Generative Medical Image Anonymization Based on Latent Code Projection and Optimization

TL;DR

This paper introduces a two-stage method for medical image anonymization that projects images into a latent space and refines them to protect patient identity while maintaining diagnostic utility, demonstrated on chest X-ray data.

Contribution

The paper proposes a novel two-stage approach combining latent code projection and optimization for effective medical image anonymization.

Findings

Effective anonymization demonstrated on MIMIC-CXR dataset

Generated images preserve diagnostic utility for lung pathology detection

Method outperforms existing anonymization techniques

Abstract

Medical image anonymization aims to protect patient privacy by removing identifying information, while preserving the data utility to solve downstream tasks. In this paper, we address the medical image anonymization problem with a two-stage solution: latent code projection and optimization. In the projection stage, we design a streamlined encoder to project input images into a latent space and propose a co-training scheme to enhance the projection process. In the optimization stage, we refine the latent code using two deep loss functions designed to address the trade-off between identity protection and data utility dedicated to medical images. Through a comprehensive set of qualitative and quantitative experiments, we showcase the effectiveness of our approach on the MIMIC-CXR chest X-ray dataset by generating anonymized synthetic images that can serve as training set for detecting lung pathologies. Source codes are available at https://github.com/Huiyu-Li/GMIA.