Generative Medical Image Anonymization Based on Latent Code Projection and Optimization
This work addresses privacy protection in medical imaging for healthcare applications, presenting an incremental improvement over existing methods.
The paper tackles medical image anonymization by proposing a two-stage method involving latent code projection and optimization, achieving effective anonymization on the MIMIC-CXR dataset for training lung pathology detection models.
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.