arXiv 2604.071282026-04-08cs.CV

一种保持效用的跨医院放射学数据共享脱敏流程

A Utility-preserving De-identification Pipeline for Cross-hospital Radiology Data Sharing

Shandong University（山东大学）；Australian National University（澳大利亚国立大学）；Hong Kong University of Science and Technology（香港科技大学）；Curtin University（科廷大学）；Edith Cowan University（埃迪斯科文大学）；University of Western Australia（西澳大利亚大学）

Chenhao Liu, Zelin Wen, Yan Tong, Junjie Zhu, Xinyu Tian, Yuchi Liu, Ashu Gupta, Syed M. S. Islam, Tom Gedeon, Yue Yao

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出一种保持效用的脱敏流程，用于跨医院放射学数据共享，通过黑名单和白名单过滤机制，在保护隐私的同时保留诊断相关病理信息，实验证明其在诊断准确性上的竞争力。

摘要：

大规模放射学数据对于开发稳健的医疗AI系统至关重要。然而，跨医院共享此类数据受到隐私问题的严重限制。现有放射学脱敏研究主要集中在去除可识别信息以实现合规的数据发布。然而，脱敏放射学数据是否仍能保持足够的效用用于大规模视觉-语言模型训练和跨医院转移仍鲜有研究。本文介绍了一种保持效用的脱敏流程（UPDP）用于跨医院放射学数据共享。具体而言，我们编制了隐私敏感术语的黑名单和病理相关术语的白名单。对于放射学图像，我们使用生成过滤机制，合成隐私过滤且病理保留的原始图像对应物。这些合成图像对应物，加上ID过滤的报告，可以安全地在医院之间共享，用于下游模型开发和评估。在公开的胸部X光基准测试中，我们的方法有效去除了隐私敏感信息，同时保留了诊断相关的病理线索。训练在脱敏数据上的模型在诊断准确性上与训练在原始数据上的模型具有竞争力，同时在身份相关准确性上显示出显著下降，证实了有效的隐私保护。在跨医院设置中，我们进一步证明脱敏数据可以与本地数据结合，以获得更好的性能。

英文摘要：

Large-scale radiology data are critical for developing robust medical AI systems. However, sharing such data across hospitals remains heavily constrained by privacy concerns. Existing de-identification research in radiology mainly focus on removing identifiable information to enable compliant data release. Yet whether de-identified radiology data can still preserve sufficient utility for large-scale vision-language model training and cross-hospital transfer remains underexplored. In this paper, we introduce a utility-preserving de-identification pipeline (UPDP) for cross-hospital radiology data sharing. Specifically, we compile a blacklist of privacy-sensitive terms and a whitelist of pathology-related terms. For radiology images, we use a generative filtering mechanism that synthesis a privacy-filtered and pathology-reserved counterparts of the original images. These synthetic image counterparts, together with ID-filtered reports, can then be securely shared across hospitals for downstream model development and evaluation. Experiments on public chest X-ray benchmarks demonstrate that our method effectively removes privacy-sensitive information while preserving diagnostically relevant pathology cues. Models trained on the de-identified data maintain competitive diagnostic accuracy compared with those trained on the original data, while exhibiting a marked decline in identity-related accuracy, confirming effective privacy protection. In the cross-hospital setting, we further show that de-identified data can be combined with local data to yield better performance.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。