Problem
Research questions and friction points this paper is trying to address.
PHI
multimodal systems
medical image-text data
de-identification
Masking Is Not Enough: Generative Restoration for Multimodal De-Identification in Medical AI
🤖 AI Summary
本文针对医疗图像文本数据中的隐私保护问题，提出ClinX框架，通过OCR检测、生成式恢复等方法实现多模态去标识化。
📝 Abstract
Medical image-text data can expose protected health information (PHI) through both visible image content as well as accompanying text, creating a barrier to privacy-preserving medical AI systems. This risk is especially prominent in multimodal systems, where images, questions, reports, and clinical context may enter training, evaluation, or inference pipelines. Existing medical vision-language benchmarks primarily emphasize task utility, while de-identification methods are often evaluated separately from downstream reasoning. We introduce ClinX, an end-to-end multimodal PHI sanitization framework for medical image-text data. ClinX detects visible identifiers with optical character recognition (OCR), constructs binary PHI masks, and applies ClinX-PRISM, a no-skip generative restoration module with privacy-oriented post-processing for burned-in identifier suppression. In parallel, text-side PHI is reduced through progressive de-identification levels: regex masking, context-aware masking, and rewrite-based sanitization. We evaluate ClinX in medical visual question answering (MedVQA), jointly measuring PHI leakage and downstream utility across image-side, text-side, and combined de-identification settings. Results show that OCR-only masking is not sufficient as a standalone solution, and restoration-based sanitization better preserves clinically relevant visual context while sharply reducing recoverable PHI.
Innovation
Methods, ideas, or system contributions that make the work stand out.
end-to-end multimodal PHI sanitization
no-skip generative restoration
privacy-oriented post-processing
context-aware masking
rewrite-based sanitization
🔎 Similar Papers
No similar papers found.
