Semantics versus Identity: A Divide-and-Conquer Approach towards Adjustable Medical Image De-Identification

TL;DR

This paper introduces a flexible, two-step de-identification framework for medical images that balances privacy and medical utility by blocking identity features and compensating with semantic features from foundation models.

Contribution

It proposes a novel divide-and-conquer approach combining identity blocking and semantic compensation, with a feature decoupling strategy to enhance privacy without sacrificing medical information.

Findings

Achieves state-of-the-art privacy preservation across multiple datasets.

Effectively balances privacy and medical utility in de-identified images.

Demonstrates robustness across various downstream tasks.

Abstract

Medical imaging has significantly advanced computer-aided diagnosis, yet its re-identification (ReID) risks raise critical privacy concerns, calling for de-identification (DeID) techniques. Unfortunately, existing DeID methods neither particularly preserve medical semantics, nor are flexibly adjustable towards different privacy levels. To address these issues, we propose a divide-and-conquer framework comprising two steps: (1) Identity-Blocking, which blocks varying proportions of identity-related regions, to achieve different privacy levels; and (2) Medical-Semantics-Compensation, which leverages pre-trained Medical Foundation Models (MFMs) to extract medical semantic features to compensate the blocked regions. Moreover, recognizing that features from MFMs may still contain residual identity information, we introduce a Minimum Description Length principle-based feature decoupling strategy, to effectively decouple and discard such identity components. Extensive evaluations against existing approaches across seven datasets and three downstream tasks, demonstrates our state-of-the-art performance.