arXiv Open Access 2025

ROFI: A Deep Learning-Based Ophthalmic Sign-Preserving and Reversible Patient Face Anonymizer

Yuan Tian Min Zhou Yitong Chen Fang Li Lingzi Qi +17 lainnya
Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

Penulis (22)

Y

Yuan Tian

M

Min Zhou

Y

Yitong Chen

F

Fang Li

L

Lingzi Qi

S

Shuo Wang

X

Xieyang Xu

Y

Yu Yu

S

Shiqiong Xu

C

Chaoyu Lei

Y

Yankai Jiang

R

Rongzhao Zhang

J

Jia Tan

L

Li Wu

H

Hong Chen

X

Xiaowei Liu

W

Wei Lu

L

Lin Li

H

Huifang Zhou

X

Xuefei Song

G

Guangtao Zhai

X

Xianqun Fan

Format Sitasi

Tian, Y., Zhou, M., Chen, Y., Li, F., Qi, L., Wang, S. et al. (2025). ROFI: A Deep Learning-Based Ophthalmic Sign-Preserving and Reversible Patient Face Anonymizer. https://arxiv.org/abs/2510.11073

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓