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

arXiv:2609.15647v1 Announce Type: new 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.

Related

• One Sequence to Segment Them All: Efficient Data Augmentation for CT and MRI Cross-Domain 3D Spine Segmentation
• Tuning-Free Latent Diffusion Models for Ultrahigh-Resolution Image Editing
• RoLA: Rotary-Positioned Low-Rank Linear Attention for Efficient Diffusion Transformers

Source: arXiv cs.CV | 2026-09-15