用几何过滤生成隐私保护的肺部CT切片，兼顾真实感与隐私安全。
DS@GT ARC at ImageCLEFmed GANs 2026: Geometric Filtering for Privacy-Preserving CT Slice Generation
- 结合最优传输流匹配与几何空间过滤，提升生成隐私性。
- 最佳模型隐私得分0.549，FID达0.3290，真实感强。
- 适合医疗图像生成与隐私保护研究者参考。
我们为Image-CLEFmed GANs 2026挑战赛提出了一种隐私保护的合成肺部CT切片生成框架。该方法融合最优传输条件流匹配与面向隐私的训练，并引入后处理“监督器”管道，在学习到的几何潜在空间中，利用自编码器嵌入、行列式点过程和斯坦核稀疏化对生成样本进行筛选。官方结果表明，该模型在真实感与隐私保护之间取得良好平衡：最佳模型隐私保留得分为0.549，视觉保真度优异，FID为0.3290。尽管几何过滤显著降低了最近邻记忆化和成员推断泄漏，但患者重识别分数仍存在，说明仅防图像复制不足以消除深层解剖身份特征，揭示了未来医学图像生成隐私保护的重要方向。
原文摘要 · Abstract (English)
We present a privacy-preserving framework for synthetic lung CT slice generation developed for the Image-CLEFmed GANs 2026 challenge. The approach combines Optimal Transport Conditional Flow Matching with privacy-oriented training and a post-generation "Supervisor" pipeline that filters generated candidates in learned geometric latent spaces using autoencoder embeddings, Determinantal Point Processes, and Stein Kernel Thinning. Official results show a strong realism-privacy trade-off, with the best-performing model achieving a Privacy Preservation Score of 0.549 and competitive visual fidelity with an FID of 0.3290. While the proposed geometric filtering substantially reduces nearest-neighbor memorization and membership-inference leakage, persistent patient re-identification scores indicate that preventing direct image copying is not sufficient to remove deeper patient-specific anatomical identity, highlighting an important frontier for future privacy-preserving medical image generation.
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。