MedDiME: Efficient Latent Diffusion with Adaptive Masking for Medical Counterfactual Generation

📅 2026-09-14
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
为解决医学反事实生成中计算慢和内存消耗大的问题,提出MedDiME框架,采用潜在空间分类器引导扩散和自适应掩码机制,提高生成效率。
📝 Abstract
Medical counterfactual generation modifies images to change model predictions for interpretability. However, existing diffusion-based approaches are often prohibitively slow and memory-intensive, making them difficult to apply in high-resolution settings. Moreover, existing masking strategies are tightly coupled with pixel-space representations, making them incompatible with latent-space diffusion editing. To address these challenges, we propose MedDiME, a latent-space classifier-guided diffusion framework that reduces computational and memory overhead while introducing a latent-compatible, gradient-driven adaptive masking mechanism for spatially precise medical counterfactual generation. Extensive experiments demonstrate that MedDiME achieves high-quality counterfactual generation with significant efficiency gains compared to prior classifier-guided diffusion baselines, achieving up to 40 times faster inference and 13 times lower peak GPU memory usage.
Problem

Research questions and friction points this paper is trying to address.

Medical Counterfactual Generation
Diffusion-based Approaches
Latent Space
Adaptive Masking
Computational Efficiency
Innovation

Methods, ideas, or system contributions that make the work stand out.

latent-space diffusion
adaptive masking
gradient-driven
medical counterfactual generation
efficiency improvement