex Percentile: Top 8%
Retinal Imaging and Analysis
2.72
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.