用潜在空间投影与优化实现医疗图像匿名，保护隐私同时保留诊断价值。
Generative Medical Image Anonymization Based on Latent Code Projection and Optimization
- 先将图像压缩到潜在空间，再通过双损失函数优化
- 在MIMIC-CXR数据集上生成可训练的匿名肺部病理图像
- 适合需要隐私保护的医学AI训练场景
医疗图像匿名化旨在移除患者身份信息的同时保持数据对下游任务的可用性。本文提出两阶段方案：潜在码投影与优化。在投影阶段，设计轻量化编码器将输入图像映射至潜在空间，并提出协同训练机制提升投影效果。在优化阶段，采用两个深度损失函数，针对医学图像中隐私保护与数据效用的权衡进行潜码精修。通过大量定性与定量实验，在MIMIC-CXR胸部X光数据集上验证了方法有效性，生成的匿名合成图像可作为肺部病灶检测任务的训练集。源代码已公开于https://github.com/Huiyu-Li/GMIA。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。