DS@GT ARC at ImageCLEFmed GANs 2026: Geometric Filtering for Privacy-Preserving CT Slice Generation

Researchers from the Data Science and Analytics Group at Georgia Tech (DS@GT ARC) developed a privacy-preserving framework for synthetic lung CT slice generation for the ImageCLEFmed GANs 2026 challenge, achieving a Privacy Preservation Score of 0.549 and an FID of 0.3290. The framework combines Optimal Transport Conditional Flow Matching with a geometric filtering pipeline, but persistent patient re-identification scores show that preventing direct image copying does not eliminate deeper anatomical identity, highlighting a frontier for future work.

arXiv:2607.20692v1 Announce Type: new Abstract: 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.